From 5d1646d90e1f2cceb9f0828f4b28318cd0ec7744 Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Sat, 27 Apr 2024 12:05:51 +0200 Subject: Adding upstream version 5.10.209. Signed-off-by: Daniel Baumann --- mm/Kconfig | 862 +++++ mm/Kconfig.debug | 172 + mm/Makefile | 122 + mm/backing-dev.c | 1031 +++++ mm/balloon_compaction.c | 260 ++ mm/cleancache.c | 315 ++ mm/cma.c | 543 +++ mm/cma.h | 29 + mm/cma_debug.c | 200 + mm/compaction.c | 2926 ++++++++++++++ mm/debug.c | 324 ++ mm/debug_page_ref.c | 55 + mm/debug_vm_pgtable.c | 1147 ++++++ mm/dmapool.c | 529 +++ mm/early_ioremap.c | 303 ++ mm/fadvise.c | 219 ++ mm/failslab.c | 62 + mm/filemap.c | 3536 +++++++++++++++++ mm/frame_vector.c | 223 ++ mm/frontswap.c | 497 +++ mm/gup.c | 3040 +++++++++++++++ mm/gup_benchmark.c | 210 ++ mm/highmem.c | 484 +++ mm/hmm.c | 599 +++ mm/huge_memory.c | 3015 +++++++++++++++ mm/hugetlb.c | 5788 ++++++++++++++++++++++++++++ mm/hugetlb_cgroup.c | 812 ++++ mm/hwpoison-inject.c | 110 + mm/init-mm.c | 42 + mm/internal.h | 646 ++++ mm/interval_tree.c | 111 + mm/ioremap.c | 289 ++ mm/kasan/Makefile | 34 + mm/kasan/common.c | 931 +++++ mm/kasan/generic.c | 369 ++ mm/kasan/generic_report.c | 165 + mm/kasan/init.c | 497 +++ mm/kasan/kasan.h | 299 ++ mm/kasan/quarantine.c | 376 ++ mm/kasan/report.c | 599 +++ mm/kasan/tags.c | 200 + mm/kasan/tags_report.c | 93 + mm/khugepaged.c | 2400 ++++++++++++ mm/kmemleak.c | 1995 ++++++++++ mm/ksm.c | 3205 ++++++++++++++++ mm/list_lru.c | 649 ++++ mm/maccess.c | 321 ++ mm/madvise.c | 1247 ++++++ mm/mapping_dirty_helpers.c | 349 ++ mm/memblock.c | 2031 ++++++++++ mm/memcontrol.c | 7535 +++++++++++++++++++++++++++++++++++++ mm/memfd.c | 346 ++ mm/memory-failure.c | 1936 ++++++++++ mm/memory.c | 5343 ++++++++++++++++++++++++++ mm/memory_hotplug.c | 1906 ++++++++++ mm/mempolicy.c | 3050 +++++++++++++++ mm/mempool.c | 555 +++ mm/memremap.c | 532 +++ mm/memtest.c | 113 + mm/migrate.c | 3122 +++++++++++++++ mm/mincore.c | 280 ++ mm/mlock.c | 878 +++++ mm/mm_init.c | 207 + mm/mmap.c | 3854 +++++++++++++++++++ mm/mmu_gather.c | 332 ++ mm/mmu_notifier.c | 1139 ++++++ mm/mmzone.c | 101 + mm/mprotect.c | 700 ++++ mm/mremap.c | 815 ++++ mm/msync.c | 110 + mm/nommu.c | 1853 +++++++++ mm/oom_kill.c | 1165 ++++++ mm/page-writeback.c | 2850 ++++++++++++++ mm/page_alloc.c | 8997 ++++++++++++++++++++++++++++++++++++++++++++ mm/page_counter.c | 262 ++ mm/page_ext.c | 412 ++ mm/page_idle.c | 235 ++ mm/page_io.c | 417 ++ mm/page_isolation.c | 313 ++ mm/page_owner.c | 654 ++++ mm/page_poison.c | 144 + mm/page_reporting.c | 364 ++ mm/page_reporting.h | 54 + mm/page_vma_mapped.c | 318 ++ mm/pagewalk.c | 563 +++ mm/percpu-internal.h | 285 ++ mm/percpu-km.c | 120 + mm/percpu-stats.c | 249 ++ mm/percpu-vm.c | 379 ++ mm/percpu.c | 3181 ++++++++++++++++ mm/pgalloc-track.h | 51 + mm/pgtable-generic.c | 222 ++ mm/process_vm_access.c | 305 ++ mm/ptdump.c | 154 + mm/readahead.c | 641 ++++ mm/rmap.c | 2019 ++++++++++ mm/rodata_test.c | 54 + mm/shmem.c | 4350 +++++++++++++++++++++ mm/shuffle.c | 183 + mm/shuffle.h | 53 + mm/slab.c | 4201 +++++++++++++++++++++ mm/slab.h | 638 ++++ mm/slab_common.c | 1197 ++++++ mm/slob.c | 720 ++++ mm/slub.c | 5771 ++++++++++++++++++++++++++++ mm/sparse-vmemmap.c | 265 ++ mm/sparse.c | 974 +++++ mm/swap.c | 1215 ++++++ mm/swap_cgroup.c | 227 ++ mm/swap_slots.c | 354 ++ mm/swap_state.c | 953 +++++ mm/swapfile.c | 3862 +++++++++++++++++++ mm/truncate.c | 950 +++++ mm/usercopy.c | 312 ++ mm/userfaultfd.c | 694 ++++ mm/util.c | 1025 +++++ mm/vmacache.c | 117 + mm/vmalloc.c | 3589 ++++++++++++++++++ mm/vmpressure.c | 469 +++ mm/vmscan.c | 4322 +++++++++++++++++++++ mm/vmstat.c | 2182 +++++++++++ mm/workingset.c | 629 ++++ mm/z3fold.c | 1832 +++++++++ mm/zbud.c | 636 ++++ mm/zpool.c | 398 ++ mm/zsmalloc.c | 2581 +++++++++++++ mm/zswap.c | 1379 +++++++ 127 files changed, 149454 insertions(+) create mode 100644 mm/Kconfig create mode 100644 mm/Kconfig.debug create mode 100644 mm/Makefile create mode 100644 mm/backing-dev.c create mode 100644 mm/balloon_compaction.c create mode 100644 mm/cleancache.c create mode 100644 mm/cma.c create mode 100644 mm/cma.h create mode 100644 mm/cma_debug.c create mode 100644 mm/compaction.c create mode 100644 mm/debug.c create mode 100644 mm/debug_page_ref.c create mode 100644 mm/debug_vm_pgtable.c create mode 100644 mm/dmapool.c create mode 100644 mm/early_ioremap.c create mode 100644 mm/fadvise.c create mode 100644 mm/failslab.c create mode 100644 mm/filemap.c create mode 100644 mm/frame_vector.c create mode 100644 mm/frontswap.c create mode 100644 mm/gup.c create mode 100644 mm/gup_benchmark.c create mode 100644 mm/highmem.c create mode 100644 mm/hmm.c create mode 100644 mm/huge_memory.c create mode 100644 mm/hugetlb.c create mode 100644 mm/hugetlb_cgroup.c create mode 100644 mm/hwpoison-inject.c create mode 100644 mm/init-mm.c create mode 100644 mm/internal.h create mode 100644 mm/interval_tree.c create mode 100644 mm/ioremap.c create mode 100644 mm/kasan/Makefile create mode 100644 mm/kasan/common.c create mode 100644 mm/kasan/generic.c create mode 100644 mm/kasan/generic_report.c create mode 100644 mm/kasan/init.c create mode 100644 mm/kasan/kasan.h create mode 100644 mm/kasan/quarantine.c create mode 100644 mm/kasan/report.c create mode 100644 mm/kasan/tags.c create mode 100644 mm/kasan/tags_report.c create mode 100644 mm/khugepaged.c create mode 100644 mm/kmemleak.c create mode 100644 mm/ksm.c create mode 100644 mm/list_lru.c create mode 100644 mm/maccess.c create mode 100644 mm/madvise.c create mode 100644 mm/mapping_dirty_helpers.c create mode 100644 mm/memblock.c create mode 100644 mm/memcontrol.c create mode 100644 mm/memfd.c create mode 100644 mm/memory-failure.c create mode 100644 mm/memory.c create mode 100644 mm/memory_hotplug.c create mode 100644 mm/mempolicy.c create mode 100644 mm/mempool.c create mode 100644 mm/memremap.c create mode 100644 mm/memtest.c create mode 100644 mm/migrate.c create mode 100644 mm/mincore.c create mode 100644 mm/mlock.c create mode 100644 mm/mm_init.c create mode 100644 mm/mmap.c create mode 100644 mm/mmu_gather.c create mode 100644 mm/mmu_notifier.c create mode 100644 mm/mmzone.c create mode 100644 mm/mprotect.c create mode 100644 mm/mremap.c create mode 100644 mm/msync.c create mode 100644 mm/nommu.c create mode 100644 mm/oom_kill.c create mode 100644 mm/page-writeback.c create mode 100644 mm/page_alloc.c create mode 100644 mm/page_counter.c create mode 100644 mm/page_ext.c create mode 100644 mm/page_idle.c create mode 100644 mm/page_io.c create mode 100644 mm/page_isolation.c create mode 100644 mm/page_owner.c create mode 100644 mm/page_poison.c create mode 100644 mm/page_reporting.c create mode 100644 mm/page_reporting.h create mode 100644 mm/page_vma_mapped.c create mode 100644 mm/pagewalk.c create mode 100644 mm/percpu-internal.h create mode 100644 mm/percpu-km.c create mode 100644 mm/percpu-stats.c create mode 100644 mm/percpu-vm.c create mode 100644 mm/percpu.c create mode 100644 mm/pgalloc-track.h create mode 100644 mm/pgtable-generic.c create mode 100644 mm/process_vm_access.c create mode 100644 mm/ptdump.c create mode 100644 mm/readahead.c create mode 100644 mm/rmap.c create mode 100644 mm/rodata_test.c create mode 100644 mm/shmem.c create mode 100644 mm/shuffle.c create mode 100644 mm/shuffle.h create mode 100644 mm/slab.c create mode 100644 mm/slab.h create mode 100644 mm/slab_common.c create mode 100644 mm/slob.c create mode 100644 mm/slub.c create mode 100644 mm/sparse-vmemmap.c create mode 100644 mm/sparse.c create mode 100644 mm/swap.c create mode 100644 mm/swap_cgroup.c create mode 100644 mm/swap_slots.c create mode 100644 mm/swap_state.c create mode 100644 mm/swapfile.c create mode 100644 mm/truncate.c create mode 100644 mm/usercopy.c create mode 100644 mm/userfaultfd.c create mode 100644 mm/util.c create mode 100644 mm/vmacache.c create mode 100644 mm/vmalloc.c create mode 100644 mm/vmpressure.c create mode 100644 mm/vmscan.c create mode 100644 mm/vmstat.c create mode 100644 mm/workingset.c create mode 100644 mm/z3fold.c create mode 100644 mm/zbud.c create mode 100644 mm/zpool.c create mode 100644 mm/zsmalloc.c create mode 100644 mm/zswap.c (limited to 'mm') diff --git a/mm/Kconfig b/mm/Kconfig new file mode 100644 index 000000000..390165ffb --- /dev/null +++ b/mm/Kconfig @@ -0,0 +1,862 @@ +# SPDX-License-Identifier: GPL-2.0-only + +menu "Memory Management options" + +config SELECT_MEMORY_MODEL + def_bool y + depends on ARCH_SELECT_MEMORY_MODEL + +choice + prompt "Memory model" + depends on SELECT_MEMORY_MODEL + default DISCONTIGMEM_MANUAL if ARCH_DISCONTIGMEM_DEFAULT + default SPARSEMEM_MANUAL if ARCH_SPARSEMEM_DEFAULT + default FLATMEM_MANUAL + help + This option allows you to change some of the ways that + Linux manages its memory internally. Most users will + only have one option here selected by the architecture + configuration. This is normal. + +config FLATMEM_MANUAL + bool "Flat Memory" + depends on !(ARCH_DISCONTIGMEM_ENABLE || ARCH_SPARSEMEM_ENABLE) || ARCH_FLATMEM_ENABLE + help + This option is best suited for non-NUMA systems with + flat address space. The FLATMEM is the most efficient + system in terms of performance and resource consumption + and it is the best option for smaller systems. + + For systems that have holes in their physical address + spaces and for features like NUMA and memory hotplug, + choose "Sparse Memory". + + If unsure, choose this option (Flat Memory) over any other. + +config DISCONTIGMEM_MANUAL + bool "Discontiguous Memory" + depends on ARCH_DISCONTIGMEM_ENABLE + help + This option provides enhanced support for discontiguous + memory systems, over FLATMEM. These systems have holes + in their physical address spaces, and this option provides + more efficient handling of these holes. + + Although "Discontiguous Memory" is still used by several + architectures, it is considered deprecated in favor of + "Sparse Memory". + + If unsure, choose "Sparse Memory" over this option. + +config SPARSEMEM_MANUAL + bool "Sparse Memory" + depends on ARCH_SPARSEMEM_ENABLE + help + This will be the only option for some systems, including + memory hot-plug systems. This is normal. + + This option provides efficient support for systems with + holes is their physical address space and allows memory + hot-plug and hot-remove. + + If unsure, choose "Flat Memory" over this option. + +endchoice + +config DISCONTIGMEM + def_bool y + depends on (!SELECT_MEMORY_MODEL && ARCH_DISCONTIGMEM_ENABLE) || DISCONTIGMEM_MANUAL + +config SPARSEMEM + def_bool y + depends on (!SELECT_MEMORY_MODEL && ARCH_SPARSEMEM_ENABLE) || SPARSEMEM_MANUAL + +config FLATMEM + def_bool y + depends on (!DISCONTIGMEM && !SPARSEMEM) || FLATMEM_MANUAL + +config FLAT_NODE_MEM_MAP + def_bool y + depends on !SPARSEMEM + +# +# Both the NUMA code and DISCONTIGMEM use arrays of pg_data_t's +# to represent different areas of memory. This variable allows +# those dependencies to exist individually. +# +config NEED_MULTIPLE_NODES + def_bool y + depends on DISCONTIGMEM || NUMA + +# +# SPARSEMEM_EXTREME (which is the default) does some bootmem +# allocations when sparse_init() is called. If this cannot +# be done on your architecture, select this option. However, +# statically allocating the mem_section[] array can potentially +# consume vast quantities of .bss, so be careful. +# +# This option will also potentially produce smaller runtime code +# with gcc 3.4 and later. +# +config SPARSEMEM_STATIC + bool + +# +# Architecture platforms which require a two level mem_section in SPARSEMEM +# must select this option. This is usually for architecture platforms with +# an extremely sparse physical address space. +# +config SPARSEMEM_EXTREME + def_bool y + depends on SPARSEMEM && !SPARSEMEM_STATIC + +config SPARSEMEM_VMEMMAP_ENABLE + bool + +config SPARSEMEM_VMEMMAP + bool "Sparse Memory virtual memmap" + depends on SPARSEMEM && SPARSEMEM_VMEMMAP_ENABLE + default y + help + SPARSEMEM_VMEMMAP uses a virtually mapped memmap to optimise + pfn_to_page and page_to_pfn operations. This is the most + efficient option when sufficient kernel resources are available. + +config HAVE_MEMBLOCK_PHYS_MAP + bool + +config HAVE_FAST_GUP + depends on MMU + bool + +# Don't discard allocated memory used to track "memory" and "reserved" memblocks +# after early boot, so it can still be used to test for validity of memory. +# Also, memblocks are updated with memory hot(un)plug. +config ARCH_KEEP_MEMBLOCK + bool + +# Keep arch NUMA mapping infrastructure post-init. +config NUMA_KEEP_MEMINFO + bool + +config MEMORY_ISOLATION + bool + +# +# Only be set on architectures that have completely implemented memory hotplug +# feature. If you are not sure, don't touch it. +# +config HAVE_BOOTMEM_INFO_NODE + def_bool n + +# eventually, we can have this option just 'select SPARSEMEM' +config MEMORY_HOTPLUG + bool "Allow for memory hot-add" + select MEMORY_ISOLATION + depends on SPARSEMEM || X86_64_ACPI_NUMA + depends on ARCH_ENABLE_MEMORY_HOTPLUG + depends on 64BIT || BROKEN + select NUMA_KEEP_MEMINFO if NUMA + +config MEMORY_HOTPLUG_SPARSE + def_bool y + depends on SPARSEMEM && MEMORY_HOTPLUG + +config MEMORY_HOTPLUG_DEFAULT_ONLINE + bool "Online the newly added memory blocks by default" + depends on MEMORY_HOTPLUG + help + This option sets the default policy setting for memory hotplug + onlining policy (/sys/devices/system/memory/auto_online_blocks) which + determines what happens to newly added memory regions. Policy setting + can always be changed at runtime. + See Documentation/admin-guide/mm/memory-hotplug.rst for more information. + + Say Y here if you want all hot-plugged memory blocks to appear in + 'online' state by default. + Say N here if you want the default policy to keep all hot-plugged + memory blocks in 'offline' state. + +config MEMORY_HOTREMOVE + bool "Allow for memory hot remove" + select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64) + depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE + depends on MIGRATION + +# Heavily threaded applications may benefit from splitting the mm-wide +# page_table_lock, so that faults on different parts of the user address +# space can be handled with less contention: split it at this NR_CPUS. +# Default to 4 for wider testing, though 8 might be more appropriate. +# ARM's adjust_pte (unused if VIPT) depends on mm-wide page_table_lock. +# PA-RISC 7xxx's spinlock_t would enlarge struct page from 32 to 44 bytes. +# SPARC32 allocates multiple pte tables within a single page, and therefore +# a per-page lock leads to problems when multiple tables need to be locked +# at the same time (e.g. copy_page_range()). +# DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page. +# +config SPLIT_PTLOCK_CPUS + int + default "999999" if !MMU + default "999999" if ARM && !CPU_CACHE_VIPT + default "999999" if PARISC && !PA20 + default "999999" if SPARC32 + default "4" + +config ARCH_ENABLE_SPLIT_PMD_PTLOCK + bool + +# +# support for memory balloon +config MEMORY_BALLOON + bool + +# +# support for memory balloon compaction +config BALLOON_COMPACTION + bool "Allow for balloon memory compaction/migration" + def_bool y + depends on COMPACTION && MEMORY_BALLOON + help + Memory fragmentation introduced by ballooning might reduce + significantly the number of 2MB contiguous memory blocks that can be + used within a guest, thus imposing performance penalties associated + with the reduced number of transparent huge pages that could be used + by the guest workload. Allowing the compaction & migration for memory + pages enlisted as being part of memory balloon devices avoids the + scenario aforementioned and helps improving memory defragmentation. + +# +# support for memory compaction +config COMPACTION + bool "Allow for memory compaction" + def_bool y + select MIGRATION + depends on MMU + help + Compaction is the only memory management component to form + high order (larger physically contiguous) memory blocks + reliably. The page allocator relies on compaction heavily and + the lack of the feature can lead to unexpected OOM killer + invocations for high order memory requests. You shouldn't + disable this option unless there really is a strong reason for + it and then we would be really interested to hear about that at + linux-mm@kvack.org. + +# +# support for free page reporting +config PAGE_REPORTING + bool "Free page reporting" + def_bool n + help + Free page reporting allows for the incremental acquisition of + free pages from the buddy allocator for the purpose of reporting + those pages to another entity, such as a hypervisor, so that the + memory can be freed within the host for other uses. + +# +# support for page migration +# +config MIGRATION + bool "Page migration" + def_bool y + depends on (NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA) && MMU + help + Allows the migration of the physical location of pages of processes + while the virtual addresses are not changed. This is useful in + two situations. The first is on NUMA systems to put pages nearer + to the processors accessing. The second is when allocating huge + pages as migration can relocate pages to satisfy a huge page + allocation instead of reclaiming. + +config ARCH_ENABLE_HUGEPAGE_MIGRATION + bool + +config ARCH_ENABLE_THP_MIGRATION + bool + +config CONTIG_ALLOC + def_bool (MEMORY_ISOLATION && COMPACTION) || CMA + +config PHYS_ADDR_T_64BIT + def_bool 64BIT + +config BOUNCE + bool "Enable bounce buffers" + default y + depends on BLOCK && MMU && (ZONE_DMA || HIGHMEM) + help + Enable bounce buffers for devices that cannot access + the full range of memory available to the CPU. Enabled + by default when ZONE_DMA or HIGHMEM is selected, but you + may say n to override this. + +config VIRT_TO_BUS + bool + help + An architecture should select this if it implements the + deprecated interface virt_to_bus(). All new architectures + should probably not select this. + + +config MMU_NOTIFIER + bool + select SRCU + select INTERVAL_TREE + +config KSM + bool "Enable KSM for page merging" + depends on MMU + select XXHASH + help + Enable Kernel Samepage Merging: KSM periodically scans those areas + of an application's address space that an app has advised may be + mergeable. When it finds pages of identical content, it replaces + the many instances by a single page with that content, so + saving memory until one or another app needs to modify the content. + Recommended for use with KVM, or with other duplicative applications. + See Documentation/vm/ksm.rst for more information: KSM is inactive + until a program has madvised that an area is MADV_MERGEABLE, and + root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set). + +config DEFAULT_MMAP_MIN_ADDR + int "Low address space to protect from user allocation" + depends on MMU + default 4096 + help + This is the portion of low virtual memory which should be protected + from userspace allocation. Keeping a user from writing to low pages + can help reduce the impact of kernel NULL pointer bugs. + + For most ia64, ppc64 and x86 users with lots of address space + a value of 65536 is reasonable and should cause no problems. + On arm and other archs it should not be higher than 32768. + Programs which use vm86 functionality or have some need to map + this low address space will need CAP_SYS_RAWIO or disable this + protection by setting the value to 0. + + This value can be changed after boot using the + /proc/sys/vm/mmap_min_addr tunable. + +config ARCH_SUPPORTS_MEMORY_FAILURE + bool + +config MEMORY_FAILURE + depends on MMU + depends on ARCH_SUPPORTS_MEMORY_FAILURE + bool "Enable recovery from hardware memory errors" + select MEMORY_ISOLATION + select RAS + help + Enables code to recover from some memory failures on systems + with MCA recovery. This allows a system to continue running + even when some of its memory has uncorrected errors. This requires + special hardware support and typically ECC memory. + +config HWPOISON_INJECT + tristate "HWPoison pages injector" + depends on MEMORY_FAILURE && DEBUG_KERNEL && PROC_FS + select PROC_PAGE_MONITOR + +config NOMMU_INITIAL_TRIM_EXCESS + int "Turn on mmap() excess space trimming before booting" + depends on !MMU + default 1 + help + The NOMMU mmap() frequently needs to allocate large contiguous chunks + of memory on which to store mappings, but it can only ask the system + allocator for chunks in 2^N*PAGE_SIZE amounts - which is frequently + more than it requires. To deal with this, mmap() is able to trim off + the excess and return it to the allocator. + + If trimming is enabled, the excess is trimmed off and returned to the + system allocator, which can cause extra fragmentation, particularly + if there are a lot of transient processes. + + If trimming is disabled, the excess is kept, but not used, which for + long-term mappings means that the space is wasted. + + Trimming can be dynamically controlled through a sysctl option + (/proc/sys/vm/nr_trim_pages) which specifies the minimum number of + excess pages there must be before trimming should occur, or zero if + no trimming is to occur. + + This option specifies the initial value of this option. The default + of 1 says that all excess pages should be trimmed. + + See Documentation/admin-guide/mm/nommu-mmap.rst for more information. + +config TRANSPARENT_HUGEPAGE + bool "Transparent Hugepage Support" + depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE + select COMPACTION + select XARRAY_MULTI + help + Transparent Hugepages allows the kernel to use huge pages and + huge tlb transparently to the applications whenever possible. + This feature can improve computing performance to certain + applications by speeding up page faults during memory + allocation, by reducing the number of tlb misses and by speeding + up the pagetable walking. + + If memory constrained on embedded, you may want to say N. + +choice + prompt "Transparent Hugepage Support sysfs defaults" + depends on TRANSPARENT_HUGEPAGE + default TRANSPARENT_HUGEPAGE_ALWAYS + help + Selects the sysfs defaults for Transparent Hugepage Support. + + config TRANSPARENT_HUGEPAGE_ALWAYS + bool "always" + help + Enabling Transparent Hugepage always, can increase the + memory footprint of applications without a guaranteed + benefit but it will work automatically for all applications. + + config TRANSPARENT_HUGEPAGE_MADVISE + bool "madvise" + help + Enabling Transparent Hugepage madvise, will only provide a + performance improvement benefit to the applications using + madvise(MADV_HUGEPAGE) but it won't risk to increase the + memory footprint of applications without a guaranteed + benefit. +endchoice + +config ARCH_WANTS_THP_SWAP + def_bool n + +config THP_SWAP + def_bool y + depends on TRANSPARENT_HUGEPAGE && ARCH_WANTS_THP_SWAP && SWAP + help + Swap transparent huge pages in one piece, without splitting. + XXX: For now, swap cluster backing transparent huge page + will be split after swapout. + + For selection by architectures with reasonable THP sizes. + +# +# UP and nommu archs use km based percpu allocator +# +config NEED_PER_CPU_KM + depends on !SMP + bool + default y + +config CLEANCACHE + bool "Enable cleancache driver to cache clean pages if tmem is present" + help + Cleancache can be thought of as a page-granularity victim cache + for clean pages that the kernel's pageframe replacement algorithm + (PFRA) would like to keep around, but can't since there isn't enough + memory. So when the PFRA "evicts" a page, it first attempts to use + cleancache code to put the data contained in that page into + "transcendent memory", memory that is not directly accessible or + addressable by the kernel and is of unknown and possibly + time-varying size. And when a cleancache-enabled + filesystem wishes to access a page in a file on disk, it first + checks cleancache to see if it already contains it; if it does, + the page is copied into the kernel and a disk access is avoided. + When a transcendent memory driver is available (such as zcache or + Xen transcendent memory), a significant I/O reduction + may be achieved. When none is available, all cleancache calls + are reduced to a single pointer-compare-against-NULL resulting + in a negligible performance hit. + + If unsure, say Y to enable cleancache + +config FRONTSWAP + bool "Enable frontswap to cache swap pages if tmem is present" + depends on SWAP + help + Frontswap is so named because it can be thought of as the opposite + of a "backing" store for a swap device. The data is stored into + "transcendent memory", memory that is not directly accessible or + addressable by the kernel and is of unknown and possibly + time-varying size. When space in transcendent memory is available, + a significant swap I/O reduction may be achieved. When none is + available, all frontswap calls are reduced to a single pointer- + compare-against-NULL resulting in a negligible performance hit + and swap data is stored as normal on the matching swap device. + + If unsure, say Y to enable frontswap. + +config CMA + bool "Contiguous Memory Allocator" + depends on MMU + select MIGRATION + select MEMORY_ISOLATION + help + This enables the Contiguous Memory Allocator which allows other + subsystems to allocate big physically-contiguous blocks of memory. + CMA reserves a region of memory and allows only movable pages to + be allocated from it. This way, the kernel can use the memory for + pagecache and when a subsystem requests for contiguous area, the + allocated pages are migrated away to serve the contiguous request. + + If unsure, say "n". + +config CMA_DEBUG + bool "CMA debug messages (DEVELOPMENT)" + depends on DEBUG_KERNEL && CMA + help + Turns on debug messages in CMA. This produces KERN_DEBUG + messages for every CMA call as well as various messages while + processing calls such as dma_alloc_from_contiguous(). + This option does not affect warning and error messages. + +config CMA_DEBUGFS + bool "CMA debugfs interface" + depends on CMA && DEBUG_FS + help + Turns on the DebugFS interface for CMA. + +config CMA_AREAS + int "Maximum count of the CMA areas" + depends on CMA + default 19 if NUMA + default 7 + help + CMA allows to create CMA areas for particular purpose, mainly, + used as device private area. This parameter sets the maximum + number of CMA area in the system. + + If unsure, leave the default value "7" in UMA and "19" in NUMA. + +config MEM_SOFT_DIRTY + bool "Track memory changes" + depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY && PROC_FS + select PROC_PAGE_MONITOR + help + This option enables memory changes tracking by introducing a + soft-dirty bit on pte-s. This bit it set when someone writes + into a page just as regular dirty bit, but unlike the latter + it can be cleared by hands. + + See Documentation/admin-guide/mm/soft-dirty.rst for more details. + +config ZSWAP + bool "Compressed cache for swap pages (EXPERIMENTAL)" + depends on FRONTSWAP && CRYPTO=y + select ZPOOL + help + A lightweight compressed cache for swap pages. It takes + pages that are in the process of being swapped out and attempts to + compress them into a dynamically allocated RAM-based memory pool. + This can result in a significant I/O reduction on swap device and, + in the case where decompressing from RAM is faster that swap device + reads, can also improve workload performance. + + This is marked experimental because it is a new feature (as of + v3.11) that interacts heavily with memory reclaim. While these + interactions don't cause any known issues on simple memory setups, + they have not be fully explored on the large set of potential + configurations and workloads that exist. + +choice + prompt "Compressed cache for swap pages default compressor" + depends on ZSWAP + default ZSWAP_COMPRESSOR_DEFAULT_LZO + help + Selects the default compression algorithm for the compressed cache + for swap pages. + + For an overview what kind of performance can be expected from + a particular compression algorithm please refer to the benchmarks + available at the following LWN page: + https://lwn.net/Articles/751795/ + + If in doubt, select 'LZO'. + + The selection made here can be overridden by using the kernel + command line 'zswap.compressor=' option. + +config ZSWAP_COMPRESSOR_DEFAULT_DEFLATE + bool "Deflate" + select CRYPTO_DEFLATE + help + Use the Deflate algorithm as the default compression algorithm. + +config ZSWAP_COMPRESSOR_DEFAULT_LZO + bool "LZO" + select CRYPTO_LZO + help + Use the LZO algorithm as the default compression algorithm. + +config ZSWAP_COMPRESSOR_DEFAULT_842 + bool "842" + select CRYPTO_842 + help + Use the 842 algorithm as the default compression algorithm. + +config ZSWAP_COMPRESSOR_DEFAULT_LZ4 + bool "LZ4" + select CRYPTO_LZ4 + help + Use the LZ4 algorithm as the default compression algorithm. + +config ZSWAP_COMPRESSOR_DEFAULT_LZ4HC + bool "LZ4HC" + select CRYPTO_LZ4HC + help + Use the LZ4HC algorithm as the default compression algorithm. + +config ZSWAP_COMPRESSOR_DEFAULT_ZSTD + bool "zstd" + select CRYPTO_ZSTD + help + Use the zstd algorithm as the default compression algorithm. +endchoice + +config ZSWAP_COMPRESSOR_DEFAULT + string + depends on ZSWAP + default "deflate" if ZSWAP_COMPRESSOR_DEFAULT_DEFLATE + default "lzo" if ZSWAP_COMPRESSOR_DEFAULT_LZO + default "842" if ZSWAP_COMPRESSOR_DEFAULT_842 + default "lz4" if ZSWAP_COMPRESSOR_DEFAULT_LZ4 + default "lz4hc" if ZSWAP_COMPRESSOR_DEFAULT_LZ4HC + default "zstd" if ZSWAP_COMPRESSOR_DEFAULT_ZSTD + default "" + +choice + prompt "Compressed cache for swap pages default allocator" + depends on ZSWAP + default ZSWAP_ZPOOL_DEFAULT_ZBUD + help + Selects the default allocator for the compressed cache for + swap pages. + The default is 'zbud' for compatibility, however please do + read the description of each of the allocators below before + making a right choice. + + The selection made here can be overridden by using the kernel + command line 'zswap.zpool=' option. + +config ZSWAP_ZPOOL_DEFAULT_ZBUD + bool "zbud" + select ZBUD + help + Use the zbud allocator as the default allocator. + +config ZSWAP_ZPOOL_DEFAULT_Z3FOLD + bool "z3fold" + select Z3FOLD + help + Use the z3fold allocator as the default allocator. + +config ZSWAP_ZPOOL_DEFAULT_ZSMALLOC + bool "zsmalloc" + select ZSMALLOC + help + Use the zsmalloc allocator as the default allocator. +endchoice + +config ZSWAP_ZPOOL_DEFAULT + string + depends on ZSWAP + default "zbud" if ZSWAP_ZPOOL_DEFAULT_ZBUD + default "z3fold" if ZSWAP_ZPOOL_DEFAULT_Z3FOLD + default "zsmalloc" if ZSWAP_ZPOOL_DEFAULT_ZSMALLOC + default "" + +config ZSWAP_DEFAULT_ON + bool "Enable the compressed cache for swap pages by default" + depends on ZSWAP + help + If selected, the compressed cache for swap pages will be enabled + at boot, otherwise it will be disabled. + + The selection made here can be overridden by using the kernel + command line 'zswap.enabled=' option. + +config ZPOOL + tristate "Common API for compressed memory storage" + help + Compressed memory storage API. This allows using either zbud or + zsmalloc. + +config ZBUD + tristate "Low (Up to 2x) density storage for compressed pages" + help + A special purpose allocator for storing compressed pages. + It is designed to store up to two compressed pages per physical + page. While this design limits storage density, it has simple and + deterministic reclaim properties that make it preferable to a higher + density approach when reclaim will be used. + +config Z3FOLD + tristate "Up to 3x density storage for compressed pages" + depends on ZPOOL + help + A special purpose allocator for storing compressed pages. + It is designed to store up to three compressed pages per physical + page. It is a ZBUD derivative so the simplicity and determinism are + still there. + +config ZSMALLOC + tristate "Memory allocator for compressed pages" + depends on MMU + help + zsmalloc is a slab-based memory allocator designed to store + compressed RAM pages. zsmalloc uses virtual memory mapping + in order to reduce fragmentation. However, this results in a + non-standard allocator interface where a handle, not a pointer, is + returned by an alloc(). This handle must be mapped in order to + access the allocated space. + +config ZSMALLOC_STAT + bool "Export zsmalloc statistics" + depends on ZSMALLOC + select DEBUG_FS + help + This option enables code in the zsmalloc to collect various + statistics about whats happening in zsmalloc and exports that + information to userspace via debugfs. + If unsure, say N. + +config GENERIC_EARLY_IOREMAP + bool + +config MAX_STACK_SIZE_MB + int "Maximum user stack size for 32-bit processes (MB)" + default 80 + range 8 2048 + depends on STACK_GROWSUP && (!64BIT || COMPAT) + help + This is the maximum stack size in Megabytes in the VM layout of 32-bit + user processes when the stack grows upwards (currently only on parisc + arch). The stack will be located at the highest memory address minus + the given value, unless the RLIMIT_STACK hard limit is changed to a + smaller value in which case that is used. + + A sane initial value is 80 MB. + +config DEFERRED_STRUCT_PAGE_INIT + bool "Defer initialisation of struct pages to kthreads" + depends on SPARSEMEM + depends on !NEED_PER_CPU_KM + depends on 64BIT + select PADATA + help + Ordinarily all struct pages are initialised during early boot in a + single thread. On very large machines this can take a considerable + amount of time. If this option is set, large machines will bring up + a subset of memmap at boot and then initialise the rest in parallel. + This has a potential performance impact on tasks running early in the + lifetime of the system until these kthreads finish the + initialisation. + +config IDLE_PAGE_TRACKING + bool "Enable idle page tracking" + depends on SYSFS && MMU + select PAGE_EXTENSION if !64BIT + help + This feature allows to estimate the amount of user pages that have + not been touched during a given period of time. This information can + be useful to tune memory cgroup limits and/or for job placement + within a compute cluster. + + See Documentation/admin-guide/mm/idle_page_tracking.rst for + more details. + +config ARCH_HAS_PTE_DEVMAP + bool + +config ZONE_DEVICE + bool "Device memory (pmem, HMM, etc...) hotplug support" + depends on MEMORY_HOTPLUG + depends on MEMORY_HOTREMOVE + depends on SPARSEMEM_VMEMMAP + depends on ARCH_HAS_PTE_DEVMAP + select XARRAY_MULTI + + help + Device memory hotplug support allows for establishing pmem, + or other device driver discovered memory regions, in the + memmap. This allows pfn_to_page() lookups of otherwise + "device-physical" addresses which is needed for using a DAX + mapping in an O_DIRECT operation, among other things. + + If FS_DAX is enabled, then say Y. + +config DEV_PAGEMAP_OPS + bool + +# +# Helpers to mirror range of the CPU page tables of a process into device page +# tables. +# +config HMM_MIRROR + bool + depends on MMU + +config DEVICE_PRIVATE + bool "Unaddressable device memory (GPU memory, ...)" + depends on ZONE_DEVICE + select DEV_PAGEMAP_OPS + + help + Allows creation of struct pages to represent unaddressable device + memory; i.e., memory that is only accessible from the device (or + group of devices). You likely also want to select HMM_MIRROR. + +config VMAP_PFN + bool + +config FRAME_VECTOR + bool + +config ARCH_USES_HIGH_VMA_FLAGS + bool +config ARCH_HAS_PKEYS + bool + +config PERCPU_STATS + bool "Collect percpu memory statistics" + help + This feature collects and exposes statistics via debugfs. The + information includes global and per chunk statistics, which can + be used to help understand percpu memory usage. + +config GUP_BENCHMARK + bool "Enable infrastructure for get_user_pages() and related calls benchmarking" + help + Provides /sys/kernel/debug/gup_benchmark that helps with testing + performance of get_user_pages() and related calls. + + See tools/testing/selftests/vm/gup_benchmark.c + +config GUP_GET_PTE_LOW_HIGH + bool + +config READ_ONLY_THP_FOR_FS + bool "Read-only THP for filesystems (EXPERIMENTAL)" + depends on TRANSPARENT_HUGEPAGE && SHMEM + + help + Allow khugepaged to put read-only file-backed pages in THP. + + This is marked experimental because it is a new feature. Write + support of file THPs will be developed in the next few release + cycles. + +config ARCH_HAS_PTE_SPECIAL + bool + +# +# Some architectures require a special hugepage directory format that is +# required to support multiple hugepage sizes. For example a4fe3ce76 +# "powerpc/mm: Allow more flexible layouts for hugepage pagetables" +# introduced it on powerpc. This allows for a more flexible hugepage +# pagetable layouts. +# +config ARCH_HAS_HUGEPD + bool + +config MAPPING_DIRTY_HELPERS + bool + +endmenu diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug new file mode 100644 index 000000000..864f129f1 --- /dev/null +++ b/mm/Kconfig.debug @@ -0,0 +1,172 @@ +# SPDX-License-Identifier: GPL-2.0-only +config PAGE_EXTENSION + bool "Extend memmap on extra space for more information on page" + help + Extend memmap on extra space for more information on page. This + could be used for debugging features that need to insert extra + field for every page. This extension enables us to save memory + by not allocating this extra memory according to boottime + configuration. + +config DEBUG_PAGEALLOC + bool "Debug page memory allocations" + depends on DEBUG_KERNEL + depends on !HIBERNATION || ARCH_SUPPORTS_DEBUG_PAGEALLOC && !PPC && !SPARC + select PAGE_POISONING if !ARCH_SUPPORTS_DEBUG_PAGEALLOC + help + Unmap pages from the kernel linear mapping after free_pages(). + Depending on runtime enablement, this results in a small or large + slowdown, but helps to find certain types of memory corruption. + + Also, the state of page tracking structures is checked more often as + pages are being allocated and freed, as unexpected state changes + often happen for same reasons as memory corruption (e.g. double free, + use-after-free). The error reports for these checks can be augmented + with stack traces of last allocation and freeing of the page, when + PAGE_OWNER is also selected and enabled on boot. + + For architectures which don't enable ARCH_SUPPORTS_DEBUG_PAGEALLOC, + fill the pages with poison patterns after free_pages() and verify + the patterns before alloc_pages(). Additionally, this option cannot + be enabled in combination with hibernation as that would result in + incorrect warnings of memory corruption after a resume because free + pages are not saved to the suspend image. + + By default this option will have a small overhead, e.g. by not + allowing the kernel mapping to be backed by large pages on some + architectures. Even bigger overhead comes when the debugging is + enabled by DEBUG_PAGEALLOC_ENABLE_DEFAULT or the debug_pagealloc + command line parameter. + +config DEBUG_PAGEALLOC_ENABLE_DEFAULT + bool "Enable debug page memory allocations by default?" + depends on DEBUG_PAGEALLOC + help + Enable debug page memory allocations by default? This value + can be overridden by debug_pagealloc=off|on. + +config PAGE_OWNER + bool "Track page owner" + depends on DEBUG_KERNEL && STACKTRACE_SUPPORT + select DEBUG_FS + select STACKTRACE + select STACKDEPOT + select PAGE_EXTENSION + help + This keeps track of what call chain is the owner of a page, may + help to find bare alloc_page(s) leaks. Even if you include this + feature on your build, it is disabled in default. You should pass + "page_owner=on" to boot parameter in order to enable it. Eats + a fair amount of memory if enabled. See tools/vm/page_owner_sort.c + for user-space helper. + + If unsure, say N. + +config PAGE_POISONING + bool "Poison pages after freeing" + select PAGE_POISONING_NO_SANITY if HIBERNATION + help + Fill the pages with poison patterns after free_pages() and verify + the patterns before alloc_pages. The filling of the memory helps + reduce the risk of information leaks from freed data. This does + have a potential performance impact if enabled with the + "page_poison=1" kernel boot option. + + Note that "poison" here is not the same thing as the "HWPoison" + for CONFIG_MEMORY_FAILURE. This is software poisoning only. + + If unsure, say N + +config PAGE_POISONING_NO_SANITY + depends on PAGE_POISONING + bool "Only poison, don't sanity check" + help + Skip the sanity checking on alloc, only fill the pages with + poison on free. This reduces some of the overhead of the + poisoning feature. + + If you are only interested in sanitization, say Y. Otherwise + say N. + +config PAGE_POISONING_ZERO + bool "Use zero for poisoning instead of debugging value" + depends on PAGE_POISONING + help + Instead of using the existing poison value, fill the pages with + zeros. This makes it harder to detect when errors are occurring + due to sanitization but the zeroing at free means that it is + no longer necessary to write zeros when GFP_ZERO is used on + allocation. + + If unsure, say N + +config DEBUG_PAGE_REF + bool "Enable tracepoint to track down page reference manipulation" + depends on DEBUG_KERNEL + depends on TRACEPOINTS + help + This is a feature to add tracepoint for tracking down page reference + manipulation. This tracking is useful to diagnose functional failure + due to migration failures caused by page reference mismatches. Be + careful when enabling this feature because it adds about 30 KB to the + kernel code. However the runtime performance overhead is virtually + nil until the tracepoints are actually enabled. + +config DEBUG_RODATA_TEST + bool "Testcase for the marking rodata read-only" + depends on STRICT_KERNEL_RWX + help + This option enables a testcase for the setting rodata read-only. + +config ARCH_HAS_DEBUG_WX + bool + +config DEBUG_WX + bool "Warn on W+X mappings at boot" + depends on ARCH_HAS_DEBUG_WX + depends on MMU + select PTDUMP_CORE + help + Generate a warning if any W+X mappings are found at boot. + + This is useful for discovering cases where the kernel is leaving W+X + mappings after applying NX, as such mappings are a security risk. + + Look for a message in dmesg output like this: + + /mm: Checked W+X mappings: passed, no W+X pages found. + + or like this, if the check failed: + + /mm: Checked W+X mappings: failed, W+X pages found. + + Note that even if the check fails, your kernel is possibly + still fine, as W+X mappings are not a security hole in + themselves, what they do is that they make the exploitation + of other unfixed kernel bugs easier. + + There is no runtime or memory usage effect of this option + once the kernel has booted up - it's a one time check. + + If in doubt, say "Y". + +config GENERIC_PTDUMP + bool + +config PTDUMP_CORE + bool + +config PTDUMP_DEBUGFS + bool "Export kernel pagetable layout to userspace via debugfs" + depends on DEBUG_KERNEL + depends on DEBUG_FS + depends on GENERIC_PTDUMP + select PTDUMP_CORE + help + Say Y here if you want to show the kernel pagetable layout in a + debugfs file. This information is only useful for kernel developers + who are working in architecture specific areas of the kernel. + It is probably not a good idea to enable this feature in a production + kernel. + + If in doubt, say N. diff --git a/mm/Makefile b/mm/Makefile new file mode 100644 index 000000000..d73aed0fc --- /dev/null +++ b/mm/Makefile @@ -0,0 +1,122 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for the linux memory manager. +# + +KASAN_SANITIZE_slab_common.o := n +KASAN_SANITIZE_slab.o := n +KASAN_SANITIZE_slub.o := n +KCSAN_SANITIZE_kmemleak.o := n + +# These produce frequent data race reports: most of them are due to races on +# the same word but accesses to different bits of that word. Re-enable KCSAN +# for these when we have more consensus on what to do about them. +KCSAN_SANITIZE_slab_common.o := n +KCSAN_SANITIZE_slab.o := n +KCSAN_SANITIZE_slub.o := n +KCSAN_SANITIZE_page_alloc.o := n + +# These files are disabled because they produce non-interesting and/or +# flaky coverage that is not a function of syscall inputs. E.g. slab is out of +# free pages, or a task is migrated between nodes. +KCOV_INSTRUMENT_slab_common.o := n +KCOV_INSTRUMENT_slob.o := n +KCOV_INSTRUMENT_slab.o := n +KCOV_INSTRUMENT_slub.o := n +KCOV_INSTRUMENT_page_alloc.o := n +KCOV_INSTRUMENT_debug-pagealloc.o := n +KCOV_INSTRUMENT_kmemleak.o := n +KCOV_INSTRUMENT_memcontrol.o := n +KCOV_INSTRUMENT_mmzone.o := n +KCOV_INSTRUMENT_vmstat.o := n +KCOV_INSTRUMENT_failslab.o := n + +CFLAGS_init-mm.o += $(call cc-disable-warning, override-init) +CFLAGS_init-mm.o += $(call cc-disable-warning, initializer-overrides) + +mmu-y := nommu.o +mmu-$(CONFIG_MMU) := highmem.o memory.o mincore.o \ + mlock.o mmap.o mmu_gather.o mprotect.o mremap.o \ + msync.o page_vma_mapped.o pagewalk.o \ + pgtable-generic.o rmap.o vmalloc.o ioremap.o + + +ifdef CONFIG_CROSS_MEMORY_ATTACH +mmu-$(CONFIG_MMU) += process_vm_access.o +endif + +obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ + maccess.o page-writeback.o \ + readahead.o swap.o truncate.o vmscan.o shmem.o \ + util.o mmzone.o vmstat.o backing-dev.o \ + mm_init.o percpu.o slab_common.o \ + compaction.o vmacache.o \ + interval_tree.o list_lru.o workingset.o \ + debug.o gup.o $(mmu-y) + +# Give 'page_alloc' its own module-parameter namespace +page-alloc-y := page_alloc.o +page-alloc-$(CONFIG_SHUFFLE_PAGE_ALLOCATOR) += shuffle.o + +obj-y += page-alloc.o +obj-y += init-mm.o +obj-y += memblock.o + +ifdef CONFIG_MMU + obj-$(CONFIG_ADVISE_SYSCALLS) += madvise.o +endif + +obj-$(CONFIG_SWAP) += page_io.o swap_state.o swapfile.o swap_slots.o +obj-$(CONFIG_FRONTSWAP) += frontswap.o +obj-$(CONFIG_ZSWAP) += zswap.o +obj-$(CONFIG_HAS_DMA) += dmapool.o +obj-$(CONFIG_HUGETLBFS) += hugetlb.o +obj-$(CONFIG_NUMA) += mempolicy.o +obj-$(CONFIG_SPARSEMEM) += sparse.o +obj-$(CONFIG_SPARSEMEM_VMEMMAP) += sparse-vmemmap.o +obj-$(CONFIG_SLOB) += slob.o +obj-$(CONFIG_MMU_NOTIFIER) += mmu_notifier.o +obj-$(CONFIG_KSM) += ksm.o +obj-$(CONFIG_PAGE_POISONING) += page_poison.o +obj-$(CONFIG_SLAB) += slab.o +obj-$(CONFIG_SLUB) += slub.o +obj-$(CONFIG_KASAN) += kasan/ +obj-$(CONFIG_FAILSLAB) += failslab.o +obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o +obj-$(CONFIG_MEMTEST) += memtest.o +obj-$(CONFIG_MIGRATION) += migrate.o +obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o khugepaged.o +obj-$(CONFIG_PAGE_COUNTER) += page_counter.o +obj-$(CONFIG_MEMCG) += memcontrol.o vmpressure.o +obj-$(CONFIG_MEMCG_SWAP) += swap_cgroup.o +obj-$(CONFIG_CGROUP_HUGETLB) += hugetlb_cgroup.o +obj-$(CONFIG_GUP_BENCHMARK) += gup_benchmark.o +obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o +obj-$(CONFIG_HWPOISON_INJECT) += hwpoison-inject.o +obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o +obj-$(CONFIG_DEBUG_RODATA_TEST) += rodata_test.o +obj-$(CONFIG_DEBUG_VM_PGTABLE) += debug_vm_pgtable.o +obj-$(CONFIG_PAGE_OWNER) += page_owner.o +obj-$(CONFIG_CLEANCACHE) += cleancache.o +obj-$(CONFIG_MEMORY_ISOLATION) += page_isolation.o +obj-$(CONFIG_ZPOOL) += zpool.o +obj-$(CONFIG_ZBUD) += zbud.o +obj-$(CONFIG_ZSMALLOC) += zsmalloc.o +obj-$(CONFIG_Z3FOLD) += z3fold.o +obj-$(CONFIG_GENERIC_EARLY_IOREMAP) += early_ioremap.o +obj-$(CONFIG_CMA) += cma.o +obj-$(CONFIG_MEMORY_BALLOON) += balloon_compaction.o +obj-$(CONFIG_PAGE_EXTENSION) += page_ext.o +obj-$(CONFIG_CMA_DEBUGFS) += cma_debug.o +obj-$(CONFIG_USERFAULTFD) += userfaultfd.o +obj-$(CONFIG_IDLE_PAGE_TRACKING) += page_idle.o +obj-$(CONFIG_FRAME_VECTOR) += frame_vector.o +obj-$(CONFIG_DEBUG_PAGE_REF) += debug_page_ref.o +obj-$(CONFIG_HARDENED_USERCOPY) += usercopy.o +obj-$(CONFIG_PERCPU_STATS) += percpu-stats.o +obj-$(CONFIG_ZONE_DEVICE) += memremap.o +obj-$(CONFIG_HMM_MIRROR) += hmm.o +obj-$(CONFIG_MEMFD_CREATE) += memfd.o +obj-$(CONFIG_MAPPING_DIRTY_HELPERS) += mapping_dirty_helpers.o +obj-$(CONFIG_PTDUMP_CORE) += ptdump.o +obj-$(CONFIG_PAGE_REPORTING) += page_reporting.o diff --git a/mm/backing-dev.c b/mm/backing-dev.c new file mode 100644 index 000000000..dd08ab928 --- /dev/null +++ b/mm/backing-dev.c @@ -0,0 +1,1031 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct backing_dev_info noop_backing_dev_info; +EXPORT_SYMBOL_GPL(noop_backing_dev_info); + +static struct class *bdi_class; +static const char *bdi_unknown_name = "(unknown)"; + +/* + * bdi_lock protects bdi_tree and updates to bdi_list. bdi_list has RCU + * reader side locking. + */ +DEFINE_SPINLOCK(bdi_lock); +static u64 bdi_id_cursor; +static struct rb_root bdi_tree = RB_ROOT; +LIST_HEAD(bdi_list); + +/* bdi_wq serves all asynchronous writeback tasks */ +struct workqueue_struct *bdi_wq; + +#ifdef CONFIG_DEBUG_FS +#include +#include + +static struct dentry *bdi_debug_root; + +static void bdi_debug_init(void) +{ + bdi_debug_root = debugfs_create_dir("bdi", NULL); +} + +static int bdi_debug_stats_show(struct seq_file *m, void *v) +{ + struct backing_dev_info *bdi = m->private; + struct bdi_writeback *wb = &bdi->wb; + unsigned long background_thresh; + unsigned long dirty_thresh; + unsigned long wb_thresh; + unsigned long nr_dirty, nr_io, nr_more_io, nr_dirty_time; + struct inode *inode; + + nr_dirty = nr_io = nr_more_io = nr_dirty_time = 0; + spin_lock(&wb->list_lock); + list_for_each_entry(inode, &wb->b_dirty, i_io_list) + nr_dirty++; + list_for_each_entry(inode, &wb->b_io, i_io_list) + nr_io++; + list_for_each_entry(inode, &wb->b_more_io, i_io_list) + nr_more_io++; + list_for_each_entry(inode, &wb->b_dirty_time, i_io_list) + if (inode->i_state & I_DIRTY_TIME) + nr_dirty_time++; + spin_unlock(&wb->list_lock); + + global_dirty_limits(&background_thresh, &dirty_thresh); + wb_thresh = wb_calc_thresh(wb, dirty_thresh); + +#define K(x) ((x) << (PAGE_SHIFT - 10)) + seq_printf(m, + "BdiWriteback: %10lu kB\n" + "BdiReclaimable: %10lu kB\n" + "BdiDirtyThresh: %10lu kB\n" + "DirtyThresh: %10lu kB\n" + "BackgroundThresh: %10lu kB\n" + "BdiDirtied: %10lu kB\n" + "BdiWritten: %10lu kB\n" + "BdiWriteBandwidth: %10lu kBps\n" + "b_dirty: %10lu\n" + "b_io: %10lu\n" + "b_more_io: %10lu\n" + "b_dirty_time: %10lu\n" + "bdi_list: %10u\n" + "state: %10lx\n", + (unsigned long) K(wb_stat(wb, WB_WRITEBACK)), + (unsigned long) K(wb_stat(wb, WB_RECLAIMABLE)), + K(wb_thresh), + K(dirty_thresh), + K(background_thresh), + (unsigned long) K(wb_stat(wb, WB_DIRTIED)), + (unsigned long) K(wb_stat(wb, WB_WRITTEN)), + (unsigned long) K(wb->write_bandwidth), + nr_dirty, + nr_io, + nr_more_io, + nr_dirty_time, + !list_empty(&bdi->bdi_list), bdi->wb.state); +#undef K + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(bdi_debug_stats); + +static void bdi_debug_register(struct backing_dev_info *bdi, const char *name) +{ + bdi->debug_dir = debugfs_create_dir(name, bdi_debug_root); + + debugfs_create_file("stats", 0444, bdi->debug_dir, bdi, + &bdi_debug_stats_fops); +} + +static void bdi_debug_unregister(struct backing_dev_info *bdi) +{ + debugfs_remove_recursive(bdi->debug_dir); +} +#else +static inline void bdi_debug_init(void) +{ +} +static inline void bdi_debug_register(struct backing_dev_info *bdi, + const char *name) +{ +} +static inline void bdi_debug_unregister(struct backing_dev_info *bdi) +{ +} +#endif + +static ssize_t read_ahead_kb_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct backing_dev_info *bdi = dev_get_drvdata(dev); + unsigned long read_ahead_kb; + ssize_t ret; + + ret = kstrtoul(buf, 10, &read_ahead_kb); + if (ret < 0) + return ret; + + bdi->ra_pages = read_ahead_kb >> (PAGE_SHIFT - 10); + + return count; +} + +#define K(pages) ((pages) << (PAGE_SHIFT - 10)) + +#define BDI_SHOW(name, expr) \ +static ssize_t name##_show(struct device *dev, \ + struct device_attribute *attr, char *page) \ +{ \ + struct backing_dev_info *bdi = dev_get_drvdata(dev); \ + \ + return snprintf(page, PAGE_SIZE-1, "%lld\n", (long long)expr); \ +} \ +static DEVICE_ATTR_RW(name); + +BDI_SHOW(read_ahead_kb, K(bdi->ra_pages)) + +static ssize_t min_ratio_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + struct backing_dev_info *bdi = dev_get_drvdata(dev); + unsigned int ratio; + ssize_t ret; + + ret = kstrtouint(buf, 10, &ratio); + if (ret < 0) + return ret; + + ret = bdi_set_min_ratio(bdi, ratio); + if (!ret) + ret = count; + + return ret; +} +BDI_SHOW(min_ratio, bdi->min_ratio) + +static ssize_t max_ratio_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + struct backing_dev_info *bdi = dev_get_drvdata(dev); + unsigned int ratio; + ssize_t ret; + + ret = kstrtouint(buf, 10, &ratio); + if (ret < 0) + return ret; + + ret = bdi_set_max_ratio(bdi, ratio); + if (!ret) + ret = count; + + return ret; +} +BDI_SHOW(max_ratio, bdi->max_ratio) + +static ssize_t stable_pages_required_show(struct device *dev, + struct device_attribute *attr, + char *page) +{ + dev_warn_once(dev, + "the stable_pages_required attribute has been removed. Use the stable_writes queue attribute instead.\n"); + return snprintf(page, PAGE_SIZE-1, "%d\n", 0); +} +static DEVICE_ATTR_RO(stable_pages_required); + +static struct attribute *bdi_dev_attrs[] = { + &dev_attr_read_ahead_kb.attr, + &dev_attr_min_ratio.attr, + &dev_attr_max_ratio.attr, + &dev_attr_stable_pages_required.attr, + NULL, +}; +ATTRIBUTE_GROUPS(bdi_dev); + +static __init int bdi_class_init(void) +{ + bdi_class = class_create(THIS_MODULE, "bdi"); + if (IS_ERR(bdi_class)) + return PTR_ERR(bdi_class); + + bdi_class->dev_groups = bdi_dev_groups; + bdi_debug_init(); + + return 0; +} +postcore_initcall(bdi_class_init); + +static int bdi_init(struct backing_dev_info *bdi); + +static int __init default_bdi_init(void) +{ + int err; + + bdi_wq = alloc_workqueue("writeback", WQ_MEM_RECLAIM | WQ_UNBOUND | + WQ_SYSFS, 0); + if (!bdi_wq) + return -ENOMEM; + + err = bdi_init(&noop_backing_dev_info); + + return err; +} +subsys_initcall(default_bdi_init); + +/* + * This function is used when the first inode for this wb is marked dirty. It + * wakes-up the corresponding bdi thread which should then take care of the + * periodic background write-out of dirty inodes. Since the write-out would + * starts only 'dirty_writeback_interval' centisecs from now anyway, we just + * set up a timer which wakes the bdi thread up later. + * + * Note, we wouldn't bother setting up the timer, but this function is on the + * fast-path (used by '__mark_inode_dirty()'), so we save few context switches + * by delaying the wake-up. + * + * We have to be careful not to postpone flush work if it is scheduled for + * earlier. Thus we use queue_delayed_work(). + */ +void wb_wakeup_delayed(struct bdi_writeback *wb) +{ + unsigned long timeout; + + timeout = msecs_to_jiffies(dirty_writeback_interval * 10); + spin_lock_bh(&wb->work_lock); + if (test_bit(WB_registered, &wb->state)) + queue_delayed_work(bdi_wq, &wb->dwork, timeout); + spin_unlock_bh(&wb->work_lock); +} + +/* + * Initial write bandwidth: 100 MB/s + */ +#define INIT_BW (100 << (20 - PAGE_SHIFT)) + +static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, + gfp_t gfp) +{ + int i, err; + + memset(wb, 0, sizeof(*wb)); + + if (wb != &bdi->wb) + bdi_get(bdi); + wb->bdi = bdi; + wb->last_old_flush = jiffies; + INIT_LIST_HEAD(&wb->b_dirty); + INIT_LIST_HEAD(&wb->b_io); + INIT_LIST_HEAD(&wb->b_more_io); + INIT_LIST_HEAD(&wb->b_dirty_time); + spin_lock_init(&wb->list_lock); + + wb->bw_time_stamp = jiffies; + wb->balanced_dirty_ratelimit = INIT_BW; + wb->dirty_ratelimit = INIT_BW; + wb->write_bandwidth = INIT_BW; + wb->avg_write_bandwidth = INIT_BW; + + spin_lock_init(&wb->work_lock); + INIT_LIST_HEAD(&wb->work_list); + INIT_DELAYED_WORK(&wb->dwork, wb_workfn); + wb->dirty_sleep = jiffies; + + err = fprop_local_init_percpu(&wb->completions, gfp); + if (err) + goto out_put_bdi; + + for (i = 0; i < NR_WB_STAT_ITEMS; i++) { + err = percpu_counter_init(&wb->stat[i], 0, gfp); + if (err) + goto out_destroy_stat; + } + + return 0; + +out_destroy_stat: + while (i--) + percpu_counter_destroy(&wb->stat[i]); + fprop_local_destroy_percpu(&wb->completions); +out_put_bdi: + if (wb != &bdi->wb) + bdi_put(bdi); + return err; +} + +static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb); + +/* + * Remove bdi from the global list and shutdown any threads we have running + */ +static void wb_shutdown(struct bdi_writeback *wb) +{ + /* Make sure nobody queues further work */ + spin_lock_bh(&wb->work_lock); + if (!test_and_clear_bit(WB_registered, &wb->state)) { + spin_unlock_bh(&wb->work_lock); + return; + } + spin_unlock_bh(&wb->work_lock); + + cgwb_remove_from_bdi_list(wb); + /* + * Drain work list and shutdown the delayed_work. !WB_registered + * tells wb_workfn() that @wb is dying and its work_list needs to + * be drained no matter what. + */ + mod_delayed_work(bdi_wq, &wb->dwork, 0); + flush_delayed_work(&wb->dwork); + WARN_ON(!list_empty(&wb->work_list)); +} + +static void wb_exit(struct bdi_writeback *wb) +{ + int i; + + WARN_ON(delayed_work_pending(&wb->dwork)); + + for (i = 0; i < NR_WB_STAT_ITEMS; i++) + percpu_counter_destroy(&wb->stat[i]); + + fprop_local_destroy_percpu(&wb->completions); + if (wb != &wb->bdi->wb) + bdi_put(wb->bdi); +} + +#ifdef CONFIG_CGROUP_WRITEBACK + +#include + +/* + * cgwb_lock protects bdi->cgwb_tree, blkcg->cgwb_list, and memcg->cgwb_list. + * bdi->cgwb_tree is also RCU protected. + */ +static DEFINE_SPINLOCK(cgwb_lock); +static struct workqueue_struct *cgwb_release_wq; + +static void cgwb_free_rcu(struct rcu_head *rcu_head) +{ + struct bdi_writeback *wb = container_of(rcu_head, + struct bdi_writeback, rcu); + + percpu_ref_exit(&wb->refcnt); + kfree(wb); +} + +static void cgwb_release_workfn(struct work_struct *work) +{ + struct bdi_writeback *wb = container_of(work, struct bdi_writeback, + release_work); + struct blkcg *blkcg = css_to_blkcg(wb->blkcg_css); + + mutex_lock(&wb->bdi->cgwb_release_mutex); + wb_shutdown(wb); + + css_put(wb->memcg_css); + css_put(wb->blkcg_css); + mutex_unlock(&wb->bdi->cgwb_release_mutex); + + /* triggers blkg destruction if no online users left */ + blkcg_unpin_online(blkcg); + + fprop_local_destroy_percpu(&wb->memcg_completions); + wb_exit(wb); + call_rcu(&wb->rcu, cgwb_free_rcu); +} + +static void cgwb_release(struct percpu_ref *refcnt) +{ + struct bdi_writeback *wb = container_of(refcnt, struct bdi_writeback, + refcnt); + queue_work(cgwb_release_wq, &wb->release_work); +} + +static void cgwb_kill(struct bdi_writeback *wb) +{ + lockdep_assert_held(&cgwb_lock); + + WARN_ON(!radix_tree_delete(&wb->bdi->cgwb_tree, wb->memcg_css->id)); + list_del(&wb->memcg_node); + list_del(&wb->blkcg_node); + percpu_ref_kill(&wb->refcnt); +} + +static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb) +{ + spin_lock_irq(&cgwb_lock); + list_del_rcu(&wb->bdi_node); + spin_unlock_irq(&cgwb_lock); +} + +static int cgwb_create(struct backing_dev_info *bdi, + struct cgroup_subsys_state *memcg_css, gfp_t gfp) +{ + struct mem_cgroup *memcg; + struct cgroup_subsys_state *blkcg_css; + struct blkcg *blkcg; + struct list_head *memcg_cgwb_list, *blkcg_cgwb_list; + struct bdi_writeback *wb; + unsigned long flags; + int ret = 0; + + memcg = mem_cgroup_from_css(memcg_css); + blkcg_css = cgroup_get_e_css(memcg_css->cgroup, &io_cgrp_subsys); + blkcg = css_to_blkcg(blkcg_css); + memcg_cgwb_list = &memcg->cgwb_list; + blkcg_cgwb_list = &blkcg->cgwb_list; + + /* look up again under lock and discard on blkcg mismatch */ + spin_lock_irqsave(&cgwb_lock, flags); + wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); + if (wb && wb->blkcg_css != blkcg_css) { + cgwb_kill(wb); + wb = NULL; + } + spin_unlock_irqrestore(&cgwb_lock, flags); + if (wb) + goto out_put; + + /* need to create a new one */ + wb = kmalloc(sizeof(*wb), gfp); + if (!wb) { + ret = -ENOMEM; + goto out_put; + } + + ret = wb_init(wb, bdi, gfp); + if (ret) + goto err_free; + + ret = percpu_ref_init(&wb->refcnt, cgwb_release, 0, gfp); + if (ret) + goto err_wb_exit; + + ret = fprop_local_init_percpu(&wb->memcg_completions, gfp); + if (ret) + goto err_ref_exit; + + wb->memcg_css = memcg_css; + wb->blkcg_css = blkcg_css; + INIT_WORK(&wb->release_work, cgwb_release_workfn); + set_bit(WB_registered, &wb->state); + + /* + * The root wb determines the registered state of the whole bdi and + * memcg_cgwb_list and blkcg_cgwb_list's next pointers indicate + * whether they're still online. Don't link @wb if any is dead. + * See wb_memcg_offline() and wb_blkcg_offline(). + */ + ret = -ENODEV; + spin_lock_irqsave(&cgwb_lock, flags); + if (test_bit(WB_registered, &bdi->wb.state) && + blkcg_cgwb_list->next && memcg_cgwb_list->next) { + /* we might have raced another instance of this function */ + ret = radix_tree_insert(&bdi->cgwb_tree, memcg_css->id, wb); + if (!ret) { + list_add_tail_rcu(&wb->bdi_node, &bdi->wb_list); + list_add(&wb->memcg_node, memcg_cgwb_list); + list_add(&wb->blkcg_node, blkcg_cgwb_list); + blkcg_pin_online(blkcg); + css_get(memcg_css); + css_get(blkcg_css); + } + } + spin_unlock_irqrestore(&cgwb_lock, flags); + if (ret) { + if (ret == -EEXIST) + ret = 0; + goto err_fprop_exit; + } + goto out_put; + +err_fprop_exit: + fprop_local_destroy_percpu(&wb->memcg_completions); +err_ref_exit: + percpu_ref_exit(&wb->refcnt); +err_wb_exit: + wb_exit(wb); +err_free: + kfree(wb); +out_put: + css_put(blkcg_css); + return ret; +} + +/** + * wb_get_lookup - get wb for a given memcg + * @bdi: target bdi + * @memcg_css: cgroup_subsys_state of the target memcg (must have positive ref) + * + * Try to get the wb for @memcg_css on @bdi. The returned wb has its + * refcount incremented. + * + * This function uses css_get() on @memcg_css and thus expects its refcnt + * to be positive on invocation. IOW, rcu_read_lock() protection on + * @memcg_css isn't enough. try_get it before calling this function. + * + * A wb is keyed by its associated memcg. As blkcg implicitly enables + * memcg on the default hierarchy, memcg association is guaranteed to be + * more specific (equal or descendant to the associated blkcg) and thus can + * identify both the memcg and blkcg associations. + * + * Because the blkcg associated with a memcg may change as blkcg is enabled + * and disabled closer to root in the hierarchy, each wb keeps track of + * both the memcg and blkcg associated with it and verifies the blkcg on + * each lookup. On mismatch, the existing wb is discarded and a new one is + * created. + */ +struct bdi_writeback *wb_get_lookup(struct backing_dev_info *bdi, + struct cgroup_subsys_state *memcg_css) +{ + struct bdi_writeback *wb; + + if (!memcg_css->parent) + return &bdi->wb; + + rcu_read_lock(); + wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); + if (wb) { + struct cgroup_subsys_state *blkcg_css; + + /* see whether the blkcg association has changed */ + blkcg_css = cgroup_get_e_css(memcg_css->cgroup, &io_cgrp_subsys); + if (unlikely(wb->blkcg_css != blkcg_css || !wb_tryget(wb))) + wb = NULL; + css_put(blkcg_css); + } + rcu_read_unlock(); + + return wb; +} + +/** + * wb_get_create - get wb for a given memcg, create if necessary + * @bdi: target bdi + * @memcg_css: cgroup_subsys_state of the target memcg (must have positive ref) + * @gfp: allocation mask to use + * + * Try to get the wb for @memcg_css on @bdi. If it doesn't exist, try to + * create one. See wb_get_lookup() for more details. + */ +struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, + struct cgroup_subsys_state *memcg_css, + gfp_t gfp) +{ + struct bdi_writeback *wb; + + might_sleep_if(gfpflags_allow_blocking(gfp)); + + if (!memcg_css->parent) + return &bdi->wb; + + do { + wb = wb_get_lookup(bdi, memcg_css); + } while (!wb && !cgwb_create(bdi, memcg_css, gfp)); + + return wb; +} + +static int cgwb_bdi_init(struct backing_dev_info *bdi) +{ + int ret; + + INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC); + mutex_init(&bdi->cgwb_release_mutex); + init_rwsem(&bdi->wb_switch_rwsem); + + ret = wb_init(&bdi->wb, bdi, GFP_KERNEL); + if (!ret) { + bdi->wb.memcg_css = &root_mem_cgroup->css; + bdi->wb.blkcg_css = blkcg_root_css; + } + return ret; +} + +static void cgwb_bdi_unregister(struct backing_dev_info *bdi) +{ + struct radix_tree_iter iter; + void **slot; + struct bdi_writeback *wb; + + WARN_ON(test_bit(WB_registered, &bdi->wb.state)); + + spin_lock_irq(&cgwb_lock); + radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0) + cgwb_kill(*slot); + spin_unlock_irq(&cgwb_lock); + + mutex_lock(&bdi->cgwb_release_mutex); + spin_lock_irq(&cgwb_lock); + while (!list_empty(&bdi->wb_list)) { + wb = list_first_entry(&bdi->wb_list, struct bdi_writeback, + bdi_node); + spin_unlock_irq(&cgwb_lock); + wb_shutdown(wb); + spin_lock_irq(&cgwb_lock); + } + spin_unlock_irq(&cgwb_lock); + mutex_unlock(&bdi->cgwb_release_mutex); +} + +/** + * wb_memcg_offline - kill all wb's associated with a memcg being offlined + * @memcg: memcg being offlined + * + * Also prevents creation of any new wb's associated with @memcg. + */ +void wb_memcg_offline(struct mem_cgroup *memcg) +{ + struct list_head *memcg_cgwb_list = &memcg->cgwb_list; + struct bdi_writeback *wb, *next; + + spin_lock_irq(&cgwb_lock); + list_for_each_entry_safe(wb, next, memcg_cgwb_list, memcg_node) + cgwb_kill(wb); + memcg_cgwb_list->next = NULL; /* prevent new wb's */ + spin_unlock_irq(&cgwb_lock); +} + +/** + * wb_blkcg_offline - kill all wb's associated with a blkcg being offlined + * @blkcg: blkcg being offlined + * + * Also prevents creation of any new wb's associated with @blkcg. + */ +void wb_blkcg_offline(struct blkcg *blkcg) +{ + struct bdi_writeback *wb, *next; + + spin_lock_irq(&cgwb_lock); + list_for_each_entry_safe(wb, next, &blkcg->cgwb_list, blkcg_node) + cgwb_kill(wb); + blkcg->cgwb_list.next = NULL; /* prevent new wb's */ + spin_unlock_irq(&cgwb_lock); +} + +static void cgwb_bdi_register(struct backing_dev_info *bdi) +{ + spin_lock_irq(&cgwb_lock); + list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list); + spin_unlock_irq(&cgwb_lock); +} + +static int __init cgwb_init(void) +{ + /* + * There can be many concurrent release work items overwhelming + * system_wq. Put them in a separate wq and limit concurrency. + * There's no point in executing many of these in parallel. + */ + cgwb_release_wq = alloc_workqueue("cgwb_release", 0, 1); + if (!cgwb_release_wq) + return -ENOMEM; + + return 0; +} +subsys_initcall(cgwb_init); + +#else /* CONFIG_CGROUP_WRITEBACK */ + +static int cgwb_bdi_init(struct backing_dev_info *bdi) +{ + return wb_init(&bdi->wb, bdi, GFP_KERNEL); +} + +static void cgwb_bdi_unregister(struct backing_dev_info *bdi) { } + +static void cgwb_bdi_register(struct backing_dev_info *bdi) +{ + list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list); +} + +static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb) +{ + list_del_rcu(&wb->bdi_node); +} + +#endif /* CONFIG_CGROUP_WRITEBACK */ + +static int bdi_init(struct backing_dev_info *bdi) +{ + int ret; + + bdi->dev = NULL; + + kref_init(&bdi->refcnt); + bdi->min_ratio = 0; + bdi->max_ratio = 100; + bdi->max_prop_frac = FPROP_FRAC_BASE; + INIT_LIST_HEAD(&bdi->bdi_list); + INIT_LIST_HEAD(&bdi->wb_list); + init_waitqueue_head(&bdi->wb_waitq); + + ret = cgwb_bdi_init(bdi); + + return ret; +} + +struct backing_dev_info *bdi_alloc(int node_id) +{ + struct backing_dev_info *bdi; + + bdi = kzalloc_node(sizeof(*bdi), GFP_KERNEL, node_id); + if (!bdi) + return NULL; + + if (bdi_init(bdi)) { + kfree(bdi); + return NULL; + } + bdi->capabilities = BDI_CAP_WRITEBACK | BDI_CAP_WRITEBACK_ACCT; + bdi->ra_pages = VM_READAHEAD_PAGES; + bdi->io_pages = VM_READAHEAD_PAGES; + return bdi; +} +EXPORT_SYMBOL(bdi_alloc); + +static struct rb_node **bdi_lookup_rb_node(u64 id, struct rb_node **parentp) +{ + struct rb_node **p = &bdi_tree.rb_node; + struct rb_node *parent = NULL; + struct backing_dev_info *bdi; + + lockdep_assert_held(&bdi_lock); + + while (*p) { + parent = *p; + bdi = rb_entry(parent, struct backing_dev_info, rb_node); + + if (bdi->id > id) + p = &(*p)->rb_left; + else if (bdi->id < id) + p = &(*p)->rb_right; + else + break; + } + + if (parentp) + *parentp = parent; + return p; +} + +/** + * bdi_get_by_id - lookup and get bdi from its id + * @id: bdi id to lookup + * + * Find bdi matching @id and get it. Returns NULL if the matching bdi + * doesn't exist or is already unregistered. + */ +struct backing_dev_info *bdi_get_by_id(u64 id) +{ + struct backing_dev_info *bdi = NULL; + struct rb_node **p; + + spin_lock_bh(&bdi_lock); + p = bdi_lookup_rb_node(id, NULL); + if (*p) { + bdi = rb_entry(*p, struct backing_dev_info, rb_node); + bdi_get(bdi); + } + spin_unlock_bh(&bdi_lock); + + return bdi; +} + +int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args) +{ + struct device *dev; + struct rb_node *parent, **p; + + if (bdi->dev) /* The driver needs to use separate queues per device */ + return 0; + + vsnprintf(bdi->dev_name, sizeof(bdi->dev_name), fmt, args); + dev = device_create(bdi_class, NULL, MKDEV(0, 0), bdi, bdi->dev_name); + if (IS_ERR(dev)) + return PTR_ERR(dev); + + cgwb_bdi_register(bdi); + bdi->dev = dev; + + bdi_debug_register(bdi, dev_name(dev)); + set_bit(WB_registered, &bdi->wb.state); + + spin_lock_bh(&bdi_lock); + + bdi->id = ++bdi_id_cursor; + + p = bdi_lookup_rb_node(bdi->id, &parent); + rb_link_node(&bdi->rb_node, parent, p); + rb_insert_color(&bdi->rb_node, &bdi_tree); + + list_add_tail_rcu(&bdi->bdi_list, &bdi_list); + + spin_unlock_bh(&bdi_lock); + + trace_writeback_bdi_register(bdi); + return 0; +} + +int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...) +{ + va_list args; + int ret; + + va_start(args, fmt); + ret = bdi_register_va(bdi, fmt, args); + va_end(args); + return ret; +} +EXPORT_SYMBOL(bdi_register); + +void bdi_set_owner(struct backing_dev_info *bdi, struct device *owner) +{ + WARN_ON_ONCE(bdi->owner); + bdi->owner = owner; + get_device(owner); +} + +/* + * Remove bdi from bdi_list, and ensure that it is no longer visible + */ +static void bdi_remove_from_list(struct backing_dev_info *bdi) +{ + spin_lock_bh(&bdi_lock); + rb_erase(&bdi->rb_node, &bdi_tree); + list_del_rcu(&bdi->bdi_list); + spin_unlock_bh(&bdi_lock); + + synchronize_rcu_expedited(); +} + +void bdi_unregister(struct backing_dev_info *bdi) +{ + /* make sure nobody finds us on the bdi_list anymore */ + bdi_remove_from_list(bdi); + wb_shutdown(&bdi->wb); + cgwb_bdi_unregister(bdi); + + /* + * If this BDI's min ratio has been set, use bdi_set_min_ratio() to + * update the global bdi_min_ratio. + */ + if (bdi->min_ratio) + bdi_set_min_ratio(bdi, 0); + + if (bdi->dev) { + bdi_debug_unregister(bdi); + device_unregister(bdi->dev); + bdi->dev = NULL; + } + + if (bdi->owner) { + put_device(bdi->owner); + bdi->owner = NULL; + } +} + +static void release_bdi(struct kref *ref) +{ + struct backing_dev_info *bdi = + container_of(ref, struct backing_dev_info, refcnt); + + if (test_bit(WB_registered, &bdi->wb.state)) + bdi_unregister(bdi); + WARN_ON_ONCE(bdi->dev); + wb_exit(&bdi->wb); + kfree(bdi); +} + +void bdi_put(struct backing_dev_info *bdi) +{ + kref_put(&bdi->refcnt, release_bdi); +} +EXPORT_SYMBOL(bdi_put); + +const char *bdi_dev_name(struct backing_dev_info *bdi) +{ + if (!bdi || !bdi->dev) + return bdi_unknown_name; + return bdi->dev_name; +} +EXPORT_SYMBOL_GPL(bdi_dev_name); + +static wait_queue_head_t congestion_wqh[2] = { + __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]), + __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1]) + }; +static atomic_t nr_wb_congested[2]; + +void clear_bdi_congested(struct backing_dev_info *bdi, int sync) +{ + wait_queue_head_t *wqh = &congestion_wqh[sync]; + enum wb_congested_state bit; + + bit = sync ? WB_sync_congested : WB_async_congested; + if (test_and_clear_bit(bit, &bdi->wb.congested)) + atomic_dec(&nr_wb_congested[sync]); + smp_mb__after_atomic(); + if (waitqueue_active(wqh)) + wake_up(wqh); +} +EXPORT_SYMBOL(clear_bdi_congested); + +void set_bdi_congested(struct backing_dev_info *bdi, int sync) +{ + enum wb_congested_state bit; + + bit = sync ? WB_sync_congested : WB_async_congested; + if (!test_and_set_bit(bit, &bdi->wb.congested)) + atomic_inc(&nr_wb_congested[sync]); +} +EXPORT_SYMBOL(set_bdi_congested); + +/** + * congestion_wait - wait for a backing_dev to become uncongested + * @sync: SYNC or ASYNC IO + * @timeout: timeout in jiffies + * + * Waits for up to @timeout jiffies for a backing_dev (any backing_dev) to exit + * write congestion. If no backing_devs are congested then just wait for the + * next write to be completed. + */ +long congestion_wait(int sync, long timeout) +{ + long ret; + unsigned long start = jiffies; + DEFINE_WAIT(wait); + wait_queue_head_t *wqh = &congestion_wqh[sync]; + + prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); + ret = io_schedule_timeout(timeout); + finish_wait(wqh, &wait); + + trace_writeback_congestion_wait(jiffies_to_usecs(timeout), + jiffies_to_usecs(jiffies - start)); + + return ret; +} +EXPORT_SYMBOL(congestion_wait); + +/** + * wait_iff_congested - Conditionally wait for a backing_dev to become uncongested or a pgdat to complete writes + * @sync: SYNC or ASYNC IO + * @timeout: timeout in jiffies + * + * In the event of a congested backing_dev (any backing_dev) this waits + * for up to @timeout jiffies for either a BDI to exit congestion of the + * given @sync queue or a write to complete. + * + * The return value is 0 if the sleep is for the full timeout. Otherwise, + * it is the number of jiffies that were still remaining when the function + * returned. return_value == timeout implies the function did not sleep. + */ +long wait_iff_congested(int sync, long timeout) +{ + long ret; + unsigned long start = jiffies; + DEFINE_WAIT(wait); + wait_queue_head_t *wqh = &congestion_wqh[sync]; + + /* + * If there is no congestion, yield if necessary instead + * of sleeping on the congestion queue + */ + if (atomic_read(&nr_wb_congested[sync]) == 0) { + cond_resched(); + + /* In case we scheduled, work out time remaining */ + ret = timeout - (jiffies - start); + if (ret < 0) + ret = 0; + + goto out; + } + + /* Sleep until uncongested or a write happens */ + prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); + ret = io_schedule_timeout(timeout); + finish_wait(wqh, &wait); + +out: + trace_writeback_wait_iff_congested(jiffies_to_usecs(timeout), + jiffies_to_usecs(jiffies - start)); + + return ret; +} +EXPORT_SYMBOL(wait_iff_congested); diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c new file mode 100644 index 000000000..26de020aa --- /dev/null +++ b/mm/balloon_compaction.c @@ -0,0 +1,260 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * mm/balloon_compaction.c + * + * Common interface for making balloon pages movable by compaction. + * + * Copyright (C) 2012, Red Hat, Inc. Rafael Aquini + */ +#include +#include +#include +#include + +static void balloon_page_enqueue_one(struct balloon_dev_info *b_dev_info, + struct page *page) +{ + /* + * Block others from accessing the 'page' when we get around to + * establishing additional references. We should be the only one + * holding a reference to the 'page' at this point. If we are not, then + * memory corruption is possible and we should stop execution. + */ + BUG_ON(!trylock_page(page)); + balloon_page_insert(b_dev_info, page); + unlock_page(page); + __count_vm_event(BALLOON_INFLATE); +} + +/** + * balloon_page_list_enqueue() - inserts a list of pages into the balloon page + * list. + * @b_dev_info: balloon device descriptor where we will insert a new page to + * @pages: pages to enqueue - allocated using balloon_page_alloc. + * + * Driver must call this function to properly enqueue balloon pages before + * definitively removing them from the guest system. + * + * Return: number of pages that were enqueued. + */ +size_t balloon_page_list_enqueue(struct balloon_dev_info *b_dev_info, + struct list_head *pages) +{ + struct page *page, *tmp; + unsigned long flags; + size_t n_pages = 0; + + spin_lock_irqsave(&b_dev_info->pages_lock, flags); + list_for_each_entry_safe(page, tmp, pages, lru) { + list_del(&page->lru); + balloon_page_enqueue_one(b_dev_info, page); + n_pages++; + } + spin_unlock_irqrestore(&b_dev_info->pages_lock, flags); + return n_pages; +} +EXPORT_SYMBOL_GPL(balloon_page_list_enqueue); + +/** + * balloon_page_list_dequeue() - removes pages from balloon's page list and + * returns a list of the pages. + * @b_dev_info: balloon device decriptor where we will grab a page from. + * @pages: pointer to the list of pages that would be returned to the caller. + * @n_req_pages: number of requested pages. + * + * Driver must call this function to properly de-allocate a previous enlisted + * balloon pages before definitively releasing it back to the guest system. + * This function tries to remove @n_req_pages from the ballooned pages and + * return them to the caller in the @pages list. + * + * Note that this function may fail to dequeue some pages even if the balloon + * isn't empty - since the page list can be temporarily empty due to compaction + * of isolated pages. + * + * Return: number of pages that were added to the @pages list. + */ +size_t balloon_page_list_dequeue(struct balloon_dev_info *b_dev_info, + struct list_head *pages, size_t n_req_pages) +{ + struct page *page, *tmp; + unsigned long flags; + size_t n_pages = 0; + + spin_lock_irqsave(&b_dev_info->pages_lock, flags); + list_for_each_entry_safe(page, tmp, &b_dev_info->pages, lru) { + if (n_pages == n_req_pages) + break; + + /* + * Block others from accessing the 'page' while we get around to + * establishing additional references and preparing the 'page' + * to be released by the balloon driver. + */ + if (!trylock_page(page)) + continue; + + if (IS_ENABLED(CONFIG_BALLOON_COMPACTION) && + PageIsolated(page)) { + /* raced with isolation */ + unlock_page(page); + continue; + } + balloon_page_delete(page); + __count_vm_event(BALLOON_DEFLATE); + list_add(&page->lru, pages); + unlock_page(page); + n_pages++; + } + spin_unlock_irqrestore(&b_dev_info->pages_lock, flags); + + return n_pages; +} +EXPORT_SYMBOL_GPL(balloon_page_list_dequeue); + +/* + * balloon_page_alloc - allocates a new page for insertion into the balloon + * page list. + * + * Driver must call this function to properly allocate a new balloon page. + * Driver must call balloon_page_enqueue before definitively removing the page + * from the guest system. + * + * Return: struct page for the allocated page or NULL on allocation failure. + */ +struct page *balloon_page_alloc(void) +{ + struct page *page = alloc_page(balloon_mapping_gfp_mask() | + __GFP_NOMEMALLOC | __GFP_NORETRY | + __GFP_NOWARN); + return page; +} +EXPORT_SYMBOL_GPL(balloon_page_alloc); + +/* + * balloon_page_enqueue - inserts a new page into the balloon page list. + * + * @b_dev_info: balloon device descriptor where we will insert a new page + * @page: new page to enqueue - allocated using balloon_page_alloc. + * + * Drivers must call this function to properly enqueue a new allocated balloon + * page before definitively removing the page from the guest system. + * + * Drivers must not call balloon_page_enqueue on pages that have been pushed to + * a list with balloon_page_push before removing them with balloon_page_pop. To + * enqueue a list of pages, use balloon_page_list_enqueue instead. + */ +void balloon_page_enqueue(struct balloon_dev_info *b_dev_info, + struct page *page) +{ + unsigned long flags; + + spin_lock_irqsave(&b_dev_info->pages_lock, flags); + balloon_page_enqueue_one(b_dev_info, page); + spin_unlock_irqrestore(&b_dev_info->pages_lock, flags); +} +EXPORT_SYMBOL_GPL(balloon_page_enqueue); + +/* + * balloon_page_dequeue - removes a page from balloon's page list and returns + * its address to allow the driver to release the page. + * @b_dev_info: balloon device decriptor where we will grab a page from. + * + * Driver must call this function to properly dequeue a previously enqueued page + * before definitively releasing it back to the guest system. + * + * Caller must perform its own accounting to ensure that this + * function is called only if some pages are actually enqueued. + * + * Note that this function may fail to dequeue some pages even if there are + * some enqueued pages - since the page list can be temporarily empty due to + * the compaction of isolated pages. + * + * TODO: remove the caller accounting requirements, and allow caller to wait + * until all pages can be dequeued. + * + * Return: struct page for the dequeued page, or NULL if no page was dequeued. + */ +struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info) +{ + unsigned long flags; + LIST_HEAD(pages); + int n_pages; + + n_pages = balloon_page_list_dequeue(b_dev_info, &pages, 1); + + if (n_pages != 1) { + /* + * If we are unable to dequeue a balloon page because the page + * list is empty and there are no isolated pages, then something + * went out of track and some balloon pages are lost. + * BUG() here, otherwise the balloon driver may get stuck in + * an infinite loop while attempting to release all its pages. + */ + spin_lock_irqsave(&b_dev_info->pages_lock, flags); + if (unlikely(list_empty(&b_dev_info->pages) && + !b_dev_info->isolated_pages)) + BUG(); + spin_unlock_irqrestore(&b_dev_info->pages_lock, flags); + return NULL; + } + return list_first_entry(&pages, struct page, lru); +} +EXPORT_SYMBOL_GPL(balloon_page_dequeue); + +#ifdef CONFIG_BALLOON_COMPACTION + +bool balloon_page_isolate(struct page *page, isolate_mode_t mode) + +{ + struct balloon_dev_info *b_dev_info = balloon_page_device(page); + unsigned long flags; + + spin_lock_irqsave(&b_dev_info->pages_lock, flags); + list_del(&page->lru); + b_dev_info->isolated_pages++; + spin_unlock_irqrestore(&b_dev_info->pages_lock, flags); + + return true; +} + +void balloon_page_putback(struct page *page) +{ + struct balloon_dev_info *b_dev_info = balloon_page_device(page); + unsigned long flags; + + spin_lock_irqsave(&b_dev_info->pages_lock, flags); + list_add(&page->lru, &b_dev_info->pages); + b_dev_info->isolated_pages--; + spin_unlock_irqrestore(&b_dev_info->pages_lock, flags); +} + + +/* move_to_new_page() counterpart for a ballooned page */ +int balloon_page_migrate(struct address_space *mapping, + struct page *newpage, struct page *page, + enum migrate_mode mode) +{ + struct balloon_dev_info *balloon = balloon_page_device(page); + + /* + * We can not easily support the no copy case here so ignore it as it + * is unlikely to be used with balloon pages. See include/linux/hmm.h + * for a user of the MIGRATE_SYNC_NO_COPY mode. + */ + if (mode == MIGRATE_SYNC_NO_COPY) + return -EINVAL; + + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(!PageLocked(newpage), newpage); + + return balloon->migratepage(balloon, newpage, page, mode); +} + +const struct address_space_operations balloon_aops = { + .migratepage = balloon_page_migrate, + .isolate_page = balloon_page_isolate, + .putback_page = balloon_page_putback, +}; +EXPORT_SYMBOL_GPL(balloon_aops); + +#endif /* CONFIG_BALLOON_COMPACTION */ diff --git a/mm/cleancache.c b/mm/cleancache.c new file mode 100644 index 000000000..db7eee9c0 --- /dev/null +++ b/mm/cleancache.c @@ -0,0 +1,315 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Cleancache frontend + * + * This code provides the generic "frontend" layer to call a matching + * "backend" driver implementation of cleancache. See + * Documentation/vm/cleancache.rst for more information. + * + * Copyright (C) 2009-2010 Oracle Corp. All rights reserved. + * Author: Dan Magenheimer + */ + +#include +#include +#include +#include +#include +#include + +/* + * cleancache_ops is set by cleancache_register_ops to contain the pointers + * to the cleancache "backend" implementation functions. + */ +static const struct cleancache_ops *cleancache_ops __read_mostly; + +/* + * Counters available via /sys/kernel/debug/cleancache (if debugfs is + * properly configured. These are for information only so are not protected + * against increment races. + */ +static u64 cleancache_succ_gets; +static u64 cleancache_failed_gets; +static u64 cleancache_puts; +static u64 cleancache_invalidates; + +static void cleancache_register_ops_sb(struct super_block *sb, void *unused) +{ + switch (sb->cleancache_poolid) { + case CLEANCACHE_NO_BACKEND: + __cleancache_init_fs(sb); + break; + case CLEANCACHE_NO_BACKEND_SHARED: + __cleancache_init_shared_fs(sb); + break; + } +} + +/* + * Register operations for cleancache. Returns 0 on success. + */ +int cleancache_register_ops(const struct cleancache_ops *ops) +{ + if (cmpxchg(&cleancache_ops, NULL, ops)) + return -EBUSY; + + /* + * A cleancache backend can be built as a module and hence loaded after + * a cleancache enabled filesystem has called cleancache_init_fs. To + * handle such a scenario, here we call ->init_fs or ->init_shared_fs + * for each active super block. To differentiate between local and + * shared filesystems, we temporarily initialize sb->cleancache_poolid + * to CLEANCACHE_NO_BACKEND or CLEANCACHE_NO_BACKEND_SHARED + * respectively in case there is no backend registered at the time + * cleancache_init_fs or cleancache_init_shared_fs is called. + * + * Since filesystems can be mounted concurrently with cleancache + * backend registration, we have to be careful to guarantee that all + * cleancache enabled filesystems that has been mounted by the time + * cleancache_register_ops is called has got and all mounted later will + * get cleancache_poolid. This is assured by the following statements + * tied together: + * + * a) iterate_supers skips only those super blocks that has started + * ->kill_sb + * + * b) if iterate_supers encounters a super block that has not finished + * ->mount yet, it waits until it is finished + * + * c) cleancache_init_fs is called from ->mount and + * cleancache_invalidate_fs is called from ->kill_sb + * + * d) we call iterate_supers after cleancache_ops has been set + * + * From a) it follows that if iterate_supers skips a super block, then + * either the super block is already dead, in which case we do not need + * to bother initializing cleancache for it, or it was mounted after we + * initiated iterate_supers. In the latter case, it must have seen + * cleancache_ops set according to d) and initialized cleancache from + * ->mount by itself according to c). This proves that we call + * ->init_fs at least once for each active super block. + * + * From b) and c) it follows that if iterate_supers encounters a super + * block that has already started ->init_fs, it will wait until ->mount + * and hence ->init_fs has finished, then check cleancache_poolid, see + * that it has already been set and therefore do nothing. This proves + * that we call ->init_fs no more than once for each super block. + * + * Combined together, the last two paragraphs prove the function + * correctness. + * + * Note that various cleancache callbacks may proceed before this + * function is called or even concurrently with it, but since + * CLEANCACHE_NO_BACKEND is negative, they will all result in a noop + * until the corresponding ->init_fs has been actually called and + * cleancache_ops has been set. + */ + iterate_supers(cleancache_register_ops_sb, NULL); + return 0; +} +EXPORT_SYMBOL(cleancache_register_ops); + +/* Called by a cleancache-enabled filesystem at time of mount */ +void __cleancache_init_fs(struct super_block *sb) +{ + int pool_id = CLEANCACHE_NO_BACKEND; + + if (cleancache_ops) { + pool_id = cleancache_ops->init_fs(PAGE_SIZE); + if (pool_id < 0) + pool_id = CLEANCACHE_NO_POOL; + } + sb->cleancache_poolid = pool_id; +} +EXPORT_SYMBOL(__cleancache_init_fs); + +/* Called by a cleancache-enabled clustered filesystem at time of mount */ +void __cleancache_init_shared_fs(struct super_block *sb) +{ + int pool_id = CLEANCACHE_NO_BACKEND_SHARED; + + if (cleancache_ops) { + pool_id = cleancache_ops->init_shared_fs(&sb->s_uuid, PAGE_SIZE); + if (pool_id < 0) + pool_id = CLEANCACHE_NO_POOL; + } + sb->cleancache_poolid = pool_id; +} +EXPORT_SYMBOL(__cleancache_init_shared_fs); + +/* + * If the filesystem uses exportable filehandles, use the filehandle as + * the key, else use the inode number. + */ +static int cleancache_get_key(struct inode *inode, + struct cleancache_filekey *key) +{ + int (*fhfn)(struct inode *, __u32 *fh, int *, struct inode *); + int len = 0, maxlen = CLEANCACHE_KEY_MAX; + struct super_block *sb = inode->i_sb; + + key->u.ino = inode->i_ino; + if (sb->s_export_op != NULL) { + fhfn = sb->s_export_op->encode_fh; + if (fhfn) { + len = (*fhfn)(inode, &key->u.fh[0], &maxlen, NULL); + if (len <= FILEID_ROOT || len == FILEID_INVALID) + return -1; + if (maxlen > CLEANCACHE_KEY_MAX) + return -1; + } + } + return 0; +} + +/* + * "Get" data from cleancache associated with the poolid/inode/index + * that were specified when the data was put to cleanache and, if + * successful, use it to fill the specified page with data and return 0. + * The pageframe is unchanged and returns -1 if the get fails. + * Page must be locked by caller. + * + * The function has two checks before any action is taken - whether + * a backend is registered and whether the sb->cleancache_poolid + * is correct. + */ +int __cleancache_get_page(struct page *page) +{ + int ret = -1; + int pool_id; + struct cleancache_filekey key = { .u.key = { 0 } }; + + if (!cleancache_ops) { + cleancache_failed_gets++; + goto out; + } + + VM_BUG_ON_PAGE(!PageLocked(page), page); + pool_id = page->mapping->host->i_sb->cleancache_poolid; + if (pool_id < 0) + goto out; + + if (cleancache_get_key(page->mapping->host, &key) < 0) + goto out; + + ret = cleancache_ops->get_page(pool_id, key, page->index, page); + if (ret == 0) + cleancache_succ_gets++; + else + cleancache_failed_gets++; +out: + return ret; +} +EXPORT_SYMBOL(__cleancache_get_page); + +/* + * "Put" data from a page to cleancache and associate it with the + * (previously-obtained per-filesystem) poolid and the page's, + * inode and page index. Page must be locked. Note that a put_page + * always "succeeds", though a subsequent get_page may succeed or fail. + * + * The function has two checks before any action is taken - whether + * a backend is registered and whether the sb->cleancache_poolid + * is correct. + */ +void __cleancache_put_page(struct page *page) +{ + int pool_id; + struct cleancache_filekey key = { .u.key = { 0 } }; + + if (!cleancache_ops) { + cleancache_puts++; + return; + } + + VM_BUG_ON_PAGE(!PageLocked(page), page); + pool_id = page->mapping->host->i_sb->cleancache_poolid; + if (pool_id >= 0 && + cleancache_get_key(page->mapping->host, &key) >= 0) { + cleancache_ops->put_page(pool_id, key, page->index, page); + cleancache_puts++; + } +} +EXPORT_SYMBOL(__cleancache_put_page); + +/* + * Invalidate any data from cleancache associated with the poolid and the + * page's inode and page index so that a subsequent "get" will fail. + * + * The function has two checks before any action is taken - whether + * a backend is registered and whether the sb->cleancache_poolid + * is correct. + */ +void __cleancache_invalidate_page(struct address_space *mapping, + struct page *page) +{ + /* careful... page->mapping is NULL sometimes when this is called */ + int pool_id = mapping->host->i_sb->cleancache_poolid; + struct cleancache_filekey key = { .u.key = { 0 } }; + + if (!cleancache_ops) + return; + + if (pool_id >= 0) { + VM_BUG_ON_PAGE(!PageLocked(page), page); + if (cleancache_get_key(mapping->host, &key) >= 0) { + cleancache_ops->invalidate_page(pool_id, + key, page->index); + cleancache_invalidates++; + } + } +} +EXPORT_SYMBOL(__cleancache_invalidate_page); + +/* + * Invalidate all data from cleancache associated with the poolid and the + * mappings's inode so that all subsequent gets to this poolid/inode + * will fail. + * + * The function has two checks before any action is taken - whether + * a backend is registered and whether the sb->cleancache_poolid + * is correct. + */ +void __cleancache_invalidate_inode(struct address_space *mapping) +{ + int pool_id = mapping->host->i_sb->cleancache_poolid; + struct cleancache_filekey key = { .u.key = { 0 } }; + + if (!cleancache_ops) + return; + + if (pool_id >= 0 && cleancache_get_key(mapping->host, &key) >= 0) + cleancache_ops->invalidate_inode(pool_id, key); +} +EXPORT_SYMBOL(__cleancache_invalidate_inode); + +/* + * Called by any cleancache-enabled filesystem at time of unmount; + * note that pool_id is surrendered and may be returned by a subsequent + * cleancache_init_fs or cleancache_init_shared_fs. + */ +void __cleancache_invalidate_fs(struct super_block *sb) +{ + int pool_id; + + pool_id = sb->cleancache_poolid; + sb->cleancache_poolid = CLEANCACHE_NO_POOL; + + if (cleancache_ops && pool_id >= 0) + cleancache_ops->invalidate_fs(pool_id); +} +EXPORT_SYMBOL(__cleancache_invalidate_fs); + +static int __init init_cleancache(void) +{ +#ifdef CONFIG_DEBUG_FS + struct dentry *root = debugfs_create_dir("cleancache", NULL); + + debugfs_create_u64("succ_gets", 0444, root, &cleancache_succ_gets); + debugfs_create_u64("failed_gets", 0444, root, &cleancache_failed_gets); + debugfs_create_u64("puts", 0444, root, &cleancache_puts); + debugfs_create_u64("invalidates", 0444, root, &cleancache_invalidates); +#endif + return 0; +} +module_init(init_cleancache) diff --git a/mm/cma.c b/mm/cma.c new file mode 100644 index 000000000..3c3f1436f --- /dev/null +++ b/mm/cma.c @@ -0,0 +1,543 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Contiguous Memory Allocator + * + * Copyright (c) 2010-2011 by Samsung Electronics. + * Copyright IBM Corporation, 2013 + * Copyright LG Electronics Inc., 2014 + * Written by: + * Marek Szyprowski + * Michal Nazarewicz + * Aneesh Kumar K.V + * Joonsoo Kim + */ + +#define pr_fmt(fmt) "cma: " fmt + +#ifdef CONFIG_CMA_DEBUG +#ifndef DEBUG +# define DEBUG +#endif +#endif +#define CREATE_TRACE_POINTS + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "cma.h" + +struct cma cma_areas[MAX_CMA_AREAS]; +unsigned cma_area_count; +static DEFINE_MUTEX(cma_mutex); + +phys_addr_t cma_get_base(const struct cma *cma) +{ + return PFN_PHYS(cma->base_pfn); +} + +unsigned long cma_get_size(const struct cma *cma) +{ + return cma->count << PAGE_SHIFT; +} + +const char *cma_get_name(const struct cma *cma) +{ + return cma->name; +} + +static unsigned long cma_bitmap_aligned_mask(const struct cma *cma, + unsigned int align_order) +{ + if (align_order <= cma->order_per_bit) + return 0; + return (1UL << (align_order - cma->order_per_bit)) - 1; +} + +/* + * Find the offset of the base PFN from the specified align_order. + * The value returned is represented in order_per_bits. + */ +static unsigned long cma_bitmap_aligned_offset(const struct cma *cma, + unsigned int align_order) +{ + return (cma->base_pfn & ((1UL << align_order) - 1)) + >> cma->order_per_bit; +} + +static unsigned long cma_bitmap_pages_to_bits(const struct cma *cma, + unsigned long pages) +{ + return ALIGN(pages, 1UL << cma->order_per_bit) >> cma->order_per_bit; +} + +static void cma_clear_bitmap(struct cma *cma, unsigned long pfn, + unsigned int count) +{ + unsigned long bitmap_no, bitmap_count; + + bitmap_no = (pfn - cma->base_pfn) >> cma->order_per_bit; + bitmap_count = cma_bitmap_pages_to_bits(cma, count); + + mutex_lock(&cma->lock); + bitmap_clear(cma->bitmap, bitmap_no, bitmap_count); + mutex_unlock(&cma->lock); +} + +static void __init cma_activate_area(struct cma *cma) +{ + unsigned long base_pfn = cma->base_pfn, pfn = base_pfn; + unsigned i = cma->count >> pageblock_order; + struct zone *zone; + + cma->bitmap = bitmap_zalloc(cma_bitmap_maxno(cma), GFP_KERNEL); + if (!cma->bitmap) + goto out_error; + + WARN_ON_ONCE(!pfn_valid(pfn)); + zone = page_zone(pfn_to_page(pfn)); + + do { + unsigned j; + + base_pfn = pfn; + for (j = pageblock_nr_pages; j; --j, pfn++) { + WARN_ON_ONCE(!pfn_valid(pfn)); + /* + * alloc_contig_range requires the pfn range + * specified to be in the same zone. Make this + * simple by forcing the entire CMA resv range + * to be in the same zone. + */ + if (page_zone(pfn_to_page(pfn)) != zone) + goto not_in_zone; + } + init_cma_reserved_pageblock(pfn_to_page(base_pfn)); + } while (--i); + + mutex_init(&cma->lock); + +#ifdef CONFIG_CMA_DEBUGFS + INIT_HLIST_HEAD(&cma->mem_head); + spin_lock_init(&cma->mem_head_lock); +#endif + + return; + +not_in_zone: + bitmap_free(cma->bitmap); +out_error: + cma->count = 0; + pr_err("CMA area %s could not be activated\n", cma->name); + return; +} + +static int __init cma_init_reserved_areas(void) +{ + int i; + + for (i = 0; i < cma_area_count; i++) + cma_activate_area(&cma_areas[i]); + + return 0; +} +core_initcall(cma_init_reserved_areas); + +/** + * cma_init_reserved_mem() - create custom contiguous area from reserved memory + * @base: Base address of the reserved area + * @size: Size of the reserved area (in bytes), + * @order_per_bit: Order of pages represented by one bit on bitmap. + * @name: The name of the area. If this parameter is NULL, the name of + * the area will be set to "cmaN", where N is a running counter of + * used areas. + * @res_cma: Pointer to store the created cma region. + * + * This function creates custom contiguous area from already reserved memory. + */ +int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size, + unsigned int order_per_bit, + const char *name, + struct cma **res_cma) +{ + struct cma *cma; + phys_addr_t alignment; + + /* Sanity checks */ + if (cma_area_count == ARRAY_SIZE(cma_areas)) { + pr_err("Not enough slots for CMA reserved regions!\n"); + return -ENOSPC; + } + + if (!size || !memblock_is_region_reserved(base, size)) + return -EINVAL; + + /* ensure minimal alignment required by mm core */ + alignment = PAGE_SIZE << + max_t(unsigned long, MAX_ORDER - 1, pageblock_order); + + /* alignment should be aligned with order_per_bit */ + if (!IS_ALIGNED(alignment >> PAGE_SHIFT, 1 << order_per_bit)) + return -EINVAL; + + if (ALIGN(base, alignment) != base || ALIGN(size, alignment) != size) + return -EINVAL; + + /* + * Each reserved area must be initialised later, when more kernel + * subsystems (like slab allocator) are available. + */ + cma = &cma_areas[cma_area_count]; + + if (name) + snprintf(cma->name, CMA_MAX_NAME, name); + else + snprintf(cma->name, CMA_MAX_NAME, "cma%d\n", cma_area_count); + + cma->base_pfn = PFN_DOWN(base); + cma->count = size >> PAGE_SHIFT; + cma->order_per_bit = order_per_bit; + *res_cma = cma; + cma_area_count++; + totalcma_pages += (size / PAGE_SIZE); + + return 0; +} + +/** + * cma_declare_contiguous_nid() - reserve custom contiguous area + * @base: Base address of the reserved area optional, use 0 for any + * @size: Size of the reserved area (in bytes), + * @limit: End address of the reserved memory (optional, 0 for any). + * @alignment: Alignment for the CMA area, should be power of 2 or zero + * @order_per_bit: Order of pages represented by one bit on bitmap. + * @fixed: hint about where to place the reserved area + * @name: The name of the area. See function cma_init_reserved_mem() + * @res_cma: Pointer to store the created cma region. + * @nid: nid of the free area to find, %NUMA_NO_NODE for any node + * + * This function reserves memory from early allocator. It should be + * called by arch specific code once the early allocator (memblock or bootmem) + * has been activated and all other subsystems have already allocated/reserved + * memory. This function allows to create custom reserved areas. + * + * If @fixed is true, reserve contiguous area at exactly @base. If false, + * reserve in range from @base to @limit. + */ +int __init cma_declare_contiguous_nid(phys_addr_t base, + phys_addr_t size, phys_addr_t limit, + phys_addr_t alignment, unsigned int order_per_bit, + bool fixed, const char *name, struct cma **res_cma, + int nid) +{ + phys_addr_t memblock_end = memblock_end_of_DRAM(); + phys_addr_t highmem_start; + int ret = 0; + + /* + * We can't use __pa(high_memory) directly, since high_memory + * isn't a valid direct map VA, and DEBUG_VIRTUAL will (validly) + * complain. Find the boundary by adding one to the last valid + * address. + */ + highmem_start = __pa(high_memory - 1) + 1; + pr_debug("%s(size %pa, base %pa, limit %pa alignment %pa)\n", + __func__, &size, &base, &limit, &alignment); + + if (cma_area_count == ARRAY_SIZE(cma_areas)) { + pr_err("Not enough slots for CMA reserved regions!\n"); + return -ENOSPC; + } + + if (!size) + return -EINVAL; + + if (alignment && !is_power_of_2(alignment)) + return -EINVAL; + + /* + * Sanitise input arguments. + * Pages both ends in CMA area could be merged into adjacent unmovable + * migratetype page by page allocator's buddy algorithm. In the case, + * you couldn't get a contiguous memory, which is not what we want. + */ + alignment = max(alignment, (phys_addr_t)PAGE_SIZE << + max_t(unsigned long, MAX_ORDER - 1, pageblock_order)); + if (fixed && base & (alignment - 1)) { + ret = -EINVAL; + pr_err("Region at %pa must be aligned to %pa bytes\n", + &base, &alignment); + goto err; + } + base = ALIGN(base, alignment); + size = ALIGN(size, alignment); + limit &= ~(alignment - 1); + + if (!base) + fixed = false; + + /* size should be aligned with order_per_bit */ + if (!IS_ALIGNED(size >> PAGE_SHIFT, 1 << order_per_bit)) + return -EINVAL; + + /* + * If allocating at a fixed base the request region must not cross the + * low/high memory boundary. + */ + if (fixed && base < highmem_start && base + size > highmem_start) { + ret = -EINVAL; + pr_err("Region at %pa defined on low/high memory boundary (%pa)\n", + &base, &highmem_start); + goto err; + } + + /* + * If the limit is unspecified or above the memblock end, its effective + * value will be the memblock end. Set it explicitly to simplify further + * checks. + */ + if (limit == 0 || limit > memblock_end) + limit = memblock_end; + + if (base + size > limit) { + ret = -EINVAL; + pr_err("Size (%pa) of region at %pa exceeds limit (%pa)\n", + &size, &base, &limit); + goto err; + } + + /* Reserve memory */ + if (fixed) { + if (memblock_is_region_reserved(base, size) || + memblock_reserve(base, size) < 0) { + ret = -EBUSY; + goto err; + } + } else { + phys_addr_t addr = 0; + + /* + * All pages in the reserved area must come from the same zone. + * If the requested region crosses the low/high memory boundary, + * try allocating from high memory first and fall back to low + * memory in case of failure. + */ + if (base < highmem_start && limit > highmem_start) { + addr = memblock_alloc_range_nid(size, alignment, + highmem_start, limit, nid, true); + limit = highmem_start; + } + + if (!addr) { + addr = memblock_alloc_range_nid(size, alignment, base, + limit, nid, true); + if (!addr) { + ret = -ENOMEM; + goto err; + } + } + + /* + * kmemleak scans/reads tracked objects for pointers to other + * objects but this address isn't mapped and accessible + */ + kmemleak_ignore_phys(addr); + base = addr; + } + + ret = cma_init_reserved_mem(base, size, order_per_bit, name, res_cma); + if (ret) + goto free_mem; + + pr_info("Reserved %ld MiB at %pa\n", (unsigned long)size / SZ_1M, + &base); + return 0; + +free_mem: + memblock_free(base, size); +err: + pr_err("Failed to reserve %ld MiB\n", (unsigned long)size / SZ_1M); + return ret; +} + +#ifdef CONFIG_CMA_DEBUG +static void cma_debug_show_areas(struct cma *cma) +{ + unsigned long next_zero_bit, next_set_bit, nr_zero; + unsigned long start = 0; + unsigned long nr_part, nr_total = 0; + unsigned long nbits = cma_bitmap_maxno(cma); + + mutex_lock(&cma->lock); + pr_info("number of available pages: "); + for (;;) { + next_zero_bit = find_next_zero_bit(cma->bitmap, nbits, start); + if (next_zero_bit >= nbits) + break; + next_set_bit = find_next_bit(cma->bitmap, nbits, next_zero_bit); + nr_zero = next_set_bit - next_zero_bit; + nr_part = nr_zero << cma->order_per_bit; + pr_cont("%s%lu@%lu", nr_total ? "+" : "", nr_part, + next_zero_bit); + nr_total += nr_part; + start = next_zero_bit + nr_zero; + } + pr_cont("=> %lu free of %lu total pages\n", nr_total, cma->count); + mutex_unlock(&cma->lock); +} +#else +static inline void cma_debug_show_areas(struct cma *cma) { } +#endif + +/** + * cma_alloc() - allocate pages from contiguous area + * @cma: Contiguous memory region for which the allocation is performed. + * @count: Requested number of pages. + * @align: Requested alignment of pages (in PAGE_SIZE order). + * @no_warn: Avoid printing message about failed allocation + * + * This function allocates part of contiguous memory on specific + * contiguous memory area. + */ +struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align, + bool no_warn) +{ + unsigned long mask, offset; + unsigned long pfn = -1; + unsigned long start = 0; + unsigned long bitmap_maxno, bitmap_no, bitmap_count; + size_t i; + struct page *page = NULL; + int ret = -ENOMEM; + + if (!cma || !cma->count || !cma->bitmap) + return NULL; + + pr_debug("%s(cma %p, count %zu, align %d)\n", __func__, (void *)cma, + count, align); + + if (!count) + return NULL; + + mask = cma_bitmap_aligned_mask(cma, align); + offset = cma_bitmap_aligned_offset(cma, align); + bitmap_maxno = cma_bitmap_maxno(cma); + bitmap_count = cma_bitmap_pages_to_bits(cma, count); + + if (bitmap_count > bitmap_maxno) + return NULL; + + for (;;) { + mutex_lock(&cma->lock); + bitmap_no = bitmap_find_next_zero_area_off(cma->bitmap, + bitmap_maxno, start, bitmap_count, mask, + offset); + if (bitmap_no >= bitmap_maxno) { + mutex_unlock(&cma->lock); + break; + } + bitmap_set(cma->bitmap, bitmap_no, bitmap_count); + /* + * It's safe to drop the lock here. We've marked this region for + * our exclusive use. If the migration fails we will take the + * lock again and unmark it. + */ + mutex_unlock(&cma->lock); + + pfn = cma->base_pfn + (bitmap_no << cma->order_per_bit); + mutex_lock(&cma_mutex); + ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA, + GFP_KERNEL | (no_warn ? __GFP_NOWARN : 0)); + mutex_unlock(&cma_mutex); + if (ret == 0) { + page = pfn_to_page(pfn); + break; + } + + cma_clear_bitmap(cma, pfn, count); + if (ret != -EBUSY) + break; + + pr_debug("%s(): memory range at %p is busy, retrying\n", + __func__, pfn_to_page(pfn)); + /* try again with a bit different memory target */ + start = bitmap_no + mask + 1; + } + + trace_cma_alloc(pfn, page, count, align); + + /* + * CMA can allocate multiple page blocks, which results in different + * blocks being marked with different tags. Reset the tags to ignore + * those page blocks. + */ + if (page) { + for (i = 0; i < count; i++) + page_kasan_tag_reset(nth_page(page, i)); + } + + if (ret && !no_warn) { + pr_err("%s: alloc failed, req-size: %zu pages, ret: %d\n", + __func__, count, ret); + cma_debug_show_areas(cma); + } + + pr_debug("%s(): returned %p\n", __func__, page); + return page; +} + +/** + * cma_release() - release allocated pages + * @cma: Contiguous memory region for which the allocation is performed. + * @pages: Allocated pages. + * @count: Number of allocated pages. + * + * This function releases memory allocated by cma_alloc(). + * It returns false when provided pages do not belong to contiguous area and + * true otherwise. + */ +bool cma_release(struct cma *cma, const struct page *pages, unsigned int count) +{ + unsigned long pfn; + + if (!cma || !pages) + return false; + + pr_debug("%s(page %p)\n", __func__, (void *)pages); + + pfn = page_to_pfn(pages); + + if (pfn < cma->base_pfn || pfn >= cma->base_pfn + cma->count) + return false; + + VM_BUG_ON(pfn + count > cma->base_pfn + cma->count); + + free_contig_range(pfn, count); + cma_clear_bitmap(cma, pfn, count); + trace_cma_release(pfn, pages, count); + + return true; +} + +int cma_for_each_area(int (*it)(struct cma *cma, void *data), void *data) +{ + int i; + + for (i = 0; i < cma_area_count; i++) { + int ret = it(&cma_areas[i], data); + + if (ret) + return ret; + } + + return 0; +} diff --git a/mm/cma.h b/mm/cma.h new file mode 100644 index 000000000..42ae082cb --- /dev/null +++ b/mm/cma.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __MM_CMA_H__ +#define __MM_CMA_H__ + +#include + +struct cma { + unsigned long base_pfn; + unsigned long count; + unsigned long *bitmap; + unsigned int order_per_bit; /* Order of pages represented by one bit */ + struct mutex lock; +#ifdef CONFIG_CMA_DEBUGFS + struct hlist_head mem_head; + spinlock_t mem_head_lock; + struct debugfs_u32_array dfs_bitmap; +#endif + char name[CMA_MAX_NAME]; +}; + +extern struct cma cma_areas[MAX_CMA_AREAS]; +extern unsigned cma_area_count; + +static inline unsigned long cma_bitmap_maxno(struct cma *cma) +{ + return cma->count >> cma->order_per_bit; +} + +#endif diff --git a/mm/cma_debug.c b/mm/cma_debug.c new file mode 100644 index 000000000..d5bf8aa34 --- /dev/null +++ b/mm/cma_debug.c @@ -0,0 +1,200 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * CMA DebugFS Interface + * + * Copyright (c) 2015 Sasha Levin + */ + + +#include +#include +#include +#include +#include +#include + +#include "cma.h" + +struct cma_mem { + struct hlist_node node; + struct page *p; + unsigned long n; +}; + +static int cma_debugfs_get(void *data, u64 *val) +{ + unsigned long *p = data; + + *val = *p; + + return 0; +} +DEFINE_DEBUGFS_ATTRIBUTE(cma_debugfs_fops, cma_debugfs_get, NULL, "%llu\n"); + +static int cma_used_get(void *data, u64 *val) +{ + struct cma *cma = data; + unsigned long used; + + mutex_lock(&cma->lock); + /* pages counter is smaller than sizeof(int) */ + used = bitmap_weight(cma->bitmap, (int)cma_bitmap_maxno(cma)); + mutex_unlock(&cma->lock); + *val = (u64)used << cma->order_per_bit; + + return 0; +} +DEFINE_DEBUGFS_ATTRIBUTE(cma_used_fops, cma_used_get, NULL, "%llu\n"); + +static int cma_maxchunk_get(void *data, u64 *val) +{ + struct cma *cma = data; + unsigned long maxchunk = 0; + unsigned long start, end = 0; + unsigned long bitmap_maxno = cma_bitmap_maxno(cma); + + mutex_lock(&cma->lock); + for (;;) { + start = find_next_zero_bit(cma->bitmap, bitmap_maxno, end); + if (start >= bitmap_maxno) + break; + end = find_next_bit(cma->bitmap, bitmap_maxno, start); + maxchunk = max(end - start, maxchunk); + } + mutex_unlock(&cma->lock); + *val = (u64)maxchunk << cma->order_per_bit; + + return 0; +} +DEFINE_DEBUGFS_ATTRIBUTE(cma_maxchunk_fops, cma_maxchunk_get, NULL, "%llu\n"); + +static void cma_add_to_cma_mem_list(struct cma *cma, struct cma_mem *mem) +{ + spin_lock(&cma->mem_head_lock); + hlist_add_head(&mem->node, &cma->mem_head); + spin_unlock(&cma->mem_head_lock); +} + +static struct cma_mem *cma_get_entry_from_list(struct cma *cma) +{ + struct cma_mem *mem = NULL; + + spin_lock(&cma->mem_head_lock); + if (!hlist_empty(&cma->mem_head)) { + mem = hlist_entry(cma->mem_head.first, struct cma_mem, node); + hlist_del_init(&mem->node); + } + spin_unlock(&cma->mem_head_lock); + + return mem; +} + +static int cma_free_mem(struct cma *cma, int count) +{ + struct cma_mem *mem = NULL; + + while (count) { + mem = cma_get_entry_from_list(cma); + if (mem == NULL) + return 0; + + if (mem->n <= count) { + cma_release(cma, mem->p, mem->n); + count -= mem->n; + kfree(mem); + } else if (cma->order_per_bit == 0) { + cma_release(cma, mem->p, count); + mem->p += count; + mem->n -= count; + count = 0; + cma_add_to_cma_mem_list(cma, mem); + } else { + pr_debug("cma: cannot release partial block when order_per_bit != 0\n"); + cma_add_to_cma_mem_list(cma, mem); + break; + } + } + + return 0; + +} + +static int cma_free_write(void *data, u64 val) +{ + int pages = val; + struct cma *cma = data; + + return cma_free_mem(cma, pages); +} +DEFINE_DEBUGFS_ATTRIBUTE(cma_free_fops, NULL, cma_free_write, "%llu\n"); + +static int cma_alloc_mem(struct cma *cma, int count) +{ + struct cma_mem *mem; + struct page *p; + + mem = kzalloc(sizeof(*mem), GFP_KERNEL); + if (!mem) + return -ENOMEM; + + p = cma_alloc(cma, count, 0, false); + if (!p) { + kfree(mem); + return -ENOMEM; + } + + mem->p = p; + mem->n = count; + + cma_add_to_cma_mem_list(cma, mem); + + return 0; +} + +static int cma_alloc_write(void *data, u64 val) +{ + int pages = val; + struct cma *cma = data; + + return cma_alloc_mem(cma, pages); +} +DEFINE_DEBUGFS_ATTRIBUTE(cma_alloc_fops, NULL, cma_alloc_write, "%llu\n"); + +static void cma_debugfs_add_one(struct cma *cma, struct dentry *root_dentry) +{ + struct dentry *tmp; + char name[16]; + + scnprintf(name, sizeof(name), "cma-%s", cma->name); + + tmp = debugfs_create_dir(name, root_dentry); + + debugfs_create_file("alloc", 0200, tmp, cma, &cma_alloc_fops); + debugfs_create_file("free", 0200, tmp, cma, &cma_free_fops); + debugfs_create_file("base_pfn", 0444, tmp, + &cma->base_pfn, &cma_debugfs_fops); + debugfs_create_file("count", 0444, tmp, &cma->count, &cma_debugfs_fops); + debugfs_create_file("order_per_bit", 0444, tmp, + &cma->order_per_bit, &cma_debugfs_fops); + debugfs_create_file("used", 0444, tmp, cma, &cma_used_fops); + debugfs_create_file("maxchunk", 0444, tmp, cma, &cma_maxchunk_fops); + + cma->dfs_bitmap.array = (u32 *)cma->bitmap; + cma->dfs_bitmap.n_elements = DIV_ROUND_UP(cma_bitmap_maxno(cma), + BITS_PER_BYTE * sizeof(u32)); + debugfs_create_u32_array("bitmap", 0444, tmp, &cma->dfs_bitmap); +} + +static int __init cma_debugfs_init(void) +{ + struct dentry *cma_debugfs_root; + int i; + + cma_debugfs_root = debugfs_create_dir("cma", NULL); + + for (i = 0; i < cma_area_count; i++) + cma_debugfs_add_one(&cma_areas[i], cma_debugfs_root); + + return 0; +} +late_initcall(cma_debugfs_init); diff --git a/mm/compaction.c b/mm/compaction.c new file mode 100644 index 000000000..b58021666 --- /dev/null +++ b/mm/compaction.c @@ -0,0 +1,2926 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/mm/compaction.c + * + * Memory compaction for the reduction of external fragmentation. Note that + * this heavily depends upon page migration to do all the real heavy + * lifting + * + * Copyright IBM Corp. 2007-2010 Mel Gorman + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "internal.h" + +#ifdef CONFIG_COMPACTION +static inline void count_compact_event(enum vm_event_item item) +{ + count_vm_event(item); +} + +static inline void count_compact_events(enum vm_event_item item, long delta) +{ + count_vm_events(item, delta); +} +#else +#define count_compact_event(item) do { } while (0) +#define count_compact_events(item, delta) do { } while (0) +#endif + +#if defined CONFIG_COMPACTION || defined CONFIG_CMA + +#define CREATE_TRACE_POINTS +#include + +#define block_start_pfn(pfn, order) round_down(pfn, 1UL << (order)) +#define block_end_pfn(pfn, order) ALIGN((pfn) + 1, 1UL << (order)) +#define pageblock_start_pfn(pfn) block_start_pfn(pfn, pageblock_order) +#define pageblock_end_pfn(pfn) block_end_pfn(pfn, pageblock_order) + +/* + * Fragmentation score check interval for proactive compaction purposes. + */ +static const unsigned int HPAGE_FRAG_CHECK_INTERVAL_MSEC = 500; + +/* + * Page order with-respect-to which proactive compaction + * calculates external fragmentation, which is used as + * the "fragmentation score" of a node/zone. + */ +#if defined CONFIG_TRANSPARENT_HUGEPAGE +#define COMPACTION_HPAGE_ORDER HPAGE_PMD_ORDER +#elif defined CONFIG_HUGETLBFS +#define COMPACTION_HPAGE_ORDER HUGETLB_PAGE_ORDER +#else +#define COMPACTION_HPAGE_ORDER (PMD_SHIFT - PAGE_SHIFT) +#endif + +static unsigned long release_freepages(struct list_head *freelist) +{ + struct page *page, *next; + unsigned long high_pfn = 0; + + list_for_each_entry_safe(page, next, freelist, lru) { + unsigned long pfn = page_to_pfn(page); + list_del(&page->lru); + __free_page(page); + if (pfn > high_pfn) + high_pfn = pfn; + } + + return high_pfn; +} + +static void split_map_pages(struct list_head *list) +{ + unsigned int i, order, nr_pages; + struct page *page, *next; + LIST_HEAD(tmp_list); + + list_for_each_entry_safe(page, next, list, lru) { + list_del(&page->lru); + + order = page_private(page); + nr_pages = 1 << order; + + post_alloc_hook(page, order, __GFP_MOVABLE); + if (order) + split_page(page, order); + + for (i = 0; i < nr_pages; i++) { + list_add(&page->lru, &tmp_list); + page++; + } + } + + list_splice(&tmp_list, list); +} + +#ifdef CONFIG_COMPACTION + +int PageMovable(struct page *page) +{ + struct address_space *mapping; + + VM_BUG_ON_PAGE(!PageLocked(page), page); + if (!__PageMovable(page)) + return 0; + + mapping = page_mapping(page); + if (mapping && mapping->a_ops && mapping->a_ops->isolate_page) + return 1; + + return 0; +} +EXPORT_SYMBOL(PageMovable); + +void __SetPageMovable(struct page *page, struct address_space *mapping) +{ + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE((unsigned long)mapping & PAGE_MAPPING_MOVABLE, page); + page->mapping = (void *)((unsigned long)mapping | PAGE_MAPPING_MOVABLE); +} +EXPORT_SYMBOL(__SetPageMovable); + +void __ClearPageMovable(struct page *page) +{ + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(!PageMovable(page), page); + /* + * Clear registered address_space val with keeping PAGE_MAPPING_MOVABLE + * flag so that VM can catch up released page by driver after isolation. + * With it, VM migration doesn't try to put it back. + */ + page->mapping = (void *)((unsigned long)page->mapping & + PAGE_MAPPING_MOVABLE); +} +EXPORT_SYMBOL(__ClearPageMovable); + +/* Do not skip compaction more than 64 times */ +#define COMPACT_MAX_DEFER_SHIFT 6 + +/* + * Compaction is deferred when compaction fails to result in a page + * allocation success. 1 << compact_defer_shift, compactions are skipped up + * to a limit of 1 << COMPACT_MAX_DEFER_SHIFT + */ +void defer_compaction(struct zone *zone, int order) +{ + zone->compact_considered = 0; + zone->compact_defer_shift++; + + if (order < zone->compact_order_failed) + zone->compact_order_failed = order; + + if (zone->compact_defer_shift > COMPACT_MAX_DEFER_SHIFT) + zone->compact_defer_shift = COMPACT_MAX_DEFER_SHIFT; + + trace_mm_compaction_defer_compaction(zone, order); +} + +/* Returns true if compaction should be skipped this time */ +bool compaction_deferred(struct zone *zone, int order) +{ + unsigned long defer_limit = 1UL << zone->compact_defer_shift; + + if (order < zone->compact_order_failed) + return false; + + /* Avoid possible overflow */ + if (++zone->compact_considered >= defer_limit) { + zone->compact_considered = defer_limit; + return false; + } + + trace_mm_compaction_deferred(zone, order); + + return true; +} + +/* + * Update defer tracking counters after successful compaction of given order, + * which means an allocation either succeeded (alloc_success == true) or is + * expected to succeed. + */ +void compaction_defer_reset(struct zone *zone, int order, + bool alloc_success) +{ + if (alloc_success) { + zone->compact_considered = 0; + zone->compact_defer_shift = 0; + } + if (order >= zone->compact_order_failed) + zone->compact_order_failed = order + 1; + + trace_mm_compaction_defer_reset(zone, order); +} + +/* Returns true if restarting compaction after many failures */ +bool compaction_restarting(struct zone *zone, int order) +{ + if (order < zone->compact_order_failed) + return false; + + return zone->compact_defer_shift == COMPACT_MAX_DEFER_SHIFT && + zone->compact_considered >= 1UL << zone->compact_defer_shift; +} + +/* Returns true if the pageblock should be scanned for pages to isolate. */ +static inline bool isolation_suitable(struct compact_control *cc, + struct page *page) +{ + if (cc->ignore_skip_hint) + return true; + + return !get_pageblock_skip(page); +} + +static void reset_cached_positions(struct zone *zone) +{ + zone->compact_cached_migrate_pfn[0] = zone->zone_start_pfn; + zone->compact_cached_migrate_pfn[1] = zone->zone_start_pfn; + zone->compact_cached_free_pfn = + pageblock_start_pfn(zone_end_pfn(zone) - 1); +} + +/* + * Compound pages of >= pageblock_order should consistenly be skipped until + * released. It is always pointless to compact pages of such order (if they are + * migratable), and the pageblocks they occupy cannot contain any free pages. + */ +static bool pageblock_skip_persistent(struct page *page) +{ + if (!PageCompound(page)) + return false; + + page = compound_head(page); + + if (compound_order(page) >= pageblock_order) + return true; + + return false; +} + +static bool +__reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source, + bool check_target) +{ + struct page *page = pfn_to_online_page(pfn); + struct page *block_page; + struct page *end_page; + unsigned long block_pfn; + + if (!page) + return false; + if (zone != page_zone(page)) + return false; + if (pageblock_skip_persistent(page)) + return false; + + /* + * If skip is already cleared do no further checking once the + * restart points have been set. + */ + if (check_source && check_target && !get_pageblock_skip(page)) + return true; + + /* + * If clearing skip for the target scanner, do not select a + * non-movable pageblock as the starting point. + */ + if (!check_source && check_target && + get_pageblock_migratetype(page) != MIGRATE_MOVABLE) + return false; + + /* Ensure the start of the pageblock or zone is online and valid */ + block_pfn = pageblock_start_pfn(pfn); + block_pfn = max(block_pfn, zone->zone_start_pfn); + block_page = pfn_to_online_page(block_pfn); + if (block_page) { + page = block_page; + pfn = block_pfn; + } + + /* Ensure the end of the pageblock or zone is online and valid */ + block_pfn = pageblock_end_pfn(pfn) - 1; + block_pfn = min(block_pfn, zone_end_pfn(zone) - 1); + end_page = pfn_to_online_page(block_pfn); + if (!end_page) + return false; + + /* + * Only clear the hint if a sample indicates there is either a + * free page or an LRU page in the block. One or other condition + * is necessary for the block to be a migration source/target. + */ + do { + if (pfn_valid_within(pfn)) { + if (check_source && PageLRU(page)) { + clear_pageblock_skip(page); + return true; + } + + if (check_target && PageBuddy(page)) { + clear_pageblock_skip(page); + return true; + } + } + + page += (1 << PAGE_ALLOC_COSTLY_ORDER); + pfn += (1 << PAGE_ALLOC_COSTLY_ORDER); + } while (page <= end_page); + + return false; +} + +/* + * This function is called to clear all cached information on pageblocks that + * should be skipped for page isolation when the migrate and free page scanner + * meet. + */ +static void __reset_isolation_suitable(struct zone *zone) +{ + unsigned long migrate_pfn = zone->zone_start_pfn; + unsigned long free_pfn = zone_end_pfn(zone) - 1; + unsigned long reset_migrate = free_pfn; + unsigned long reset_free = migrate_pfn; + bool source_set = false; + bool free_set = false; + + if (!zone->compact_blockskip_flush) + return; + + zone->compact_blockskip_flush = false; + + /* + * Walk the zone and update pageblock skip information. Source looks + * for PageLRU while target looks for PageBuddy. When the scanner + * is found, both PageBuddy and PageLRU are checked as the pageblock + * is suitable as both source and target. + */ + for (; migrate_pfn < free_pfn; migrate_pfn += pageblock_nr_pages, + free_pfn -= pageblock_nr_pages) { + cond_resched(); + + /* Update the migrate PFN */ + if (__reset_isolation_pfn(zone, migrate_pfn, true, source_set) && + migrate_pfn < reset_migrate) { + source_set = true; + reset_migrate = migrate_pfn; + zone->compact_init_migrate_pfn = reset_migrate; + zone->compact_cached_migrate_pfn[0] = reset_migrate; + zone->compact_cached_migrate_pfn[1] = reset_migrate; + } + + /* Update the free PFN */ + if (__reset_isolation_pfn(zone, free_pfn, free_set, true) && + free_pfn > reset_free) { + free_set = true; + reset_free = free_pfn; + zone->compact_init_free_pfn = reset_free; + zone->compact_cached_free_pfn = reset_free; + } + } + + /* Leave no distance if no suitable block was reset */ + if (reset_migrate >= reset_free) { + zone->compact_cached_migrate_pfn[0] = migrate_pfn; + zone->compact_cached_migrate_pfn[1] = migrate_pfn; + zone->compact_cached_free_pfn = free_pfn; + } +} + +void reset_isolation_suitable(pg_data_t *pgdat) +{ + int zoneid; + + for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) { + struct zone *zone = &pgdat->node_zones[zoneid]; + if (!populated_zone(zone)) + continue; + + /* Only flush if a full compaction finished recently */ + if (zone->compact_blockskip_flush) + __reset_isolation_suitable(zone); + } +} + +/* + * Sets the pageblock skip bit if it was clear. Note that this is a hint as + * locks are not required for read/writers. Returns true if it was already set. + */ +static bool test_and_set_skip(struct compact_control *cc, struct page *page, + unsigned long pfn) +{ + bool skip; + + /* Do no update if skip hint is being ignored */ + if (cc->ignore_skip_hint) + return false; + + if (!IS_ALIGNED(pfn, pageblock_nr_pages)) + return false; + + skip = get_pageblock_skip(page); + if (!skip && !cc->no_set_skip_hint) + set_pageblock_skip(page); + + return skip; +} + +static void update_cached_migrate(struct compact_control *cc, unsigned long pfn) +{ + struct zone *zone = cc->zone; + + pfn = pageblock_end_pfn(pfn); + + /* Set for isolation rather than compaction */ + if (cc->no_set_skip_hint) + return; + + if (pfn > zone->compact_cached_migrate_pfn[0]) + zone->compact_cached_migrate_pfn[0] = pfn; + if (cc->mode != MIGRATE_ASYNC && + pfn > zone->compact_cached_migrate_pfn[1]) + zone->compact_cached_migrate_pfn[1] = pfn; +} + +/* + * If no pages were isolated then mark this pageblock to be skipped in the + * future. The information is later cleared by __reset_isolation_suitable(). + */ +static void update_pageblock_skip(struct compact_control *cc, + struct page *page, unsigned long pfn) +{ + struct zone *zone = cc->zone; + + if (cc->no_set_skip_hint) + return; + + if (!page) + return; + + set_pageblock_skip(page); + + /* Update where async and sync compaction should restart */ + if (pfn < zone->compact_cached_free_pfn) + zone->compact_cached_free_pfn = pfn; +} +#else +static inline bool isolation_suitable(struct compact_control *cc, + struct page *page) +{ + return true; +} + +static inline bool pageblock_skip_persistent(struct page *page) +{ + return false; +} + +static inline void update_pageblock_skip(struct compact_control *cc, + struct page *page, unsigned long pfn) +{ +} + +static void update_cached_migrate(struct compact_control *cc, unsigned long pfn) +{ +} + +static bool test_and_set_skip(struct compact_control *cc, struct page *page, + unsigned long pfn) +{ + return false; +} +#endif /* CONFIG_COMPACTION */ + +/* + * Compaction requires the taking of some coarse locks that are potentially + * very heavily contended. For async compaction, trylock and record if the + * lock is contended. The lock will still be acquired but compaction will + * abort when the current block is finished regardless of success rate. + * Sync compaction acquires the lock. + * + * Always returns true which makes it easier to track lock state in callers. + */ +static bool compact_lock_irqsave(spinlock_t *lock, unsigned long *flags, + struct compact_control *cc) + __acquires(lock) +{ + /* Track if the lock is contended in async mode */ + if (cc->mode == MIGRATE_ASYNC && !cc->contended) { + if (spin_trylock_irqsave(lock, *flags)) + return true; + + cc->contended = true; + } + + spin_lock_irqsave(lock, *flags); + return true; +} + +/* + * Compaction requires the taking of some coarse locks that are potentially + * very heavily contended. The lock should be periodically unlocked to avoid + * having disabled IRQs for a long time, even when there is nobody waiting on + * the lock. It might also be that allowing the IRQs will result in + * need_resched() becoming true. If scheduling is needed, async compaction + * aborts. Sync compaction schedules. + * Either compaction type will also abort if a fatal signal is pending. + * In either case if the lock was locked, it is dropped and not regained. + * + * Returns true if compaction should abort due to fatal signal pending, or + * async compaction due to need_resched() + * Returns false when compaction can continue (sync compaction might have + * scheduled) + */ +static bool compact_unlock_should_abort(spinlock_t *lock, + unsigned long flags, bool *locked, struct compact_control *cc) +{ + if (*locked) { + spin_unlock_irqrestore(lock, flags); + *locked = false; + } + + if (fatal_signal_pending(current)) { + cc->contended = true; + return true; + } + + cond_resched(); + + return false; +} + +/* + * Isolate free pages onto a private freelist. If @strict is true, will abort + * returning 0 on any invalid PFNs or non-free pages inside of the pageblock + * (even though it may still end up isolating some pages). + */ +static unsigned long isolate_freepages_block(struct compact_control *cc, + unsigned long *start_pfn, + unsigned long end_pfn, + struct list_head *freelist, + unsigned int stride, + bool strict) +{ + int nr_scanned = 0, total_isolated = 0; + struct page *cursor; + unsigned long flags = 0; + bool locked = false; + unsigned long blockpfn = *start_pfn; + unsigned int order; + + /* Strict mode is for isolation, speed is secondary */ + if (strict) + stride = 1; + + cursor = pfn_to_page(blockpfn); + + /* Isolate free pages. */ + for (; blockpfn < end_pfn; blockpfn += stride, cursor += stride) { + int isolated; + struct page *page = cursor; + + /* + * Periodically drop the lock (if held) regardless of its + * contention, to give chance to IRQs. Abort if fatal signal + * pending or async compaction detects need_resched() + */ + if (!(blockpfn % SWAP_CLUSTER_MAX) + && compact_unlock_should_abort(&cc->zone->lock, flags, + &locked, cc)) + break; + + nr_scanned++; + if (!pfn_valid_within(blockpfn)) + goto isolate_fail; + + /* + * For compound pages such as THP and hugetlbfs, we can save + * potentially a lot of iterations if we skip them at once. + * The check is racy, but we can consider only valid values + * and the only danger is skipping too much. + */ + if (PageCompound(page)) { + const unsigned int order = compound_order(page); + + if (likely(order < MAX_ORDER)) { + blockpfn += (1UL << order) - 1; + cursor += (1UL << order) - 1; + } + goto isolate_fail; + } + + if (!PageBuddy(page)) + goto isolate_fail; + + /* + * If we already hold the lock, we can skip some rechecking. + * Note that if we hold the lock now, checked_pageblock was + * already set in some previous iteration (or strict is true), + * so it is correct to skip the suitable migration target + * recheck as well. + */ + if (!locked) { + locked = compact_lock_irqsave(&cc->zone->lock, + &flags, cc); + + /* Recheck this is a buddy page under lock */ + if (!PageBuddy(page)) + goto isolate_fail; + } + + /* Found a free page, will break it into order-0 pages */ + order = buddy_order(page); + isolated = __isolate_free_page(page, order); + if (!isolated) + break; + set_page_private(page, order); + + total_isolated += isolated; + cc->nr_freepages += isolated; + list_add_tail(&page->lru, freelist); + + if (!strict && cc->nr_migratepages <= cc->nr_freepages) { + blockpfn += isolated; + break; + } + /* Advance to the end of split page */ + blockpfn += isolated - 1; + cursor += isolated - 1; + continue; + +isolate_fail: + if (strict) + break; + else + continue; + + } + + if (locked) + spin_unlock_irqrestore(&cc->zone->lock, flags); + + /* + * There is a tiny chance that we have read bogus compound_order(), + * so be careful to not go outside of the pageblock. + */ + if (unlikely(blockpfn > end_pfn)) + blockpfn = end_pfn; + + trace_mm_compaction_isolate_freepages(*start_pfn, blockpfn, + nr_scanned, total_isolated); + + /* Record how far we have got within the block */ + *start_pfn = blockpfn; + + /* + * If strict isolation is requested by CMA then check that all the + * pages requested were isolated. If there were any failures, 0 is + * returned and CMA will fail. + */ + if (strict && blockpfn < end_pfn) + total_isolated = 0; + + cc->total_free_scanned += nr_scanned; + if (total_isolated) + count_compact_events(COMPACTISOLATED, total_isolated); + return total_isolated; +} + +/** + * isolate_freepages_range() - isolate free pages. + * @cc: Compaction control structure. + * @start_pfn: The first PFN to start isolating. + * @end_pfn: The one-past-last PFN. + * + * Non-free pages, invalid PFNs, or zone boundaries within the + * [start_pfn, end_pfn) range are considered errors, cause function to + * undo its actions and return zero. + * + * Otherwise, function returns one-past-the-last PFN of isolated page + * (which may be greater then end_pfn if end fell in a middle of + * a free page). + */ +unsigned long +isolate_freepages_range(struct compact_control *cc, + unsigned long start_pfn, unsigned long end_pfn) +{ + unsigned long isolated, pfn, block_start_pfn, block_end_pfn; + LIST_HEAD(freelist); + + pfn = start_pfn; + block_start_pfn = pageblock_start_pfn(pfn); + if (block_start_pfn < cc->zone->zone_start_pfn) + block_start_pfn = cc->zone->zone_start_pfn; + block_end_pfn = pageblock_end_pfn(pfn); + + for (; pfn < end_pfn; pfn += isolated, + block_start_pfn = block_end_pfn, + block_end_pfn += pageblock_nr_pages) { + /* Protect pfn from changing by isolate_freepages_block */ + unsigned long isolate_start_pfn = pfn; + + block_end_pfn = min(block_end_pfn, end_pfn); + + /* + * pfn could pass the block_end_pfn if isolated freepage + * is more than pageblock order. In this case, we adjust + * scanning range to right one. + */ + if (pfn >= block_end_pfn) { + block_start_pfn = pageblock_start_pfn(pfn); + block_end_pfn = pageblock_end_pfn(pfn); + block_end_pfn = min(block_end_pfn, end_pfn); + } + + if (!pageblock_pfn_to_page(block_start_pfn, + block_end_pfn, cc->zone)) + break; + + isolated = isolate_freepages_block(cc, &isolate_start_pfn, + block_end_pfn, &freelist, 0, true); + + /* + * In strict mode, isolate_freepages_block() returns 0 if + * there are any holes in the block (ie. invalid PFNs or + * non-free pages). + */ + if (!isolated) + break; + + /* + * If we managed to isolate pages, it is always (1 << n) * + * pageblock_nr_pages for some non-negative n. (Max order + * page may span two pageblocks). + */ + } + + /* __isolate_free_page() does not map the pages */ + split_map_pages(&freelist); + + if (pfn < end_pfn) { + /* Loop terminated early, cleanup. */ + release_freepages(&freelist); + return 0; + } + + /* We don't use freelists for anything. */ + return pfn; +} + +/* Similar to reclaim, but different enough that they don't share logic */ +static bool too_many_isolated(pg_data_t *pgdat) +{ + unsigned long active, inactive, isolated; + + inactive = node_page_state(pgdat, NR_INACTIVE_FILE) + + node_page_state(pgdat, NR_INACTIVE_ANON); + active = node_page_state(pgdat, NR_ACTIVE_FILE) + + node_page_state(pgdat, NR_ACTIVE_ANON); + isolated = node_page_state(pgdat, NR_ISOLATED_FILE) + + node_page_state(pgdat, NR_ISOLATED_ANON); + + return isolated > (inactive + active) / 2; +} + +/** + * isolate_migratepages_block() - isolate all migrate-able pages within + * a single pageblock + * @cc: Compaction control structure. + * @low_pfn: The first PFN to isolate + * @end_pfn: The one-past-the-last PFN to isolate, within same pageblock + * @isolate_mode: Isolation mode to be used. + * + * Isolate all pages that can be migrated from the range specified by + * [low_pfn, end_pfn). The range is expected to be within same pageblock. + * Returns zero if there is a fatal signal pending, otherwise PFN of the + * first page that was not scanned (which may be both less, equal to or more + * than end_pfn). + * + * The pages are isolated on cc->migratepages list (not required to be empty), + * and cc->nr_migratepages is updated accordingly. The cc->migrate_pfn field + * is neither read nor updated. + */ +static unsigned long +isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, + unsigned long end_pfn, isolate_mode_t isolate_mode) +{ + pg_data_t *pgdat = cc->zone->zone_pgdat; + unsigned long nr_scanned = 0, nr_isolated = 0; + struct lruvec *lruvec; + unsigned long flags = 0; + bool locked = false; + struct page *page = NULL, *valid_page = NULL; + unsigned long start_pfn = low_pfn; + bool skip_on_failure = false; + unsigned long next_skip_pfn = 0; + bool skip_updated = false; + + /* + * Ensure that there are not too many pages isolated from the LRU + * list by either parallel reclaimers or compaction. If there are, + * delay for some time until fewer pages are isolated + */ + while (unlikely(too_many_isolated(pgdat))) { + /* stop isolation if there are still pages not migrated */ + if (cc->nr_migratepages) + return 0; + + /* async migration should just abort */ + if (cc->mode == MIGRATE_ASYNC) + return 0; + + congestion_wait(BLK_RW_ASYNC, HZ/10); + + if (fatal_signal_pending(current)) + return 0; + } + + cond_resched(); + + if (cc->direct_compaction && (cc->mode == MIGRATE_ASYNC)) { + skip_on_failure = true; + next_skip_pfn = block_end_pfn(low_pfn, cc->order); + } + + /* Time to isolate some pages for migration */ + for (; low_pfn < end_pfn; low_pfn++) { + + if (skip_on_failure && low_pfn >= next_skip_pfn) { + /* + * We have isolated all migration candidates in the + * previous order-aligned block, and did not skip it due + * to failure. We should migrate the pages now and + * hopefully succeed compaction. + */ + if (nr_isolated) + break; + + /* + * We failed to isolate in the previous order-aligned + * block. Set the new boundary to the end of the + * current block. Note we can't simply increase + * next_skip_pfn by 1 << order, as low_pfn might have + * been incremented by a higher number due to skipping + * a compound or a high-order buddy page in the + * previous loop iteration. + */ + next_skip_pfn = block_end_pfn(low_pfn, cc->order); + } + + /* + * Periodically drop the lock (if held) regardless of its + * contention, to give chance to IRQs. Abort completely if + * a fatal signal is pending. + */ + if (!(low_pfn % SWAP_CLUSTER_MAX) + && compact_unlock_should_abort(&pgdat->lru_lock, + flags, &locked, cc)) { + low_pfn = 0; + goto fatal_pending; + } + + if (!pfn_valid_within(low_pfn)) + goto isolate_fail; + nr_scanned++; + + page = pfn_to_page(low_pfn); + + /* + * Check if the pageblock has already been marked skipped. + * Only the aligned PFN is checked as the caller isolates + * COMPACT_CLUSTER_MAX at a time so the second call must + * not falsely conclude that the block should be skipped. + */ + if (!valid_page && IS_ALIGNED(low_pfn, pageblock_nr_pages)) { + if (!cc->ignore_skip_hint && get_pageblock_skip(page)) { + low_pfn = end_pfn; + goto isolate_abort; + } + valid_page = page; + } + + /* + * Skip if free. We read page order here without zone lock + * which is generally unsafe, but the race window is small and + * the worst thing that can happen is that we skip some + * potential isolation targets. + */ + if (PageBuddy(page)) { + unsigned long freepage_order = buddy_order_unsafe(page); + + /* + * Without lock, we cannot be sure that what we got is + * a valid page order. Consider only values in the + * valid order range to prevent low_pfn overflow. + */ + if (freepage_order > 0 && freepage_order < MAX_ORDER) + low_pfn += (1UL << freepage_order) - 1; + continue; + } + + /* + * Regardless of being on LRU, compound pages such as THP and + * hugetlbfs are not to be compacted unless we are attempting + * an allocation much larger than the huge page size (eg CMA). + * We can potentially save a lot of iterations if we skip them + * at once. The check is racy, but we can consider only valid + * values and the only danger is skipping too much. + */ + if (PageCompound(page) && !cc->alloc_contig) { + const unsigned int order = compound_order(page); + + if (likely(order < MAX_ORDER)) + low_pfn += (1UL << order) - 1; + goto isolate_fail; + } + + /* + * Check may be lockless but that's ok as we recheck later. + * It's possible to migrate LRU and non-lru movable pages. + * Skip any other type of page + */ + if (!PageLRU(page)) { + /* + * __PageMovable can return false positive so we need + * to verify it under page_lock. + */ + if (unlikely(__PageMovable(page)) && + !PageIsolated(page)) { + if (locked) { + spin_unlock_irqrestore(&pgdat->lru_lock, + flags); + locked = false; + } + + if (!isolate_movable_page(page, isolate_mode)) + goto isolate_success; + } + + goto isolate_fail; + } + + /* + * Migration will fail if an anonymous page is pinned in memory, + * so avoid taking lru_lock and isolating it unnecessarily in an + * admittedly racy check. + */ + if (!page_mapping(page) && + page_count(page) > page_mapcount(page)) + goto isolate_fail; + + /* + * Only allow to migrate anonymous pages in GFP_NOFS context + * because those do not depend on fs locks. + */ + if (!(cc->gfp_mask & __GFP_FS) && page_mapping(page)) + goto isolate_fail; + + /* If we already hold the lock, we can skip some rechecking */ + if (!locked) { + locked = compact_lock_irqsave(&pgdat->lru_lock, + &flags, cc); + + /* Try get exclusive access under lock */ + if (!skip_updated) { + skip_updated = true; + if (test_and_set_skip(cc, page, low_pfn)) + goto isolate_abort; + } + + /* Recheck PageLRU and PageCompound under lock */ + if (!PageLRU(page)) + goto isolate_fail; + + /* + * Page become compound since the non-locked check, + * and it's on LRU. It can only be a THP so the order + * is safe to read and it's 0 for tail pages. + */ + if (unlikely(PageCompound(page) && !cc->alloc_contig)) { + low_pfn += compound_nr(page) - 1; + goto isolate_fail; + } + } + + lruvec = mem_cgroup_page_lruvec(page, pgdat); + + /* Try isolate the page */ + if (__isolate_lru_page(page, isolate_mode) != 0) + goto isolate_fail; + + /* The whole page is taken off the LRU; skip the tail pages. */ + if (PageCompound(page)) + low_pfn += compound_nr(page) - 1; + + /* Successfully isolated */ + del_page_from_lru_list(page, lruvec, page_lru(page)); + mod_node_page_state(page_pgdat(page), + NR_ISOLATED_ANON + page_is_file_lru(page), + thp_nr_pages(page)); + +isolate_success: + list_add(&page->lru, &cc->migratepages); + cc->nr_migratepages += compound_nr(page); + nr_isolated += compound_nr(page); + + /* + * Avoid isolating too much unless this block is being + * rescanned (e.g. dirty/writeback pages, parallel allocation) + * or a lock is contended. For contention, isolate quickly to + * potentially remove one source of contention. + */ + if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX && + !cc->rescan && !cc->contended) { + ++low_pfn; + break; + } + + continue; +isolate_fail: + if (!skip_on_failure) + continue; + + /* + * We have isolated some pages, but then failed. Release them + * instead of migrating, as we cannot form the cc->order buddy + * page anyway. + */ + if (nr_isolated) { + if (locked) { + spin_unlock_irqrestore(&pgdat->lru_lock, flags); + locked = false; + } + putback_movable_pages(&cc->migratepages); + cc->nr_migratepages = 0; + nr_isolated = 0; + } + + if (low_pfn < next_skip_pfn) { + low_pfn = next_skip_pfn - 1; + /* + * The check near the loop beginning would have updated + * next_skip_pfn too, but this is a bit simpler. + */ + next_skip_pfn += 1UL << cc->order; + } + } + + /* + * The PageBuddy() check could have potentially brought us outside + * the range to be scanned. + */ + if (unlikely(low_pfn > end_pfn)) + low_pfn = end_pfn; + +isolate_abort: + if (locked) + spin_unlock_irqrestore(&pgdat->lru_lock, flags); + + /* + * Updated the cached scanner pfn once the pageblock has been scanned + * Pages will either be migrated in which case there is no point + * scanning in the near future or migration failed in which case the + * failure reason may persist. The block is marked for skipping if + * there were no pages isolated in the block or if the block is + * rescanned twice in a row. + */ + if (low_pfn == end_pfn && (!nr_isolated || cc->rescan)) { + if (valid_page && !skip_updated) + set_pageblock_skip(valid_page); + update_cached_migrate(cc, low_pfn); + } + + trace_mm_compaction_isolate_migratepages(start_pfn, low_pfn, + nr_scanned, nr_isolated); + +fatal_pending: + cc->total_migrate_scanned += nr_scanned; + if (nr_isolated) + count_compact_events(COMPACTISOLATED, nr_isolated); + + return low_pfn; +} + +/** + * isolate_migratepages_range() - isolate migrate-able pages in a PFN range + * @cc: Compaction control structure. + * @start_pfn: The first PFN to start isolating. + * @end_pfn: The one-past-last PFN. + * + * Returns zero if isolation fails fatally due to e.g. pending signal. + * Otherwise, function returns one-past-the-last PFN of isolated page + * (which may be greater than end_pfn if end fell in a middle of a THP page). + */ +unsigned long +isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn, + unsigned long end_pfn) +{ + unsigned long pfn, block_start_pfn, block_end_pfn; + + /* Scan block by block. First and last block may be incomplete */ + pfn = start_pfn; + block_start_pfn = pageblock_start_pfn(pfn); + if (block_start_pfn < cc->zone->zone_start_pfn) + block_start_pfn = cc->zone->zone_start_pfn; + block_end_pfn = pageblock_end_pfn(pfn); + + for (; pfn < end_pfn; pfn = block_end_pfn, + block_start_pfn = block_end_pfn, + block_end_pfn += pageblock_nr_pages) { + + block_end_pfn = min(block_end_pfn, end_pfn); + + if (!pageblock_pfn_to_page(block_start_pfn, + block_end_pfn, cc->zone)) + continue; + + pfn = isolate_migratepages_block(cc, pfn, block_end_pfn, + ISOLATE_UNEVICTABLE); + + if (!pfn) + break; + + if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX) + break; + } + + return pfn; +} + +#endif /* CONFIG_COMPACTION || CONFIG_CMA */ +#ifdef CONFIG_COMPACTION + +static bool suitable_migration_source(struct compact_control *cc, + struct page *page) +{ + int block_mt; + + if (pageblock_skip_persistent(page)) + return false; + + if ((cc->mode != MIGRATE_ASYNC) || !cc->direct_compaction) + return true; + + block_mt = get_pageblock_migratetype(page); + + if (cc->migratetype == MIGRATE_MOVABLE) + return is_migrate_movable(block_mt); + else + return block_mt == cc->migratetype; +} + +/* Returns true if the page is within a block suitable for migration to */ +static bool suitable_migration_target(struct compact_control *cc, + struct page *page) +{ + /* If the page is a large free page, then disallow migration */ + if (PageBuddy(page)) { + /* + * We are checking page_order without zone->lock taken. But + * the only small danger is that we skip a potentially suitable + * pageblock, so it's not worth to check order for valid range. + */ + if (buddy_order_unsafe(page) >= pageblock_order) + return false; + } + + if (cc->ignore_block_suitable) + return true; + + /* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */ + if (is_migrate_movable(get_pageblock_migratetype(page))) + return true; + + /* Otherwise skip the block */ + return false; +} + +static inline unsigned int +freelist_scan_limit(struct compact_control *cc) +{ + unsigned short shift = BITS_PER_LONG - 1; + + return (COMPACT_CLUSTER_MAX >> min(shift, cc->fast_search_fail)) + 1; +} + +/* + * Test whether the free scanner has reached the same or lower pageblock than + * the migration scanner, and compaction should thus terminate. + */ +static inline bool compact_scanners_met(struct compact_control *cc) +{ + return (cc->free_pfn >> pageblock_order) + <= (cc->migrate_pfn >> pageblock_order); +} + +/* + * Used when scanning for a suitable migration target which scans freelists + * in reverse. Reorders the list such as the unscanned pages are scanned + * first on the next iteration of the free scanner + */ +static void +move_freelist_head(struct list_head *freelist, struct page *freepage) +{ + LIST_HEAD(sublist); + + if (!list_is_last(freelist, &freepage->lru)) { + list_cut_before(&sublist, freelist, &freepage->lru); + if (!list_empty(&sublist)) + list_splice_tail(&sublist, freelist); + } +} + +/* + * Similar to move_freelist_head except used by the migration scanner + * when scanning forward. It's possible for these list operations to + * move against each other if they search the free list exactly in + * lockstep. + */ +static void +move_freelist_tail(struct list_head *freelist, struct page *freepage) +{ + LIST_HEAD(sublist); + + if (!list_is_first(freelist, &freepage->lru)) { + list_cut_position(&sublist, freelist, &freepage->lru); + if (!list_empty(&sublist)) + list_splice_tail(&sublist, freelist); + } +} + +static void +fast_isolate_around(struct compact_control *cc, unsigned long pfn) +{ + unsigned long start_pfn, end_pfn; + struct page *page; + + /* Do not search around if there are enough pages already */ + if (cc->nr_freepages >= cc->nr_migratepages) + return; + + /* Minimise scanning during async compaction */ + if (cc->direct_compaction && cc->mode == MIGRATE_ASYNC) + return; + + /* Pageblock boundaries */ + start_pfn = max(pageblock_start_pfn(pfn), cc->zone->zone_start_pfn); + end_pfn = min(pageblock_end_pfn(pfn), zone_end_pfn(cc->zone)); + + page = pageblock_pfn_to_page(start_pfn, end_pfn, cc->zone); + if (!page) + return; + + isolate_freepages_block(cc, &start_pfn, end_pfn, &cc->freepages, 1, false); + + /* Skip this pageblock in the future as it's full or nearly full */ + if (cc->nr_freepages < cc->nr_migratepages) + set_pageblock_skip(page); + + return; +} + +/* Search orders in round-robin fashion */ +static int next_search_order(struct compact_control *cc, int order) +{ + order--; + if (order < 0) + order = cc->order - 1; + + /* Search wrapped around? */ + if (order == cc->search_order) { + cc->search_order--; + if (cc->search_order < 0) + cc->search_order = cc->order - 1; + return -1; + } + + return order; +} + +static unsigned long +fast_isolate_freepages(struct compact_control *cc) +{ + unsigned int limit = min(1U, freelist_scan_limit(cc) >> 1); + unsigned int nr_scanned = 0; + unsigned long low_pfn, min_pfn, highest = 0; + unsigned long nr_isolated = 0; + unsigned long distance; + struct page *page = NULL; + bool scan_start = false; + int order; + + /* Full compaction passes in a negative order */ + if (cc->order <= 0) + return cc->free_pfn; + + /* + * If starting the scan, use a deeper search and use the highest + * PFN found if a suitable one is not found. + */ + if (cc->free_pfn >= cc->zone->compact_init_free_pfn) { + limit = pageblock_nr_pages >> 1; + scan_start = true; + } + + /* + * Preferred point is in the top quarter of the scan space but take + * a pfn from the top half if the search is problematic. + */ + distance = (cc->free_pfn - cc->migrate_pfn); + low_pfn = pageblock_start_pfn(cc->free_pfn - (distance >> 2)); + min_pfn = pageblock_start_pfn(cc->free_pfn - (distance >> 1)); + + if (WARN_ON_ONCE(min_pfn > low_pfn)) + low_pfn = min_pfn; + + /* + * Search starts from the last successful isolation order or the next + * order to search after a previous failure + */ + cc->search_order = min_t(unsigned int, cc->order - 1, cc->search_order); + + for (order = cc->search_order; + !page && order >= 0; + order = next_search_order(cc, order)) { + struct free_area *area = &cc->zone->free_area[order]; + struct list_head *freelist; + struct page *freepage; + unsigned long flags; + unsigned int order_scanned = 0; + unsigned long high_pfn = 0; + + if (!area->nr_free) + continue; + + spin_lock_irqsave(&cc->zone->lock, flags); + freelist = &area->free_list[MIGRATE_MOVABLE]; + list_for_each_entry_reverse(freepage, freelist, lru) { + unsigned long pfn; + + order_scanned++; + nr_scanned++; + pfn = page_to_pfn(freepage); + + if (pfn >= highest) + highest = max(pageblock_start_pfn(pfn), + cc->zone->zone_start_pfn); + + if (pfn >= low_pfn) { + cc->fast_search_fail = 0; + cc->search_order = order; + page = freepage; + break; + } + + if (pfn >= min_pfn && pfn > high_pfn) { + high_pfn = pfn; + + /* Shorten the scan if a candidate is found */ + limit >>= 1; + } + + if (order_scanned >= limit) + break; + } + + /* Use a minimum pfn if a preferred one was not found */ + if (!page && high_pfn) { + page = pfn_to_page(high_pfn); + + /* Update freepage for the list reorder below */ + freepage = page; + } + + /* Reorder to so a future search skips recent pages */ + move_freelist_head(freelist, freepage); + + /* Isolate the page if available */ + if (page) { + if (__isolate_free_page(page, order)) { + set_page_private(page, order); + nr_isolated = 1 << order; + cc->nr_freepages += nr_isolated; + list_add_tail(&page->lru, &cc->freepages); + count_compact_events(COMPACTISOLATED, nr_isolated); + } else { + /* If isolation fails, abort the search */ + order = cc->search_order + 1; + page = NULL; + } + } + + spin_unlock_irqrestore(&cc->zone->lock, flags); + + /* + * Smaller scan on next order so the total scan ig related + * to freelist_scan_limit. + */ + if (order_scanned >= limit) + limit = min(1U, limit >> 1); + } + + if (!page) { + cc->fast_search_fail++; + if (scan_start) { + /* + * Use the highest PFN found above min. If one was + * not found, be pessimistic for direct compaction + * and use the min mark. + */ + if (highest) { + page = pfn_to_page(highest); + cc->free_pfn = highest; + } else { + if (cc->direct_compaction && pfn_valid(min_pfn)) { + page = pageblock_pfn_to_page(min_pfn, + min(pageblock_end_pfn(min_pfn), + zone_end_pfn(cc->zone)), + cc->zone); + cc->free_pfn = min_pfn; + } + } + } + } + + if (highest && highest >= cc->zone->compact_cached_free_pfn) { + highest -= pageblock_nr_pages; + cc->zone->compact_cached_free_pfn = highest; + } + + cc->total_free_scanned += nr_scanned; + if (!page) + return cc->free_pfn; + + low_pfn = page_to_pfn(page); + fast_isolate_around(cc, low_pfn); + return low_pfn; +} + +/* + * Based on information in the current compact_control, find blocks + * suitable for isolating free pages from and then isolate them. + */ +static void isolate_freepages(struct compact_control *cc) +{ + struct zone *zone = cc->zone; + struct page *page; + unsigned long block_start_pfn; /* start of current pageblock */ + unsigned long isolate_start_pfn; /* exact pfn we start at */ + unsigned long block_end_pfn; /* end of current pageblock */ + unsigned long low_pfn; /* lowest pfn scanner is able to scan */ + struct list_head *freelist = &cc->freepages; + unsigned int stride; + + /* Try a small search of the free lists for a candidate */ + isolate_start_pfn = fast_isolate_freepages(cc); + if (cc->nr_freepages) + goto splitmap; + + /* + * Initialise the free scanner. The starting point is where we last + * successfully isolated from, zone-cached value, or the end of the + * zone when isolating for the first time. For looping we also need + * this pfn aligned down to the pageblock boundary, because we do + * block_start_pfn -= pageblock_nr_pages in the for loop. + * For ending point, take care when isolating in last pageblock of a + * zone which ends in the middle of a pageblock. + * The low boundary is the end of the pageblock the migration scanner + * is using. + */ + isolate_start_pfn = cc->free_pfn; + block_start_pfn = pageblock_start_pfn(isolate_start_pfn); + block_end_pfn = min(block_start_pfn + pageblock_nr_pages, + zone_end_pfn(zone)); + low_pfn = pageblock_end_pfn(cc->migrate_pfn); + stride = cc->mode == MIGRATE_ASYNC ? COMPACT_CLUSTER_MAX : 1; + + /* + * Isolate free pages until enough are available to migrate the + * pages on cc->migratepages. We stop searching if the migrate + * and free page scanners meet or enough free pages are isolated. + */ + for (; block_start_pfn >= low_pfn; + block_end_pfn = block_start_pfn, + block_start_pfn -= pageblock_nr_pages, + isolate_start_pfn = block_start_pfn) { + unsigned long nr_isolated; + + /* + * This can iterate a massively long zone without finding any + * suitable migration targets, so periodically check resched. + */ + if (!(block_start_pfn % (SWAP_CLUSTER_MAX * pageblock_nr_pages))) + cond_resched(); + + page = pageblock_pfn_to_page(block_start_pfn, block_end_pfn, + zone); + if (!page) + continue; + + /* Check the block is suitable for migration */ + if (!suitable_migration_target(cc, page)) + continue; + + /* If isolation recently failed, do not retry */ + if (!isolation_suitable(cc, page)) + continue; + + /* Found a block suitable for isolating free pages from. */ + nr_isolated = isolate_freepages_block(cc, &isolate_start_pfn, + block_end_pfn, freelist, stride, false); + + /* Update the skip hint if the full pageblock was scanned */ + if (isolate_start_pfn == block_end_pfn) + update_pageblock_skip(cc, page, block_start_pfn); + + /* Are enough freepages isolated? */ + if (cc->nr_freepages >= cc->nr_migratepages) { + if (isolate_start_pfn >= block_end_pfn) { + /* + * Restart at previous pageblock if more + * freepages can be isolated next time. + */ + isolate_start_pfn = + block_start_pfn - pageblock_nr_pages; + } + break; + } else if (isolate_start_pfn < block_end_pfn) { + /* + * If isolation failed early, do not continue + * needlessly. + */ + break; + } + + /* Adjust stride depending on isolation */ + if (nr_isolated) { + stride = 1; + continue; + } + stride = min_t(unsigned int, COMPACT_CLUSTER_MAX, stride << 1); + } + + /* + * Record where the free scanner will restart next time. Either we + * broke from the loop and set isolate_start_pfn based on the last + * call to isolate_freepages_block(), or we met the migration scanner + * and the loop terminated due to isolate_start_pfn < low_pfn + */ + cc->free_pfn = isolate_start_pfn; + +splitmap: + /* __isolate_free_page() does not map the pages */ + split_map_pages(freelist); +} + +/* + * This is a migrate-callback that "allocates" freepages by taking pages + * from the isolated freelists in the block we are migrating to. + */ +static struct page *compaction_alloc(struct page *migratepage, + unsigned long data) +{ + struct compact_control *cc = (struct compact_control *)data; + struct page *freepage; + + if (list_empty(&cc->freepages)) { + isolate_freepages(cc); + + if (list_empty(&cc->freepages)) + return NULL; + } + + freepage = list_entry(cc->freepages.next, struct page, lru); + list_del(&freepage->lru); + cc->nr_freepages--; + + return freepage; +} + +/* + * This is a migrate-callback that "frees" freepages back to the isolated + * freelist. All pages on the freelist are from the same zone, so there is no + * special handling needed for NUMA. + */ +static void compaction_free(struct page *page, unsigned long data) +{ + struct compact_control *cc = (struct compact_control *)data; + + list_add(&page->lru, &cc->freepages); + cc->nr_freepages++; +} + +/* possible outcome of isolate_migratepages */ +typedef enum { + ISOLATE_ABORT, /* Abort compaction now */ + ISOLATE_NONE, /* No pages isolated, continue scanning */ + ISOLATE_SUCCESS, /* Pages isolated, migrate */ +} isolate_migrate_t; + +/* + * Allow userspace to control policy on scanning the unevictable LRU for + * compactable pages. + */ +#ifdef CONFIG_PREEMPT_RT +int sysctl_compact_unevictable_allowed __read_mostly = 0; +#else +int sysctl_compact_unevictable_allowed __read_mostly = 1; +#endif + +static inline void +update_fast_start_pfn(struct compact_control *cc, unsigned long pfn) +{ + if (cc->fast_start_pfn == ULONG_MAX) + return; + + if (!cc->fast_start_pfn) + cc->fast_start_pfn = pfn; + + cc->fast_start_pfn = min(cc->fast_start_pfn, pfn); +} + +static inline unsigned long +reinit_migrate_pfn(struct compact_control *cc) +{ + if (!cc->fast_start_pfn || cc->fast_start_pfn == ULONG_MAX) + return cc->migrate_pfn; + + cc->migrate_pfn = cc->fast_start_pfn; + cc->fast_start_pfn = ULONG_MAX; + + return cc->migrate_pfn; +} + +/* + * Briefly search the free lists for a migration source that already has + * some free pages to reduce the number of pages that need migration + * before a pageblock is free. + */ +static unsigned long fast_find_migrateblock(struct compact_control *cc) +{ + unsigned int limit = freelist_scan_limit(cc); + unsigned int nr_scanned = 0; + unsigned long distance; + unsigned long pfn = cc->migrate_pfn; + unsigned long high_pfn; + int order; + bool found_block = false; + + /* Skip hints are relied on to avoid repeats on the fast search */ + if (cc->ignore_skip_hint) + return pfn; + + /* + * If the migrate_pfn is not at the start of a zone or the start + * of a pageblock then assume this is a continuation of a previous + * scan restarted due to COMPACT_CLUSTER_MAX. + */ + if (pfn != cc->zone->zone_start_pfn && pfn != pageblock_start_pfn(pfn)) + return pfn; + + /* + * For smaller orders, just linearly scan as the number of pages + * to migrate should be relatively small and does not necessarily + * justify freeing up a large block for a small allocation. + */ + if (cc->order <= PAGE_ALLOC_COSTLY_ORDER) + return pfn; + + /* + * Only allow kcompactd and direct requests for movable pages to + * quickly clear out a MOVABLE pageblock for allocation. This + * reduces the risk that a large movable pageblock is freed for + * an unmovable/reclaimable small allocation. + */ + if (cc->direct_compaction && cc->migratetype != MIGRATE_MOVABLE) + return pfn; + + /* + * When starting the migration scanner, pick any pageblock within the + * first half of the search space. Otherwise try and pick a pageblock + * within the first eighth to reduce the chances that a migration + * target later becomes a source. + */ + distance = (cc->free_pfn - cc->migrate_pfn) >> 1; + if (cc->migrate_pfn != cc->zone->zone_start_pfn) + distance >>= 2; + high_pfn = pageblock_start_pfn(cc->migrate_pfn + distance); + + for (order = cc->order - 1; + order >= PAGE_ALLOC_COSTLY_ORDER && !found_block && nr_scanned < limit; + order--) { + struct free_area *area = &cc->zone->free_area[order]; + struct list_head *freelist; + unsigned long flags; + struct page *freepage; + + if (!area->nr_free) + continue; + + spin_lock_irqsave(&cc->zone->lock, flags); + freelist = &area->free_list[MIGRATE_MOVABLE]; + list_for_each_entry(freepage, freelist, lru) { + unsigned long free_pfn; + + if (nr_scanned++ >= limit) { + move_freelist_tail(freelist, freepage); + break; + } + + free_pfn = page_to_pfn(freepage); + if (free_pfn < high_pfn) { + /* + * Avoid if skipped recently. Ideally it would + * move to the tail but even safe iteration of + * the list assumes an entry is deleted, not + * reordered. + */ + if (get_pageblock_skip(freepage)) + continue; + + /* Reorder to so a future search skips recent pages */ + move_freelist_tail(freelist, freepage); + + update_fast_start_pfn(cc, free_pfn); + pfn = pageblock_start_pfn(free_pfn); + if (pfn < cc->zone->zone_start_pfn) + pfn = cc->zone->zone_start_pfn; + cc->fast_search_fail = 0; + found_block = true; + set_pageblock_skip(freepage); + break; + } + } + spin_unlock_irqrestore(&cc->zone->lock, flags); + } + + cc->total_migrate_scanned += nr_scanned; + + /* + * If fast scanning failed then use a cached entry for a page block + * that had free pages as the basis for starting a linear scan. + */ + if (!found_block) { + cc->fast_search_fail++; + pfn = reinit_migrate_pfn(cc); + } + return pfn; +} + +/* + * Isolate all pages that can be migrated from the first suitable block, + * starting at the block pointed to by the migrate scanner pfn within + * compact_control. + */ +static isolate_migrate_t isolate_migratepages(struct compact_control *cc) +{ + unsigned long block_start_pfn; + unsigned long block_end_pfn; + unsigned long low_pfn; + struct page *page; + const isolate_mode_t isolate_mode = + (sysctl_compact_unevictable_allowed ? ISOLATE_UNEVICTABLE : 0) | + (cc->mode != MIGRATE_SYNC ? ISOLATE_ASYNC_MIGRATE : 0); + bool fast_find_block; + + /* + * Start at where we last stopped, or beginning of the zone as + * initialized by compact_zone(). The first failure will use + * the lowest PFN as the starting point for linear scanning. + */ + low_pfn = fast_find_migrateblock(cc); + block_start_pfn = pageblock_start_pfn(low_pfn); + if (block_start_pfn < cc->zone->zone_start_pfn) + block_start_pfn = cc->zone->zone_start_pfn; + + /* + * fast_find_migrateblock marks a pageblock skipped so to avoid + * the isolation_suitable check below, check whether the fast + * search was successful. + */ + fast_find_block = low_pfn != cc->migrate_pfn && !cc->fast_search_fail; + + /* Only scan within a pageblock boundary */ + block_end_pfn = pageblock_end_pfn(low_pfn); + + /* + * Iterate over whole pageblocks until we find the first suitable. + * Do not cross the free scanner. + */ + for (; block_end_pfn <= cc->free_pfn; + fast_find_block = false, + low_pfn = block_end_pfn, + block_start_pfn = block_end_pfn, + block_end_pfn += pageblock_nr_pages) { + + /* + * This can potentially iterate a massively long zone with + * many pageblocks unsuitable, so periodically check if we + * need to schedule. + */ + if (!(low_pfn % (SWAP_CLUSTER_MAX * pageblock_nr_pages))) + cond_resched(); + + page = pageblock_pfn_to_page(block_start_pfn, + block_end_pfn, cc->zone); + if (!page) + continue; + + /* + * If isolation recently failed, do not retry. Only check the + * pageblock once. COMPACT_CLUSTER_MAX causes a pageblock + * to be visited multiple times. Assume skip was checked + * before making it "skip" so other compaction instances do + * not scan the same block. + */ + if (IS_ALIGNED(low_pfn, pageblock_nr_pages) && + !fast_find_block && !isolation_suitable(cc, page)) + continue; + + /* + * For async compaction, also only scan in MOVABLE blocks + * without huge pages. Async compaction is optimistic to see + * if the minimum amount of work satisfies the allocation. + * The cached PFN is updated as it's possible that all + * remaining blocks between source and target are unsuitable + * and the compaction scanners fail to meet. + */ + if (!suitable_migration_source(cc, page)) { + update_cached_migrate(cc, block_end_pfn); + continue; + } + + /* Perform the isolation */ + low_pfn = isolate_migratepages_block(cc, low_pfn, + block_end_pfn, isolate_mode); + + if (!low_pfn) + return ISOLATE_ABORT; + + /* + * Either we isolated something and proceed with migration. Or + * we failed and compact_zone should decide if we should + * continue or not. + */ + break; + } + + /* Record where migration scanner will be restarted. */ + cc->migrate_pfn = low_pfn; + + return cc->nr_migratepages ? ISOLATE_SUCCESS : ISOLATE_NONE; +} + +/* + * order == -1 is expected when compacting via + * /proc/sys/vm/compact_memory + */ +static inline bool is_via_compact_memory(int order) +{ + return order == -1; +} + +static bool kswapd_is_running(pg_data_t *pgdat) +{ + return pgdat->kswapd && (pgdat->kswapd->state == TASK_RUNNING); +} + +/* + * A zone's fragmentation score is the external fragmentation wrt to the + * COMPACTION_HPAGE_ORDER scaled by the zone's size. It returns a value + * in the range [0, 100]. + * + * The scaling factor ensures that proactive compaction focuses on larger + * zones like ZONE_NORMAL, rather than smaller, specialized zones like + * ZONE_DMA32. For smaller zones, the score value remains close to zero, + * and thus never exceeds the high threshold for proactive compaction. + */ +static unsigned int fragmentation_score_zone(struct zone *zone) +{ + unsigned long score; + + score = zone->present_pages * + extfrag_for_order(zone, COMPACTION_HPAGE_ORDER); + return div64_ul(score, zone->zone_pgdat->node_present_pages + 1); +} + +/* + * The per-node proactive (background) compaction process is started by its + * corresponding kcompactd thread when the node's fragmentation score + * exceeds the high threshold. The compaction process remains active till + * the node's score falls below the low threshold, or one of the back-off + * conditions is met. + */ +static unsigned int fragmentation_score_node(pg_data_t *pgdat) +{ + unsigned int score = 0; + int zoneid; + + for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) { + struct zone *zone; + + zone = &pgdat->node_zones[zoneid]; + score += fragmentation_score_zone(zone); + } + + return score; +} + +static unsigned int fragmentation_score_wmark(pg_data_t *pgdat, bool low) +{ + unsigned int wmark_low; + + /* + * Cap the low watermak to avoid excessive compaction + * activity in case a user sets the proactivess tunable + * close to 100 (maximum). + */ + wmark_low = max(100U - sysctl_compaction_proactiveness, 5U); + return low ? wmark_low : min(wmark_low + 10, 100U); +} + +static bool should_proactive_compact_node(pg_data_t *pgdat) +{ + int wmark_high; + + if (!sysctl_compaction_proactiveness || kswapd_is_running(pgdat)) + return false; + + wmark_high = fragmentation_score_wmark(pgdat, false); + return fragmentation_score_node(pgdat) > wmark_high; +} + +static enum compact_result __compact_finished(struct compact_control *cc) +{ + unsigned int order; + const int migratetype = cc->migratetype; + int ret; + + /* Compaction run completes if the migrate and free scanner meet */ + if (compact_scanners_met(cc)) { + /* Let the next compaction start anew. */ + reset_cached_positions(cc->zone); + + /* + * Mark that the PG_migrate_skip information should be cleared + * by kswapd when it goes to sleep. kcompactd does not set the + * flag itself as the decision to be clear should be directly + * based on an allocation request. + */ + if (cc->direct_compaction) + cc->zone->compact_blockskip_flush = true; + + if (cc->whole_zone) + return COMPACT_COMPLETE; + else + return COMPACT_PARTIAL_SKIPPED; + } + + if (cc->proactive_compaction) { + int score, wmark_low; + pg_data_t *pgdat; + + pgdat = cc->zone->zone_pgdat; + if (kswapd_is_running(pgdat)) + return COMPACT_PARTIAL_SKIPPED; + + score = fragmentation_score_zone(cc->zone); + wmark_low = fragmentation_score_wmark(pgdat, true); + + if (score > wmark_low) + ret = COMPACT_CONTINUE; + else + ret = COMPACT_SUCCESS; + + goto out; + } + + if (is_via_compact_memory(cc->order)) + return COMPACT_CONTINUE; + + /* + * Always finish scanning a pageblock to reduce the possibility of + * fallbacks in the future. This is particularly important when + * migration source is unmovable/reclaimable but it's not worth + * special casing. + */ + if (!IS_ALIGNED(cc->migrate_pfn, pageblock_nr_pages)) + return COMPACT_CONTINUE; + + /* Direct compactor: Is a suitable page free? */ + ret = COMPACT_NO_SUITABLE_PAGE; + for (order = cc->order; order < MAX_ORDER; order++) { + struct free_area *area = &cc->zone->free_area[order]; + bool can_steal; + + /* Job done if page is free of the right migratetype */ + if (!free_area_empty(area, migratetype)) + return COMPACT_SUCCESS; + +#ifdef CONFIG_CMA + /* MIGRATE_MOVABLE can fallback on MIGRATE_CMA */ + if (migratetype == MIGRATE_MOVABLE && + !free_area_empty(area, MIGRATE_CMA)) + return COMPACT_SUCCESS; +#endif + /* + * Job done if allocation would steal freepages from + * other migratetype buddy lists. + */ + if (find_suitable_fallback(area, order, migratetype, + true, &can_steal) != -1) { + + /* movable pages are OK in any pageblock */ + if (migratetype == MIGRATE_MOVABLE) + return COMPACT_SUCCESS; + + /* + * We are stealing for a non-movable allocation. Make + * sure we finish compacting the current pageblock + * first so it is as free as possible and we won't + * have to steal another one soon. This only applies + * to sync compaction, as async compaction operates + * on pageblocks of the same migratetype. + */ + if (cc->mode == MIGRATE_ASYNC || + IS_ALIGNED(cc->migrate_pfn, + pageblock_nr_pages)) { + return COMPACT_SUCCESS; + } + + ret = COMPACT_CONTINUE; + break; + } + } + +out: + if (cc->contended || fatal_signal_pending(current)) + ret = COMPACT_CONTENDED; + + return ret; +} + +static enum compact_result compact_finished(struct compact_control *cc) +{ + int ret; + + ret = __compact_finished(cc); + trace_mm_compaction_finished(cc->zone, cc->order, ret); + if (ret == COMPACT_NO_SUITABLE_PAGE) + ret = COMPACT_CONTINUE; + + return ret; +} + +/* + * compaction_suitable: Is this suitable to run compaction on this zone now? + * Returns + * COMPACT_SKIPPED - If there are too few free pages for compaction + * COMPACT_SUCCESS - If the allocation would succeed without compaction + * COMPACT_CONTINUE - If compaction should run now + */ +static enum compact_result __compaction_suitable(struct zone *zone, int order, + unsigned int alloc_flags, + int highest_zoneidx, + unsigned long wmark_target) +{ + unsigned long watermark; + + if (is_via_compact_memory(order)) + return COMPACT_CONTINUE; + + watermark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK); + /* + * If watermarks for high-order allocation are already met, there + * should be no need for compaction at all. + */ + if (zone_watermark_ok(zone, order, watermark, highest_zoneidx, + alloc_flags)) + return COMPACT_SUCCESS; + + /* + * Watermarks for order-0 must be met for compaction to be able to + * isolate free pages for migration targets. This means that the + * watermark and alloc_flags have to match, or be more pessimistic than + * the check in __isolate_free_page(). We don't use the direct + * compactor's alloc_flags, as they are not relevant for freepage + * isolation. We however do use the direct compactor's highest_zoneidx + * to skip over zones where lowmem reserves would prevent allocation + * even if compaction succeeds. + * For costly orders, we require low watermark instead of min for + * compaction to proceed to increase its chances. + * ALLOC_CMA is used, as pages in CMA pageblocks are considered + * suitable migration targets + */ + watermark = (order > PAGE_ALLOC_COSTLY_ORDER) ? + low_wmark_pages(zone) : min_wmark_pages(zone); + watermark += compact_gap(order); + if (!__zone_watermark_ok(zone, 0, watermark, highest_zoneidx, + ALLOC_CMA, wmark_target)) + return COMPACT_SKIPPED; + + return COMPACT_CONTINUE; +} + +enum compact_result compaction_suitable(struct zone *zone, int order, + unsigned int alloc_flags, + int highest_zoneidx) +{ + enum compact_result ret; + int fragindex; + + ret = __compaction_suitable(zone, order, alloc_flags, highest_zoneidx, + zone_page_state(zone, NR_FREE_PAGES)); + /* + * fragmentation index determines if allocation failures are due to + * low memory or external fragmentation + * + * index of -1000 would imply allocations might succeed depending on + * watermarks, but we already failed the high-order watermark check + * index towards 0 implies failure is due to lack of memory + * index towards 1000 implies failure is due to fragmentation + * + * Only compact if a failure would be due to fragmentation. Also + * ignore fragindex for non-costly orders where the alternative to + * a successful reclaim/compaction is OOM. Fragindex and the + * vm.extfrag_threshold sysctl is meant as a heuristic to prevent + * excessive compaction for costly orders, but it should not be at the + * expense of system stability. + */ + if (ret == COMPACT_CONTINUE && (order > PAGE_ALLOC_COSTLY_ORDER)) { + fragindex = fragmentation_index(zone, order); + if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold) + ret = COMPACT_NOT_SUITABLE_ZONE; + } + + trace_mm_compaction_suitable(zone, order, ret); + if (ret == COMPACT_NOT_SUITABLE_ZONE) + ret = COMPACT_SKIPPED; + + return ret; +} + +bool compaction_zonelist_suitable(struct alloc_context *ac, int order, + int alloc_flags) +{ + struct zone *zone; + struct zoneref *z; + + /* + * Make sure at least one zone would pass __compaction_suitable if we continue + * retrying the reclaim. + */ + for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, + ac->highest_zoneidx, ac->nodemask) { + unsigned long available; + enum compact_result compact_result; + + /* + * Do not consider all the reclaimable memory because we do not + * want to trash just for a single high order allocation which + * is even not guaranteed to appear even if __compaction_suitable + * is happy about the watermark check. + */ + available = zone_reclaimable_pages(zone) / order; + available += zone_page_state_snapshot(zone, NR_FREE_PAGES); + compact_result = __compaction_suitable(zone, order, alloc_flags, + ac->highest_zoneidx, available); + if (compact_result != COMPACT_SKIPPED) + return true; + } + + return false; +} + +static enum compact_result +compact_zone(struct compact_control *cc, struct capture_control *capc) +{ + enum compact_result ret; + unsigned long start_pfn = cc->zone->zone_start_pfn; + unsigned long end_pfn = zone_end_pfn(cc->zone); + unsigned long last_migrated_pfn; + const bool sync = cc->mode != MIGRATE_ASYNC; + bool update_cached; + + /* + * These counters track activities during zone compaction. Initialize + * them before compacting a new zone. + */ + cc->total_migrate_scanned = 0; + cc->total_free_scanned = 0; + cc->nr_migratepages = 0; + cc->nr_freepages = 0; + INIT_LIST_HEAD(&cc->freepages); + INIT_LIST_HEAD(&cc->migratepages); + + cc->migratetype = gfp_migratetype(cc->gfp_mask); + ret = compaction_suitable(cc->zone, cc->order, cc->alloc_flags, + cc->highest_zoneidx); + /* Compaction is likely to fail */ + if (ret == COMPACT_SUCCESS || ret == COMPACT_SKIPPED) + return ret; + + /* huh, compaction_suitable is returning something unexpected */ + VM_BUG_ON(ret != COMPACT_CONTINUE); + + /* + * Clear pageblock skip if there were failures recently and compaction + * is about to be retried after being deferred. + */ + if (compaction_restarting(cc->zone, cc->order)) + __reset_isolation_suitable(cc->zone); + + /* + * Setup to move all movable pages to the end of the zone. Used cached + * information on where the scanners should start (unless we explicitly + * want to compact the whole zone), but check that it is initialised + * by ensuring the values are within zone boundaries. + */ + cc->fast_start_pfn = 0; + if (cc->whole_zone) { + cc->migrate_pfn = start_pfn; + cc->free_pfn = pageblock_start_pfn(end_pfn - 1); + } else { + cc->migrate_pfn = cc->zone->compact_cached_migrate_pfn[sync]; + cc->free_pfn = cc->zone->compact_cached_free_pfn; + if (cc->free_pfn < start_pfn || cc->free_pfn >= end_pfn) { + cc->free_pfn = pageblock_start_pfn(end_pfn - 1); + cc->zone->compact_cached_free_pfn = cc->free_pfn; + } + if (cc->migrate_pfn < start_pfn || cc->migrate_pfn >= end_pfn) { + cc->migrate_pfn = start_pfn; + cc->zone->compact_cached_migrate_pfn[0] = cc->migrate_pfn; + cc->zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn; + } + + if (cc->migrate_pfn <= cc->zone->compact_init_migrate_pfn) + cc->whole_zone = true; + } + + last_migrated_pfn = 0; + + /* + * Migrate has separate cached PFNs for ASYNC and SYNC* migration on + * the basis that some migrations will fail in ASYNC mode. However, + * if the cached PFNs match and pageblocks are skipped due to having + * no isolation candidates, then the sync state does not matter. + * Until a pageblock with isolation candidates is found, keep the + * cached PFNs in sync to avoid revisiting the same blocks. + */ + update_cached = !sync && + cc->zone->compact_cached_migrate_pfn[0] == cc->zone->compact_cached_migrate_pfn[1]; + + trace_mm_compaction_begin(start_pfn, cc->migrate_pfn, + cc->free_pfn, end_pfn, sync); + + migrate_prep_local(); + + while ((ret = compact_finished(cc)) == COMPACT_CONTINUE) { + int err; + unsigned long start_pfn = cc->migrate_pfn; + + /* + * Avoid multiple rescans which can happen if a page cannot be + * isolated (dirty/writeback in async mode) or if the migrated + * pages are being allocated before the pageblock is cleared. + * The first rescan will capture the entire pageblock for + * migration. If it fails, it'll be marked skip and scanning + * will proceed as normal. + */ + cc->rescan = false; + if (pageblock_start_pfn(last_migrated_pfn) == + pageblock_start_pfn(start_pfn)) { + cc->rescan = true; + } + + switch (isolate_migratepages(cc)) { + case ISOLATE_ABORT: + ret = COMPACT_CONTENDED; + putback_movable_pages(&cc->migratepages); + cc->nr_migratepages = 0; + goto out; + case ISOLATE_NONE: + if (update_cached) { + cc->zone->compact_cached_migrate_pfn[1] = + cc->zone->compact_cached_migrate_pfn[0]; + } + + /* + * We haven't isolated and migrated anything, but + * there might still be unflushed migrations from + * previous cc->order aligned block. + */ + goto check_drain; + case ISOLATE_SUCCESS: + update_cached = false; + last_migrated_pfn = start_pfn; + ; + } + + err = migrate_pages(&cc->migratepages, compaction_alloc, + compaction_free, (unsigned long)cc, cc->mode, + MR_COMPACTION); + + trace_mm_compaction_migratepages(cc->nr_migratepages, err, + &cc->migratepages); + + /* All pages were either migrated or will be released */ + cc->nr_migratepages = 0; + if (err) { + putback_movable_pages(&cc->migratepages); + /* + * migrate_pages() may return -ENOMEM when scanners meet + * and we want compact_finished() to detect it + */ + if (err == -ENOMEM && !compact_scanners_met(cc)) { + ret = COMPACT_CONTENDED; + goto out; + } + /* + * We failed to migrate at least one page in the current + * order-aligned block, so skip the rest of it. + */ + if (cc->direct_compaction && + (cc->mode == MIGRATE_ASYNC)) { + cc->migrate_pfn = block_end_pfn( + cc->migrate_pfn - 1, cc->order); + /* Draining pcplists is useless in this case */ + last_migrated_pfn = 0; + } + } + +check_drain: + /* + * Has the migration scanner moved away from the previous + * cc->order aligned block where we migrated from? If yes, + * flush the pages that were freed, so that they can merge and + * compact_finished() can detect immediately if allocation + * would succeed. + */ + if (cc->order > 0 && last_migrated_pfn) { + unsigned long current_block_start = + block_start_pfn(cc->migrate_pfn, cc->order); + + if (last_migrated_pfn < current_block_start) { + lru_add_drain_cpu_zone(cc->zone); + /* No more flushing until we migrate again */ + last_migrated_pfn = 0; + } + } + + /* Stop if a page has been captured */ + if (capc && capc->page) { + ret = COMPACT_SUCCESS; + break; + } + } + +out: + /* + * Release free pages and update where the free scanner should restart, + * so we don't leave any returned pages behind in the next attempt. + */ + if (cc->nr_freepages > 0) { + unsigned long free_pfn = release_freepages(&cc->freepages); + + cc->nr_freepages = 0; + VM_BUG_ON(free_pfn == 0); + /* The cached pfn is always the first in a pageblock */ + free_pfn = pageblock_start_pfn(free_pfn); + /* + * Only go back, not forward. The cached pfn might have been + * already reset to zone end in compact_finished() + */ + if (free_pfn > cc->zone->compact_cached_free_pfn) + cc->zone->compact_cached_free_pfn = free_pfn; + } + + count_compact_events(COMPACTMIGRATE_SCANNED, cc->total_migrate_scanned); + count_compact_events(COMPACTFREE_SCANNED, cc->total_free_scanned); + + trace_mm_compaction_end(start_pfn, cc->migrate_pfn, + cc->free_pfn, end_pfn, sync, ret); + + return ret; +} + +static enum compact_result compact_zone_order(struct zone *zone, int order, + gfp_t gfp_mask, enum compact_priority prio, + unsigned int alloc_flags, int highest_zoneidx, + struct page **capture) +{ + enum compact_result ret; + struct compact_control cc = { + .order = order, + .search_order = order, + .gfp_mask = gfp_mask, + .zone = zone, + .mode = (prio == COMPACT_PRIO_ASYNC) ? + MIGRATE_ASYNC : MIGRATE_SYNC_LIGHT, + .alloc_flags = alloc_flags, + .highest_zoneidx = highest_zoneidx, + .direct_compaction = true, + .whole_zone = (prio == MIN_COMPACT_PRIORITY), + .ignore_skip_hint = (prio == MIN_COMPACT_PRIORITY), + .ignore_block_suitable = (prio == MIN_COMPACT_PRIORITY) + }; + struct capture_control capc = { + .cc = &cc, + .page = NULL, + }; + + /* + * Make sure the structs are really initialized before we expose the + * capture control, in case we are interrupted and the interrupt handler + * frees a page. + */ + barrier(); + WRITE_ONCE(current->capture_control, &capc); + + ret = compact_zone(&cc, &capc); + + VM_BUG_ON(!list_empty(&cc.freepages)); + VM_BUG_ON(!list_empty(&cc.migratepages)); + + /* + * Make sure we hide capture control first before we read the captured + * page pointer, otherwise an interrupt could free and capture a page + * and we would leak it. + */ + WRITE_ONCE(current->capture_control, NULL); + *capture = READ_ONCE(capc.page); + + return ret; +} + +int sysctl_extfrag_threshold = 500; + +/** + * try_to_compact_pages - Direct compact to satisfy a high-order allocation + * @gfp_mask: The GFP mask of the current allocation + * @order: The order of the current allocation + * @alloc_flags: The allocation flags of the current allocation + * @ac: The context of current allocation + * @prio: Determines how hard direct compaction should try to succeed + * @capture: Pointer to free page created by compaction will be stored here + * + * This is the main entry point for direct page compaction. + */ +enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, + unsigned int alloc_flags, const struct alloc_context *ac, + enum compact_priority prio, struct page **capture) +{ + int may_perform_io = gfp_mask & __GFP_IO; + struct zoneref *z; + struct zone *zone; + enum compact_result rc = COMPACT_SKIPPED; + + /* + * Check if the GFP flags allow compaction - GFP_NOIO is really + * tricky context because the migration might require IO + */ + if (!may_perform_io) + return COMPACT_SKIPPED; + + trace_mm_compaction_try_to_compact_pages(order, gfp_mask, prio); + + /* Compact each zone in the list */ + for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, + ac->highest_zoneidx, ac->nodemask) { + enum compact_result status; + + if (prio > MIN_COMPACT_PRIORITY + && compaction_deferred(zone, order)) { + rc = max_t(enum compact_result, COMPACT_DEFERRED, rc); + continue; + } + + status = compact_zone_order(zone, order, gfp_mask, prio, + alloc_flags, ac->highest_zoneidx, capture); + rc = max(status, rc); + + /* The allocation should succeed, stop compacting */ + if (status == COMPACT_SUCCESS) { + /* + * We think the allocation will succeed in this zone, + * but it is not certain, hence the false. The caller + * will repeat this with true if allocation indeed + * succeeds in this zone. + */ + compaction_defer_reset(zone, order, false); + + break; + } + + if (prio != COMPACT_PRIO_ASYNC && (status == COMPACT_COMPLETE || + status == COMPACT_PARTIAL_SKIPPED)) + /* + * We think that allocation won't succeed in this zone + * so we defer compaction there. If it ends up + * succeeding after all, it will be reset. + */ + defer_compaction(zone, order); + + /* + * We might have stopped compacting due to need_resched() in + * async compaction, or due to a fatal signal detected. In that + * case do not try further zones + */ + if ((prio == COMPACT_PRIO_ASYNC && need_resched()) + || fatal_signal_pending(current)) + break; + } + + return rc; +} + +/* + * Compact all zones within a node till each zone's fragmentation score + * reaches within proactive compaction thresholds (as determined by the + * proactiveness tunable). + * + * It is possible that the function returns before reaching score targets + * due to various back-off conditions, such as, contention on per-node or + * per-zone locks. + */ +static void proactive_compact_node(pg_data_t *pgdat) +{ + int zoneid; + struct zone *zone; + struct compact_control cc = { + .order = -1, + .mode = MIGRATE_SYNC_LIGHT, + .ignore_skip_hint = true, + .whole_zone = true, + .gfp_mask = GFP_KERNEL, + .proactive_compaction = true, + }; + + for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) { + zone = &pgdat->node_zones[zoneid]; + if (!populated_zone(zone)) + continue; + + cc.zone = zone; + + compact_zone(&cc, NULL); + + VM_BUG_ON(!list_empty(&cc.freepages)); + VM_BUG_ON(!list_empty(&cc.migratepages)); + } +} + +/* Compact all zones within a node */ +static void compact_node(int nid) +{ + pg_data_t *pgdat = NODE_DATA(nid); + int zoneid; + struct zone *zone; + struct compact_control cc = { + .order = -1, + .mode = MIGRATE_SYNC, + .ignore_skip_hint = true, + .whole_zone = true, + .gfp_mask = GFP_KERNEL, + }; + + + for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) { + + zone = &pgdat->node_zones[zoneid]; + if (!populated_zone(zone)) + continue; + + cc.zone = zone; + + compact_zone(&cc, NULL); + + VM_BUG_ON(!list_empty(&cc.freepages)); + VM_BUG_ON(!list_empty(&cc.migratepages)); + } +} + +/* Compact all nodes in the system */ +static void compact_nodes(void) +{ + int nid; + + /* Flush pending updates to the LRU lists */ + lru_add_drain_all(); + + for_each_online_node(nid) + compact_node(nid); +} + +/* The written value is actually unused, all memory is compacted */ +int sysctl_compact_memory; + +/* + * Tunable for proactive compaction. It determines how + * aggressively the kernel should compact memory in the + * background. It takes values in the range [0, 100]. + */ +unsigned int __read_mostly sysctl_compaction_proactiveness = 20; + +/* + * This is the entry point for compacting all nodes via + * /proc/sys/vm/compact_memory + */ +int sysctl_compaction_handler(struct ctl_table *table, int write, + void *buffer, size_t *length, loff_t *ppos) +{ + if (write) + compact_nodes(); + + return 0; +} + +#if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA) +static ssize_t sysfs_compact_node(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + int nid = dev->id; + + if (nid >= 0 && nid < nr_node_ids && node_online(nid)) { + /* Flush pending updates to the LRU lists */ + lru_add_drain_all(); + + compact_node(nid); + } + + return count; +} +static DEVICE_ATTR(compact, 0200, NULL, sysfs_compact_node); + +int compaction_register_node(struct node *node) +{ + return device_create_file(&node->dev, &dev_attr_compact); +} + +void compaction_unregister_node(struct node *node) +{ + return device_remove_file(&node->dev, &dev_attr_compact); +} +#endif /* CONFIG_SYSFS && CONFIG_NUMA */ + +static inline bool kcompactd_work_requested(pg_data_t *pgdat) +{ + return pgdat->kcompactd_max_order > 0 || kthread_should_stop(); +} + +static bool kcompactd_node_suitable(pg_data_t *pgdat) +{ + int zoneid; + struct zone *zone; + enum zone_type highest_zoneidx = pgdat->kcompactd_highest_zoneidx; + + for (zoneid = 0; zoneid <= highest_zoneidx; zoneid++) { + zone = &pgdat->node_zones[zoneid]; + + if (!populated_zone(zone)) + continue; + + if (compaction_suitable(zone, pgdat->kcompactd_max_order, 0, + highest_zoneidx) == COMPACT_CONTINUE) + return true; + } + + return false; +} + +static void kcompactd_do_work(pg_data_t *pgdat) +{ + /* + * With no special task, compact all zones so that a page of requested + * order is allocatable. + */ + int zoneid; + struct zone *zone; + struct compact_control cc = { + .order = pgdat->kcompactd_max_order, + .search_order = pgdat->kcompactd_max_order, + .highest_zoneidx = pgdat->kcompactd_highest_zoneidx, + .mode = MIGRATE_SYNC_LIGHT, + .ignore_skip_hint = false, + .gfp_mask = GFP_KERNEL, + }; + trace_mm_compaction_kcompactd_wake(pgdat->node_id, cc.order, + cc.highest_zoneidx); + count_compact_event(KCOMPACTD_WAKE); + + for (zoneid = 0; zoneid <= cc.highest_zoneidx; zoneid++) { + int status; + + zone = &pgdat->node_zones[zoneid]; + if (!populated_zone(zone)) + continue; + + if (compaction_deferred(zone, cc.order)) + continue; + + if (compaction_suitable(zone, cc.order, 0, zoneid) != + COMPACT_CONTINUE) + continue; + + if (kthread_should_stop()) + return; + + cc.zone = zone; + status = compact_zone(&cc, NULL); + + if (status == COMPACT_SUCCESS) { + compaction_defer_reset(zone, cc.order, false); + } else if (status == COMPACT_PARTIAL_SKIPPED || status == COMPACT_COMPLETE) { + /* + * Buddy pages may become stranded on pcps that could + * otherwise coalesce on the zone's free area for + * order >= cc.order. This is ratelimited by the + * upcoming deferral. + */ + drain_all_pages(zone); + + /* + * We use sync migration mode here, so we defer like + * sync direct compaction does. + */ + defer_compaction(zone, cc.order); + } + + count_compact_events(KCOMPACTD_MIGRATE_SCANNED, + cc.total_migrate_scanned); + count_compact_events(KCOMPACTD_FREE_SCANNED, + cc.total_free_scanned); + + VM_BUG_ON(!list_empty(&cc.freepages)); + VM_BUG_ON(!list_empty(&cc.migratepages)); + } + + /* + * Regardless of success, we are done until woken up next. But remember + * the requested order/highest_zoneidx in case it was higher/tighter + * than our current ones + */ + if (pgdat->kcompactd_max_order <= cc.order) + pgdat->kcompactd_max_order = 0; + if (pgdat->kcompactd_highest_zoneidx >= cc.highest_zoneidx) + pgdat->kcompactd_highest_zoneidx = pgdat->nr_zones - 1; +} + +void wakeup_kcompactd(pg_data_t *pgdat, int order, int highest_zoneidx) +{ + if (!order) + return; + + if (pgdat->kcompactd_max_order < order) + pgdat->kcompactd_max_order = order; + + if (pgdat->kcompactd_highest_zoneidx > highest_zoneidx) + pgdat->kcompactd_highest_zoneidx = highest_zoneidx; + + /* + * Pairs with implicit barrier in wait_event_freezable() + * such that wakeups are not missed. + */ + if (!wq_has_sleeper(&pgdat->kcompactd_wait)) + return; + + if (!kcompactd_node_suitable(pgdat)) + return; + + trace_mm_compaction_wakeup_kcompactd(pgdat->node_id, order, + highest_zoneidx); + wake_up_interruptible(&pgdat->kcompactd_wait); +} + +/* + * The background compaction daemon, started as a kernel thread + * from the init process. + */ +static int kcompactd(void *p) +{ + pg_data_t *pgdat = (pg_data_t*)p; + struct task_struct *tsk = current; + unsigned int proactive_defer = 0; + + const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id); + + if (!cpumask_empty(cpumask)) + set_cpus_allowed_ptr(tsk, cpumask); + + set_freezable(); + + pgdat->kcompactd_max_order = 0; + pgdat->kcompactd_highest_zoneidx = pgdat->nr_zones - 1; + + while (!kthread_should_stop()) { + unsigned long pflags; + + trace_mm_compaction_kcompactd_sleep(pgdat->node_id); + if (wait_event_freezable_timeout(pgdat->kcompactd_wait, + kcompactd_work_requested(pgdat), + msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC))) { + + psi_memstall_enter(&pflags); + kcompactd_do_work(pgdat); + psi_memstall_leave(&pflags); + continue; + } + + /* kcompactd wait timeout */ + if (should_proactive_compact_node(pgdat)) { + unsigned int prev_score, score; + + if (proactive_defer) { + proactive_defer--; + continue; + } + prev_score = fragmentation_score_node(pgdat); + proactive_compact_node(pgdat); + score = fragmentation_score_node(pgdat); + /* + * Defer proactive compaction if the fragmentation + * score did not go down i.e. no progress made. + */ + proactive_defer = score < prev_score ? + 0 : 1 << COMPACT_MAX_DEFER_SHIFT; + } + } + + return 0; +} + +/* + * This kcompactd start function will be called by init and node-hot-add. + * On node-hot-add, kcompactd will moved to proper cpus if cpus are hot-added. + */ +int kcompactd_run(int nid) +{ + pg_data_t *pgdat = NODE_DATA(nid); + int ret = 0; + + if (pgdat->kcompactd) + return 0; + + pgdat->kcompactd = kthread_run(kcompactd, pgdat, "kcompactd%d", nid); + if (IS_ERR(pgdat->kcompactd)) { + pr_err("Failed to start kcompactd on node %d\n", nid); + ret = PTR_ERR(pgdat->kcompactd); + pgdat->kcompactd = NULL; + } + return ret; +} + +/* + * Called by memory hotplug when all memory in a node is offlined. Caller must + * hold mem_hotplug_begin/end(). + */ +void kcompactd_stop(int nid) +{ + struct task_struct *kcompactd = NODE_DATA(nid)->kcompactd; + + if (kcompactd) { + kthread_stop(kcompactd); + NODE_DATA(nid)->kcompactd = NULL; + } +} + +/* + * It's optimal to keep kcompactd on the same CPUs as their memory, but + * not required for correctness. So if the last cpu in a node goes + * away, we get changed to run anywhere: as the first one comes back, + * restore their cpu bindings. + */ +static int kcompactd_cpu_online(unsigned int cpu) +{ + int nid; + + for_each_node_state(nid, N_MEMORY) { + pg_data_t *pgdat = NODE_DATA(nid); + const struct cpumask *mask; + + mask = cpumask_of_node(pgdat->node_id); + + if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids) + /* One of our CPUs online: restore mask */ + set_cpus_allowed_ptr(pgdat->kcompactd, mask); + } + return 0; +} + +static int __init kcompactd_init(void) +{ + int nid; + int ret; + + ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, + "mm/compaction:online", + kcompactd_cpu_online, NULL); + if (ret < 0) { + pr_err("kcompactd: failed to register hotplug callbacks.\n"); + return ret; + } + + for_each_node_state(nid, N_MEMORY) + kcompactd_run(nid); + return 0; +} +subsys_initcall(kcompactd_init) + +#endif /* CONFIG_COMPACTION */ diff --git a/mm/debug.c b/mm/debug.c new file mode 100644 index 000000000..ccca576b2 --- /dev/null +++ b/mm/debug.c @@ -0,0 +1,324 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * mm/debug.c + * + * mm/ specific debug routines. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "internal.h" + +const char *migrate_reason_names[MR_TYPES] = { + "compaction", + "memory_failure", + "memory_hotplug", + "syscall_or_cpuset", + "mempolicy_mbind", + "numa_misplaced", + "cma", +}; + +const struct trace_print_flags pageflag_names[] = { + __def_pageflag_names, + {0, NULL} +}; + +const struct trace_print_flags gfpflag_names[] = { + __def_gfpflag_names, + {0, NULL} +}; + +const struct trace_print_flags vmaflag_names[] = { + __def_vmaflag_names, + {0, NULL} +}; + +void __dump_page(struct page *page, const char *reason) +{ + struct page *head = compound_head(page); + struct address_space *mapping; + bool page_poisoned = PagePoisoned(page); + bool compound = PageCompound(page); + /* + * Accessing the pageblock without the zone lock. It could change to + * "isolate" again in the meantime, but since we are just dumping the + * state for debugging, it should be fine to accept a bit of + * inaccuracy here due to racing. + */ + bool page_cma = is_migrate_cma_page(page); + int mapcount; + char *type = ""; + + /* + * If struct page is poisoned don't access Page*() functions as that + * leads to recursive loop. Page*() check for poisoned pages, and calls + * dump_page() when detected. + */ + if (page_poisoned) { + pr_warn("page:%px is uninitialized and poisoned", page); + goto hex_only; + } + + if (page < head || (page >= head + MAX_ORDER_NR_PAGES)) { + /* + * Corrupt page, so we cannot call page_mapping. Instead, do a + * safe subset of the steps that page_mapping() does. Caution: + * this will be misleading for tail pages, PageSwapCache pages, + * and potentially other situations. (See the page_mapping() + * implementation for what's missing here.) + */ + unsigned long tmp = (unsigned long)page->mapping; + + if (tmp & PAGE_MAPPING_ANON) + mapping = NULL; + else + mapping = (void *)(tmp & ~PAGE_MAPPING_FLAGS); + head = page; + compound = false; + } else { + mapping = page_mapping(page); + } + + /* + * Avoid VM_BUG_ON() in page_mapcount(). + * page->_mapcount space in struct page is used by sl[aou]b pages to + * encode own info. + */ + mapcount = PageSlab(head) ? 0 : page_mapcount(page); + + pr_warn("page:%p refcount:%d mapcount:%d mapping:%p index:%#lx pfn:%#lx\n", + page, page_ref_count(head), mapcount, mapping, + page_to_pgoff(page), page_to_pfn(page)); + if (compound) { + if (hpage_pincount_available(page)) { + pr_warn("head:%p order:%u compound_mapcount:%d compound_pincount:%d\n", + head, compound_order(head), + head_compound_mapcount(head), + head_compound_pincount(head)); + } else { + pr_warn("head:%p order:%u compound_mapcount:%d\n", + head, compound_order(head), + head_compound_mapcount(head)); + } + } + if (PageKsm(page)) + type = "ksm "; + else if (PageAnon(page)) + type = "anon "; + else if (mapping) { + struct inode *host; + const struct address_space_operations *a_ops; + struct hlist_node *dentry_first; + struct dentry *dentry_ptr; + struct dentry dentry; + unsigned long ino; + + /* + * mapping can be invalid pointer and we don't want to crash + * accessing it, so probe everything depending on it carefully + */ + if (get_kernel_nofault(host, &mapping->host) || + get_kernel_nofault(a_ops, &mapping->a_ops)) { + pr_warn("failed to read mapping contents, not a valid kernel address?\n"); + goto out_mapping; + } + + if (!host) { + pr_warn("aops:%ps\n", a_ops); + goto out_mapping; + } + + if (get_kernel_nofault(dentry_first, &host->i_dentry.first) || + get_kernel_nofault(ino, &host->i_ino)) { + pr_warn("aops:%ps with invalid host inode %px\n", + a_ops, host); + goto out_mapping; + } + + if (!dentry_first) { + pr_warn("aops:%ps ino:%lx\n", a_ops, ino); + goto out_mapping; + } + + dentry_ptr = container_of(dentry_first, struct dentry, d_u.d_alias); + if (get_kernel_nofault(dentry, dentry_ptr)) { + pr_warn("aops:%ps ino:%lx with invalid dentry %px\n", + a_ops, ino, dentry_ptr); + } else { + /* + * if dentry is corrupted, the %pd handler may still + * crash, but it's unlikely that we reach here with a + * corrupted struct page + */ + pr_warn("aops:%ps ino:%lx dentry name:\"%pd\"\n", + a_ops, ino, &dentry); + } + } +out_mapping: + BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS + 1); + + pr_warn("%sflags: %#lx(%pGp)%s\n", type, head->flags, &head->flags, + page_cma ? " CMA" : ""); + +hex_only: + print_hex_dump(KERN_WARNING, "raw: ", DUMP_PREFIX_NONE, 32, + sizeof(unsigned long), page, + sizeof(struct page), false); + if (head != page) + print_hex_dump(KERN_WARNING, "head: ", DUMP_PREFIX_NONE, 32, + sizeof(unsigned long), head, + sizeof(struct page), false); + + if (reason) + pr_warn("page dumped because: %s\n", reason); + +#ifdef CONFIG_MEMCG + if (!page_poisoned && page->mem_cgroup) + pr_warn("page->mem_cgroup:%px\n", page->mem_cgroup); +#endif +} + +void dump_page(struct page *page, const char *reason) +{ + __dump_page(page, reason); + dump_page_owner(page); +} +EXPORT_SYMBOL(dump_page); + +#ifdef CONFIG_DEBUG_VM + +void dump_vma(const struct vm_area_struct *vma) +{ + pr_emerg("vma %px start %px end %px\n" + "next %px prev %px mm %px\n" + "prot %lx anon_vma %px vm_ops %px\n" + "pgoff %lx file %px private_data %px\n" + "flags: %#lx(%pGv)\n", + vma, (void *)vma->vm_start, (void *)vma->vm_end, vma->vm_next, + vma->vm_prev, vma->vm_mm, + (unsigned long)pgprot_val(vma->vm_page_prot), + vma->anon_vma, vma->vm_ops, vma->vm_pgoff, + vma->vm_file, vma->vm_private_data, + vma->vm_flags, &vma->vm_flags); +} +EXPORT_SYMBOL(dump_vma); + +void dump_mm(const struct mm_struct *mm) +{ + pr_emerg("mm %px mmap %px seqnum %llu task_size %lu\n" +#ifdef CONFIG_MMU + "get_unmapped_area %px\n" +#endif + "mmap_base %lu mmap_legacy_base %lu highest_vm_end %lu\n" + "pgd %px mm_users %d mm_count %d pgtables_bytes %lu map_count %d\n" + "hiwater_rss %lx hiwater_vm %lx total_vm %lx locked_vm %lx\n" + "pinned_vm %llx data_vm %lx exec_vm %lx stack_vm %lx\n" + "start_code %lx end_code %lx start_data %lx end_data %lx\n" + "start_brk %lx brk %lx start_stack %lx\n" + "arg_start %lx arg_end %lx env_start %lx env_end %lx\n" + "binfmt %px flags %lx core_state %px\n" +#ifdef CONFIG_AIO + "ioctx_table %px\n" +#endif +#ifdef CONFIG_MEMCG + "owner %px " +#endif + "exe_file %px\n" +#ifdef CONFIG_MMU_NOTIFIER + "notifier_subscriptions %px\n" +#endif +#ifdef CONFIG_NUMA_BALANCING + "numa_next_scan %lu numa_scan_offset %lu numa_scan_seq %d\n" +#endif + "tlb_flush_pending %d\n" + "def_flags: %#lx(%pGv)\n", + + mm, mm->mmap, (long long) mm->vmacache_seqnum, mm->task_size, +#ifdef CONFIG_MMU + mm->get_unmapped_area, +#endif + mm->mmap_base, mm->mmap_legacy_base, mm->highest_vm_end, + mm->pgd, atomic_read(&mm->mm_users), + atomic_read(&mm->mm_count), + mm_pgtables_bytes(mm), + mm->map_count, + mm->hiwater_rss, mm->hiwater_vm, mm->total_vm, mm->locked_vm, + (u64)atomic64_read(&mm->pinned_vm), + mm->data_vm, mm->exec_vm, mm->stack_vm, + mm->start_code, mm->end_code, mm->start_data, mm->end_data, + mm->start_brk, mm->brk, mm->start_stack, + mm->arg_start, mm->arg_end, mm->env_start, mm->env_end, + mm->binfmt, mm->flags, mm->core_state, +#ifdef CONFIG_AIO + mm->ioctx_table, +#endif +#ifdef CONFIG_MEMCG + mm->owner, +#endif + mm->exe_file, +#ifdef CONFIG_MMU_NOTIFIER + mm->notifier_subscriptions, +#endif +#ifdef CONFIG_NUMA_BALANCING + mm->numa_next_scan, mm->numa_scan_offset, mm->numa_scan_seq, +#endif + atomic_read(&mm->tlb_flush_pending), + mm->def_flags, &mm->def_flags + ); +} + +static bool page_init_poisoning __read_mostly = true; + +static int __init setup_vm_debug(char *str) +{ + bool __page_init_poisoning = true; + + /* + * Calling vm_debug with no arguments is equivalent to requesting + * to enable all debugging options we can control. + */ + if (*str++ != '=' || !*str) + goto out; + + __page_init_poisoning = false; + if (*str == '-') + goto out; + + while (*str) { + switch (tolower(*str)) { + case'p': + __page_init_poisoning = true; + break; + default: + pr_err("vm_debug option '%c' unknown. skipped\n", + *str); + } + + str++; + } +out: + if (page_init_poisoning && !__page_init_poisoning) + pr_warn("Page struct poisoning disabled by kernel command line option 'vm_debug'\n"); + + page_init_poisoning = __page_init_poisoning; + + return 1; +} +__setup("vm_debug", setup_vm_debug); + +void page_init_poison(struct page *page, size_t size) +{ + if (page_init_poisoning) + memset(page, PAGE_POISON_PATTERN, size); +} +EXPORT_SYMBOL_GPL(page_init_poison); +#endif /* CONFIG_DEBUG_VM */ diff --git a/mm/debug_page_ref.c b/mm/debug_page_ref.c new file mode 100644 index 000000000..f3b2c9d3e --- /dev/null +++ b/mm/debug_page_ref.c @@ -0,0 +1,55 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include + +#define CREATE_TRACE_POINTS +#include + +void __page_ref_set(struct page *page, int v) +{ + trace_page_ref_set(page, v); +} +EXPORT_SYMBOL(__page_ref_set); +EXPORT_TRACEPOINT_SYMBOL(page_ref_set); + +void __page_ref_mod(struct page *page, int v) +{ + trace_page_ref_mod(page, v); +} +EXPORT_SYMBOL(__page_ref_mod); +EXPORT_TRACEPOINT_SYMBOL(page_ref_mod); + +void __page_ref_mod_and_test(struct page *page, int v, int ret) +{ + trace_page_ref_mod_and_test(page, v, ret); +} +EXPORT_SYMBOL(__page_ref_mod_and_test); +EXPORT_TRACEPOINT_SYMBOL(page_ref_mod_and_test); + +void __page_ref_mod_and_return(struct page *page, int v, int ret) +{ + trace_page_ref_mod_and_return(page, v, ret); +} +EXPORT_SYMBOL(__page_ref_mod_and_return); +EXPORT_TRACEPOINT_SYMBOL(page_ref_mod_and_return); + +void __page_ref_mod_unless(struct page *page, int v, int u) +{ + trace_page_ref_mod_unless(page, v, u); +} +EXPORT_SYMBOL(__page_ref_mod_unless); +EXPORT_TRACEPOINT_SYMBOL(page_ref_mod_unless); + +void __page_ref_freeze(struct page *page, int v, int ret) +{ + trace_page_ref_freeze(page, v, ret); +} +EXPORT_SYMBOL(__page_ref_freeze); +EXPORT_TRACEPOINT_SYMBOL(page_ref_freeze); + +void __page_ref_unfreeze(struct page *page, int v) +{ + trace_page_ref_unfreeze(page, v); +} +EXPORT_SYMBOL(__page_ref_unfreeze); +EXPORT_TRACEPOINT_SYMBOL(page_ref_unfreeze); diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c new file mode 100644 index 000000000..d6fbf28eb --- /dev/null +++ b/mm/debug_vm_pgtable.c @@ -0,0 +1,1147 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * This kernel test validates architecture page table helpers and + * accessors and helps in verifying their continued compliance with + * expected generic MM semantics. + * + * Copyright (C) 2019 ARM Ltd. + * + * Author: Anshuman Khandual + */ +#define pr_fmt(fmt) "debug_vm_pgtable: [%-25s]: " fmt, __func__ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * Please refer Documentation/vm/arch_pgtable_helpers.rst for the semantics + * expectations that are being validated here. All future changes in here + * or the documentation need to be in sync. + */ + +#define VMFLAGS (VM_READ|VM_WRITE|VM_EXEC) + +/* + * On s390 platform, the lower 4 bits are used to identify given page table + * entry type. But these bits might affect the ability to clear entries with + * pxx_clear() because of how dynamic page table folding works on s390. So + * while loading up the entries do not change the lower 4 bits. It does not + * have affect any other platform. Also avoid the 62nd bit on ppc64 that is + * used to mark a pte entry. + */ +#define S390_SKIP_MASK GENMASK(3, 0) +#if __BITS_PER_LONG == 64 +#define PPC64_SKIP_MASK GENMASK(62, 62) +#else +#define PPC64_SKIP_MASK 0x0 +#endif +#define ARCH_SKIP_MASK (S390_SKIP_MASK | PPC64_SKIP_MASK) +#define RANDOM_ORVALUE (GENMASK(BITS_PER_LONG - 1, 0) & ~ARCH_SKIP_MASK) +#define RANDOM_NZVALUE GENMASK(7, 0) + +static void __init pte_basic_tests(unsigned long pfn, int idx) +{ + pgprot_t prot = protection_map[idx]; + pte_t pte = pfn_pte(pfn, prot); + unsigned long val = idx, *ptr = &val; + + pr_debug("Validating PTE basic (%pGv)\n", ptr); + + /* + * This test needs to be executed after the given page table entry + * is created with pfn_pte() to make sure that protection_map[idx] + * does not have the dirty bit enabled from the beginning. This is + * important for platforms like arm64 where (!PTE_RDONLY) indicate + * dirty bit being set. + */ + WARN_ON(pte_dirty(pte_wrprotect(pte))); + + WARN_ON(!pte_same(pte, pte)); + WARN_ON(!pte_young(pte_mkyoung(pte_mkold(pte)))); + WARN_ON(!pte_dirty(pte_mkdirty(pte_mkclean(pte)))); + WARN_ON(!pte_write(pte_mkwrite(pte_wrprotect(pte)))); + WARN_ON(pte_young(pte_mkold(pte_mkyoung(pte)))); + WARN_ON(pte_dirty(pte_mkclean(pte_mkdirty(pte)))); + WARN_ON(pte_write(pte_wrprotect(pte_mkwrite(pte)))); + WARN_ON(pte_dirty(pte_wrprotect(pte_mkclean(pte)))); + WARN_ON(!pte_dirty(pte_wrprotect(pte_mkdirty(pte)))); +} + +static void __init pte_advanced_tests(struct mm_struct *mm, + struct vm_area_struct *vma, pte_t *ptep, + unsigned long pfn, unsigned long vaddr, + pgprot_t prot) +{ + pte_t pte = pfn_pte(pfn, prot); + + /* + * Architectures optimize set_pte_at by avoiding TLB flush. + * This requires set_pte_at to be not used to update an + * existing pte entry. Clear pte before we do set_pte_at + */ + + pr_debug("Validating PTE advanced\n"); + pte = pfn_pte(pfn, prot); + set_pte_at(mm, vaddr, ptep, pte); + ptep_set_wrprotect(mm, vaddr, ptep); + pte = ptep_get(ptep); + WARN_ON(pte_write(pte)); + ptep_get_and_clear(mm, vaddr, ptep); + pte = ptep_get(ptep); + WARN_ON(!pte_none(pte)); + + pte = pfn_pte(pfn, prot); + pte = pte_wrprotect(pte); + pte = pte_mkclean(pte); + set_pte_at(mm, vaddr, ptep, pte); + pte = pte_mkwrite(pte); + pte = pte_mkdirty(pte); + ptep_set_access_flags(vma, vaddr, ptep, pte, 1); + pte = ptep_get(ptep); + WARN_ON(!(pte_write(pte) && pte_dirty(pte))); + ptep_get_and_clear_full(mm, vaddr, ptep, 1); + pte = ptep_get(ptep); + WARN_ON(!pte_none(pte)); + + pte = pfn_pte(pfn, prot); + pte = pte_mkyoung(pte); + set_pte_at(mm, vaddr, ptep, pte); + ptep_test_and_clear_young(vma, vaddr, ptep); + pte = ptep_get(ptep); + WARN_ON(pte_young(pte)); + + ptep_get_and_clear_full(mm, vaddr, ptep, 1); +} + +static void __init pte_savedwrite_tests(unsigned long pfn, pgprot_t prot) +{ + pte_t pte = pfn_pte(pfn, prot); + + if (!IS_ENABLED(CONFIG_NUMA_BALANCING)) + return; + + pr_debug("Validating PTE saved write\n"); + WARN_ON(!pte_savedwrite(pte_mk_savedwrite(pte_clear_savedwrite(pte)))); + WARN_ON(pte_savedwrite(pte_clear_savedwrite(pte_mk_savedwrite(pte)))); +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static void __init pmd_basic_tests(unsigned long pfn, int idx) +{ + pgprot_t prot = protection_map[idx]; + unsigned long val = idx, *ptr = &val; + pmd_t pmd; + + if (!has_transparent_hugepage()) + return; + + pr_debug("Validating PMD basic (%pGv)\n", ptr); + pmd = pfn_pmd(pfn, prot); + + /* + * This test needs to be executed after the given page table entry + * is created with pfn_pmd() to make sure that protection_map[idx] + * does not have the dirty bit enabled from the beginning. This is + * important for platforms like arm64 where (!PTE_RDONLY) indicate + * dirty bit being set. + */ + WARN_ON(pmd_dirty(pmd_wrprotect(pmd))); + + + WARN_ON(!pmd_same(pmd, pmd)); + WARN_ON(!pmd_young(pmd_mkyoung(pmd_mkold(pmd)))); + WARN_ON(!pmd_dirty(pmd_mkdirty(pmd_mkclean(pmd)))); + WARN_ON(!pmd_write(pmd_mkwrite(pmd_wrprotect(pmd)))); + WARN_ON(pmd_young(pmd_mkold(pmd_mkyoung(pmd)))); + WARN_ON(pmd_dirty(pmd_mkclean(pmd_mkdirty(pmd)))); + WARN_ON(pmd_write(pmd_wrprotect(pmd_mkwrite(pmd)))); + WARN_ON(pmd_dirty(pmd_wrprotect(pmd_mkclean(pmd)))); + WARN_ON(!pmd_dirty(pmd_wrprotect(pmd_mkdirty(pmd)))); + /* + * A huge page does not point to next level page table + * entry. Hence this must qualify as pmd_bad(). + */ + WARN_ON(!pmd_bad(pmd_mkhuge(pmd))); +} + +static void __init pmd_advanced_tests(struct mm_struct *mm, + struct vm_area_struct *vma, pmd_t *pmdp, + unsigned long pfn, unsigned long vaddr, + pgprot_t prot, pgtable_t pgtable) +{ + pmd_t pmd; + + if (!has_transparent_hugepage()) + return; + + pr_debug("Validating PMD advanced\n"); + /* Align the address wrt HPAGE_PMD_SIZE */ + vaddr &= HPAGE_PMD_MASK; + + pgtable_trans_huge_deposit(mm, pmdp, pgtable); + + pmd = pfn_pmd(pfn, prot); + set_pmd_at(mm, vaddr, pmdp, pmd); + pmdp_set_wrprotect(mm, vaddr, pmdp); + pmd = READ_ONCE(*pmdp); + WARN_ON(pmd_write(pmd)); + pmdp_huge_get_and_clear(mm, vaddr, pmdp); + pmd = READ_ONCE(*pmdp); + WARN_ON(!pmd_none(pmd)); + + pmd = pfn_pmd(pfn, prot); + pmd = pmd_wrprotect(pmd); + pmd = pmd_mkclean(pmd); + set_pmd_at(mm, vaddr, pmdp, pmd); + pmd = pmd_mkwrite(pmd); + pmd = pmd_mkdirty(pmd); + pmdp_set_access_flags(vma, vaddr, pmdp, pmd, 1); + pmd = READ_ONCE(*pmdp); + WARN_ON(!(pmd_write(pmd) && pmd_dirty(pmd))); + pmdp_huge_get_and_clear_full(vma, vaddr, pmdp, 1); + pmd = READ_ONCE(*pmdp); + WARN_ON(!pmd_none(pmd)); + + pmd = pmd_mkhuge(pfn_pmd(pfn, prot)); + pmd = pmd_mkyoung(pmd); + set_pmd_at(mm, vaddr, pmdp, pmd); + pmdp_test_and_clear_young(vma, vaddr, pmdp); + pmd = READ_ONCE(*pmdp); + WARN_ON(pmd_young(pmd)); + + /* Clear the pte entries */ + pmdp_huge_get_and_clear(mm, vaddr, pmdp); + pgtable = pgtable_trans_huge_withdraw(mm, pmdp); +} + +static void __init pmd_leaf_tests(unsigned long pfn, pgprot_t prot) +{ + pmd_t pmd; + + if (!has_transparent_hugepage()) + return; + + pr_debug("Validating PMD leaf\n"); + pmd = pfn_pmd(pfn, prot); + + /* + * PMD based THP is a leaf entry. + */ + pmd = pmd_mkhuge(pmd); + WARN_ON(!pmd_leaf(pmd)); +} + +#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP +static void __init pmd_huge_tests(pmd_t *pmdp, unsigned long pfn, pgprot_t prot) +{ + pmd_t pmd; + + if (!arch_ioremap_pmd_supported()) + return; + + pr_debug("Validating PMD huge\n"); + /* + * X86 defined pmd_set_huge() verifies that the given + * PMD is not a populated non-leaf entry. + */ + WRITE_ONCE(*pmdp, __pmd(0)); + WARN_ON(!pmd_set_huge(pmdp, __pfn_to_phys(pfn), prot)); + WARN_ON(!pmd_clear_huge(pmdp)); + pmd = READ_ONCE(*pmdp); + WARN_ON(!pmd_none(pmd)); +} +#else /* CONFIG_HAVE_ARCH_HUGE_VMAP */ +static void __init pmd_huge_tests(pmd_t *pmdp, unsigned long pfn, pgprot_t prot) { } +#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ + +static void __init pmd_savedwrite_tests(unsigned long pfn, pgprot_t prot) +{ + pmd_t pmd; + + if (!IS_ENABLED(CONFIG_NUMA_BALANCING)) + return; + + if (!has_transparent_hugepage()) + return; + + pr_debug("Validating PMD saved write\n"); + pmd = pfn_pmd(pfn, prot); + WARN_ON(!pmd_savedwrite(pmd_mk_savedwrite(pmd_clear_savedwrite(pmd)))); + WARN_ON(pmd_savedwrite(pmd_clear_savedwrite(pmd_mk_savedwrite(pmd)))); +} + +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +static void __init pud_basic_tests(struct mm_struct *mm, unsigned long pfn, int idx) +{ + pgprot_t prot = protection_map[idx]; + unsigned long val = idx, *ptr = &val; + pud_t pud; + + if (!has_transparent_hugepage()) + return; + + pr_debug("Validating PUD basic (%pGv)\n", ptr); + pud = pfn_pud(pfn, prot); + + /* + * This test needs to be executed after the given page table entry + * is created with pfn_pud() to make sure that protection_map[idx] + * does not have the dirty bit enabled from the beginning. This is + * important for platforms like arm64 where (!PTE_RDONLY) indicate + * dirty bit being set. + */ + WARN_ON(pud_dirty(pud_wrprotect(pud))); + + WARN_ON(!pud_same(pud, pud)); + WARN_ON(!pud_young(pud_mkyoung(pud_mkold(pud)))); + WARN_ON(!pud_dirty(pud_mkdirty(pud_mkclean(pud)))); + WARN_ON(pud_dirty(pud_mkclean(pud_mkdirty(pud)))); + WARN_ON(!pud_write(pud_mkwrite(pud_wrprotect(pud)))); + WARN_ON(pud_write(pud_wrprotect(pud_mkwrite(pud)))); + WARN_ON(pud_young(pud_mkold(pud_mkyoung(pud)))); + WARN_ON(pud_dirty(pud_wrprotect(pud_mkclean(pud)))); + WARN_ON(!pud_dirty(pud_wrprotect(pud_mkdirty(pud)))); + + if (mm_pmd_folded(mm)) + return; + + /* + * A huge page does not point to next level page table + * entry. Hence this must qualify as pud_bad(). + */ + WARN_ON(!pud_bad(pud_mkhuge(pud))); +} + +static void __init pud_advanced_tests(struct mm_struct *mm, + struct vm_area_struct *vma, pud_t *pudp, + unsigned long pfn, unsigned long vaddr, + pgprot_t prot) +{ + pud_t pud; + + if (!has_transparent_hugepage()) + return; + + pr_debug("Validating PUD advanced\n"); + /* Align the address wrt HPAGE_PUD_SIZE */ + vaddr &= HPAGE_PUD_MASK; + + pud = pfn_pud(pfn, prot); + set_pud_at(mm, vaddr, pudp, pud); + pudp_set_wrprotect(mm, vaddr, pudp); + pud = READ_ONCE(*pudp); + WARN_ON(pud_write(pud)); + +#ifndef __PAGETABLE_PMD_FOLDED + pudp_huge_get_and_clear(mm, vaddr, pudp); + pud = READ_ONCE(*pudp); + WARN_ON(!pud_none(pud)); +#endif /* __PAGETABLE_PMD_FOLDED */ + pud = pfn_pud(pfn, prot); + pud = pud_wrprotect(pud); + pud = pud_mkclean(pud); + set_pud_at(mm, vaddr, pudp, pud); + pud = pud_mkwrite(pud); + pud = pud_mkdirty(pud); + pudp_set_access_flags(vma, vaddr, pudp, pud, 1); + pud = READ_ONCE(*pudp); + WARN_ON(!(pud_write(pud) && pud_dirty(pud))); + +#ifndef __PAGETABLE_PMD_FOLDED + pudp_huge_get_and_clear_full(mm, vaddr, pudp, 1); + pud = READ_ONCE(*pudp); + WARN_ON(!pud_none(pud)); +#endif /* __PAGETABLE_PMD_FOLDED */ + + pud = pfn_pud(pfn, prot); + pud = pud_mkyoung(pud); + set_pud_at(mm, vaddr, pudp, pud); + pudp_test_and_clear_young(vma, vaddr, pudp); + pud = READ_ONCE(*pudp); + WARN_ON(pud_young(pud)); + + pudp_huge_get_and_clear(mm, vaddr, pudp); +} + +static void __init pud_leaf_tests(unsigned long pfn, pgprot_t prot) +{ + pud_t pud; + + if (!has_transparent_hugepage()) + return; + + pr_debug("Validating PUD leaf\n"); + pud = pfn_pud(pfn, prot); + /* + * PUD based THP is a leaf entry. + */ + pud = pud_mkhuge(pud); + WARN_ON(!pud_leaf(pud)); +} + +#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP +static void __init pud_huge_tests(pud_t *pudp, unsigned long pfn, pgprot_t prot) +{ + pud_t pud; + + if (!arch_ioremap_pud_supported()) + return; + + pr_debug("Validating PUD huge\n"); + /* + * X86 defined pud_set_huge() verifies that the given + * PUD is not a populated non-leaf entry. + */ + WRITE_ONCE(*pudp, __pud(0)); + WARN_ON(!pud_set_huge(pudp, __pfn_to_phys(pfn), prot)); + WARN_ON(!pud_clear_huge(pudp)); + pud = READ_ONCE(*pudp); + WARN_ON(!pud_none(pud)); +} +#else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */ +static void __init pud_huge_tests(pud_t *pudp, unsigned long pfn, pgprot_t prot) { } +#endif /* !CONFIG_HAVE_ARCH_HUGE_VMAP */ + +#else /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ +static void __init pud_basic_tests(struct mm_struct *mm, unsigned long pfn, int idx) { } +static void __init pud_advanced_tests(struct mm_struct *mm, + struct vm_area_struct *vma, pud_t *pudp, + unsigned long pfn, unsigned long vaddr, + pgprot_t prot) +{ +} +static void __init pud_leaf_tests(unsigned long pfn, pgprot_t prot) { } +static void __init pud_huge_tests(pud_t *pudp, unsigned long pfn, pgprot_t prot) +{ +} +#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ +#else /* !CONFIG_TRANSPARENT_HUGEPAGE */ +static void __init pmd_basic_tests(unsigned long pfn, int idx) { } +static void __init pud_basic_tests(struct mm_struct *mm, unsigned long pfn, int idx) { } +static void __init pmd_advanced_tests(struct mm_struct *mm, + struct vm_area_struct *vma, pmd_t *pmdp, + unsigned long pfn, unsigned long vaddr, + pgprot_t prot, pgtable_t pgtable) +{ +} +static void __init pud_advanced_tests(struct mm_struct *mm, + struct vm_area_struct *vma, pud_t *pudp, + unsigned long pfn, unsigned long vaddr, + pgprot_t prot) +{ +} +static void __init pmd_leaf_tests(unsigned long pfn, pgprot_t prot) { } +static void __init pud_leaf_tests(unsigned long pfn, pgprot_t prot) { } +static void __init pmd_huge_tests(pmd_t *pmdp, unsigned long pfn, pgprot_t prot) +{ +} +static void __init pud_huge_tests(pud_t *pudp, unsigned long pfn, pgprot_t prot) +{ +} +static void __init pmd_savedwrite_tests(unsigned long pfn, pgprot_t prot) { } +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +static void __init p4d_basic_tests(unsigned long pfn, pgprot_t prot) +{ + p4d_t p4d; + + pr_debug("Validating P4D basic\n"); + memset(&p4d, RANDOM_NZVALUE, sizeof(p4d_t)); + WARN_ON(!p4d_same(p4d, p4d)); +} + +static void __init pgd_basic_tests(unsigned long pfn, pgprot_t prot) +{ + pgd_t pgd; + + pr_debug("Validating PGD basic\n"); + memset(&pgd, RANDOM_NZVALUE, sizeof(pgd_t)); + WARN_ON(!pgd_same(pgd, pgd)); +} + +#ifndef __PAGETABLE_PUD_FOLDED +static void __init pud_clear_tests(struct mm_struct *mm, pud_t *pudp) +{ + pud_t pud = READ_ONCE(*pudp); + + if (mm_pmd_folded(mm)) + return; + + pr_debug("Validating PUD clear\n"); + pud = __pud(pud_val(pud) | RANDOM_ORVALUE); + WRITE_ONCE(*pudp, pud); + pud_clear(pudp); + pud = READ_ONCE(*pudp); + WARN_ON(!pud_none(pud)); +} + +static void __init pud_populate_tests(struct mm_struct *mm, pud_t *pudp, + pmd_t *pmdp) +{ + pud_t pud; + + if (mm_pmd_folded(mm)) + return; + + pr_debug("Validating PUD populate\n"); + /* + * This entry points to next level page table page. + * Hence this must not qualify as pud_bad(). + */ + pud_populate(mm, pudp, pmdp); + pud = READ_ONCE(*pudp); + WARN_ON(pud_bad(pud)); +} +#else /* !__PAGETABLE_PUD_FOLDED */ +static void __init pud_clear_tests(struct mm_struct *mm, pud_t *pudp) { } +static void __init pud_populate_tests(struct mm_struct *mm, pud_t *pudp, + pmd_t *pmdp) +{ +} +#endif /* PAGETABLE_PUD_FOLDED */ + +#ifndef __PAGETABLE_P4D_FOLDED +static void __init p4d_clear_tests(struct mm_struct *mm, p4d_t *p4dp) +{ + p4d_t p4d = READ_ONCE(*p4dp); + + if (mm_pud_folded(mm)) + return; + + pr_debug("Validating P4D clear\n"); + p4d = __p4d(p4d_val(p4d) | RANDOM_ORVALUE); + WRITE_ONCE(*p4dp, p4d); + p4d_clear(p4dp); + p4d = READ_ONCE(*p4dp); + WARN_ON(!p4d_none(p4d)); +} + +static void __init p4d_populate_tests(struct mm_struct *mm, p4d_t *p4dp, + pud_t *pudp) +{ + p4d_t p4d; + + if (mm_pud_folded(mm)) + return; + + pr_debug("Validating P4D populate\n"); + /* + * This entry points to next level page table page. + * Hence this must not qualify as p4d_bad(). + */ + pud_clear(pudp); + p4d_clear(p4dp); + p4d_populate(mm, p4dp, pudp); + p4d = READ_ONCE(*p4dp); + WARN_ON(p4d_bad(p4d)); +} + +static void __init pgd_clear_tests(struct mm_struct *mm, pgd_t *pgdp) +{ + pgd_t pgd = READ_ONCE(*pgdp); + + if (mm_p4d_folded(mm)) + return; + + pr_debug("Validating PGD clear\n"); + pgd = __pgd(pgd_val(pgd) | RANDOM_ORVALUE); + WRITE_ONCE(*pgdp, pgd); + pgd_clear(pgdp); + pgd = READ_ONCE(*pgdp); + WARN_ON(!pgd_none(pgd)); +} + +static void __init pgd_populate_tests(struct mm_struct *mm, pgd_t *pgdp, + p4d_t *p4dp) +{ + pgd_t pgd; + + if (mm_p4d_folded(mm)) + return; + + pr_debug("Validating PGD populate\n"); + /* + * This entry points to next level page table page. + * Hence this must not qualify as pgd_bad(). + */ + p4d_clear(p4dp); + pgd_clear(pgdp); + pgd_populate(mm, pgdp, p4dp); + pgd = READ_ONCE(*pgdp); + WARN_ON(pgd_bad(pgd)); +} +#else /* !__PAGETABLE_P4D_FOLDED */ +static void __init p4d_clear_tests(struct mm_struct *mm, p4d_t *p4dp) { } +static void __init pgd_clear_tests(struct mm_struct *mm, pgd_t *pgdp) { } +static void __init p4d_populate_tests(struct mm_struct *mm, p4d_t *p4dp, + pud_t *pudp) +{ +} +static void __init pgd_populate_tests(struct mm_struct *mm, pgd_t *pgdp, + p4d_t *p4dp) +{ +} +#endif /* PAGETABLE_P4D_FOLDED */ + +static void __init pte_clear_tests(struct mm_struct *mm, pte_t *ptep, + unsigned long pfn, unsigned long vaddr, + pgprot_t prot) +{ + pte_t pte = pfn_pte(pfn, prot); + + pr_debug("Validating PTE clear\n"); +#ifndef CONFIG_RISCV + pte = __pte(pte_val(pte) | RANDOM_ORVALUE); +#endif + set_pte_at(mm, vaddr, ptep, pte); + barrier(); + pte_clear(mm, vaddr, ptep); + pte = ptep_get(ptep); + WARN_ON(!pte_none(pte)); +} + +static void __init pmd_clear_tests(struct mm_struct *mm, pmd_t *pmdp) +{ + pmd_t pmd = READ_ONCE(*pmdp); + + pr_debug("Validating PMD clear\n"); + pmd = __pmd(pmd_val(pmd) | RANDOM_ORVALUE); + WRITE_ONCE(*pmdp, pmd); + pmd_clear(pmdp); + pmd = READ_ONCE(*pmdp); + WARN_ON(!pmd_none(pmd)); +} + +static void __init pmd_populate_tests(struct mm_struct *mm, pmd_t *pmdp, + pgtable_t pgtable) +{ + pmd_t pmd; + + pr_debug("Validating PMD populate\n"); + /* + * This entry points to next level page table page. + * Hence this must not qualify as pmd_bad(). + */ + pmd_populate(mm, pmdp, pgtable); + pmd = READ_ONCE(*pmdp); + WARN_ON(pmd_bad(pmd)); +} + +static void __init pte_special_tests(unsigned long pfn, pgprot_t prot) +{ + pte_t pte = pfn_pte(pfn, prot); + + if (!IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL)) + return; + + pr_debug("Validating PTE special\n"); + WARN_ON(!pte_special(pte_mkspecial(pte))); +} + +static void __init pte_protnone_tests(unsigned long pfn, pgprot_t prot) +{ + pte_t pte = pfn_pte(pfn, prot); + + if (!IS_ENABLED(CONFIG_NUMA_BALANCING)) + return; + + pr_debug("Validating PTE protnone\n"); + WARN_ON(!pte_protnone(pte)); + WARN_ON(!pte_present(pte)); +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static void __init pmd_protnone_tests(unsigned long pfn, pgprot_t prot) +{ + pmd_t pmd; + + if (!IS_ENABLED(CONFIG_NUMA_BALANCING)) + return; + + if (!has_transparent_hugepage()) + return; + + pr_debug("Validating PMD protnone\n"); + pmd = pmd_mkhuge(pfn_pmd(pfn, prot)); + WARN_ON(!pmd_protnone(pmd)); + WARN_ON(!pmd_present(pmd)); +} +#else /* !CONFIG_TRANSPARENT_HUGEPAGE */ +static void __init pmd_protnone_tests(unsigned long pfn, pgprot_t prot) { } +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +#ifdef CONFIG_ARCH_HAS_PTE_DEVMAP +static void __init pte_devmap_tests(unsigned long pfn, pgprot_t prot) +{ + pte_t pte = pfn_pte(pfn, prot); + + pr_debug("Validating PTE devmap\n"); + WARN_ON(!pte_devmap(pte_mkdevmap(pte))); +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static void __init pmd_devmap_tests(unsigned long pfn, pgprot_t prot) +{ + pmd_t pmd; + + if (!has_transparent_hugepage()) + return; + + pr_debug("Validating PMD devmap\n"); + pmd = pfn_pmd(pfn, prot); + WARN_ON(!pmd_devmap(pmd_mkdevmap(pmd))); +} + +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +static void __init pud_devmap_tests(unsigned long pfn, pgprot_t prot) +{ + pud_t pud; + + if (!has_transparent_hugepage()) + return; + + pr_debug("Validating PUD devmap\n"); + pud = pfn_pud(pfn, prot); + WARN_ON(!pud_devmap(pud_mkdevmap(pud))); +} +#else /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ +static void __init pud_devmap_tests(unsigned long pfn, pgprot_t prot) { } +#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ +#else /* CONFIG_TRANSPARENT_HUGEPAGE */ +static void __init pmd_devmap_tests(unsigned long pfn, pgprot_t prot) { } +static void __init pud_devmap_tests(unsigned long pfn, pgprot_t prot) { } +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#else +static void __init pte_devmap_tests(unsigned long pfn, pgprot_t prot) { } +static void __init pmd_devmap_tests(unsigned long pfn, pgprot_t prot) { } +static void __init pud_devmap_tests(unsigned long pfn, pgprot_t prot) { } +#endif /* CONFIG_ARCH_HAS_PTE_DEVMAP */ + +static void __init pte_soft_dirty_tests(unsigned long pfn, pgprot_t prot) +{ + pte_t pte = pfn_pte(pfn, prot); + + if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY)) + return; + + pr_debug("Validating PTE soft dirty\n"); + WARN_ON(!pte_soft_dirty(pte_mksoft_dirty(pte))); + WARN_ON(pte_soft_dirty(pte_clear_soft_dirty(pte))); +} + +static void __init pte_swap_soft_dirty_tests(unsigned long pfn, pgprot_t prot) +{ + pte_t pte = pfn_pte(pfn, prot); + + if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY)) + return; + + pr_debug("Validating PTE swap soft dirty\n"); + WARN_ON(!pte_swp_soft_dirty(pte_swp_mksoft_dirty(pte))); + WARN_ON(pte_swp_soft_dirty(pte_swp_clear_soft_dirty(pte))); +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static void __init pmd_soft_dirty_tests(unsigned long pfn, pgprot_t prot) +{ + pmd_t pmd; + + if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY)) + return; + + if (!has_transparent_hugepage()) + return; + + pr_debug("Validating PMD soft dirty\n"); + pmd = pfn_pmd(pfn, prot); + WARN_ON(!pmd_soft_dirty(pmd_mksoft_dirty(pmd))); + WARN_ON(pmd_soft_dirty(pmd_clear_soft_dirty(pmd))); +} + +static void __init pmd_swap_soft_dirty_tests(unsigned long pfn, pgprot_t prot) +{ + pmd_t pmd; + + if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY) || + !IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION)) + return; + + if (!has_transparent_hugepage()) + return; + + pr_debug("Validating PMD swap soft dirty\n"); + pmd = pfn_pmd(pfn, prot); + WARN_ON(!pmd_swp_soft_dirty(pmd_swp_mksoft_dirty(pmd))); + WARN_ON(pmd_swp_soft_dirty(pmd_swp_clear_soft_dirty(pmd))); +} +#else /* !CONFIG_ARCH_HAS_PTE_DEVMAP */ +static void __init pmd_soft_dirty_tests(unsigned long pfn, pgprot_t prot) { } +static void __init pmd_swap_soft_dirty_tests(unsigned long pfn, pgprot_t prot) +{ +} +#endif /* CONFIG_ARCH_HAS_PTE_DEVMAP */ + +static void __init pte_swap_tests(unsigned long pfn, pgprot_t prot) +{ + swp_entry_t swp; + pte_t pte; + + pr_debug("Validating PTE swap\n"); + pte = pfn_pte(pfn, prot); + swp = __pte_to_swp_entry(pte); + pte = __swp_entry_to_pte(swp); + WARN_ON(pfn != pte_pfn(pte)); +} + +#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION +static void __init pmd_swap_tests(unsigned long pfn, pgprot_t prot) +{ + swp_entry_t swp; + pmd_t pmd; + + if (!has_transparent_hugepage()) + return; + + pr_debug("Validating PMD swap\n"); + pmd = pfn_pmd(pfn, prot); + swp = __pmd_to_swp_entry(pmd); + pmd = __swp_entry_to_pmd(swp); + WARN_ON(pfn != pmd_pfn(pmd)); +} +#else /* !CONFIG_ARCH_ENABLE_THP_MIGRATION */ +static void __init pmd_swap_tests(unsigned long pfn, pgprot_t prot) { } +#endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ + +static void __init swap_migration_tests(void) +{ + struct page *page; + swp_entry_t swp; + + if (!IS_ENABLED(CONFIG_MIGRATION)) + return; + + pr_debug("Validating swap migration\n"); + /* + * swap_migration_tests() requires a dedicated page as it needs to + * be locked before creating a migration entry from it. Locking the + * page that actually maps kernel text ('start_kernel') can be real + * problematic. Lets allocate a dedicated page explicitly for this + * purpose that will be freed subsequently. + */ + page = alloc_page(GFP_KERNEL); + if (!page) { + pr_err("page allocation failed\n"); + return; + } + + /* + * make_migration_entry() expects given page to be + * locked, otherwise it stumbles upon a BUG_ON(). + */ + __SetPageLocked(page); + swp = make_migration_entry(page, 1); + WARN_ON(!is_migration_entry(swp)); + WARN_ON(!is_write_migration_entry(swp)); + + make_migration_entry_read(&swp); + WARN_ON(!is_migration_entry(swp)); + WARN_ON(is_write_migration_entry(swp)); + + swp = make_migration_entry(page, 0); + WARN_ON(!is_migration_entry(swp)); + WARN_ON(is_write_migration_entry(swp)); + __ClearPageLocked(page); + __free_page(page); +} + +#ifdef CONFIG_HUGETLB_PAGE +static void __init hugetlb_basic_tests(unsigned long pfn, pgprot_t prot) +{ + struct page *page; + pte_t pte; + + pr_debug("Validating HugeTLB basic\n"); + /* + * Accessing the page associated with the pfn is safe here, + * as it was previously derived from a real kernel symbol. + */ + page = pfn_to_page(pfn); + pte = mk_huge_pte(page, prot); + + WARN_ON(!huge_pte_dirty(huge_pte_mkdirty(pte))); + WARN_ON(!huge_pte_write(huge_pte_mkwrite(huge_pte_wrprotect(pte)))); + WARN_ON(huge_pte_write(huge_pte_wrprotect(huge_pte_mkwrite(pte)))); + +#ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB + pte = pfn_pte(pfn, prot); + + WARN_ON(!pte_huge(pte_mkhuge(pte))); +#endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */ +} +#else /* !CONFIG_HUGETLB_PAGE */ +static void __init hugetlb_basic_tests(unsigned long pfn, pgprot_t prot) { } +#endif /* CONFIG_HUGETLB_PAGE */ + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static void __init pmd_thp_tests(unsigned long pfn, pgprot_t prot) +{ + pmd_t pmd; + + if (!has_transparent_hugepage()) + return; + + pr_debug("Validating PMD based THP\n"); + /* + * pmd_trans_huge() and pmd_present() must return positive after + * MMU invalidation with pmd_mkinvalid(). This behavior is an + * optimization for transparent huge page. pmd_trans_huge() must + * be true if pmd_page() returns a valid THP to avoid taking the + * pmd_lock when others walk over non transhuge pmds (i.e. there + * are no THP allocated). Especially when splitting a THP and + * removing the present bit from the pmd, pmd_trans_huge() still + * needs to return true. pmd_present() should be true whenever + * pmd_trans_huge() returns true. + */ + pmd = pfn_pmd(pfn, prot); + WARN_ON(!pmd_trans_huge(pmd_mkhuge(pmd))); + +#ifndef __HAVE_ARCH_PMDP_INVALIDATE + WARN_ON(!pmd_trans_huge(pmd_mkinvalid(pmd_mkhuge(pmd)))); + WARN_ON(!pmd_present(pmd_mkinvalid(pmd_mkhuge(pmd)))); +#endif /* __HAVE_ARCH_PMDP_INVALIDATE */ +} + +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +static void __init pud_thp_tests(unsigned long pfn, pgprot_t prot) +{ + pud_t pud; + + if (!has_transparent_hugepage()) + return; + + pr_debug("Validating PUD based THP\n"); + pud = pfn_pud(pfn, prot); + WARN_ON(!pud_trans_huge(pud_mkhuge(pud))); + + /* + * pud_mkinvalid() has been dropped for now. Enable back + * these tests when it comes back with a modified pud_present(). + * + * WARN_ON(!pud_trans_huge(pud_mkinvalid(pud_mkhuge(pud)))); + * WARN_ON(!pud_present(pud_mkinvalid(pud_mkhuge(pud)))); + */ +} +#else /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ +static void __init pud_thp_tests(unsigned long pfn, pgprot_t prot) { } +#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ +#else /* !CONFIG_TRANSPARENT_HUGEPAGE */ +static void __init pmd_thp_tests(unsigned long pfn, pgprot_t prot) { } +static void __init pud_thp_tests(unsigned long pfn, pgprot_t prot) { } +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +static unsigned long __init get_random_vaddr(void) +{ + unsigned long random_vaddr, random_pages, total_user_pages; + + total_user_pages = (TASK_SIZE - FIRST_USER_ADDRESS) / PAGE_SIZE; + + random_pages = get_random_long() % total_user_pages; + random_vaddr = FIRST_USER_ADDRESS + random_pages * PAGE_SIZE; + + return random_vaddr; +} + +static int __init debug_vm_pgtable(void) +{ + struct vm_area_struct *vma; + struct mm_struct *mm; + pgd_t *pgdp; + p4d_t *p4dp, *saved_p4dp; + pud_t *pudp, *saved_pudp; + pmd_t *pmdp, *saved_pmdp, pmd; + pte_t *ptep; + pgtable_t saved_ptep; + pgprot_t prot, protnone; + phys_addr_t paddr; + unsigned long vaddr, pte_aligned, pmd_aligned; + unsigned long pud_aligned, p4d_aligned, pgd_aligned; + spinlock_t *ptl = NULL; + int idx; + + pr_info("Validating architecture page table helpers\n"); + prot = vm_get_page_prot(VMFLAGS); + vaddr = get_random_vaddr(); + mm = mm_alloc(); + if (!mm) { + pr_err("mm_struct allocation failed\n"); + return 1; + } + + /* + * __P000 (or even __S000) will help create page table entries with + * PROT_NONE permission as required for pxx_protnone_tests(). + */ + protnone = __P000; + + vma = vm_area_alloc(mm); + if (!vma) { + pr_err("vma allocation failed\n"); + return 1; + } + + /* + * PFN for mapping at PTE level is determined from a standard kernel + * text symbol. But pfns for higher page table levels are derived by + * masking lower bits of this real pfn. These derived pfns might not + * exist on the platform but that does not really matter as pfn_pxx() + * helpers will still create appropriate entries for the test. This + * helps avoid large memory block allocations to be used for mapping + * at higher page table levels. + */ + paddr = __pa_symbol(&start_kernel); + + pte_aligned = (paddr & PAGE_MASK) >> PAGE_SHIFT; + pmd_aligned = (paddr & PMD_MASK) >> PAGE_SHIFT; + pud_aligned = (paddr & PUD_MASK) >> PAGE_SHIFT; + p4d_aligned = (paddr & P4D_MASK) >> PAGE_SHIFT; + pgd_aligned = (paddr & PGDIR_MASK) >> PAGE_SHIFT; + WARN_ON(!pfn_valid(pte_aligned)); + + pgdp = pgd_offset(mm, vaddr); + p4dp = p4d_alloc(mm, pgdp, vaddr); + pudp = pud_alloc(mm, p4dp, vaddr); + pmdp = pmd_alloc(mm, pudp, vaddr); + /* + * Allocate pgtable_t + */ + if (pte_alloc(mm, pmdp)) { + pr_err("pgtable allocation failed\n"); + return 1; + } + + /* + * Save all the page table page addresses as the page table + * entries will be used for testing with random or garbage + * values. These saved addresses will be used for freeing + * page table pages. + */ + pmd = READ_ONCE(*pmdp); + saved_p4dp = p4d_offset(pgdp, 0UL); + saved_pudp = pud_offset(p4dp, 0UL); + saved_pmdp = pmd_offset(pudp, 0UL); + saved_ptep = pmd_pgtable(pmd); + + /* + * Iterate over the protection_map[] to make sure that all + * the basic page table transformation validations just hold + * true irrespective of the starting protection value for a + * given page table entry. + */ + for (idx = 0; idx < ARRAY_SIZE(protection_map); idx++) { + pte_basic_tests(pte_aligned, idx); + pmd_basic_tests(pmd_aligned, idx); + pud_basic_tests(mm, pud_aligned, idx); + } + + /* + * Both P4D and PGD level tests are very basic which do not + * involve creating page table entries from the protection + * value and the given pfn. Hence just keep them out from + * the above iteration for now to save some test execution + * time. + */ + p4d_basic_tests(p4d_aligned, prot); + pgd_basic_tests(pgd_aligned, prot); + + pmd_leaf_tests(pmd_aligned, prot); + pud_leaf_tests(pud_aligned, prot); + + pte_savedwrite_tests(pte_aligned, protnone); + pmd_savedwrite_tests(pmd_aligned, protnone); + + pte_special_tests(pte_aligned, prot); + pte_protnone_tests(pte_aligned, protnone); + pmd_protnone_tests(pmd_aligned, protnone); + + pte_devmap_tests(pte_aligned, prot); + pmd_devmap_tests(pmd_aligned, prot); + pud_devmap_tests(pud_aligned, prot); + + pte_soft_dirty_tests(pte_aligned, prot); + pmd_soft_dirty_tests(pmd_aligned, prot); + pte_swap_soft_dirty_tests(pte_aligned, prot); + pmd_swap_soft_dirty_tests(pmd_aligned, prot); + + pte_swap_tests(pte_aligned, prot); + pmd_swap_tests(pmd_aligned, prot); + + swap_migration_tests(); + + pmd_thp_tests(pmd_aligned, prot); + pud_thp_tests(pud_aligned, prot); + + hugetlb_basic_tests(pte_aligned, prot); + + /* + * Page table modifying tests. They need to hold + * proper page table lock. + */ + + ptep = pte_offset_map_lock(mm, pmdp, vaddr, &ptl); + pte_clear_tests(mm, ptep, pte_aligned, vaddr, prot); + pte_advanced_tests(mm, vma, ptep, pte_aligned, vaddr, prot); + pte_unmap_unlock(ptep, ptl); + + ptl = pmd_lock(mm, pmdp); + pmd_clear_tests(mm, pmdp); + pmd_advanced_tests(mm, vma, pmdp, pmd_aligned, vaddr, prot, saved_ptep); + pmd_huge_tests(pmdp, pmd_aligned, prot); + pmd_populate_tests(mm, pmdp, saved_ptep); + spin_unlock(ptl); + + ptl = pud_lock(mm, pudp); + pud_clear_tests(mm, pudp); + pud_advanced_tests(mm, vma, pudp, pud_aligned, vaddr, prot); + pud_huge_tests(pudp, pud_aligned, prot); + pud_populate_tests(mm, pudp, saved_pmdp); + spin_unlock(ptl); + + spin_lock(&mm->page_table_lock); + p4d_clear_tests(mm, p4dp); + pgd_clear_tests(mm, pgdp); + p4d_populate_tests(mm, p4dp, saved_pudp); + pgd_populate_tests(mm, pgdp, saved_p4dp); + spin_unlock(&mm->page_table_lock); + + p4d_free(mm, saved_p4dp); + pud_free(mm, saved_pudp); + pmd_free(mm, saved_pmdp); + pte_free(mm, saved_ptep); + + vm_area_free(vma); + mm_dec_nr_puds(mm); + mm_dec_nr_pmds(mm); + mm_dec_nr_ptes(mm); + mmdrop(mm); + return 0; +} +late_initcall(debug_vm_pgtable); diff --git a/mm/dmapool.c b/mm/dmapool.c new file mode 100644 index 000000000..a97c97232 --- /dev/null +++ b/mm/dmapool.c @@ -0,0 +1,529 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * DMA Pool allocator + * + * Copyright 2001 David Brownell + * Copyright 2007 Intel Corporation + * Author: Matthew Wilcox + * + * This allocator returns small blocks of a given size which are DMA-able by + * the given device. It uses the dma_alloc_coherent page allocator to get + * new pages, then splits them up into blocks of the required size. + * Many older drivers still have their own code to do this. + * + * The current design of this allocator is fairly simple. The pool is + * represented by the 'struct dma_pool' which keeps a doubly-linked list of + * allocated pages. Each page in the page_list is split into blocks of at + * least 'size' bytes. Free blocks are tracked in an unsorted singly-linked + * list of free blocks within the page. Used blocks aren't tracked, but we + * keep a count of how many are currently allocated from each page. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_SLUB_DEBUG_ON) +#define DMAPOOL_DEBUG 1 +#endif + +struct dma_pool { /* the pool */ + struct list_head page_list; + spinlock_t lock; + size_t size; + struct device *dev; + size_t allocation; + size_t boundary; + char name[32]; + struct list_head pools; +}; + +struct dma_page { /* cacheable header for 'allocation' bytes */ + struct list_head page_list; + void *vaddr; + dma_addr_t dma; + unsigned int in_use; + unsigned int offset; +}; + +static DEFINE_MUTEX(pools_lock); +static DEFINE_MUTEX(pools_reg_lock); + +static ssize_t +show_pools(struct device *dev, struct device_attribute *attr, char *buf) +{ + unsigned temp; + unsigned size; + char *next; + struct dma_page *page; + struct dma_pool *pool; + + next = buf; + size = PAGE_SIZE; + + temp = scnprintf(next, size, "poolinfo - 0.1\n"); + size -= temp; + next += temp; + + mutex_lock(&pools_lock); + list_for_each_entry(pool, &dev->dma_pools, pools) { + unsigned pages = 0; + unsigned blocks = 0; + + spin_lock_irq(&pool->lock); + list_for_each_entry(page, &pool->page_list, page_list) { + pages++; + blocks += page->in_use; + } + spin_unlock_irq(&pool->lock); + + /* per-pool info, no real statistics yet */ + temp = scnprintf(next, size, "%-16s %4u %4zu %4zu %2u\n", + pool->name, blocks, + pages * (pool->allocation / pool->size), + pool->size, pages); + size -= temp; + next += temp; + } + mutex_unlock(&pools_lock); + + return PAGE_SIZE - size; +} + +static DEVICE_ATTR(pools, 0444, show_pools, NULL); + +/** + * dma_pool_create - Creates a pool of consistent memory blocks, for dma. + * @name: name of pool, for diagnostics + * @dev: device that will be doing the DMA + * @size: size of the blocks in this pool. + * @align: alignment requirement for blocks; must be a power of two + * @boundary: returned blocks won't cross this power of two boundary + * Context: not in_interrupt() + * + * Given one of these pools, dma_pool_alloc() + * may be used to allocate memory. Such memory will all have "consistent" + * DMA mappings, accessible by the device and its driver without using + * cache flushing primitives. The actual size of blocks allocated may be + * larger than requested because of alignment. + * + * If @boundary is nonzero, objects returned from dma_pool_alloc() won't + * cross that size boundary. This is useful for devices which have + * addressing restrictions on individual DMA transfers, such as not crossing + * boundaries of 4KBytes. + * + * Return: a dma allocation pool with the requested characteristics, or + * %NULL if one can't be created. + */ +struct dma_pool *dma_pool_create(const char *name, struct device *dev, + size_t size, size_t align, size_t boundary) +{ + struct dma_pool *retval; + size_t allocation; + bool empty = false; + + if (align == 0) + align = 1; + else if (align & (align - 1)) + return NULL; + + if (size == 0) + return NULL; + else if (size < 4) + size = 4; + + size = ALIGN(size, align); + allocation = max_t(size_t, size, PAGE_SIZE); + + if (!boundary) + boundary = allocation; + else if ((boundary < size) || (boundary & (boundary - 1))) + return NULL; + + retval = kmalloc_node(sizeof(*retval), GFP_KERNEL, dev_to_node(dev)); + if (!retval) + return retval; + + strlcpy(retval->name, name, sizeof(retval->name)); + + retval->dev = dev; + + INIT_LIST_HEAD(&retval->page_list); + spin_lock_init(&retval->lock); + retval->size = size; + retval->boundary = boundary; + retval->allocation = allocation; + + INIT_LIST_HEAD(&retval->pools); + + /* + * pools_lock ensures that the ->dma_pools list does not get corrupted. + * pools_reg_lock ensures that there is not a race between + * dma_pool_create() and dma_pool_destroy() or within dma_pool_create() + * when the first invocation of dma_pool_create() failed on + * device_create_file() and the second assumes that it has been done (I + * know it is a short window). + */ + mutex_lock(&pools_reg_lock); + mutex_lock(&pools_lock); + if (list_empty(&dev->dma_pools)) + empty = true; + list_add(&retval->pools, &dev->dma_pools); + mutex_unlock(&pools_lock); + if (empty) { + int err; + + err = device_create_file(dev, &dev_attr_pools); + if (err) { + mutex_lock(&pools_lock); + list_del(&retval->pools); + mutex_unlock(&pools_lock); + mutex_unlock(&pools_reg_lock); + kfree(retval); + return NULL; + } + } + mutex_unlock(&pools_reg_lock); + return retval; +} +EXPORT_SYMBOL(dma_pool_create); + +static void pool_initialise_page(struct dma_pool *pool, struct dma_page *page) +{ + unsigned int offset = 0; + unsigned int next_boundary = pool->boundary; + + do { + unsigned int next = offset + pool->size; + if (unlikely((next + pool->size) >= next_boundary)) { + next = next_boundary; + next_boundary += pool->boundary; + } + *(int *)(page->vaddr + offset) = next; + offset = next; + } while (offset < pool->allocation); +} + +static struct dma_page *pool_alloc_page(struct dma_pool *pool, gfp_t mem_flags) +{ + struct dma_page *page; + + page = kmalloc(sizeof(*page), mem_flags); + if (!page) + return NULL; + page->vaddr = dma_alloc_coherent(pool->dev, pool->allocation, + &page->dma, mem_flags); + if (page->vaddr) { +#ifdef DMAPOOL_DEBUG + memset(page->vaddr, POOL_POISON_FREED, pool->allocation); +#endif + pool_initialise_page(pool, page); + page->in_use = 0; + page->offset = 0; + } else { + kfree(page); + page = NULL; + } + return page; +} + +static inline bool is_page_busy(struct dma_page *page) +{ + return page->in_use != 0; +} + +static void pool_free_page(struct dma_pool *pool, struct dma_page *page) +{ + dma_addr_t dma = page->dma; + +#ifdef DMAPOOL_DEBUG + memset(page->vaddr, POOL_POISON_FREED, pool->allocation); +#endif + dma_free_coherent(pool->dev, pool->allocation, page->vaddr, dma); + list_del(&page->page_list); + kfree(page); +} + +/** + * dma_pool_destroy - destroys a pool of dma memory blocks. + * @pool: dma pool that will be destroyed + * Context: !in_interrupt() + * + * Caller guarantees that no more memory from the pool is in use, + * and that nothing will try to use the pool after this call. + */ +void dma_pool_destroy(struct dma_pool *pool) +{ + struct dma_page *page, *tmp; + bool empty = false; + + if (unlikely(!pool)) + return; + + mutex_lock(&pools_reg_lock); + mutex_lock(&pools_lock); + list_del(&pool->pools); + if (pool->dev && list_empty(&pool->dev->dma_pools)) + empty = true; + mutex_unlock(&pools_lock); + if (empty) + device_remove_file(pool->dev, &dev_attr_pools); + mutex_unlock(&pools_reg_lock); + + list_for_each_entry_safe(page, tmp, &pool->page_list, page_list) { + if (is_page_busy(page)) { + if (pool->dev) + dev_err(pool->dev, "%s %s, %p busy\n", __func__, + pool->name, page->vaddr); + else + pr_err("%s %s, %p busy\n", __func__, + pool->name, page->vaddr); + /* leak the still-in-use consistent memory */ + list_del(&page->page_list); + kfree(page); + } else + pool_free_page(pool, page); + } + + kfree(pool); +} +EXPORT_SYMBOL(dma_pool_destroy); + +/** + * dma_pool_alloc - get a block of consistent memory + * @pool: dma pool that will produce the block + * @mem_flags: GFP_* bitmask + * @handle: pointer to dma address of block + * + * Return: the kernel virtual address of a currently unused block, + * and reports its dma address through the handle. + * If such a memory block can't be allocated, %NULL is returned. + */ +void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags, + dma_addr_t *handle) +{ + unsigned long flags; + struct dma_page *page; + size_t offset; + void *retval; + + might_sleep_if(gfpflags_allow_blocking(mem_flags)); + + spin_lock_irqsave(&pool->lock, flags); + list_for_each_entry(page, &pool->page_list, page_list) { + if (page->offset < pool->allocation) + goto ready; + } + + /* pool_alloc_page() might sleep, so temporarily drop &pool->lock */ + spin_unlock_irqrestore(&pool->lock, flags); + + page = pool_alloc_page(pool, mem_flags & (~__GFP_ZERO)); + if (!page) + return NULL; + + spin_lock_irqsave(&pool->lock, flags); + + list_add(&page->page_list, &pool->page_list); + ready: + page->in_use++; + offset = page->offset; + page->offset = *(int *)(page->vaddr + offset); + retval = offset + page->vaddr; + *handle = offset + page->dma; +#ifdef DMAPOOL_DEBUG + { + int i; + u8 *data = retval; + /* page->offset is stored in first 4 bytes */ + for (i = sizeof(page->offset); i < pool->size; i++) { + if (data[i] == POOL_POISON_FREED) + continue; + if (pool->dev) + dev_err(pool->dev, "%s %s, %p (corrupted)\n", + __func__, pool->name, retval); + else + pr_err("%s %s, %p (corrupted)\n", + __func__, pool->name, retval); + + /* + * Dump the first 4 bytes even if they are not + * POOL_POISON_FREED + */ + print_hex_dump(KERN_ERR, "", DUMP_PREFIX_OFFSET, 16, 1, + data, pool->size, 1); + break; + } + } + if (!(mem_flags & __GFP_ZERO)) + memset(retval, POOL_POISON_ALLOCATED, pool->size); +#endif + spin_unlock_irqrestore(&pool->lock, flags); + + if (want_init_on_alloc(mem_flags)) + memset(retval, 0, pool->size); + + return retval; +} +EXPORT_SYMBOL(dma_pool_alloc); + +static struct dma_page *pool_find_page(struct dma_pool *pool, dma_addr_t dma) +{ + struct dma_page *page; + + list_for_each_entry(page, &pool->page_list, page_list) { + if (dma < page->dma) + continue; + if ((dma - page->dma) < pool->allocation) + return page; + } + return NULL; +} + +/** + * dma_pool_free - put block back into dma pool + * @pool: the dma pool holding the block + * @vaddr: virtual address of block + * @dma: dma address of block + * + * Caller promises neither device nor driver will again touch this block + * unless it is first re-allocated. + */ +void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma) +{ + struct dma_page *page; + unsigned long flags; + unsigned int offset; + + spin_lock_irqsave(&pool->lock, flags); + page = pool_find_page(pool, dma); + if (!page) { + spin_unlock_irqrestore(&pool->lock, flags); + if (pool->dev) + dev_err(pool->dev, "%s %s, %p/%pad (bad dma)\n", + __func__, pool->name, vaddr, &dma); + else + pr_err("%s %s, %p/%pad (bad dma)\n", + __func__, pool->name, vaddr, &dma); + return; + } + + offset = vaddr - page->vaddr; + if (want_init_on_free()) + memset(vaddr, 0, pool->size); +#ifdef DMAPOOL_DEBUG + if ((dma - page->dma) != offset) { + spin_unlock_irqrestore(&pool->lock, flags); + if (pool->dev) + dev_err(pool->dev, "%s %s, %p (bad vaddr)/%pad\n", + __func__, pool->name, vaddr, &dma); + else + pr_err("%s %s, %p (bad vaddr)/%pad\n", + __func__, pool->name, vaddr, &dma); + return; + } + { + unsigned int chain = page->offset; + while (chain < pool->allocation) { + if (chain != offset) { + chain = *(int *)(page->vaddr + chain); + continue; + } + spin_unlock_irqrestore(&pool->lock, flags); + if (pool->dev) + dev_err(pool->dev, "%s %s, dma %pad already free\n", + __func__, pool->name, &dma); + else + pr_err("%s %s, dma %pad already free\n", + __func__, pool->name, &dma); + return; + } + } + memset(vaddr, POOL_POISON_FREED, pool->size); +#endif + + page->in_use--; + *(int *)vaddr = page->offset; + page->offset = offset; + /* + * Resist a temptation to do + * if (!is_page_busy(page)) pool_free_page(pool, page); + * Better have a few empty pages hang around. + */ + spin_unlock_irqrestore(&pool->lock, flags); +} +EXPORT_SYMBOL(dma_pool_free); + +/* + * Managed DMA pool + */ +static void dmam_pool_release(struct device *dev, void *res) +{ + struct dma_pool *pool = *(struct dma_pool **)res; + + dma_pool_destroy(pool); +} + +static int dmam_pool_match(struct device *dev, void *res, void *match_data) +{ + return *(struct dma_pool **)res == match_data; +} + +/** + * dmam_pool_create - Managed dma_pool_create() + * @name: name of pool, for diagnostics + * @dev: device that will be doing the DMA + * @size: size of the blocks in this pool. + * @align: alignment requirement for blocks; must be a power of two + * @allocation: returned blocks won't cross this boundary (or zero) + * + * Managed dma_pool_create(). DMA pool created with this function is + * automatically destroyed on driver detach. + * + * Return: a managed dma allocation pool with the requested + * characteristics, or %NULL if one can't be created. + */ +struct dma_pool *dmam_pool_create(const char *name, struct device *dev, + size_t size, size_t align, size_t allocation) +{ + struct dma_pool **ptr, *pool; + + ptr = devres_alloc(dmam_pool_release, sizeof(*ptr), GFP_KERNEL); + if (!ptr) + return NULL; + + pool = *ptr = dma_pool_create(name, dev, size, align, allocation); + if (pool) + devres_add(dev, ptr); + else + devres_free(ptr); + + return pool; +} +EXPORT_SYMBOL(dmam_pool_create); + +/** + * dmam_pool_destroy - Managed dma_pool_destroy() + * @pool: dma pool that will be destroyed + * + * Managed dma_pool_destroy(). + */ +void dmam_pool_destroy(struct dma_pool *pool) +{ + struct device *dev = pool->dev; + + WARN_ON(devres_release(dev, dmam_pool_release, dmam_pool_match, pool)); +} +EXPORT_SYMBOL(dmam_pool_destroy); diff --git a/mm/early_ioremap.c b/mm/early_ioremap.c new file mode 100644 index 000000000..a0018ad1a --- /dev/null +++ b/mm/early_ioremap.c @@ -0,0 +1,303 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Provide common bits of early_ioremap() support for architectures needing + * temporary mappings during boot before ioremap() is available. + * + * This is mostly a direct copy of the x86 early_ioremap implementation. + * + * (C) Copyright 1995 1996, 2014 Linus Torvalds + * + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef CONFIG_MMU +static int early_ioremap_debug __initdata; + +static int __init early_ioremap_debug_setup(char *str) +{ + early_ioremap_debug = 1; + + return 0; +} +early_param("early_ioremap_debug", early_ioremap_debug_setup); + +static int after_paging_init __initdata; + +pgprot_t __init __weak early_memremap_pgprot_adjust(resource_size_t phys_addr, + unsigned long size, + pgprot_t prot) +{ + return prot; +} + +void __init __weak early_ioremap_shutdown(void) +{ +} + +void __init early_ioremap_reset(void) +{ + early_ioremap_shutdown(); + after_paging_init = 1; +} + +/* + * Generally, ioremap() is available after paging_init() has been called. + * Architectures wanting to allow early_ioremap after paging_init() can + * define __late_set_fixmap and __late_clear_fixmap to do the right thing. + */ +#ifndef __late_set_fixmap +static inline void __init __late_set_fixmap(enum fixed_addresses idx, + phys_addr_t phys, pgprot_t prot) +{ + BUG(); +} +#endif + +#ifndef __late_clear_fixmap +static inline void __init __late_clear_fixmap(enum fixed_addresses idx) +{ + BUG(); +} +#endif + +static void __iomem *prev_map[FIX_BTMAPS_SLOTS] __initdata; +static unsigned long prev_size[FIX_BTMAPS_SLOTS] __initdata; +static unsigned long slot_virt[FIX_BTMAPS_SLOTS] __initdata; + +void __init early_ioremap_setup(void) +{ + int i; + + for (i = 0; i < FIX_BTMAPS_SLOTS; i++) + if (WARN_ON(prev_map[i])) + break; + + for (i = 0; i < FIX_BTMAPS_SLOTS; i++) + slot_virt[i] = __fix_to_virt(FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*i); +} + +static int __init check_early_ioremap_leak(void) +{ + int count = 0; + int i; + + for (i = 0; i < FIX_BTMAPS_SLOTS; i++) + if (prev_map[i]) + count++; + + if (WARN(count, KERN_WARNING + "Debug warning: early ioremap leak of %d areas detected.\n" + "please boot with early_ioremap_debug and report the dmesg.\n", + count)) + return 1; + return 0; +} +late_initcall(check_early_ioremap_leak); + +static void __init __iomem * +__early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot) +{ + unsigned long offset; + resource_size_t last_addr; + unsigned int nrpages; + enum fixed_addresses idx; + int i, slot; + + WARN_ON(system_state >= SYSTEM_RUNNING); + + slot = -1; + for (i = 0; i < FIX_BTMAPS_SLOTS; i++) { + if (!prev_map[i]) { + slot = i; + break; + } + } + + if (WARN(slot < 0, "%s(%pa, %08lx) not found slot\n", + __func__, &phys_addr, size)) + return NULL; + + /* Don't allow wraparound or zero size */ + last_addr = phys_addr + size - 1; + if (WARN_ON(!size || last_addr < phys_addr)) + return NULL; + + prev_size[slot] = size; + /* + * Mappings have to be page-aligned + */ + offset = offset_in_page(phys_addr); + phys_addr &= PAGE_MASK; + size = PAGE_ALIGN(last_addr + 1) - phys_addr; + + /* + * Mappings have to fit in the FIX_BTMAP area. + */ + nrpages = size >> PAGE_SHIFT; + if (WARN_ON(nrpages > NR_FIX_BTMAPS)) + return NULL; + + /* + * Ok, go for it.. + */ + idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot; + while (nrpages > 0) { + if (after_paging_init) + __late_set_fixmap(idx, phys_addr, prot); + else + __early_set_fixmap(idx, phys_addr, prot); + phys_addr += PAGE_SIZE; + --idx; + --nrpages; + } + WARN(early_ioremap_debug, "%s(%pa, %08lx) [%d] => %08lx + %08lx\n", + __func__, &phys_addr, size, slot, offset, slot_virt[slot]); + + prev_map[slot] = (void __iomem *)(offset + slot_virt[slot]); + return prev_map[slot]; +} + +void __init early_iounmap(void __iomem *addr, unsigned long size) +{ + unsigned long virt_addr; + unsigned long offset; + unsigned int nrpages; + enum fixed_addresses idx; + int i, slot; + + slot = -1; + for (i = 0; i < FIX_BTMAPS_SLOTS; i++) { + if (prev_map[i] == addr) { + slot = i; + break; + } + } + + if (WARN(slot < 0, "early_iounmap(%p, %08lx) not found slot\n", + addr, size)) + return; + + if (WARN(prev_size[slot] != size, + "early_iounmap(%p, %08lx) [%d] size not consistent %08lx\n", + addr, size, slot, prev_size[slot])) + return; + + WARN(early_ioremap_debug, "early_iounmap(%p, %08lx) [%d]\n", + addr, size, slot); + + virt_addr = (unsigned long)addr; + if (WARN_ON(virt_addr < fix_to_virt(FIX_BTMAP_BEGIN))) + return; + + offset = offset_in_page(virt_addr); + nrpages = PAGE_ALIGN(offset + size) >> PAGE_SHIFT; + + idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot; + while (nrpages > 0) { + if (after_paging_init) + __late_clear_fixmap(idx); + else + __early_set_fixmap(idx, 0, FIXMAP_PAGE_CLEAR); + --idx; + --nrpages; + } + prev_map[slot] = NULL; +} + +/* Remap an IO device */ +void __init __iomem * +early_ioremap(resource_size_t phys_addr, unsigned long size) +{ + return __early_ioremap(phys_addr, size, FIXMAP_PAGE_IO); +} + +/* Remap memory */ +void __init * +early_memremap(resource_size_t phys_addr, unsigned long size) +{ + pgprot_t prot = early_memremap_pgprot_adjust(phys_addr, size, + FIXMAP_PAGE_NORMAL); + + return (__force void *)__early_ioremap(phys_addr, size, prot); +} +#ifdef FIXMAP_PAGE_RO +void __init * +early_memremap_ro(resource_size_t phys_addr, unsigned long size) +{ + pgprot_t prot = early_memremap_pgprot_adjust(phys_addr, size, + FIXMAP_PAGE_RO); + + return (__force void *)__early_ioremap(phys_addr, size, prot); +} +#endif + +#ifdef CONFIG_ARCH_USE_MEMREMAP_PROT +void __init * +early_memremap_prot(resource_size_t phys_addr, unsigned long size, + unsigned long prot_val) +{ + return (__force void *)__early_ioremap(phys_addr, size, + __pgprot(prot_val)); +} +#endif + +#define MAX_MAP_CHUNK (NR_FIX_BTMAPS << PAGE_SHIFT) + +void __init copy_from_early_mem(void *dest, phys_addr_t src, unsigned long size) +{ + unsigned long slop, clen; + char *p; + + while (size) { + slop = offset_in_page(src); + clen = size; + if (clen > MAX_MAP_CHUNK - slop) + clen = MAX_MAP_CHUNK - slop; + p = early_memremap(src & PAGE_MASK, clen + slop); + memcpy(dest, p + slop, clen); + early_memunmap(p, clen + slop); + dest += clen; + src += clen; + size -= clen; + } +} + +#else /* CONFIG_MMU */ + +void __init __iomem * +early_ioremap(resource_size_t phys_addr, unsigned long size) +{ + return (__force void __iomem *)phys_addr; +} + +/* Remap memory */ +void __init * +early_memremap(resource_size_t phys_addr, unsigned long size) +{ + return (void *)phys_addr; +} +void __init * +early_memremap_ro(resource_size_t phys_addr, unsigned long size) +{ + return (void *)phys_addr; +} + +void __init early_iounmap(void __iomem *addr, unsigned long size) +{ +} + +#endif /* CONFIG_MMU */ + + +void __init early_memunmap(void *addr, unsigned long size) +{ + early_iounmap((__force void __iomem *)addr, size); +} diff --git a/mm/fadvise.c b/mm/fadvise.c new file mode 100644 index 000000000..d6baa4f45 --- /dev/null +++ b/mm/fadvise.c @@ -0,0 +1,219 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * mm/fadvise.c + * + * Copyright (C) 2002, Linus Torvalds + * + * 11Jan2003 Andrew Morton + * Initial version. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "internal.h" + +/* + * POSIX_FADV_WILLNEED could set PG_Referenced, and POSIX_FADV_NOREUSE could + * deactivate the pages and clear PG_Referenced. + */ + +int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice) +{ + struct inode *inode; + struct address_space *mapping; + struct backing_dev_info *bdi; + loff_t endbyte; /* inclusive */ + pgoff_t start_index; + pgoff_t end_index; + unsigned long nrpages; + + inode = file_inode(file); + if (S_ISFIFO(inode->i_mode)) + return -ESPIPE; + + mapping = file->f_mapping; + if (!mapping || len < 0) + return -EINVAL; + + bdi = inode_to_bdi(mapping->host); + + if (IS_DAX(inode) || (bdi == &noop_backing_dev_info)) { + switch (advice) { + case POSIX_FADV_NORMAL: + case POSIX_FADV_RANDOM: + case POSIX_FADV_SEQUENTIAL: + case POSIX_FADV_WILLNEED: + case POSIX_FADV_NOREUSE: + case POSIX_FADV_DONTNEED: + /* no bad return value, but ignore advice */ + break; + default: + return -EINVAL; + } + return 0; + } + + /* + * Careful about overflows. Len == 0 means "as much as possible". Use + * unsigned math because signed overflows are undefined and UBSan + * complains. + */ + endbyte = (u64)offset + (u64)len; + if (!len || endbyte < len) + endbyte = -1; + else + endbyte--; /* inclusive */ + + switch (advice) { + case POSIX_FADV_NORMAL: + file->f_ra.ra_pages = bdi->ra_pages; + spin_lock(&file->f_lock); + file->f_mode &= ~FMODE_RANDOM; + spin_unlock(&file->f_lock); + break; + case POSIX_FADV_RANDOM: + spin_lock(&file->f_lock); + file->f_mode |= FMODE_RANDOM; + spin_unlock(&file->f_lock); + break; + case POSIX_FADV_SEQUENTIAL: + file->f_ra.ra_pages = bdi->ra_pages * 2; + spin_lock(&file->f_lock); + file->f_mode &= ~FMODE_RANDOM; + spin_unlock(&file->f_lock); + break; + case POSIX_FADV_WILLNEED: + /* First and last PARTIAL page! */ + start_index = offset >> PAGE_SHIFT; + end_index = endbyte >> PAGE_SHIFT; + + /* Careful about overflow on the "+1" */ + nrpages = end_index - start_index + 1; + if (!nrpages) + nrpages = ~0UL; + + force_page_cache_readahead(mapping, file, start_index, nrpages); + break; + case POSIX_FADV_NOREUSE: + break; + case POSIX_FADV_DONTNEED: + if (!inode_write_congested(mapping->host)) + __filemap_fdatawrite_range(mapping, offset, endbyte, + WB_SYNC_NONE); + + /* + * First and last FULL page! Partial pages are deliberately + * preserved on the expectation that it is better to preserve + * needed memory than to discard unneeded memory. + */ + start_index = (offset+(PAGE_SIZE-1)) >> PAGE_SHIFT; + end_index = (endbyte >> PAGE_SHIFT); + /* + * The page at end_index will be inclusively discarded according + * by invalidate_mapping_pages(), so subtracting 1 from + * end_index means we will skip the last page. But if endbyte + * is page aligned or is at the end of file, we should not skip + * that page - discarding the last page is safe enough. + */ + if ((endbyte & ~PAGE_MASK) != ~PAGE_MASK && + endbyte != inode->i_size - 1) { + /* First page is tricky as 0 - 1 = -1, but pgoff_t + * is unsigned, so the end_index >= start_index + * check below would be true and we'll discard the whole + * file cache which is not what was asked. + */ + if (end_index == 0) + break; + + end_index--; + } + + if (end_index >= start_index) { + unsigned long nr_pagevec = 0; + + /* + * It's common to FADV_DONTNEED right after + * the read or write that instantiates the + * pages, in which case there will be some + * sitting on the local LRU cache. Try to + * avoid the expensive remote drain and the + * second cache tree walk below by flushing + * them out right away. + */ + lru_add_drain(); + + invalidate_mapping_pagevec(mapping, + start_index, end_index, + &nr_pagevec); + + /* + * If fewer pages were invalidated than expected then + * it is possible that some of the pages were on + * a per-cpu pagevec for a remote CPU. Drain all + * pagevecs and try again. + */ + if (nr_pagevec) { + lru_add_drain_all(); + invalidate_mapping_pages(mapping, start_index, + end_index); + } + } + break; + default: + return -EINVAL; + } + return 0; +} +EXPORT_SYMBOL(generic_fadvise); + +int vfs_fadvise(struct file *file, loff_t offset, loff_t len, int advice) +{ + if (file->f_op->fadvise) + return file->f_op->fadvise(file, offset, len, advice); + + return generic_fadvise(file, offset, len, advice); +} +EXPORT_SYMBOL(vfs_fadvise); + +#ifdef CONFIG_ADVISE_SYSCALLS + +int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) +{ + struct fd f = fdget(fd); + int ret; + + if (!f.file) + return -EBADF; + + ret = vfs_fadvise(f.file, offset, len, advice); + + fdput(f); + return ret; +} + +SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice) +{ + return ksys_fadvise64_64(fd, offset, len, advice); +} + +#ifdef __ARCH_WANT_SYS_FADVISE64 + +SYSCALL_DEFINE4(fadvise64, int, fd, loff_t, offset, size_t, len, int, advice) +{ + return ksys_fadvise64_64(fd, offset, len, advice); +} + +#endif +#endif diff --git a/mm/failslab.c b/mm/failslab.c new file mode 100644 index 000000000..f92fed91a --- /dev/null +++ b/mm/failslab.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include "slab.h" + +static struct { + struct fault_attr attr; + bool ignore_gfp_reclaim; + bool cache_filter; +} failslab = { + .attr = FAULT_ATTR_INITIALIZER, + .ignore_gfp_reclaim = true, + .cache_filter = false, +}; + +bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags) +{ + /* No fault-injection for bootstrap cache */ + if (unlikely(s == kmem_cache)) + return false; + + if (gfpflags & __GFP_NOFAIL) + return false; + + if (failslab.ignore_gfp_reclaim && + (gfpflags & __GFP_DIRECT_RECLAIM)) + return false; + + if (failslab.cache_filter && !(s->flags & SLAB_FAILSLAB)) + return false; + + return should_fail(&failslab.attr, s->object_size); +} + +static int __init setup_failslab(char *str) +{ + return setup_fault_attr(&failslab.attr, str); +} +__setup("failslab=", setup_failslab); + +#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS +static int __init failslab_debugfs_init(void) +{ + struct dentry *dir; + umode_t mode = S_IFREG | 0600; + + dir = fault_create_debugfs_attr("failslab", NULL, &failslab.attr); + if (IS_ERR(dir)) + return PTR_ERR(dir); + + debugfs_create_bool("ignore-gfp-wait", mode, dir, + &failslab.ignore_gfp_reclaim); + debugfs_create_bool("cache-filter", mode, dir, + &failslab.cache_filter); + + return 0; +} + +late_initcall(failslab_debugfs_init); + +#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ diff --git a/mm/filemap.c b/mm/filemap.c new file mode 100644 index 000000000..3b0d8c6dd --- /dev/null +++ b/mm/filemap.c @@ -0,0 +1,3536 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/mm/filemap.c + * + * Copyright (C) 1994-1999 Linus Torvalds + */ + +/* + * This file handles the generic file mmap semantics used by + * most "normal" filesystems (but you don't /have/ to use this: + * the NFS filesystem used to do this differently, for example) + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "internal.h" + +#define CREATE_TRACE_POINTS +#include + +/* + * FIXME: remove all knowledge of the buffer layer from the core VM + */ +#include /* for try_to_free_buffers */ + +#include + +/* + * Shared mappings implemented 30.11.1994. It's not fully working yet, + * though. + * + * Shared mappings now work. 15.8.1995 Bruno. + * + * finished 'unifying' the page and buffer cache and SMP-threaded the + * page-cache, 21.05.1999, Ingo Molnar + * + * SMP-threaded pagemap-LRU 1999, Andrea Arcangeli + */ + +/* + * Lock ordering: + * + * ->i_mmap_rwsem (truncate_pagecache) + * ->private_lock (__free_pte->__set_page_dirty_buffers) + * ->swap_lock (exclusive_swap_page, others) + * ->i_pages lock + * + * ->i_mutex + * ->i_mmap_rwsem (truncate->unmap_mapping_range) + * + * ->mmap_lock + * ->i_mmap_rwsem + * ->page_table_lock or pte_lock (various, mainly in memory.c) + * ->i_pages lock (arch-dependent flush_dcache_mmap_lock) + * + * ->mmap_lock + * ->lock_page (access_process_vm) + * + * ->i_mutex (generic_perform_write) + * ->mmap_lock (fault_in_pages_readable->do_page_fault) + * + * bdi->wb.list_lock + * sb_lock (fs/fs-writeback.c) + * ->i_pages lock (__sync_single_inode) + * + * ->i_mmap_rwsem + * ->anon_vma.lock (vma_adjust) + * + * ->anon_vma.lock + * ->page_table_lock or pte_lock (anon_vma_prepare and various) + * + * ->page_table_lock or pte_lock + * ->swap_lock (try_to_unmap_one) + * ->private_lock (try_to_unmap_one) + * ->i_pages lock (try_to_unmap_one) + * ->pgdat->lru_lock (follow_page->mark_page_accessed) + * ->pgdat->lru_lock (check_pte_range->isolate_lru_page) + * ->private_lock (page_remove_rmap->set_page_dirty) + * ->i_pages lock (page_remove_rmap->set_page_dirty) + * bdi.wb->list_lock (page_remove_rmap->set_page_dirty) + * ->inode->i_lock (page_remove_rmap->set_page_dirty) + * ->memcg->move_lock (page_remove_rmap->lock_page_memcg) + * bdi.wb->list_lock (zap_pte_range->set_page_dirty) + * ->inode->i_lock (zap_pte_range->set_page_dirty) + * ->private_lock (zap_pte_range->__set_page_dirty_buffers) + * + * ->i_mmap_rwsem + * ->tasklist_lock (memory_failure, collect_procs_ao) + */ + +static void page_cache_delete(struct address_space *mapping, + struct page *page, void *shadow) +{ + XA_STATE(xas, &mapping->i_pages, page->index); + unsigned int nr = 1; + + mapping_set_update(&xas, mapping); + + /* hugetlb pages are represented by a single entry in the xarray */ + if (!PageHuge(page)) { + xas_set_order(&xas, page->index, compound_order(page)); + nr = compound_nr(page); + } + + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(PageTail(page), page); + VM_BUG_ON_PAGE(nr != 1 && shadow, page); + + xas_store(&xas, shadow); + xas_init_marks(&xas); + + page->mapping = NULL; + /* Leave page->index set: truncation lookup relies upon it */ + + if (shadow) { + mapping->nrexceptional += nr; + /* + * Make sure the nrexceptional update is committed before + * the nrpages update so that final truncate racing + * with reclaim does not see both counters 0 at the + * same time and miss a shadow entry. + */ + smp_wmb(); + } + mapping->nrpages -= nr; +} + +static void unaccount_page_cache_page(struct address_space *mapping, + struct page *page) +{ + int nr; + + /* + * if we're uptodate, flush out into the cleancache, otherwise + * invalidate any existing cleancache entries. We can't leave + * stale data around in the cleancache once our page is gone + */ + if (PageUptodate(page) && PageMappedToDisk(page)) + cleancache_put_page(page); + else + cleancache_invalidate_page(mapping, page); + + VM_BUG_ON_PAGE(PageTail(page), page); + VM_BUG_ON_PAGE(page_mapped(page), page); + if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(page_mapped(page))) { + int mapcount; + + pr_alert("BUG: Bad page cache in process %s pfn:%05lx\n", + current->comm, page_to_pfn(page)); + dump_page(page, "still mapped when deleted"); + dump_stack(); + add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); + + mapcount = page_mapcount(page); + if (mapping_exiting(mapping) && + page_count(page) >= mapcount + 2) { + /* + * All vmas have already been torn down, so it's + * a good bet that actually the page is unmapped, + * and we'd prefer not to leak it: if we're wrong, + * some other bad page check should catch it later. + */ + page_mapcount_reset(page); + page_ref_sub(page, mapcount); + } + } + + /* hugetlb pages do not participate in page cache accounting. */ + if (PageHuge(page)) + return; + + nr = thp_nr_pages(page); + + __mod_lruvec_page_state(page, NR_FILE_PAGES, -nr); + if (PageSwapBacked(page)) { + __mod_lruvec_page_state(page, NR_SHMEM, -nr); + if (PageTransHuge(page)) + __dec_node_page_state(page, NR_SHMEM_THPS); + } else if (PageTransHuge(page)) { + __dec_node_page_state(page, NR_FILE_THPS); + filemap_nr_thps_dec(mapping); + } + + /* + * At this point page must be either written or cleaned by + * truncate. Dirty page here signals a bug and loss of + * unwritten data. + * + * This fixes dirty accounting after removing the page entirely + * but leaves PageDirty set: it has no effect for truncated + * page and anyway will be cleared before returning page into + * buddy allocator. + */ + if (WARN_ON_ONCE(PageDirty(page))) + account_page_cleaned(page, mapping, inode_to_wb(mapping->host)); +} + +/* + * Delete a page from the page cache and free it. Caller has to make + * sure the page is locked and that nobody else uses it - or that usage + * is safe. The caller must hold the i_pages lock. + */ +void __delete_from_page_cache(struct page *page, void *shadow) +{ + struct address_space *mapping = page->mapping; + + trace_mm_filemap_delete_from_page_cache(page); + + unaccount_page_cache_page(mapping, page); + page_cache_delete(mapping, page, shadow); +} + +static void page_cache_free_page(struct address_space *mapping, + struct page *page) +{ + void (*freepage)(struct page *); + + freepage = mapping->a_ops->freepage; + if (freepage) + freepage(page); + + if (PageTransHuge(page) && !PageHuge(page)) { + page_ref_sub(page, thp_nr_pages(page)); + VM_BUG_ON_PAGE(page_count(page) <= 0, page); + } else { + put_page(page); + } +} + +/** + * delete_from_page_cache - delete page from page cache + * @page: the page which the kernel is trying to remove from page cache + * + * This must be called only on pages that have been verified to be in the page + * cache and locked. It will never put the page into the free list, the caller + * has a reference on the page. + */ +void delete_from_page_cache(struct page *page) +{ + struct address_space *mapping = page_mapping(page); + unsigned long flags; + + BUG_ON(!PageLocked(page)); + xa_lock_irqsave(&mapping->i_pages, flags); + __delete_from_page_cache(page, NULL); + xa_unlock_irqrestore(&mapping->i_pages, flags); + + page_cache_free_page(mapping, page); +} +EXPORT_SYMBOL(delete_from_page_cache); + +/* + * page_cache_delete_batch - delete several pages from page cache + * @mapping: the mapping to which pages belong + * @pvec: pagevec with pages to delete + * + * The function walks over mapping->i_pages and removes pages passed in @pvec + * from the mapping. The function expects @pvec to be sorted by page index + * and is optimised for it to be dense. + * It tolerates holes in @pvec (mapping entries at those indices are not + * modified). The function expects only THP head pages to be present in the + * @pvec. + * + * The function expects the i_pages lock to be held. + */ +static void page_cache_delete_batch(struct address_space *mapping, + struct pagevec *pvec) +{ + XA_STATE(xas, &mapping->i_pages, pvec->pages[0]->index); + int total_pages = 0; + int i = 0; + struct page *page; + + mapping_set_update(&xas, mapping); + xas_for_each(&xas, page, ULONG_MAX) { + if (i >= pagevec_count(pvec)) + break; + + /* A swap/dax/shadow entry got inserted? Skip it. */ + if (xa_is_value(page)) + continue; + /* + * A page got inserted in our range? Skip it. We have our + * pages locked so they are protected from being removed. + * If we see a page whose index is higher than ours, it + * means our page has been removed, which shouldn't be + * possible because we're holding the PageLock. + */ + if (page != pvec->pages[i]) { + VM_BUG_ON_PAGE(page->index > pvec->pages[i]->index, + page); + continue; + } + + WARN_ON_ONCE(!PageLocked(page)); + + if (page->index == xas.xa_index) + page->mapping = NULL; + /* Leave page->index set: truncation lookup relies on it */ + + /* + * Move to the next page in the vector if this is a regular + * page or the index is of the last sub-page of this compound + * page. + */ + if (page->index + compound_nr(page) - 1 == xas.xa_index) + i++; + xas_store(&xas, NULL); + total_pages++; + } + mapping->nrpages -= total_pages; +} + +void delete_from_page_cache_batch(struct address_space *mapping, + struct pagevec *pvec) +{ + int i; + unsigned long flags; + + if (!pagevec_count(pvec)) + return; + + xa_lock_irqsave(&mapping->i_pages, flags); + for (i = 0; i < pagevec_count(pvec); i++) { + trace_mm_filemap_delete_from_page_cache(pvec->pages[i]); + + unaccount_page_cache_page(mapping, pvec->pages[i]); + } + page_cache_delete_batch(mapping, pvec); + xa_unlock_irqrestore(&mapping->i_pages, flags); + + for (i = 0; i < pagevec_count(pvec); i++) + page_cache_free_page(mapping, pvec->pages[i]); +} + +int filemap_check_errors(struct address_space *mapping) +{ + int ret = 0; + /* Check for outstanding write errors */ + if (test_bit(AS_ENOSPC, &mapping->flags) && + test_and_clear_bit(AS_ENOSPC, &mapping->flags)) + ret = -ENOSPC; + if (test_bit(AS_EIO, &mapping->flags) && + test_and_clear_bit(AS_EIO, &mapping->flags)) + ret = -EIO; + return ret; +} +EXPORT_SYMBOL(filemap_check_errors); + +static int filemap_check_and_keep_errors(struct address_space *mapping) +{ + /* Check for outstanding write errors */ + if (test_bit(AS_EIO, &mapping->flags)) + return -EIO; + if (test_bit(AS_ENOSPC, &mapping->flags)) + return -ENOSPC; + return 0; +} + +/** + * __filemap_fdatawrite_range - start writeback on mapping dirty pages in range + * @mapping: address space structure to write + * @start: offset in bytes where the range starts + * @end: offset in bytes where the range ends (inclusive) + * @sync_mode: enable synchronous operation + * + * Start writeback against all of a mapping's dirty pages that lie + * within the byte offsets inclusive. + * + * If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as + * opposed to a regular memory cleansing writeback. The difference between + * these two operations is that if a dirty page/buffer is encountered, it must + * be waited upon, and not just skipped over. + * + * Return: %0 on success, negative error code otherwise. + */ +int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, + loff_t end, int sync_mode) +{ + int ret; + struct writeback_control wbc = { + .sync_mode = sync_mode, + .nr_to_write = LONG_MAX, + .range_start = start, + .range_end = end, + }; + + if (!mapping_can_writeback(mapping) || + !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) + return 0; + + wbc_attach_fdatawrite_inode(&wbc, mapping->host); + ret = do_writepages(mapping, &wbc); + wbc_detach_inode(&wbc); + return ret; +} + +static inline int __filemap_fdatawrite(struct address_space *mapping, + int sync_mode) +{ + return __filemap_fdatawrite_range(mapping, 0, LLONG_MAX, sync_mode); +} + +int filemap_fdatawrite(struct address_space *mapping) +{ + return __filemap_fdatawrite(mapping, WB_SYNC_ALL); +} +EXPORT_SYMBOL(filemap_fdatawrite); + +int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, + loff_t end) +{ + return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL); +} +EXPORT_SYMBOL(filemap_fdatawrite_range); + +/** + * filemap_flush - mostly a non-blocking flush + * @mapping: target address_space + * + * This is a mostly non-blocking flush. Not suitable for data-integrity + * purposes - I/O may not be started against all dirty pages. + * + * Return: %0 on success, negative error code otherwise. + */ +int filemap_flush(struct address_space *mapping) +{ + return __filemap_fdatawrite(mapping, WB_SYNC_NONE); +} +EXPORT_SYMBOL(filemap_flush); + +/** + * filemap_range_has_page - check if a page exists in range. + * @mapping: address space within which to check + * @start_byte: offset in bytes where the range starts + * @end_byte: offset in bytes where the range ends (inclusive) + * + * Find at least one page in the range supplied, usually used to check if + * direct writing in this range will trigger a writeback. + * + * Return: %true if at least one page exists in the specified range, + * %false otherwise. + */ +bool filemap_range_has_page(struct address_space *mapping, + loff_t start_byte, loff_t end_byte) +{ + struct page *page; + XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT); + pgoff_t max = end_byte >> PAGE_SHIFT; + + if (end_byte < start_byte) + return false; + + rcu_read_lock(); + for (;;) { + page = xas_find(&xas, max); + if (xas_retry(&xas, page)) + continue; + /* Shadow entries don't count */ + if (xa_is_value(page)) + continue; + /* + * We don't need to try to pin this page; we're about to + * release the RCU lock anyway. It is enough to know that + * there was a page here recently. + */ + break; + } + rcu_read_unlock(); + + return page != NULL; +} +EXPORT_SYMBOL(filemap_range_has_page); + +static void __filemap_fdatawait_range(struct address_space *mapping, + loff_t start_byte, loff_t end_byte) +{ + pgoff_t index = start_byte >> PAGE_SHIFT; + pgoff_t end = end_byte >> PAGE_SHIFT; + struct pagevec pvec; + int nr_pages; + + if (end_byte < start_byte) + return; + + pagevec_init(&pvec); + while (index <= end) { + unsigned i; + + nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, + end, PAGECACHE_TAG_WRITEBACK); + if (!nr_pages) + break; + + for (i = 0; i < nr_pages; i++) { + struct page *page = pvec.pages[i]; + + wait_on_page_writeback(page); + ClearPageError(page); + } + pagevec_release(&pvec); + cond_resched(); + } +} + +/** + * filemap_fdatawait_range - wait for writeback to complete + * @mapping: address space structure to wait for + * @start_byte: offset in bytes where the range starts + * @end_byte: offset in bytes where the range ends (inclusive) + * + * Walk the list of under-writeback pages of the given address space + * in the given range and wait for all of them. Check error status of + * the address space and return it. + * + * Since the error status of the address space is cleared by this function, + * callers are responsible for checking the return value and handling and/or + * reporting the error. + * + * Return: error status of the address space. + */ +int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, + loff_t end_byte) +{ + __filemap_fdatawait_range(mapping, start_byte, end_byte); + return filemap_check_errors(mapping); +} +EXPORT_SYMBOL(filemap_fdatawait_range); + +/** + * filemap_fdatawait_range_keep_errors - wait for writeback to complete + * @mapping: address space structure to wait for + * @start_byte: offset in bytes where the range starts + * @end_byte: offset in bytes where the range ends (inclusive) + * + * Walk the list of under-writeback pages of the given address space in the + * given range and wait for all of them. Unlike filemap_fdatawait_range(), + * this function does not clear error status of the address space. + * + * Use this function if callers don't handle errors themselves. Expected + * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2), + * fsfreeze(8) + */ +int filemap_fdatawait_range_keep_errors(struct address_space *mapping, + loff_t start_byte, loff_t end_byte) +{ + __filemap_fdatawait_range(mapping, start_byte, end_byte); + return filemap_check_and_keep_errors(mapping); +} +EXPORT_SYMBOL(filemap_fdatawait_range_keep_errors); + +/** + * file_fdatawait_range - wait for writeback to complete + * @file: file pointing to address space structure to wait for + * @start_byte: offset in bytes where the range starts + * @end_byte: offset in bytes where the range ends (inclusive) + * + * Walk the list of under-writeback pages of the address space that file + * refers to, in the given range and wait for all of them. Check error + * status of the address space vs. the file->f_wb_err cursor and return it. + * + * Since the error status of the file is advanced by this function, + * callers are responsible for checking the return value and handling and/or + * reporting the error. + * + * Return: error status of the address space vs. the file->f_wb_err cursor. + */ +int file_fdatawait_range(struct file *file, loff_t start_byte, loff_t end_byte) +{ + struct address_space *mapping = file->f_mapping; + + __filemap_fdatawait_range(mapping, start_byte, end_byte); + return file_check_and_advance_wb_err(file); +} +EXPORT_SYMBOL(file_fdatawait_range); + +/** + * filemap_fdatawait_keep_errors - wait for writeback without clearing errors + * @mapping: address space structure to wait for + * + * Walk the list of under-writeback pages of the given address space + * and wait for all of them. Unlike filemap_fdatawait(), this function + * does not clear error status of the address space. + * + * Use this function if callers don't handle errors themselves. Expected + * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2), + * fsfreeze(8) + * + * Return: error status of the address space. + */ +int filemap_fdatawait_keep_errors(struct address_space *mapping) +{ + __filemap_fdatawait_range(mapping, 0, LLONG_MAX); + return filemap_check_and_keep_errors(mapping); +} +EXPORT_SYMBOL(filemap_fdatawait_keep_errors); + +/* Returns true if writeback might be needed or already in progress. */ +static bool mapping_needs_writeback(struct address_space *mapping) +{ + if (dax_mapping(mapping)) + return mapping->nrexceptional; + + return mapping->nrpages; +} + +/** + * filemap_write_and_wait_range - write out & wait on a file range + * @mapping: the address_space for the pages + * @lstart: offset in bytes where the range starts + * @lend: offset in bytes where the range ends (inclusive) + * + * Write out and wait upon file offsets lstart->lend, inclusive. + * + * Note that @lend is inclusive (describes the last byte to be written) so + * that this function can be used to write to the very end-of-file (end = -1). + * + * Return: error status of the address space. + */ +int filemap_write_and_wait_range(struct address_space *mapping, + loff_t lstart, loff_t lend) +{ + int err = 0; + + if (mapping_needs_writeback(mapping)) { + err = __filemap_fdatawrite_range(mapping, lstart, lend, + WB_SYNC_ALL); + /* + * Even if the above returned error, the pages may be + * written partially (e.g. -ENOSPC), so we wait for it. + * But the -EIO is special case, it may indicate the worst + * thing (e.g. bug) happened, so we avoid waiting for it. + */ + if (err != -EIO) { + int err2 = filemap_fdatawait_range(mapping, + lstart, lend); + if (!err) + err = err2; + } else { + /* Clear any previously stored errors */ + filemap_check_errors(mapping); + } + } else { + err = filemap_check_errors(mapping); + } + return err; +} +EXPORT_SYMBOL(filemap_write_and_wait_range); + +void __filemap_set_wb_err(struct address_space *mapping, int err) +{ + errseq_t eseq = errseq_set(&mapping->wb_err, err); + + trace_filemap_set_wb_err(mapping, eseq); +} +EXPORT_SYMBOL(__filemap_set_wb_err); + +/** + * file_check_and_advance_wb_err - report wb error (if any) that was previously + * and advance wb_err to current one + * @file: struct file on which the error is being reported + * + * When userland calls fsync (or something like nfsd does the equivalent), we + * want to report any writeback errors that occurred since the last fsync (or + * since the file was opened if there haven't been any). + * + * Grab the wb_err from the mapping. If it matches what we have in the file, + * then just quickly return 0. The file is all caught up. + * + * If it doesn't match, then take the mapping value, set the "seen" flag in + * it and try to swap it into place. If it works, or another task beat us + * to it with the new value, then update the f_wb_err and return the error + * portion. The error at this point must be reported via proper channels + * (a'la fsync, or NFS COMMIT operation, etc.). + * + * While we handle mapping->wb_err with atomic operations, the f_wb_err + * value is protected by the f_lock since we must ensure that it reflects + * the latest value swapped in for this file descriptor. + * + * Return: %0 on success, negative error code otherwise. + */ +int file_check_and_advance_wb_err(struct file *file) +{ + int err = 0; + errseq_t old = READ_ONCE(file->f_wb_err); + struct address_space *mapping = file->f_mapping; + + /* Locklessly handle the common case where nothing has changed */ + if (errseq_check(&mapping->wb_err, old)) { + /* Something changed, must use slow path */ + spin_lock(&file->f_lock); + old = file->f_wb_err; + err = errseq_check_and_advance(&mapping->wb_err, + &file->f_wb_err); + trace_file_check_and_advance_wb_err(file, old); + spin_unlock(&file->f_lock); + } + + /* + * We're mostly using this function as a drop in replacement for + * filemap_check_errors. Clear AS_EIO/AS_ENOSPC to emulate the effect + * that the legacy code would have had on these flags. + */ + clear_bit(AS_EIO, &mapping->flags); + clear_bit(AS_ENOSPC, &mapping->flags); + return err; +} +EXPORT_SYMBOL(file_check_and_advance_wb_err); + +/** + * file_write_and_wait_range - write out & wait on a file range + * @file: file pointing to address_space with pages + * @lstart: offset in bytes where the range starts + * @lend: offset in bytes where the range ends (inclusive) + * + * Write out and wait upon file offsets lstart->lend, inclusive. + * + * Note that @lend is inclusive (describes the last byte to be written) so + * that this function can be used to write to the very end-of-file (end = -1). + * + * After writing out and waiting on the data, we check and advance the + * f_wb_err cursor to the latest value, and return any errors detected there. + * + * Return: %0 on success, negative error code otherwise. + */ +int file_write_and_wait_range(struct file *file, loff_t lstart, loff_t lend) +{ + int err = 0, err2; + struct address_space *mapping = file->f_mapping; + + if (mapping_needs_writeback(mapping)) { + err = __filemap_fdatawrite_range(mapping, lstart, lend, + WB_SYNC_ALL); + /* See comment of filemap_write_and_wait() */ + if (err != -EIO) + __filemap_fdatawait_range(mapping, lstart, lend); + } + err2 = file_check_and_advance_wb_err(file); + if (!err) + err = err2; + return err; +} +EXPORT_SYMBOL(file_write_and_wait_range); + +/** + * replace_page_cache_page - replace a pagecache page with a new one + * @old: page to be replaced + * @new: page to replace with + * @gfp_mask: allocation mode + * + * This function replaces a page in the pagecache with a new one. On + * success it acquires the pagecache reference for the new page and + * drops it for the old page. Both the old and new pages must be + * locked. This function does not add the new page to the LRU, the + * caller must do that. + * + * The remove + add is atomic. This function cannot fail. + * + * Return: %0 + */ +int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) +{ + struct address_space *mapping = old->mapping; + void (*freepage)(struct page *) = mapping->a_ops->freepage; + pgoff_t offset = old->index; + XA_STATE(xas, &mapping->i_pages, offset); + unsigned long flags; + + VM_BUG_ON_PAGE(!PageLocked(old), old); + VM_BUG_ON_PAGE(!PageLocked(new), new); + VM_BUG_ON_PAGE(new->mapping, new); + + get_page(new); + new->mapping = mapping; + new->index = offset; + + mem_cgroup_migrate(old, new); + + xas_lock_irqsave(&xas, flags); + xas_store(&xas, new); + + old->mapping = NULL; + /* hugetlb pages do not participate in page cache accounting. */ + if (!PageHuge(old)) + __dec_lruvec_page_state(old, NR_FILE_PAGES); + if (!PageHuge(new)) + __inc_lruvec_page_state(new, NR_FILE_PAGES); + if (PageSwapBacked(old)) + __dec_lruvec_page_state(old, NR_SHMEM); + if (PageSwapBacked(new)) + __inc_lruvec_page_state(new, NR_SHMEM); + xas_unlock_irqrestore(&xas, flags); + if (freepage) + freepage(old); + put_page(old); + + return 0; +} +EXPORT_SYMBOL_GPL(replace_page_cache_page); + +noinline int __add_to_page_cache_locked(struct page *page, + struct address_space *mapping, + pgoff_t offset, gfp_t gfp, + void **shadowp) +{ + XA_STATE(xas, &mapping->i_pages, offset); + int huge = PageHuge(page); + int error; + bool charged = false; + + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(PageSwapBacked(page), page); + mapping_set_update(&xas, mapping); + + get_page(page); + page->mapping = mapping; + page->index = offset; + + if (!huge) { + error = mem_cgroup_charge(page, current->mm, gfp); + if (error) + goto error; + charged = true; + } + + gfp &= GFP_RECLAIM_MASK; + + do { + unsigned int order = xa_get_order(xas.xa, xas.xa_index); + void *entry, *old = NULL; + + if (order > thp_order(page)) + xas_split_alloc(&xas, xa_load(xas.xa, xas.xa_index), + order, gfp); + xas_lock_irq(&xas); + xas_for_each_conflict(&xas, entry) { + old = entry; + if (!xa_is_value(entry)) { + xas_set_err(&xas, -EEXIST); + goto unlock; + } + } + + if (old) { + if (shadowp) + *shadowp = old; + /* entry may have been split before we acquired lock */ + order = xa_get_order(xas.xa, xas.xa_index); + if (order > thp_order(page)) { + xas_split(&xas, old, order); + xas_reset(&xas); + } + } + + xas_store(&xas, page); + if (xas_error(&xas)) + goto unlock; + + if (old) + mapping->nrexceptional--; + mapping->nrpages++; + + /* hugetlb pages do not participate in page cache accounting */ + if (!huge) + __inc_lruvec_page_state(page, NR_FILE_PAGES); +unlock: + xas_unlock_irq(&xas); + } while (xas_nomem(&xas, gfp)); + + if (xas_error(&xas)) { + error = xas_error(&xas); + if (charged) + mem_cgroup_uncharge(page); + goto error; + } + + trace_mm_filemap_add_to_page_cache(page); + return 0; +error: + page->mapping = NULL; + /* Leave page->index set: truncation relies upon it */ + put_page(page); + return error; +} +ALLOW_ERROR_INJECTION(__add_to_page_cache_locked, ERRNO); + +/** + * add_to_page_cache_locked - add a locked page to the pagecache + * @page: page to add + * @mapping: the page's address_space + * @offset: page index + * @gfp_mask: page allocation mode + * + * This function is used to add a page to the pagecache. It must be locked. + * This function does not add the page to the LRU. The caller must do that. + * + * Return: %0 on success, negative error code otherwise. + */ +int add_to_page_cache_locked(struct page *page, struct address_space *mapping, + pgoff_t offset, gfp_t gfp_mask) +{ + return __add_to_page_cache_locked(page, mapping, offset, + gfp_mask, NULL); +} +EXPORT_SYMBOL(add_to_page_cache_locked); + +int add_to_page_cache_lru(struct page *page, struct address_space *mapping, + pgoff_t offset, gfp_t gfp_mask) +{ + void *shadow = NULL; + int ret; + + __SetPageLocked(page); + ret = __add_to_page_cache_locked(page, mapping, offset, + gfp_mask, &shadow); + if (unlikely(ret)) + __ClearPageLocked(page); + else { + /* + * The page might have been evicted from cache only + * recently, in which case it should be activated like + * any other repeatedly accessed page. + * The exception is pages getting rewritten; evicting other + * data from the working set, only to cache data that will + * get overwritten with something else, is a waste of memory. + */ + WARN_ON_ONCE(PageActive(page)); + if (!(gfp_mask & __GFP_WRITE) && shadow) + workingset_refault(page, shadow); + lru_cache_add(page); + } + return ret; +} +EXPORT_SYMBOL_GPL(add_to_page_cache_lru); + +#ifdef CONFIG_NUMA +struct page *__page_cache_alloc(gfp_t gfp) +{ + int n; + struct page *page; + + if (cpuset_do_page_mem_spread()) { + unsigned int cpuset_mems_cookie; + do { + cpuset_mems_cookie = read_mems_allowed_begin(); + n = cpuset_mem_spread_node(); + page = __alloc_pages_node(n, gfp, 0); + } while (!page && read_mems_allowed_retry(cpuset_mems_cookie)); + + return page; + } + return alloc_pages(gfp, 0); +} +EXPORT_SYMBOL(__page_cache_alloc); +#endif + +/* + * In order to wait for pages to become available there must be + * waitqueues associated with pages. By using a hash table of + * waitqueues where the bucket discipline is to maintain all + * waiters on the same queue and wake all when any of the pages + * become available, and for the woken contexts to check to be + * sure the appropriate page became available, this saves space + * at a cost of "thundering herd" phenomena during rare hash + * collisions. + */ +#define PAGE_WAIT_TABLE_BITS 8 +#define PAGE_WAIT_TABLE_SIZE (1 << PAGE_WAIT_TABLE_BITS) +static wait_queue_head_t page_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned; + +static wait_queue_head_t *page_waitqueue(struct page *page) +{ + return &page_wait_table[hash_ptr(page, PAGE_WAIT_TABLE_BITS)]; +} + +void __init pagecache_init(void) +{ + int i; + + for (i = 0; i < PAGE_WAIT_TABLE_SIZE; i++) + init_waitqueue_head(&page_wait_table[i]); + + page_writeback_init(); +} + +/* + * The page wait code treats the "wait->flags" somewhat unusually, because + * we have multiple different kinds of waits, not just the usual "exclusive" + * one. + * + * We have: + * + * (a) no special bits set: + * + * We're just waiting for the bit to be released, and when a waker + * calls the wakeup function, we set WQ_FLAG_WOKEN and wake it up, + * and remove it from the wait queue. + * + * Simple and straightforward. + * + * (b) WQ_FLAG_EXCLUSIVE: + * + * The waiter is waiting to get the lock, and only one waiter should + * be woken up to avoid any thundering herd behavior. We'll set the + * WQ_FLAG_WOKEN bit, wake it up, and remove it from the wait queue. + * + * This is the traditional exclusive wait. + * + * (c) WQ_FLAG_EXCLUSIVE | WQ_FLAG_CUSTOM: + * + * The waiter is waiting to get the bit, and additionally wants the + * lock to be transferred to it for fair lock behavior. If the lock + * cannot be taken, we stop walking the wait queue without waking + * the waiter. + * + * This is the "fair lock handoff" case, and in addition to setting + * WQ_FLAG_WOKEN, we set WQ_FLAG_DONE to let the waiter easily see + * that it now has the lock. + */ +static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg) +{ + unsigned int flags; + struct wait_page_key *key = arg; + struct wait_page_queue *wait_page + = container_of(wait, struct wait_page_queue, wait); + + if (!wake_page_match(wait_page, key)) + return 0; + + /* + * If it's a lock handoff wait, we get the bit for it, and + * stop walking (and do not wake it up) if we can't. + */ + flags = wait->flags; + if (flags & WQ_FLAG_EXCLUSIVE) { + if (test_bit(key->bit_nr, &key->page->flags)) + return -1; + if (flags & WQ_FLAG_CUSTOM) { + if (test_and_set_bit(key->bit_nr, &key->page->flags)) + return -1; + flags |= WQ_FLAG_DONE; + } + } + + /* + * We are holding the wait-queue lock, but the waiter that + * is waiting for this will be checking the flags without + * any locking. + * + * So update the flags atomically, and wake up the waiter + * afterwards to avoid any races. This store-release pairs + * with the load-acquire in wait_on_page_bit_common(). + */ + smp_store_release(&wait->flags, flags | WQ_FLAG_WOKEN); + wake_up_state(wait->private, mode); + + /* + * Ok, we have successfully done what we're waiting for, + * and we can unconditionally remove the wait entry. + * + * Note that this pairs with the "finish_wait()" in the + * waiter, and has to be the absolute last thing we do. + * After this list_del_init(&wait->entry) the wait entry + * might be de-allocated and the process might even have + * exited. + */ + list_del_init_careful(&wait->entry); + return (flags & WQ_FLAG_EXCLUSIVE) != 0; +} + +static void wake_up_page_bit(struct page *page, int bit_nr) +{ + wait_queue_head_t *q = page_waitqueue(page); + struct wait_page_key key; + unsigned long flags; + wait_queue_entry_t bookmark; + + key.page = page; + key.bit_nr = bit_nr; + key.page_match = 0; + + bookmark.flags = 0; + bookmark.private = NULL; + bookmark.func = NULL; + INIT_LIST_HEAD(&bookmark.entry); + + spin_lock_irqsave(&q->lock, flags); + __wake_up_locked_key_bookmark(q, TASK_NORMAL, &key, &bookmark); + + while (bookmark.flags & WQ_FLAG_BOOKMARK) { + /* + * Take a breather from holding the lock, + * allow pages that finish wake up asynchronously + * to acquire the lock and remove themselves + * from wait queue + */ + spin_unlock_irqrestore(&q->lock, flags); + cpu_relax(); + spin_lock_irqsave(&q->lock, flags); + __wake_up_locked_key_bookmark(q, TASK_NORMAL, &key, &bookmark); + } + + /* + * It is possible for other pages to have collided on the waitqueue + * hash, so in that case check for a page match. That prevents a long- + * term waiter + * + * It is still possible to miss a case here, when we woke page waiters + * and removed them from the waitqueue, but there are still other + * page waiters. + */ + if (!waitqueue_active(q) || !key.page_match) { + ClearPageWaiters(page); + /* + * It's possible to miss clearing Waiters here, when we woke + * our page waiters, but the hashed waitqueue has waiters for + * other pages on it. + * + * That's okay, it's a rare case. The next waker will clear it. + */ + } + spin_unlock_irqrestore(&q->lock, flags); +} + +static void wake_up_page(struct page *page, int bit) +{ + if (!PageWaiters(page)) + return; + wake_up_page_bit(page, bit); +} + +/* + * A choice of three behaviors for wait_on_page_bit_common(): + */ +enum behavior { + EXCLUSIVE, /* Hold ref to page and take the bit when woken, like + * __lock_page() waiting on then setting PG_locked. + */ + SHARED, /* Hold ref to page and check the bit when woken, like + * wait_on_page_writeback() waiting on PG_writeback. + */ + DROP, /* Drop ref to page before wait, no check when woken, + * like put_and_wait_on_page_locked() on PG_locked. + */ +}; + +/* + * Attempt to check (or get) the page bit, and mark us done + * if successful. + */ +static inline bool trylock_page_bit_common(struct page *page, int bit_nr, + struct wait_queue_entry *wait) +{ + if (wait->flags & WQ_FLAG_EXCLUSIVE) { + if (test_and_set_bit(bit_nr, &page->flags)) + return false; + } else if (test_bit(bit_nr, &page->flags)) + return false; + + wait->flags |= WQ_FLAG_WOKEN | WQ_FLAG_DONE; + return true; +} + +/* How many times do we accept lock stealing from under a waiter? */ +int sysctl_page_lock_unfairness = 5; + +static inline int wait_on_page_bit_common(wait_queue_head_t *q, + struct page *page, int bit_nr, int state, enum behavior behavior) +{ + int unfairness = sysctl_page_lock_unfairness; + struct wait_page_queue wait_page; + wait_queue_entry_t *wait = &wait_page.wait; + bool thrashing = false; + bool delayacct = false; + unsigned long pflags; + + if (bit_nr == PG_locked && + !PageUptodate(page) && PageWorkingset(page)) { + if (!PageSwapBacked(page)) { + delayacct_thrashing_start(); + delayacct = true; + } + psi_memstall_enter(&pflags); + thrashing = true; + } + + init_wait(wait); + wait->func = wake_page_function; + wait_page.page = page; + wait_page.bit_nr = bit_nr; + +repeat: + wait->flags = 0; + if (behavior == EXCLUSIVE) { + wait->flags = WQ_FLAG_EXCLUSIVE; + if (--unfairness < 0) + wait->flags |= WQ_FLAG_CUSTOM; + } + + /* + * Do one last check whether we can get the + * page bit synchronously. + * + * Do the SetPageWaiters() marking before that + * to let any waker we _just_ missed know they + * need to wake us up (otherwise they'll never + * even go to the slow case that looks at the + * page queue), and add ourselves to the wait + * queue if we need to sleep. + * + * This part needs to be done under the queue + * lock to avoid races. + */ + spin_lock_irq(&q->lock); + SetPageWaiters(page); + if (!trylock_page_bit_common(page, bit_nr, wait)) + __add_wait_queue_entry_tail(q, wait); + spin_unlock_irq(&q->lock); + + /* + * From now on, all the logic will be based on + * the WQ_FLAG_WOKEN and WQ_FLAG_DONE flag, to + * see whether the page bit testing has already + * been done by the wake function. + * + * We can drop our reference to the page. + */ + if (behavior == DROP) + put_page(page); + + /* + * Note that until the "finish_wait()", or until + * we see the WQ_FLAG_WOKEN flag, we need to + * be very careful with the 'wait->flags', because + * we may race with a waker that sets them. + */ + for (;;) { + unsigned int flags; + + set_current_state(state); + + /* Loop until we've been woken or interrupted */ + flags = smp_load_acquire(&wait->flags); + if (!(flags & WQ_FLAG_WOKEN)) { + if (signal_pending_state(state, current)) + break; + + io_schedule(); + continue; + } + + /* If we were non-exclusive, we're done */ + if (behavior != EXCLUSIVE) + break; + + /* If the waker got the lock for us, we're done */ + if (flags & WQ_FLAG_DONE) + break; + + /* + * Otherwise, if we're getting the lock, we need to + * try to get it ourselves. + * + * And if that fails, we'll have to retry this all. + */ + if (unlikely(test_and_set_bit(bit_nr, &page->flags))) + goto repeat; + + wait->flags |= WQ_FLAG_DONE; + break; + } + + /* + * If a signal happened, this 'finish_wait()' may remove the last + * waiter from the wait-queues, but the PageWaiters bit will remain + * set. That's ok. The next wakeup will take care of it, and trying + * to do it here would be difficult and prone to races. + */ + finish_wait(q, wait); + + if (thrashing) { + if (delayacct) + delayacct_thrashing_end(); + psi_memstall_leave(&pflags); + } + + /* + * NOTE! The wait->flags weren't stable until we've done the + * 'finish_wait()', and we could have exited the loop above due + * to a signal, and had a wakeup event happen after the signal + * test but before the 'finish_wait()'. + * + * So only after the finish_wait() can we reliably determine + * if we got woken up or not, so we can now figure out the final + * return value based on that state without races. + * + * Also note that WQ_FLAG_WOKEN is sufficient for a non-exclusive + * waiter, but an exclusive one requires WQ_FLAG_DONE. + */ + if (behavior == EXCLUSIVE) + return wait->flags & WQ_FLAG_DONE ? 0 : -EINTR; + + return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR; +} + +void wait_on_page_bit(struct page *page, int bit_nr) +{ + wait_queue_head_t *q = page_waitqueue(page); + wait_on_page_bit_common(q, page, bit_nr, TASK_UNINTERRUPTIBLE, SHARED); +} +EXPORT_SYMBOL(wait_on_page_bit); + +int wait_on_page_bit_killable(struct page *page, int bit_nr) +{ + wait_queue_head_t *q = page_waitqueue(page); + return wait_on_page_bit_common(q, page, bit_nr, TASK_KILLABLE, SHARED); +} +EXPORT_SYMBOL(wait_on_page_bit_killable); + +static int __wait_on_page_locked_async(struct page *page, + struct wait_page_queue *wait, bool set) +{ + struct wait_queue_head *q = page_waitqueue(page); + int ret = 0; + + wait->page = page; + wait->bit_nr = PG_locked; + + spin_lock_irq(&q->lock); + __add_wait_queue_entry_tail(q, &wait->wait); + SetPageWaiters(page); + if (set) + ret = !trylock_page(page); + else + ret = PageLocked(page); + /* + * If we were succesful now, we know we're still on the + * waitqueue as we're still under the lock. This means it's + * safe to remove and return success, we know the callback + * isn't going to trigger. + */ + if (!ret) + __remove_wait_queue(q, &wait->wait); + else + ret = -EIOCBQUEUED; + spin_unlock_irq(&q->lock); + return ret; +} + +static int wait_on_page_locked_async(struct page *page, + struct wait_page_queue *wait) +{ + if (!PageLocked(page)) + return 0; + return __wait_on_page_locked_async(compound_head(page), wait, false); +} + +/** + * put_and_wait_on_page_locked - Drop a reference and wait for it to be unlocked + * @page: The page to wait for. + * + * The caller should hold a reference on @page. They expect the page to + * become unlocked relatively soon, but do not wish to hold up migration + * (for example) by holding the reference while waiting for the page to + * come unlocked. After this function returns, the caller should not + * dereference @page. + */ +void put_and_wait_on_page_locked(struct page *page) +{ + wait_queue_head_t *q; + + page = compound_head(page); + q = page_waitqueue(page); + wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, DROP); +} + +/** + * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue + * @page: Page defining the wait queue of interest + * @waiter: Waiter to add to the queue + * + * Add an arbitrary @waiter to the wait queue for the nominated @page. + */ +void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter) +{ + wait_queue_head_t *q = page_waitqueue(page); + unsigned long flags; + + spin_lock_irqsave(&q->lock, flags); + __add_wait_queue_entry_tail(q, waiter); + SetPageWaiters(page); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL_GPL(add_page_wait_queue); + +#ifndef clear_bit_unlock_is_negative_byte + +/* + * PG_waiters is the high bit in the same byte as PG_lock. + * + * On x86 (and on many other architectures), we can clear PG_lock and + * test the sign bit at the same time. But if the architecture does + * not support that special operation, we just do this all by hand + * instead. + * + * The read of PG_waiters has to be after (or concurrently with) PG_locked + * being cleared, but a memory barrier should be unnecessary since it is + * in the same byte as PG_locked. + */ +static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile void *mem) +{ + clear_bit_unlock(nr, mem); + /* smp_mb__after_atomic(); */ + return test_bit(PG_waiters, mem); +} + +#endif + +/** + * unlock_page - unlock a locked page + * @page: the page + * + * Unlocks the page and wakes up sleepers in wait_on_page_locked(). + * Also wakes sleepers in wait_on_page_writeback() because the wakeup + * mechanism between PageLocked pages and PageWriteback pages is shared. + * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep. + * + * Note that this depends on PG_waiters being the sign bit in the byte + * that contains PG_locked - thus the BUILD_BUG_ON(). That allows us to + * clear the PG_locked bit and test PG_waiters at the same time fairly + * portably (architectures that do LL/SC can test any bit, while x86 can + * test the sign bit). + */ +void unlock_page(struct page *page) +{ + BUILD_BUG_ON(PG_waiters != 7); + page = compound_head(page); + VM_BUG_ON_PAGE(!PageLocked(page), page); + if (clear_bit_unlock_is_negative_byte(PG_locked, &page->flags)) + wake_up_page_bit(page, PG_locked); +} +EXPORT_SYMBOL(unlock_page); + +/** + * end_page_writeback - end writeback against a page + * @page: the page + */ +void end_page_writeback(struct page *page) +{ + /* + * TestClearPageReclaim could be used here but it is an atomic + * operation and overkill in this particular case. Failing to + * shuffle a page marked for immediate reclaim is too mild to + * justify taking an atomic operation penalty at the end of + * ever page writeback. + */ + if (PageReclaim(page)) { + ClearPageReclaim(page); + rotate_reclaimable_page(page); + } + + /* + * Writeback does not hold a page reference of its own, relying + * on truncation to wait for the clearing of PG_writeback. + * But here we must make sure that the page is not freed and + * reused before the wake_up_page(). + */ + get_page(page); + if (!test_clear_page_writeback(page)) + BUG(); + + smp_mb__after_atomic(); + wake_up_page(page, PG_writeback); + put_page(page); +} +EXPORT_SYMBOL(end_page_writeback); + +/* + * After completing I/O on a page, call this routine to update the page + * flags appropriately + */ +void page_endio(struct page *page, bool is_write, int err) +{ + if (!is_write) { + if (!err) { + SetPageUptodate(page); + } else { + ClearPageUptodate(page); + SetPageError(page); + } + unlock_page(page); + } else { + if (err) { + struct address_space *mapping; + + SetPageError(page); + mapping = page_mapping(page); + if (mapping) + mapping_set_error(mapping, err); + } + end_page_writeback(page); + } +} +EXPORT_SYMBOL_GPL(page_endio); + +/** + * __lock_page - get a lock on the page, assuming we need to sleep to get it + * @__page: the page to lock + */ +void __lock_page(struct page *__page) +{ + struct page *page = compound_head(__page); + wait_queue_head_t *q = page_waitqueue(page); + wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, + EXCLUSIVE); +} +EXPORT_SYMBOL(__lock_page); + +int __lock_page_killable(struct page *__page) +{ + struct page *page = compound_head(__page); + wait_queue_head_t *q = page_waitqueue(page); + return wait_on_page_bit_common(q, page, PG_locked, TASK_KILLABLE, + EXCLUSIVE); +} +EXPORT_SYMBOL_GPL(__lock_page_killable); + +int __lock_page_async(struct page *page, struct wait_page_queue *wait) +{ + return __wait_on_page_locked_async(page, wait, true); +} + +/* + * Return values: + * 1 - page is locked; mmap_lock is still held. + * 0 - page is not locked. + * mmap_lock has been released (mmap_read_unlock(), unless flags had both + * FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_RETRY_NOWAIT set, in + * which case mmap_lock is still held. + * + * If neither ALLOW_RETRY nor KILLABLE are set, will always return 1 + * with the page locked and the mmap_lock unperturbed. + */ +int __lock_page_or_retry(struct page *page, struct mm_struct *mm, + unsigned int flags) +{ + if (fault_flag_allow_retry_first(flags)) { + /* + * CAUTION! In this case, mmap_lock is not released + * even though return 0. + */ + if (flags & FAULT_FLAG_RETRY_NOWAIT) + return 0; + + mmap_read_unlock(mm); + if (flags & FAULT_FLAG_KILLABLE) + wait_on_page_locked_killable(page); + else + wait_on_page_locked(page); + return 0; + } else { + if (flags & FAULT_FLAG_KILLABLE) { + int ret; + + ret = __lock_page_killable(page); + if (ret) { + mmap_read_unlock(mm); + return 0; + } + } else + __lock_page(page); + return 1; + } +} + +/** + * page_cache_next_miss() - Find the next gap in the page cache. + * @mapping: Mapping. + * @index: Index. + * @max_scan: Maximum range to search. + * + * Search the range [index, min(index + max_scan - 1, ULONG_MAX)] for the + * gap with the lowest index. + * + * This function may be called under the rcu_read_lock. However, this will + * not atomically search a snapshot of the cache at a single point in time. + * For example, if a gap is created at index 5, then subsequently a gap is + * created at index 10, page_cache_next_miss covering both indices may + * return 10 if called under the rcu_read_lock. + * + * Return: The index of the gap if found, otherwise an index outside the + * range specified (in which case 'return - index >= max_scan' will be true). + * In the rare case of index wrap-around, 0 will be returned. + */ +pgoff_t page_cache_next_miss(struct address_space *mapping, + pgoff_t index, unsigned long max_scan) +{ + XA_STATE(xas, &mapping->i_pages, index); + + while (max_scan--) { + void *entry = xas_next(&xas); + if (!entry || xa_is_value(entry)) + break; + if (xas.xa_index == 0) + break; + } + + return xas.xa_index; +} +EXPORT_SYMBOL(page_cache_next_miss); + +/** + * page_cache_prev_miss() - Find the previous gap in the page cache. + * @mapping: Mapping. + * @index: Index. + * @max_scan: Maximum range to search. + * + * Search the range [max(index - max_scan + 1, 0), index] for the + * gap with the highest index. + * + * This function may be called under the rcu_read_lock. However, this will + * not atomically search a snapshot of the cache at a single point in time. + * For example, if a gap is created at index 10, then subsequently a gap is + * created at index 5, page_cache_prev_miss() covering both indices may + * return 5 if called under the rcu_read_lock. + * + * Return: The index of the gap if found, otherwise an index outside the + * range specified (in which case 'index - return >= max_scan' will be true). + * In the rare case of wrap-around, ULONG_MAX will be returned. + */ +pgoff_t page_cache_prev_miss(struct address_space *mapping, + pgoff_t index, unsigned long max_scan) +{ + XA_STATE(xas, &mapping->i_pages, index); + + while (max_scan--) { + void *entry = xas_prev(&xas); + if (!entry || xa_is_value(entry)) + break; + if (xas.xa_index == ULONG_MAX) + break; + } + + return xas.xa_index; +} +EXPORT_SYMBOL(page_cache_prev_miss); + +/** + * find_get_entry - find and get a page cache entry + * @mapping: the address_space to search + * @index: The page cache index. + * + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, the head page is returned with an increased refcount. + * + * If the slot holds a shadow entry of a previously evicted page, or a + * swap entry from shmem/tmpfs, it is returned. + * + * Return: The head page or shadow entry, %NULL if nothing is found. + */ +struct page *find_get_entry(struct address_space *mapping, pgoff_t index) +{ + XA_STATE(xas, &mapping->i_pages, index); + struct page *page; + + rcu_read_lock(); +repeat: + xas_reset(&xas); + page = xas_load(&xas); + if (xas_retry(&xas, page)) + goto repeat; + /* + * A shadow entry of a recently evicted page, or a swap entry from + * shmem/tmpfs. Return it without attempting to raise page count. + */ + if (!page || xa_is_value(page)) + goto out; + + if (!page_cache_get_speculative(page)) + goto repeat; + + /* + * Has the page moved or been split? + * This is part of the lockless pagecache protocol. See + * include/linux/pagemap.h for details. + */ + if (unlikely(page != xas_reload(&xas))) { + put_page(page); + goto repeat; + } +out: + rcu_read_unlock(); + + return page; +} + +/** + * find_lock_entry - Locate and lock a page cache entry. + * @mapping: The address_space to search. + * @index: The page cache index. + * + * Looks up the page at @mapping & @index. If there is a page in the + * cache, the head page is returned locked and with an increased refcount. + * + * If the slot holds a shadow entry of a previously evicted page, or a + * swap entry from shmem/tmpfs, it is returned. + * + * Context: May sleep. + * Return: The head page or shadow entry, %NULL if nothing is found. + */ +struct page *find_lock_entry(struct address_space *mapping, pgoff_t index) +{ + struct page *page; + +repeat: + page = find_get_entry(mapping, index); + if (page && !xa_is_value(page)) { + lock_page(page); + /* Has the page been truncated? */ + if (unlikely(page->mapping != mapping)) { + unlock_page(page); + put_page(page); + goto repeat; + } + VM_BUG_ON_PAGE(!thp_contains(page, index), page); + } + return page; +} + +/** + * pagecache_get_page - Find and get a reference to a page. + * @mapping: The address_space to search. + * @index: The page index. + * @fgp_flags: %FGP flags modify how the page is returned. + * @gfp_mask: Memory allocation flags to use if %FGP_CREAT is specified. + * + * Looks up the page cache entry at @mapping & @index. + * + * @fgp_flags can be zero or more of these flags: + * + * * %FGP_ACCESSED - The page will be marked accessed. + * * %FGP_LOCK - The page is returned locked. + * * %FGP_HEAD - If the page is present and a THP, return the head page + * rather than the exact page specified by the index. + * * %FGP_CREAT - If no page is present then a new page is allocated using + * @gfp_mask and added to the page cache and the VM's LRU list. + * The page is returned locked and with an increased refcount. + * * %FGP_FOR_MMAP - The caller wants to do its own locking dance if the + * page is already in cache. If the page was allocated, unlock it before + * returning so the caller can do the same dance. + * * %FGP_WRITE - The page will be written + * * %FGP_NOFS - __GFP_FS will get cleared in gfp mask + * * %FGP_NOWAIT - Don't get blocked by page lock + * + * If %FGP_LOCK or %FGP_CREAT are specified then the function may sleep even + * if the %GFP flags specified for %FGP_CREAT are atomic. + * + * If there is a page cache page, it is returned with an increased refcount. + * + * Return: The found page or %NULL otherwise. + */ +struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, + int fgp_flags, gfp_t gfp_mask) +{ + struct page *page; + +repeat: + page = find_get_entry(mapping, index); + if (xa_is_value(page)) + page = NULL; + if (!page) + goto no_page; + + if (fgp_flags & FGP_LOCK) { + if (fgp_flags & FGP_NOWAIT) { + if (!trylock_page(page)) { + put_page(page); + return NULL; + } + } else { + lock_page(page); + } + + /* Has the page been truncated? */ + if (unlikely(page->mapping != mapping)) { + unlock_page(page); + put_page(page); + goto repeat; + } + VM_BUG_ON_PAGE(!thp_contains(page, index), page); + } + + if (fgp_flags & FGP_ACCESSED) + mark_page_accessed(page); + else if (fgp_flags & FGP_WRITE) { + /* Clear idle flag for buffer write */ + if (page_is_idle(page)) + clear_page_idle(page); + } + if (!(fgp_flags & FGP_HEAD)) + page = find_subpage(page, index); + +no_page: + if (!page && (fgp_flags & FGP_CREAT)) { + int err; + if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping)) + gfp_mask |= __GFP_WRITE; + if (fgp_flags & FGP_NOFS) + gfp_mask &= ~__GFP_FS; + + page = __page_cache_alloc(gfp_mask); + if (!page) + return NULL; + + if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP)))) + fgp_flags |= FGP_LOCK; + + /* Init accessed so avoid atomic mark_page_accessed later */ + if (fgp_flags & FGP_ACCESSED) + __SetPageReferenced(page); + + err = add_to_page_cache_lru(page, mapping, index, gfp_mask); + if (unlikely(err)) { + put_page(page); + page = NULL; + if (err == -EEXIST) + goto repeat; + } + + /* + * add_to_page_cache_lru locks the page, and for mmap we expect + * an unlocked page. + */ + if (page && (fgp_flags & FGP_FOR_MMAP)) + unlock_page(page); + } + + return page; +} +EXPORT_SYMBOL(pagecache_get_page); + +/** + * find_get_entries - gang pagecache lookup + * @mapping: The address_space to search + * @start: The starting page cache index + * @nr_entries: The maximum number of entries + * @entries: Where the resulting entries are placed + * @indices: The cache indices corresponding to the entries in @entries + * + * find_get_entries() will search for and return a group of up to + * @nr_entries entries in the mapping. The entries are placed at + * @entries. find_get_entries() takes a reference against any actual + * pages it returns. + * + * The search returns a group of mapping-contiguous page cache entries + * with ascending indexes. There may be holes in the indices due to + * not-present pages. + * + * Any shadow entries of evicted pages, or swap entries from + * shmem/tmpfs, are included in the returned array. + * + * If it finds a Transparent Huge Page, head or tail, find_get_entries() + * stops at that page: the caller is likely to have a better way to handle + * the compound page as a whole, and then skip its extent, than repeatedly + * calling find_get_entries() to return all its tails. + * + * Return: the number of pages and shadow entries which were found. + */ +unsigned find_get_entries(struct address_space *mapping, + pgoff_t start, unsigned int nr_entries, + struct page **entries, pgoff_t *indices) +{ + XA_STATE(xas, &mapping->i_pages, start); + struct page *page; + unsigned int ret = 0; + + if (!nr_entries) + return 0; + + rcu_read_lock(); + xas_for_each(&xas, page, ULONG_MAX) { + if (xas_retry(&xas, page)) + continue; + /* + * A shadow entry of a recently evicted page, a swap + * entry from shmem/tmpfs or a DAX entry. Return it + * without attempting to raise page count. + */ + if (xa_is_value(page)) + goto export; + + if (!page_cache_get_speculative(page)) + goto retry; + + /* Has the page moved or been split? */ + if (unlikely(page != xas_reload(&xas))) + goto put_page; + + /* + * Terminate early on finding a THP, to allow the caller to + * handle it all at once; but continue if this is hugetlbfs. + */ + if (PageTransHuge(page) && !PageHuge(page)) { + page = find_subpage(page, xas.xa_index); + nr_entries = ret + 1; + } +export: + indices[ret] = xas.xa_index; + entries[ret] = page; + if (++ret == nr_entries) + break; + continue; +put_page: + put_page(page); +retry: + xas_reset(&xas); + } + rcu_read_unlock(); + return ret; +} + +/** + * find_get_pages_range - gang pagecache lookup + * @mapping: The address_space to search + * @start: The starting page index + * @end: The final page index (inclusive) + * @nr_pages: The maximum number of pages + * @pages: Where the resulting pages are placed + * + * find_get_pages_range() will search for and return a group of up to @nr_pages + * pages in the mapping starting at index @start and up to index @end + * (inclusive). The pages are placed at @pages. find_get_pages_range() takes + * a reference against the returned pages. + * + * The search returns a group of mapping-contiguous pages with ascending + * indexes. There may be holes in the indices due to not-present pages. + * We also update @start to index the next page for the traversal. + * + * Return: the number of pages which were found. If this number is + * smaller than @nr_pages, the end of specified range has been + * reached. + */ +unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start, + pgoff_t end, unsigned int nr_pages, + struct page **pages) +{ + XA_STATE(xas, &mapping->i_pages, *start); + struct page *page; + unsigned ret = 0; + + if (unlikely(!nr_pages)) + return 0; + + rcu_read_lock(); + xas_for_each(&xas, page, end) { + if (xas_retry(&xas, page)) + continue; + /* Skip over shadow, swap and DAX entries */ + if (xa_is_value(page)) + continue; + + if (!page_cache_get_speculative(page)) + goto retry; + + /* Has the page moved or been split? */ + if (unlikely(page != xas_reload(&xas))) + goto put_page; + + pages[ret] = find_subpage(page, xas.xa_index); + if (++ret == nr_pages) { + *start = xas.xa_index + 1; + goto out; + } + continue; +put_page: + put_page(page); +retry: + xas_reset(&xas); + } + + /* + * We come here when there is no page beyond @end. We take care to not + * overflow the index @start as it confuses some of the callers. This + * breaks the iteration when there is a page at index -1 but that is + * already broken anyway. + */ + if (end == (pgoff_t)-1) + *start = (pgoff_t)-1; + else + *start = end + 1; +out: + rcu_read_unlock(); + + return ret; +} + +/** + * find_get_pages_contig - gang contiguous pagecache lookup + * @mapping: The address_space to search + * @index: The starting page index + * @nr_pages: The maximum number of pages + * @pages: Where the resulting pages are placed + * + * find_get_pages_contig() works exactly like find_get_pages(), except + * that the returned number of pages are guaranteed to be contiguous. + * + * Return: the number of pages which were found. + */ +unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index, + unsigned int nr_pages, struct page **pages) +{ + XA_STATE(xas, &mapping->i_pages, index); + struct page *page; + unsigned int ret = 0; + + if (unlikely(!nr_pages)) + return 0; + + rcu_read_lock(); + for (page = xas_load(&xas); page; page = xas_next(&xas)) { + if (xas_retry(&xas, page)) + continue; + /* + * If the entry has been swapped out, we can stop looking. + * No current caller is looking for DAX entries. + */ + if (xa_is_value(page)) + break; + + if (!page_cache_get_speculative(page)) + goto retry; + + /* Has the page moved or been split? */ + if (unlikely(page != xas_reload(&xas))) + goto put_page; + + pages[ret] = find_subpage(page, xas.xa_index); + if (++ret == nr_pages) + break; + continue; +put_page: + put_page(page); +retry: + xas_reset(&xas); + } + rcu_read_unlock(); + return ret; +} +EXPORT_SYMBOL(find_get_pages_contig); + +/** + * find_get_pages_range_tag - find and return pages in given range matching @tag + * @mapping: the address_space to search + * @index: the starting page index + * @end: The final page index (inclusive) + * @tag: the tag index + * @nr_pages: the maximum number of pages + * @pages: where the resulting pages are placed + * + * Like find_get_pages, except we only return pages which are tagged with + * @tag. We update @index to index the next page for the traversal. + * + * Return: the number of pages which were found. + */ +unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, + pgoff_t end, xa_mark_t tag, unsigned int nr_pages, + struct page **pages) +{ + XA_STATE(xas, &mapping->i_pages, *index); + struct page *page; + unsigned ret = 0; + + if (unlikely(!nr_pages)) + return 0; + + rcu_read_lock(); + xas_for_each_marked(&xas, page, end, tag) { + if (xas_retry(&xas, page)) + continue; + /* + * Shadow entries should never be tagged, but this iteration + * is lockless so there is a window for page reclaim to evict + * a page we saw tagged. Skip over it. + */ + if (xa_is_value(page)) + continue; + + if (!page_cache_get_speculative(page)) + goto retry; + + /* Has the page moved or been split? */ + if (unlikely(page != xas_reload(&xas))) + goto put_page; + + pages[ret] = find_subpage(page, xas.xa_index); + if (++ret == nr_pages) { + *index = xas.xa_index + 1; + goto out; + } + continue; +put_page: + put_page(page); +retry: + xas_reset(&xas); + } + + /* + * We come here when we got to @end. We take care to not overflow the + * index @index as it confuses some of the callers. This breaks the + * iteration when there is a page at index -1 but that is already + * broken anyway. + */ + if (end == (pgoff_t)-1) + *index = (pgoff_t)-1; + else + *index = end + 1; +out: + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL(find_get_pages_range_tag); + +/* + * CD/DVDs are error prone. When a medium error occurs, the driver may fail + * a _large_ part of the i/o request. Imagine the worst scenario: + * + * ---R__________________________________________B__________ + * ^ reading here ^ bad block(assume 4k) + * + * read(R) => miss => readahead(R...B) => media error => frustrating retries + * => failing the whole request => read(R) => read(R+1) => + * readahead(R+1...B+1) => bang => read(R+2) => read(R+3) => + * readahead(R+3...B+2) => bang => read(R+3) => read(R+4) => + * readahead(R+4...B+3) => bang => read(R+4) => read(R+5) => ...... + * + * It is going insane. Fix it by quickly scaling down the readahead size. + */ +static void shrink_readahead_size_eio(struct file_ra_state *ra) +{ + ra->ra_pages /= 4; +} + +/** + * generic_file_buffered_read - generic file read routine + * @iocb: the iocb to read + * @iter: data destination + * @written: already copied + * + * This is a generic file read routine, and uses the + * mapping->a_ops->readpage() function for the actual low-level stuff. + * + * This is really ugly. But the goto's actually try to clarify some + * of the logic when it comes to error handling etc. + * + * Return: + * * total number of bytes copied, including those the were already @written + * * negative error code if nothing was copied + */ +ssize_t generic_file_buffered_read(struct kiocb *iocb, + struct iov_iter *iter, ssize_t written) +{ + struct file *filp = iocb->ki_filp; + struct address_space *mapping = filp->f_mapping; + struct inode *inode = mapping->host; + struct file_ra_state *ra = &filp->f_ra; + loff_t *ppos = &iocb->ki_pos; + pgoff_t index; + pgoff_t last_index; + pgoff_t prev_index; + unsigned long offset; /* offset into pagecache page */ + unsigned int prev_offset; + int error = 0; + + if (unlikely(*ppos >= inode->i_sb->s_maxbytes)) + return 0; + if (unlikely(!iov_iter_count(iter))) + return 0; + + iov_iter_truncate(iter, inode->i_sb->s_maxbytes); + + index = *ppos >> PAGE_SHIFT; + prev_index = ra->prev_pos >> PAGE_SHIFT; + prev_offset = ra->prev_pos & (PAGE_SIZE-1); + last_index = (*ppos + iter->count + PAGE_SIZE-1) >> PAGE_SHIFT; + offset = *ppos & ~PAGE_MASK; + + /* + * If we've already successfully copied some data, then we + * can no longer safely return -EIOCBQUEUED. Hence mark + * an async read NOWAIT at that point. + */ + if (written && (iocb->ki_flags & IOCB_WAITQ)) + iocb->ki_flags |= IOCB_NOWAIT; + + for (;;) { + struct page *page; + pgoff_t end_index; + loff_t isize; + unsigned long nr, ret; + + cond_resched(); +find_page: + if (fatal_signal_pending(current)) { + error = -EINTR; + goto out; + } + + page = find_get_page(mapping, index); + if (!page) { + if (iocb->ki_flags & IOCB_NOIO) + goto would_block; + page_cache_sync_readahead(mapping, + ra, filp, + index, last_index - index); + page = find_get_page(mapping, index); + if (unlikely(page == NULL)) + goto no_cached_page; + } + if (PageReadahead(page)) { + if (iocb->ki_flags & IOCB_NOIO) { + put_page(page); + goto out; + } + page_cache_async_readahead(mapping, + ra, filp, page, + index, last_index - index); + } + if (!PageUptodate(page)) { + /* + * See comment in do_read_cache_page on why + * wait_on_page_locked is used to avoid unnecessarily + * serialisations and why it's safe. + */ + if (iocb->ki_flags & IOCB_WAITQ) { + if (written) { + put_page(page); + goto out; + } + error = wait_on_page_locked_async(page, + iocb->ki_waitq); + } else { + if (iocb->ki_flags & IOCB_NOWAIT) { + put_page(page); + goto would_block; + } + error = wait_on_page_locked_killable(page); + } + if (unlikely(error)) + goto readpage_error; + if (PageUptodate(page)) + goto page_ok; + + if (inode->i_blkbits == PAGE_SHIFT || + !mapping->a_ops->is_partially_uptodate) + goto page_not_up_to_date; + /* pipes can't handle partially uptodate pages */ + if (unlikely(iov_iter_is_pipe(iter))) + goto page_not_up_to_date; + if (!trylock_page(page)) + goto page_not_up_to_date; + /* Did it get truncated before we got the lock? */ + if (!page->mapping) + goto page_not_up_to_date_locked; + if (!mapping->a_ops->is_partially_uptodate(page, + offset, iter->count)) + goto page_not_up_to_date_locked; + unlock_page(page); + } +page_ok: + /* + * i_size must be checked after we know the page is Uptodate. + * + * Checking i_size after the check allows us to calculate + * the correct value for "nr", which means the zero-filled + * part of the page is not copied back to userspace (unless + * another truncate extends the file - this is desired though). + */ + + isize = i_size_read(inode); + end_index = (isize - 1) >> PAGE_SHIFT; + if (unlikely(!isize || index > end_index)) { + put_page(page); + goto out; + } + + /* nr is the maximum number of bytes to copy from this page */ + nr = PAGE_SIZE; + if (index == end_index) { + nr = ((isize - 1) & ~PAGE_MASK) + 1; + if (nr <= offset) { + put_page(page); + goto out; + } + } + nr = nr - offset; + + /* If users can be writing to this page using arbitrary + * virtual addresses, take care about potential aliasing + * before reading the page on the kernel side. + */ + if (mapping_writably_mapped(mapping)) + flush_dcache_page(page); + + /* + * When a sequential read accesses a page several times, + * only mark it as accessed the first time. + */ + if (prev_index != index || offset != prev_offset) + mark_page_accessed(page); + prev_index = index; + + /* + * Ok, we have the page, and it's up-to-date, so + * now we can copy it to user space... + */ + + ret = copy_page_to_iter(page, offset, nr, iter); + offset += ret; + index += offset >> PAGE_SHIFT; + offset &= ~PAGE_MASK; + prev_offset = offset; + + put_page(page); + written += ret; + if (!iov_iter_count(iter)) + goto out; + if (ret < nr) { + error = -EFAULT; + goto out; + } + continue; + +page_not_up_to_date: + /* Get exclusive access to the page ... */ + if (iocb->ki_flags & IOCB_WAITQ) { + if (written) { + put_page(page); + goto out; + } + error = lock_page_async(page, iocb->ki_waitq); + } else { + error = lock_page_killable(page); + } + if (unlikely(error)) + goto readpage_error; + +page_not_up_to_date_locked: + /* Did it get truncated before we got the lock? */ + if (!page->mapping) { + unlock_page(page); + put_page(page); + continue; + } + + /* Did somebody else fill it already? */ + if (PageUptodate(page)) { + unlock_page(page); + goto page_ok; + } + +readpage: + if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT)) { + unlock_page(page); + put_page(page); + goto would_block; + } + /* + * A previous I/O error may have been due to temporary + * failures, eg. multipath errors. + * PG_error will be set again if readpage fails. + */ + ClearPageError(page); + /* Start the actual read. The read will unlock the page. */ + error = mapping->a_ops->readpage(filp, page); + + if (unlikely(error)) { + if (error == AOP_TRUNCATED_PAGE) { + put_page(page); + error = 0; + goto find_page; + } + goto readpage_error; + } + + if (!PageUptodate(page)) { + if (iocb->ki_flags & IOCB_WAITQ) { + if (written) { + put_page(page); + goto out; + } + error = lock_page_async(page, iocb->ki_waitq); + } else { + error = lock_page_killable(page); + } + + if (unlikely(error)) + goto readpage_error; + if (!PageUptodate(page)) { + if (page->mapping == NULL) { + /* + * invalidate_mapping_pages got it + */ + unlock_page(page); + put_page(page); + goto find_page; + } + unlock_page(page); + shrink_readahead_size_eio(ra); + error = -EIO; + goto readpage_error; + } + unlock_page(page); + } + + goto page_ok; + +readpage_error: + /* UHHUH! A synchronous read error occurred. Report it */ + put_page(page); + goto out; + +no_cached_page: + /* + * Ok, it wasn't cached, so we need to create a new + * page.. + */ + page = page_cache_alloc(mapping); + if (!page) { + error = -ENOMEM; + goto out; + } + error = add_to_page_cache_lru(page, mapping, index, + mapping_gfp_constraint(mapping, GFP_KERNEL)); + if (error) { + put_page(page); + if (error == -EEXIST) { + error = 0; + goto find_page; + } + goto out; + } + goto readpage; + } + +would_block: + error = -EAGAIN; +out: + ra->prev_pos = prev_index; + ra->prev_pos <<= PAGE_SHIFT; + ra->prev_pos |= prev_offset; + + *ppos = ((loff_t)index << PAGE_SHIFT) + offset; + file_accessed(filp); + return written ? written : error; +} +EXPORT_SYMBOL_GPL(generic_file_buffered_read); + +/** + * generic_file_read_iter - generic filesystem read routine + * @iocb: kernel I/O control block + * @iter: destination for the data read + * + * This is the "read_iter()" routine for all filesystems + * that can use the page cache directly. + * + * The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall + * be returned when no data can be read without waiting for I/O requests + * to complete; it doesn't prevent readahead. + * + * The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O + * requests shall be made for the read or for readahead. When no data + * can be read, -EAGAIN shall be returned. When readahead would be + * triggered, a partial, possibly empty read shall be returned. + * + * Return: + * * number of bytes copied, even for partial reads + * * negative error code (or 0 if IOCB_NOIO) if nothing was read + */ +ssize_t +generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) +{ + size_t count = iov_iter_count(iter); + ssize_t retval = 0; + + if (!count) + goto out; /* skip atime */ + + if (iocb->ki_flags & IOCB_DIRECT) { + struct file *file = iocb->ki_filp; + struct address_space *mapping = file->f_mapping; + struct inode *inode = mapping->host; + loff_t size; + + size = i_size_read(inode); + if (iocb->ki_flags & IOCB_NOWAIT) { + if (filemap_range_has_page(mapping, iocb->ki_pos, + iocb->ki_pos + count - 1)) + return -EAGAIN; + } else { + retval = filemap_write_and_wait_range(mapping, + iocb->ki_pos, + iocb->ki_pos + count - 1); + if (retval < 0) + goto out; + } + + file_accessed(file); + + retval = mapping->a_ops->direct_IO(iocb, iter); + if (retval >= 0) { + iocb->ki_pos += retval; + count -= retval; + } + iov_iter_revert(iter, count - iov_iter_count(iter)); + + /* + * Btrfs can have a short DIO read if we encounter + * compressed extents, so if there was an error, or if + * we've already read everything we wanted to, or if + * there was a short read because we hit EOF, go ahead + * and return. Otherwise fallthrough to buffered io for + * the rest of the read. Buffered reads will not work for + * DAX files, so don't bother trying. + */ + if (retval < 0 || !count || iocb->ki_pos >= size || + IS_DAX(inode)) + goto out; + } + + retval = generic_file_buffered_read(iocb, iter, retval); +out: + return retval; +} +EXPORT_SYMBOL(generic_file_read_iter); + +#ifdef CONFIG_MMU +#define MMAP_LOTSAMISS (100) +/* + * lock_page_maybe_drop_mmap - lock the page, possibly dropping the mmap_lock + * @vmf - the vm_fault for this fault. + * @page - the page to lock. + * @fpin - the pointer to the file we may pin (or is already pinned). + * + * This works similar to lock_page_or_retry in that it can drop the mmap_lock. + * It differs in that it actually returns the page locked if it returns 1 and 0 + * if it couldn't lock the page. If we did have to drop the mmap_lock then fpin + * will point to the pinned file and needs to be fput()'ed at a later point. + */ +static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page, + struct file **fpin) +{ + if (trylock_page(page)) + return 1; + + /* + * NOTE! This will make us return with VM_FAULT_RETRY, but with + * the mmap_lock still held. That's how FAULT_FLAG_RETRY_NOWAIT + * is supposed to work. We have way too many special cases.. + */ + if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) + return 0; + + *fpin = maybe_unlock_mmap_for_io(vmf, *fpin); + if (vmf->flags & FAULT_FLAG_KILLABLE) { + if (__lock_page_killable(page)) { + /* + * We didn't have the right flags to drop the mmap_lock, + * but all fault_handlers only check for fatal signals + * if we return VM_FAULT_RETRY, so we need to drop the + * mmap_lock here and return 0 if we don't have a fpin. + */ + if (*fpin == NULL) + mmap_read_unlock(vmf->vma->vm_mm); + return 0; + } + } else + __lock_page(page); + return 1; +} + + +/* + * Synchronous readahead happens when we don't even find a page in the page + * cache at all. We don't want to perform IO under the mmap sem, so if we have + * to drop the mmap sem we return the file that was pinned in order for us to do + * that. If we didn't pin a file then we return NULL. The file that is + * returned needs to be fput()'ed when we're done with it. + */ +static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) +{ + struct file *file = vmf->vma->vm_file; + struct file_ra_state *ra = &file->f_ra; + struct address_space *mapping = file->f_mapping; + DEFINE_READAHEAD(ractl, file, mapping, vmf->pgoff); + struct file *fpin = NULL; + unsigned int mmap_miss; + + /* If we don't want any read-ahead, don't bother */ + if (vmf->vma->vm_flags & VM_RAND_READ) + return fpin; + if (!ra->ra_pages) + return fpin; + + if (vmf->vma->vm_flags & VM_SEQ_READ) { + fpin = maybe_unlock_mmap_for_io(vmf, fpin); + page_cache_sync_ra(&ractl, ra, ra->ra_pages); + return fpin; + } + + /* Avoid banging the cache line if not needed */ + mmap_miss = READ_ONCE(ra->mmap_miss); + if (mmap_miss < MMAP_LOTSAMISS * 10) + WRITE_ONCE(ra->mmap_miss, ++mmap_miss); + + /* + * Do we miss much more than hit in this file? If so, + * stop bothering with read-ahead. It will only hurt. + */ + if (mmap_miss > MMAP_LOTSAMISS) + return fpin; + + /* + * mmap read-around + */ + fpin = maybe_unlock_mmap_for_io(vmf, fpin); + ra->start = max_t(long, 0, vmf->pgoff - ra->ra_pages / 2); + ra->size = ra->ra_pages; + ra->async_size = ra->ra_pages / 4; + ractl._index = ra->start; + do_page_cache_ra(&ractl, ra->size, ra->async_size); + return fpin; +} + +/* + * Asynchronous readahead happens when we find the page and PG_readahead, + * so we want to possibly extend the readahead further. We return the file that + * was pinned if we have to drop the mmap_lock in order to do IO. + */ +static struct file *do_async_mmap_readahead(struct vm_fault *vmf, + struct page *page) +{ + struct file *file = vmf->vma->vm_file; + struct file_ra_state *ra = &file->f_ra; + struct address_space *mapping = file->f_mapping; + struct file *fpin = NULL; + unsigned int mmap_miss; + pgoff_t offset = vmf->pgoff; + + /* If we don't want any read-ahead, don't bother */ + if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages) + return fpin; + mmap_miss = READ_ONCE(ra->mmap_miss); + if (mmap_miss) + WRITE_ONCE(ra->mmap_miss, --mmap_miss); + if (PageReadahead(page)) { + fpin = maybe_unlock_mmap_for_io(vmf, fpin); + page_cache_async_readahead(mapping, ra, file, + page, offset, ra->ra_pages); + } + return fpin; +} + +/** + * filemap_fault - read in file data for page fault handling + * @vmf: struct vm_fault containing details of the fault + * + * filemap_fault() is invoked via the vma operations vector for a + * mapped memory region to read in file data during a page fault. + * + * The goto's are kind of ugly, but this streamlines the normal case of having + * it in the page cache, and handles the special cases reasonably without + * having a lot of duplicated code. + * + * vma->vm_mm->mmap_lock must be held on entry. + * + * If our return value has VM_FAULT_RETRY set, it's because the mmap_lock + * may be dropped before doing I/O or by lock_page_maybe_drop_mmap(). + * + * If our return value does not have VM_FAULT_RETRY set, the mmap_lock + * has not been released. + * + * We never return with VM_FAULT_RETRY and a bit from VM_FAULT_ERROR set. + * + * Return: bitwise-OR of %VM_FAULT_ codes. + */ +vm_fault_t filemap_fault(struct vm_fault *vmf) +{ + int error; + struct file *file = vmf->vma->vm_file; + struct file *fpin = NULL; + struct address_space *mapping = file->f_mapping; + struct file_ra_state *ra = &file->f_ra; + struct inode *inode = mapping->host; + pgoff_t offset = vmf->pgoff; + pgoff_t max_off; + struct page *page; + vm_fault_t ret = 0; + + max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + if (unlikely(offset >= max_off)) + return VM_FAULT_SIGBUS; + + /* + * Do we have something in the page cache already? + */ + page = find_get_page(mapping, offset); + if (likely(page) && !(vmf->flags & FAULT_FLAG_TRIED)) { + /* + * We found the page, so try async readahead before + * waiting for the lock. + */ + fpin = do_async_mmap_readahead(vmf, page); + } else if (!page) { + /* No page in the page cache at all */ + count_vm_event(PGMAJFAULT); + count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT); + ret = VM_FAULT_MAJOR; + fpin = do_sync_mmap_readahead(vmf); +retry_find: + page = pagecache_get_page(mapping, offset, + FGP_CREAT|FGP_FOR_MMAP, + vmf->gfp_mask); + if (!page) { + if (fpin) + goto out_retry; + return VM_FAULT_OOM; + } + } + + if (!lock_page_maybe_drop_mmap(vmf, page, &fpin)) + goto out_retry; + + /* Did it get truncated? */ + if (unlikely(compound_head(page)->mapping != mapping)) { + unlock_page(page); + put_page(page); + goto retry_find; + } + VM_BUG_ON_PAGE(page_to_pgoff(page) != offset, page); + + /* + * We have a locked page in the page cache, now we need to check + * that it's up-to-date. If not, it is going to be due to an error. + */ + if (unlikely(!PageUptodate(page))) + goto page_not_uptodate; + + /* + * We've made it this far and we had to drop our mmap_lock, now is the + * time to return to the upper layer and have it re-find the vma and + * redo the fault. + */ + if (fpin) { + unlock_page(page); + goto out_retry; + } + + /* + * Found the page and have a reference on it. + * We must recheck i_size under page lock. + */ + max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + if (unlikely(offset >= max_off)) { + unlock_page(page); + put_page(page); + return VM_FAULT_SIGBUS; + } + + vmf->page = page; + return ret | VM_FAULT_LOCKED; + +page_not_uptodate: + /* + * Umm, take care of errors if the page isn't up-to-date. + * Try to re-read it _once_. We do this synchronously, + * because there really aren't any performance issues here + * and we need to check for errors. + */ + ClearPageError(page); + fpin = maybe_unlock_mmap_for_io(vmf, fpin); + error = mapping->a_ops->readpage(file, page); + if (!error) { + wait_on_page_locked(page); + if (!PageUptodate(page)) + error = -EIO; + } + if (fpin) + goto out_retry; + put_page(page); + + if (!error || error == AOP_TRUNCATED_PAGE) + goto retry_find; + + shrink_readahead_size_eio(ra); + return VM_FAULT_SIGBUS; + +out_retry: + /* + * We dropped the mmap_lock, we need to return to the fault handler to + * re-find the vma and come back and find our hopefully still populated + * page. + */ + if (page) + put_page(page); + if (fpin) + fput(fpin); + return ret | VM_FAULT_RETRY; +} +EXPORT_SYMBOL(filemap_fault); + +void filemap_map_pages(struct vm_fault *vmf, + pgoff_t start_pgoff, pgoff_t end_pgoff) +{ + struct file *file = vmf->vma->vm_file; + struct address_space *mapping = file->f_mapping; + pgoff_t last_pgoff = start_pgoff; + unsigned long max_idx; + XA_STATE(xas, &mapping->i_pages, start_pgoff); + struct page *head, *page; + unsigned int mmap_miss = READ_ONCE(file->f_ra.mmap_miss); + + rcu_read_lock(); + xas_for_each(&xas, head, end_pgoff) { + if (xas_retry(&xas, head)) + continue; + if (xa_is_value(head)) + goto next; + + /* + * Check for a locked page first, as a speculative + * reference may adversely influence page migration. + */ + if (PageLocked(head)) + goto next; + if (!page_cache_get_speculative(head)) + goto next; + + /* Has the page moved or been split? */ + if (unlikely(head != xas_reload(&xas))) + goto skip; + page = find_subpage(head, xas.xa_index); + + if (!PageUptodate(head) || + PageReadahead(page) || + PageHWPoison(page)) + goto skip; + if (!trylock_page(head)) + goto skip; + + if (head->mapping != mapping || !PageUptodate(head)) + goto unlock; + + max_idx = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE); + if (xas.xa_index >= max_idx) + goto unlock; + + if (mmap_miss > 0) + mmap_miss--; + + vmf->address += (xas.xa_index - last_pgoff) << PAGE_SHIFT; + if (vmf->pte) + vmf->pte += xas.xa_index - last_pgoff; + last_pgoff = xas.xa_index; + if (alloc_set_pte(vmf, page)) + goto unlock; + unlock_page(head); + goto next; +unlock: + unlock_page(head); +skip: + put_page(head); +next: + /* Huge page is mapped? No need to proceed. */ + if (pmd_trans_huge(*vmf->pmd)) + break; + } + rcu_read_unlock(); + WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss); +} +EXPORT_SYMBOL(filemap_map_pages); + +vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) +{ + struct page *page = vmf->page; + struct inode *inode = file_inode(vmf->vma->vm_file); + vm_fault_t ret = VM_FAULT_LOCKED; + + sb_start_pagefault(inode->i_sb); + file_update_time(vmf->vma->vm_file); + lock_page(page); + if (page->mapping != inode->i_mapping) { + unlock_page(page); + ret = VM_FAULT_NOPAGE; + goto out; + } + /* + * We mark the page dirty already here so that when freeze is in + * progress, we are guaranteed that writeback during freezing will + * see the dirty page and writeprotect it again. + */ + set_page_dirty(page); + wait_for_stable_page(page); +out: + sb_end_pagefault(inode->i_sb); + return ret; +} + +const struct vm_operations_struct generic_file_vm_ops = { + .fault = filemap_fault, + .map_pages = filemap_map_pages, + .page_mkwrite = filemap_page_mkwrite, +}; + +/* This is used for a general mmap of a disk file */ + +int generic_file_mmap(struct file * file, struct vm_area_struct * vma) +{ + struct address_space *mapping = file->f_mapping; + + if (!mapping->a_ops->readpage) + return -ENOEXEC; + file_accessed(file); + vma->vm_ops = &generic_file_vm_ops; + return 0; +} + +/* + * This is for filesystems which do not implement ->writepage. + */ +int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma) +{ + if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE)) + return -EINVAL; + return generic_file_mmap(file, vma); +} +#else +vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) +{ + return VM_FAULT_SIGBUS; +} +int generic_file_mmap(struct file * file, struct vm_area_struct * vma) +{ + return -ENOSYS; +} +int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma) +{ + return -ENOSYS; +} +#endif /* CONFIG_MMU */ + +EXPORT_SYMBOL(filemap_page_mkwrite); +EXPORT_SYMBOL(generic_file_mmap); +EXPORT_SYMBOL(generic_file_readonly_mmap); + +static struct page *wait_on_page_read(struct page *page) +{ + if (!IS_ERR(page)) { + wait_on_page_locked(page); + if (!PageUptodate(page)) { + put_page(page); + page = ERR_PTR(-EIO); + } + } + return page; +} + +static struct page *do_read_cache_page(struct address_space *mapping, + pgoff_t index, + int (*filler)(void *, struct page *), + void *data, + gfp_t gfp) +{ + struct page *page; + int err; +repeat: + page = find_get_page(mapping, index); + if (!page) { + page = __page_cache_alloc(gfp); + if (!page) + return ERR_PTR(-ENOMEM); + err = add_to_page_cache_lru(page, mapping, index, gfp); + if (unlikely(err)) { + put_page(page); + if (err == -EEXIST) + goto repeat; + /* Presumably ENOMEM for xarray node */ + return ERR_PTR(err); + } + +filler: + if (filler) + err = filler(data, page); + else + err = mapping->a_ops->readpage(data, page); + + if (err < 0) { + put_page(page); + return ERR_PTR(err); + } + + page = wait_on_page_read(page); + if (IS_ERR(page)) + return page; + goto out; + } + if (PageUptodate(page)) + goto out; + + /* + * Page is not up to date and may be locked due to one of the following + * case a: Page is being filled and the page lock is held + * case b: Read/write error clearing the page uptodate status + * case c: Truncation in progress (page locked) + * case d: Reclaim in progress + * + * Case a, the page will be up to date when the page is unlocked. + * There is no need to serialise on the page lock here as the page + * is pinned so the lock gives no additional protection. Even if the + * page is truncated, the data is still valid if PageUptodate as + * it's a race vs truncate race. + * Case b, the page will not be up to date + * Case c, the page may be truncated but in itself, the data may still + * be valid after IO completes as it's a read vs truncate race. The + * operation must restart if the page is not uptodate on unlock but + * otherwise serialising on page lock to stabilise the mapping gives + * no additional guarantees to the caller as the page lock is + * released before return. + * Case d, similar to truncation. If reclaim holds the page lock, it + * will be a race with remove_mapping that determines if the mapping + * is valid on unlock but otherwise the data is valid and there is + * no need to serialise with page lock. + * + * As the page lock gives no additional guarantee, we optimistically + * wait on the page to be unlocked and check if it's up to date and + * use the page if it is. Otherwise, the page lock is required to + * distinguish between the different cases. The motivation is that we + * avoid spurious serialisations and wakeups when multiple processes + * wait on the same page for IO to complete. + */ + wait_on_page_locked(page); + if (PageUptodate(page)) + goto out; + + /* Distinguish between all the cases under the safety of the lock */ + lock_page(page); + + /* Case c or d, restart the operation */ + if (!page->mapping) { + unlock_page(page); + put_page(page); + goto repeat; + } + + /* Someone else locked and filled the page in a very small window */ + if (PageUptodate(page)) { + unlock_page(page); + goto out; + } + + /* + * A previous I/O error may have been due to temporary + * failures. + * Clear page error before actual read, PG_error will be + * set again if read page fails. + */ + ClearPageError(page); + goto filler; + +out: + mark_page_accessed(page); + return page; +} + +/** + * read_cache_page - read into page cache, fill it if needed + * @mapping: the page's address_space + * @index: the page index + * @filler: function to perform the read + * @data: first arg to filler(data, page) function, often left as NULL + * + * Read into the page cache. If a page already exists, and PageUptodate() is + * not set, try to fill the page and wait for it to become unlocked. + * + * If the page does not get brought uptodate, return -EIO. + * + * Return: up to date page on success, ERR_PTR() on failure. + */ +struct page *read_cache_page(struct address_space *mapping, + pgoff_t index, + int (*filler)(void *, struct page *), + void *data) +{ + return do_read_cache_page(mapping, index, filler, data, + mapping_gfp_mask(mapping)); +} +EXPORT_SYMBOL(read_cache_page); + +/** + * read_cache_page_gfp - read into page cache, using specified page allocation flags. + * @mapping: the page's address_space + * @index: the page index + * @gfp: the page allocator flags to use if allocating + * + * This is the same as "read_mapping_page(mapping, index, NULL)", but with + * any new page allocations done using the specified allocation flags. + * + * If the page does not get brought uptodate, return -EIO. + * + * Return: up to date page on success, ERR_PTR() on failure. + */ +struct page *read_cache_page_gfp(struct address_space *mapping, + pgoff_t index, + gfp_t gfp) +{ + return do_read_cache_page(mapping, index, NULL, NULL, gfp); +} +EXPORT_SYMBOL(read_cache_page_gfp); + +int pagecache_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata) +{ + const struct address_space_operations *aops = mapping->a_ops; + + return aops->write_begin(file, mapping, pos, len, flags, + pagep, fsdata); +} +EXPORT_SYMBOL(pagecache_write_begin); + +int pagecache_write_end(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) +{ + const struct address_space_operations *aops = mapping->a_ops; + + return aops->write_end(file, mapping, pos, len, copied, page, fsdata); +} +EXPORT_SYMBOL(pagecache_write_end); + +/* + * Warn about a page cache invalidation failure during a direct I/O write. + */ +void dio_warn_stale_pagecache(struct file *filp) +{ + static DEFINE_RATELIMIT_STATE(_rs, 86400 * HZ, DEFAULT_RATELIMIT_BURST); + char pathname[128]; + struct inode *inode = file_inode(filp); + char *path; + + errseq_set(&inode->i_mapping->wb_err, -EIO); + if (__ratelimit(&_rs)) { + path = file_path(filp, pathname, sizeof(pathname)); + if (IS_ERR(path)) + path = "(unknown)"; + pr_crit("Page cache invalidation failure on direct I/O. Possible data corruption due to collision with buffered I/O!\n"); + pr_crit("File: %s PID: %d Comm: %.20s\n", path, current->pid, + current->comm); + } +} + +ssize_t +generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from) +{ + struct file *file = iocb->ki_filp; + struct address_space *mapping = file->f_mapping; + struct inode *inode = mapping->host; + loff_t pos = iocb->ki_pos; + ssize_t written; + size_t write_len; + pgoff_t end; + + write_len = iov_iter_count(from); + end = (pos + write_len - 1) >> PAGE_SHIFT; + + if (iocb->ki_flags & IOCB_NOWAIT) { + /* If there are pages to writeback, return */ + if (filemap_range_has_page(inode->i_mapping, pos, + pos + write_len - 1)) + return -EAGAIN; + } else { + written = filemap_write_and_wait_range(mapping, pos, + pos + write_len - 1); + if (written) + goto out; + } + + /* + * After a write we want buffered reads to be sure to go to disk to get + * the new data. We invalidate clean cached page from the region we're + * about to write. We do this *before* the write so that we can return + * without clobbering -EIOCBQUEUED from ->direct_IO(). + */ + written = invalidate_inode_pages2_range(mapping, + pos >> PAGE_SHIFT, end); + /* + * If a page can not be invalidated, return 0 to fall back + * to buffered write. + */ + if (written) { + if (written == -EBUSY) + return 0; + goto out; + } + + written = mapping->a_ops->direct_IO(iocb, from); + + /* + * Finally, try again to invalidate clean pages which might have been + * cached by non-direct readahead, or faulted in by get_user_pages() + * if the source of the write was an mmap'ed region of the file + * we're writing. Either one is a pretty crazy thing to do, + * so we don't support it 100%. If this invalidation + * fails, tough, the write still worked... + * + * Most of the time we do not need this since dio_complete() will do + * the invalidation for us. However there are some file systems that + * do not end up with dio_complete() being called, so let's not break + * them by removing it completely. + * + * Noticeable example is a blkdev_direct_IO(). + * + * Skip invalidation for async writes or if mapping has no pages. + */ + if (written > 0 && mapping->nrpages && + invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, end)) + dio_warn_stale_pagecache(file); + + if (written > 0) { + pos += written; + write_len -= written; + if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) { + i_size_write(inode, pos); + mark_inode_dirty(inode); + } + iocb->ki_pos = pos; + } + iov_iter_revert(from, write_len - iov_iter_count(from)); +out: + return written; +} +EXPORT_SYMBOL(generic_file_direct_write); + +/* + * Find or create a page at the given pagecache position. Return the locked + * page. This function is specifically for buffered writes. + */ +struct page *grab_cache_page_write_begin(struct address_space *mapping, + pgoff_t index, unsigned flags) +{ + struct page *page; + int fgp_flags = FGP_LOCK|FGP_WRITE|FGP_CREAT; + + if (flags & AOP_FLAG_NOFS) + fgp_flags |= FGP_NOFS; + + page = pagecache_get_page(mapping, index, fgp_flags, + mapping_gfp_mask(mapping)); + if (page) + wait_for_stable_page(page); + + return page; +} +EXPORT_SYMBOL(grab_cache_page_write_begin); + +ssize_t generic_perform_write(struct file *file, + struct iov_iter *i, loff_t pos) +{ + struct address_space *mapping = file->f_mapping; + const struct address_space_operations *a_ops = mapping->a_ops; + long status = 0; + ssize_t written = 0; + unsigned int flags = 0; + + do { + struct page *page; + unsigned long offset; /* Offset into pagecache page */ + unsigned long bytes; /* Bytes to write to page */ + size_t copied; /* Bytes copied from user */ + void *fsdata = NULL; + + offset = (pos & (PAGE_SIZE - 1)); + bytes = min_t(unsigned long, PAGE_SIZE - offset, + iov_iter_count(i)); + +again: + /* + * Bring in the user page that we will copy from _first_. + * Otherwise there's a nasty deadlock on copying from the + * same page as we're writing to, without it being marked + * up-to-date. + * + * Not only is this an optimisation, but it is also required + * to check that the address is actually valid, when atomic + * usercopies are used, below. + */ + if (unlikely(iov_iter_fault_in_readable(i, bytes))) { + status = -EFAULT; + break; + } + + if (fatal_signal_pending(current)) { + status = -EINTR; + break; + } + + status = a_ops->write_begin(file, mapping, pos, bytes, flags, + &page, &fsdata); + if (unlikely(status < 0)) + break; + + if (mapping_writably_mapped(mapping)) + flush_dcache_page(page); + + copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes); + flush_dcache_page(page); + + status = a_ops->write_end(file, mapping, pos, bytes, copied, + page, fsdata); + if (unlikely(status < 0)) + break; + copied = status; + + cond_resched(); + + iov_iter_advance(i, copied); + if (unlikely(copied == 0)) { + /* + * If we were unable to copy any data at all, we must + * fall back to a single segment length write. + * + * If we didn't fallback here, we could livelock + * because not all segments in the iov can be copied at + * once without a pagefault. + */ + bytes = min_t(unsigned long, PAGE_SIZE - offset, + iov_iter_single_seg_count(i)); + goto again; + } + pos += copied; + written += copied; + + balance_dirty_pages_ratelimited(mapping); + } while (iov_iter_count(i)); + + return written ? written : status; +} +EXPORT_SYMBOL(generic_perform_write); + +/** + * __generic_file_write_iter - write data to a file + * @iocb: IO state structure (file, offset, etc.) + * @from: iov_iter with data to write + * + * This function does all the work needed for actually writing data to a + * file. It does all basic checks, removes SUID from the file, updates + * modification times and calls proper subroutines depending on whether we + * do direct IO or a standard buffered write. + * + * It expects i_mutex to be grabbed unless we work on a block device or similar + * object which does not need locking at all. + * + * This function does *not* take care of syncing data in case of O_SYNC write. + * A caller has to handle it. This is mainly due to the fact that we want to + * avoid syncing under i_mutex. + * + * Return: + * * number of bytes written, even for truncated writes + * * negative error code if no data has been written at all + */ +ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) +{ + struct file *file = iocb->ki_filp; + struct address_space * mapping = file->f_mapping; + struct inode *inode = mapping->host; + ssize_t written = 0; + ssize_t err; + ssize_t status; + + /* We can write back this queue in page reclaim */ + current->backing_dev_info = inode_to_bdi(inode); + err = file_remove_privs(file); + if (err) + goto out; + + err = file_update_time(file); + if (err) + goto out; + + if (iocb->ki_flags & IOCB_DIRECT) { + loff_t pos, endbyte; + + written = generic_file_direct_write(iocb, from); + /* + * If the write stopped short of completing, fall back to + * buffered writes. Some filesystems do this for writes to + * holes, for example. For DAX files, a buffered write will + * not succeed (even if it did, DAX does not handle dirty + * page-cache pages correctly). + */ + if (written < 0 || !iov_iter_count(from) || IS_DAX(inode)) + goto out; + + status = generic_perform_write(file, from, pos = iocb->ki_pos); + /* + * If generic_perform_write() returned a synchronous error + * then we want to return the number of bytes which were + * direct-written, or the error code if that was zero. Note + * that this differs from normal direct-io semantics, which + * will return -EFOO even if some bytes were written. + */ + if (unlikely(status < 0)) { + err = status; + goto out; + } + /* + * We need to ensure that the page cache pages are written to + * disk and invalidated to preserve the expected O_DIRECT + * semantics. + */ + endbyte = pos + status - 1; + err = filemap_write_and_wait_range(mapping, pos, endbyte); + if (err == 0) { + iocb->ki_pos = endbyte + 1; + written += status; + invalidate_mapping_pages(mapping, + pos >> PAGE_SHIFT, + endbyte >> PAGE_SHIFT); + } else { + /* + * We don't know how much we wrote, so just return + * the number of bytes which were direct-written + */ + } + } else { + written = generic_perform_write(file, from, iocb->ki_pos); + if (likely(written > 0)) + iocb->ki_pos += written; + } +out: + current->backing_dev_info = NULL; + return written ? written : err; +} +EXPORT_SYMBOL(__generic_file_write_iter); + +/** + * generic_file_write_iter - write data to a file + * @iocb: IO state structure + * @from: iov_iter with data to write + * + * This is a wrapper around __generic_file_write_iter() to be used by most + * filesystems. It takes care of syncing the file in case of O_SYNC file + * and acquires i_mutex as needed. + * Return: + * * negative error code if no data has been written at all of + * vfs_fsync_range() failed for a synchronous write + * * number of bytes written, even for truncated writes + */ +ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file->f_mapping->host; + ssize_t ret; + + inode_lock(inode); + ret = generic_write_checks(iocb, from); + if (ret > 0) + ret = __generic_file_write_iter(iocb, from); + inode_unlock(inode); + + if (ret > 0) + ret = generic_write_sync(iocb, ret); + return ret; +} +EXPORT_SYMBOL(generic_file_write_iter); + +/** + * try_to_release_page() - release old fs-specific metadata on a page + * + * @page: the page which the kernel is trying to free + * @gfp_mask: memory allocation flags (and I/O mode) + * + * The address_space is to try to release any data against the page + * (presumably at page->private). + * + * This may also be called if PG_fscache is set on a page, indicating that the + * page is known to the local caching routines. + * + * The @gfp_mask argument specifies whether I/O may be performed to release + * this page (__GFP_IO), and whether the call may block (__GFP_RECLAIM & __GFP_FS). + * + * Return: %1 if the release was successful, otherwise return zero. + */ +int try_to_release_page(struct page *page, gfp_t gfp_mask) +{ + struct address_space * const mapping = page->mapping; + + BUG_ON(!PageLocked(page)); + if (PageWriteback(page)) + return 0; + + if (mapping && mapping->a_ops->releasepage) + return mapping->a_ops->releasepage(page, gfp_mask); + return try_to_free_buffers(page); +} + +EXPORT_SYMBOL(try_to_release_page); diff --git a/mm/frame_vector.c b/mm/frame_vector.c new file mode 100644 index 000000000..1cd81d38a --- /dev/null +++ b/mm/frame_vector.c @@ -0,0 +1,223 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include + +/** + * get_vaddr_frames() - map virtual addresses to pfns + * @start: starting user address + * @nr_frames: number of pages / pfns from start to map + * @gup_flags: flags modifying lookup behaviour + * @vec: structure which receives pages / pfns of the addresses mapped. + * It should have space for at least nr_frames entries. + * + * This function maps virtual addresses from @start and fills @vec structure + * with page frame numbers or page pointers to corresponding pages (choice + * depends on the type of the vma underlying the virtual address). If @start + * belongs to a normal vma, the function grabs reference to each of the pages + * to pin them in memory. If @start belongs to VM_IO | VM_PFNMAP vma, we don't + * touch page structures and the caller must make sure pfns aren't reused for + * anything else while he is using them. + * + * The function returns number of pages mapped which may be less than + * @nr_frames. In particular we stop mapping if there are more vmas of + * different type underlying the specified range of virtual addresses. + * When the function isn't able to map a single page, it returns error. + * + * Note that get_vaddr_frames() cannot follow VM_IO mappings. It used + * to be able to do that, but that could (racily) return non-refcounted + * pfns. + * + * This function takes care of grabbing mmap_lock as necessary. + */ +int get_vaddr_frames(unsigned long start, unsigned int nr_frames, + unsigned int gup_flags, struct frame_vector *vec) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + int ret = 0; + int locked; + + if (nr_frames == 0) + return 0; + + if (WARN_ON_ONCE(nr_frames > vec->nr_allocated)) + nr_frames = vec->nr_allocated; + + start = untagged_addr(start); + + mmap_read_lock(mm); + locked = 1; + vma = find_vma_intersection(mm, start, start + 1); + if (!vma) { + ret = -EFAULT; + goto out; + } + + /* + * While get_vaddr_frames() could be used for transient (kernel + * controlled lifetime) pinning of memory pages all current + * users establish long term (userspace controlled lifetime) + * page pinning. Treat get_vaddr_frames() like + * get_user_pages_longterm() and disallow it for filesystem-dax + * mappings. + */ + if (vma_is_fsdax(vma)) { + ret = -EOPNOTSUPP; + goto out; + } + + if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) { + vec->got_ref = true; + vec->is_pfns = false; + ret = pin_user_pages_locked(start, nr_frames, + gup_flags, (struct page **)(vec->ptrs), &locked); + if (likely(ret > 0)) + goto out; + } + + vec->nr_frames = 0; + +out: + if (locked) + mmap_read_unlock(mm); + if (!ret) + ret = -EFAULT; + if (ret > 0) + vec->nr_frames = ret; + return ret; +} +EXPORT_SYMBOL(get_vaddr_frames); + +/** + * put_vaddr_frames() - drop references to pages if get_vaddr_frames() acquired + * them + * @vec: frame vector to put + * + * Drop references to pages if get_vaddr_frames() acquired them. We also + * invalidate the frame vector so that it is prepared for the next call into + * get_vaddr_frames(). + */ +void put_vaddr_frames(struct frame_vector *vec) +{ + struct page **pages; + + if (!vec->got_ref) + goto out; + pages = frame_vector_pages(vec); + /* + * frame_vector_pages() might needed to do a conversion when + * get_vaddr_frames() got pages but vec was later converted to pfns. + * But it shouldn't really fail to convert pfns back... + */ + if (WARN_ON(IS_ERR(pages))) + goto out; + + unpin_user_pages(pages, vec->nr_frames); + vec->got_ref = false; +out: + vec->nr_frames = 0; +} +EXPORT_SYMBOL(put_vaddr_frames); + +/** + * frame_vector_to_pages - convert frame vector to contain page pointers + * @vec: frame vector to convert + * + * Convert @vec to contain array of page pointers. If the conversion is + * successful, return 0. Otherwise return an error. Note that we do not grab + * page references for the page structures. + */ +int frame_vector_to_pages(struct frame_vector *vec) +{ + int i; + unsigned long *nums; + struct page **pages; + + if (!vec->is_pfns) + return 0; + nums = frame_vector_pfns(vec); + for (i = 0; i < vec->nr_frames; i++) + if (!pfn_valid(nums[i])) + return -EINVAL; + pages = (struct page **)nums; + for (i = 0; i < vec->nr_frames; i++) + pages[i] = pfn_to_page(nums[i]); + vec->is_pfns = false; + return 0; +} +EXPORT_SYMBOL(frame_vector_to_pages); + +/** + * frame_vector_to_pfns - convert frame vector to contain pfns + * @vec: frame vector to convert + * + * Convert @vec to contain array of pfns. + */ +void frame_vector_to_pfns(struct frame_vector *vec) +{ + int i; + unsigned long *nums; + struct page **pages; + + if (vec->is_pfns) + return; + pages = (struct page **)(vec->ptrs); + nums = (unsigned long *)pages; + for (i = 0; i < vec->nr_frames; i++) + nums[i] = page_to_pfn(pages[i]); + vec->is_pfns = true; +} +EXPORT_SYMBOL(frame_vector_to_pfns); + +/** + * frame_vector_create() - allocate & initialize structure for pinned pfns + * @nr_frames: number of pfns slots we should reserve + * + * Allocate and initialize struct pinned_pfns to be able to hold @nr_pfns + * pfns. + */ +struct frame_vector *frame_vector_create(unsigned int nr_frames) +{ + struct frame_vector *vec; + int size = sizeof(struct frame_vector) + sizeof(void *) * nr_frames; + + if (WARN_ON_ONCE(nr_frames == 0)) + return NULL; + /* + * This is absurdly high. It's here just to avoid strange effects when + * arithmetics overflows. + */ + if (WARN_ON_ONCE(nr_frames > INT_MAX / sizeof(void *) / 2)) + return NULL; + /* + * Avoid higher order allocations, use vmalloc instead. It should + * be rare anyway. + */ + vec = kvmalloc(size, GFP_KERNEL); + if (!vec) + return NULL; + vec->nr_allocated = nr_frames; + vec->nr_frames = 0; + return vec; +} +EXPORT_SYMBOL(frame_vector_create); + +/** + * frame_vector_destroy() - free memory allocated to carry frame vector + * @vec: Frame vector to free + * + * Free structure allocated by frame_vector_create() to carry frames. + */ +void frame_vector_destroy(struct frame_vector *vec) +{ + /* Make sure put_vaddr_frames() got called properly... */ + VM_BUG_ON(vec->nr_frames > 0); + kvfree(vec); +} +EXPORT_SYMBOL(frame_vector_destroy); diff --git a/mm/frontswap.c b/mm/frontswap.c new file mode 100644 index 000000000..2183a56c7 --- /dev/null +++ b/mm/frontswap.c @@ -0,0 +1,497 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Frontswap frontend + * + * This code provides the generic "frontend" layer to call a matching + * "backend" driver implementation of frontswap. See + * Documentation/vm/frontswap.rst for more information. + * + * Copyright (C) 2009-2012 Oracle Corp. All rights reserved. + * Author: Dan Magenheimer + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +DEFINE_STATIC_KEY_FALSE(frontswap_enabled_key); + +/* + * frontswap_ops are added by frontswap_register_ops, and provide the + * frontswap "backend" implementation functions. Multiple implementations + * may be registered, but implementations can never deregister. This + * is a simple singly-linked list of all registered implementations. + */ +static struct frontswap_ops *frontswap_ops __read_mostly; + +#define for_each_frontswap_ops(ops) \ + for ((ops) = frontswap_ops; (ops); (ops) = (ops)->next) + +/* + * If enabled, frontswap_store will return failure even on success. As + * a result, the swap subsystem will always write the page to swap, in + * effect converting frontswap into a writethrough cache. In this mode, + * there is no direct reduction in swap writes, but a frontswap backend + * can unilaterally "reclaim" any pages in use with no data loss, thus + * providing increases control over maximum memory usage due to frontswap. + */ +static bool frontswap_writethrough_enabled __read_mostly; + +/* + * If enabled, the underlying tmem implementation is capable of doing + * exclusive gets, so frontswap_load, on a successful tmem_get must + * mark the page as no longer in frontswap AND mark it dirty. + */ +static bool frontswap_tmem_exclusive_gets_enabled __read_mostly; + +#ifdef CONFIG_DEBUG_FS +/* + * Counters available via /sys/kernel/debug/frontswap (if debugfs is + * properly configured). These are for information only so are not protected + * against increment races. + */ +static u64 frontswap_loads; +static u64 frontswap_succ_stores; +static u64 frontswap_failed_stores; +static u64 frontswap_invalidates; + +static inline void inc_frontswap_loads(void) { + data_race(frontswap_loads++); +} +static inline void inc_frontswap_succ_stores(void) { + data_race(frontswap_succ_stores++); +} +static inline void inc_frontswap_failed_stores(void) { + data_race(frontswap_failed_stores++); +} +static inline void inc_frontswap_invalidates(void) { + data_race(frontswap_invalidates++); +} +#else +static inline void inc_frontswap_loads(void) { } +static inline void inc_frontswap_succ_stores(void) { } +static inline void inc_frontswap_failed_stores(void) { } +static inline void inc_frontswap_invalidates(void) { } +#endif + +/* + * Due to the asynchronous nature of the backends loading potentially + * _after_ the swap system has been activated, we have chokepoints + * on all frontswap functions to not call the backend until the backend + * has registered. + * + * This would not guards us against the user deciding to call swapoff right as + * we are calling the backend to initialize (so swapon is in action). + * Fortunately for us, the swapon_mutex has been taken by the callee so we are + * OK. The other scenario where calls to frontswap_store (called via + * swap_writepage) is racing with frontswap_invalidate_area (called via + * swapoff) is again guarded by the swap subsystem. + * + * While no backend is registered all calls to frontswap_[store|load| + * invalidate_area|invalidate_page] are ignored or fail. + * + * The time between the backend being registered and the swap file system + * calling the backend (via the frontswap_* functions) is indeterminate as + * frontswap_ops is not atomic_t (or a value guarded by a spinlock). + * That is OK as we are comfortable missing some of these calls to the newly + * registered backend. + * + * Obviously the opposite (unloading the backend) must be done after all + * the frontswap_[store|load|invalidate_area|invalidate_page] start + * ignoring or failing the requests. However, there is currently no way + * to unload a backend once it is registered. + */ + +/* + * Register operations for frontswap + */ +void frontswap_register_ops(struct frontswap_ops *ops) +{ + DECLARE_BITMAP(a, MAX_SWAPFILES); + DECLARE_BITMAP(b, MAX_SWAPFILES); + struct swap_info_struct *si; + unsigned int i; + + bitmap_zero(a, MAX_SWAPFILES); + bitmap_zero(b, MAX_SWAPFILES); + + spin_lock(&swap_lock); + plist_for_each_entry(si, &swap_active_head, list) { + if (!WARN_ON(!si->frontswap_map)) + set_bit(si->type, a); + } + spin_unlock(&swap_lock); + + /* the new ops needs to know the currently active swap devices */ + for_each_set_bit(i, a, MAX_SWAPFILES) + ops->init(i); + + /* + * Setting frontswap_ops must happen after the ops->init() calls + * above; cmpxchg implies smp_mb() which will ensure the init is + * complete at this point. + */ + do { + ops->next = frontswap_ops; + } while (cmpxchg(&frontswap_ops, ops->next, ops) != ops->next); + + static_branch_inc(&frontswap_enabled_key); + + spin_lock(&swap_lock); + plist_for_each_entry(si, &swap_active_head, list) { + if (si->frontswap_map) + set_bit(si->type, b); + } + spin_unlock(&swap_lock); + + /* + * On the very unlikely chance that a swap device was added or + * removed between setting the "a" list bits and the ops init + * calls, we re-check and do init or invalidate for any changed + * bits. + */ + if (unlikely(!bitmap_equal(a, b, MAX_SWAPFILES))) { + for (i = 0; i < MAX_SWAPFILES; i++) { + if (!test_bit(i, a) && test_bit(i, b)) + ops->init(i); + else if (test_bit(i, a) && !test_bit(i, b)) + ops->invalidate_area(i); + } + } +} +EXPORT_SYMBOL(frontswap_register_ops); + +/* + * Enable/disable frontswap writethrough (see above). + */ +void frontswap_writethrough(bool enable) +{ + frontswap_writethrough_enabled = enable; +} +EXPORT_SYMBOL(frontswap_writethrough); + +/* + * Enable/disable frontswap exclusive gets (see above). + */ +void frontswap_tmem_exclusive_gets(bool enable) +{ + frontswap_tmem_exclusive_gets_enabled = enable; +} +EXPORT_SYMBOL(frontswap_tmem_exclusive_gets); + +/* + * Called when a swap device is swapon'd. + */ +void __frontswap_init(unsigned type, unsigned long *map) +{ + struct swap_info_struct *sis = swap_info[type]; + struct frontswap_ops *ops; + + VM_BUG_ON(sis == NULL); + + /* + * p->frontswap is a bitmap that we MUST have to figure out which page + * has gone in frontswap. Without it there is no point of continuing. + */ + if (WARN_ON(!map)) + return; + /* + * Irregardless of whether the frontswap backend has been loaded + * before this function or it will be later, we _MUST_ have the + * p->frontswap set to something valid to work properly. + */ + frontswap_map_set(sis, map); + + for_each_frontswap_ops(ops) + ops->init(type); +} +EXPORT_SYMBOL(__frontswap_init); + +bool __frontswap_test(struct swap_info_struct *sis, + pgoff_t offset) +{ + if (sis->frontswap_map) + return test_bit(offset, sis->frontswap_map); + return false; +} +EXPORT_SYMBOL(__frontswap_test); + +static inline void __frontswap_set(struct swap_info_struct *sis, + pgoff_t offset) +{ + set_bit(offset, sis->frontswap_map); + atomic_inc(&sis->frontswap_pages); +} + +static inline void __frontswap_clear(struct swap_info_struct *sis, + pgoff_t offset) +{ + clear_bit(offset, sis->frontswap_map); + atomic_dec(&sis->frontswap_pages); +} + +/* + * "Store" data from a page to frontswap and associate it with the page's + * swaptype and offset. Page must be locked and in the swap cache. + * If frontswap already contains a page with matching swaptype and + * offset, the frontswap implementation may either overwrite the data and + * return success or invalidate the page from frontswap and return failure. + */ +int __frontswap_store(struct page *page) +{ + int ret = -1; + swp_entry_t entry = { .val = page_private(page), }; + int type = swp_type(entry); + struct swap_info_struct *sis = swap_info[type]; + pgoff_t offset = swp_offset(entry); + struct frontswap_ops *ops; + + VM_BUG_ON(!frontswap_ops); + VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON(sis == NULL); + + /* + * If a dup, we must remove the old page first; we can't leave the + * old page no matter if the store of the new page succeeds or fails, + * and we can't rely on the new page replacing the old page as we may + * not store to the same implementation that contains the old page. + */ + if (__frontswap_test(sis, offset)) { + __frontswap_clear(sis, offset); + for_each_frontswap_ops(ops) + ops->invalidate_page(type, offset); + } + + /* Try to store in each implementation, until one succeeds. */ + for_each_frontswap_ops(ops) { + ret = ops->store(type, offset, page); + if (!ret) /* successful store */ + break; + } + if (ret == 0) { + __frontswap_set(sis, offset); + inc_frontswap_succ_stores(); + } else { + inc_frontswap_failed_stores(); + } + if (frontswap_writethrough_enabled) + /* report failure so swap also writes to swap device */ + ret = -1; + return ret; +} +EXPORT_SYMBOL(__frontswap_store); + +/* + * "Get" data from frontswap associated with swaptype and offset that were + * specified when the data was put to frontswap and use it to fill the + * specified page with data. Page must be locked and in the swap cache. + */ +int __frontswap_load(struct page *page) +{ + int ret = -1; + swp_entry_t entry = { .val = page_private(page), }; + int type = swp_type(entry); + struct swap_info_struct *sis = swap_info[type]; + pgoff_t offset = swp_offset(entry); + struct frontswap_ops *ops; + + VM_BUG_ON(!frontswap_ops); + VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON(sis == NULL); + + if (!__frontswap_test(sis, offset)) + return -1; + + /* Try loading from each implementation, until one succeeds. */ + for_each_frontswap_ops(ops) { + ret = ops->load(type, offset, page); + if (!ret) /* successful load */ + break; + } + if (ret == 0) { + inc_frontswap_loads(); + if (frontswap_tmem_exclusive_gets_enabled) { + SetPageDirty(page); + __frontswap_clear(sis, offset); + } + } + return ret; +} +EXPORT_SYMBOL(__frontswap_load); + +/* + * Invalidate any data from frontswap associated with the specified swaptype + * and offset so that a subsequent "get" will fail. + */ +void __frontswap_invalidate_page(unsigned type, pgoff_t offset) +{ + struct swap_info_struct *sis = swap_info[type]; + struct frontswap_ops *ops; + + VM_BUG_ON(!frontswap_ops); + VM_BUG_ON(sis == NULL); + + if (!__frontswap_test(sis, offset)) + return; + + for_each_frontswap_ops(ops) + ops->invalidate_page(type, offset); + __frontswap_clear(sis, offset); + inc_frontswap_invalidates(); +} +EXPORT_SYMBOL(__frontswap_invalidate_page); + +/* + * Invalidate all data from frontswap associated with all offsets for the + * specified swaptype. + */ +void __frontswap_invalidate_area(unsigned type) +{ + struct swap_info_struct *sis = swap_info[type]; + struct frontswap_ops *ops; + + VM_BUG_ON(!frontswap_ops); + VM_BUG_ON(sis == NULL); + + if (sis->frontswap_map == NULL) + return; + + for_each_frontswap_ops(ops) + ops->invalidate_area(type); + atomic_set(&sis->frontswap_pages, 0); + bitmap_zero(sis->frontswap_map, sis->max); +} +EXPORT_SYMBOL(__frontswap_invalidate_area); + +static unsigned long __frontswap_curr_pages(void) +{ + unsigned long totalpages = 0; + struct swap_info_struct *si = NULL; + + assert_spin_locked(&swap_lock); + plist_for_each_entry(si, &swap_active_head, list) + totalpages += atomic_read(&si->frontswap_pages); + return totalpages; +} + +static int __frontswap_unuse_pages(unsigned long total, unsigned long *unused, + int *swapid) +{ + int ret = -EINVAL; + struct swap_info_struct *si = NULL; + int si_frontswap_pages; + unsigned long total_pages_to_unuse = total; + unsigned long pages = 0, pages_to_unuse = 0; + + assert_spin_locked(&swap_lock); + plist_for_each_entry(si, &swap_active_head, list) { + si_frontswap_pages = atomic_read(&si->frontswap_pages); + if (total_pages_to_unuse < si_frontswap_pages) { + pages = pages_to_unuse = total_pages_to_unuse; + } else { + pages = si_frontswap_pages; + pages_to_unuse = 0; /* unuse all */ + } + /* ensure there is enough RAM to fetch pages from frontswap */ + if (security_vm_enough_memory_mm(current->mm, pages)) { + ret = -ENOMEM; + continue; + } + vm_unacct_memory(pages); + *unused = pages_to_unuse; + *swapid = si->type; + ret = 0; + break; + } + + return ret; +} + +/* + * Used to check if it's necessary and feasible to unuse pages. + * Return 1 when nothing to do, 0 when need to shrink pages, + * error code when there is an error. + */ +static int __frontswap_shrink(unsigned long target_pages, + unsigned long *pages_to_unuse, + int *type) +{ + unsigned long total_pages = 0, total_pages_to_unuse; + + assert_spin_locked(&swap_lock); + + total_pages = __frontswap_curr_pages(); + if (total_pages <= target_pages) { + /* Nothing to do */ + *pages_to_unuse = 0; + return 1; + } + total_pages_to_unuse = total_pages - target_pages; + return __frontswap_unuse_pages(total_pages_to_unuse, pages_to_unuse, type); +} + +/* + * Frontswap, like a true swap device, may unnecessarily retain pages + * under certain circumstances; "shrink" frontswap is essentially a + * "partial swapoff" and works by calling try_to_unuse to attempt to + * unuse enough frontswap pages to attempt to -- subject to memory + * constraints -- reduce the number of pages in frontswap to the + * number given in the parameter target_pages. + */ +void frontswap_shrink(unsigned long target_pages) +{ + unsigned long pages_to_unuse = 0; + int type, ret; + + /* + * we don't want to hold swap_lock while doing a very + * lengthy try_to_unuse, but swap_list may change + * so restart scan from swap_active_head each time + */ + spin_lock(&swap_lock); + ret = __frontswap_shrink(target_pages, &pages_to_unuse, &type); + spin_unlock(&swap_lock); + if (ret == 0) + try_to_unuse(type, true, pages_to_unuse); + return; +} +EXPORT_SYMBOL(frontswap_shrink); + +/* + * Count and return the number of frontswap pages across all + * swap devices. This is exported so that backend drivers can + * determine current usage without reading debugfs. + */ +unsigned long frontswap_curr_pages(void) +{ + unsigned long totalpages = 0; + + spin_lock(&swap_lock); + totalpages = __frontswap_curr_pages(); + spin_unlock(&swap_lock); + + return totalpages; +} +EXPORT_SYMBOL(frontswap_curr_pages); + +static int __init init_frontswap(void) +{ +#ifdef CONFIG_DEBUG_FS + struct dentry *root = debugfs_create_dir("frontswap", NULL); + if (root == NULL) + return -ENXIO; + debugfs_create_u64("loads", 0444, root, &frontswap_loads); + debugfs_create_u64("succ_stores", 0444, root, &frontswap_succ_stores); + debugfs_create_u64("failed_stores", 0444, root, + &frontswap_failed_stores); + debugfs_create_u64("invalidates", 0444, root, &frontswap_invalidates); +#endif + return 0; +} + +module_init(init_frontswap); diff --git a/mm/gup.c b/mm/gup.c new file mode 100644 index 000000000..11307a8b2 --- /dev/null +++ b/mm/gup.c @@ -0,0 +1,3040 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include + +#include +#include + +#include "internal.h" + +struct follow_page_context { + struct dev_pagemap *pgmap; + unsigned int page_mask; +}; + +static void hpage_pincount_add(struct page *page, int refs) +{ + VM_BUG_ON_PAGE(!hpage_pincount_available(page), page); + VM_BUG_ON_PAGE(page != compound_head(page), page); + + atomic_add(refs, compound_pincount_ptr(page)); +} + +static void hpage_pincount_sub(struct page *page, int refs) +{ + VM_BUG_ON_PAGE(!hpage_pincount_available(page), page); + VM_BUG_ON_PAGE(page != compound_head(page), page); + + atomic_sub(refs, compound_pincount_ptr(page)); +} + +/* Equivalent to calling put_page() @refs times. */ +static void put_page_refs(struct page *page, int refs) +{ +#ifdef CONFIG_DEBUG_VM + if (VM_WARN_ON_ONCE_PAGE(page_ref_count(page) < refs, page)) + return; +#endif + + /* + * Calling put_page() for each ref is unnecessarily slow. Only the last + * ref needs a put_page(). + */ + if (refs > 1) + page_ref_sub(page, refs - 1); + put_page(page); +} + +/* + * Return the compound head page with ref appropriately incremented, + * or NULL if that failed. + */ +static inline struct page *try_get_compound_head(struct page *page, int refs) +{ + struct page *head = compound_head(page); + + if (WARN_ON_ONCE(page_ref_count(head) < 0)) + return NULL; + if (unlikely(!page_cache_add_speculative(head, refs))) + return NULL; + + /* + * At this point we have a stable reference to the head page; but it + * could be that between the compound_head() lookup and the refcount + * increment, the compound page was split, in which case we'd end up + * holding a reference on a page that has nothing to do with the page + * we were given anymore. + * So now that the head page is stable, recheck that the pages still + * belong together. + */ + if (unlikely(compound_head(page) != head)) { + put_page_refs(head, refs); + return NULL; + } + + return head; +} + +/* + * try_grab_compound_head() - attempt to elevate a page's refcount, by a + * flags-dependent amount. + * + * "grab" names in this file mean, "look at flags to decide whether to use + * FOLL_PIN or FOLL_GET behavior, when incrementing the page's refcount. + * + * Either FOLL_PIN or FOLL_GET (or neither) must be set, but not both at the + * same time. (That's true throughout the get_user_pages*() and + * pin_user_pages*() APIs.) Cases: + * + * FOLL_GET: page's refcount will be incremented by 1. + * FOLL_PIN: page's refcount will be incremented by GUP_PIN_COUNTING_BIAS. + * + * Return: head page (with refcount appropriately incremented) for success, or + * NULL upon failure. If neither FOLL_GET nor FOLL_PIN was set, that's + * considered failure, and furthermore, a likely bug in the caller, so a warning + * is also emitted. + */ +static __maybe_unused struct page *try_grab_compound_head(struct page *page, + int refs, + unsigned int flags) +{ + if (flags & FOLL_GET) + return try_get_compound_head(page, refs); + else if (flags & FOLL_PIN) { + int orig_refs = refs; + + /* + * Can't do FOLL_LONGTERM + FOLL_PIN with CMA in the gup fast + * path, so fail and let the caller fall back to the slow path. + */ + if (unlikely(flags & FOLL_LONGTERM) && + is_migrate_cma_page(page)) + return NULL; + + /* + * CAUTION: Don't use compound_head() on the page before this + * point, the result won't be stable. + */ + page = try_get_compound_head(page, refs); + if (!page) + return NULL; + + /* + * When pinning a compound page of order > 1 (which is what + * hpage_pincount_available() checks for), use an exact count to + * track it, via hpage_pincount_add/_sub(). + * + * However, be sure to *also* increment the normal page refcount + * field at least once, so that the page really is pinned. + */ + if (hpage_pincount_available(page)) + hpage_pincount_add(page, refs); + else + page_ref_add(page, refs * (GUP_PIN_COUNTING_BIAS - 1)); + + mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_ACQUIRED, + orig_refs); + + return page; + } + + WARN_ON_ONCE(1); + return NULL; +} + +static void put_compound_head(struct page *page, int refs, unsigned int flags) +{ + if (flags & FOLL_PIN) { + mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_RELEASED, + refs); + + if (hpage_pincount_available(page)) + hpage_pincount_sub(page, refs); + else + refs *= GUP_PIN_COUNTING_BIAS; + } + + put_page_refs(page, refs); +} + +/** + * try_grab_page() - elevate a page's refcount by a flag-dependent amount + * + * This might not do anything at all, depending on the flags argument. + * + * "grab" names in this file mean, "look at flags to decide whether to use + * FOLL_PIN or FOLL_GET behavior, when incrementing the page's refcount. + * + * @page: pointer to page to be grabbed + * @flags: gup flags: these are the FOLL_* flag values. + * + * Either FOLL_PIN or FOLL_GET (or neither) may be set, but not both at the same + * time. Cases: + * + * FOLL_GET: page's refcount will be incremented by 1. + * FOLL_PIN: page's refcount will be incremented by GUP_PIN_COUNTING_BIAS. + * + * Return: true for success, or if no action was required (if neither FOLL_PIN + * nor FOLL_GET was set, nothing is done). False for failure: FOLL_GET or + * FOLL_PIN was set, but the page could not be grabbed. + */ +bool __must_check try_grab_page(struct page *page, unsigned int flags) +{ + WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == (FOLL_GET | FOLL_PIN)); + + if (flags & FOLL_GET) + return try_get_page(page); + else if (flags & FOLL_PIN) { + int refs = 1; + + page = compound_head(page); + + if (WARN_ON_ONCE(page_ref_count(page) <= 0)) + return false; + + if (hpage_pincount_available(page)) + hpage_pincount_add(page, 1); + else + refs = GUP_PIN_COUNTING_BIAS; + + /* + * Similar to try_grab_compound_head(): even if using the + * hpage_pincount_add/_sub() routines, be sure to + * *also* increment the normal page refcount field at least + * once, so that the page really is pinned. + */ + page_ref_add(page, refs); + + mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_ACQUIRED, 1); + } + + return true; +} + +/** + * unpin_user_page() - release a dma-pinned page + * @page: pointer to page to be released + * + * Pages that were pinned via pin_user_pages*() must be released via either + * unpin_user_page(), or one of the unpin_user_pages*() routines. This is so + * that such pages can be separately tracked and uniquely handled. In + * particular, interactions with RDMA and filesystems need special handling. + */ +void unpin_user_page(struct page *page) +{ + put_compound_head(compound_head(page), 1, FOLL_PIN); +} +EXPORT_SYMBOL(unpin_user_page); + +/** + * unpin_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages + * @pages: array of pages to be maybe marked dirty, and definitely released. + * @npages: number of pages in the @pages array. + * @make_dirty: whether to mark the pages dirty + * + * "gup-pinned page" refers to a page that has had one of the get_user_pages() + * variants called on that page. + * + * For each page in the @pages array, make that page (or its head page, if a + * compound page) dirty, if @make_dirty is true, and if the page was previously + * listed as clean. In any case, releases all pages using unpin_user_page(), + * possibly via unpin_user_pages(), for the non-dirty case. + * + * Please see the unpin_user_page() documentation for details. + * + * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is + * required, then the caller should a) verify that this is really correct, + * because _lock() is usually required, and b) hand code it: + * set_page_dirty_lock(), unpin_user_page(). + * + */ +void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, + bool make_dirty) +{ + unsigned long index; + + /* + * TODO: this can be optimized for huge pages: if a series of pages is + * physically contiguous and part of the same compound page, then a + * single operation to the head page should suffice. + */ + + if (!make_dirty) { + unpin_user_pages(pages, npages); + return; + } + + for (index = 0; index < npages; index++) { + struct page *page = compound_head(pages[index]); + /* + * Checking PageDirty at this point may race with + * clear_page_dirty_for_io(), but that's OK. Two key + * cases: + * + * 1) This code sees the page as already dirty, so it + * skips the call to set_page_dirty(). That could happen + * because clear_page_dirty_for_io() called + * page_mkclean(), followed by set_page_dirty(). + * However, now the page is going to get written back, + * which meets the original intention of setting it + * dirty, so all is well: clear_page_dirty_for_io() goes + * on to call TestClearPageDirty(), and write the page + * back. + * + * 2) This code sees the page as clean, so it calls + * set_page_dirty(). The page stays dirty, despite being + * written back, so it gets written back again in the + * next writeback cycle. This is harmless. + */ + if (!PageDirty(page)) + set_page_dirty_lock(page); + unpin_user_page(page); + } +} +EXPORT_SYMBOL(unpin_user_pages_dirty_lock); + +/** + * unpin_user_pages() - release an array of gup-pinned pages. + * @pages: array of pages to be marked dirty and released. + * @npages: number of pages in the @pages array. + * + * For each page in the @pages array, release the page using unpin_user_page(). + * + * Please see the unpin_user_page() documentation for details. + */ +void unpin_user_pages(struct page **pages, unsigned long npages) +{ + unsigned long index; + + /* + * If this WARN_ON() fires, then the system *might* be leaking pages (by + * leaving them pinned), but probably not. More likely, gup/pup returned + * a hard -ERRNO error to the caller, who erroneously passed it here. + */ + if (WARN_ON(IS_ERR_VALUE(npages))) + return; + /* + * TODO: this can be optimized for huge pages: if a series of pages is + * physically contiguous and part of the same compound page, then a + * single operation to the head page should suffice. + */ + for (index = 0; index < npages; index++) + unpin_user_page(pages[index]); +} +EXPORT_SYMBOL(unpin_user_pages); + +#ifdef CONFIG_MMU +static struct page *no_page_table(struct vm_area_struct *vma, + unsigned int flags) +{ + /* + * When core dumping an enormous anonymous area that nobody + * has touched so far, we don't want to allocate unnecessary pages or + * page tables. Return error instead of NULL to skip handle_mm_fault, + * then get_dump_page() will return NULL to leave a hole in the dump. + * But we can only make this optimization where a hole would surely + * be zero-filled if handle_mm_fault() actually did handle it. + */ + if ((flags & FOLL_DUMP) && + (vma_is_anonymous(vma) || !vma->vm_ops->fault)) + return ERR_PTR(-EFAULT); + return NULL; +} + +static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address, + pte_t *pte, unsigned int flags) +{ + /* No page to get reference */ + if (flags & FOLL_GET) + return -EFAULT; + + if (flags & FOLL_TOUCH) { + pte_t entry = *pte; + + if (flags & FOLL_WRITE) + entry = pte_mkdirty(entry); + entry = pte_mkyoung(entry); + + if (!pte_same(*pte, entry)) { + set_pte_at(vma->vm_mm, address, pte, entry); + update_mmu_cache(vma, address, pte); + } + } + + /* Proper page table entry exists, but no corresponding struct page */ + return -EEXIST; +} + +/* + * FOLL_FORCE can write to even unwritable pte's, but only + * after we've gone through a COW cycle and they are dirty. + */ +static inline bool can_follow_write_pte(pte_t pte, unsigned int flags) +{ + return pte_write(pte) || + ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte)); +} + +static struct page *follow_page_pte(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmd, unsigned int flags, + struct dev_pagemap **pgmap) +{ + struct mm_struct *mm = vma->vm_mm; + struct page *page; + spinlock_t *ptl; + pte_t *ptep, pte; + int ret; + + /* FOLL_GET and FOLL_PIN are mutually exclusive. */ + if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == + (FOLL_PIN | FOLL_GET))) + return ERR_PTR(-EINVAL); + + /* + * Considering PTE level hugetlb, like continuous-PTE hugetlb on + * ARM64 architecture. + */ + if (is_vm_hugetlb_page(vma)) { + page = follow_huge_pmd_pte(vma, address, flags); + if (page) + return page; + return no_page_table(vma, flags); + } + +retry: + if (unlikely(pmd_bad(*pmd))) + return no_page_table(vma, flags); + + ptep = pte_offset_map_lock(mm, pmd, address, &ptl); + pte = *ptep; + if (!pte_present(pte)) { + swp_entry_t entry; + /* + * KSM's break_ksm() relies upon recognizing a ksm page + * even while it is being migrated, so for that case we + * need migration_entry_wait(). + */ + if (likely(!(flags & FOLL_MIGRATION))) + goto no_page; + if (pte_none(pte)) + goto no_page; + entry = pte_to_swp_entry(pte); + if (!is_migration_entry(entry)) + goto no_page; + pte_unmap_unlock(ptep, ptl); + migration_entry_wait(mm, pmd, address); + goto retry; + } + if ((flags & FOLL_NUMA) && pte_protnone(pte)) + goto no_page; + if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, flags)) { + pte_unmap_unlock(ptep, ptl); + return NULL; + } + + page = vm_normal_page(vma, address, pte); + if (!page && pte_devmap(pte) && (flags & (FOLL_GET | FOLL_PIN))) { + /* + * Only return device mapping pages in the FOLL_GET or FOLL_PIN + * case since they are only valid while holding the pgmap + * reference. + */ + *pgmap = get_dev_pagemap(pte_pfn(pte), *pgmap); + if (*pgmap) + page = pte_page(pte); + else + goto no_page; + } else if (unlikely(!page)) { + if (flags & FOLL_DUMP) { + /* Avoid special (like zero) pages in core dumps */ + page = ERR_PTR(-EFAULT); + goto out; + } + + if (is_zero_pfn(pte_pfn(pte))) { + page = pte_page(pte); + } else { + ret = follow_pfn_pte(vma, address, ptep, flags); + page = ERR_PTR(ret); + goto out; + } + } + + if (flags & FOLL_SPLIT && PageTransCompound(page)) { + get_page(page); + pte_unmap_unlock(ptep, ptl); + lock_page(page); + ret = split_huge_page(page); + unlock_page(page); + put_page(page); + if (ret) + return ERR_PTR(ret); + goto retry; + } + + /* try_grab_page() does nothing unless FOLL_GET or FOLL_PIN is set. */ + if (unlikely(!try_grab_page(page, flags))) { + page = ERR_PTR(-ENOMEM); + goto out; + } + /* + * We need to make the page accessible if and only if we are going + * to access its content (the FOLL_PIN case). Please see + * Documentation/core-api/pin_user_pages.rst for details. + */ + if (flags & FOLL_PIN) { + ret = arch_make_page_accessible(page); + if (ret) { + unpin_user_page(page); + page = ERR_PTR(ret); + goto out; + } + } + if (flags & FOLL_TOUCH) { + if ((flags & FOLL_WRITE) && + !pte_dirty(pte) && !PageDirty(page)) + set_page_dirty(page); + /* + * pte_mkyoung() would be more correct here, but atomic care + * is needed to avoid losing the dirty bit: it is easier to use + * mark_page_accessed(). + */ + mark_page_accessed(page); + } + if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) { + /* Do not mlock pte-mapped THP */ + if (PageTransCompound(page)) + goto out; + + /* + * The preliminary mapping check is mainly to avoid the + * pointless overhead of lock_page on the ZERO_PAGE + * which might bounce very badly if there is contention. + * + * If the page is already locked, we don't need to + * handle it now - vmscan will handle it later if and + * when it attempts to reclaim the page. + */ + if (page->mapping && trylock_page(page)) { + lru_add_drain(); /* push cached pages to LRU */ + /* + * Because we lock page here, and migration is + * blocked by the pte's page reference, and we + * know the page is still mapped, we don't even + * need to check for file-cache page truncation. + */ + mlock_vma_page(page); + unlock_page(page); + } + } +out: + pte_unmap_unlock(ptep, ptl); + return page; +no_page: + pte_unmap_unlock(ptep, ptl); + if (!pte_none(pte)) + return NULL; + return no_page_table(vma, flags); +} + +static struct page *follow_pmd_mask(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp, + unsigned int flags, + struct follow_page_context *ctx) +{ + pmd_t *pmd, pmdval; + spinlock_t *ptl; + struct page *page; + struct mm_struct *mm = vma->vm_mm; + + pmd = pmd_offset(pudp, address); + /* + * The READ_ONCE() will stabilize the pmdval in a register or + * on the stack so that it will stop changing under the code. + */ + pmdval = READ_ONCE(*pmd); + if (pmd_none(pmdval)) + return no_page_table(vma, flags); + if (pmd_huge(pmdval) && is_vm_hugetlb_page(vma)) { + page = follow_huge_pmd_pte(vma, address, flags); + if (page) + return page; + return no_page_table(vma, flags); + } + if (is_hugepd(__hugepd(pmd_val(pmdval)))) { + page = follow_huge_pd(vma, address, + __hugepd(pmd_val(pmdval)), flags, + PMD_SHIFT); + if (page) + return page; + return no_page_table(vma, flags); + } +retry: + if (!pmd_present(pmdval)) { + if (likely(!(flags & FOLL_MIGRATION))) + return no_page_table(vma, flags); + VM_BUG_ON(thp_migration_supported() && + !is_pmd_migration_entry(pmdval)); + if (is_pmd_migration_entry(pmdval)) + pmd_migration_entry_wait(mm, pmd); + pmdval = READ_ONCE(*pmd); + /* + * MADV_DONTNEED may convert the pmd to null because + * mmap_lock is held in read mode + */ + if (pmd_none(pmdval)) + return no_page_table(vma, flags); + goto retry; + } + if (pmd_devmap(pmdval)) { + ptl = pmd_lock(mm, pmd); + page = follow_devmap_pmd(vma, address, pmd, flags, &ctx->pgmap); + spin_unlock(ptl); + if (page) + return page; + } + if (likely(!pmd_trans_huge(pmdval))) + return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); + + if ((flags & FOLL_NUMA) && pmd_protnone(pmdval)) + return no_page_table(vma, flags); + +retry_locked: + ptl = pmd_lock(mm, pmd); + if (unlikely(pmd_none(*pmd))) { + spin_unlock(ptl); + return no_page_table(vma, flags); + } + if (unlikely(!pmd_present(*pmd))) { + spin_unlock(ptl); + if (likely(!(flags & FOLL_MIGRATION))) + return no_page_table(vma, flags); + pmd_migration_entry_wait(mm, pmd); + goto retry_locked; + } + if (unlikely(!pmd_trans_huge(*pmd))) { + spin_unlock(ptl); + return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); + } + if (flags & (FOLL_SPLIT | FOLL_SPLIT_PMD)) { + int ret; + page = pmd_page(*pmd); + if (is_huge_zero_page(page)) { + spin_unlock(ptl); + ret = 0; + split_huge_pmd(vma, pmd, address); + if (pmd_trans_unstable(pmd)) + ret = -EBUSY; + } else if (flags & FOLL_SPLIT) { + if (unlikely(!try_get_page(page))) { + spin_unlock(ptl); + return ERR_PTR(-ENOMEM); + } + spin_unlock(ptl); + lock_page(page); + ret = split_huge_page(page); + unlock_page(page); + put_page(page); + if (pmd_none(*pmd)) + return no_page_table(vma, flags); + } else { /* flags & FOLL_SPLIT_PMD */ + spin_unlock(ptl); + split_huge_pmd(vma, pmd, address); + ret = pte_alloc(mm, pmd) ? -ENOMEM : 0; + } + + return ret ? ERR_PTR(ret) : + follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); + } + page = follow_trans_huge_pmd(vma, address, pmd, flags); + spin_unlock(ptl); + ctx->page_mask = HPAGE_PMD_NR - 1; + return page; +} + +static struct page *follow_pud_mask(struct vm_area_struct *vma, + unsigned long address, p4d_t *p4dp, + unsigned int flags, + struct follow_page_context *ctx) +{ + pud_t *pud; + spinlock_t *ptl; + struct page *page; + struct mm_struct *mm = vma->vm_mm; + + pud = pud_offset(p4dp, address); + if (pud_none(*pud)) + return no_page_table(vma, flags); + if (pud_huge(*pud) && is_vm_hugetlb_page(vma)) { + page = follow_huge_pud(mm, address, pud, flags); + if (page) + return page; + return no_page_table(vma, flags); + } + if (is_hugepd(__hugepd(pud_val(*pud)))) { + page = follow_huge_pd(vma, address, + __hugepd(pud_val(*pud)), flags, + PUD_SHIFT); + if (page) + return page; + return no_page_table(vma, flags); + } + if (pud_devmap(*pud)) { + ptl = pud_lock(mm, pud); + page = follow_devmap_pud(vma, address, pud, flags, &ctx->pgmap); + spin_unlock(ptl); + if (page) + return page; + } + if (unlikely(pud_bad(*pud))) + return no_page_table(vma, flags); + + return follow_pmd_mask(vma, address, pud, flags, ctx); +} + +static struct page *follow_p4d_mask(struct vm_area_struct *vma, + unsigned long address, pgd_t *pgdp, + unsigned int flags, + struct follow_page_context *ctx) +{ + p4d_t *p4d; + struct page *page; + + p4d = p4d_offset(pgdp, address); + if (p4d_none(*p4d)) + return no_page_table(vma, flags); + BUILD_BUG_ON(p4d_huge(*p4d)); + if (unlikely(p4d_bad(*p4d))) + return no_page_table(vma, flags); + + if (is_hugepd(__hugepd(p4d_val(*p4d)))) { + page = follow_huge_pd(vma, address, + __hugepd(p4d_val(*p4d)), flags, + P4D_SHIFT); + if (page) + return page; + return no_page_table(vma, flags); + } + return follow_pud_mask(vma, address, p4d, flags, ctx); +} + +/** + * follow_page_mask - look up a page descriptor from a user-virtual address + * @vma: vm_area_struct mapping @address + * @address: virtual address to look up + * @flags: flags modifying lookup behaviour + * @ctx: contains dev_pagemap for %ZONE_DEVICE memory pinning and a + * pointer to output page_mask + * + * @flags can have FOLL_ flags set, defined in + * + * When getting pages from ZONE_DEVICE memory, the @ctx->pgmap caches + * the device's dev_pagemap metadata to avoid repeating expensive lookups. + * + * On output, the @ctx->page_mask is set according to the size of the page. + * + * Return: the mapped (struct page *), %NULL if no mapping exists, or + * an error pointer if there is a mapping to something not represented + * by a page descriptor (see also vm_normal_page()). + */ +static struct page *follow_page_mask(struct vm_area_struct *vma, + unsigned long address, unsigned int flags, + struct follow_page_context *ctx) +{ + pgd_t *pgd; + struct page *page; + struct mm_struct *mm = vma->vm_mm; + + ctx->page_mask = 0; + + /* make this handle hugepd */ + page = follow_huge_addr(mm, address, flags & FOLL_WRITE); + if (!IS_ERR(page)) { + WARN_ON_ONCE(flags & (FOLL_GET | FOLL_PIN)); + return page; + } + + pgd = pgd_offset(mm, address); + + if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) + return no_page_table(vma, flags); + + if (pgd_huge(*pgd)) { + page = follow_huge_pgd(mm, address, pgd, flags); + if (page) + return page; + return no_page_table(vma, flags); + } + if (is_hugepd(__hugepd(pgd_val(*pgd)))) { + page = follow_huge_pd(vma, address, + __hugepd(pgd_val(*pgd)), flags, + PGDIR_SHIFT); + if (page) + return page; + return no_page_table(vma, flags); + } + + return follow_p4d_mask(vma, address, pgd, flags, ctx); +} + +struct page *follow_page(struct vm_area_struct *vma, unsigned long address, + unsigned int foll_flags) +{ + struct follow_page_context ctx = { NULL }; + struct page *page; + + page = follow_page_mask(vma, address, foll_flags, &ctx); + if (ctx.pgmap) + put_dev_pagemap(ctx.pgmap); + return page; +} + +static int get_gate_page(struct mm_struct *mm, unsigned long address, + unsigned int gup_flags, struct vm_area_struct **vma, + struct page **page) +{ + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + int ret = -EFAULT; + + /* user gate pages are read-only */ + if (gup_flags & FOLL_WRITE) + return -EFAULT; + if (address > TASK_SIZE) + pgd = pgd_offset_k(address); + else + pgd = pgd_offset_gate(mm, address); + if (pgd_none(*pgd)) + return -EFAULT; + p4d = p4d_offset(pgd, address); + if (p4d_none(*p4d)) + return -EFAULT; + pud = pud_offset(p4d, address); + if (pud_none(*pud)) + return -EFAULT; + pmd = pmd_offset(pud, address); + if (!pmd_present(*pmd)) + return -EFAULT; + VM_BUG_ON(pmd_trans_huge(*pmd)); + pte = pte_offset_map(pmd, address); + if (pte_none(*pte)) + goto unmap; + *vma = get_gate_vma(mm); + if (!page) + goto out; + *page = vm_normal_page(*vma, address, *pte); + if (!*page) { + if ((gup_flags & FOLL_DUMP) || !is_zero_pfn(pte_pfn(*pte))) + goto unmap; + *page = pte_page(*pte); + } + if (unlikely(!try_grab_page(*page, gup_flags))) { + ret = -ENOMEM; + goto unmap; + } +out: + ret = 0; +unmap: + pte_unmap(pte); + return ret; +} + +/* + * mmap_lock must be held on entry. If @locked != NULL and *@flags + * does not include FOLL_NOWAIT, the mmap_lock may be released. If it + * is, *@locked will be set to 0 and -EBUSY returned. + */ +static int faultin_page(struct vm_area_struct *vma, + unsigned long address, unsigned int *flags, int *locked) +{ + unsigned int fault_flags = 0; + vm_fault_t ret; + + /* mlock all present pages, but do not fault in new pages */ + if ((*flags & (FOLL_POPULATE | FOLL_MLOCK)) == FOLL_MLOCK) + return -ENOENT; + if (*flags & FOLL_WRITE) + fault_flags |= FAULT_FLAG_WRITE; + if (*flags & FOLL_REMOTE) + fault_flags |= FAULT_FLAG_REMOTE; + if (locked) + fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + if (*flags & FOLL_NOWAIT) + fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT; + if (*flags & FOLL_TRIED) { + /* + * Note: FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_TRIED + * can co-exist + */ + fault_flags |= FAULT_FLAG_TRIED; + } + + ret = handle_mm_fault(vma, address, fault_flags, NULL); + if (ret & VM_FAULT_ERROR) { + int err = vm_fault_to_errno(ret, *flags); + + if (err) + return err; + BUG(); + } + + if (ret & VM_FAULT_RETRY) { + if (locked && !(fault_flags & FAULT_FLAG_RETRY_NOWAIT)) + *locked = 0; + return -EBUSY; + } + + /* + * The VM_FAULT_WRITE bit tells us that do_wp_page has broken COW when + * necessary, even if maybe_mkwrite decided not to set pte_write. We + * can thus safely do subsequent page lookups as if they were reads. + * But only do so when looping for pte_write is futile: in some cases + * userspace may also be wanting to write to the gotten user page, + * which a read fault here might prevent (a readonly page might get + * reCOWed by userspace write). + */ + if ((ret & VM_FAULT_WRITE) && !(vma->vm_flags & VM_WRITE)) + *flags |= FOLL_COW; + return 0; +} + +static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) +{ + vm_flags_t vm_flags = vma->vm_flags; + int write = (gup_flags & FOLL_WRITE); + int foreign = (gup_flags & FOLL_REMOTE); + + if (vm_flags & (VM_IO | VM_PFNMAP)) + return -EFAULT; + + if (gup_flags & FOLL_ANON && !vma_is_anonymous(vma)) + return -EFAULT; + + if (write) { + if (!(vm_flags & VM_WRITE)) { + if (!(gup_flags & FOLL_FORCE)) + return -EFAULT; + /* + * We used to let the write,force case do COW in a + * VM_MAYWRITE VM_SHARED !VM_WRITE vma, so ptrace could + * set a breakpoint in a read-only mapping of an + * executable, without corrupting the file (yet only + * when that file had been opened for writing!). + * Anon pages in shared mappings are surprising: now + * just reject it. + */ + if (!is_cow_mapping(vm_flags)) + return -EFAULT; + } + } else if (!(vm_flags & VM_READ)) { + if (!(gup_flags & FOLL_FORCE)) + return -EFAULT; + /* + * Is there actually any vma we can reach here which does not + * have VM_MAYREAD set? + */ + if (!(vm_flags & VM_MAYREAD)) + return -EFAULT; + } + /* + * gups are always data accesses, not instruction + * fetches, so execute=false here + */ + if (!arch_vma_access_permitted(vma, write, false, foreign)) + return -EFAULT; + return 0; +} + +/** + * __get_user_pages() - pin user pages in memory + * @mm: mm_struct of target mm + * @start: starting user address + * @nr_pages: number of pages from start to pin + * @gup_flags: flags modifying pin behaviour + * @pages: array that receives pointers to the pages pinned. + * Should be at least nr_pages long. Or NULL, if caller + * only intends to ensure the pages are faulted in. + * @vmas: array of pointers to vmas corresponding to each page. + * Or NULL if the caller does not require them. + * @locked: whether we're still with the mmap_lock held + * + * Returns either number of pages pinned (which may be less than the + * number requested), or an error. Details about the return value: + * + * -- If nr_pages is 0, returns 0. + * -- If nr_pages is >0, but no pages were pinned, returns -errno. + * -- If nr_pages is >0, and some pages were pinned, returns the number of + * pages pinned. Again, this may be less than nr_pages. + * -- 0 return value is possible when the fault would need to be retried. + * + * The caller is responsible for releasing returned @pages, via put_page(). + * + * @vmas are valid only as long as mmap_lock is held. + * + * Must be called with mmap_lock held. It may be released. See below. + * + * __get_user_pages walks a process's page tables and takes a reference to + * each struct page that each user address corresponds to at a given + * instant. That is, it takes the page that would be accessed if a user + * thread accesses the given user virtual address at that instant. + * + * This does not guarantee that the page exists in the user mappings when + * __get_user_pages returns, and there may even be a completely different + * page there in some cases (eg. if mmapped pagecache has been invalidated + * and subsequently re faulted). However it does guarantee that the page + * won't be freed completely. And mostly callers simply care that the page + * contains data that was valid *at some point in time*. Typically, an IO + * or similar operation cannot guarantee anything stronger anyway because + * locks can't be held over the syscall boundary. + * + * If @gup_flags & FOLL_WRITE == 0, the page must not be written to. If + * the page is written to, set_page_dirty (or set_page_dirty_lock, as + * appropriate) must be called after the page is finished with, and + * before put_page is called. + * + * If @locked != NULL, *@locked will be set to 0 when mmap_lock is + * released by an up_read(). That can happen if @gup_flags does not + * have FOLL_NOWAIT. + * + * A caller using such a combination of @locked and @gup_flags + * must therefore hold the mmap_lock for reading only, and recognize + * when it's been released. Otherwise, it must be held for either + * reading or writing and will not be released. + * + * In most cases, get_user_pages or get_user_pages_fast should be used + * instead of __get_user_pages. __get_user_pages should be used only if + * you need some special @gup_flags. + */ +static long __get_user_pages(struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas, int *locked) +{ + long ret = 0, i = 0; + struct vm_area_struct *vma = NULL; + struct follow_page_context ctx = { NULL }; + + if (!nr_pages) + return 0; + + start = untagged_addr(start); + + VM_BUG_ON(!!pages != !!(gup_flags & (FOLL_GET | FOLL_PIN))); + + /* + * If FOLL_FORCE is set then do not force a full fault as the hinting + * fault information is unrelated to the reference behaviour of a task + * using the address space + */ + if (!(gup_flags & FOLL_FORCE)) + gup_flags |= FOLL_NUMA; + + do { + struct page *page; + unsigned int foll_flags = gup_flags; + unsigned int page_increm; + + /* first iteration or cross vma bound */ + if (!vma || start >= vma->vm_end) { + vma = find_extend_vma(mm, start); + if (!vma && in_gate_area(mm, start)) { + ret = get_gate_page(mm, start & PAGE_MASK, + gup_flags, &vma, + pages ? &pages[i] : NULL); + if (ret) + goto out; + ctx.page_mask = 0; + goto next_page; + } + + if (!vma || check_vma_flags(vma, gup_flags)) { + ret = -EFAULT; + goto out; + } + if (is_vm_hugetlb_page(vma)) { + i = follow_hugetlb_page(mm, vma, pages, vmas, + &start, &nr_pages, i, + gup_flags, locked); + if (locked && *locked == 0) { + /* + * We've got a VM_FAULT_RETRY + * and we've lost mmap_lock. + * We must stop here. + */ + BUG_ON(gup_flags & FOLL_NOWAIT); + BUG_ON(ret != 0); + goto out; + } + continue; + } + } +retry: + /* + * If we have a pending SIGKILL, don't keep faulting pages and + * potentially allocating memory. + */ + if (fatal_signal_pending(current)) { + ret = -EINTR; + goto out; + } + cond_resched(); + + page = follow_page_mask(vma, start, foll_flags, &ctx); + if (!page) { + ret = faultin_page(vma, start, &foll_flags, locked); + switch (ret) { + case 0: + goto retry; + case -EBUSY: + ret = 0; + fallthrough; + case -EFAULT: + case -ENOMEM: + case -EHWPOISON: + goto out; + case -ENOENT: + goto next_page; + } + BUG(); + } else if (PTR_ERR(page) == -EEXIST) { + /* + * Proper page table entry exists, but no corresponding + * struct page. + */ + goto next_page; + } else if (IS_ERR(page)) { + ret = PTR_ERR(page); + goto out; + } + if (pages) { + pages[i] = page; + flush_anon_page(vma, page, start); + flush_dcache_page(page); + ctx.page_mask = 0; + } +next_page: + if (vmas) { + vmas[i] = vma; + ctx.page_mask = 0; + } + page_increm = 1 + (~(start >> PAGE_SHIFT) & ctx.page_mask); + if (page_increm > nr_pages) + page_increm = nr_pages; + i += page_increm; + start += page_increm * PAGE_SIZE; + nr_pages -= page_increm; + } while (nr_pages); +out: + if (ctx.pgmap) + put_dev_pagemap(ctx.pgmap); + return i ? i : ret; +} + +static bool vma_permits_fault(struct vm_area_struct *vma, + unsigned int fault_flags) +{ + bool write = !!(fault_flags & FAULT_FLAG_WRITE); + bool foreign = !!(fault_flags & FAULT_FLAG_REMOTE); + vm_flags_t vm_flags = write ? VM_WRITE : VM_READ; + + if (!(vm_flags & vma->vm_flags)) + return false; + + /* + * The architecture might have a hardware protection + * mechanism other than read/write that can deny access. + * + * gup always represents data access, not instruction + * fetches, so execute=false here: + */ + if (!arch_vma_access_permitted(vma, write, false, foreign)) + return false; + + return true; +} + +/** + * fixup_user_fault() - manually resolve a user page fault + * @mm: mm_struct of target mm + * @address: user address + * @fault_flags:flags to pass down to handle_mm_fault() + * @unlocked: did we unlock the mmap_lock while retrying, maybe NULL if caller + * does not allow retry. If NULL, the caller must guarantee + * that fault_flags does not contain FAULT_FLAG_ALLOW_RETRY. + * + * This is meant to be called in the specific scenario where for locking reasons + * we try to access user memory in atomic context (within a pagefault_disable() + * section), this returns -EFAULT, and we want to resolve the user fault before + * trying again. + * + * Typically this is meant to be used by the futex code. + * + * The main difference with get_user_pages() is that this function will + * unconditionally call handle_mm_fault() which will in turn perform all the + * necessary SW fixup of the dirty and young bits in the PTE, while + * get_user_pages() only guarantees to update these in the struct page. + * + * This is important for some architectures where those bits also gate the + * access permission to the page because they are maintained in software. On + * such architectures, gup() will not be enough to make a subsequent access + * succeed. + * + * This function will not return with an unlocked mmap_lock. So it has not the + * same semantics wrt the @mm->mmap_lock as does filemap_fault(). + */ +int fixup_user_fault(struct mm_struct *mm, + unsigned long address, unsigned int fault_flags, + bool *unlocked) +{ + struct vm_area_struct *vma; + vm_fault_t ret, major = 0; + + address = untagged_addr(address); + + if (unlocked) + fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + +retry: + vma = find_extend_vma(mm, address); + if (!vma || address < vma->vm_start) + return -EFAULT; + + if (!vma_permits_fault(vma, fault_flags)) + return -EFAULT; + + if ((fault_flags & FAULT_FLAG_KILLABLE) && + fatal_signal_pending(current)) + return -EINTR; + + ret = handle_mm_fault(vma, address, fault_flags, NULL); + major |= ret & VM_FAULT_MAJOR; + if (ret & VM_FAULT_ERROR) { + int err = vm_fault_to_errno(ret, 0); + + if (err) + return err; + BUG(); + } + + if (ret & VM_FAULT_RETRY) { + mmap_read_lock(mm); + *unlocked = true; + fault_flags |= FAULT_FLAG_TRIED; + goto retry; + } + + return 0; +} +EXPORT_SYMBOL_GPL(fixup_user_fault); + +/* + * Please note that this function, unlike __get_user_pages will not + * return 0 for nr_pages > 0 without FOLL_NOWAIT + */ +static __always_inline long __get_user_pages_locked(struct mm_struct *mm, + unsigned long start, + unsigned long nr_pages, + struct page **pages, + struct vm_area_struct **vmas, + int *locked, + unsigned int flags) +{ + long ret, pages_done; + bool lock_dropped; + + if (locked) { + /* if VM_FAULT_RETRY can be returned, vmas become invalid */ + BUG_ON(vmas); + /* check caller initialized locked */ + BUG_ON(*locked != 1); + } + + if (flags & FOLL_PIN) + atomic_set(&mm->has_pinned, 1); + + /* + * FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior + * is to set FOLL_GET if the caller wants pages[] filled in (but has + * carelessly failed to specify FOLL_GET), so keep doing that, but only + * for FOLL_GET, not for the newer FOLL_PIN. + * + * FOLL_PIN always expects pages to be non-null, but no need to assert + * that here, as any failures will be obvious enough. + */ + if (pages && !(flags & FOLL_PIN)) + flags |= FOLL_GET; + + pages_done = 0; + lock_dropped = false; + for (;;) { + ret = __get_user_pages(mm, start, nr_pages, flags, pages, + vmas, locked); + if (!locked) + /* VM_FAULT_RETRY couldn't trigger, bypass */ + return ret; + + /* VM_FAULT_RETRY cannot return errors */ + if (!*locked) { + BUG_ON(ret < 0); + BUG_ON(ret >= nr_pages); + } + + if (ret > 0) { + nr_pages -= ret; + pages_done += ret; + if (!nr_pages) + break; + } + if (*locked) { + /* + * VM_FAULT_RETRY didn't trigger or it was a + * FOLL_NOWAIT. + */ + if (!pages_done) + pages_done = ret; + break; + } + /* + * VM_FAULT_RETRY triggered, so seek to the faulting offset. + * For the prefault case (!pages) we only update counts. + */ + if (likely(pages)) + pages += ret; + start += ret << PAGE_SHIFT; + lock_dropped = true; + +retry: + /* + * Repeat on the address that fired VM_FAULT_RETRY + * with both FAULT_FLAG_ALLOW_RETRY and + * FAULT_FLAG_TRIED. Note that GUP can be interrupted + * by fatal signals, so we need to check it before we + * start trying again otherwise it can loop forever. + */ + + if (fatal_signal_pending(current)) { + if (!pages_done) + pages_done = -EINTR; + break; + } + + ret = mmap_read_lock_killable(mm); + if (ret) { + BUG_ON(ret > 0); + if (!pages_done) + pages_done = ret; + break; + } + + *locked = 1; + ret = __get_user_pages(mm, start, 1, flags | FOLL_TRIED, + pages, NULL, locked); + if (!*locked) { + /* Continue to retry until we succeeded */ + BUG_ON(ret != 0); + goto retry; + } + if (ret != 1) { + BUG_ON(ret > 1); + if (!pages_done) + pages_done = ret; + break; + } + nr_pages--; + pages_done++; + if (!nr_pages) + break; + if (likely(pages)) + pages++; + start += PAGE_SIZE; + } + if (lock_dropped && *locked) { + /* + * We must let the caller know we temporarily dropped the lock + * and so the critical section protected by it was lost. + */ + mmap_read_unlock(mm); + *locked = 0; + } + return pages_done; +} + +/** + * populate_vma_page_range() - populate a range of pages in the vma. + * @vma: target vma + * @start: start address + * @end: end address + * @locked: whether the mmap_lock is still held + * + * This takes care of mlocking the pages too if VM_LOCKED is set. + * + * Return either number of pages pinned in the vma, or a negative error + * code on error. + * + * vma->vm_mm->mmap_lock must be held. + * + * If @locked is NULL, it may be held for read or write and will + * be unperturbed. + * + * If @locked is non-NULL, it must held for read only and may be + * released. If it's released, *@locked will be set to 0. + */ +long populate_vma_page_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end, int *locked) +{ + struct mm_struct *mm = vma->vm_mm; + unsigned long nr_pages = (end - start) / PAGE_SIZE; + int gup_flags; + + VM_BUG_ON(start & ~PAGE_MASK); + VM_BUG_ON(end & ~PAGE_MASK); + VM_BUG_ON_VMA(start < vma->vm_start, vma); + VM_BUG_ON_VMA(end > vma->vm_end, vma); + mmap_assert_locked(mm); + + gup_flags = FOLL_TOUCH | FOLL_POPULATE | FOLL_MLOCK; + if (vma->vm_flags & VM_LOCKONFAULT) + gup_flags &= ~FOLL_POPULATE; + /* + * We want to touch writable mappings with a write fault in order + * to break COW, except for shared mappings because these don't COW + * and we would not want to dirty them for nothing. + */ + if ((vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE) + gup_flags |= FOLL_WRITE; + + /* + * We want mlock to succeed for regions that have any permissions + * other than PROT_NONE. + */ + if (vma_is_accessible(vma)) + gup_flags |= FOLL_FORCE; + + /* + * We made sure addr is within a VMA, so the following will + * not result in a stack expansion that recurses back here. + */ + return __get_user_pages(mm, start, nr_pages, gup_flags, + NULL, NULL, locked); +} + +/* + * __mm_populate - populate and/or mlock pages within a range of address space. + * + * This is used to implement mlock() and the MAP_POPULATE / MAP_LOCKED mmap + * flags. VMAs must be already marked with the desired vm_flags, and + * mmap_lock must not be held. + */ +int __mm_populate(unsigned long start, unsigned long len, int ignore_errors) +{ + struct mm_struct *mm = current->mm; + unsigned long end, nstart, nend; + struct vm_area_struct *vma = NULL; + int locked = 0; + long ret = 0; + + end = start + len; + + for (nstart = start; nstart < end; nstart = nend) { + /* + * We want to fault in pages for [nstart; end) address range. + * Find first corresponding VMA. + */ + if (!locked) { + locked = 1; + mmap_read_lock(mm); + vma = find_vma(mm, nstart); + } else if (nstart >= vma->vm_end) + vma = vma->vm_next; + if (!vma || vma->vm_start >= end) + break; + /* + * Set [nstart; nend) to intersection of desired address + * range with the first VMA. Also, skip undesirable VMA types. + */ + nend = min(end, vma->vm_end); + if (vma->vm_flags & (VM_IO | VM_PFNMAP)) + continue; + if (nstart < vma->vm_start) + nstart = vma->vm_start; + /* + * Now fault in a range of pages. populate_vma_page_range() + * double checks the vma flags, so that it won't mlock pages + * if the vma was already munlocked. + */ + ret = populate_vma_page_range(vma, nstart, nend, &locked); + if (ret < 0) { + if (ignore_errors) { + ret = 0; + continue; /* continue at next VMA */ + } + break; + } + nend = nstart + ret * PAGE_SIZE; + ret = 0; + } + if (locked) + mmap_read_unlock(mm); + return ret; /* 0 or negative error code */ +} +#else /* CONFIG_MMU */ +static long __get_user_pages_locked(struct mm_struct *mm, unsigned long start, + unsigned long nr_pages, struct page **pages, + struct vm_area_struct **vmas, int *locked, + unsigned int foll_flags) +{ + struct vm_area_struct *vma; + unsigned long vm_flags; + int i; + + /* calculate required read or write permissions. + * If FOLL_FORCE is set, we only require the "MAY" flags. + */ + vm_flags = (foll_flags & FOLL_WRITE) ? + (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD); + vm_flags &= (foll_flags & FOLL_FORCE) ? + (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE); + + for (i = 0; i < nr_pages; i++) { + vma = find_vma(mm, start); + if (!vma) + goto finish_or_fault; + + /* protect what we can, including chardevs */ + if ((vma->vm_flags & (VM_IO | VM_PFNMAP)) || + !(vm_flags & vma->vm_flags)) + goto finish_or_fault; + + if (pages) { + pages[i] = virt_to_page(start); + if (pages[i]) + get_page(pages[i]); + } + if (vmas) + vmas[i] = vma; + start = (start + PAGE_SIZE) & PAGE_MASK; + } + + return i; + +finish_or_fault: + return i ? : -EFAULT; +} +#endif /* !CONFIG_MMU */ + +/** + * get_dump_page() - pin user page in memory while writing it to core dump + * @addr: user address + * + * Returns struct page pointer of user page pinned for dump, + * to be freed afterwards by put_page(). + * + * Returns NULL on any kind of failure - a hole must then be inserted into + * the corefile, to preserve alignment with its headers; and also returns + * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found - + * allowing a hole to be left in the corefile to save diskspace. + * + * Called without mmap_lock (takes and releases the mmap_lock by itself). + */ +#ifdef CONFIG_ELF_CORE +struct page *get_dump_page(unsigned long addr) +{ + struct mm_struct *mm = current->mm; + struct page *page; + int locked = 1; + int ret; + + if (mmap_read_lock_killable(mm)) + return NULL; + ret = __get_user_pages_locked(mm, addr, 1, &page, NULL, &locked, + FOLL_FORCE | FOLL_DUMP | FOLL_GET); + if (locked) + mmap_read_unlock(mm); + return (ret == 1) ? page : NULL; +} +#endif /* CONFIG_ELF_CORE */ + +#if defined(CONFIG_FS_DAX) || defined (CONFIG_CMA) +static bool check_dax_vmas(struct vm_area_struct **vmas, long nr_pages) +{ + long i; + struct vm_area_struct *vma_prev = NULL; + + for (i = 0; i < nr_pages; i++) { + struct vm_area_struct *vma = vmas[i]; + + if (vma == vma_prev) + continue; + + vma_prev = vma; + + if (vma_is_fsdax(vma)) + return true; + } + return false; +} + +#ifdef CONFIG_CMA +static long check_and_migrate_cma_pages(struct mm_struct *mm, + unsigned long start, + unsigned long nr_pages, + struct page **pages, + struct vm_area_struct **vmas, + unsigned int gup_flags) +{ + unsigned long i, isolation_error_count; + bool drain_allow; + LIST_HEAD(cma_page_list); + long ret = nr_pages; + struct page *prev_head, *head; + struct migration_target_control mtc = { + .nid = NUMA_NO_NODE, + .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_NOWARN, + }; + +check_again: + prev_head = NULL; + isolation_error_count = 0; + drain_allow = true; + for (i = 0; i < nr_pages; i++) { + head = compound_head(pages[i]); + if (head == prev_head) + continue; + prev_head = head; + /* + * If we get a page from the CMA zone, since we are going to + * be pinning these entries, we might as well move them out + * of the CMA zone if possible. + */ + if (is_migrate_cma_page(head)) { + if (PageHuge(head)) { + if (isolate_hugetlb(head, &cma_page_list)) + isolation_error_count++; + } else { + if (!PageLRU(head) && drain_allow) { + lru_add_drain_all(); + drain_allow = false; + } + + if (isolate_lru_page(head)) { + isolation_error_count++; + continue; + } + list_add_tail(&head->lru, &cma_page_list); + mod_node_page_state(page_pgdat(head), + NR_ISOLATED_ANON + + page_is_file_lru(head), + thp_nr_pages(head)); + } + } + } + + /* + * If list is empty, and no isolation errors, means that all pages are + * in the correct zone. + */ + if (list_empty(&cma_page_list) && !isolation_error_count) + return ret; + + if (!list_empty(&cma_page_list)) { + /* + * drop the above get_user_pages reference. + */ + if (gup_flags & FOLL_PIN) + unpin_user_pages(pages, nr_pages); + else + for (i = 0; i < nr_pages; i++) + put_page(pages[i]); + + ret = migrate_pages(&cma_page_list, alloc_migration_target, + NULL, (unsigned long)&mtc, MIGRATE_SYNC, + MR_CONTIG_RANGE); + if (ret) { + if (!list_empty(&cma_page_list)) + putback_movable_pages(&cma_page_list); + return ret > 0 ? -ENOMEM : ret; + } + + /* We unpinned pages before migration, pin them again */ + ret = __get_user_pages_locked(mm, start, nr_pages, pages, vmas, + NULL, gup_flags); + if (ret <= 0) + return ret; + nr_pages = ret; + } + + /* + * check again because pages were unpinned, and we also might have + * had isolation errors and need more pages to migrate. + */ + goto check_again; +} +#else +static long check_and_migrate_cma_pages(struct mm_struct *mm, + unsigned long start, + unsigned long nr_pages, + struct page **pages, + struct vm_area_struct **vmas, + unsigned int gup_flags) +{ + return nr_pages; +} +#endif /* CONFIG_CMA */ + +/* + * __gup_longterm_locked() is a wrapper for __get_user_pages_locked which + * allows us to process the FOLL_LONGTERM flag. + */ +static long __gup_longterm_locked(struct mm_struct *mm, + unsigned long start, + unsigned long nr_pages, + struct page **pages, + struct vm_area_struct **vmas, + unsigned int gup_flags) +{ + struct vm_area_struct **vmas_tmp = vmas; + unsigned long flags = 0; + long rc, i; + + if (gup_flags & FOLL_LONGTERM) { + if (!pages) + return -EINVAL; + + if (!vmas_tmp) { + vmas_tmp = kcalloc(nr_pages, + sizeof(struct vm_area_struct *), + GFP_KERNEL); + if (!vmas_tmp) + return -ENOMEM; + } + flags = memalloc_nocma_save(); + } + + rc = __get_user_pages_locked(mm, start, nr_pages, pages, + vmas_tmp, NULL, gup_flags); + + if (gup_flags & FOLL_LONGTERM) { + if (rc < 0) + goto out; + + if (check_dax_vmas(vmas_tmp, rc)) { + if (gup_flags & FOLL_PIN) + unpin_user_pages(pages, rc); + else + for (i = 0; i < rc; i++) + put_page(pages[i]); + rc = -EOPNOTSUPP; + goto out; + } + + rc = check_and_migrate_cma_pages(mm, start, rc, pages, + vmas_tmp, gup_flags); +out: + memalloc_nocma_restore(flags); + } + + if (vmas_tmp != vmas) + kfree(vmas_tmp); + return rc; +} +#else /* !CONFIG_FS_DAX && !CONFIG_CMA */ +static __always_inline long __gup_longterm_locked(struct mm_struct *mm, + unsigned long start, + unsigned long nr_pages, + struct page **pages, + struct vm_area_struct **vmas, + unsigned int flags) +{ + return __get_user_pages_locked(mm, start, nr_pages, pages, vmas, + NULL, flags); +} +#endif /* CONFIG_FS_DAX || CONFIG_CMA */ + +static bool is_valid_gup_flags(unsigned int gup_flags) +{ + /* + * FOLL_PIN must only be set internally by the pin_user_pages*() APIs, + * never directly by the caller, so enforce that with an assertion: + */ + if (WARN_ON_ONCE(gup_flags & FOLL_PIN)) + return false; + /* + * FOLL_PIN is a prerequisite to FOLL_LONGTERM. Another way of saying + * that is, FOLL_LONGTERM is a specific case, more restrictive case of + * FOLL_PIN. + */ + if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM)) + return false; + + return true; +} + +#ifdef CONFIG_MMU +static long __get_user_pages_remote(struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas, int *locked) +{ + /* + * Parts of FOLL_LONGTERM behavior are incompatible with + * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on + * vmas. However, this only comes up if locked is set, and there are + * callers that do request FOLL_LONGTERM, but do not set locked. So, + * allow what we can. + */ + if (gup_flags & FOLL_LONGTERM) { + if (WARN_ON_ONCE(locked)) + return -EINVAL; + /* + * This will check the vmas (even if our vmas arg is NULL) + * and return -ENOTSUPP if DAX isn't allowed in this case: + */ + return __gup_longterm_locked(mm, start, nr_pages, pages, + vmas, gup_flags | FOLL_TOUCH | + FOLL_REMOTE); + } + + return __get_user_pages_locked(mm, start, nr_pages, pages, vmas, + locked, + gup_flags | FOLL_TOUCH | FOLL_REMOTE); +} + +/** + * get_user_pages_remote() - pin user pages in memory + * @mm: mm_struct of target mm + * @start: starting user address + * @nr_pages: number of pages from start to pin + * @gup_flags: flags modifying lookup behaviour + * @pages: array that receives pointers to the pages pinned. + * Should be at least nr_pages long. Or NULL, if caller + * only intends to ensure the pages are faulted in. + * @vmas: array of pointers to vmas corresponding to each page. + * Or NULL if the caller does not require them. + * @locked: pointer to lock flag indicating whether lock is held and + * subsequently whether VM_FAULT_RETRY functionality can be + * utilised. Lock must initially be held. + * + * Returns either number of pages pinned (which may be less than the + * number requested), or an error. Details about the return value: + * + * -- If nr_pages is 0, returns 0. + * -- If nr_pages is >0, but no pages were pinned, returns -errno. + * -- If nr_pages is >0, and some pages were pinned, returns the number of + * pages pinned. Again, this may be less than nr_pages. + * + * The caller is responsible for releasing returned @pages, via put_page(). + * + * @vmas are valid only as long as mmap_lock is held. + * + * Must be called with mmap_lock held for read or write. + * + * get_user_pages_remote walks a process's page tables and takes a reference + * to each struct page that each user address corresponds to at a given + * instant. That is, it takes the page that would be accessed if a user + * thread accesses the given user virtual address at that instant. + * + * This does not guarantee that the page exists in the user mappings when + * get_user_pages_remote returns, and there may even be a completely different + * page there in some cases (eg. if mmapped pagecache has been invalidated + * and subsequently re faulted). However it does guarantee that the page + * won't be freed completely. And mostly callers simply care that the page + * contains data that was valid *at some point in time*. Typically, an IO + * or similar operation cannot guarantee anything stronger anyway because + * locks can't be held over the syscall boundary. + * + * If gup_flags & FOLL_WRITE == 0, the page must not be written to. If the page + * is written to, set_page_dirty (or set_page_dirty_lock, as appropriate) must + * be called after the page is finished with, and before put_page is called. + * + * get_user_pages_remote is typically used for fewer-copy IO operations, + * to get a handle on the memory by some means other than accesses + * via the user virtual addresses. The pages may be submitted for + * DMA to devices or accessed via their kernel linear mapping (via the + * kmap APIs). Care should be taken to use the correct cache flushing APIs. + * + * See also get_user_pages_fast, for performance critical applications. + * + * get_user_pages_remote should be phased out in favor of + * get_user_pages_locked|unlocked or get_user_pages_fast. Nothing + * should use get_user_pages_remote because it cannot pass + * FAULT_FLAG_ALLOW_RETRY to handle_mm_fault. + */ +long get_user_pages_remote(struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas, int *locked) +{ + if (!is_valid_gup_flags(gup_flags)) + return -EINVAL; + + return __get_user_pages_remote(mm, start, nr_pages, gup_flags, + pages, vmas, locked); +} +EXPORT_SYMBOL(get_user_pages_remote); + +#else /* CONFIG_MMU */ +long get_user_pages_remote(struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas, int *locked) +{ + return 0; +} + +static long __get_user_pages_remote(struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas, int *locked) +{ + return 0; +} +#endif /* !CONFIG_MMU */ + +/** + * get_user_pages() - pin user pages in memory + * @start: starting user address + * @nr_pages: number of pages from start to pin + * @gup_flags: flags modifying lookup behaviour + * @pages: array that receives pointers to the pages pinned. + * Should be at least nr_pages long. Or NULL, if caller + * only intends to ensure the pages are faulted in. + * @vmas: array of pointers to vmas corresponding to each page. + * Or NULL if the caller does not require them. + * + * This is the same as get_user_pages_remote(), just with a less-flexible + * calling convention where we assume that the mm being operated on belongs to + * the current task, and doesn't allow passing of a locked parameter. We also + * obviously don't pass FOLL_REMOTE in here. + */ +long get_user_pages(unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas) +{ + if (!is_valid_gup_flags(gup_flags)) + return -EINVAL; + + return __gup_longterm_locked(current->mm, start, nr_pages, + pages, vmas, gup_flags | FOLL_TOUCH); +} +EXPORT_SYMBOL(get_user_pages); + +/** + * get_user_pages_locked() is suitable to replace the form: + * + * mmap_read_lock(mm); + * do_something() + * get_user_pages(mm, ..., pages, NULL); + * mmap_read_unlock(mm); + * + * to: + * + * int locked = 1; + * mmap_read_lock(mm); + * do_something() + * get_user_pages_locked(mm, ..., pages, &locked); + * if (locked) + * mmap_read_unlock(mm); + * + * @start: starting user address + * @nr_pages: number of pages from start to pin + * @gup_flags: flags modifying lookup behaviour + * @pages: array that receives pointers to the pages pinned. + * Should be at least nr_pages long. Or NULL, if caller + * only intends to ensure the pages are faulted in. + * @locked: pointer to lock flag indicating whether lock is held and + * subsequently whether VM_FAULT_RETRY functionality can be + * utilised. Lock must initially be held. + * + * We can leverage the VM_FAULT_RETRY functionality in the page fault + * paths better by using either get_user_pages_locked() or + * get_user_pages_unlocked(). + * + */ +long get_user_pages_locked(unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + int *locked) +{ + /* + * FIXME: Current FOLL_LONGTERM behavior is incompatible with + * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on + * vmas. As there are no users of this flag in this call we simply + * disallow this option for now. + */ + if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM)) + return -EINVAL; + /* + * FOLL_PIN must only be set internally by the pin_user_pages*() APIs, + * never directly by the caller, so enforce that: + */ + if (WARN_ON_ONCE(gup_flags & FOLL_PIN)) + return -EINVAL; + + return __get_user_pages_locked(current->mm, start, nr_pages, + pages, NULL, locked, + gup_flags | FOLL_TOUCH); +} +EXPORT_SYMBOL(get_user_pages_locked); + +/* + * get_user_pages_unlocked() is suitable to replace the form: + * + * mmap_read_lock(mm); + * get_user_pages(mm, ..., pages, NULL); + * mmap_read_unlock(mm); + * + * with: + * + * get_user_pages_unlocked(mm, ..., pages); + * + * It is functionally equivalent to get_user_pages_fast so + * get_user_pages_fast should be used instead if specific gup_flags + * (e.g. FOLL_FORCE) are not required. + */ +long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, + struct page **pages, unsigned int gup_flags) +{ + struct mm_struct *mm = current->mm; + int locked = 1; + long ret; + + /* + * FIXME: Current FOLL_LONGTERM behavior is incompatible with + * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on + * vmas. As there are no users of this flag in this call we simply + * disallow this option for now. + */ + if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM)) + return -EINVAL; + + mmap_read_lock(mm); + ret = __get_user_pages_locked(mm, start, nr_pages, pages, NULL, + &locked, gup_flags | FOLL_TOUCH); + if (locked) + mmap_read_unlock(mm); + return ret; +} +EXPORT_SYMBOL(get_user_pages_unlocked); + +/* + * Fast GUP + * + * get_user_pages_fast attempts to pin user pages by walking the page + * tables directly and avoids taking locks. Thus the walker needs to be + * protected from page table pages being freed from under it, and should + * block any THP splits. + * + * One way to achieve this is to have the walker disable interrupts, and + * rely on IPIs from the TLB flushing code blocking before the page table + * pages are freed. This is unsuitable for architectures that do not need + * to broadcast an IPI when invalidating TLBs. + * + * Another way to achieve this is to batch up page table containing pages + * belonging to more than one mm_user, then rcu_sched a callback to free those + * pages. Disabling interrupts will allow the fast_gup walker to both block + * the rcu_sched callback, and an IPI that we broadcast for splitting THPs + * (which is a relatively rare event). The code below adopts this strategy. + * + * Before activating this code, please be aware that the following assumptions + * are currently made: + * + * *) Either MMU_GATHER_RCU_TABLE_FREE is enabled, and tlb_remove_table() is used to + * free pages containing page tables or TLB flushing requires IPI broadcast. + * + * *) ptes can be read atomically by the architecture. + * + * *) access_ok is sufficient to validate userspace address ranges. + * + * The last two assumptions can be relaxed by the addition of helper functions. + * + * This code is based heavily on the PowerPC implementation by Nick Piggin. + */ +#ifdef CONFIG_HAVE_FAST_GUP +#ifdef CONFIG_GUP_GET_PTE_LOW_HIGH + +/* + * WARNING: only to be used in the get_user_pages_fast() implementation. + * + * With get_user_pages_fast(), we walk down the pagetables without taking any + * locks. For this we would like to load the pointers atomically, but sometimes + * that is not possible (e.g. without expensive cmpxchg8b on x86_32 PAE). What + * we do have is the guarantee that a PTE will only either go from not present + * to present, or present to not present or both -- it will not switch to a + * completely different present page without a TLB flush in between; something + * that we are blocking by holding interrupts off. + * + * Setting ptes from not present to present goes: + * + * ptep->pte_high = h; + * smp_wmb(); + * ptep->pte_low = l; + * + * And present to not present goes: + * + * ptep->pte_low = 0; + * smp_wmb(); + * ptep->pte_high = 0; + * + * We must ensure here that the load of pte_low sees 'l' IFF pte_high sees 'h'. + * We load pte_high *after* loading pte_low, which ensures we don't see an older + * value of pte_high. *Then* we recheck pte_low, which ensures that we haven't + * picked up a changed pte high. We might have gotten rubbish values from + * pte_low and pte_high, but we are guaranteed that pte_low will not have the + * present bit set *unless* it is 'l'. Because get_user_pages_fast() only + * operates on present ptes we're safe. + */ +static inline pte_t gup_get_pte(pte_t *ptep) +{ + pte_t pte; + + do { + pte.pte_low = ptep->pte_low; + smp_rmb(); + pte.pte_high = ptep->pte_high; + smp_rmb(); + } while (unlikely(pte.pte_low != ptep->pte_low)); + + return pte; +} +#else /* CONFIG_GUP_GET_PTE_LOW_HIGH */ +/* + * We require that the PTE can be read atomically. + */ +static inline pte_t gup_get_pte(pte_t *ptep) +{ + return ptep_get(ptep); +} +#endif /* CONFIG_GUP_GET_PTE_LOW_HIGH */ + +static void __maybe_unused undo_dev_pagemap(int *nr, int nr_start, + unsigned int flags, + struct page **pages) +{ + while ((*nr) - nr_start) { + struct page *page = pages[--(*nr)]; + + ClearPageReferenced(page); + if (flags & FOLL_PIN) + unpin_user_page(page); + else + put_page(page); + } +} + +#ifdef CONFIG_ARCH_HAS_PTE_SPECIAL +/* + * Fast-gup relies on pte change detection to avoid concurrent pgtable + * operations. + * + * To pin the page, fast-gup needs to do below in order: + * (1) pin the page (by prefetching pte), then (2) check pte not changed. + * + * For the rest of pgtable operations where pgtable updates can be racy + * with fast-gup, we need to do (1) clear pte, then (2) check whether page + * is pinned. + * + * Above will work for all pte-level operations, including THP split. + * + * For THP collapse, it's a bit more complicated because fast-gup may be + * walking a pgtable page that is being freed (pte is still valid but pmd + * can be cleared already). To avoid race in such condition, we need to + * also check pmd here to make sure pmd doesn't change (corresponds to + * pmdp_collapse_flush() in the THP collapse code path). + */ +static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, + unsigned long end, unsigned int flags, + struct page **pages, int *nr) +{ + struct dev_pagemap *pgmap = NULL; + int nr_start = *nr, ret = 0; + pte_t *ptep, *ptem; + + ptem = ptep = pte_offset_map(&pmd, addr); + do { + pte_t pte = gup_get_pte(ptep); + struct page *head, *page; + + /* + * Similar to the PMD case below, NUMA hinting must take slow + * path using the pte_protnone check. + */ + if (pte_protnone(pte)) + goto pte_unmap; + + if (!pte_access_permitted(pte, flags & FOLL_WRITE)) + goto pte_unmap; + + if (pte_devmap(pte)) { + if (unlikely(flags & FOLL_LONGTERM)) + goto pte_unmap; + + pgmap = get_dev_pagemap(pte_pfn(pte), pgmap); + if (unlikely(!pgmap)) { + undo_dev_pagemap(nr, nr_start, flags, pages); + goto pte_unmap; + } + } else if (pte_special(pte)) + goto pte_unmap; + + VM_BUG_ON(!pfn_valid(pte_pfn(pte))); + page = pte_page(pte); + + head = try_grab_compound_head(page, 1, flags); + if (!head) + goto pte_unmap; + + if (unlikely(pmd_val(pmd) != pmd_val(*pmdp)) || + unlikely(pte_val(pte) != pte_val(*ptep))) { + put_compound_head(head, 1, flags); + goto pte_unmap; + } + + VM_BUG_ON_PAGE(compound_head(page) != head, page); + + /* + * We need to make the page accessible if and only if we are + * going to access its content (the FOLL_PIN case). Please + * see Documentation/core-api/pin_user_pages.rst for + * details. + */ + if (flags & FOLL_PIN) { + ret = arch_make_page_accessible(page); + if (ret) { + unpin_user_page(page); + goto pte_unmap; + } + } + SetPageReferenced(page); + pages[*nr] = page; + (*nr)++; + + } while (ptep++, addr += PAGE_SIZE, addr != end); + + ret = 1; + +pte_unmap: + if (pgmap) + put_dev_pagemap(pgmap); + pte_unmap(ptem); + return ret; +} +#else + +/* + * If we can't determine whether or not a pte is special, then fail immediately + * for ptes. Note, we can still pin HugeTLB and THP as these are guaranteed not + * to be special. + * + * For a futex to be placed on a THP tail page, get_futex_key requires a + * get_user_pages_fast_only implementation that can pin pages. Thus it's still + * useful to have gup_huge_pmd even if we can't operate on ptes. + */ +static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, + unsigned long end, unsigned int flags, + struct page **pages, int *nr) +{ + return 0; +} +#endif /* CONFIG_ARCH_HAS_PTE_SPECIAL */ + +#if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && defined(CONFIG_TRANSPARENT_HUGEPAGE) +static int __gup_device_huge(unsigned long pfn, unsigned long addr, + unsigned long end, unsigned int flags, + struct page **pages, int *nr) +{ + int nr_start = *nr; + struct dev_pagemap *pgmap = NULL; + + do { + struct page *page = pfn_to_page(pfn); + + pgmap = get_dev_pagemap(pfn, pgmap); + if (unlikely(!pgmap)) { + undo_dev_pagemap(nr, nr_start, flags, pages); + return 0; + } + SetPageReferenced(page); + pages[*nr] = page; + if (unlikely(!try_grab_page(page, flags))) { + undo_dev_pagemap(nr, nr_start, flags, pages); + return 0; + } + (*nr)++; + pfn++; + } while (addr += PAGE_SIZE, addr != end); + + if (pgmap) + put_dev_pagemap(pgmap); + return 1; +} + +static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, + unsigned long end, unsigned int flags, + struct page **pages, int *nr) +{ + unsigned long fault_pfn; + int nr_start = *nr; + + fault_pfn = pmd_pfn(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); + if (!__gup_device_huge(fault_pfn, addr, end, flags, pages, nr)) + return 0; + + if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) { + undo_dev_pagemap(nr, nr_start, flags, pages); + return 0; + } + return 1; +} + +static int __gup_device_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, + unsigned long end, unsigned int flags, + struct page **pages, int *nr) +{ + unsigned long fault_pfn; + int nr_start = *nr; + + fault_pfn = pud_pfn(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); + if (!__gup_device_huge(fault_pfn, addr, end, flags, pages, nr)) + return 0; + + if (unlikely(pud_val(orig) != pud_val(*pudp))) { + undo_dev_pagemap(nr, nr_start, flags, pages); + return 0; + } + return 1; +} +#else +static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, + unsigned long end, unsigned int flags, + struct page **pages, int *nr) +{ + BUILD_BUG(); + return 0; +} + +static int __gup_device_huge_pud(pud_t pud, pud_t *pudp, unsigned long addr, + unsigned long end, unsigned int flags, + struct page **pages, int *nr) +{ + BUILD_BUG(); + return 0; +} +#endif + +static int record_subpages(struct page *page, unsigned long addr, + unsigned long end, struct page **pages) +{ + int nr; + + for (nr = 0; addr != end; addr += PAGE_SIZE) + pages[nr++] = page++; + + return nr; +} + +#ifdef CONFIG_ARCH_HAS_HUGEPD +static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end, + unsigned long sz) +{ + unsigned long __boundary = (addr + sz) & ~(sz-1); + return (__boundary - 1 < end - 1) ? __boundary : end; +} + +static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, + unsigned long end, unsigned int flags, + struct page **pages, int *nr) +{ + unsigned long pte_end; + struct page *head, *page; + pte_t pte; + int refs; + + pte_end = (addr + sz) & ~(sz-1); + if (pte_end < end) + end = pte_end; + + pte = huge_ptep_get(ptep); + + if (!pte_access_permitted(pte, flags & FOLL_WRITE)) + return 0; + + /* hugepages are never "special" */ + VM_BUG_ON(!pfn_valid(pte_pfn(pte))); + + head = pte_page(pte); + page = head + ((addr & (sz-1)) >> PAGE_SHIFT); + refs = record_subpages(page, addr, end, pages + *nr); + + head = try_grab_compound_head(head, refs, flags); + if (!head) + return 0; + + if (unlikely(pte_val(pte) != pte_val(*ptep))) { + put_compound_head(head, refs, flags); + return 0; + } + + *nr += refs; + SetPageReferenced(head); + return 1; +} + +static int gup_huge_pd(hugepd_t hugepd, unsigned long addr, + unsigned int pdshift, unsigned long end, unsigned int flags, + struct page **pages, int *nr) +{ + pte_t *ptep; + unsigned long sz = 1UL << hugepd_shift(hugepd); + unsigned long next; + + ptep = hugepte_offset(hugepd, addr, pdshift); + do { + next = hugepte_addr_end(addr, end, sz); + if (!gup_hugepte(ptep, sz, addr, end, flags, pages, nr)) + return 0; + } while (ptep++, addr = next, addr != end); + + return 1; +} +#else +static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr, + unsigned int pdshift, unsigned long end, unsigned int flags, + struct page **pages, int *nr) +{ + return 0; +} +#endif /* CONFIG_ARCH_HAS_HUGEPD */ + +static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, + unsigned long end, unsigned int flags, + struct page **pages, int *nr) +{ + struct page *head, *page; + int refs; + + if (!pmd_access_permitted(orig, flags & FOLL_WRITE)) + return 0; + + if (pmd_devmap(orig)) { + if (unlikely(flags & FOLL_LONGTERM)) + return 0; + return __gup_device_huge_pmd(orig, pmdp, addr, end, flags, + pages, nr); + } + + page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); + refs = record_subpages(page, addr, end, pages + *nr); + + head = try_grab_compound_head(pmd_page(orig), refs, flags); + if (!head) + return 0; + + if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) { + put_compound_head(head, refs, flags); + return 0; + } + + *nr += refs; + SetPageReferenced(head); + return 1; +} + +static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, + unsigned long end, unsigned int flags, + struct page **pages, int *nr) +{ + struct page *head, *page; + int refs; + + if (!pud_access_permitted(orig, flags & FOLL_WRITE)) + return 0; + + if (pud_devmap(orig)) { + if (unlikely(flags & FOLL_LONGTERM)) + return 0; + return __gup_device_huge_pud(orig, pudp, addr, end, flags, + pages, nr); + } + + page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); + refs = record_subpages(page, addr, end, pages + *nr); + + head = try_grab_compound_head(pud_page(orig), refs, flags); + if (!head) + return 0; + + if (unlikely(pud_val(orig) != pud_val(*pudp))) { + put_compound_head(head, refs, flags); + return 0; + } + + *nr += refs; + SetPageReferenced(head); + return 1; +} + +static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, + unsigned long end, unsigned int flags, + struct page **pages, int *nr) +{ + int refs; + struct page *head, *page; + + if (!pgd_access_permitted(orig, flags & FOLL_WRITE)) + return 0; + + BUILD_BUG_ON(pgd_devmap(orig)); + + page = pgd_page(orig) + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT); + refs = record_subpages(page, addr, end, pages + *nr); + + head = try_grab_compound_head(pgd_page(orig), refs, flags); + if (!head) + return 0; + + if (unlikely(pgd_val(orig) != pgd_val(*pgdp))) { + put_compound_head(head, refs, flags); + return 0; + } + + *nr += refs; + SetPageReferenced(head); + return 1; +} + +static int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, unsigned long end, + unsigned int flags, struct page **pages, int *nr) +{ + unsigned long next; + pmd_t *pmdp; + + pmdp = pmd_offset_lockless(pudp, pud, addr); + do { + pmd_t pmd = READ_ONCE(*pmdp); + + next = pmd_addr_end(addr, end); + if (!pmd_present(pmd)) + return 0; + + if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd) || + pmd_devmap(pmd))) { + /* + * NUMA hinting faults need to be handled in the GUP + * slowpath for accounting purposes and so that they + * can be serialised against THP migration. + */ + if (pmd_protnone(pmd)) + return 0; + + if (!gup_huge_pmd(pmd, pmdp, addr, next, flags, + pages, nr)) + return 0; + + } else if (unlikely(is_hugepd(__hugepd(pmd_val(pmd))))) { + /* + * architecture have different format for hugetlbfs + * pmd format and THP pmd format + */ + if (!gup_huge_pd(__hugepd(pmd_val(pmd)), addr, + PMD_SHIFT, next, flags, pages, nr)) + return 0; + } else if (!gup_pte_range(pmd, pmdp, addr, next, flags, pages, nr)) + return 0; + } while (pmdp++, addr = next, addr != end); + + return 1; +} + +static int gup_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, unsigned long end, + unsigned int flags, struct page **pages, int *nr) +{ + unsigned long next; + pud_t *pudp; + + pudp = pud_offset_lockless(p4dp, p4d, addr); + do { + pud_t pud = READ_ONCE(*pudp); + + next = pud_addr_end(addr, end); + if (unlikely(!pud_present(pud))) + return 0; + if (unlikely(pud_huge(pud) || pud_devmap(pud))) { + if (!gup_huge_pud(pud, pudp, addr, next, flags, + pages, nr)) + return 0; + } else if (unlikely(is_hugepd(__hugepd(pud_val(pud))))) { + if (!gup_huge_pd(__hugepd(pud_val(pud)), addr, + PUD_SHIFT, next, flags, pages, nr)) + return 0; + } else if (!gup_pmd_range(pudp, pud, addr, next, flags, pages, nr)) + return 0; + } while (pudp++, addr = next, addr != end); + + return 1; +} + +static int gup_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, unsigned long end, + unsigned int flags, struct page **pages, int *nr) +{ + unsigned long next; + p4d_t *p4dp; + + p4dp = p4d_offset_lockless(pgdp, pgd, addr); + do { + p4d_t p4d = READ_ONCE(*p4dp); + + next = p4d_addr_end(addr, end); + if (p4d_none(p4d)) + return 0; + BUILD_BUG_ON(p4d_huge(p4d)); + if (unlikely(is_hugepd(__hugepd(p4d_val(p4d))))) { + if (!gup_huge_pd(__hugepd(p4d_val(p4d)), addr, + P4D_SHIFT, next, flags, pages, nr)) + return 0; + } else if (!gup_pud_range(p4dp, p4d, addr, next, flags, pages, nr)) + return 0; + } while (p4dp++, addr = next, addr != end); + + return 1; +} + +static void gup_pgd_range(unsigned long addr, unsigned long end, + unsigned int flags, struct page **pages, int *nr) +{ + unsigned long next; + pgd_t *pgdp; + + pgdp = pgd_offset(current->mm, addr); + do { + pgd_t pgd = READ_ONCE(*pgdp); + + next = pgd_addr_end(addr, end); + if (pgd_none(pgd)) + return; + if (unlikely(pgd_huge(pgd))) { + if (!gup_huge_pgd(pgd, pgdp, addr, next, flags, + pages, nr)) + return; + } else if (unlikely(is_hugepd(__hugepd(pgd_val(pgd))))) { + if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr, + PGDIR_SHIFT, next, flags, pages, nr)) + return; + } else if (!gup_p4d_range(pgdp, pgd, addr, next, flags, pages, nr)) + return; + } while (pgdp++, addr = next, addr != end); +} +#else +static inline void gup_pgd_range(unsigned long addr, unsigned long end, + unsigned int flags, struct page **pages, int *nr) +{ +} +#endif /* CONFIG_HAVE_FAST_GUP */ + +#ifndef gup_fast_permitted +/* + * Check if it's allowed to use get_user_pages_fast_only() for the range, or + * we need to fall back to the slow version: + */ +static bool gup_fast_permitted(unsigned long start, unsigned long end) +{ + return true; +} +#endif + +static int __gup_longterm_unlocked(unsigned long start, int nr_pages, + unsigned int gup_flags, struct page **pages) +{ + int ret; + + /* + * FIXME: FOLL_LONGTERM does not work with + * get_user_pages_unlocked() (see comments in that function) + */ + if (gup_flags & FOLL_LONGTERM) { + mmap_read_lock(current->mm); + ret = __gup_longterm_locked(current->mm, + start, nr_pages, + pages, NULL, gup_flags); + mmap_read_unlock(current->mm); + } else { + ret = get_user_pages_unlocked(start, nr_pages, + pages, gup_flags); + } + + return ret; +} + +static unsigned long lockless_pages_from_mm(unsigned long start, + unsigned long end, + unsigned int gup_flags, + struct page **pages) +{ + unsigned long flags; + int nr_pinned = 0; + unsigned seq; + + if (!IS_ENABLED(CONFIG_HAVE_FAST_GUP) || + !gup_fast_permitted(start, end)) + return 0; + + if (gup_flags & FOLL_PIN) { + seq = raw_read_seqcount(¤t->mm->write_protect_seq); + if (seq & 1) + return 0; + } + + /* + * Disable interrupts. The nested form is used, in order to allow full, + * general purpose use of this routine. + * + * With interrupts disabled, we block page table pages from being freed + * from under us. See struct mmu_table_batch comments in + * include/asm-generic/tlb.h for more details. + * + * We do not adopt an rcu_read_lock() here as we also want to block IPIs + * that come from THPs splitting. + */ + local_irq_save(flags); + gup_pgd_range(start, end, gup_flags, pages, &nr_pinned); + local_irq_restore(flags); + + /* + * When pinning pages for DMA there could be a concurrent write protect + * from fork() via copy_page_range(), in this case always fail fast GUP. + */ + if (gup_flags & FOLL_PIN) { + if (read_seqcount_retry(¤t->mm->write_protect_seq, seq)) { + unpin_user_pages(pages, nr_pinned); + return 0; + } + } + return nr_pinned; +} + +static int internal_get_user_pages_fast(unsigned long start, + unsigned long nr_pages, + unsigned int gup_flags, + struct page **pages) +{ + unsigned long len, end; + unsigned long nr_pinned; + int ret; + + if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM | + FOLL_FORCE | FOLL_PIN | FOLL_GET | + FOLL_FAST_ONLY))) + return -EINVAL; + + if (gup_flags & FOLL_PIN) + atomic_set(¤t->mm->has_pinned, 1); + + if (!(gup_flags & FOLL_FAST_ONLY)) + might_lock_read(¤t->mm->mmap_lock); + + start = untagged_addr(start) & PAGE_MASK; + len = nr_pages << PAGE_SHIFT; + if (check_add_overflow(start, len, &end)) + return 0; + if (unlikely(!access_ok((void __user *)start, len))) + return -EFAULT; + + nr_pinned = lockless_pages_from_mm(start, end, gup_flags, pages); + if (nr_pinned == nr_pages || gup_flags & FOLL_FAST_ONLY) + return nr_pinned; + + /* Slow path: try to get the remaining pages with get_user_pages */ + start += nr_pinned << PAGE_SHIFT; + pages += nr_pinned; + ret = __gup_longterm_unlocked(start, nr_pages - nr_pinned, gup_flags, + pages); + if (ret < 0) { + /* + * The caller has to unpin the pages we already pinned so + * returning -errno is not an option + */ + if (nr_pinned) + return nr_pinned; + return ret; + } + return ret + nr_pinned; +} + +/** + * get_user_pages_fast_only() - pin user pages in memory + * @start: starting user address + * @nr_pages: number of pages from start to pin + * @gup_flags: flags modifying pin behaviour + * @pages: array that receives pointers to the pages pinned. + * Should be at least nr_pages long. + * + * Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to + * the regular GUP. + * Note a difference with get_user_pages_fast: this always returns the + * number of pages pinned, 0 if no pages were pinned. + * + * If the architecture does not support this function, simply return with no + * pages pinned. + * + * Careful, careful! COW breaking can go either way, so a non-write + * access can get ambiguous page results. If you call this function without + * 'write' set, you'd better be sure that you're ok with that ambiguity. + */ +int get_user_pages_fast_only(unsigned long start, int nr_pages, + unsigned int gup_flags, struct page **pages) +{ + int nr_pinned; + /* + * Internally (within mm/gup.c), gup fast variants must set FOLL_GET, + * because gup fast is always a "pin with a +1 page refcount" request. + * + * FOLL_FAST_ONLY is required in order to match the API description of + * this routine: no fall back to regular ("slow") GUP. + */ + gup_flags |= FOLL_GET | FOLL_FAST_ONLY; + + nr_pinned = internal_get_user_pages_fast(start, nr_pages, gup_flags, + pages); + + /* + * As specified in the API description above, this routine is not + * allowed to return negative values. However, the common core + * routine internal_get_user_pages_fast() *can* return -errno. + * Therefore, correct for that here: + */ + if (nr_pinned < 0) + nr_pinned = 0; + + return nr_pinned; +} +EXPORT_SYMBOL_GPL(get_user_pages_fast_only); + +/** + * get_user_pages_fast() - pin user pages in memory + * @start: starting user address + * @nr_pages: number of pages from start to pin + * @gup_flags: flags modifying pin behaviour + * @pages: array that receives pointers to the pages pinned. + * Should be at least nr_pages long. + * + * Attempt to pin user pages in memory without taking mm->mmap_lock. + * If not successful, it will fall back to taking the lock and + * calling get_user_pages(). + * + * Returns number of pages pinned. This may be fewer than the number requested. + * If nr_pages is 0 or negative, returns 0. If no pages were pinned, returns + * -errno. + */ +int get_user_pages_fast(unsigned long start, int nr_pages, + unsigned int gup_flags, struct page **pages) +{ + if (!is_valid_gup_flags(gup_flags)) + return -EINVAL; + + /* + * The caller may or may not have explicitly set FOLL_GET; either way is + * OK. However, internally (within mm/gup.c), gup fast variants must set + * FOLL_GET, because gup fast is always a "pin with a +1 page refcount" + * request. + */ + gup_flags |= FOLL_GET; + return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages); +} +EXPORT_SYMBOL_GPL(get_user_pages_fast); + +/** + * pin_user_pages_fast() - pin user pages in memory without taking locks + * + * @start: starting user address + * @nr_pages: number of pages from start to pin + * @gup_flags: flags modifying pin behaviour + * @pages: array that receives pointers to the pages pinned. + * Should be at least nr_pages long. + * + * Nearly the same as get_user_pages_fast(), except that FOLL_PIN is set. See + * get_user_pages_fast() for documentation on the function arguments, because + * the arguments here are identical. + * + * FOLL_PIN means that the pages must be released via unpin_user_page(). Please + * see Documentation/core-api/pin_user_pages.rst for further details. + */ +int pin_user_pages_fast(unsigned long start, int nr_pages, + unsigned int gup_flags, struct page **pages) +{ + /* FOLL_GET and FOLL_PIN are mutually exclusive. */ + if (WARN_ON_ONCE(gup_flags & FOLL_GET)) + return -EINVAL; + + gup_flags |= FOLL_PIN; + return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages); +} +EXPORT_SYMBOL_GPL(pin_user_pages_fast); + +/* + * This is the FOLL_PIN equivalent of get_user_pages_fast_only(). Behavior + * is the same, except that this one sets FOLL_PIN instead of FOLL_GET. + * + * The API rules are the same, too: no negative values may be returned. + */ +int pin_user_pages_fast_only(unsigned long start, int nr_pages, + unsigned int gup_flags, struct page **pages) +{ + int nr_pinned; + + /* + * FOLL_GET and FOLL_PIN are mutually exclusive. Note that the API + * rules require returning 0, rather than -errno: + */ + if (WARN_ON_ONCE(gup_flags & FOLL_GET)) + return 0; + /* + * FOLL_FAST_ONLY is required in order to match the API description of + * this routine: no fall back to regular ("slow") GUP. + */ + gup_flags |= (FOLL_PIN | FOLL_FAST_ONLY); + nr_pinned = internal_get_user_pages_fast(start, nr_pages, gup_flags, + pages); + /* + * This routine is not allowed to return negative values. However, + * internal_get_user_pages_fast() *can* return -errno. Therefore, + * correct for that here: + */ + if (nr_pinned < 0) + nr_pinned = 0; + + return nr_pinned; +} +EXPORT_SYMBOL_GPL(pin_user_pages_fast_only); + +/** + * pin_user_pages_remote() - pin pages of a remote process + * + * @mm: mm_struct of target mm + * @start: starting user address + * @nr_pages: number of pages from start to pin + * @gup_flags: flags modifying lookup behaviour + * @pages: array that receives pointers to the pages pinned. + * Should be at least nr_pages long. Or NULL, if caller + * only intends to ensure the pages are faulted in. + * @vmas: array of pointers to vmas corresponding to each page. + * Or NULL if the caller does not require them. + * @locked: pointer to lock flag indicating whether lock is held and + * subsequently whether VM_FAULT_RETRY functionality can be + * utilised. Lock must initially be held. + * + * Nearly the same as get_user_pages_remote(), except that FOLL_PIN is set. See + * get_user_pages_remote() for documentation on the function arguments, because + * the arguments here are identical. + * + * FOLL_PIN means that the pages must be released via unpin_user_page(). Please + * see Documentation/core-api/pin_user_pages.rst for details. + */ +long pin_user_pages_remote(struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas, int *locked) +{ + /* FOLL_GET and FOLL_PIN are mutually exclusive. */ + if (WARN_ON_ONCE(gup_flags & FOLL_GET)) + return -EINVAL; + + gup_flags |= FOLL_PIN; + return __get_user_pages_remote(mm, start, nr_pages, gup_flags, + pages, vmas, locked); +} +EXPORT_SYMBOL(pin_user_pages_remote); + +/** + * pin_user_pages() - pin user pages in memory for use by other devices + * + * @start: starting user address + * @nr_pages: number of pages from start to pin + * @gup_flags: flags modifying lookup behaviour + * @pages: array that receives pointers to the pages pinned. + * Should be at least nr_pages long. Or NULL, if caller + * only intends to ensure the pages are faulted in. + * @vmas: array of pointers to vmas corresponding to each page. + * Or NULL if the caller does not require them. + * + * Nearly the same as get_user_pages(), except that FOLL_TOUCH is not set, and + * FOLL_PIN is set. + * + * FOLL_PIN means that the pages must be released via unpin_user_page(). Please + * see Documentation/core-api/pin_user_pages.rst for details. + */ +long pin_user_pages(unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas) +{ + /* FOLL_GET and FOLL_PIN are mutually exclusive. */ + if (WARN_ON_ONCE(gup_flags & FOLL_GET)) + return -EINVAL; + + gup_flags |= FOLL_PIN; + return __gup_longterm_locked(current->mm, start, nr_pages, + pages, vmas, gup_flags); +} +EXPORT_SYMBOL(pin_user_pages); + +/* + * pin_user_pages_unlocked() is the FOLL_PIN variant of + * get_user_pages_unlocked(). Behavior is the same, except that this one sets + * FOLL_PIN and rejects FOLL_GET. + */ +long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, + struct page **pages, unsigned int gup_flags) +{ + /* FOLL_GET and FOLL_PIN are mutually exclusive. */ + if (WARN_ON_ONCE(gup_flags & FOLL_GET)) + return -EINVAL; + + gup_flags |= FOLL_PIN; + return get_user_pages_unlocked(start, nr_pages, pages, gup_flags); +} +EXPORT_SYMBOL(pin_user_pages_unlocked); + +/* + * pin_user_pages_locked() is the FOLL_PIN variant of get_user_pages_locked(). + * Behavior is the same, except that this one sets FOLL_PIN and rejects + * FOLL_GET. + */ +long pin_user_pages_locked(unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + int *locked) +{ + /* + * FIXME: Current FOLL_LONGTERM behavior is incompatible with + * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on + * vmas. As there are no users of this flag in this call we simply + * disallow this option for now. + */ + if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM)) + return -EINVAL; + + /* FOLL_GET and FOLL_PIN are mutually exclusive. */ + if (WARN_ON_ONCE(gup_flags & FOLL_GET)) + return -EINVAL; + + gup_flags |= FOLL_PIN; + return __get_user_pages_locked(current->mm, start, nr_pages, + pages, NULL, locked, + gup_flags | FOLL_TOUCH); +} +EXPORT_SYMBOL(pin_user_pages_locked); diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c new file mode 100644 index 000000000..8b3e5b5cd --- /dev/null +++ b/mm/gup_benchmark.c @@ -0,0 +1,210 @@ +#include +#include +#include +#include +#include +#include + +#define GUP_FAST_BENCHMARK _IOWR('g', 1, struct gup_benchmark) +#define GUP_BENCHMARK _IOWR('g', 2, struct gup_benchmark) +#define PIN_FAST_BENCHMARK _IOWR('g', 3, struct gup_benchmark) +#define PIN_BENCHMARK _IOWR('g', 4, struct gup_benchmark) +#define PIN_LONGTERM_BENCHMARK _IOWR('g', 5, struct gup_benchmark) + +struct gup_benchmark { + __u64 get_delta_usec; + __u64 put_delta_usec; + __u64 addr; + __u64 size; + __u32 nr_pages_per_call; + __u32 flags; + __u64 expansion[10]; /* For future use */ +}; + +static void put_back_pages(unsigned int cmd, struct page **pages, + unsigned long nr_pages) +{ + unsigned long i; + + switch (cmd) { + case GUP_FAST_BENCHMARK: + case GUP_BENCHMARK: + for (i = 0; i < nr_pages; i++) + put_page(pages[i]); + break; + + case PIN_FAST_BENCHMARK: + case PIN_BENCHMARK: + case PIN_LONGTERM_BENCHMARK: + unpin_user_pages(pages, nr_pages); + break; + } +} + +static void verify_dma_pinned(unsigned int cmd, struct page **pages, + unsigned long nr_pages) +{ + unsigned long i; + struct page *page; + + switch (cmd) { + case PIN_FAST_BENCHMARK: + case PIN_BENCHMARK: + case PIN_LONGTERM_BENCHMARK: + for (i = 0; i < nr_pages; i++) { + page = pages[i]; + if (WARN(!page_maybe_dma_pinned(page), + "pages[%lu] is NOT dma-pinned\n", i)) { + + dump_page(page, "gup_benchmark failure"); + break; + } + } + break; + } +} + +static int __gup_benchmark_ioctl(unsigned int cmd, + struct gup_benchmark *gup) +{ + ktime_t start_time, end_time; + unsigned long i, nr_pages, addr, next; + int nr; + struct page **pages; + int ret = 0; + bool needs_mmap_lock = + cmd != GUP_FAST_BENCHMARK && cmd != PIN_FAST_BENCHMARK; + + if (gup->size > ULONG_MAX) + return -EINVAL; + + nr_pages = gup->size / PAGE_SIZE; + pages = kvcalloc(nr_pages, sizeof(void *), GFP_KERNEL); + if (!pages) + return -ENOMEM; + + if (needs_mmap_lock && mmap_read_lock_killable(current->mm)) { + ret = -EINTR; + goto free_pages; + } + + i = 0; + nr = gup->nr_pages_per_call; + start_time = ktime_get(); + for (addr = gup->addr; addr < gup->addr + gup->size; addr = next) { + if (nr != gup->nr_pages_per_call) + break; + + next = addr + nr * PAGE_SIZE; + if (next > gup->addr + gup->size) { + next = gup->addr + gup->size; + nr = (next - addr) / PAGE_SIZE; + } + + /* Filter out most gup flags: only allow a tiny subset here: */ + gup->flags &= FOLL_WRITE; + + switch (cmd) { + case GUP_FAST_BENCHMARK: + nr = get_user_pages_fast(addr, nr, gup->flags, + pages + i); + break; + case GUP_BENCHMARK: + nr = get_user_pages(addr, nr, gup->flags, pages + i, + NULL); + break; + case PIN_FAST_BENCHMARK: + nr = pin_user_pages_fast(addr, nr, gup->flags, + pages + i); + break; + case PIN_BENCHMARK: + nr = pin_user_pages(addr, nr, gup->flags, pages + i, + NULL); + break; + case PIN_LONGTERM_BENCHMARK: + nr = pin_user_pages(addr, nr, + gup->flags | FOLL_LONGTERM, + pages + i, NULL); + break; + default: + ret = -EINVAL; + goto unlock; + } + + if (nr <= 0) + break; + i += nr; + } + end_time = ktime_get(); + + /* Shifting the meaning of nr_pages: now it is actual number pinned: */ + nr_pages = i; + + gup->get_delta_usec = ktime_us_delta(end_time, start_time); + gup->size = addr - gup->addr; + + /* + * Take an un-benchmark-timed moment to verify DMA pinned + * state: print a warning if any non-dma-pinned pages are found: + */ + verify_dma_pinned(cmd, pages, nr_pages); + + start_time = ktime_get(); + + put_back_pages(cmd, pages, nr_pages); + + end_time = ktime_get(); + gup->put_delta_usec = ktime_us_delta(end_time, start_time); + +unlock: + if (needs_mmap_lock) + mmap_read_unlock(current->mm); +free_pages: + kvfree(pages); + return ret; +} + +static long gup_benchmark_ioctl(struct file *filep, unsigned int cmd, + unsigned long arg) +{ + struct gup_benchmark gup; + int ret; + + switch (cmd) { + case GUP_FAST_BENCHMARK: + case GUP_BENCHMARK: + case PIN_FAST_BENCHMARK: + case PIN_BENCHMARK: + case PIN_LONGTERM_BENCHMARK: + break; + default: + return -EINVAL; + } + + if (copy_from_user(&gup, (void __user *)arg, sizeof(gup))) + return -EFAULT; + + ret = __gup_benchmark_ioctl(cmd, &gup); + if (ret) + return ret; + + if (copy_to_user((void __user *)arg, &gup, sizeof(gup))) + return -EFAULT; + + return 0; +} + +static const struct file_operations gup_benchmark_fops = { + .open = nonseekable_open, + .unlocked_ioctl = gup_benchmark_ioctl, +}; + +static int gup_benchmark_init(void) +{ + debugfs_create_file_unsafe("gup_benchmark", 0600, NULL, NULL, + &gup_benchmark_fops); + + return 0; +} + +late_initcall(gup_benchmark_init); diff --git a/mm/highmem.c b/mm/highmem.c new file mode 100644 index 000000000..1352a2795 --- /dev/null +++ b/mm/highmem.c @@ -0,0 +1,484 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * High memory handling common code and variables. + * + * (C) 1999 Andrea Arcangeli, SuSE GmbH, andrea@suse.de + * Gerhard Wichert, Siemens AG, Gerhard.Wichert@pdb.siemens.de + * + * + * Redesigned the x86 32-bit VM architecture to deal with + * 64-bit physical space. With current x86 CPUs this + * means up to 64 Gigabytes physical RAM. + * + * Rewrote high memory support to move the page cache into + * high memory. Implemented permanent (schedulable) kmaps + * based on Linus' idea. + * + * Copyright (C) 1999 Ingo Molnar + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32) +DEFINE_PER_CPU(int, __kmap_atomic_idx); +#endif + +/* + * Virtual_count is not a pure "count". + * 0 means that it is not mapped, and has not been mapped + * since a TLB flush - it is usable. + * 1 means that there are no users, but it has been mapped + * since the last TLB flush - so we can't use it. + * n means that there are (n-1) current users of it. + */ +#ifdef CONFIG_HIGHMEM + +/* + * Architecture with aliasing data cache may define the following family of + * helper functions in its asm/highmem.h to control cache color of virtual + * addresses where physical memory pages are mapped by kmap. + */ +#ifndef get_pkmap_color + +/* + * Determine color of virtual address where the page should be mapped. + */ +static inline unsigned int get_pkmap_color(struct page *page) +{ + return 0; +} +#define get_pkmap_color get_pkmap_color + +/* + * Get next index for mapping inside PKMAP region for page with given color. + */ +static inline unsigned int get_next_pkmap_nr(unsigned int color) +{ + static unsigned int last_pkmap_nr; + + last_pkmap_nr = (last_pkmap_nr + 1) & LAST_PKMAP_MASK; + return last_pkmap_nr; +} + +/* + * Determine if page index inside PKMAP region (pkmap_nr) of given color + * has wrapped around PKMAP region end. When this happens an attempt to + * flush all unused PKMAP slots is made. + */ +static inline int no_more_pkmaps(unsigned int pkmap_nr, unsigned int color) +{ + return pkmap_nr == 0; +} + +/* + * Get the number of PKMAP entries of the given color. If no free slot is + * found after checking that many entries, kmap will sleep waiting for + * someone to call kunmap and free PKMAP slot. + */ +static inline int get_pkmap_entries_count(unsigned int color) +{ + return LAST_PKMAP; +} + +/* + * Get head of a wait queue for PKMAP entries of the given color. + * Wait queues for different mapping colors should be independent to avoid + * unnecessary wakeups caused by freeing of slots of other colors. + */ +static inline wait_queue_head_t *get_pkmap_wait_queue_head(unsigned int color) +{ + static DECLARE_WAIT_QUEUE_HEAD(pkmap_map_wait); + + return &pkmap_map_wait; +} +#endif + +atomic_long_t _totalhigh_pages __read_mostly; +EXPORT_SYMBOL(_totalhigh_pages); + +EXPORT_PER_CPU_SYMBOL(__kmap_atomic_idx); + +unsigned int nr_free_highpages (void) +{ + struct zone *zone; + unsigned int pages = 0; + + for_each_populated_zone(zone) { + if (is_highmem(zone)) + pages += zone_page_state(zone, NR_FREE_PAGES); + } + + return pages; +} + +static int pkmap_count[LAST_PKMAP]; +static __cacheline_aligned_in_smp DEFINE_SPINLOCK(kmap_lock); + +pte_t * pkmap_page_table; + +/* + * Most architectures have no use for kmap_high_get(), so let's abstract + * the disabling of IRQ out of the locking in that case to save on a + * potential useless overhead. + */ +#ifdef ARCH_NEEDS_KMAP_HIGH_GET +#define lock_kmap() spin_lock_irq(&kmap_lock) +#define unlock_kmap() spin_unlock_irq(&kmap_lock) +#define lock_kmap_any(flags) spin_lock_irqsave(&kmap_lock, flags) +#define unlock_kmap_any(flags) spin_unlock_irqrestore(&kmap_lock, flags) +#else +#define lock_kmap() spin_lock(&kmap_lock) +#define unlock_kmap() spin_unlock(&kmap_lock) +#define lock_kmap_any(flags) \ + do { spin_lock(&kmap_lock); (void)(flags); } while (0) +#define unlock_kmap_any(flags) \ + do { spin_unlock(&kmap_lock); (void)(flags); } while (0) +#endif + +struct page *kmap_to_page(void *vaddr) +{ + unsigned long addr = (unsigned long)vaddr; + + if (addr >= PKMAP_ADDR(0) && addr < PKMAP_ADDR(LAST_PKMAP)) { + int i = PKMAP_NR(addr); + return pte_page(pkmap_page_table[i]); + } + + return virt_to_page(addr); +} +EXPORT_SYMBOL(kmap_to_page); + +static void flush_all_zero_pkmaps(void) +{ + int i; + int need_flush = 0; + + flush_cache_kmaps(); + + for (i = 0; i < LAST_PKMAP; i++) { + struct page *page; + + /* + * zero means we don't have anything to do, + * >1 means that it is still in use. Only + * a count of 1 means that it is free but + * needs to be unmapped + */ + if (pkmap_count[i] != 1) + continue; + pkmap_count[i] = 0; + + /* sanity check */ + BUG_ON(pte_none(pkmap_page_table[i])); + + /* + * Don't need an atomic fetch-and-clear op here; + * no-one has the page mapped, and cannot get at + * its virtual address (and hence PTE) without first + * getting the kmap_lock (which is held here). + * So no dangers, even with speculative execution. + */ + page = pte_page(pkmap_page_table[i]); + pte_clear(&init_mm, PKMAP_ADDR(i), &pkmap_page_table[i]); + + set_page_address(page, NULL); + need_flush = 1; + } + if (need_flush) + flush_tlb_kernel_range(PKMAP_ADDR(0), PKMAP_ADDR(LAST_PKMAP)); +} + +/** + * kmap_flush_unused - flush all unused kmap mappings in order to remove stray mappings + */ +void kmap_flush_unused(void) +{ + lock_kmap(); + flush_all_zero_pkmaps(); + unlock_kmap(); +} + +static inline unsigned long map_new_virtual(struct page *page) +{ + unsigned long vaddr; + int count; + unsigned int last_pkmap_nr; + unsigned int color = get_pkmap_color(page); + +start: + count = get_pkmap_entries_count(color); + /* Find an empty entry */ + for (;;) { + last_pkmap_nr = get_next_pkmap_nr(color); + if (no_more_pkmaps(last_pkmap_nr, color)) { + flush_all_zero_pkmaps(); + count = get_pkmap_entries_count(color); + } + if (!pkmap_count[last_pkmap_nr]) + break; /* Found a usable entry */ + if (--count) + continue; + + /* + * Sleep for somebody else to unmap their entries + */ + { + DECLARE_WAITQUEUE(wait, current); + wait_queue_head_t *pkmap_map_wait = + get_pkmap_wait_queue_head(color); + + __set_current_state(TASK_UNINTERRUPTIBLE); + add_wait_queue(pkmap_map_wait, &wait); + unlock_kmap(); + schedule(); + remove_wait_queue(pkmap_map_wait, &wait); + lock_kmap(); + + /* Somebody else might have mapped it while we slept */ + if (page_address(page)) + return (unsigned long)page_address(page); + + /* Re-start */ + goto start; + } + } + vaddr = PKMAP_ADDR(last_pkmap_nr); + set_pte_at(&init_mm, vaddr, + &(pkmap_page_table[last_pkmap_nr]), mk_pte(page, kmap_prot)); + + pkmap_count[last_pkmap_nr] = 1; + set_page_address(page, (void *)vaddr); + + return vaddr; +} + +/** + * kmap_high - map a highmem page into memory + * @page: &struct page to map + * + * Returns the page's virtual memory address. + * + * We cannot call this from interrupts, as it may block. + */ +void *kmap_high(struct page *page) +{ + unsigned long vaddr; + + /* + * For highmem pages, we can't trust "virtual" until + * after we have the lock. + */ + lock_kmap(); + vaddr = (unsigned long)page_address(page); + if (!vaddr) + vaddr = map_new_virtual(page); + pkmap_count[PKMAP_NR(vaddr)]++; + BUG_ON(pkmap_count[PKMAP_NR(vaddr)] < 2); + unlock_kmap(); + return (void*) vaddr; +} + +EXPORT_SYMBOL(kmap_high); + +#ifdef ARCH_NEEDS_KMAP_HIGH_GET +/** + * kmap_high_get - pin a highmem page into memory + * @page: &struct page to pin + * + * Returns the page's current virtual memory address, or NULL if no mapping + * exists. If and only if a non null address is returned then a + * matching call to kunmap_high() is necessary. + * + * This can be called from any context. + */ +void *kmap_high_get(struct page *page) +{ + unsigned long vaddr, flags; + + lock_kmap_any(flags); + vaddr = (unsigned long)page_address(page); + if (vaddr) { + BUG_ON(pkmap_count[PKMAP_NR(vaddr)] < 1); + pkmap_count[PKMAP_NR(vaddr)]++; + } + unlock_kmap_any(flags); + return (void*) vaddr; +} +#endif + +/** + * kunmap_high - unmap a highmem page into memory + * @page: &struct page to unmap + * + * If ARCH_NEEDS_KMAP_HIGH_GET is not defined then this may be called + * only from user context. + */ +void kunmap_high(struct page *page) +{ + unsigned long vaddr; + unsigned long nr; + unsigned long flags; + int need_wakeup; + unsigned int color = get_pkmap_color(page); + wait_queue_head_t *pkmap_map_wait; + + lock_kmap_any(flags); + vaddr = (unsigned long)page_address(page); + BUG_ON(!vaddr); + nr = PKMAP_NR(vaddr); + + /* + * A count must never go down to zero + * without a TLB flush! + */ + need_wakeup = 0; + switch (--pkmap_count[nr]) { + case 0: + BUG(); + case 1: + /* + * Avoid an unnecessary wake_up() function call. + * The common case is pkmap_count[] == 1, but + * no waiters. + * The tasks queued in the wait-queue are guarded + * by both the lock in the wait-queue-head and by + * the kmap_lock. As the kmap_lock is held here, + * no need for the wait-queue-head's lock. Simply + * test if the queue is empty. + */ + pkmap_map_wait = get_pkmap_wait_queue_head(color); + need_wakeup = waitqueue_active(pkmap_map_wait); + } + unlock_kmap_any(flags); + + /* do wake-up, if needed, race-free outside of the spin lock */ + if (need_wakeup) + wake_up(pkmap_map_wait); +} + +EXPORT_SYMBOL(kunmap_high); +#endif /* CONFIG_HIGHMEM */ + +#if defined(HASHED_PAGE_VIRTUAL) + +#define PA_HASH_ORDER 7 + +/* + * Describes one page->virtual association + */ +struct page_address_map { + struct page *page; + void *virtual; + struct list_head list; +}; + +static struct page_address_map page_address_maps[LAST_PKMAP]; + +/* + * Hash table bucket + */ +static struct page_address_slot { + struct list_head lh; /* List of page_address_maps */ + spinlock_t lock; /* Protect this bucket's list */ +} ____cacheline_aligned_in_smp page_address_htable[1<lock, flags); + if (!list_empty(&pas->lh)) { + struct page_address_map *pam; + + list_for_each_entry(pam, &pas->lh, list) { + if (pam->page == page) { + ret = pam->virtual; + goto done; + } + } + } +done: + spin_unlock_irqrestore(&pas->lock, flags); + return ret; +} + +EXPORT_SYMBOL(page_address); + +/** + * set_page_address - set a page's virtual address + * @page: &struct page to set + * @virtual: virtual address to use + */ +void set_page_address(struct page *page, void *virtual) +{ + unsigned long flags; + struct page_address_slot *pas; + struct page_address_map *pam; + + BUG_ON(!PageHighMem(page)); + + pas = page_slot(page); + if (virtual) { /* Add */ + pam = &page_address_maps[PKMAP_NR((unsigned long)virtual)]; + pam->page = page; + pam->virtual = virtual; + + spin_lock_irqsave(&pas->lock, flags); + list_add_tail(&pam->list, &pas->lh); + spin_unlock_irqrestore(&pas->lock, flags); + } else { /* Remove */ + spin_lock_irqsave(&pas->lock, flags); + list_for_each_entry(pam, &pas->lh, list) { + if (pam->page == page) { + list_del(&pam->list); + spin_unlock_irqrestore(&pas->lock, flags); + goto done; + } + } + spin_unlock_irqrestore(&pas->lock, flags); + } +done: + return; +} + +void __init page_address_init(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(page_address_htable); i++) { + INIT_LIST_HEAD(&page_address_htable[i].lh); + spin_lock_init(&page_address_htable[i].lock); + } +} + +#endif /* defined(HASHED_PAGE_VIRTUAL) */ diff --git a/mm/hmm.c b/mm/hmm.c new file mode 100644 index 000000000..cbe9d0c66 --- /dev/null +++ b/mm/hmm.c @@ -0,0 +1,599 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright 2013 Red Hat Inc. + * + * Authors: Jérôme Glisse + */ +/* + * Refer to include/linux/hmm.h for information about heterogeneous memory + * management or HMM for short. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct hmm_vma_walk { + struct hmm_range *range; + unsigned long last; +}; + +enum { + HMM_NEED_FAULT = 1 << 0, + HMM_NEED_WRITE_FAULT = 1 << 1, + HMM_NEED_ALL_BITS = HMM_NEED_FAULT | HMM_NEED_WRITE_FAULT, +}; + +static int hmm_pfns_fill(unsigned long addr, unsigned long end, + struct hmm_range *range, unsigned long cpu_flags) +{ + unsigned long i = (addr - range->start) >> PAGE_SHIFT; + + for (; addr < end; addr += PAGE_SIZE, i++) + range->hmm_pfns[i] = cpu_flags; + return 0; +} + +/* + * hmm_vma_fault() - fault in a range lacking valid pmd or pte(s) + * @addr: range virtual start address (inclusive) + * @end: range virtual end address (exclusive) + * @required_fault: HMM_NEED_* flags + * @walk: mm_walk structure + * Return: -EBUSY after page fault, or page fault error + * + * This function will be called whenever pmd_none() or pte_none() returns true, + * or whenever there is no page directory covering the virtual address range. + */ +static int hmm_vma_fault(unsigned long addr, unsigned long end, + unsigned int required_fault, struct mm_walk *walk) +{ + struct hmm_vma_walk *hmm_vma_walk = walk->private; + struct vm_area_struct *vma = walk->vma; + unsigned int fault_flags = FAULT_FLAG_REMOTE; + + WARN_ON_ONCE(!required_fault); + hmm_vma_walk->last = addr; + + if (required_fault & HMM_NEED_WRITE_FAULT) { + if (!(vma->vm_flags & VM_WRITE)) + return -EPERM; + fault_flags |= FAULT_FLAG_WRITE; + } + + for (; addr < end; addr += PAGE_SIZE) + if (handle_mm_fault(vma, addr, fault_flags, NULL) & + VM_FAULT_ERROR) + return -EFAULT; + return -EBUSY; +} + +static unsigned int hmm_pte_need_fault(const struct hmm_vma_walk *hmm_vma_walk, + unsigned long pfn_req_flags, + unsigned long cpu_flags) +{ + struct hmm_range *range = hmm_vma_walk->range; + + /* + * So we not only consider the individual per page request we also + * consider the default flags requested for the range. The API can + * be used 2 ways. The first one where the HMM user coalesces + * multiple page faults into one request and sets flags per pfn for + * those faults. The second one where the HMM user wants to pre- + * fault a range with specific flags. For the latter one it is a + * waste to have the user pre-fill the pfn arrays with a default + * flags value. + */ + pfn_req_flags &= range->pfn_flags_mask; + pfn_req_flags |= range->default_flags; + + /* We aren't ask to do anything ... */ + if (!(pfn_req_flags & HMM_PFN_REQ_FAULT)) + return 0; + + /* Need to write fault ? */ + if ((pfn_req_flags & HMM_PFN_REQ_WRITE) && + !(cpu_flags & HMM_PFN_WRITE)) + return HMM_NEED_FAULT | HMM_NEED_WRITE_FAULT; + + /* If CPU page table is not valid then we need to fault */ + if (!(cpu_flags & HMM_PFN_VALID)) + return HMM_NEED_FAULT; + return 0; +} + +static unsigned int +hmm_range_need_fault(const struct hmm_vma_walk *hmm_vma_walk, + const unsigned long hmm_pfns[], unsigned long npages, + unsigned long cpu_flags) +{ + struct hmm_range *range = hmm_vma_walk->range; + unsigned int required_fault = 0; + unsigned long i; + + /* + * If the default flags do not request to fault pages, and the mask does + * not allow for individual pages to be faulted, then + * hmm_pte_need_fault() will always return 0. + */ + if (!((range->default_flags | range->pfn_flags_mask) & + HMM_PFN_REQ_FAULT)) + return 0; + + for (i = 0; i < npages; ++i) { + required_fault |= hmm_pte_need_fault(hmm_vma_walk, hmm_pfns[i], + cpu_flags); + if (required_fault == HMM_NEED_ALL_BITS) + return required_fault; + } + return required_fault; +} + +static int hmm_vma_walk_hole(unsigned long addr, unsigned long end, + __always_unused int depth, struct mm_walk *walk) +{ + struct hmm_vma_walk *hmm_vma_walk = walk->private; + struct hmm_range *range = hmm_vma_walk->range; + unsigned int required_fault; + unsigned long i, npages; + unsigned long *hmm_pfns; + + i = (addr - range->start) >> PAGE_SHIFT; + npages = (end - addr) >> PAGE_SHIFT; + hmm_pfns = &range->hmm_pfns[i]; + required_fault = + hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, 0); + if (!walk->vma) { + if (required_fault) + return -EFAULT; + return hmm_pfns_fill(addr, end, range, HMM_PFN_ERROR); + } + if (required_fault) + return hmm_vma_fault(addr, end, required_fault, walk); + return hmm_pfns_fill(addr, end, range, 0); +} + +static inline unsigned long hmm_pfn_flags_order(unsigned long order) +{ + return order << HMM_PFN_ORDER_SHIFT; +} + +static inline unsigned long pmd_to_hmm_pfn_flags(struct hmm_range *range, + pmd_t pmd) +{ + if (pmd_protnone(pmd)) + return 0; + return (pmd_write(pmd) ? (HMM_PFN_VALID | HMM_PFN_WRITE) : + HMM_PFN_VALID) | + hmm_pfn_flags_order(PMD_SHIFT - PAGE_SHIFT); +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr, + unsigned long end, unsigned long hmm_pfns[], + pmd_t pmd) +{ + struct hmm_vma_walk *hmm_vma_walk = walk->private; + struct hmm_range *range = hmm_vma_walk->range; + unsigned long pfn, npages, i; + unsigned int required_fault; + unsigned long cpu_flags; + + npages = (end - addr) >> PAGE_SHIFT; + cpu_flags = pmd_to_hmm_pfn_flags(range, pmd); + required_fault = + hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, cpu_flags); + if (required_fault) + return hmm_vma_fault(addr, end, required_fault, walk); + + pfn = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); + for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++) + hmm_pfns[i] = pfn | cpu_flags; + return 0; +} +#else /* CONFIG_TRANSPARENT_HUGEPAGE */ +/* stub to allow the code below to compile */ +int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr, + unsigned long end, unsigned long hmm_pfns[], pmd_t pmd); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +static inline bool hmm_is_device_private_entry(struct hmm_range *range, + swp_entry_t entry) +{ + return is_device_private_entry(entry) && + device_private_entry_to_page(entry)->pgmap->owner == + range->dev_private_owner; +} + +static inline unsigned long pte_to_hmm_pfn_flags(struct hmm_range *range, + pte_t pte) +{ + if (pte_none(pte) || !pte_present(pte) || pte_protnone(pte)) + return 0; + return pte_write(pte) ? (HMM_PFN_VALID | HMM_PFN_WRITE) : HMM_PFN_VALID; +} + +static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr, + unsigned long end, pmd_t *pmdp, pte_t *ptep, + unsigned long *hmm_pfn) +{ + struct hmm_vma_walk *hmm_vma_walk = walk->private; + struct hmm_range *range = hmm_vma_walk->range; + unsigned int required_fault; + unsigned long cpu_flags; + pte_t pte = *ptep; + uint64_t pfn_req_flags = *hmm_pfn; + + if (pte_none(pte)) { + required_fault = + hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0); + if (required_fault) + goto fault; + *hmm_pfn = 0; + return 0; + } + + if (!pte_present(pte)) { + swp_entry_t entry = pte_to_swp_entry(pte); + + /* + * Never fault in device private pages, but just report + * the PFN even if not present. + */ + if (hmm_is_device_private_entry(range, entry)) { + cpu_flags = HMM_PFN_VALID; + if (is_write_device_private_entry(entry)) + cpu_flags |= HMM_PFN_WRITE; + *hmm_pfn = device_private_entry_to_pfn(entry) | + cpu_flags; + return 0; + } + + required_fault = + hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0); + if (!required_fault) { + *hmm_pfn = 0; + return 0; + } + + if (!non_swap_entry(entry)) + goto fault; + + if (is_migration_entry(entry)) { + pte_unmap(ptep); + hmm_vma_walk->last = addr; + migration_entry_wait(walk->mm, pmdp, addr); + return -EBUSY; + } + + /* Report error for everything else */ + pte_unmap(ptep); + return -EFAULT; + } + + cpu_flags = pte_to_hmm_pfn_flags(range, pte); + required_fault = + hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, cpu_flags); + if (required_fault) + goto fault; + + /* + * Bypass devmap pte such as DAX page when all pfn requested + * flags(pfn_req_flags) are fulfilled. + * Since each architecture defines a struct page for the zero page, just + * fall through and treat it like a normal page. + */ + if (!vm_normal_page(walk->vma, addr, pte) && + !pte_devmap(pte) && + !is_zero_pfn(pte_pfn(pte))) { + if (hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0)) { + pte_unmap(ptep); + return -EFAULT; + } + *hmm_pfn = HMM_PFN_ERROR; + return 0; + } + + *hmm_pfn = pte_pfn(pte) | cpu_flags; + return 0; + +fault: + pte_unmap(ptep); + /* Fault any virtual address we were asked to fault */ + return hmm_vma_fault(addr, end, required_fault, walk); +} + +static int hmm_vma_walk_pmd(pmd_t *pmdp, + unsigned long start, + unsigned long end, + struct mm_walk *walk) +{ + struct hmm_vma_walk *hmm_vma_walk = walk->private; + struct hmm_range *range = hmm_vma_walk->range; + unsigned long *hmm_pfns = + &range->hmm_pfns[(start - range->start) >> PAGE_SHIFT]; + unsigned long npages = (end - start) >> PAGE_SHIFT; + unsigned long addr = start; + pte_t *ptep; + pmd_t pmd; + +again: + pmd = READ_ONCE(*pmdp); + if (pmd_none(pmd)) + return hmm_vma_walk_hole(start, end, -1, walk); + + if (thp_migration_supported() && is_pmd_migration_entry(pmd)) { + if (hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, 0)) { + hmm_vma_walk->last = addr; + pmd_migration_entry_wait(walk->mm, pmdp); + return -EBUSY; + } + return hmm_pfns_fill(start, end, range, 0); + } + + if (!pmd_present(pmd)) { + if (hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, 0)) + return -EFAULT; + return hmm_pfns_fill(start, end, range, HMM_PFN_ERROR); + } + + if (pmd_devmap(pmd) || pmd_trans_huge(pmd)) { + /* + * No need to take pmd_lock here, even if some other thread + * is splitting the huge pmd we will get that event through + * mmu_notifier callback. + * + * So just read pmd value and check again it's a transparent + * huge or device mapping one and compute corresponding pfn + * values. + */ + pmd = pmd_read_atomic(pmdp); + barrier(); + if (!pmd_devmap(pmd) && !pmd_trans_huge(pmd)) + goto again; + + return hmm_vma_handle_pmd(walk, addr, end, hmm_pfns, pmd); + } + + /* + * We have handled all the valid cases above ie either none, migration, + * huge or transparent huge. At this point either it is a valid pmd + * entry pointing to pte directory or it is a bad pmd that will not + * recover. + */ + if (pmd_bad(pmd)) { + if (hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, 0)) + return -EFAULT; + return hmm_pfns_fill(start, end, range, HMM_PFN_ERROR); + } + + ptep = pte_offset_map(pmdp, addr); + for (; addr < end; addr += PAGE_SIZE, ptep++, hmm_pfns++) { + int r; + + r = hmm_vma_handle_pte(walk, addr, end, pmdp, ptep, hmm_pfns); + if (r) { + /* hmm_vma_handle_pte() did pte_unmap() */ + return r; + } + } + pte_unmap(ptep - 1); + return 0; +} + +#if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && \ + defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) +static inline unsigned long pud_to_hmm_pfn_flags(struct hmm_range *range, + pud_t pud) +{ + if (!pud_present(pud)) + return 0; + return (pud_write(pud) ? (HMM_PFN_VALID | HMM_PFN_WRITE) : + HMM_PFN_VALID) | + hmm_pfn_flags_order(PUD_SHIFT - PAGE_SHIFT); +} + +static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end, + struct mm_walk *walk) +{ + struct hmm_vma_walk *hmm_vma_walk = walk->private; + struct hmm_range *range = hmm_vma_walk->range; + unsigned long addr = start; + pud_t pud; + int ret = 0; + spinlock_t *ptl = pud_trans_huge_lock(pudp, walk->vma); + + if (!ptl) + return 0; + + /* Normally we don't want to split the huge page */ + walk->action = ACTION_CONTINUE; + + pud = READ_ONCE(*pudp); + if (pud_none(pud)) { + spin_unlock(ptl); + return hmm_vma_walk_hole(start, end, -1, walk); + } + + if (pud_huge(pud) && pud_devmap(pud)) { + unsigned long i, npages, pfn; + unsigned int required_fault; + unsigned long *hmm_pfns; + unsigned long cpu_flags; + + if (!pud_present(pud)) { + spin_unlock(ptl); + return hmm_vma_walk_hole(start, end, -1, walk); + } + + i = (addr - range->start) >> PAGE_SHIFT; + npages = (end - addr) >> PAGE_SHIFT; + hmm_pfns = &range->hmm_pfns[i]; + + cpu_flags = pud_to_hmm_pfn_flags(range, pud); + required_fault = hmm_range_need_fault(hmm_vma_walk, hmm_pfns, + npages, cpu_flags); + if (required_fault) { + spin_unlock(ptl); + return hmm_vma_fault(addr, end, required_fault, walk); + } + + pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); + for (i = 0; i < npages; ++i, ++pfn) + hmm_pfns[i] = pfn | cpu_flags; + goto out_unlock; + } + + /* Ask for the PUD to be split */ + walk->action = ACTION_SUBTREE; + +out_unlock: + spin_unlock(ptl); + return ret; +} +#else +#define hmm_vma_walk_pud NULL +#endif + +#ifdef CONFIG_HUGETLB_PAGE +static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask, + unsigned long start, unsigned long end, + struct mm_walk *walk) +{ + unsigned long addr = start, i, pfn; + struct hmm_vma_walk *hmm_vma_walk = walk->private; + struct hmm_range *range = hmm_vma_walk->range; + struct vm_area_struct *vma = walk->vma; + unsigned int required_fault; + unsigned long pfn_req_flags; + unsigned long cpu_flags; + spinlock_t *ptl; + pte_t entry; + + ptl = huge_pte_lock(hstate_vma(vma), walk->mm, pte); + entry = huge_ptep_get(pte); + + i = (start - range->start) >> PAGE_SHIFT; + pfn_req_flags = range->hmm_pfns[i]; + cpu_flags = pte_to_hmm_pfn_flags(range, entry) | + hmm_pfn_flags_order(huge_page_order(hstate_vma(vma))); + required_fault = + hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, cpu_flags); + if (required_fault) { + spin_unlock(ptl); + return hmm_vma_fault(addr, end, required_fault, walk); + } + + pfn = pte_pfn(entry) + ((start & ~hmask) >> PAGE_SHIFT); + for (; addr < end; addr += PAGE_SIZE, i++, pfn++) + range->hmm_pfns[i] = pfn | cpu_flags; + + spin_unlock(ptl); + return 0; +} +#else +#define hmm_vma_walk_hugetlb_entry NULL +#endif /* CONFIG_HUGETLB_PAGE */ + +static int hmm_vma_walk_test(unsigned long start, unsigned long end, + struct mm_walk *walk) +{ + struct hmm_vma_walk *hmm_vma_walk = walk->private; + struct hmm_range *range = hmm_vma_walk->range; + struct vm_area_struct *vma = walk->vma; + + if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)) && + vma->vm_flags & VM_READ) + return 0; + + /* + * vma ranges that don't have struct page backing them or map I/O + * devices directly cannot be handled by hmm_range_fault(). + * + * If the vma does not allow read access, then assume that it does not + * allow write access either. HMM does not support architectures that + * allow write without read. + * + * If a fault is requested for an unsupported range then it is a hard + * failure. + */ + if (hmm_range_need_fault(hmm_vma_walk, + range->hmm_pfns + + ((start - range->start) >> PAGE_SHIFT), + (end - start) >> PAGE_SHIFT, 0)) + return -EFAULT; + + hmm_pfns_fill(start, end, range, HMM_PFN_ERROR); + + /* Skip this vma and continue processing the next vma. */ + return 1; +} + +static const struct mm_walk_ops hmm_walk_ops = { + .pud_entry = hmm_vma_walk_pud, + .pmd_entry = hmm_vma_walk_pmd, + .pte_hole = hmm_vma_walk_hole, + .hugetlb_entry = hmm_vma_walk_hugetlb_entry, + .test_walk = hmm_vma_walk_test, +}; + +/** + * hmm_range_fault - try to fault some address in a virtual address range + * @range: argument structure + * + * Returns 0 on success or one of the following error codes: + * + * -EINVAL: Invalid arguments or mm or virtual address is in an invalid vma + * (e.g., device file vma). + * -ENOMEM: Out of memory. + * -EPERM: Invalid permission (e.g., asking for write and range is read + * only). + * -EBUSY: The range has been invalidated and the caller needs to wait for + * the invalidation to finish. + * -EFAULT: A page was requested to be valid and could not be made valid + * ie it has no backing VMA or it is illegal to access + * + * This is similar to get_user_pages(), except that it can read the page tables + * without mutating them (ie causing faults). + */ +int hmm_range_fault(struct hmm_range *range) +{ + struct hmm_vma_walk hmm_vma_walk = { + .range = range, + .last = range->start, + }; + struct mm_struct *mm = range->notifier->mm; + int ret; + + mmap_assert_locked(mm); + + do { + /* If range is no longer valid force retry. */ + if (mmu_interval_check_retry(range->notifier, + range->notifier_seq)) + return -EBUSY; + ret = walk_page_range(mm, hmm_vma_walk.last, range->end, + &hmm_walk_ops, &hmm_vma_walk); + /* + * When -EBUSY is returned the loop restarts with + * hmm_vma_walk.last set to an address that has not been stored + * in pfns. All entries < last in the pfn array are set to their + * output, and all >= are still at their input values. + */ + } while (ret == -EBUSY); + return ret; +} +EXPORT_SYMBOL(hmm_range_fault); diff --git a/mm/huge_memory.c b/mm/huge_memory.c new file mode 100644 index 000000000..e4c690c21 --- /dev/null +++ b/mm/huge_memory.c @@ -0,0 +1,3015 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2009 Red Hat, Inc. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include "internal.h" + +/* + * By default, transparent hugepage support is disabled in order to avoid + * risking an increased memory footprint for applications that are not + * guaranteed to benefit from it. When transparent hugepage support is + * enabled, it is for all mappings, and khugepaged scans all mappings. + * Defrag is invoked by khugepaged hugepage allocations and by page faults + * for all hugepage allocations. + */ +unsigned long transparent_hugepage_flags __read_mostly = +#ifdef CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS + (1<vm_flags) && vma->vm_file && + !inode_is_open_for_write(vma->vm_file->f_inode) && + (vma->vm_flags & VM_EXEC); +} + +bool transparent_hugepage_active(struct vm_area_struct *vma) +{ + /* The addr is used to check if the vma size fits */ + unsigned long addr = (vma->vm_end & HPAGE_PMD_MASK) - HPAGE_PMD_SIZE; + + if (!transhuge_vma_suitable(vma, addr)) + return false; + if (vma_is_anonymous(vma)) + return __transparent_hugepage_enabled(vma); + if (vma_is_shmem(vma)) + return shmem_huge_enabled(vma); + if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS)) + return file_thp_enabled(vma); + + return false; +} + +static struct page *get_huge_zero_page(void) +{ + struct page *zero_page; +retry: + if (likely(atomic_inc_not_zero(&huge_zero_refcount))) + return READ_ONCE(huge_zero_page); + + zero_page = alloc_pages((GFP_TRANSHUGE | __GFP_ZERO) & ~__GFP_MOVABLE, + HPAGE_PMD_ORDER); + if (!zero_page) { + count_vm_event(THP_ZERO_PAGE_ALLOC_FAILED); + return NULL; + } + count_vm_event(THP_ZERO_PAGE_ALLOC); + preempt_disable(); + if (cmpxchg(&huge_zero_page, NULL, zero_page)) { + preempt_enable(); + __free_pages(zero_page, compound_order(zero_page)); + goto retry; + } + WRITE_ONCE(huge_zero_pfn, page_to_pfn(zero_page)); + + /* We take additional reference here. It will be put back by shrinker */ + atomic_set(&huge_zero_refcount, 2); + preempt_enable(); + return READ_ONCE(huge_zero_page); +} + +static void put_huge_zero_page(void) +{ + /* + * Counter should never go to zero here. Only shrinker can put + * last reference. + */ + BUG_ON(atomic_dec_and_test(&huge_zero_refcount)); +} + +struct page *mm_get_huge_zero_page(struct mm_struct *mm) +{ + if (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags)) + return READ_ONCE(huge_zero_page); + + if (!get_huge_zero_page()) + return NULL; + + if (test_and_set_bit(MMF_HUGE_ZERO_PAGE, &mm->flags)) + put_huge_zero_page(); + + return READ_ONCE(huge_zero_page); +} + +void mm_put_huge_zero_page(struct mm_struct *mm) +{ + if (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags)) + put_huge_zero_page(); +} + +static unsigned long shrink_huge_zero_page_count(struct shrinker *shrink, + struct shrink_control *sc) +{ + /* we can free zero page only if last reference remains */ + return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0; +} + +static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink, + struct shrink_control *sc) +{ + if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) { + struct page *zero_page = xchg(&huge_zero_page, NULL); + BUG_ON(zero_page == NULL); + WRITE_ONCE(huge_zero_pfn, ~0UL); + __free_pages(zero_page, compound_order(zero_page)); + return HPAGE_PMD_NR; + } + + return 0; +} + +static struct shrinker huge_zero_page_shrinker = { + .count_objects = shrink_huge_zero_page_count, + .scan_objects = shrink_huge_zero_page_scan, + .seeks = DEFAULT_SEEKS, +}; + +#ifdef CONFIG_SYSFS +static ssize_t enabled_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + if (test_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags)) + return sprintf(buf, "[always] madvise never\n"); + else if (test_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags)) + return sprintf(buf, "always [madvise] never\n"); + else + return sprintf(buf, "always madvise [never]\n"); +} + +static ssize_t enabled_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + ssize_t ret = count; + + if (sysfs_streq(buf, "always")) { + clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); + set_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); + } else if (sysfs_streq(buf, "madvise")) { + clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); + set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); + } else if (sysfs_streq(buf, "never")) { + clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); + } else + ret = -EINVAL; + + if (ret > 0) { + int err = start_stop_khugepaged(); + if (err) + ret = err; + } + return ret; +} +static struct kobj_attribute enabled_attr = + __ATTR(enabled, 0644, enabled_show, enabled_store); + +ssize_t single_hugepage_flag_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf, + enum transparent_hugepage_flag flag) +{ + return sprintf(buf, "%d\n", + !!test_bit(flag, &transparent_hugepage_flags)); +} + +ssize_t single_hugepage_flag_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count, + enum transparent_hugepage_flag flag) +{ + unsigned long value; + int ret; + + ret = kstrtoul(buf, 10, &value); + if (ret < 0) + return ret; + if (value > 1) + return -EINVAL; + + if (value) + set_bit(flag, &transparent_hugepage_flags); + else + clear_bit(flag, &transparent_hugepage_flags); + + return count; +} + +static ssize_t defrag_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags)) + return sprintf(buf, "[always] defer defer+madvise madvise never\n"); + if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags)) + return sprintf(buf, "always [defer] defer+madvise madvise never\n"); + if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags)) + return sprintf(buf, "always defer [defer+madvise] madvise never\n"); + if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags)) + return sprintf(buf, "always defer defer+madvise [madvise] never\n"); + return sprintf(buf, "always defer defer+madvise madvise [never]\n"); +} + +static ssize_t defrag_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + if (sysfs_streq(buf, "always")) { + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); + set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); + } else if (sysfs_streq(buf, "defer+madvise")) { + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); + set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); + } else if (sysfs_streq(buf, "defer")) { + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); + set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); + } else if (sysfs_streq(buf, "madvise")) { + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); + set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); + } else if (sysfs_streq(buf, "never")) { + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); + } else + return -EINVAL; + + return count; +} +static struct kobj_attribute defrag_attr = + __ATTR(defrag, 0644, defrag_show, defrag_store); + +static ssize_t use_zero_page_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return single_hugepage_flag_show(kobj, attr, buf, + TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG); +} +static ssize_t use_zero_page_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + return single_hugepage_flag_store(kobj, attr, buf, count, + TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG); +} +static struct kobj_attribute use_zero_page_attr = + __ATTR(use_zero_page, 0644, use_zero_page_show, use_zero_page_store); + +static ssize_t hpage_pmd_size_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%lu\n", HPAGE_PMD_SIZE); +} +static struct kobj_attribute hpage_pmd_size_attr = + __ATTR_RO(hpage_pmd_size); + +static struct attribute *hugepage_attr[] = { + &enabled_attr.attr, + &defrag_attr.attr, + &use_zero_page_attr.attr, + &hpage_pmd_size_attr.attr, +#ifdef CONFIG_SHMEM + &shmem_enabled_attr.attr, +#endif + NULL, +}; + +static const struct attribute_group hugepage_attr_group = { + .attrs = hugepage_attr, +}; + +static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj) +{ + int err; + + *hugepage_kobj = kobject_create_and_add("transparent_hugepage", mm_kobj); + if (unlikely(!*hugepage_kobj)) { + pr_err("failed to create transparent hugepage kobject\n"); + return -ENOMEM; + } + + err = sysfs_create_group(*hugepage_kobj, &hugepage_attr_group); + if (err) { + pr_err("failed to register transparent hugepage group\n"); + goto delete_obj; + } + + err = sysfs_create_group(*hugepage_kobj, &khugepaged_attr_group); + if (err) { + pr_err("failed to register transparent hugepage group\n"); + goto remove_hp_group; + } + + return 0; + +remove_hp_group: + sysfs_remove_group(*hugepage_kobj, &hugepage_attr_group); +delete_obj: + kobject_put(*hugepage_kobj); + return err; +} + +static void __init hugepage_exit_sysfs(struct kobject *hugepage_kobj) +{ + sysfs_remove_group(hugepage_kobj, &khugepaged_attr_group); + sysfs_remove_group(hugepage_kobj, &hugepage_attr_group); + kobject_put(hugepage_kobj); +} +#else +static inline int hugepage_init_sysfs(struct kobject **hugepage_kobj) +{ + return 0; +} + +static inline void hugepage_exit_sysfs(struct kobject *hugepage_kobj) +{ +} +#endif /* CONFIG_SYSFS */ + +static int __init hugepage_init(void) +{ + int err; + struct kobject *hugepage_kobj; + + if (!has_transparent_hugepage()) { + /* + * Hardware doesn't support hugepages, hence disable + * DAX PMD support. + */ + transparent_hugepage_flags = 1 << TRANSPARENT_HUGEPAGE_NEVER_DAX; + return -EINVAL; + } + + /* + * hugepages can't be allocated by the buddy allocator + */ + MAYBE_BUILD_BUG_ON(HPAGE_PMD_ORDER >= MAX_ORDER); + /* + * we use page->mapping and page->index in second tail page + * as list_head: assuming THP order >= 2 + */ + MAYBE_BUILD_BUG_ON(HPAGE_PMD_ORDER < 2); + + err = hugepage_init_sysfs(&hugepage_kobj); + if (err) + goto err_sysfs; + + err = khugepaged_init(); + if (err) + goto err_slab; + + err = register_shrinker(&huge_zero_page_shrinker); + if (err) + goto err_hzp_shrinker; + err = register_shrinker(&deferred_split_shrinker); + if (err) + goto err_split_shrinker; + + /* + * By default disable transparent hugepages on smaller systems, + * where the extra memory used could hurt more than TLB overhead + * is likely to save. The admin can still enable it through /sys. + */ + if (totalram_pages() < (512 << (20 - PAGE_SHIFT))) { + transparent_hugepage_flags = 0; + return 0; + } + + err = start_stop_khugepaged(); + if (err) + goto err_khugepaged; + + return 0; +err_khugepaged: + unregister_shrinker(&deferred_split_shrinker); +err_split_shrinker: + unregister_shrinker(&huge_zero_page_shrinker); +err_hzp_shrinker: + khugepaged_destroy(); +err_slab: + hugepage_exit_sysfs(hugepage_kobj); +err_sysfs: + return err; +} +subsys_initcall(hugepage_init); + +static int __init setup_transparent_hugepage(char *str) +{ + int ret = 0; + if (!str) + goto out; + if (!strcmp(str, "always")) { + set_bit(TRANSPARENT_HUGEPAGE_FLAG, + &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, + &transparent_hugepage_flags); + ret = 1; + } else if (!strcmp(str, "madvise")) { + clear_bit(TRANSPARENT_HUGEPAGE_FLAG, + &transparent_hugepage_flags); + set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, + &transparent_hugepage_flags); + ret = 1; + } else if (!strcmp(str, "never")) { + clear_bit(TRANSPARENT_HUGEPAGE_FLAG, + &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, + &transparent_hugepage_flags); + ret = 1; + } +out: + if (!ret) + pr_warn("transparent_hugepage= cannot parse, ignored\n"); + return ret; +} +__setup("transparent_hugepage=", setup_transparent_hugepage); + +pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma) +{ + if (likely(vma->vm_flags & VM_WRITE)) + pmd = pmd_mkwrite(pmd); + return pmd; +} + +#ifdef CONFIG_MEMCG +static inline struct deferred_split *get_deferred_split_queue(struct page *page) +{ + struct mem_cgroup *memcg = compound_head(page)->mem_cgroup; + struct pglist_data *pgdat = NODE_DATA(page_to_nid(page)); + + if (memcg) + return &memcg->deferred_split_queue; + else + return &pgdat->deferred_split_queue; +} +#else +static inline struct deferred_split *get_deferred_split_queue(struct page *page) +{ + struct pglist_data *pgdat = NODE_DATA(page_to_nid(page)); + + return &pgdat->deferred_split_queue; +} +#endif + +void prep_transhuge_page(struct page *page) +{ + /* + * we use page->mapping and page->indexlru in second tail page + * as list_head: assuming THP order >= 2 + */ + + INIT_LIST_HEAD(page_deferred_list(page)); + set_compound_page_dtor(page, TRANSHUGE_PAGE_DTOR); +} + +bool is_transparent_hugepage(struct page *page) +{ + if (!PageCompound(page)) + return false; + + page = compound_head(page); + return is_huge_zero_page(page) || + page[1].compound_dtor == TRANSHUGE_PAGE_DTOR; +} +EXPORT_SYMBOL_GPL(is_transparent_hugepage); + +static unsigned long __thp_get_unmapped_area(struct file *filp, + unsigned long addr, unsigned long len, + loff_t off, unsigned long flags, unsigned long size) +{ + loff_t off_end = off + len; + loff_t off_align = round_up(off, size); + unsigned long len_pad, ret; + + if (off_end <= off_align || (off_end - off_align) < size) + return 0; + + len_pad = len + size; + if (len_pad < len || (off + len_pad) < off) + return 0; + + ret = current->mm->get_unmapped_area(filp, addr, len_pad, + off >> PAGE_SHIFT, flags); + + /* + * The failure might be due to length padding. The caller will retry + * without the padding. + */ + if (IS_ERR_VALUE(ret)) + return 0; + + /* + * Do not try to align to THP boundary if allocation at the address + * hint succeeds. + */ + if (ret == addr) + return addr; + + ret += (off - ret) & (size - 1); + return ret; +} + +unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags) +{ + unsigned long ret; + loff_t off = (loff_t)pgoff << PAGE_SHIFT; + + if (!IS_DAX(filp->f_mapping->host) || !IS_ENABLED(CONFIG_FS_DAX_PMD)) + goto out; + + ret = __thp_get_unmapped_area(filp, addr, len, off, flags, PMD_SIZE); + if (ret) + return ret; +out: + return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags); +} +EXPORT_SYMBOL_GPL(thp_get_unmapped_area); + +static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, + struct page *page, gfp_t gfp) +{ + struct vm_area_struct *vma = vmf->vma; + pgtable_t pgtable; + unsigned long haddr = vmf->address & HPAGE_PMD_MASK; + vm_fault_t ret = 0; + + VM_BUG_ON_PAGE(!PageCompound(page), page); + + if (mem_cgroup_charge(page, vma->vm_mm, gfp)) { + put_page(page); + count_vm_event(THP_FAULT_FALLBACK); + count_vm_event(THP_FAULT_FALLBACK_CHARGE); + return VM_FAULT_FALLBACK; + } + cgroup_throttle_swaprate(page, gfp); + + pgtable = pte_alloc_one(vma->vm_mm); + if (unlikely(!pgtable)) { + ret = VM_FAULT_OOM; + goto release; + } + + clear_huge_page(page, vmf->address, HPAGE_PMD_NR); + /* + * The memory barrier inside __SetPageUptodate makes sure that + * clear_huge_page writes become visible before the set_pmd_at() + * write. + */ + __SetPageUptodate(page); + + vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); + if (unlikely(!pmd_none(*vmf->pmd))) { + goto unlock_release; + } else { + pmd_t entry; + + ret = check_stable_address_space(vma->vm_mm); + if (ret) + goto unlock_release; + + /* Deliver the page fault to userland */ + if (userfaultfd_missing(vma)) { + vm_fault_t ret2; + + spin_unlock(vmf->ptl); + put_page(page); + pte_free(vma->vm_mm, pgtable); + ret2 = handle_userfault(vmf, VM_UFFD_MISSING); + VM_BUG_ON(ret2 & VM_FAULT_FALLBACK); + return ret2; + } + + entry = mk_huge_pmd(page, vma->vm_page_prot); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); + page_add_new_anon_rmap(page, vma, haddr, true); + lru_cache_add_inactive_or_unevictable(page, vma); + pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable); + set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry); + add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR); + mm_inc_nr_ptes(vma->vm_mm); + spin_unlock(vmf->ptl); + count_vm_event(THP_FAULT_ALLOC); + count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC); + } + + return 0; +unlock_release: + spin_unlock(vmf->ptl); +release: + if (pgtable) + pte_free(vma->vm_mm, pgtable); + put_page(page); + return ret; + +} + +/* + * always: directly stall for all thp allocations + * defer: wake kswapd and fail if not immediately available + * defer+madvise: wake kswapd and directly stall for MADV_HUGEPAGE, otherwise + * fail if not immediately available + * madvise: directly stall for MADV_HUGEPAGE, otherwise fail if not immediately + * available + * never: never stall for any thp allocation + */ +static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma) +{ + const bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE); + + /* Always do synchronous compaction */ + if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags)) + return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY); + + /* Kick kcompactd and fail quickly */ + if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags)) + return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM; + + /* Synchronous compaction if madvised, otherwise kick kcompactd */ + if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags)) + return GFP_TRANSHUGE_LIGHT | + (vma_madvised ? __GFP_DIRECT_RECLAIM : + __GFP_KSWAPD_RECLAIM); + + /* Only do synchronous compaction if madvised */ + if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags)) + return GFP_TRANSHUGE_LIGHT | + (vma_madvised ? __GFP_DIRECT_RECLAIM : 0); + + return GFP_TRANSHUGE_LIGHT; +} + +/* Caller must hold page table lock. */ +static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm, + struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd, + struct page *zero_page) +{ + pmd_t entry; + if (!pmd_none(*pmd)) + return false; + entry = mk_pmd(zero_page, vma->vm_page_prot); + entry = pmd_mkhuge(entry); + if (pgtable) + pgtable_trans_huge_deposit(mm, pmd, pgtable); + set_pmd_at(mm, haddr, pmd, entry); + mm_inc_nr_ptes(mm); + return true; +} + +vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + gfp_t gfp; + struct page *page; + unsigned long haddr = vmf->address & HPAGE_PMD_MASK; + + if (!transhuge_vma_suitable(vma, haddr)) + return VM_FAULT_FALLBACK; + if (unlikely(anon_vma_prepare(vma))) + return VM_FAULT_OOM; + if (unlikely(khugepaged_enter(vma, vma->vm_flags))) + return VM_FAULT_OOM; + if (!(vmf->flags & FAULT_FLAG_WRITE) && + !mm_forbids_zeropage(vma->vm_mm) && + transparent_hugepage_use_zero_page()) { + pgtable_t pgtable; + struct page *zero_page; + vm_fault_t ret; + pgtable = pte_alloc_one(vma->vm_mm); + if (unlikely(!pgtable)) + return VM_FAULT_OOM; + zero_page = mm_get_huge_zero_page(vma->vm_mm); + if (unlikely(!zero_page)) { + pte_free(vma->vm_mm, pgtable); + count_vm_event(THP_FAULT_FALLBACK); + return VM_FAULT_FALLBACK; + } + vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); + ret = 0; + if (pmd_none(*vmf->pmd)) { + ret = check_stable_address_space(vma->vm_mm); + if (ret) { + spin_unlock(vmf->ptl); + pte_free(vma->vm_mm, pgtable); + } else if (userfaultfd_missing(vma)) { + spin_unlock(vmf->ptl); + pte_free(vma->vm_mm, pgtable); + ret = handle_userfault(vmf, VM_UFFD_MISSING); + VM_BUG_ON(ret & VM_FAULT_FALLBACK); + } else { + set_huge_zero_page(pgtable, vma->vm_mm, vma, + haddr, vmf->pmd, zero_page); + spin_unlock(vmf->ptl); + } + } else { + spin_unlock(vmf->ptl); + pte_free(vma->vm_mm, pgtable); + } + return ret; + } + gfp = alloc_hugepage_direct_gfpmask(vma); + page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER); + if (unlikely(!page)) { + count_vm_event(THP_FAULT_FALLBACK); + return VM_FAULT_FALLBACK; + } + prep_transhuge_page(page); + return __do_huge_pmd_anonymous_page(vmf, page, gfp); +} + +static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd, pfn_t pfn, pgprot_t prot, bool write, + pgtable_t pgtable) +{ + struct mm_struct *mm = vma->vm_mm; + pmd_t entry; + spinlock_t *ptl; + + ptl = pmd_lock(mm, pmd); + if (!pmd_none(*pmd)) { + if (write) { + if (pmd_pfn(*pmd) != pfn_t_to_pfn(pfn)) { + WARN_ON_ONCE(!is_huge_zero_pmd(*pmd)); + goto out_unlock; + } + entry = pmd_mkyoung(*pmd); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); + if (pmdp_set_access_flags(vma, addr, pmd, entry, 1)) + update_mmu_cache_pmd(vma, addr, pmd); + } + + goto out_unlock; + } + + entry = pmd_mkhuge(pfn_t_pmd(pfn, prot)); + if (pfn_t_devmap(pfn)) + entry = pmd_mkdevmap(entry); + if (write) { + entry = pmd_mkyoung(pmd_mkdirty(entry)); + entry = maybe_pmd_mkwrite(entry, vma); + } + + if (pgtable) { + pgtable_trans_huge_deposit(mm, pmd, pgtable); + mm_inc_nr_ptes(mm); + pgtable = NULL; + } + + set_pmd_at(mm, addr, pmd, entry); + update_mmu_cache_pmd(vma, addr, pmd); + +out_unlock: + spin_unlock(ptl); + if (pgtable) + pte_free(mm, pgtable); +} + +/** + * vmf_insert_pfn_pmd_prot - insert a pmd size pfn + * @vmf: Structure describing the fault + * @pfn: pfn to insert + * @pgprot: page protection to use + * @write: whether it's a write fault + * + * Insert a pmd size pfn. See vmf_insert_pfn() for additional info and + * also consult the vmf_insert_mixed_prot() documentation when + * @pgprot != @vmf->vma->vm_page_prot. + * + * Return: vm_fault_t value. + */ +vm_fault_t vmf_insert_pfn_pmd_prot(struct vm_fault *vmf, pfn_t pfn, + pgprot_t pgprot, bool write) +{ + unsigned long addr = vmf->address & PMD_MASK; + struct vm_area_struct *vma = vmf->vma; + pgtable_t pgtable = NULL; + + /* + * If we had pmd_special, we could avoid all these restrictions, + * but we need to be consistent with PTEs and architectures that + * can't support a 'special' bit. + */ + BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) && + !pfn_t_devmap(pfn)); + BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == + (VM_PFNMAP|VM_MIXEDMAP)); + BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); + + if (addr < vma->vm_start || addr >= vma->vm_end) + return VM_FAULT_SIGBUS; + + if (arch_needs_pgtable_deposit()) { + pgtable = pte_alloc_one(vma->vm_mm); + if (!pgtable) + return VM_FAULT_OOM; + } + + track_pfn_insert(vma, &pgprot, pfn); + + insert_pfn_pmd(vma, addr, vmf->pmd, pfn, pgprot, write, pgtable); + return VM_FAULT_NOPAGE; +} +EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd_prot); + +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +static pud_t maybe_pud_mkwrite(pud_t pud, struct vm_area_struct *vma) +{ + if (likely(vma->vm_flags & VM_WRITE)) + pud = pud_mkwrite(pud); + return pud; +} + +static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr, + pud_t *pud, pfn_t pfn, pgprot_t prot, bool write) +{ + struct mm_struct *mm = vma->vm_mm; + pud_t entry; + spinlock_t *ptl; + + ptl = pud_lock(mm, pud); + if (!pud_none(*pud)) { + if (write) { + if (pud_pfn(*pud) != pfn_t_to_pfn(pfn)) { + WARN_ON_ONCE(!is_huge_zero_pud(*pud)); + goto out_unlock; + } + entry = pud_mkyoung(*pud); + entry = maybe_pud_mkwrite(pud_mkdirty(entry), vma); + if (pudp_set_access_flags(vma, addr, pud, entry, 1)) + update_mmu_cache_pud(vma, addr, pud); + } + goto out_unlock; + } + + entry = pud_mkhuge(pfn_t_pud(pfn, prot)); + if (pfn_t_devmap(pfn)) + entry = pud_mkdevmap(entry); + if (write) { + entry = pud_mkyoung(pud_mkdirty(entry)); + entry = maybe_pud_mkwrite(entry, vma); + } + set_pud_at(mm, addr, pud, entry); + update_mmu_cache_pud(vma, addr, pud); + +out_unlock: + spin_unlock(ptl); +} + +/** + * vmf_insert_pfn_pud_prot - insert a pud size pfn + * @vmf: Structure describing the fault + * @pfn: pfn to insert + * @pgprot: page protection to use + * @write: whether it's a write fault + * + * Insert a pud size pfn. See vmf_insert_pfn() for additional info and + * also consult the vmf_insert_mixed_prot() documentation when + * @pgprot != @vmf->vma->vm_page_prot. + * + * Return: vm_fault_t value. + */ +vm_fault_t vmf_insert_pfn_pud_prot(struct vm_fault *vmf, pfn_t pfn, + pgprot_t pgprot, bool write) +{ + unsigned long addr = vmf->address & PUD_MASK; + struct vm_area_struct *vma = vmf->vma; + + /* + * If we had pud_special, we could avoid all these restrictions, + * but we need to be consistent with PTEs and architectures that + * can't support a 'special' bit. + */ + BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) && + !pfn_t_devmap(pfn)); + BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == + (VM_PFNMAP|VM_MIXEDMAP)); + BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); + + if (addr < vma->vm_start || addr >= vma->vm_end) + return VM_FAULT_SIGBUS; + + track_pfn_insert(vma, &pgprot, pfn); + + insert_pfn_pud(vma, addr, vmf->pud, pfn, pgprot, write); + return VM_FAULT_NOPAGE; +} +EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud_prot); +#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ + +static void touch_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd, int flags) +{ + pmd_t _pmd; + + _pmd = pmd_mkyoung(*pmd); + if (flags & FOLL_WRITE) + _pmd = pmd_mkdirty(_pmd); + if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK, + pmd, _pmd, flags & FOLL_WRITE)) + update_mmu_cache_pmd(vma, addr, pmd); +} + +struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd, int flags, struct dev_pagemap **pgmap) +{ + unsigned long pfn = pmd_pfn(*pmd); + struct mm_struct *mm = vma->vm_mm; + struct page *page; + + assert_spin_locked(pmd_lockptr(mm, pmd)); + + /* + * When we COW a devmap PMD entry, we split it into PTEs, so we should + * not be in this function with `flags & FOLL_COW` set. + */ + WARN_ONCE(flags & FOLL_COW, "mm: In follow_devmap_pmd with FOLL_COW set"); + + /* FOLL_GET and FOLL_PIN are mutually exclusive. */ + if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == + (FOLL_PIN | FOLL_GET))) + return NULL; + + if (flags & FOLL_WRITE && !pmd_write(*pmd)) + return NULL; + + if (pmd_present(*pmd) && pmd_devmap(*pmd)) + /* pass */; + else + return NULL; + + if (flags & FOLL_TOUCH) + touch_pmd(vma, addr, pmd, flags); + + /* + * device mapped pages can only be returned if the + * caller will manage the page reference count. + */ + if (!(flags & (FOLL_GET | FOLL_PIN))) + return ERR_PTR(-EEXIST); + + pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT; + *pgmap = get_dev_pagemap(pfn, *pgmap); + if (!*pgmap) + return ERR_PTR(-EFAULT); + page = pfn_to_page(pfn); + if (!try_grab_page(page, flags)) + page = ERR_PTR(-ENOMEM); + + return page; +} + +int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, + struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) +{ + spinlock_t *dst_ptl, *src_ptl; + struct page *src_page; + pmd_t pmd; + pgtable_t pgtable = NULL; + int ret = -ENOMEM; + + /* Skip if can be re-fill on fault */ + if (!vma_is_anonymous(dst_vma)) + return 0; + + pgtable = pte_alloc_one(dst_mm); + if (unlikely(!pgtable)) + goto out; + + dst_ptl = pmd_lock(dst_mm, dst_pmd); + src_ptl = pmd_lockptr(src_mm, src_pmd); + spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); + + ret = -EAGAIN; + pmd = *src_pmd; + +#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION + if (unlikely(is_swap_pmd(pmd))) { + swp_entry_t entry = pmd_to_swp_entry(pmd); + + VM_BUG_ON(!is_pmd_migration_entry(pmd)); + if (is_write_migration_entry(entry)) { + make_migration_entry_read(&entry); + pmd = swp_entry_to_pmd(entry); + if (pmd_swp_soft_dirty(*src_pmd)) + pmd = pmd_swp_mksoft_dirty(pmd); + if (pmd_swp_uffd_wp(*src_pmd)) + pmd = pmd_swp_mkuffd_wp(pmd); + set_pmd_at(src_mm, addr, src_pmd, pmd); + } + add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); + mm_inc_nr_ptes(dst_mm); + pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); + if (!userfaultfd_wp(dst_vma)) + pmd = pmd_swp_clear_uffd_wp(pmd); + set_pmd_at(dst_mm, addr, dst_pmd, pmd); + ret = 0; + goto out_unlock; + } +#endif + + if (unlikely(!pmd_trans_huge(pmd))) { + pte_free(dst_mm, pgtable); + goto out_unlock; + } + /* + * When page table lock is held, the huge zero pmd should not be + * under splitting since we don't split the page itself, only pmd to + * a page table. + */ + if (is_huge_zero_pmd(pmd)) { + /* + * get_huge_zero_page() will never allocate a new page here, + * since we already have a zero page to copy. It just takes a + * reference. + */ + mm_get_huge_zero_page(dst_mm); + goto out_zero_page; + } + + src_page = pmd_page(pmd); + VM_BUG_ON_PAGE(!PageHead(src_page), src_page); + + /* + * If this page is a potentially pinned page, split and retry the fault + * with smaller page size. Normally this should not happen because the + * userspace should use MADV_DONTFORK upon pinned regions. This is a + * best effort that the pinned pages won't be replaced by another + * random page during the coming copy-on-write. + */ + if (unlikely(is_cow_mapping(src_vma->vm_flags) && + atomic_read(&src_mm->has_pinned) && + page_maybe_dma_pinned(src_page))) { + pte_free(dst_mm, pgtable); + spin_unlock(src_ptl); + spin_unlock(dst_ptl); + __split_huge_pmd(src_vma, src_pmd, addr, false, NULL); + return -EAGAIN; + } + + get_page(src_page); + page_dup_rmap(src_page, true); + add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); +out_zero_page: + mm_inc_nr_ptes(dst_mm); + pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); + pmdp_set_wrprotect(src_mm, addr, src_pmd); + if (!userfaultfd_wp(dst_vma)) + pmd = pmd_clear_uffd_wp(pmd); + pmd = pmd_mkold(pmd_wrprotect(pmd)); + set_pmd_at(dst_mm, addr, dst_pmd, pmd); + + ret = 0; +out_unlock: + spin_unlock(src_ptl); + spin_unlock(dst_ptl); +out: + return ret; +} + +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +static void touch_pud(struct vm_area_struct *vma, unsigned long addr, + pud_t *pud, int flags) +{ + pud_t _pud; + + _pud = pud_mkyoung(*pud); + if (flags & FOLL_WRITE) + _pud = pud_mkdirty(_pud); + if (pudp_set_access_flags(vma, addr & HPAGE_PUD_MASK, + pud, _pud, flags & FOLL_WRITE)) + update_mmu_cache_pud(vma, addr, pud); +} + +struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, + pud_t *pud, int flags, struct dev_pagemap **pgmap) +{ + unsigned long pfn = pud_pfn(*pud); + struct mm_struct *mm = vma->vm_mm; + struct page *page; + + assert_spin_locked(pud_lockptr(mm, pud)); + + if (flags & FOLL_WRITE && !pud_write(*pud)) + return NULL; + + /* FOLL_GET and FOLL_PIN are mutually exclusive. */ + if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == + (FOLL_PIN | FOLL_GET))) + return NULL; + + if (pud_present(*pud) && pud_devmap(*pud)) + /* pass */; + else + return NULL; + + if (flags & FOLL_TOUCH) + touch_pud(vma, addr, pud, flags); + + /* + * device mapped pages can only be returned if the + * caller will manage the page reference count. + * + * At least one of FOLL_GET | FOLL_PIN must be set, so assert that here: + */ + if (!(flags & (FOLL_GET | FOLL_PIN))) + return ERR_PTR(-EEXIST); + + pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT; + *pgmap = get_dev_pagemap(pfn, *pgmap); + if (!*pgmap) + return ERR_PTR(-EFAULT); + page = pfn_to_page(pfn); + if (!try_grab_page(page, flags)) + page = ERR_PTR(-ENOMEM); + + return page; +} + +int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pud_t *dst_pud, pud_t *src_pud, unsigned long addr, + struct vm_area_struct *vma) +{ + spinlock_t *dst_ptl, *src_ptl; + pud_t pud; + int ret; + + dst_ptl = pud_lock(dst_mm, dst_pud); + src_ptl = pud_lockptr(src_mm, src_pud); + spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); + + ret = -EAGAIN; + pud = *src_pud; + if (unlikely(!pud_trans_huge(pud) && !pud_devmap(pud))) + goto out_unlock; + + /* + * When page table lock is held, the huge zero pud should not be + * under splitting since we don't split the page itself, only pud to + * a page table. + */ + if (is_huge_zero_pud(pud)) { + /* No huge zero pud yet */ + } + + /* Please refer to comments in copy_huge_pmd() */ + if (unlikely(is_cow_mapping(vma->vm_flags) && + atomic_read(&src_mm->has_pinned) && + page_maybe_dma_pinned(pud_page(pud)))) { + spin_unlock(src_ptl); + spin_unlock(dst_ptl); + __split_huge_pud(vma, src_pud, addr); + return -EAGAIN; + } + + pudp_set_wrprotect(src_mm, addr, src_pud); + pud = pud_mkold(pud_wrprotect(pud)); + set_pud_at(dst_mm, addr, dst_pud, pud); + + ret = 0; +out_unlock: + spin_unlock(src_ptl); + spin_unlock(dst_ptl); + return ret; +} + +void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud) +{ + pud_t entry; + unsigned long haddr; + bool write = vmf->flags & FAULT_FLAG_WRITE; + + vmf->ptl = pud_lock(vmf->vma->vm_mm, vmf->pud); + if (unlikely(!pud_same(*vmf->pud, orig_pud))) + goto unlock; + + entry = pud_mkyoung(orig_pud); + if (write) + entry = pud_mkdirty(entry); + haddr = vmf->address & HPAGE_PUD_MASK; + if (pudp_set_access_flags(vmf->vma, haddr, vmf->pud, entry, write)) + update_mmu_cache_pud(vmf->vma, vmf->address, vmf->pud); + +unlock: + spin_unlock(vmf->ptl); +} +#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ + +void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd) +{ + pmd_t entry; + unsigned long haddr; + bool write = vmf->flags & FAULT_FLAG_WRITE; + + vmf->ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd); + if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) + goto unlock; + + entry = pmd_mkyoung(orig_pmd); + if (write) + entry = pmd_mkdirty(entry); + haddr = vmf->address & HPAGE_PMD_MASK; + if (pmdp_set_access_flags(vmf->vma, haddr, vmf->pmd, entry, write)) + update_mmu_cache_pmd(vmf->vma, vmf->address, vmf->pmd); + +unlock: + spin_unlock(vmf->ptl); +} + +vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd) +{ + struct vm_area_struct *vma = vmf->vma; + struct page *page; + unsigned long haddr = vmf->address & HPAGE_PMD_MASK; + + vmf->ptl = pmd_lockptr(vma->vm_mm, vmf->pmd); + VM_BUG_ON_VMA(!vma->anon_vma, vma); + + if (is_huge_zero_pmd(orig_pmd)) + goto fallback; + + spin_lock(vmf->ptl); + + if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) { + spin_unlock(vmf->ptl); + return 0; + } + + page = pmd_page(orig_pmd); + VM_BUG_ON_PAGE(!PageCompound(page) || !PageHead(page), page); + + /* Lock page for reuse_swap_page() */ + if (!trylock_page(page)) { + get_page(page); + spin_unlock(vmf->ptl); + lock_page(page); + spin_lock(vmf->ptl); + if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) { + spin_unlock(vmf->ptl); + unlock_page(page); + put_page(page); + return 0; + } + put_page(page); + } + + /* + * We can only reuse the page if nobody else maps the huge page or it's + * part. + */ + if (reuse_swap_page(page, NULL)) { + pmd_t entry; + entry = pmd_mkyoung(orig_pmd); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); + if (pmdp_set_access_flags(vma, haddr, vmf->pmd, entry, 1)) + update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); + unlock_page(page); + spin_unlock(vmf->ptl); + return VM_FAULT_WRITE; + } + + unlock_page(page); + spin_unlock(vmf->ptl); +fallback: + __split_huge_pmd(vma, vmf->pmd, vmf->address, false, NULL); + return VM_FAULT_FALLBACK; +} + +/* + * FOLL_FORCE can write to even unwritable pmd's, but only + * after we've gone through a COW cycle and they are dirty. + */ +static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags) +{ + return pmd_write(pmd) || + ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd)); +} + +struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, + unsigned long addr, + pmd_t *pmd, + unsigned int flags) +{ + struct mm_struct *mm = vma->vm_mm; + struct page *page = NULL; + + assert_spin_locked(pmd_lockptr(mm, pmd)); + + if (flags & FOLL_WRITE && !can_follow_write_pmd(*pmd, flags)) + goto out; + + /* Avoid dumping huge zero page */ + if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd)) + return ERR_PTR(-EFAULT); + + /* Full NUMA hinting faults to serialise migration in fault paths */ + if ((flags & FOLL_NUMA) && pmd_protnone(*pmd)) + goto out; + + page = pmd_page(*pmd); + VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page); + + if (!try_grab_page(page, flags)) + return ERR_PTR(-ENOMEM); + + if (flags & FOLL_TOUCH) + touch_pmd(vma, addr, pmd, flags); + + if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) { + /* + * We don't mlock() pte-mapped THPs. This way we can avoid + * leaking mlocked pages into non-VM_LOCKED VMAs. + * + * For anon THP: + * + * In most cases the pmd is the only mapping of the page as we + * break COW for the mlock() -- see gup_flags |= FOLL_WRITE for + * writable private mappings in populate_vma_page_range(). + * + * The only scenario when we have the page shared here is if we + * mlocking read-only mapping shared over fork(). We skip + * mlocking such pages. + * + * For file THP: + * + * We can expect PageDoubleMap() to be stable under page lock: + * for file pages we set it in page_add_file_rmap(), which + * requires page to be locked. + */ + + if (PageAnon(page) && compound_mapcount(page) != 1) + goto skip_mlock; + if (PageDoubleMap(page) || !page->mapping) + goto skip_mlock; + if (!trylock_page(page)) + goto skip_mlock; + if (page->mapping && !PageDoubleMap(page)) + mlock_vma_page(page); + unlock_page(page); + } +skip_mlock: + page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; + VM_BUG_ON_PAGE(!PageCompound(page) && !is_zone_device_page(page), page); + +out: + return page; +} + +/* NUMA hinting page fault entry point for trans huge pmds */ +vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd) +{ + struct vm_area_struct *vma = vmf->vma; + struct anon_vma *anon_vma = NULL; + struct page *page; + unsigned long haddr = vmf->address & HPAGE_PMD_MASK; + int page_nid = NUMA_NO_NODE, this_nid = numa_node_id(); + int target_nid, last_cpupid = -1; + bool page_locked; + bool migrated = false; + bool was_writable; + int flags = 0; + + vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); + if (unlikely(!pmd_same(pmd, *vmf->pmd))) + goto out_unlock; + + /* + * If there are potential migrations, wait for completion and retry + * without disrupting NUMA hinting information. Do not relock and + * check_same as the page may no longer be mapped. + */ + if (unlikely(pmd_trans_migrating(*vmf->pmd))) { + page = pmd_page(*vmf->pmd); + if (!get_page_unless_zero(page)) + goto out_unlock; + spin_unlock(vmf->ptl); + put_and_wait_on_page_locked(page); + goto out; + } + + page = pmd_page(pmd); + BUG_ON(is_huge_zero_page(page)); + page_nid = page_to_nid(page); + last_cpupid = page_cpupid_last(page); + count_vm_numa_event(NUMA_HINT_FAULTS); + if (page_nid == this_nid) { + count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL); + flags |= TNF_FAULT_LOCAL; + } + + /* See similar comment in do_numa_page for explanation */ + if (!pmd_savedwrite(pmd)) + flags |= TNF_NO_GROUP; + + /* + * Acquire the page lock to serialise THP migrations but avoid dropping + * page_table_lock if at all possible + */ + page_locked = trylock_page(page); + target_nid = mpol_misplaced(page, vma, haddr); + if (target_nid == NUMA_NO_NODE) { + /* If the page was locked, there are no parallel migrations */ + if (page_locked) + goto clear_pmdnuma; + } + + /* Migration could have started since the pmd_trans_migrating check */ + if (!page_locked) { + page_nid = NUMA_NO_NODE; + if (!get_page_unless_zero(page)) + goto out_unlock; + spin_unlock(vmf->ptl); + put_and_wait_on_page_locked(page); + goto out; + } + + /* + * Page is misplaced. Page lock serialises migrations. Acquire anon_vma + * to serialises splits + */ + get_page(page); + spin_unlock(vmf->ptl); + anon_vma = page_lock_anon_vma_read(page); + + /* Confirm the PMD did not change while page_table_lock was released */ + spin_lock(vmf->ptl); + if (unlikely(!pmd_same(pmd, *vmf->pmd))) { + unlock_page(page); + put_page(page); + page_nid = NUMA_NO_NODE; + goto out_unlock; + } + + /* Bail if we fail to protect against THP splits for any reason */ + if (unlikely(!anon_vma)) { + put_page(page); + page_nid = NUMA_NO_NODE; + goto clear_pmdnuma; + } + + /* + * Since we took the NUMA fault, we must have observed the !accessible + * bit. Make sure all other CPUs agree with that, to avoid them + * modifying the page we're about to migrate. + * + * Must be done under PTL such that we'll observe the relevant + * inc_tlb_flush_pending(). + * + * We are not sure a pending tlb flush here is for a huge page + * mapping or not. Hence use the tlb range variant + */ + if (mm_tlb_flush_pending(vma->vm_mm)) { + flush_tlb_range(vma, haddr, haddr + HPAGE_PMD_SIZE); + /* + * change_huge_pmd() released the pmd lock before + * invalidating the secondary MMUs sharing the primary + * MMU pagetables (with ->invalidate_range()). The + * mmu_notifier_invalidate_range_end() (which + * internally calls ->invalidate_range()) in + * change_pmd_range() will run after us, so we can't + * rely on it here and we need an explicit invalidate. + */ + mmu_notifier_invalidate_range(vma->vm_mm, haddr, + haddr + HPAGE_PMD_SIZE); + } + + /* + * Migrate the THP to the requested node, returns with page unlocked + * and access rights restored. + */ + spin_unlock(vmf->ptl); + + migrated = migrate_misplaced_transhuge_page(vma->vm_mm, vma, + vmf->pmd, pmd, vmf->address, page, target_nid); + if (migrated) { + flags |= TNF_MIGRATED; + page_nid = target_nid; + } else + flags |= TNF_MIGRATE_FAIL; + + goto out; +clear_pmdnuma: + BUG_ON(!PageLocked(page)); + was_writable = pmd_savedwrite(pmd); + pmd = pmd_modify(pmd, vma->vm_page_prot); + pmd = pmd_mkyoung(pmd); + if (was_writable) + pmd = pmd_mkwrite(pmd); + set_pmd_at(vma->vm_mm, haddr, vmf->pmd, pmd); + update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); + unlock_page(page); +out_unlock: + spin_unlock(vmf->ptl); + +out: + if (anon_vma) + page_unlock_anon_vma_read(anon_vma); + + if (page_nid != NUMA_NO_NODE) + task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR, + flags); + + return 0; +} + +/* + * Return true if we do MADV_FREE successfully on entire pmd page. + * Otherwise, return false. + */ +bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, + pmd_t *pmd, unsigned long addr, unsigned long next) +{ + spinlock_t *ptl; + pmd_t orig_pmd; + struct page *page; + struct mm_struct *mm = tlb->mm; + bool ret = false; + + tlb_change_page_size(tlb, HPAGE_PMD_SIZE); + + ptl = pmd_trans_huge_lock(pmd, vma); + if (!ptl) + goto out_unlocked; + + orig_pmd = *pmd; + if (is_huge_zero_pmd(orig_pmd)) + goto out; + + if (unlikely(!pmd_present(orig_pmd))) { + VM_BUG_ON(thp_migration_supported() && + !is_pmd_migration_entry(orig_pmd)); + goto out; + } + + page = pmd_page(orig_pmd); + /* + * If other processes are mapping this page, we couldn't discard + * the page unless they all do MADV_FREE so let's skip the page. + */ + if (total_mapcount(page) != 1) + goto out; + + if (!trylock_page(page)) + goto out; + + /* + * If user want to discard part-pages of THP, split it so MADV_FREE + * will deactivate only them. + */ + if (next - addr != HPAGE_PMD_SIZE) { + get_page(page); + spin_unlock(ptl); + split_huge_page(page); + unlock_page(page); + put_page(page); + goto out_unlocked; + } + + if (PageDirty(page)) + ClearPageDirty(page); + unlock_page(page); + + if (pmd_young(orig_pmd) || pmd_dirty(orig_pmd)) { + pmdp_invalidate(vma, addr, pmd); + orig_pmd = pmd_mkold(orig_pmd); + orig_pmd = pmd_mkclean(orig_pmd); + + set_pmd_at(mm, addr, pmd, orig_pmd); + tlb_remove_pmd_tlb_entry(tlb, pmd, addr); + } + + mark_page_lazyfree(page); + ret = true; +out: + spin_unlock(ptl); +out_unlocked: + return ret; +} + +static inline void zap_deposited_table(struct mm_struct *mm, pmd_t *pmd) +{ + pgtable_t pgtable; + + pgtable = pgtable_trans_huge_withdraw(mm, pmd); + pte_free(mm, pgtable); + mm_dec_nr_ptes(mm); +} + +int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, + pmd_t *pmd, unsigned long addr) +{ + pmd_t orig_pmd; + spinlock_t *ptl; + + tlb_change_page_size(tlb, HPAGE_PMD_SIZE); + + ptl = __pmd_trans_huge_lock(pmd, vma); + if (!ptl) + return 0; + /* + * For architectures like ppc64 we look at deposited pgtable + * when calling pmdp_huge_get_and_clear. So do the + * pgtable_trans_huge_withdraw after finishing pmdp related + * operations. + */ + orig_pmd = pmdp_huge_get_and_clear_full(vma, addr, pmd, + tlb->fullmm); + tlb_remove_pmd_tlb_entry(tlb, pmd, addr); + if (vma_is_special_huge(vma)) { + if (arch_needs_pgtable_deposit()) + zap_deposited_table(tlb->mm, pmd); + spin_unlock(ptl); + if (is_huge_zero_pmd(orig_pmd)) + tlb_remove_page_size(tlb, pmd_page(orig_pmd), HPAGE_PMD_SIZE); + } else if (is_huge_zero_pmd(orig_pmd)) { + zap_deposited_table(tlb->mm, pmd); + spin_unlock(ptl); + tlb_remove_page_size(tlb, pmd_page(orig_pmd), HPAGE_PMD_SIZE); + } else { + struct page *page = NULL; + int flush_needed = 1; + + if (pmd_present(orig_pmd)) { + page = pmd_page(orig_pmd); + page_remove_rmap(page, true); + VM_BUG_ON_PAGE(page_mapcount(page) < 0, page); + VM_BUG_ON_PAGE(!PageHead(page), page); + } else if (thp_migration_supported()) { + swp_entry_t entry; + + VM_BUG_ON(!is_pmd_migration_entry(orig_pmd)); + entry = pmd_to_swp_entry(orig_pmd); + page = migration_entry_to_page(entry); + flush_needed = 0; + } else + WARN_ONCE(1, "Non present huge pmd without pmd migration enabled!"); + + if (PageAnon(page)) { + zap_deposited_table(tlb->mm, pmd); + add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR); + } else { + if (arch_needs_pgtable_deposit()) + zap_deposited_table(tlb->mm, pmd); + add_mm_counter(tlb->mm, mm_counter_file(page), -HPAGE_PMD_NR); + } + + spin_unlock(ptl); + if (flush_needed) + tlb_remove_page_size(tlb, page, HPAGE_PMD_SIZE); + } + return 1; +} + +#ifndef pmd_move_must_withdraw +static inline int pmd_move_must_withdraw(spinlock_t *new_pmd_ptl, + spinlock_t *old_pmd_ptl, + struct vm_area_struct *vma) +{ + /* + * With split pmd lock we also need to move preallocated + * PTE page table if new_pmd is on different PMD page table. + * + * We also don't deposit and withdraw tables for file pages. + */ + return (new_pmd_ptl != old_pmd_ptl) && vma_is_anonymous(vma); +} +#endif + +static pmd_t move_soft_dirty_pmd(pmd_t pmd) +{ +#ifdef CONFIG_MEM_SOFT_DIRTY + if (unlikely(is_pmd_migration_entry(pmd))) + pmd = pmd_swp_mksoft_dirty(pmd); + else if (pmd_present(pmd)) + pmd = pmd_mksoft_dirty(pmd); +#endif + return pmd; +} + +bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, + unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd) +{ + spinlock_t *old_ptl, *new_ptl; + pmd_t pmd; + struct mm_struct *mm = vma->vm_mm; + bool force_flush = false; + + /* + * The destination pmd shouldn't be established, free_pgtables() + * should have release it. + */ + if (WARN_ON(!pmd_none(*new_pmd))) { + VM_BUG_ON(pmd_trans_huge(*new_pmd)); + return false; + } + + /* + * We don't have to worry about the ordering of src and dst + * ptlocks because exclusive mmap_lock prevents deadlock. + */ + old_ptl = __pmd_trans_huge_lock(old_pmd, vma); + if (old_ptl) { + new_ptl = pmd_lockptr(mm, new_pmd); + if (new_ptl != old_ptl) + spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); + pmd = pmdp_huge_get_and_clear(mm, old_addr, old_pmd); + if (pmd_present(pmd)) + force_flush = true; + VM_BUG_ON(!pmd_none(*new_pmd)); + + if (pmd_move_must_withdraw(new_ptl, old_ptl, vma)) { + pgtable_t pgtable; + pgtable = pgtable_trans_huge_withdraw(mm, old_pmd); + pgtable_trans_huge_deposit(mm, new_pmd, pgtable); + } + pmd = move_soft_dirty_pmd(pmd); + set_pmd_at(mm, new_addr, new_pmd, pmd); + if (force_flush) + flush_tlb_range(vma, old_addr, old_addr + PMD_SIZE); + if (new_ptl != old_ptl) + spin_unlock(new_ptl); + spin_unlock(old_ptl); + return true; + } + return false; +} + +/* + * Returns + * - 0 if PMD could not be locked + * - 1 if PMD was locked but protections unchange and TLB flush unnecessary + * - HPAGE_PMD_NR is protections changed and TLB flush necessary + */ +int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, + unsigned long addr, pgprot_t newprot, unsigned long cp_flags) +{ + struct mm_struct *mm = vma->vm_mm; + spinlock_t *ptl; + pmd_t entry; + bool preserve_write; + int ret; + bool prot_numa = cp_flags & MM_CP_PROT_NUMA; + bool uffd_wp = cp_flags & MM_CP_UFFD_WP; + bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE; + + ptl = __pmd_trans_huge_lock(pmd, vma); + if (!ptl) + return 0; + + preserve_write = prot_numa && pmd_write(*pmd); + ret = 1; + +#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION + if (is_swap_pmd(*pmd)) { + swp_entry_t entry = pmd_to_swp_entry(*pmd); + + VM_BUG_ON(!is_pmd_migration_entry(*pmd)); + if (is_write_migration_entry(entry)) { + pmd_t newpmd; + /* + * A protection check is difficult so + * just be safe and disable write + */ + make_migration_entry_read(&entry); + newpmd = swp_entry_to_pmd(entry); + if (pmd_swp_soft_dirty(*pmd)) + newpmd = pmd_swp_mksoft_dirty(newpmd); + if (pmd_swp_uffd_wp(*pmd)) + newpmd = pmd_swp_mkuffd_wp(newpmd); + set_pmd_at(mm, addr, pmd, newpmd); + } + goto unlock; + } +#endif + + /* + * Avoid trapping faults against the zero page. The read-only + * data is likely to be read-cached on the local CPU and + * local/remote hits to the zero page are not interesting. + */ + if (prot_numa && is_huge_zero_pmd(*pmd)) + goto unlock; + + if (prot_numa && pmd_protnone(*pmd)) + goto unlock; + + /* + * In case prot_numa, we are under mmap_read_lock(mm). It's critical + * to not clear pmd intermittently to avoid race with MADV_DONTNEED + * which is also under mmap_read_lock(mm): + * + * CPU0: CPU1: + * change_huge_pmd(prot_numa=1) + * pmdp_huge_get_and_clear_notify() + * madvise_dontneed() + * zap_pmd_range() + * pmd_trans_huge(*pmd) == 0 (without ptl) + * // skip the pmd + * set_pmd_at(); + * // pmd is re-established + * + * The race makes MADV_DONTNEED miss the huge pmd and don't clear it + * which may break userspace. + * + * pmdp_invalidate() is required to make sure we don't miss + * dirty/young flags set by hardware. + */ + entry = pmdp_invalidate(vma, addr, pmd); + + entry = pmd_modify(entry, newprot); + if (preserve_write) + entry = pmd_mk_savedwrite(entry); + if (uffd_wp) { + entry = pmd_wrprotect(entry); + entry = pmd_mkuffd_wp(entry); + } else if (uffd_wp_resolve) { + /* + * Leave the write bit to be handled by PF interrupt + * handler, then things like COW could be properly + * handled. + */ + entry = pmd_clear_uffd_wp(entry); + } + ret = HPAGE_PMD_NR; + set_pmd_at(mm, addr, pmd, entry); + BUG_ON(vma_is_anonymous(vma) && !preserve_write && pmd_write(entry)); +unlock: + spin_unlock(ptl); + return ret; +} + +/* + * Returns page table lock pointer if a given pmd maps a thp, NULL otherwise. + * + * Note that if it returns page table lock pointer, this routine returns without + * unlocking page table lock. So callers must unlock it. + */ +spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) +{ + spinlock_t *ptl; + ptl = pmd_lock(vma->vm_mm, pmd); + if (likely(is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || + pmd_devmap(*pmd))) + return ptl; + spin_unlock(ptl); + return NULL; +} + +/* + * Returns true if a given pud maps a thp, false otherwise. + * + * Note that if it returns true, this routine returns without unlocking page + * table lock. So callers must unlock it. + */ +spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma) +{ + spinlock_t *ptl; + + ptl = pud_lock(vma->vm_mm, pud); + if (likely(pud_trans_huge(*pud) || pud_devmap(*pud))) + return ptl; + spin_unlock(ptl); + return NULL; +} + +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, + pud_t *pud, unsigned long addr) +{ + spinlock_t *ptl; + + ptl = __pud_trans_huge_lock(pud, vma); + if (!ptl) + return 0; + /* + * For architectures like ppc64 we look at deposited pgtable + * when calling pudp_huge_get_and_clear. So do the + * pgtable_trans_huge_withdraw after finishing pudp related + * operations. + */ + pudp_huge_get_and_clear_full(tlb->mm, addr, pud, tlb->fullmm); + tlb_remove_pud_tlb_entry(tlb, pud, addr); + if (vma_is_special_huge(vma)) { + spin_unlock(ptl); + /* No zero page support yet */ + } else { + /* No support for anonymous PUD pages yet */ + BUG(); + } + return 1; +} + +static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud, + unsigned long haddr) +{ + VM_BUG_ON(haddr & ~HPAGE_PUD_MASK); + VM_BUG_ON_VMA(vma->vm_start > haddr, vma); + VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PUD_SIZE, vma); + VM_BUG_ON(!pud_trans_huge(*pud) && !pud_devmap(*pud)); + + count_vm_event(THP_SPLIT_PUD); + + pudp_huge_clear_flush_notify(vma, haddr, pud); +} + +void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, + unsigned long address) +{ + spinlock_t *ptl; + struct mmu_notifier_range range; + + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, + address & HPAGE_PUD_MASK, + (address & HPAGE_PUD_MASK) + HPAGE_PUD_SIZE); + mmu_notifier_invalidate_range_start(&range); + ptl = pud_lock(vma->vm_mm, pud); + if (unlikely(!pud_trans_huge(*pud) && !pud_devmap(*pud))) + goto out; + __split_huge_pud_locked(vma, pud, range.start); + +out: + spin_unlock(ptl); + /* + * No need to double call mmu_notifier->invalidate_range() callback as + * the above pudp_huge_clear_flush_notify() did already call it. + */ + mmu_notifier_invalidate_range_only_end(&range); +} +#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ + +static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, + unsigned long haddr, pmd_t *pmd) +{ + struct mm_struct *mm = vma->vm_mm; + pgtable_t pgtable; + pmd_t _pmd, old_pmd; + int i; + + /* + * Leave pmd empty until pte is filled note that it is fine to delay + * notification until mmu_notifier_invalidate_range_end() as we are + * replacing a zero pmd write protected page with a zero pte write + * protected page. + * + * See Documentation/vm/mmu_notifier.rst + */ + old_pmd = pmdp_huge_clear_flush(vma, haddr, pmd); + + pgtable = pgtable_trans_huge_withdraw(mm, pmd); + pmd_populate(mm, &_pmd, pgtable); + + for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { + pte_t *pte, entry; + entry = pfn_pte(my_zero_pfn(haddr), vma->vm_page_prot); + entry = pte_mkspecial(entry); + if (pmd_uffd_wp(old_pmd)) + entry = pte_mkuffd_wp(entry); + pte = pte_offset_map(&_pmd, haddr); + VM_BUG_ON(!pte_none(*pte)); + set_pte_at(mm, haddr, pte, entry); + pte_unmap(pte); + } + smp_wmb(); /* make pte visible before pmd */ + pmd_populate(mm, pmd, pgtable); +} + +static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, + unsigned long haddr, bool freeze) +{ + struct mm_struct *mm = vma->vm_mm; + struct page *page; + pgtable_t pgtable; + pmd_t old_pmd, _pmd; + bool young, write, soft_dirty, pmd_migration = false, uffd_wp = false; + unsigned long addr; + int i; + + VM_BUG_ON(haddr & ~HPAGE_PMD_MASK); + VM_BUG_ON_VMA(vma->vm_start > haddr, vma); + VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PMD_SIZE, vma); + VM_BUG_ON(!is_pmd_migration_entry(*pmd) && !pmd_trans_huge(*pmd) + && !pmd_devmap(*pmd)); + + count_vm_event(THP_SPLIT_PMD); + + if (!vma_is_anonymous(vma)) { + old_pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd); + /* + * We are going to unmap this huge page. So + * just go ahead and zap it + */ + if (arch_needs_pgtable_deposit()) + zap_deposited_table(mm, pmd); + if (vma_is_special_huge(vma)) + return; + if (unlikely(is_pmd_migration_entry(old_pmd))) { + swp_entry_t entry; + + entry = pmd_to_swp_entry(old_pmd); + page = migration_entry_to_page(entry); + } else { + page = pmd_page(old_pmd); + if (!PageDirty(page) && pmd_dirty(old_pmd)) + set_page_dirty(page); + if (!PageReferenced(page) && pmd_young(old_pmd)) + SetPageReferenced(page); + page_remove_rmap(page, true); + put_page(page); + } + add_mm_counter(mm, mm_counter_file(page), -HPAGE_PMD_NR); + return; + } + + if (is_huge_zero_pmd(*pmd)) { + /* + * FIXME: Do we want to invalidate secondary mmu by calling + * mmu_notifier_invalidate_range() see comments below inside + * __split_huge_pmd() ? + * + * We are going from a zero huge page write protected to zero + * small page also write protected so it does not seems useful + * to invalidate secondary mmu at this time. + */ + return __split_huge_zero_page_pmd(vma, haddr, pmd); + } + + /* + * Up to this point the pmd is present and huge and userland has the + * whole access to the hugepage during the split (which happens in + * place). If we overwrite the pmd with the not-huge version pointing + * to the pte here (which of course we could if all CPUs were bug + * free), userland could trigger a small page size TLB miss on the + * small sized TLB while the hugepage TLB entry is still established in + * the huge TLB. Some CPU doesn't like that. + * See http://support.amd.com/TechDocs/41322_10h_Rev_Gd.pdf, Erratum + * 383 on page 105. Intel should be safe but is also warns that it's + * only safe if the permission and cache attributes of the two entries + * loaded in the two TLB is identical (which should be the case here). + * But it is generally safer to never allow small and huge TLB entries + * for the same virtual address to be loaded simultaneously. So instead + * of doing "pmd_populate(); flush_pmd_tlb_range();" we first mark the + * current pmd notpresent (atomically because here the pmd_trans_huge + * must remain set at all times on the pmd until the split is complete + * for this pmd), then we flush the SMP TLB and finally we write the + * non-huge version of the pmd entry with pmd_populate. + */ + old_pmd = pmdp_invalidate(vma, haddr, pmd); + + pmd_migration = is_pmd_migration_entry(old_pmd); + if (unlikely(pmd_migration)) { + swp_entry_t entry; + + entry = pmd_to_swp_entry(old_pmd); + page = migration_entry_to_page(entry); + write = is_write_migration_entry(entry); + young = false; + soft_dirty = pmd_swp_soft_dirty(old_pmd); + uffd_wp = pmd_swp_uffd_wp(old_pmd); + } else { + page = pmd_page(old_pmd); + if (pmd_dirty(old_pmd)) + SetPageDirty(page); + write = pmd_write(old_pmd); + young = pmd_young(old_pmd); + soft_dirty = pmd_soft_dirty(old_pmd); + uffd_wp = pmd_uffd_wp(old_pmd); + } + VM_BUG_ON_PAGE(!page_count(page), page); + page_ref_add(page, HPAGE_PMD_NR - 1); + + /* + * Withdraw the table only after we mark the pmd entry invalid. + * This's critical for some architectures (Power). + */ + pgtable = pgtable_trans_huge_withdraw(mm, pmd); + pmd_populate(mm, &_pmd, pgtable); + + for (i = 0, addr = haddr; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE) { + pte_t entry, *pte; + /* + * Note that NUMA hinting access restrictions are not + * transferred to avoid any possibility of altering + * permissions across VMAs. + */ + if (freeze || pmd_migration) { + swp_entry_t swp_entry; + swp_entry = make_migration_entry(page + i, write); + entry = swp_entry_to_pte(swp_entry); + if (soft_dirty) + entry = pte_swp_mksoft_dirty(entry); + if (uffd_wp) + entry = pte_swp_mkuffd_wp(entry); + } else { + entry = mk_pte(page + i, READ_ONCE(vma->vm_page_prot)); + entry = maybe_mkwrite(entry, vma); + if (!write) + entry = pte_wrprotect(entry); + if (!young) + entry = pte_mkold(entry); + if (soft_dirty) + entry = pte_mksoft_dirty(entry); + if (uffd_wp) + entry = pte_mkuffd_wp(entry); + } + pte = pte_offset_map(&_pmd, addr); + BUG_ON(!pte_none(*pte)); + set_pte_at(mm, addr, pte, entry); + if (!pmd_migration) + atomic_inc(&page[i]._mapcount); + pte_unmap(pte); + } + + if (!pmd_migration) { + /* + * Set PG_double_map before dropping compound_mapcount to avoid + * false-negative page_mapped(). + */ + if (compound_mapcount(page) > 1 && + !TestSetPageDoubleMap(page)) { + for (i = 0; i < HPAGE_PMD_NR; i++) + atomic_inc(&page[i]._mapcount); + } + + lock_page_memcg(page); + if (atomic_add_negative(-1, compound_mapcount_ptr(page))) { + /* Last compound_mapcount is gone. */ + __dec_lruvec_page_state(page, NR_ANON_THPS); + if (TestClearPageDoubleMap(page)) { + /* No need in mapcount reference anymore */ + for (i = 0; i < HPAGE_PMD_NR; i++) + atomic_dec(&page[i]._mapcount); + } + } + unlock_page_memcg(page); + } + + smp_wmb(); /* make pte visible before pmd */ + pmd_populate(mm, pmd, pgtable); + + if (freeze) { + for (i = 0; i < HPAGE_PMD_NR; i++) { + page_remove_rmap(page + i, false); + put_page(page + i); + } + } +} + +void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, + unsigned long address, bool freeze, struct page *page) +{ + spinlock_t *ptl; + struct mmu_notifier_range range; + bool do_unlock_page = false; + pmd_t _pmd; + + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, + address & HPAGE_PMD_MASK, + (address & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE); + mmu_notifier_invalidate_range_start(&range); + ptl = pmd_lock(vma->vm_mm, pmd); + + /* + * If caller asks to setup a migration entries, we need a page to check + * pmd against. Otherwise we can end up replacing wrong page. + */ + VM_BUG_ON(freeze && !page); + if (page) { + VM_WARN_ON_ONCE(!PageLocked(page)); + if (page != pmd_page(*pmd)) + goto out; + } + +repeat: + if (pmd_trans_huge(*pmd)) { + if (!page) { + page = pmd_page(*pmd); + /* + * An anonymous page must be locked, to ensure that a + * concurrent reuse_swap_page() sees stable mapcount; + * but reuse_swap_page() is not used on shmem or file, + * and page lock must not be taken when zap_pmd_range() + * calls __split_huge_pmd() while i_mmap_lock is held. + */ + if (PageAnon(page)) { + if (unlikely(!trylock_page(page))) { + get_page(page); + _pmd = *pmd; + spin_unlock(ptl); + lock_page(page); + spin_lock(ptl); + if (unlikely(!pmd_same(*pmd, _pmd))) { + unlock_page(page); + put_page(page); + page = NULL; + goto repeat; + } + put_page(page); + } + do_unlock_page = true; + } + } + if (PageMlocked(page)) + clear_page_mlock(page); + } else if (!(pmd_devmap(*pmd) || is_pmd_migration_entry(*pmd))) + goto out; + __split_huge_pmd_locked(vma, pmd, range.start, freeze); +out: + spin_unlock(ptl); + if (do_unlock_page) + unlock_page(page); + /* + * No need to double call mmu_notifier->invalidate_range() callback. + * They are 3 cases to consider inside __split_huge_pmd_locked(): + * 1) pmdp_huge_clear_flush_notify() call invalidate_range() obvious + * 2) __split_huge_zero_page_pmd() read only zero page and any write + * fault will trigger a flush_notify before pointing to a new page + * (it is fine if the secondary mmu keeps pointing to the old zero + * page in the meantime) + * 3) Split a huge pmd into pte pointing to the same page. No need + * to invalidate secondary tlb entry they are all still valid. + * any further changes to individual pte will notify. So no need + * to call mmu_notifier->invalidate_range() + */ + mmu_notifier_invalidate_range_only_end(&range); +} + +void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, + bool freeze, struct page *page) +{ + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + pgd = pgd_offset(vma->vm_mm, address); + if (!pgd_present(*pgd)) + return; + + p4d = p4d_offset(pgd, address); + if (!p4d_present(*p4d)) + return; + + pud = pud_offset(p4d, address); + if (!pud_present(*pud)) + return; + + pmd = pmd_offset(pud, address); + + __split_huge_pmd(vma, pmd, address, freeze, page); +} + +void vma_adjust_trans_huge(struct vm_area_struct *vma, + unsigned long start, + unsigned long end, + long adjust_next) +{ + /* + * If the new start address isn't hpage aligned and it could + * previously contain an hugepage: check if we need to split + * an huge pmd. + */ + if (start & ~HPAGE_PMD_MASK && + (start & HPAGE_PMD_MASK) >= vma->vm_start && + (start & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= vma->vm_end) + split_huge_pmd_address(vma, start, false, NULL); + + /* + * If the new end address isn't hpage aligned and it could + * previously contain an hugepage: check if we need to split + * an huge pmd. + */ + if (end & ~HPAGE_PMD_MASK && + (end & HPAGE_PMD_MASK) >= vma->vm_start && + (end & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= vma->vm_end) + split_huge_pmd_address(vma, end, false, NULL); + + /* + * If we're also updating the vma->vm_next->vm_start, if the new + * vm_next->vm_start isn't hpage aligned and it could previously + * contain an hugepage: check if we need to split an huge pmd. + */ + if (adjust_next > 0) { + struct vm_area_struct *next = vma->vm_next; + unsigned long nstart = next->vm_start; + nstart += adjust_next; + if (nstart & ~HPAGE_PMD_MASK && + (nstart & HPAGE_PMD_MASK) >= next->vm_start && + (nstart & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= next->vm_end) + split_huge_pmd_address(next, nstart, false, NULL); + } +} + +static void unmap_page(struct page *page) +{ + enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_SYNC | + TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD; + + VM_BUG_ON_PAGE(!PageHead(page), page); + + if (PageAnon(page)) + ttu_flags |= TTU_SPLIT_FREEZE; + + try_to_unmap(page, ttu_flags); + + VM_WARN_ON_ONCE_PAGE(page_mapped(page), page); +} + +static void remap_page(struct page *page, unsigned int nr) +{ + int i; + if (PageTransHuge(page)) { + remove_migration_ptes(page, page, true); + } else { + for (i = 0; i < nr; i++) + remove_migration_ptes(page + i, page + i, true); + } +} + +static void __split_huge_page_tail(struct page *head, int tail, + struct lruvec *lruvec, struct list_head *list) +{ + struct page *page_tail = head + tail; + + VM_BUG_ON_PAGE(atomic_read(&page_tail->_mapcount) != -1, page_tail); + + /* + * Clone page flags before unfreezing refcount. + * + * After successful get_page_unless_zero() might follow flags change, + * for exmaple lock_page() which set PG_waiters. + */ + page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; + page_tail->flags |= (head->flags & + ((1L << PG_referenced) | + (1L << PG_swapbacked) | + (1L << PG_swapcache) | + (1L << PG_mlocked) | + (1L << PG_uptodate) | + (1L << PG_active) | + (1L << PG_workingset) | + (1L << PG_locked) | + (1L << PG_unevictable) | +#ifdef CONFIG_64BIT + (1L << PG_arch_2) | +#endif + (1L << PG_dirty))); + + /* ->mapping in first tail page is compound_mapcount */ + VM_BUG_ON_PAGE(tail > 2 && page_tail->mapping != TAIL_MAPPING, + page_tail); + page_tail->mapping = head->mapping; + page_tail->index = head->index + tail; + + /* Page flags must be visible before we make the page non-compound. */ + smp_wmb(); + + /* + * Clear PageTail before unfreezing page refcount. + * + * After successful get_page_unless_zero() might follow put_page() + * which needs correct compound_head(). + */ + clear_compound_head(page_tail); + + /* Finally unfreeze refcount. Additional reference from page cache. */ + page_ref_unfreeze(page_tail, 1 + (!PageAnon(head) || + PageSwapCache(head))); + + if (page_is_young(head)) + set_page_young(page_tail); + if (page_is_idle(head)) + set_page_idle(page_tail); + + page_cpupid_xchg_last(page_tail, page_cpupid_last(head)); + + /* + * always add to the tail because some iterators expect new + * pages to show after the currently processed elements - e.g. + * migrate_pages + */ + lru_add_page_tail(head, page_tail, lruvec, list); +} + +static void __split_huge_page(struct page *page, struct list_head *list, + pgoff_t end, unsigned long flags) +{ + struct page *head = compound_head(page); + pg_data_t *pgdat = page_pgdat(head); + struct lruvec *lruvec; + struct address_space *swap_cache = NULL; + unsigned long offset = 0; + unsigned int nr = thp_nr_pages(head); + int i; + + lruvec = mem_cgroup_page_lruvec(head, pgdat); + + /* complete memcg works before add pages to LRU */ + split_page_memcg(head, nr); + + if (PageAnon(head) && PageSwapCache(head)) { + swp_entry_t entry = { .val = page_private(head) }; + + offset = swp_offset(entry); + swap_cache = swap_address_space(entry); + xa_lock(&swap_cache->i_pages); + } + + for (i = nr - 1; i >= 1; i--) { + __split_huge_page_tail(head, i, lruvec, list); + /* Some pages can be beyond i_size: drop them from page cache */ + if (head[i].index >= end) { + ClearPageDirty(head + i); + __delete_from_page_cache(head + i, NULL); + if (IS_ENABLED(CONFIG_SHMEM) && PageSwapBacked(head)) + shmem_uncharge(head->mapping->host, 1); + put_page(head + i); + } else if (!PageAnon(page)) { + __xa_store(&head->mapping->i_pages, head[i].index, + head + i, 0); + } else if (swap_cache) { + __xa_store(&swap_cache->i_pages, offset + i, + head + i, 0); + } + } + + ClearPageCompound(head); + + split_page_owner(head, nr); + + /* See comment in __split_huge_page_tail() */ + if (PageAnon(head)) { + /* Additional pin to swap cache */ + if (PageSwapCache(head)) { + page_ref_add(head, 2); + xa_unlock(&swap_cache->i_pages); + } else { + page_ref_inc(head); + } + } else { + /* Additional pin to page cache */ + page_ref_add(head, 2); + xa_unlock(&head->mapping->i_pages); + } + + spin_unlock_irqrestore(&pgdat->lru_lock, flags); + + remap_page(head, nr); + + if (PageSwapCache(head)) { + swp_entry_t entry = { .val = page_private(head) }; + + split_swap_cluster(entry); + } + + for (i = 0; i < nr; i++) { + struct page *subpage = head + i; + if (subpage == page) + continue; + unlock_page(subpage); + + /* + * Subpages may be freed if there wasn't any mapping + * like if add_to_swap() is running on a lru page that + * had its mapping zapped. And freeing these pages + * requires taking the lru_lock so we do the put_page + * of the tail pages after the split is complete. + */ + put_page(subpage); + } +} + +int total_mapcount(struct page *page) +{ + int i, compound, nr, ret; + + VM_BUG_ON_PAGE(PageTail(page), page); + + if (likely(!PageCompound(page))) + return atomic_read(&page->_mapcount) + 1; + + compound = compound_mapcount(page); + nr = compound_nr(page); + if (PageHuge(page)) + return compound; + ret = compound; + for (i = 0; i < nr; i++) + ret += atomic_read(&page[i]._mapcount) + 1; + /* File pages has compound_mapcount included in _mapcount */ + if (!PageAnon(page)) + return ret - compound * nr; + if (PageDoubleMap(page)) + ret -= nr; + return ret; +} + +/* + * This calculates accurately how many mappings a transparent hugepage + * has (unlike page_mapcount() which isn't fully accurate). This full + * accuracy is primarily needed to know if copy-on-write faults can + * reuse the page and change the mapping to read-write instead of + * copying them. At the same time this returns the total_mapcount too. + * + * The function returns the highest mapcount any one of the subpages + * has. If the return value is one, even if different processes are + * mapping different subpages of the transparent hugepage, they can + * all reuse it, because each process is reusing a different subpage. + * + * The total_mapcount is instead counting all virtual mappings of the + * subpages. If the total_mapcount is equal to "one", it tells the + * caller all mappings belong to the same "mm" and in turn the + * anon_vma of the transparent hugepage can become the vma->anon_vma + * local one as no other process may be mapping any of the subpages. + * + * It would be more accurate to replace page_mapcount() with + * page_trans_huge_mapcount(), however we only use + * page_trans_huge_mapcount() in the copy-on-write faults where we + * need full accuracy to avoid breaking page pinning, because + * page_trans_huge_mapcount() is slower than page_mapcount(). + */ +int page_trans_huge_mapcount(struct page *page, int *total_mapcount) +{ + int i, ret, _total_mapcount, mapcount; + + /* hugetlbfs shouldn't call it */ + VM_BUG_ON_PAGE(PageHuge(page), page); + + if (likely(!PageTransCompound(page))) { + mapcount = atomic_read(&page->_mapcount) + 1; + if (total_mapcount) + *total_mapcount = mapcount; + return mapcount; + } + + page = compound_head(page); + + _total_mapcount = ret = 0; + for (i = 0; i < thp_nr_pages(page); i++) { + mapcount = atomic_read(&page[i]._mapcount) + 1; + ret = max(ret, mapcount); + _total_mapcount += mapcount; + } + if (PageDoubleMap(page)) { + ret -= 1; + _total_mapcount -= thp_nr_pages(page); + } + mapcount = compound_mapcount(page); + ret += mapcount; + _total_mapcount += mapcount; + if (total_mapcount) + *total_mapcount = _total_mapcount; + return ret; +} + +/* Racy check whether the huge page can be split */ +bool can_split_huge_page(struct page *page, int *pextra_pins) +{ + int extra_pins; + + /* Additional pins from page cache */ + if (PageAnon(page)) + extra_pins = PageSwapCache(page) ? thp_nr_pages(page) : 0; + else + extra_pins = thp_nr_pages(page); + if (pextra_pins) + *pextra_pins = extra_pins; + return total_mapcount(page) == page_count(page) - extra_pins - 1; +} + +/* + * This function splits huge page into normal pages. @page can point to any + * subpage of huge page to split. Split doesn't change the position of @page. + * + * Only caller must hold pin on the @page, otherwise split fails with -EBUSY. + * The huge page must be locked. + * + * If @list is null, tail pages will be added to LRU list, otherwise, to @list. + * + * Both head page and tail pages will inherit mapping, flags, and so on from + * the hugepage. + * + * GUP pin and PG_locked transferred to @page. Rest subpages can be freed if + * they are not mapped. + * + * Returns 0 if the hugepage is split successfully. + * Returns -EBUSY if the page is pinned or if anon_vma disappeared from under + * us. + */ +int split_huge_page_to_list(struct page *page, struct list_head *list) +{ + struct page *head = compound_head(page); + struct pglist_data *pgdata = NODE_DATA(page_to_nid(head)); + struct deferred_split *ds_queue = get_deferred_split_queue(head); + struct anon_vma *anon_vma = NULL; + struct address_space *mapping = NULL; + int extra_pins, ret; + unsigned long flags; + pgoff_t end; + + VM_BUG_ON_PAGE(is_huge_zero_page(head), head); + VM_BUG_ON_PAGE(!PageLocked(head), head); + VM_BUG_ON_PAGE(!PageCompound(head), head); + + if (PageWriteback(head)) + return -EBUSY; + + if (PageAnon(head)) { + /* + * The caller does not necessarily hold an mmap_lock that would + * prevent the anon_vma disappearing so we first we take a + * reference to it and then lock the anon_vma for write. This + * is similar to page_lock_anon_vma_read except the write lock + * is taken to serialise against parallel split or collapse + * operations. + */ + anon_vma = page_get_anon_vma(head); + if (!anon_vma) { + ret = -EBUSY; + goto out; + } + end = -1; + mapping = NULL; + anon_vma_lock_write(anon_vma); + } else { + mapping = head->mapping; + + /* Truncated ? */ + if (!mapping) { + ret = -EBUSY; + goto out; + } + + anon_vma = NULL; + i_mmap_lock_read(mapping); + + /* + *__split_huge_page() may need to trim off pages beyond EOF: + * but on 32-bit, i_size_read() takes an irq-unsafe seqlock, + * which cannot be nested inside the page tree lock. So note + * end now: i_size itself may be changed at any moment, but + * head page lock is good enough to serialize the trimming. + */ + end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE); + } + + /* + * Racy check if we can split the page, before unmap_page() will + * split PMDs + */ + if (!can_split_huge_page(head, &extra_pins)) { + ret = -EBUSY; + goto out_unlock; + } + + unmap_page(head); + + /* prevent PageLRU to go away from under us, and freeze lru stats */ + spin_lock_irqsave(&pgdata->lru_lock, flags); + + if (mapping) { + XA_STATE(xas, &mapping->i_pages, page_index(head)); + + /* + * Check if the head page is present in page cache. + * We assume all tail are present too, if head is there. + */ + xa_lock(&mapping->i_pages); + if (xas_load(&xas) != head) + goto fail; + } + + /* Prevent deferred_split_scan() touching ->_refcount */ + spin_lock(&ds_queue->split_queue_lock); + if (page_ref_freeze(head, 1 + extra_pins)) { + if (!list_empty(page_deferred_list(head))) { + ds_queue->split_queue_len--; + list_del(page_deferred_list(head)); + } + spin_unlock(&ds_queue->split_queue_lock); + if (mapping) { + if (PageSwapBacked(head)) + __dec_node_page_state(head, NR_SHMEM_THPS); + else + __dec_node_page_state(head, NR_FILE_THPS); + } + + __split_huge_page(page, list, end, flags); + ret = 0; + } else { + spin_unlock(&ds_queue->split_queue_lock); +fail: + if (mapping) + xa_unlock(&mapping->i_pages); + spin_unlock_irqrestore(&pgdata->lru_lock, flags); + remap_page(head, thp_nr_pages(head)); + ret = -EBUSY; + } + +out_unlock: + if (anon_vma) { + anon_vma_unlock_write(anon_vma); + put_anon_vma(anon_vma); + } + if (mapping) + i_mmap_unlock_read(mapping); +out: + count_vm_event(!ret ? THP_SPLIT_PAGE : THP_SPLIT_PAGE_FAILED); + return ret; +} + +void free_transhuge_page(struct page *page) +{ + struct deferred_split *ds_queue = get_deferred_split_queue(page); + unsigned long flags; + + spin_lock_irqsave(&ds_queue->split_queue_lock, flags); + if (!list_empty(page_deferred_list(page))) { + ds_queue->split_queue_len--; + list_del(page_deferred_list(page)); + } + spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); + free_compound_page(page); +} + +void deferred_split_huge_page(struct page *page) +{ + struct deferred_split *ds_queue = get_deferred_split_queue(page); +#ifdef CONFIG_MEMCG + struct mem_cgroup *memcg = compound_head(page)->mem_cgroup; +#endif + unsigned long flags; + + VM_BUG_ON_PAGE(!PageTransHuge(page), page); + + /* + * The try_to_unmap() in page reclaim path might reach here too, + * this may cause a race condition to corrupt deferred split queue. + * And, if page reclaim is already handling the same page, it is + * unnecessary to handle it again in shrinker. + * + * Check PageSwapCache to determine if the page is being + * handled by page reclaim since THP swap would add the page into + * swap cache before calling try_to_unmap(). + */ + if (PageSwapCache(page)) + return; + + if (!list_empty(page_deferred_list(page))) + return; + + spin_lock_irqsave(&ds_queue->split_queue_lock, flags); + if (list_empty(page_deferred_list(page))) { + count_vm_event(THP_DEFERRED_SPLIT_PAGE); + list_add_tail(page_deferred_list(page), &ds_queue->split_queue); + ds_queue->split_queue_len++; +#ifdef CONFIG_MEMCG + if (memcg) + memcg_set_shrinker_bit(memcg, page_to_nid(page), + deferred_split_shrinker.id); +#endif + } + spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); +} + +static unsigned long deferred_split_count(struct shrinker *shrink, + struct shrink_control *sc) +{ + struct pglist_data *pgdata = NODE_DATA(sc->nid); + struct deferred_split *ds_queue = &pgdata->deferred_split_queue; + +#ifdef CONFIG_MEMCG + if (sc->memcg) + ds_queue = &sc->memcg->deferred_split_queue; +#endif + return READ_ONCE(ds_queue->split_queue_len); +} + +static unsigned long deferred_split_scan(struct shrinker *shrink, + struct shrink_control *sc) +{ + struct pglist_data *pgdata = NODE_DATA(sc->nid); + struct deferred_split *ds_queue = &pgdata->deferred_split_queue; + unsigned long flags; + LIST_HEAD(list), *pos, *next; + struct page *page; + int split = 0; + +#ifdef CONFIG_MEMCG + if (sc->memcg) + ds_queue = &sc->memcg->deferred_split_queue; +#endif + + spin_lock_irqsave(&ds_queue->split_queue_lock, flags); + /* Take pin on all head pages to avoid freeing them under us */ + list_for_each_safe(pos, next, &ds_queue->split_queue) { + page = list_entry((void *)pos, struct page, mapping); + page = compound_head(page); + if (get_page_unless_zero(page)) { + list_move(page_deferred_list(page), &list); + } else { + /* We lost race with put_compound_page() */ + list_del_init(page_deferred_list(page)); + ds_queue->split_queue_len--; + } + if (!--sc->nr_to_scan) + break; + } + spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); + + list_for_each_safe(pos, next, &list) { + page = list_entry((void *)pos, struct page, mapping); + if (!trylock_page(page)) + goto next; + /* split_huge_page() removes page from list on success */ + if (!split_huge_page(page)) + split++; + unlock_page(page); +next: + put_page(page); + } + + spin_lock_irqsave(&ds_queue->split_queue_lock, flags); + list_splice_tail(&list, &ds_queue->split_queue); + spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); + + /* + * Stop shrinker if we didn't split any page, but the queue is empty. + * This can happen if pages were freed under us. + */ + if (!split && list_empty(&ds_queue->split_queue)) + return SHRINK_STOP; + return split; +} + +static struct shrinker deferred_split_shrinker = { + .count_objects = deferred_split_count, + .scan_objects = deferred_split_scan, + .seeks = DEFAULT_SEEKS, + .flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE | + SHRINKER_NONSLAB, +}; + +#ifdef CONFIG_DEBUG_FS +static int split_huge_pages_set(void *data, u64 val) +{ + struct zone *zone; + struct page *page; + unsigned long pfn, max_zone_pfn; + unsigned long total = 0, split = 0; + + if (val != 1) + return -EINVAL; + + for_each_populated_zone(zone) { + max_zone_pfn = zone_end_pfn(zone); + for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) { + if (!pfn_valid(pfn)) + continue; + + page = pfn_to_page(pfn); + if (!get_page_unless_zero(page)) + continue; + + if (zone != page_zone(page)) + goto next; + + if (!PageHead(page) || PageHuge(page) || !PageLRU(page)) + goto next; + + total++; + lock_page(page); + if (!split_huge_page(page)) + split++; + unlock_page(page); +next: + put_page(page); + } + } + + pr_info("%lu of %lu THP split\n", split, total); + + return 0; +} +DEFINE_DEBUGFS_ATTRIBUTE(split_huge_pages_fops, NULL, split_huge_pages_set, + "%llu\n"); + +static int __init split_huge_pages_debugfs(void) +{ + debugfs_create_file("split_huge_pages", 0200, NULL, NULL, + &split_huge_pages_fops); + return 0; +} +late_initcall(split_huge_pages_debugfs); +#endif + +#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION +void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, + struct page *page) +{ + struct vm_area_struct *vma = pvmw->vma; + struct mm_struct *mm = vma->vm_mm; + unsigned long address = pvmw->address; + pmd_t pmdval; + swp_entry_t entry; + pmd_t pmdswp; + + if (!(pvmw->pmd && !pvmw->pte)) + return; + + flush_cache_range(vma, address, address + HPAGE_PMD_SIZE); + pmdval = pmdp_invalidate(vma, address, pvmw->pmd); + if (pmd_dirty(pmdval)) + set_page_dirty(page); + entry = make_migration_entry(page, pmd_write(pmdval)); + pmdswp = swp_entry_to_pmd(entry); + if (pmd_soft_dirty(pmdval)) + pmdswp = pmd_swp_mksoft_dirty(pmdswp); + set_pmd_at(mm, address, pvmw->pmd, pmdswp); + page_remove_rmap(page, true); + put_page(page); +} + +void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) +{ + struct vm_area_struct *vma = pvmw->vma; + struct mm_struct *mm = vma->vm_mm; + unsigned long address = pvmw->address; + unsigned long mmun_start = address & HPAGE_PMD_MASK; + pmd_t pmde; + swp_entry_t entry; + + if (!(pvmw->pmd && !pvmw->pte)) + return; + + entry = pmd_to_swp_entry(*pvmw->pmd); + get_page(new); + pmde = pmd_mkold(mk_huge_pmd(new, vma->vm_page_prot)); + if (pmd_swp_soft_dirty(*pvmw->pmd)) + pmde = pmd_mksoft_dirty(pmde); + if (is_write_migration_entry(entry)) + pmde = maybe_pmd_mkwrite(pmde, vma); + if (pmd_swp_uffd_wp(*pvmw->pmd)) + pmde = pmd_wrprotect(pmd_mkuffd_wp(pmde)); + + flush_cache_range(vma, mmun_start, mmun_start + HPAGE_PMD_SIZE); + if (PageAnon(new)) + page_add_anon_rmap(new, vma, mmun_start, true); + else + page_add_file_rmap(new, true); + set_pmd_at(mm, mmun_start, pvmw->pmd, pmde); + if ((vma->vm_flags & VM_LOCKED) && !PageDoubleMap(new)) + mlock_vma_page(new); + update_mmu_cache_pmd(vma, address, pvmw->pmd); +} +#endif diff --git a/mm/hugetlb.c b/mm/hugetlb.c new file mode 100644 index 000000000..81949f6d2 --- /dev/null +++ b/mm/hugetlb.c @@ -0,0 +1,5788 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Generic hugetlb support. + * (C) Nadia Yvette Chambers, April 2004 + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include "internal.h" + +int hugetlb_max_hstate __read_mostly; +unsigned int default_hstate_idx; +struct hstate hstates[HUGE_MAX_HSTATE]; + +#ifdef CONFIG_CMA +static struct cma *hugetlb_cma[MAX_NUMNODES]; +#endif +static unsigned long hugetlb_cma_size __initdata; + +/* + * Minimum page order among possible hugepage sizes, set to a proper value + * at boot time. + */ +static unsigned int minimum_order __read_mostly = UINT_MAX; + +__initdata LIST_HEAD(huge_boot_pages); + +/* for command line parsing */ +static struct hstate * __initdata parsed_hstate; +static unsigned long __initdata default_hstate_max_huge_pages; +static bool __initdata parsed_valid_hugepagesz = true; +static bool __initdata parsed_default_hugepagesz; + +/* + * Protects updates to hugepage_freelists, hugepage_activelist, nr_huge_pages, + * free_huge_pages, and surplus_huge_pages. + */ +DEFINE_SPINLOCK(hugetlb_lock); + +/* + * Serializes faults on the same logical page. This is used to + * prevent spurious OOMs when the hugepage pool is fully utilized. + */ +static int num_fault_mutexes; +struct mutex *hugetlb_fault_mutex_table ____cacheline_aligned_in_smp; + +static inline bool PageHugeFreed(struct page *head) +{ + return page_private(head + 4) == -1UL; +} + +static inline void SetPageHugeFreed(struct page *head) +{ + set_page_private(head + 4, -1UL); +} + +static inline void ClearPageHugeFreed(struct page *head) +{ + set_page_private(head + 4, 0); +} + +/* Forward declaration */ +static int hugetlb_acct_memory(struct hstate *h, long delta); + +static inline void unlock_or_release_subpool(struct hugepage_subpool *spool) +{ + bool free = (spool->count == 0) && (spool->used_hpages == 0); + + spin_unlock(&spool->lock); + + /* If no pages are used, and no other handles to the subpool + * remain, give up any reservations based on minimum size and + * free the subpool */ + if (free) { + if (spool->min_hpages != -1) + hugetlb_acct_memory(spool->hstate, + -spool->min_hpages); + kfree(spool); + } +} + +struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, + long min_hpages) +{ + struct hugepage_subpool *spool; + + spool = kzalloc(sizeof(*spool), GFP_KERNEL); + if (!spool) + return NULL; + + spin_lock_init(&spool->lock); + spool->count = 1; + spool->max_hpages = max_hpages; + spool->hstate = h; + spool->min_hpages = min_hpages; + + if (min_hpages != -1 && hugetlb_acct_memory(h, min_hpages)) { + kfree(spool); + return NULL; + } + spool->rsv_hpages = min_hpages; + + return spool; +} + +void hugepage_put_subpool(struct hugepage_subpool *spool) +{ + spin_lock(&spool->lock); + BUG_ON(!spool->count); + spool->count--; + unlock_or_release_subpool(spool); +} + +/* + * Subpool accounting for allocating and reserving pages. + * Return -ENOMEM if there are not enough resources to satisfy the + * request. Otherwise, return the number of pages by which the + * global pools must be adjusted (upward). The returned value may + * only be different than the passed value (delta) in the case where + * a subpool minimum size must be maintained. + */ +static long hugepage_subpool_get_pages(struct hugepage_subpool *spool, + long delta) +{ + long ret = delta; + + if (!spool) + return ret; + + spin_lock(&spool->lock); + + if (spool->max_hpages != -1) { /* maximum size accounting */ + if ((spool->used_hpages + delta) <= spool->max_hpages) + spool->used_hpages += delta; + else { + ret = -ENOMEM; + goto unlock_ret; + } + } + + /* minimum size accounting */ + if (spool->min_hpages != -1 && spool->rsv_hpages) { + if (delta > spool->rsv_hpages) { + /* + * Asking for more reserves than those already taken on + * behalf of subpool. Return difference. + */ + ret = delta - spool->rsv_hpages; + spool->rsv_hpages = 0; + } else { + ret = 0; /* reserves already accounted for */ + spool->rsv_hpages -= delta; + } + } + +unlock_ret: + spin_unlock(&spool->lock); + return ret; +} + +/* + * Subpool accounting for freeing and unreserving pages. + * Return the number of global page reservations that must be dropped. + * The return value may only be different than the passed value (delta) + * in the case where a subpool minimum size must be maintained. + */ +static long hugepage_subpool_put_pages(struct hugepage_subpool *spool, + long delta) +{ + long ret = delta; + + if (!spool) + return delta; + + spin_lock(&spool->lock); + + if (spool->max_hpages != -1) /* maximum size accounting */ + spool->used_hpages -= delta; + + /* minimum size accounting */ + if (spool->min_hpages != -1 && spool->used_hpages < spool->min_hpages) { + if (spool->rsv_hpages + delta <= spool->min_hpages) + ret = 0; + else + ret = spool->rsv_hpages + delta - spool->min_hpages; + + spool->rsv_hpages += delta; + if (spool->rsv_hpages > spool->min_hpages) + spool->rsv_hpages = spool->min_hpages; + } + + /* + * If hugetlbfs_put_super couldn't free spool due to an outstanding + * quota reference, free it now. + */ + unlock_or_release_subpool(spool); + + return ret; +} + +static inline struct hugepage_subpool *subpool_inode(struct inode *inode) +{ + return HUGETLBFS_SB(inode->i_sb)->spool; +} + +static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma) +{ + return subpool_inode(file_inode(vma->vm_file)); +} + +/* Helper that removes a struct file_region from the resv_map cache and returns + * it for use. + */ +static struct file_region * +get_file_region_entry_from_cache(struct resv_map *resv, long from, long to) +{ + struct file_region *nrg = NULL; + + VM_BUG_ON(resv->region_cache_count <= 0); + + resv->region_cache_count--; + nrg = list_first_entry(&resv->region_cache, struct file_region, link); + list_del(&nrg->link); + + nrg->from = from; + nrg->to = to; + + return nrg; +} + +static void copy_hugetlb_cgroup_uncharge_info(struct file_region *nrg, + struct file_region *rg) +{ +#ifdef CONFIG_CGROUP_HUGETLB + nrg->reservation_counter = rg->reservation_counter; + nrg->css = rg->css; + if (rg->css) + css_get(rg->css); +#endif +} + +/* Helper that records hugetlb_cgroup uncharge info. */ +static void record_hugetlb_cgroup_uncharge_info(struct hugetlb_cgroup *h_cg, + struct hstate *h, + struct resv_map *resv, + struct file_region *nrg) +{ +#ifdef CONFIG_CGROUP_HUGETLB + if (h_cg) { + nrg->reservation_counter = + &h_cg->rsvd_hugepage[hstate_index(h)]; + nrg->css = &h_cg->css; + /* + * The caller will hold exactly one h_cg->css reference for the + * whole contiguous reservation region. But this area might be + * scattered when there are already some file_regions reside in + * it. As a result, many file_regions may share only one css + * reference. In order to ensure that one file_region must hold + * exactly one h_cg->css reference, we should do css_get for + * each file_region and leave the reference held by caller + * untouched. + */ + css_get(&h_cg->css); + if (!resv->pages_per_hpage) + resv->pages_per_hpage = pages_per_huge_page(h); + /* pages_per_hpage should be the same for all entries in + * a resv_map. + */ + VM_BUG_ON(resv->pages_per_hpage != pages_per_huge_page(h)); + } else { + nrg->reservation_counter = NULL; + nrg->css = NULL; + } +#endif +} + +static void put_uncharge_info(struct file_region *rg) +{ +#ifdef CONFIG_CGROUP_HUGETLB + if (rg->css) + css_put(rg->css); +#endif +} + +static bool has_same_uncharge_info(struct file_region *rg, + struct file_region *org) +{ +#ifdef CONFIG_CGROUP_HUGETLB + return rg && org && + rg->reservation_counter == org->reservation_counter && + rg->css == org->css; + +#else + return true; +#endif +} + +static void coalesce_file_region(struct resv_map *resv, struct file_region *rg) +{ + struct file_region *nrg = NULL, *prg = NULL; + + prg = list_prev_entry(rg, link); + if (&prg->link != &resv->regions && prg->to == rg->from && + has_same_uncharge_info(prg, rg)) { + prg->to = rg->to; + + list_del(&rg->link); + put_uncharge_info(rg); + kfree(rg); + + rg = prg; + } + + nrg = list_next_entry(rg, link); + if (&nrg->link != &resv->regions && nrg->from == rg->to && + has_same_uncharge_info(nrg, rg)) { + nrg->from = rg->from; + + list_del(&rg->link); + put_uncharge_info(rg); + kfree(rg); + } +} + +/* + * Must be called with resv->lock held. + * + * Calling this with regions_needed != NULL will count the number of pages + * to be added but will not modify the linked list. And regions_needed will + * indicate the number of file_regions needed in the cache to carry out to add + * the regions for this range. + */ +static long add_reservation_in_range(struct resv_map *resv, long f, long t, + struct hugetlb_cgroup *h_cg, + struct hstate *h, long *regions_needed) +{ + long add = 0; + struct list_head *head = &resv->regions; + long last_accounted_offset = f; + struct file_region *rg = NULL, *trg = NULL, *nrg = NULL; + + if (regions_needed) + *regions_needed = 0; + + /* In this loop, we essentially handle an entry for the range + * [last_accounted_offset, rg->from), at every iteration, with some + * bounds checking. + */ + list_for_each_entry_safe(rg, trg, head, link) { + /* Skip irrelevant regions that start before our range. */ + if (rg->from < f) { + /* If this region ends after the last accounted offset, + * then we need to update last_accounted_offset. + */ + if (rg->to > last_accounted_offset) + last_accounted_offset = rg->to; + continue; + } + + /* When we find a region that starts beyond our range, we've + * finished. + */ + if (rg->from > t) + break; + + /* Add an entry for last_accounted_offset -> rg->from, and + * update last_accounted_offset. + */ + if (rg->from > last_accounted_offset) { + add += rg->from - last_accounted_offset; + if (!regions_needed) { + nrg = get_file_region_entry_from_cache( + resv, last_accounted_offset, rg->from); + record_hugetlb_cgroup_uncharge_info(h_cg, h, + resv, nrg); + list_add(&nrg->link, rg->link.prev); + coalesce_file_region(resv, nrg); + } else + *regions_needed += 1; + } + + last_accounted_offset = rg->to; + } + + /* Handle the case where our range extends beyond + * last_accounted_offset. + */ + if (last_accounted_offset < t) { + add += t - last_accounted_offset; + if (!regions_needed) { + nrg = get_file_region_entry_from_cache( + resv, last_accounted_offset, t); + record_hugetlb_cgroup_uncharge_info(h_cg, h, resv, nrg); + list_add(&nrg->link, rg->link.prev); + coalesce_file_region(resv, nrg); + } else + *regions_needed += 1; + } + + VM_BUG_ON(add < 0); + return add; +} + +/* Must be called with resv->lock acquired. Will drop lock to allocate entries. + */ +static int allocate_file_region_entries(struct resv_map *resv, + int regions_needed) + __must_hold(&resv->lock) +{ + struct list_head allocated_regions; + int to_allocate = 0, i = 0; + struct file_region *trg = NULL, *rg = NULL; + + VM_BUG_ON(regions_needed < 0); + + INIT_LIST_HEAD(&allocated_regions); + + /* + * Check for sufficient descriptors in the cache to accommodate + * the number of in progress add operations plus regions_needed. + * + * This is a while loop because when we drop the lock, some other call + * to region_add or region_del may have consumed some region_entries, + * so we keep looping here until we finally have enough entries for + * (adds_in_progress + regions_needed). + */ + while (resv->region_cache_count < + (resv->adds_in_progress + regions_needed)) { + to_allocate = resv->adds_in_progress + regions_needed - + resv->region_cache_count; + + /* At this point, we should have enough entries in the cache + * for all the existings adds_in_progress. We should only be + * needing to allocate for regions_needed. + */ + VM_BUG_ON(resv->region_cache_count < resv->adds_in_progress); + + spin_unlock(&resv->lock); + for (i = 0; i < to_allocate; i++) { + trg = kmalloc(sizeof(*trg), GFP_KERNEL); + if (!trg) + goto out_of_memory; + list_add(&trg->link, &allocated_regions); + } + + spin_lock(&resv->lock); + + list_splice(&allocated_regions, &resv->region_cache); + resv->region_cache_count += to_allocate; + } + + return 0; + +out_of_memory: + list_for_each_entry_safe(rg, trg, &allocated_regions, link) { + list_del(&rg->link); + kfree(rg); + } + return -ENOMEM; +} + +/* + * Add the huge page range represented by [f, t) to the reserve + * map. Regions will be taken from the cache to fill in this range. + * Sufficient regions should exist in the cache due to the previous + * call to region_chg with the same range, but in some cases the cache will not + * have sufficient entries due to races with other code doing region_add or + * region_del. The extra needed entries will be allocated. + * + * regions_needed is the out value provided by a previous call to region_chg. + * + * Return the number of new huge pages added to the map. This number is greater + * than or equal to zero. If file_region entries needed to be allocated for + * this operation and we were not able to allocate, it returns -ENOMEM. + * region_add of regions of length 1 never allocate file_regions and cannot + * fail; region_chg will always allocate at least 1 entry and a region_add for + * 1 page will only require at most 1 entry. + */ +static long region_add(struct resv_map *resv, long f, long t, + long in_regions_needed, struct hstate *h, + struct hugetlb_cgroup *h_cg) +{ + long add = 0, actual_regions_needed = 0; + + spin_lock(&resv->lock); +retry: + + /* Count how many regions are actually needed to execute this add. */ + add_reservation_in_range(resv, f, t, NULL, NULL, + &actual_regions_needed); + + /* + * Check for sufficient descriptors in the cache to accommodate + * this add operation. Note that actual_regions_needed may be greater + * than in_regions_needed, as the resv_map may have been modified since + * the region_chg call. In this case, we need to make sure that we + * allocate extra entries, such that we have enough for all the + * existing adds_in_progress, plus the excess needed for this + * operation. + */ + if (actual_regions_needed > in_regions_needed && + resv->region_cache_count < + resv->adds_in_progress + + (actual_regions_needed - in_regions_needed)) { + /* region_add operation of range 1 should never need to + * allocate file_region entries. + */ + VM_BUG_ON(t - f <= 1); + + if (allocate_file_region_entries( + resv, actual_regions_needed - in_regions_needed)) { + return -ENOMEM; + } + + goto retry; + } + + add = add_reservation_in_range(resv, f, t, h_cg, h, NULL); + + resv->adds_in_progress -= in_regions_needed; + + spin_unlock(&resv->lock); + VM_BUG_ON(add < 0); + return add; +} + +/* + * Examine the existing reserve map and determine how many + * huge pages in the specified range [f, t) are NOT currently + * represented. This routine is called before a subsequent + * call to region_add that will actually modify the reserve + * map to add the specified range [f, t). region_chg does + * not change the number of huge pages represented by the + * map. A number of new file_region structures is added to the cache as a + * placeholder, for the subsequent region_add call to use. At least 1 + * file_region structure is added. + * + * out_regions_needed is the number of regions added to the + * resv->adds_in_progress. This value needs to be provided to a follow up call + * to region_add or region_abort for proper accounting. + * + * Returns the number of huge pages that need to be added to the existing + * reservation map for the range [f, t). This number is greater or equal to + * zero. -ENOMEM is returned if a new file_region structure or cache entry + * is needed and can not be allocated. + */ +static long region_chg(struct resv_map *resv, long f, long t, + long *out_regions_needed) +{ + long chg = 0; + + spin_lock(&resv->lock); + + /* Count how many hugepages in this range are NOT represented. */ + chg = add_reservation_in_range(resv, f, t, NULL, NULL, + out_regions_needed); + + if (*out_regions_needed == 0) + *out_regions_needed = 1; + + if (allocate_file_region_entries(resv, *out_regions_needed)) + return -ENOMEM; + + resv->adds_in_progress += *out_regions_needed; + + spin_unlock(&resv->lock); + return chg; +} + +/* + * Abort the in progress add operation. The adds_in_progress field + * of the resv_map keeps track of the operations in progress between + * calls to region_chg and region_add. Operations are sometimes + * aborted after the call to region_chg. In such cases, region_abort + * is called to decrement the adds_in_progress counter. regions_needed + * is the value returned by the region_chg call, it is used to decrement + * the adds_in_progress counter. + * + * NOTE: The range arguments [f, t) are not needed or used in this + * routine. They are kept to make reading the calling code easier as + * arguments will match the associated region_chg call. + */ +static void region_abort(struct resv_map *resv, long f, long t, + long regions_needed) +{ + spin_lock(&resv->lock); + VM_BUG_ON(!resv->region_cache_count); + resv->adds_in_progress -= regions_needed; + spin_unlock(&resv->lock); +} + +/* + * Delete the specified range [f, t) from the reserve map. If the + * t parameter is LONG_MAX, this indicates that ALL regions after f + * should be deleted. Locate the regions which intersect [f, t) + * and either trim, delete or split the existing regions. + * + * Returns the number of huge pages deleted from the reserve map. + * In the normal case, the return value is zero or more. In the + * case where a region must be split, a new region descriptor must + * be allocated. If the allocation fails, -ENOMEM will be returned. + * NOTE: If the parameter t == LONG_MAX, then we will never split + * a region and possibly return -ENOMEM. Callers specifying + * t == LONG_MAX do not need to check for -ENOMEM error. + */ +static long region_del(struct resv_map *resv, long f, long t) +{ + struct list_head *head = &resv->regions; + struct file_region *rg, *trg; + struct file_region *nrg = NULL; + long del = 0; + +retry: + spin_lock(&resv->lock); + list_for_each_entry_safe(rg, trg, head, link) { + /* + * Skip regions before the range to be deleted. file_region + * ranges are normally of the form [from, to). However, there + * may be a "placeholder" entry in the map which is of the form + * (from, to) with from == to. Check for placeholder entries + * at the beginning of the range to be deleted. + */ + if (rg->to <= f && (rg->to != rg->from || rg->to != f)) + continue; + + if (rg->from >= t) + break; + + if (f > rg->from && t < rg->to) { /* Must split region */ + /* + * Check for an entry in the cache before dropping + * lock and attempting allocation. + */ + if (!nrg && + resv->region_cache_count > resv->adds_in_progress) { + nrg = list_first_entry(&resv->region_cache, + struct file_region, + link); + list_del(&nrg->link); + resv->region_cache_count--; + } + + if (!nrg) { + spin_unlock(&resv->lock); + nrg = kmalloc(sizeof(*nrg), GFP_KERNEL); + if (!nrg) + return -ENOMEM; + goto retry; + } + + del += t - f; + hugetlb_cgroup_uncharge_file_region( + resv, rg, t - f, false); + + /* New entry for end of split region */ + nrg->from = t; + nrg->to = rg->to; + + copy_hugetlb_cgroup_uncharge_info(nrg, rg); + + INIT_LIST_HEAD(&nrg->link); + + /* Original entry is trimmed */ + rg->to = f; + + list_add(&nrg->link, &rg->link); + nrg = NULL; + break; + } + + if (f <= rg->from && t >= rg->to) { /* Remove entire region */ + del += rg->to - rg->from; + hugetlb_cgroup_uncharge_file_region(resv, rg, + rg->to - rg->from, true); + list_del(&rg->link); + kfree(rg); + continue; + } + + if (f <= rg->from) { /* Trim beginning of region */ + hugetlb_cgroup_uncharge_file_region(resv, rg, + t - rg->from, false); + + del += t - rg->from; + rg->from = t; + } else { /* Trim end of region */ + hugetlb_cgroup_uncharge_file_region(resv, rg, + rg->to - f, false); + + del += rg->to - f; + rg->to = f; + } + } + + spin_unlock(&resv->lock); + kfree(nrg); + return del; +} + +/* + * A rare out of memory error was encountered which prevented removal of + * the reserve map region for a page. The huge page itself was free'ed + * and removed from the page cache. This routine will adjust the subpool + * usage count, and the global reserve count if needed. By incrementing + * these counts, the reserve map entry which could not be deleted will + * appear as a "reserved" entry instead of simply dangling with incorrect + * counts. + */ +void hugetlb_fix_reserve_counts(struct inode *inode) +{ + struct hugepage_subpool *spool = subpool_inode(inode); + long rsv_adjust; + bool reserved = false; + + rsv_adjust = hugepage_subpool_get_pages(spool, 1); + if (rsv_adjust > 0) { + struct hstate *h = hstate_inode(inode); + + if (!hugetlb_acct_memory(h, 1)) + reserved = true; + } else if (!rsv_adjust) { + reserved = true; + } + + if (!reserved) + pr_warn("hugetlb: Huge Page Reserved count may go negative.\n"); +} + +/* + * Count and return the number of huge pages in the reserve map + * that intersect with the range [f, t). + */ +static long region_count(struct resv_map *resv, long f, long t) +{ + struct list_head *head = &resv->regions; + struct file_region *rg; + long chg = 0; + + spin_lock(&resv->lock); + /* Locate each segment we overlap with, and count that overlap. */ + list_for_each_entry(rg, head, link) { + long seg_from; + long seg_to; + + if (rg->to <= f) + continue; + if (rg->from >= t) + break; + + seg_from = max(rg->from, f); + seg_to = min(rg->to, t); + + chg += seg_to - seg_from; + } + spin_unlock(&resv->lock); + + return chg; +} + +/* + * Convert the address within this vma to the page offset within + * the mapping, in pagecache page units; huge pages here. + */ +static pgoff_t vma_hugecache_offset(struct hstate *h, + struct vm_area_struct *vma, unsigned long address) +{ + return ((address - vma->vm_start) >> huge_page_shift(h)) + + (vma->vm_pgoff >> huge_page_order(h)); +} + +pgoff_t linear_hugepage_index(struct vm_area_struct *vma, + unsigned long address) +{ + return vma_hugecache_offset(hstate_vma(vma), vma, address); +} +EXPORT_SYMBOL_GPL(linear_hugepage_index); + +/* + * Return the size of the pages allocated when backing a VMA. In the majority + * cases this will be same size as used by the page table entries. + */ +unsigned long vma_kernel_pagesize(struct vm_area_struct *vma) +{ + if (vma->vm_ops && vma->vm_ops->pagesize) + return vma->vm_ops->pagesize(vma); + return PAGE_SIZE; +} +EXPORT_SYMBOL_GPL(vma_kernel_pagesize); + +/* + * Return the page size being used by the MMU to back a VMA. In the majority + * of cases, the page size used by the kernel matches the MMU size. On + * architectures where it differs, an architecture-specific 'strong' + * version of this symbol is required. + */ +__weak unsigned long vma_mmu_pagesize(struct vm_area_struct *vma) +{ + return vma_kernel_pagesize(vma); +} + +/* + * Flags for MAP_PRIVATE reservations. These are stored in the bottom + * bits of the reservation map pointer, which are always clear due to + * alignment. + */ +#define HPAGE_RESV_OWNER (1UL << 0) +#define HPAGE_RESV_UNMAPPED (1UL << 1) +#define HPAGE_RESV_MASK (HPAGE_RESV_OWNER | HPAGE_RESV_UNMAPPED) + +/* + * These helpers are used to track how many pages are reserved for + * faults in a MAP_PRIVATE mapping. Only the process that called mmap() + * is guaranteed to have their future faults succeed. + * + * With the exception of reset_vma_resv_huge_pages() which is called at fork(), + * the reserve counters are updated with the hugetlb_lock held. It is safe + * to reset the VMA at fork() time as it is not in use yet and there is no + * chance of the global counters getting corrupted as a result of the values. + * + * The private mapping reservation is represented in a subtly different + * manner to a shared mapping. A shared mapping has a region map associated + * with the underlying file, this region map represents the backing file + * pages which have ever had a reservation assigned which this persists even + * after the page is instantiated. A private mapping has a region map + * associated with the original mmap which is attached to all VMAs which + * reference it, this region map represents those offsets which have consumed + * reservation ie. where pages have been instantiated. + */ +static unsigned long get_vma_private_data(struct vm_area_struct *vma) +{ + return (unsigned long)vma->vm_private_data; +} + +static void set_vma_private_data(struct vm_area_struct *vma, + unsigned long value) +{ + vma->vm_private_data = (void *)value; +} + +static void +resv_map_set_hugetlb_cgroup_uncharge_info(struct resv_map *resv_map, + struct hugetlb_cgroup *h_cg, + struct hstate *h) +{ +#ifdef CONFIG_CGROUP_HUGETLB + if (!h_cg || !h) { + resv_map->reservation_counter = NULL; + resv_map->pages_per_hpage = 0; + resv_map->css = NULL; + } else { + resv_map->reservation_counter = + &h_cg->rsvd_hugepage[hstate_index(h)]; + resv_map->pages_per_hpage = pages_per_huge_page(h); + resv_map->css = &h_cg->css; + } +#endif +} + +struct resv_map *resv_map_alloc(void) +{ + struct resv_map *resv_map = kmalloc(sizeof(*resv_map), GFP_KERNEL); + struct file_region *rg = kmalloc(sizeof(*rg), GFP_KERNEL); + + if (!resv_map || !rg) { + kfree(resv_map); + kfree(rg); + return NULL; + } + + kref_init(&resv_map->refs); + spin_lock_init(&resv_map->lock); + INIT_LIST_HEAD(&resv_map->regions); + + resv_map->adds_in_progress = 0; + /* + * Initialize these to 0. On shared mappings, 0's here indicate these + * fields don't do cgroup accounting. On private mappings, these will be + * re-initialized to the proper values, to indicate that hugetlb cgroup + * reservations are to be un-charged from here. + */ + resv_map_set_hugetlb_cgroup_uncharge_info(resv_map, NULL, NULL); + + INIT_LIST_HEAD(&resv_map->region_cache); + list_add(&rg->link, &resv_map->region_cache); + resv_map->region_cache_count = 1; + + return resv_map; +} + +void resv_map_release(struct kref *ref) +{ + struct resv_map *resv_map = container_of(ref, struct resv_map, refs); + struct list_head *head = &resv_map->region_cache; + struct file_region *rg, *trg; + + /* Clear out any active regions before we release the map. */ + region_del(resv_map, 0, LONG_MAX); + + /* ... and any entries left in the cache */ + list_for_each_entry_safe(rg, trg, head, link) { + list_del(&rg->link); + kfree(rg); + } + + VM_BUG_ON(resv_map->adds_in_progress); + + kfree(resv_map); +} + +static inline struct resv_map *inode_resv_map(struct inode *inode) +{ + /* + * At inode evict time, i_mapping may not point to the original + * address space within the inode. This original address space + * contains the pointer to the resv_map. So, always use the + * address space embedded within the inode. + * The VERY common case is inode->mapping == &inode->i_data but, + * this may not be true for device special inodes. + */ + return (struct resv_map *)(&inode->i_data)->private_data; +} + +static struct resv_map *vma_resv_map(struct vm_area_struct *vma) +{ + VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); + if (vma->vm_flags & VM_MAYSHARE) { + struct address_space *mapping = vma->vm_file->f_mapping; + struct inode *inode = mapping->host; + + return inode_resv_map(inode); + + } else { + return (struct resv_map *)(get_vma_private_data(vma) & + ~HPAGE_RESV_MASK); + } +} + +static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map) +{ + VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); + VM_BUG_ON_VMA(vma->vm_flags & VM_MAYSHARE, vma); + + set_vma_private_data(vma, (get_vma_private_data(vma) & + HPAGE_RESV_MASK) | (unsigned long)map); +} + +static void set_vma_resv_flags(struct vm_area_struct *vma, unsigned long flags) +{ + VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); + VM_BUG_ON_VMA(vma->vm_flags & VM_MAYSHARE, vma); + + set_vma_private_data(vma, get_vma_private_data(vma) | flags); +} + +static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag) +{ + VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); + + return (get_vma_private_data(vma) & flag) != 0; +} + +/* Reset counters to 0 and clear all HPAGE_RESV_* flags */ +void reset_vma_resv_huge_pages(struct vm_area_struct *vma) +{ + VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); + if (!(vma->vm_flags & VM_MAYSHARE)) + vma->vm_private_data = (void *)0; +} + +/* Returns true if the VMA has associated reserve pages */ +static bool vma_has_reserves(struct vm_area_struct *vma, long chg) +{ + if (vma->vm_flags & VM_NORESERVE) { + /* + * This address is already reserved by other process(chg == 0), + * so, we should decrement reserved count. Without decrementing, + * reserve count remains after releasing inode, because this + * allocated page will go into page cache and is regarded as + * coming from reserved pool in releasing step. Currently, we + * don't have any other solution to deal with this situation + * properly, so add work-around here. + */ + if (vma->vm_flags & VM_MAYSHARE && chg == 0) + return true; + else + return false; + } + + /* Shared mappings always use reserves */ + if (vma->vm_flags & VM_MAYSHARE) { + /* + * We know VM_NORESERVE is not set. Therefore, there SHOULD + * be a region map for all pages. The only situation where + * there is no region map is if a hole was punched via + * fallocate. In this case, there really are no reserves to + * use. This situation is indicated if chg != 0. + */ + if (chg) + return false; + else + return true; + } + + /* + * Only the process that called mmap() has reserves for + * private mappings. + */ + if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { + /* + * Like the shared case above, a hole punch or truncate + * could have been performed on the private mapping. + * Examine the value of chg to determine if reserves + * actually exist or were previously consumed. + * Very Subtle - The value of chg comes from a previous + * call to vma_needs_reserves(). The reserve map for + * private mappings has different (opposite) semantics + * than that of shared mappings. vma_needs_reserves() + * has already taken this difference in semantics into + * account. Therefore, the meaning of chg is the same + * as in the shared case above. Code could easily be + * combined, but keeping it separate draws attention to + * subtle differences. + */ + if (chg) + return false; + else + return true; + } + + return false; +} + +static void enqueue_huge_page(struct hstate *h, struct page *page) +{ + int nid = page_to_nid(page); + list_move(&page->lru, &h->hugepage_freelists[nid]); + h->free_huge_pages++; + h->free_huge_pages_node[nid]++; + SetPageHugeFreed(page); +} + +static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid) +{ + struct page *page; + bool nocma = !!(current->flags & PF_MEMALLOC_NOCMA); + + list_for_each_entry(page, &h->hugepage_freelists[nid], lru) { + if (nocma && is_migrate_cma_page(page)) + continue; + + if (PageHWPoison(page)) + continue; + + list_move(&page->lru, &h->hugepage_activelist); + set_page_refcounted(page); + ClearPageHugeFreed(page); + h->free_huge_pages--; + h->free_huge_pages_node[nid]--; + return page; + } + + return NULL; +} + +static struct page *dequeue_huge_page_nodemask(struct hstate *h, gfp_t gfp_mask, int nid, + nodemask_t *nmask) +{ + unsigned int cpuset_mems_cookie; + struct zonelist *zonelist; + struct zone *zone; + struct zoneref *z; + int node = NUMA_NO_NODE; + + zonelist = node_zonelist(nid, gfp_mask); + +retry_cpuset: + cpuset_mems_cookie = read_mems_allowed_begin(); + for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nmask) { + struct page *page; + + if (!cpuset_zone_allowed(zone, gfp_mask)) + continue; + /* + * no need to ask again on the same node. Pool is node rather than + * zone aware + */ + if (zone_to_nid(zone) == node) + continue; + node = zone_to_nid(zone); + + page = dequeue_huge_page_node_exact(h, node); + if (page) + return page; + } + if (unlikely(read_mems_allowed_retry(cpuset_mems_cookie))) + goto retry_cpuset; + + return NULL; +} + +static struct page *dequeue_huge_page_vma(struct hstate *h, + struct vm_area_struct *vma, + unsigned long address, int avoid_reserve, + long chg) +{ + struct page *page; + struct mempolicy *mpol; + gfp_t gfp_mask; + nodemask_t *nodemask; + int nid; + + /* + * A child process with MAP_PRIVATE mappings created by their parent + * have no page reserves. This check ensures that reservations are + * not "stolen". The child may still get SIGKILLed + */ + if (!vma_has_reserves(vma, chg) && + h->free_huge_pages - h->resv_huge_pages == 0) + goto err; + + /* If reserves cannot be used, ensure enough pages are in the pool */ + if (avoid_reserve && h->free_huge_pages - h->resv_huge_pages == 0) + goto err; + + gfp_mask = htlb_alloc_mask(h); + nid = huge_node(vma, address, gfp_mask, &mpol, &nodemask); + page = dequeue_huge_page_nodemask(h, gfp_mask, nid, nodemask); + if (page && !avoid_reserve && vma_has_reserves(vma, chg)) { + SetPagePrivate(page); + h->resv_huge_pages--; + } + + mpol_cond_put(mpol); + return page; + +err: + return NULL; +} + +/* + * common helper functions for hstate_next_node_to_{alloc|free}. + * We may have allocated or freed a huge page based on a different + * nodes_allowed previously, so h->next_node_to_{alloc|free} might + * be outside of *nodes_allowed. Ensure that we use an allowed + * node for alloc or free. + */ +static int next_node_allowed(int nid, nodemask_t *nodes_allowed) +{ + nid = next_node_in(nid, *nodes_allowed); + VM_BUG_ON(nid >= MAX_NUMNODES); + + return nid; +} + +static int get_valid_node_allowed(int nid, nodemask_t *nodes_allowed) +{ + if (!node_isset(nid, *nodes_allowed)) + nid = next_node_allowed(nid, nodes_allowed); + return nid; +} + +/* + * returns the previously saved node ["this node"] from which to + * allocate a persistent huge page for the pool and advance the + * next node from which to allocate, handling wrap at end of node + * mask. + */ +static int hstate_next_node_to_alloc(struct hstate *h, + nodemask_t *nodes_allowed) +{ + int nid; + + VM_BUG_ON(!nodes_allowed); + + nid = get_valid_node_allowed(h->next_nid_to_alloc, nodes_allowed); + h->next_nid_to_alloc = next_node_allowed(nid, nodes_allowed); + + return nid; +} + +/* + * helper for free_pool_huge_page() - return the previously saved + * node ["this node"] from which to free a huge page. Advance the + * next node id whether or not we find a free huge page to free so + * that the next attempt to free addresses the next node. + */ +static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) +{ + int nid; + + VM_BUG_ON(!nodes_allowed); + + nid = get_valid_node_allowed(h->next_nid_to_free, nodes_allowed); + h->next_nid_to_free = next_node_allowed(nid, nodes_allowed); + + return nid; +} + +#define for_each_node_mask_to_alloc(hs, nr_nodes, node, mask) \ + for (nr_nodes = nodes_weight(*mask); \ + nr_nodes > 0 && \ + ((node = hstate_next_node_to_alloc(hs, mask)) || 1); \ + nr_nodes--) + +#define for_each_node_mask_to_free(hs, nr_nodes, node, mask) \ + for (nr_nodes = nodes_weight(*mask); \ + nr_nodes > 0 && \ + ((node = hstate_next_node_to_free(hs, mask)) || 1); \ + nr_nodes--) + +#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE +static void destroy_compound_gigantic_page(struct page *page, + unsigned int order) +{ + int i; + int nr_pages = 1 << order; + struct page *p = page + 1; + + atomic_set(compound_mapcount_ptr(page), 0); + atomic_set(compound_pincount_ptr(page), 0); + + for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) { + clear_compound_head(p); + set_page_refcounted(p); + } + + set_compound_order(page, 0); + page[1].compound_nr = 0; + __ClearPageHead(page); +} + +static void free_gigantic_page(struct page *page, unsigned int order) +{ + /* + * If the page isn't allocated using the cma allocator, + * cma_release() returns false. + */ +#ifdef CONFIG_CMA + if (cma_release(hugetlb_cma[page_to_nid(page)], page, 1 << order)) + return; +#endif + + free_contig_range(page_to_pfn(page), 1 << order); +} + +#ifdef CONFIG_CONTIG_ALLOC +static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, + int nid, nodemask_t *nodemask) +{ + unsigned long nr_pages = 1UL << huge_page_order(h); + if (nid == NUMA_NO_NODE) + nid = numa_mem_id(); + +#ifdef CONFIG_CMA + { + struct page *page; + int node; + + if (hugetlb_cma[nid]) { + page = cma_alloc(hugetlb_cma[nid], nr_pages, + huge_page_order(h), true); + if (page) + return page; + } + + if (!(gfp_mask & __GFP_THISNODE)) { + for_each_node_mask(node, *nodemask) { + if (node == nid || !hugetlb_cma[node]) + continue; + + page = cma_alloc(hugetlb_cma[node], nr_pages, + huge_page_order(h), true); + if (page) + return page; + } + } + } +#endif + + return alloc_contig_pages(nr_pages, gfp_mask, nid, nodemask); +} + +#else /* !CONFIG_CONTIG_ALLOC */ +static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, + int nid, nodemask_t *nodemask) +{ + return NULL; +} +#endif /* CONFIG_CONTIG_ALLOC */ + +#else /* !CONFIG_ARCH_HAS_GIGANTIC_PAGE */ +static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, + int nid, nodemask_t *nodemask) +{ + return NULL; +} +static inline void free_gigantic_page(struct page *page, unsigned int order) { } +static inline void destroy_compound_gigantic_page(struct page *page, + unsigned int order) { } +#endif + +static void update_and_free_page(struct hstate *h, struct page *page) +{ + int i; + struct page *subpage = page; + + if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) + return; + + h->nr_huge_pages--; + h->nr_huge_pages_node[page_to_nid(page)]--; + for (i = 0; i < pages_per_huge_page(h); + i++, subpage = mem_map_next(subpage, page, i)) { + subpage->flags &= ~(1 << PG_locked | 1 << PG_error | + 1 << PG_referenced | 1 << PG_dirty | + 1 << PG_active | 1 << PG_private | + 1 << PG_writeback); + } + VM_BUG_ON_PAGE(hugetlb_cgroup_from_page(page), page); + VM_BUG_ON_PAGE(hugetlb_cgroup_from_page_rsvd(page), page); + set_compound_page_dtor(page, NULL_COMPOUND_DTOR); + set_page_refcounted(page); + if (hstate_is_gigantic(h)) { + /* + * Temporarily drop the hugetlb_lock, because + * we might block in free_gigantic_page(). + */ + spin_unlock(&hugetlb_lock); + destroy_compound_gigantic_page(page, huge_page_order(h)); + free_gigantic_page(page, huge_page_order(h)); + spin_lock(&hugetlb_lock); + } else { + __free_pages(page, huge_page_order(h)); + } +} + +struct hstate *size_to_hstate(unsigned long size) +{ + struct hstate *h; + + for_each_hstate(h) { + if (huge_page_size(h) == size) + return h; + } + return NULL; +} + +/* + * Test to determine whether the hugepage is "active/in-use" (i.e. being linked + * to hstate->hugepage_activelist.) + * + * This function can be called for tail pages, but never returns true for them. + */ +bool page_huge_active(struct page *page) +{ + return PageHeadHuge(page) && PagePrivate(&page[1]); +} + +/* never called for tail page */ +void set_page_huge_active(struct page *page) +{ + VM_BUG_ON_PAGE(!PageHeadHuge(page), page); + SetPagePrivate(&page[1]); +} + +static void clear_page_huge_active(struct page *page) +{ + VM_BUG_ON_PAGE(!PageHeadHuge(page), page); + ClearPagePrivate(&page[1]); +} + +/* + * Internal hugetlb specific page flag. Do not use outside of the hugetlb + * code + */ +static inline bool PageHugeTemporary(struct page *page) +{ + if (!PageHuge(page)) + return false; + + return (unsigned long)page[2].mapping == -1U; +} + +static inline void SetPageHugeTemporary(struct page *page) +{ + page[2].mapping = (void *)-1U; +} + +static inline void ClearPageHugeTemporary(struct page *page) +{ + page[2].mapping = NULL; +} + +static void __free_huge_page(struct page *page) +{ + /* + * Can't pass hstate in here because it is called from the + * compound page destructor. + */ + struct hstate *h = page_hstate(page); + int nid = page_to_nid(page); + struct hugepage_subpool *spool = + (struct hugepage_subpool *)page_private(page); + bool restore_reserve; + + VM_BUG_ON_PAGE(page_count(page), page); + VM_BUG_ON_PAGE(page_mapcount(page), page); + + set_page_private(page, 0); + page->mapping = NULL; + restore_reserve = PagePrivate(page); + ClearPagePrivate(page); + + /* + * If PagePrivate() was set on page, page allocation consumed a + * reservation. If the page was associated with a subpool, there + * would have been a page reserved in the subpool before allocation + * via hugepage_subpool_get_pages(). Since we are 'restoring' the + * reservtion, do not call hugepage_subpool_put_pages() as this will + * remove the reserved page from the subpool. + */ + if (!restore_reserve) { + /* + * A return code of zero implies that the subpool will be + * under its minimum size if the reservation is not restored + * after page is free. Therefore, force restore_reserve + * operation. + */ + if (hugepage_subpool_put_pages(spool, 1) == 0) + restore_reserve = true; + } + + spin_lock(&hugetlb_lock); + clear_page_huge_active(page); + hugetlb_cgroup_uncharge_page(hstate_index(h), + pages_per_huge_page(h), page); + hugetlb_cgroup_uncharge_page_rsvd(hstate_index(h), + pages_per_huge_page(h), page); + if (restore_reserve) + h->resv_huge_pages++; + + if (PageHugeTemporary(page)) { + list_del(&page->lru); + ClearPageHugeTemporary(page); + update_and_free_page(h, page); + } else if (h->surplus_huge_pages_node[nid]) { + /* remove the page from active list */ + list_del(&page->lru); + update_and_free_page(h, page); + h->surplus_huge_pages--; + h->surplus_huge_pages_node[nid]--; + } else { + arch_clear_hugepage_flags(page); + enqueue_huge_page(h, page); + } + spin_unlock(&hugetlb_lock); +} + +/* + * As free_huge_page() can be called from a non-task context, we have + * to defer the actual freeing in a workqueue to prevent potential + * hugetlb_lock deadlock. + * + * free_hpage_workfn() locklessly retrieves the linked list of pages to + * be freed and frees them one-by-one. As the page->mapping pointer is + * going to be cleared in __free_huge_page() anyway, it is reused as the + * llist_node structure of a lockless linked list of huge pages to be freed. + */ +static LLIST_HEAD(hpage_freelist); + +static void free_hpage_workfn(struct work_struct *work) +{ + struct llist_node *node; + struct page *page; + + node = llist_del_all(&hpage_freelist); + + while (node) { + page = container_of((struct address_space **)node, + struct page, mapping); + node = node->next; + __free_huge_page(page); + } +} +static DECLARE_WORK(free_hpage_work, free_hpage_workfn); + +void free_huge_page(struct page *page) +{ + /* + * Defer freeing if in non-task context to avoid hugetlb_lock deadlock. + */ + if (!in_task()) { + /* + * Only call schedule_work() if hpage_freelist is previously + * empty. Otherwise, schedule_work() had been called but the + * workfn hasn't retrieved the list yet. + */ + if (llist_add((struct llist_node *)&page->mapping, + &hpage_freelist)) + schedule_work(&free_hpage_work); + return; + } + + __free_huge_page(page); +} + +static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) +{ + INIT_LIST_HEAD(&page->lru); + set_compound_page_dtor(page, HUGETLB_PAGE_DTOR); + set_hugetlb_cgroup(page, NULL); + set_hugetlb_cgroup_rsvd(page, NULL); + spin_lock(&hugetlb_lock); + h->nr_huge_pages++; + h->nr_huge_pages_node[nid]++; + ClearPageHugeFreed(page); + spin_unlock(&hugetlb_lock); +} + +static void prep_compound_gigantic_page(struct page *page, unsigned int order) +{ + int i; + int nr_pages = 1 << order; + struct page *p = page + 1; + + /* we rely on prep_new_huge_page to set the destructor */ + set_compound_order(page, order); + __ClearPageReserved(page); + __SetPageHead(page); + for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) { + /* + * For gigantic hugepages allocated through bootmem at + * boot, it's safer to be consistent with the not-gigantic + * hugepages and clear the PG_reserved bit from all tail pages + * too. Otherwise drivers using get_user_pages() to access tail + * pages may get the reference counting wrong if they see + * PG_reserved set on a tail page (despite the head page not + * having PG_reserved set). Enforcing this consistency between + * head and tail pages allows drivers to optimize away a check + * on the head page when they need know if put_page() is needed + * after get_user_pages(). + */ + __ClearPageReserved(p); + set_page_count(p, 0); + set_compound_head(p, page); + } + atomic_set(compound_mapcount_ptr(page), -1); + atomic_set(compound_pincount_ptr(page), 0); +} + +/* + * PageHuge() only returns true for hugetlbfs pages, but not for normal or + * transparent huge pages. See the PageTransHuge() documentation for more + * details. + */ +int PageHuge(struct page *page) +{ + if (!PageCompound(page)) + return 0; + + page = compound_head(page); + return page[1].compound_dtor == HUGETLB_PAGE_DTOR; +} +EXPORT_SYMBOL_GPL(PageHuge); + +/* + * PageHeadHuge() only returns true for hugetlbfs head page, but not for + * normal or transparent huge pages. + */ +int PageHeadHuge(struct page *page_head) +{ + if (!PageHead(page_head)) + return 0; + + return page_head[1].compound_dtor == HUGETLB_PAGE_DTOR; +} + +/* + * Find and lock address space (mapping) in write mode. + * + * Upon entry, the page is locked which means that page_mapping() is + * stable. Due to locking order, we can only trylock_write. If we can + * not get the lock, simply return NULL to caller. + */ +struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage) +{ + struct address_space *mapping = page_mapping(hpage); + + if (!mapping) + return mapping; + + if (i_mmap_trylock_write(mapping)) + return mapping; + + return NULL; +} + +pgoff_t hugetlb_basepage_index(struct page *page) +{ + struct page *page_head = compound_head(page); + pgoff_t index = page_index(page_head); + unsigned long compound_idx; + + if (compound_order(page_head) >= MAX_ORDER) + compound_idx = page_to_pfn(page) - page_to_pfn(page_head); + else + compound_idx = page - page_head; + + return (index << compound_order(page_head)) + compound_idx; +} + +static struct page *alloc_buddy_huge_page(struct hstate *h, + gfp_t gfp_mask, int nid, nodemask_t *nmask, + nodemask_t *node_alloc_noretry) +{ + int order = huge_page_order(h); + struct page *page; + bool alloc_try_hard = true; + + /* + * By default we always try hard to allocate the page with + * __GFP_RETRY_MAYFAIL flag. However, if we are allocating pages in + * a loop (to adjust global huge page counts) and previous allocation + * failed, do not continue to try hard on the same node. Use the + * node_alloc_noretry bitmap to manage this state information. + */ + if (node_alloc_noretry && node_isset(nid, *node_alloc_noretry)) + alloc_try_hard = false; + gfp_mask |= __GFP_COMP|__GFP_NOWARN; + if (alloc_try_hard) + gfp_mask |= __GFP_RETRY_MAYFAIL; + if (nid == NUMA_NO_NODE) + nid = numa_mem_id(); + page = __alloc_pages_nodemask(gfp_mask, order, nid, nmask); + if (page) + __count_vm_event(HTLB_BUDDY_PGALLOC); + else + __count_vm_event(HTLB_BUDDY_PGALLOC_FAIL); + + /* + * If we did not specify __GFP_RETRY_MAYFAIL, but still got a page this + * indicates an overall state change. Clear bit so that we resume + * normal 'try hard' allocations. + */ + if (node_alloc_noretry && page && !alloc_try_hard) + node_clear(nid, *node_alloc_noretry); + + /* + * If we tried hard to get a page but failed, set bit so that + * subsequent attempts will not try as hard until there is an + * overall state change. + */ + if (node_alloc_noretry && !page && alloc_try_hard) + node_set(nid, *node_alloc_noretry); + + return page; +} + +/* + * Common helper to allocate a fresh hugetlb page. All specific allocators + * should use this function to get new hugetlb pages + */ +static struct page *alloc_fresh_huge_page(struct hstate *h, + gfp_t gfp_mask, int nid, nodemask_t *nmask, + nodemask_t *node_alloc_noretry) +{ + struct page *page; + + if (hstate_is_gigantic(h)) + page = alloc_gigantic_page(h, gfp_mask, nid, nmask); + else + page = alloc_buddy_huge_page(h, gfp_mask, + nid, nmask, node_alloc_noretry); + if (!page) + return NULL; + + if (hstate_is_gigantic(h)) + prep_compound_gigantic_page(page, huge_page_order(h)); + prep_new_huge_page(h, page, page_to_nid(page)); + + return page; +} + +/* + * Allocates a fresh page to the hugetlb allocator pool in the node interleaved + * manner. + */ +static int alloc_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed, + nodemask_t *node_alloc_noretry) +{ + struct page *page; + int nr_nodes, node; + gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; + + for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) { + page = alloc_fresh_huge_page(h, gfp_mask, node, nodes_allowed, + node_alloc_noretry); + if (page) + break; + } + + if (!page) + return 0; + + put_page(page); /* free it into the hugepage allocator */ + + return 1; +} + +/* + * Free huge page from pool from next node to free. + * Attempt to keep persistent huge pages more or less + * balanced over allowed nodes. + * Called with hugetlb_lock locked. + */ +static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed, + bool acct_surplus) +{ + int nr_nodes, node; + int ret = 0; + + for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { + /* + * If we're returning unused surplus pages, only examine + * nodes with surplus pages. + */ + if ((!acct_surplus || h->surplus_huge_pages_node[node]) && + !list_empty(&h->hugepage_freelists[node])) { + struct page *page = + list_entry(h->hugepage_freelists[node].next, + struct page, lru); + list_del(&page->lru); + h->free_huge_pages--; + h->free_huge_pages_node[node]--; + if (acct_surplus) { + h->surplus_huge_pages--; + h->surplus_huge_pages_node[node]--; + } + update_and_free_page(h, page); + ret = 1; + break; + } + } + + return ret; +} + +/* + * Dissolve a given free hugepage into free buddy pages. This function does + * nothing for in-use hugepages and non-hugepages. + * This function returns values like below: + * + * -EBUSY: failed to dissolved free hugepages or the hugepage is in-use + * (allocated or reserved.) + * 0: successfully dissolved free hugepages or the page is not a + * hugepage (considered as already dissolved) + */ +int dissolve_free_huge_page(struct page *page) +{ + int rc = -EBUSY; + +retry: + /* Not to disrupt normal path by vainly holding hugetlb_lock */ + if (!PageHuge(page)) + return 0; + + spin_lock(&hugetlb_lock); + if (!PageHuge(page)) { + rc = 0; + goto out; + } + + if (!page_count(page)) { + struct page *head = compound_head(page); + struct hstate *h = page_hstate(head); + int nid = page_to_nid(head); + if (h->free_huge_pages - h->resv_huge_pages == 0) + goto out; + + /* + * We should make sure that the page is already on the free list + * when it is dissolved. + */ + if (unlikely(!PageHugeFreed(head))) { + spin_unlock(&hugetlb_lock); + cond_resched(); + + /* + * Theoretically, we should return -EBUSY when we + * encounter this race. In fact, we have a chance + * to successfully dissolve the page if we do a + * retry. Because the race window is quite small. + * If we seize this opportunity, it is an optimization + * for increasing the success rate of dissolving page. + */ + goto retry; + } + + /* + * Move PageHWPoison flag from head page to the raw error page, + * which makes any subpages rather than the error page reusable. + */ + if (PageHWPoison(head) && page != head) { + SetPageHWPoison(page); + ClearPageHWPoison(head); + } + list_del(&head->lru); + h->free_huge_pages--; + h->free_huge_pages_node[nid]--; + h->max_huge_pages--; + update_and_free_page(h, head); + rc = 0; + } +out: + spin_unlock(&hugetlb_lock); + return rc; +} + +/* + * Dissolve free hugepages in a given pfn range. Used by memory hotplug to + * make specified memory blocks removable from the system. + * Note that this will dissolve a free gigantic hugepage completely, if any + * part of it lies within the given range. + * Also note that if dissolve_free_huge_page() returns with an error, all + * free hugepages that were dissolved before that error are lost. + */ +int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn) +{ + unsigned long pfn; + struct page *page; + int rc = 0; + + if (!hugepages_supported()) + return rc; + + for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << minimum_order) { + page = pfn_to_page(pfn); + rc = dissolve_free_huge_page(page); + if (rc) + break; + } + + return rc; +} + +/* + * Allocates a fresh surplus page from the page allocator. + */ +static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask, + int nid, nodemask_t *nmask) +{ + struct page *page = NULL; + + if (hstate_is_gigantic(h)) + return NULL; + + spin_lock(&hugetlb_lock); + if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) + goto out_unlock; + spin_unlock(&hugetlb_lock); + + page = alloc_fresh_huge_page(h, gfp_mask, nid, nmask, NULL); + if (!page) + return NULL; + + spin_lock(&hugetlb_lock); + /* + * We could have raced with the pool size change. + * Double check that and simply deallocate the new page + * if we would end up overcommiting the surpluses. Abuse + * temporary page to workaround the nasty free_huge_page + * codeflow + */ + if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) { + SetPageHugeTemporary(page); + spin_unlock(&hugetlb_lock); + put_page(page); + return NULL; + } else { + h->surplus_huge_pages++; + h->surplus_huge_pages_node[page_to_nid(page)]++; + } + +out_unlock: + spin_unlock(&hugetlb_lock); + + return page; +} + +static struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask, + int nid, nodemask_t *nmask) +{ + struct page *page; + + if (hstate_is_gigantic(h)) + return NULL; + + page = alloc_fresh_huge_page(h, gfp_mask, nid, nmask, NULL); + if (!page) + return NULL; + + /* + * We do not account these pages as surplus because they are only + * temporary and will be released properly on the last reference + */ + SetPageHugeTemporary(page); + + return page; +} + +/* + * Use the VMA's mpolicy to allocate a huge page from the buddy. + */ +static +struct page *alloc_buddy_huge_page_with_mpol(struct hstate *h, + struct vm_area_struct *vma, unsigned long addr) +{ + struct page *page; + struct mempolicy *mpol; + gfp_t gfp_mask = htlb_alloc_mask(h); + int nid; + nodemask_t *nodemask; + + nid = huge_node(vma, addr, gfp_mask, &mpol, &nodemask); + page = alloc_surplus_huge_page(h, gfp_mask, nid, nodemask); + mpol_cond_put(mpol); + + return page; +} + +/* page migration callback function */ +struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, + nodemask_t *nmask, gfp_t gfp_mask) +{ + spin_lock(&hugetlb_lock); + if (h->free_huge_pages - h->resv_huge_pages > 0) { + struct page *page; + + page = dequeue_huge_page_nodemask(h, gfp_mask, preferred_nid, nmask); + if (page) { + spin_unlock(&hugetlb_lock); + return page; + } + } + spin_unlock(&hugetlb_lock); + + return alloc_migrate_huge_page(h, gfp_mask, preferred_nid, nmask); +} + +/* mempolicy aware migration callback */ +struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, + unsigned long address) +{ + struct mempolicy *mpol; + nodemask_t *nodemask; + struct page *page; + gfp_t gfp_mask; + int node; + + gfp_mask = htlb_alloc_mask(h); + node = huge_node(vma, address, gfp_mask, &mpol, &nodemask); + page = alloc_huge_page_nodemask(h, node, nodemask, gfp_mask); + mpol_cond_put(mpol); + + return page; +} + +/* + * Increase the hugetlb pool such that it can accommodate a reservation + * of size 'delta'. + */ +static int gather_surplus_pages(struct hstate *h, int delta) + __must_hold(&hugetlb_lock) +{ + struct list_head surplus_list; + struct page *page, *tmp; + int ret, i; + int needed, allocated; + bool alloc_ok = true; + + needed = (h->resv_huge_pages + delta) - h->free_huge_pages; + if (needed <= 0) { + h->resv_huge_pages += delta; + return 0; + } + + allocated = 0; + INIT_LIST_HEAD(&surplus_list); + + ret = -ENOMEM; +retry: + spin_unlock(&hugetlb_lock); + for (i = 0; i < needed; i++) { + page = alloc_surplus_huge_page(h, htlb_alloc_mask(h), + NUMA_NO_NODE, NULL); + if (!page) { + alloc_ok = false; + break; + } + list_add(&page->lru, &surplus_list); + cond_resched(); + } + allocated += i; + + /* + * After retaking hugetlb_lock, we need to recalculate 'needed' + * because either resv_huge_pages or free_huge_pages may have changed. + */ + spin_lock(&hugetlb_lock); + needed = (h->resv_huge_pages + delta) - + (h->free_huge_pages + allocated); + if (needed > 0) { + if (alloc_ok) + goto retry; + /* + * We were not able to allocate enough pages to + * satisfy the entire reservation so we free what + * we've allocated so far. + */ + goto free; + } + /* + * The surplus_list now contains _at_least_ the number of extra pages + * needed to accommodate the reservation. Add the appropriate number + * of pages to the hugetlb pool and free the extras back to the buddy + * allocator. Commit the entire reservation here to prevent another + * process from stealing the pages as they are added to the pool but + * before they are reserved. + */ + needed += allocated; + h->resv_huge_pages += delta; + ret = 0; + + /* Free the needed pages to the hugetlb pool */ + list_for_each_entry_safe(page, tmp, &surplus_list, lru) { + if ((--needed) < 0) + break; + /* + * This page is now managed by the hugetlb allocator and has + * no users -- drop the buddy allocator's reference. + */ + put_page_testzero(page); + VM_BUG_ON_PAGE(page_count(page), page); + enqueue_huge_page(h, page); + } +free: + spin_unlock(&hugetlb_lock); + + /* Free unnecessary surplus pages to the buddy allocator */ + list_for_each_entry_safe(page, tmp, &surplus_list, lru) + put_page(page); + spin_lock(&hugetlb_lock); + + return ret; +} + +/* + * This routine has two main purposes: + * 1) Decrement the reservation count (resv_huge_pages) by the value passed + * in unused_resv_pages. This corresponds to the prior adjustments made + * to the associated reservation map. + * 2) Free any unused surplus pages that may have been allocated to satisfy + * the reservation. As many as unused_resv_pages may be freed. + * + * Called with hugetlb_lock held. However, the lock could be dropped (and + * reacquired) during calls to cond_resched_lock. Whenever dropping the lock, + * we must make sure nobody else can claim pages we are in the process of + * freeing. Do this by ensuring resv_huge_page always is greater than the + * number of huge pages we plan to free when dropping the lock. + */ +static void return_unused_surplus_pages(struct hstate *h, + unsigned long unused_resv_pages) +{ + unsigned long nr_pages; + + /* Cannot return gigantic pages currently */ + if (hstate_is_gigantic(h)) + goto out; + + /* + * Part (or even all) of the reservation could have been backed + * by pre-allocated pages. Only free surplus pages. + */ + nr_pages = min(unused_resv_pages, h->surplus_huge_pages); + + /* + * We want to release as many surplus pages as possible, spread + * evenly across all nodes with memory. Iterate across these nodes + * until we can no longer free unreserved surplus pages. This occurs + * when the nodes with surplus pages have no free pages. + * free_pool_huge_page() will balance the freed pages across the + * on-line nodes with memory and will handle the hstate accounting. + * + * Note that we decrement resv_huge_pages as we free the pages. If + * we drop the lock, resv_huge_pages will still be sufficiently large + * to cover subsequent pages we may free. + */ + while (nr_pages--) { + h->resv_huge_pages--; + unused_resv_pages--; + if (!free_pool_huge_page(h, &node_states[N_MEMORY], 1)) + goto out; + cond_resched_lock(&hugetlb_lock); + } + +out: + /* Fully uncommit the reservation */ + h->resv_huge_pages -= unused_resv_pages; +} + + +/* + * vma_needs_reservation, vma_commit_reservation and vma_end_reservation + * are used by the huge page allocation routines to manage reservations. + * + * vma_needs_reservation is called to determine if the huge page at addr + * within the vma has an associated reservation. If a reservation is + * needed, the value 1 is returned. The caller is then responsible for + * managing the global reservation and subpool usage counts. After + * the huge page has been allocated, vma_commit_reservation is called + * to add the page to the reservation map. If the page allocation fails, + * the reservation must be ended instead of committed. vma_end_reservation + * is called in such cases. + * + * In the normal case, vma_commit_reservation returns the same value + * as the preceding vma_needs_reservation call. The only time this + * is not the case is if a reserve map was changed between calls. It + * is the responsibility of the caller to notice the difference and + * take appropriate action. + * + * vma_add_reservation is used in error paths where a reservation must + * be restored when a newly allocated huge page must be freed. It is + * to be called after calling vma_needs_reservation to determine if a + * reservation exists. + */ +enum vma_resv_mode { + VMA_NEEDS_RESV, + VMA_COMMIT_RESV, + VMA_END_RESV, + VMA_ADD_RESV, +}; +static long __vma_reservation_common(struct hstate *h, + struct vm_area_struct *vma, unsigned long addr, + enum vma_resv_mode mode) +{ + struct resv_map *resv; + pgoff_t idx; + long ret; + long dummy_out_regions_needed; + + resv = vma_resv_map(vma); + if (!resv) + return 1; + + idx = vma_hugecache_offset(h, vma, addr); + switch (mode) { + case VMA_NEEDS_RESV: + ret = region_chg(resv, idx, idx + 1, &dummy_out_regions_needed); + /* We assume that vma_reservation_* routines always operate on + * 1 page, and that adding to resv map a 1 page entry can only + * ever require 1 region. + */ + VM_BUG_ON(dummy_out_regions_needed != 1); + break; + case VMA_COMMIT_RESV: + ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); + /* region_add calls of range 1 should never fail. */ + VM_BUG_ON(ret < 0); + break; + case VMA_END_RESV: + region_abort(resv, idx, idx + 1, 1); + ret = 0; + break; + case VMA_ADD_RESV: + if (vma->vm_flags & VM_MAYSHARE) { + ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); + /* region_add calls of range 1 should never fail. */ + VM_BUG_ON(ret < 0); + } else { + region_abort(resv, idx, idx + 1, 1); + ret = region_del(resv, idx, idx + 1); + } + break; + default: + BUG(); + } + + if (vma->vm_flags & VM_MAYSHARE) + return ret; + else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) && ret >= 0) { + /* + * In most cases, reserves always exist for private mappings. + * However, a file associated with mapping could have been + * hole punched or truncated after reserves were consumed. + * As subsequent fault on such a range will not use reserves. + * Subtle - The reserve map for private mappings has the + * opposite meaning than that of shared mappings. If NO + * entry is in the reserve map, it means a reservation exists. + * If an entry exists in the reserve map, it means the + * reservation has already been consumed. As a result, the + * return value of this routine is the opposite of the + * value returned from reserve map manipulation routines above. + */ + if (ret) + return 0; + else + return 1; + } + else + return ret < 0 ? ret : 0; +} + +static long vma_needs_reservation(struct hstate *h, + struct vm_area_struct *vma, unsigned long addr) +{ + return __vma_reservation_common(h, vma, addr, VMA_NEEDS_RESV); +} + +static long vma_commit_reservation(struct hstate *h, + struct vm_area_struct *vma, unsigned long addr) +{ + return __vma_reservation_common(h, vma, addr, VMA_COMMIT_RESV); +} + +static void vma_end_reservation(struct hstate *h, + struct vm_area_struct *vma, unsigned long addr) +{ + (void)__vma_reservation_common(h, vma, addr, VMA_END_RESV); +} + +static long vma_add_reservation(struct hstate *h, + struct vm_area_struct *vma, unsigned long addr) +{ + return __vma_reservation_common(h, vma, addr, VMA_ADD_RESV); +} + +/* + * This routine is called to restore a reservation on error paths. In the + * specific error paths, a huge page was allocated (via alloc_huge_page) + * and is about to be freed. If a reservation for the page existed, + * alloc_huge_page would have consumed the reservation and set PagePrivate + * in the newly allocated page. When the page is freed via free_huge_page, + * the global reservation count will be incremented if PagePrivate is set. + * However, free_huge_page can not adjust the reserve map. Adjust the + * reserve map here to be consistent with global reserve count adjustments + * to be made by free_huge_page. + */ +static void restore_reserve_on_error(struct hstate *h, + struct vm_area_struct *vma, unsigned long address, + struct page *page) +{ + if (unlikely(PagePrivate(page))) { + long rc = vma_needs_reservation(h, vma, address); + + if (unlikely(rc < 0)) { + /* + * Rare out of memory condition in reserve map + * manipulation. Clear PagePrivate so that + * global reserve count will not be incremented + * by free_huge_page. This will make it appear + * as though the reservation for this page was + * consumed. This may prevent the task from + * faulting in the page at a later time. This + * is better than inconsistent global huge page + * accounting of reserve counts. + */ + ClearPagePrivate(page); + } else if (rc) { + rc = vma_add_reservation(h, vma, address); + if (unlikely(rc < 0)) + /* + * See above comment about rare out of + * memory condition. + */ + ClearPagePrivate(page); + } else + vma_end_reservation(h, vma, address); + } +} + +struct page *alloc_huge_page(struct vm_area_struct *vma, + unsigned long addr, int avoid_reserve) +{ + struct hugepage_subpool *spool = subpool_vma(vma); + struct hstate *h = hstate_vma(vma); + struct page *page; + long map_chg, map_commit; + long gbl_chg; + int ret, idx; + struct hugetlb_cgroup *h_cg; + bool deferred_reserve; + + idx = hstate_index(h); + /* + * Examine the region/reserve map to determine if the process + * has a reservation for the page to be allocated. A return + * code of zero indicates a reservation exists (no change). + */ + map_chg = gbl_chg = vma_needs_reservation(h, vma, addr); + if (map_chg < 0) + return ERR_PTR(-ENOMEM); + + /* + * Processes that did not create the mapping will have no + * reserves as indicated by the region/reserve map. Check + * that the allocation will not exceed the subpool limit. + * Allocations for MAP_NORESERVE mappings also need to be + * checked against any subpool limit. + */ + if (map_chg || avoid_reserve) { + gbl_chg = hugepage_subpool_get_pages(spool, 1); + if (gbl_chg < 0) { + vma_end_reservation(h, vma, addr); + return ERR_PTR(-ENOSPC); + } + + /* + * Even though there was no reservation in the region/reserve + * map, there could be reservations associated with the + * subpool that can be used. This would be indicated if the + * return value of hugepage_subpool_get_pages() is zero. + * However, if avoid_reserve is specified we still avoid even + * the subpool reservations. + */ + if (avoid_reserve) + gbl_chg = 1; + } + + /* If this allocation is not consuming a reservation, charge it now. + */ + deferred_reserve = map_chg || avoid_reserve || !vma_resv_map(vma); + if (deferred_reserve) { + ret = hugetlb_cgroup_charge_cgroup_rsvd( + idx, pages_per_huge_page(h), &h_cg); + if (ret) + goto out_subpool_put; + } + + ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg); + if (ret) + goto out_uncharge_cgroup_reservation; + + spin_lock(&hugetlb_lock); + /* + * glb_chg is passed to indicate whether or not a page must be taken + * from the global free pool (global change). gbl_chg == 0 indicates + * a reservation exists for the allocation. + */ + page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve, gbl_chg); + if (!page) { + spin_unlock(&hugetlb_lock); + page = alloc_buddy_huge_page_with_mpol(h, vma, addr); + if (!page) + goto out_uncharge_cgroup; + spin_lock(&hugetlb_lock); + if (!avoid_reserve && vma_has_reserves(vma, gbl_chg)) { + SetPagePrivate(page); + h->resv_huge_pages--; + } + list_add(&page->lru, &h->hugepage_activelist); + /* Fall through */ + } + hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, page); + /* If allocation is not consuming a reservation, also store the + * hugetlb_cgroup pointer on the page. + */ + if (deferred_reserve) { + hugetlb_cgroup_commit_charge_rsvd(idx, pages_per_huge_page(h), + h_cg, page); + } + + spin_unlock(&hugetlb_lock); + + set_page_private(page, (unsigned long)spool); + + map_commit = vma_commit_reservation(h, vma, addr); + if (unlikely(map_chg > map_commit)) { + /* + * The page was added to the reservation map between + * vma_needs_reservation and vma_commit_reservation. + * This indicates a race with hugetlb_reserve_pages. + * Adjust for the subpool count incremented above AND + * in hugetlb_reserve_pages for the same page. Also, + * the reservation count added in hugetlb_reserve_pages + * no longer applies. + */ + long rsv_adjust; + + rsv_adjust = hugepage_subpool_put_pages(spool, 1); + hugetlb_acct_memory(h, -rsv_adjust); + if (deferred_reserve) + hugetlb_cgroup_uncharge_page_rsvd(hstate_index(h), + pages_per_huge_page(h), page); + } + return page; + +out_uncharge_cgroup: + hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg); +out_uncharge_cgroup_reservation: + if (deferred_reserve) + hugetlb_cgroup_uncharge_cgroup_rsvd(idx, pages_per_huge_page(h), + h_cg); +out_subpool_put: + if (map_chg || avoid_reserve) + hugepage_subpool_put_pages(spool, 1); + vma_end_reservation(h, vma, addr); + return ERR_PTR(-ENOSPC); +} + +int alloc_bootmem_huge_page(struct hstate *h) + __attribute__ ((weak, alias("__alloc_bootmem_huge_page"))); +int __alloc_bootmem_huge_page(struct hstate *h) +{ + struct huge_bootmem_page *m; + int nr_nodes, node; + + for_each_node_mask_to_alloc(h, nr_nodes, node, &node_states[N_MEMORY]) { + void *addr; + + addr = memblock_alloc_try_nid_raw( + huge_page_size(h), huge_page_size(h), + 0, MEMBLOCK_ALLOC_ACCESSIBLE, node); + if (addr) { + /* + * Use the beginning of the huge page to store the + * huge_bootmem_page struct (until gather_bootmem + * puts them into the mem_map). + */ + m = addr; + goto found; + } + } + return 0; + +found: + BUG_ON(!IS_ALIGNED(virt_to_phys(m), huge_page_size(h))); + /* Put them into a private list first because mem_map is not up yet */ + INIT_LIST_HEAD(&m->list); + list_add(&m->list, &huge_boot_pages); + m->hstate = h; + return 1; +} + +/* + * Put bootmem huge pages into the standard lists after mem_map is up. + * Note: This only applies to gigantic (order > MAX_ORDER) pages. + */ +static void __init gather_bootmem_prealloc(void) +{ + struct huge_bootmem_page *m; + + list_for_each_entry(m, &huge_boot_pages, list) { + struct page *page = virt_to_page(m); + struct hstate *h = m->hstate; + + VM_BUG_ON(!hstate_is_gigantic(h)); + WARN_ON(page_count(page) != 1); + prep_compound_gigantic_page(page, huge_page_order(h)); + WARN_ON(PageReserved(page)); + prep_new_huge_page(h, page, page_to_nid(page)); + put_page(page); /* free it into the hugepage allocator */ + + /* + * We need to restore the 'stolen' pages to totalram_pages + * in order to fix confusing memory reports from free(1) and + * other side-effects, like CommitLimit going negative. + */ + adjust_managed_page_count(page, pages_per_huge_page(h)); + cond_resched(); + } +} + +static void __init hugetlb_hstate_alloc_pages(struct hstate *h) +{ + unsigned long i; + nodemask_t *node_alloc_noretry; + + if (!hstate_is_gigantic(h)) { + /* + * Bit mask controlling how hard we retry per-node allocations. + * Ignore errors as lower level routines can deal with + * node_alloc_noretry == NULL. If this kmalloc fails at boot + * time, we are likely in bigger trouble. + */ + node_alloc_noretry = kmalloc(sizeof(*node_alloc_noretry), + GFP_KERNEL); + } else { + /* allocations done at boot time */ + node_alloc_noretry = NULL; + } + + /* bit mask controlling how hard we retry per-node allocations */ + if (node_alloc_noretry) + nodes_clear(*node_alloc_noretry); + + for (i = 0; i < h->max_huge_pages; ++i) { + if (hstate_is_gigantic(h)) { + if (hugetlb_cma_size) { + pr_warn_once("HugeTLB: hugetlb_cma is enabled, skip boot time allocation\n"); + goto free; + } + if (!alloc_bootmem_huge_page(h)) + break; + } else if (!alloc_pool_huge_page(h, + &node_states[N_MEMORY], + node_alloc_noretry)) + break; + cond_resched(); + } + if (i < h->max_huge_pages) { + char buf[32]; + + string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); + pr_warn("HugeTLB: allocating %lu of page size %s failed. Only allocated %lu hugepages.\n", + h->max_huge_pages, buf, i); + h->max_huge_pages = i; + } +free: + kfree(node_alloc_noretry); +} + +static void __init hugetlb_init_hstates(void) +{ + struct hstate *h; + + for_each_hstate(h) { + if (minimum_order > huge_page_order(h)) + minimum_order = huge_page_order(h); + + /* oversize hugepages were init'ed in early boot */ + if (!hstate_is_gigantic(h)) + hugetlb_hstate_alloc_pages(h); + } + VM_BUG_ON(minimum_order == UINT_MAX); +} + +static void __init report_hugepages(void) +{ + struct hstate *h; + + for_each_hstate(h) { + char buf[32]; + + string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); + pr_info("HugeTLB registered %s page size, pre-allocated %ld pages\n", + buf, h->free_huge_pages); + } +} + +#ifdef CONFIG_HIGHMEM +static void try_to_free_low(struct hstate *h, unsigned long count, + nodemask_t *nodes_allowed) +{ + int i; + + if (hstate_is_gigantic(h)) + return; + + for_each_node_mask(i, *nodes_allowed) { + struct page *page, *next; + struct list_head *freel = &h->hugepage_freelists[i]; + list_for_each_entry_safe(page, next, freel, lru) { + if (count >= h->nr_huge_pages) + return; + if (PageHighMem(page)) + continue; + list_del(&page->lru); + update_and_free_page(h, page); + h->free_huge_pages--; + h->free_huge_pages_node[page_to_nid(page)]--; + } + } +} +#else +static inline void try_to_free_low(struct hstate *h, unsigned long count, + nodemask_t *nodes_allowed) +{ +} +#endif + +/* + * Increment or decrement surplus_huge_pages. Keep node-specific counters + * balanced by operating on them in a round-robin fashion. + * Returns 1 if an adjustment was made. + */ +static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed, + int delta) +{ + int nr_nodes, node; + + VM_BUG_ON(delta != -1 && delta != 1); + + if (delta < 0) { + for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) { + if (h->surplus_huge_pages_node[node]) + goto found; + } + } else { + for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { + if (h->surplus_huge_pages_node[node] < + h->nr_huge_pages_node[node]) + goto found; + } + } + return 0; + +found: + h->surplus_huge_pages += delta; + h->surplus_huge_pages_node[node] += delta; + return 1; +} + +#define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages) +static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, + nodemask_t *nodes_allowed) +{ + unsigned long min_count, ret; + NODEMASK_ALLOC(nodemask_t, node_alloc_noretry, GFP_KERNEL); + + /* + * Bit mask controlling how hard we retry per-node allocations. + * If we can not allocate the bit mask, do not attempt to allocate + * the requested huge pages. + */ + if (node_alloc_noretry) + nodes_clear(*node_alloc_noretry); + else + return -ENOMEM; + + spin_lock(&hugetlb_lock); + + /* + * Check for a node specific request. + * Changing node specific huge page count may require a corresponding + * change to the global count. In any case, the passed node mask + * (nodes_allowed) will restrict alloc/free to the specified node. + */ + if (nid != NUMA_NO_NODE) { + unsigned long old_count = count; + + count += h->nr_huge_pages - h->nr_huge_pages_node[nid]; + /* + * User may have specified a large count value which caused the + * above calculation to overflow. In this case, they wanted + * to allocate as many huge pages as possible. Set count to + * largest possible value to align with their intention. + */ + if (count < old_count) + count = ULONG_MAX; + } + + /* + * Gigantic pages runtime allocation depend on the capability for large + * page range allocation. + * If the system does not provide this feature, return an error when + * the user tries to allocate gigantic pages but let the user free the + * boottime allocated gigantic pages. + */ + if (hstate_is_gigantic(h) && !IS_ENABLED(CONFIG_CONTIG_ALLOC)) { + if (count > persistent_huge_pages(h)) { + spin_unlock(&hugetlb_lock); + NODEMASK_FREE(node_alloc_noretry); + return -EINVAL; + } + /* Fall through to decrease pool */ + } + + /* + * Increase the pool size + * First take pages out of surplus state. Then make up the + * remaining difference by allocating fresh huge pages. + * + * We might race with alloc_surplus_huge_page() here and be unable + * to convert a surplus huge page to a normal huge page. That is + * not critical, though, it just means the overall size of the + * pool might be one hugepage larger than it needs to be, but + * within all the constraints specified by the sysctls. + */ + while (h->surplus_huge_pages && count > persistent_huge_pages(h)) { + if (!adjust_pool_surplus(h, nodes_allowed, -1)) + break; + } + + while (count > persistent_huge_pages(h)) { + /* + * If this allocation races such that we no longer need the + * page, free_huge_page will handle it by freeing the page + * and reducing the surplus. + */ + spin_unlock(&hugetlb_lock); + + /* yield cpu to avoid soft lockup */ + cond_resched(); + + ret = alloc_pool_huge_page(h, nodes_allowed, + node_alloc_noretry); + spin_lock(&hugetlb_lock); + if (!ret) + goto out; + + /* Bail for signals. Probably ctrl-c from user */ + if (signal_pending(current)) + goto out; + } + + /* + * Decrease the pool size + * First return free pages to the buddy allocator (being careful + * to keep enough around to satisfy reservations). Then place + * pages into surplus state as needed so the pool will shrink + * to the desired size as pages become free. + * + * By placing pages into the surplus state independent of the + * overcommit value, we are allowing the surplus pool size to + * exceed overcommit. There are few sane options here. Since + * alloc_surplus_huge_page() is checking the global counter, + * though, we'll note that we're not allowed to exceed surplus + * and won't grow the pool anywhere else. Not until one of the + * sysctls are changed, or the surplus pages go out of use. + */ + min_count = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages; + min_count = max(count, min_count); + try_to_free_low(h, min_count, nodes_allowed); + while (min_count < persistent_huge_pages(h)) { + if (!free_pool_huge_page(h, nodes_allowed, 0)) + break; + cond_resched_lock(&hugetlb_lock); + } + while (count < persistent_huge_pages(h)) { + if (!adjust_pool_surplus(h, nodes_allowed, 1)) + break; + } +out: + h->max_huge_pages = persistent_huge_pages(h); + spin_unlock(&hugetlb_lock); + + NODEMASK_FREE(node_alloc_noretry); + + return 0; +} + +#define HSTATE_ATTR_RO(_name) \ + static struct kobj_attribute _name##_attr = __ATTR_RO(_name) + +#define HSTATE_ATTR(_name) \ + static struct kobj_attribute _name##_attr = \ + __ATTR(_name, 0644, _name##_show, _name##_store) + +static struct kobject *hugepages_kobj; +static struct kobject *hstate_kobjs[HUGE_MAX_HSTATE]; + +static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp); + +static struct hstate *kobj_to_hstate(struct kobject *kobj, int *nidp) +{ + int i; + + for (i = 0; i < HUGE_MAX_HSTATE; i++) + if (hstate_kobjs[i] == kobj) { + if (nidp) + *nidp = NUMA_NO_NODE; + return &hstates[i]; + } + + return kobj_to_node_hstate(kobj, nidp); +} + +static ssize_t nr_hugepages_show_common(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct hstate *h; + unsigned long nr_huge_pages; + int nid; + + h = kobj_to_hstate(kobj, &nid); + if (nid == NUMA_NO_NODE) + nr_huge_pages = h->nr_huge_pages; + else + nr_huge_pages = h->nr_huge_pages_node[nid]; + + return sprintf(buf, "%lu\n", nr_huge_pages); +} + +static ssize_t __nr_hugepages_store_common(bool obey_mempolicy, + struct hstate *h, int nid, + unsigned long count, size_t len) +{ + int err; + nodemask_t nodes_allowed, *n_mask; + + if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) + return -EINVAL; + + if (nid == NUMA_NO_NODE) { + /* + * global hstate attribute + */ + if (!(obey_mempolicy && + init_nodemask_of_mempolicy(&nodes_allowed))) + n_mask = &node_states[N_MEMORY]; + else + n_mask = &nodes_allowed; + } else { + /* + * Node specific request. count adjustment happens in + * set_max_huge_pages() after acquiring hugetlb_lock. + */ + init_nodemask_of_node(&nodes_allowed, nid); + n_mask = &nodes_allowed; + } + + err = set_max_huge_pages(h, count, nid, n_mask); + + return err ? err : len; +} + +static ssize_t nr_hugepages_store_common(bool obey_mempolicy, + struct kobject *kobj, const char *buf, + size_t len) +{ + struct hstate *h; + unsigned long count; + int nid; + int err; + + err = kstrtoul(buf, 10, &count); + if (err) + return err; + + h = kobj_to_hstate(kobj, &nid); + return __nr_hugepages_store_common(obey_mempolicy, h, nid, count, len); +} + +static ssize_t nr_hugepages_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return nr_hugepages_show_common(kobj, attr, buf); +} + +static ssize_t nr_hugepages_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t len) +{ + return nr_hugepages_store_common(false, kobj, buf, len); +} +HSTATE_ATTR(nr_hugepages); + +#ifdef CONFIG_NUMA + +/* + * hstate attribute for optionally mempolicy-based constraint on persistent + * huge page alloc/free. + */ +static ssize_t nr_hugepages_mempolicy_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return nr_hugepages_show_common(kobj, attr, buf); +} + +static ssize_t nr_hugepages_mempolicy_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t len) +{ + return nr_hugepages_store_common(true, kobj, buf, len); +} +HSTATE_ATTR(nr_hugepages_mempolicy); +#endif + + +static ssize_t nr_overcommit_hugepages_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct hstate *h = kobj_to_hstate(kobj, NULL); + return sprintf(buf, "%lu\n", h->nr_overcommit_huge_pages); +} + +static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + int err; + unsigned long input; + struct hstate *h = kobj_to_hstate(kobj, NULL); + + if (hstate_is_gigantic(h)) + return -EINVAL; + + err = kstrtoul(buf, 10, &input); + if (err) + return err; + + spin_lock(&hugetlb_lock); + h->nr_overcommit_huge_pages = input; + spin_unlock(&hugetlb_lock); + + return count; +} +HSTATE_ATTR(nr_overcommit_hugepages); + +static ssize_t free_hugepages_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct hstate *h; + unsigned long free_huge_pages; + int nid; + + h = kobj_to_hstate(kobj, &nid); + if (nid == NUMA_NO_NODE) + free_huge_pages = h->free_huge_pages; + else + free_huge_pages = h->free_huge_pages_node[nid]; + + return sprintf(buf, "%lu\n", free_huge_pages); +} +HSTATE_ATTR_RO(free_hugepages); + +static ssize_t resv_hugepages_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct hstate *h = kobj_to_hstate(kobj, NULL); + return sprintf(buf, "%lu\n", h->resv_huge_pages); +} +HSTATE_ATTR_RO(resv_hugepages); + +static ssize_t surplus_hugepages_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct hstate *h; + unsigned long surplus_huge_pages; + int nid; + + h = kobj_to_hstate(kobj, &nid); + if (nid == NUMA_NO_NODE) + surplus_huge_pages = h->surplus_huge_pages; + else + surplus_huge_pages = h->surplus_huge_pages_node[nid]; + + return sprintf(buf, "%lu\n", surplus_huge_pages); +} +HSTATE_ATTR_RO(surplus_hugepages); + +static struct attribute *hstate_attrs[] = { + &nr_hugepages_attr.attr, + &nr_overcommit_hugepages_attr.attr, + &free_hugepages_attr.attr, + &resv_hugepages_attr.attr, + &surplus_hugepages_attr.attr, +#ifdef CONFIG_NUMA + &nr_hugepages_mempolicy_attr.attr, +#endif + NULL, +}; + +static const struct attribute_group hstate_attr_group = { + .attrs = hstate_attrs, +}; + +static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent, + struct kobject **hstate_kobjs, + const struct attribute_group *hstate_attr_group) +{ + int retval; + int hi = hstate_index(h); + + hstate_kobjs[hi] = kobject_create_and_add(h->name, parent); + if (!hstate_kobjs[hi]) + return -ENOMEM; + + retval = sysfs_create_group(hstate_kobjs[hi], hstate_attr_group); + if (retval) { + kobject_put(hstate_kobjs[hi]); + hstate_kobjs[hi] = NULL; + } + + return retval; +} + +static void __init hugetlb_sysfs_init(void) +{ + struct hstate *h; + int err; + + hugepages_kobj = kobject_create_and_add("hugepages", mm_kobj); + if (!hugepages_kobj) + return; + + for_each_hstate(h) { + err = hugetlb_sysfs_add_hstate(h, hugepages_kobj, + hstate_kobjs, &hstate_attr_group); + if (err) + pr_err("HugeTLB: Unable to add hstate %s", h->name); + } +} + +#ifdef CONFIG_NUMA + +/* + * node_hstate/s - associate per node hstate attributes, via their kobjects, + * with node devices in node_devices[] using a parallel array. The array + * index of a node device or _hstate == node id. + * This is here to avoid any static dependency of the node device driver, in + * the base kernel, on the hugetlb module. + */ +struct node_hstate { + struct kobject *hugepages_kobj; + struct kobject *hstate_kobjs[HUGE_MAX_HSTATE]; +}; +static struct node_hstate node_hstates[MAX_NUMNODES]; + +/* + * A subset of global hstate attributes for node devices + */ +static struct attribute *per_node_hstate_attrs[] = { + &nr_hugepages_attr.attr, + &free_hugepages_attr.attr, + &surplus_hugepages_attr.attr, + NULL, +}; + +static const struct attribute_group per_node_hstate_attr_group = { + .attrs = per_node_hstate_attrs, +}; + +/* + * kobj_to_node_hstate - lookup global hstate for node device hstate attr kobj. + * Returns node id via non-NULL nidp. + */ +static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp) +{ + int nid; + + for (nid = 0; nid < nr_node_ids; nid++) { + struct node_hstate *nhs = &node_hstates[nid]; + int i; + for (i = 0; i < HUGE_MAX_HSTATE; i++) + if (nhs->hstate_kobjs[i] == kobj) { + if (nidp) + *nidp = nid; + return &hstates[i]; + } + } + + BUG(); + return NULL; +} + +/* + * Unregister hstate attributes from a single node device. + * No-op if no hstate attributes attached. + */ +static void hugetlb_unregister_node(struct node *node) +{ + struct hstate *h; + struct node_hstate *nhs = &node_hstates[node->dev.id]; + + if (!nhs->hugepages_kobj) + return; /* no hstate attributes */ + + for_each_hstate(h) { + int idx = hstate_index(h); + if (nhs->hstate_kobjs[idx]) { + kobject_put(nhs->hstate_kobjs[idx]); + nhs->hstate_kobjs[idx] = NULL; + } + } + + kobject_put(nhs->hugepages_kobj); + nhs->hugepages_kobj = NULL; +} + + +/* + * Register hstate attributes for a single node device. + * No-op if attributes already registered. + */ +static void hugetlb_register_node(struct node *node) +{ + struct hstate *h; + struct node_hstate *nhs = &node_hstates[node->dev.id]; + int err; + + if (nhs->hugepages_kobj) + return; /* already allocated */ + + nhs->hugepages_kobj = kobject_create_and_add("hugepages", + &node->dev.kobj); + if (!nhs->hugepages_kobj) + return; + + for_each_hstate(h) { + err = hugetlb_sysfs_add_hstate(h, nhs->hugepages_kobj, + nhs->hstate_kobjs, + &per_node_hstate_attr_group); + if (err) { + pr_err("HugeTLB: Unable to add hstate %s for node %d\n", + h->name, node->dev.id); + hugetlb_unregister_node(node); + break; + } + } +} + +/* + * hugetlb init time: register hstate attributes for all registered node + * devices of nodes that have memory. All on-line nodes should have + * registered their associated device by this time. + */ +static void __init hugetlb_register_all_nodes(void) +{ + int nid; + + for_each_node_state(nid, N_MEMORY) { + struct node *node = node_devices[nid]; + if (node->dev.id == nid) + hugetlb_register_node(node); + } + + /* + * Let the node device driver know we're here so it can + * [un]register hstate attributes on node hotplug. + */ + register_hugetlbfs_with_node(hugetlb_register_node, + hugetlb_unregister_node); +} +#else /* !CONFIG_NUMA */ + +static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp) +{ + BUG(); + if (nidp) + *nidp = -1; + return NULL; +} + +static void hugetlb_register_all_nodes(void) { } + +#endif + +static int __init hugetlb_init(void) +{ + int i; + + if (!hugepages_supported()) { + if (hugetlb_max_hstate || default_hstate_max_huge_pages) + pr_warn("HugeTLB: huge pages not supported, ignoring associated command-line parameters\n"); + return 0; + } + + /* + * Make sure HPAGE_SIZE (HUGETLB_PAGE_ORDER) hstate exists. Some + * architectures depend on setup being done here. + */ + hugetlb_add_hstate(HUGETLB_PAGE_ORDER); + if (!parsed_default_hugepagesz) { + /* + * If we did not parse a default huge page size, set + * default_hstate_idx to HPAGE_SIZE hstate. And, if the + * number of huge pages for this default size was implicitly + * specified, set that here as well. + * Note that the implicit setting will overwrite an explicit + * setting. A warning will be printed in this case. + */ + default_hstate_idx = hstate_index(size_to_hstate(HPAGE_SIZE)); + if (default_hstate_max_huge_pages) { + if (default_hstate.max_huge_pages) { + char buf[32]; + + string_get_size(huge_page_size(&default_hstate), + 1, STRING_UNITS_2, buf, 32); + pr_warn("HugeTLB: Ignoring hugepages=%lu associated with %s page size\n", + default_hstate.max_huge_pages, buf); + pr_warn("HugeTLB: Using hugepages=%lu for number of default huge pages\n", + default_hstate_max_huge_pages); + } + default_hstate.max_huge_pages = + default_hstate_max_huge_pages; + } + } + + hugetlb_cma_check(); + hugetlb_init_hstates(); + gather_bootmem_prealloc(); + report_hugepages(); + + hugetlb_sysfs_init(); + hugetlb_register_all_nodes(); + hugetlb_cgroup_file_init(); + +#ifdef CONFIG_SMP + num_fault_mutexes = roundup_pow_of_two(8 * num_possible_cpus()); +#else + num_fault_mutexes = 1; +#endif + hugetlb_fault_mutex_table = + kmalloc_array(num_fault_mutexes, sizeof(struct mutex), + GFP_KERNEL); + BUG_ON(!hugetlb_fault_mutex_table); + + for (i = 0; i < num_fault_mutexes; i++) + mutex_init(&hugetlb_fault_mutex_table[i]); + return 0; +} +subsys_initcall(hugetlb_init); + +/* Overwritten by architectures with more huge page sizes */ +bool __init __attribute((weak)) arch_hugetlb_valid_size(unsigned long size) +{ + return size == HPAGE_SIZE; +} + +void __init hugetlb_add_hstate(unsigned int order) +{ + struct hstate *h; + unsigned long i; + + if (size_to_hstate(PAGE_SIZE << order)) { + return; + } + BUG_ON(hugetlb_max_hstate >= HUGE_MAX_HSTATE); + BUG_ON(order == 0); + h = &hstates[hugetlb_max_hstate++]; + h->order = order; + h->mask = ~((1ULL << (order + PAGE_SHIFT)) - 1); + h->nr_huge_pages = 0; + h->free_huge_pages = 0; + for (i = 0; i < MAX_NUMNODES; ++i) + INIT_LIST_HEAD(&h->hugepage_freelists[i]); + INIT_LIST_HEAD(&h->hugepage_activelist); + h->next_nid_to_alloc = first_memory_node; + h->next_nid_to_free = first_memory_node; + snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB", + huge_page_size(h)/1024); + + parsed_hstate = h; +} + +/* + * hugepages command line processing + * hugepages normally follows a valid hugepagsz or default_hugepagsz + * specification. If not, ignore the hugepages value. hugepages can also + * be the first huge page command line option in which case it implicitly + * specifies the number of huge pages for the default size. + */ +static int __init hugepages_setup(char *s) +{ + unsigned long *mhp; + static unsigned long *last_mhp; + + if (!parsed_valid_hugepagesz) { + pr_warn("HugeTLB: hugepages=%s does not follow a valid hugepagesz, ignoring\n", s); + parsed_valid_hugepagesz = true; + return 0; + } + + /* + * !hugetlb_max_hstate means we haven't parsed a hugepagesz= parameter + * yet, so this hugepages= parameter goes to the "default hstate". + * Otherwise, it goes with the previously parsed hugepagesz or + * default_hugepagesz. + */ + else if (!hugetlb_max_hstate) + mhp = &default_hstate_max_huge_pages; + else + mhp = &parsed_hstate->max_huge_pages; + + if (mhp == last_mhp) { + pr_warn("HugeTLB: hugepages= specified twice without interleaving hugepagesz=, ignoring hugepages=%s\n", s); + return 0; + } + + if (sscanf(s, "%lu", mhp) <= 0) + *mhp = 0; + + /* + * Global state is always initialized later in hugetlb_init. + * But we need to allocate >= MAX_ORDER hstates here early to still + * use the bootmem allocator. + */ + if (hugetlb_max_hstate && parsed_hstate->order >= MAX_ORDER) + hugetlb_hstate_alloc_pages(parsed_hstate); + + last_mhp = mhp; + + return 1; +} +__setup("hugepages=", hugepages_setup); + +/* + * hugepagesz command line processing + * A specific huge page size can only be specified once with hugepagesz. + * hugepagesz is followed by hugepages on the command line. The global + * variable 'parsed_valid_hugepagesz' is used to determine if prior + * hugepagesz argument was valid. + */ +static int __init hugepagesz_setup(char *s) +{ + unsigned long size; + struct hstate *h; + + parsed_valid_hugepagesz = false; + size = (unsigned long)memparse(s, NULL); + + if (!arch_hugetlb_valid_size(size)) { + pr_err("HugeTLB: unsupported hugepagesz=%s\n", s); + return 0; + } + + h = size_to_hstate(size); + if (h) { + /* + * hstate for this size already exists. This is normally + * an error, but is allowed if the existing hstate is the + * default hstate. More specifically, it is only allowed if + * the number of huge pages for the default hstate was not + * previously specified. + */ + if (!parsed_default_hugepagesz || h != &default_hstate || + default_hstate.max_huge_pages) { + pr_warn("HugeTLB: hugepagesz=%s specified twice, ignoring\n", s); + return 0; + } + + /* + * No need to call hugetlb_add_hstate() as hstate already + * exists. But, do set parsed_hstate so that a following + * hugepages= parameter will be applied to this hstate. + */ + parsed_hstate = h; + parsed_valid_hugepagesz = true; + return 1; + } + + hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT); + parsed_valid_hugepagesz = true; + return 1; +} +__setup("hugepagesz=", hugepagesz_setup); + +/* + * default_hugepagesz command line input + * Only one instance of default_hugepagesz allowed on command line. + */ +static int __init default_hugepagesz_setup(char *s) +{ + unsigned long size; + + parsed_valid_hugepagesz = false; + if (parsed_default_hugepagesz) { + pr_err("HugeTLB: default_hugepagesz previously specified, ignoring %s\n", s); + return 0; + } + + size = (unsigned long)memparse(s, NULL); + + if (!arch_hugetlb_valid_size(size)) { + pr_err("HugeTLB: unsupported default_hugepagesz=%s\n", s); + return 0; + } + + hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT); + parsed_valid_hugepagesz = true; + parsed_default_hugepagesz = true; + default_hstate_idx = hstate_index(size_to_hstate(size)); + + /* + * The number of default huge pages (for this size) could have been + * specified as the first hugetlb parameter: hugepages=X. If so, + * then default_hstate_max_huge_pages is set. If the default huge + * page size is gigantic (>= MAX_ORDER), then the pages must be + * allocated here from bootmem allocator. + */ + if (default_hstate_max_huge_pages) { + default_hstate.max_huge_pages = default_hstate_max_huge_pages; + if (hstate_is_gigantic(&default_hstate)) + hugetlb_hstate_alloc_pages(&default_hstate); + default_hstate_max_huge_pages = 0; + } + + return 1; +} +__setup("default_hugepagesz=", default_hugepagesz_setup); + +static unsigned int allowed_mems_nr(struct hstate *h) +{ + int node; + unsigned int nr = 0; + nodemask_t *mpol_allowed; + unsigned int *array = h->free_huge_pages_node; + gfp_t gfp_mask = htlb_alloc_mask(h); + + mpol_allowed = policy_nodemask_current(gfp_mask); + + for_each_node_mask(node, cpuset_current_mems_allowed) { + if (!mpol_allowed || + (mpol_allowed && node_isset(node, *mpol_allowed))) + nr += array[node]; + } + + return nr; +} + +#ifdef CONFIG_SYSCTL +static int proc_hugetlb_doulongvec_minmax(struct ctl_table *table, int write, + void *buffer, size_t *length, + loff_t *ppos, unsigned long *out) +{ + struct ctl_table dup_table; + + /* + * In order to avoid races with __do_proc_doulongvec_minmax(), we + * can duplicate the @table and alter the duplicate of it. + */ + dup_table = *table; + dup_table.data = out; + + return proc_doulongvec_minmax(&dup_table, write, buffer, length, ppos); +} + +static int hugetlb_sysctl_handler_common(bool obey_mempolicy, + struct ctl_table *table, int write, + void *buffer, size_t *length, loff_t *ppos) +{ + struct hstate *h = &default_hstate; + unsigned long tmp = h->max_huge_pages; + int ret; + + if (!hugepages_supported()) + return -EOPNOTSUPP; + + ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos, + &tmp); + if (ret) + goto out; + + if (write) + ret = __nr_hugepages_store_common(obey_mempolicy, h, + NUMA_NO_NODE, tmp, *length); +out: + return ret; +} + +int hugetlb_sysctl_handler(struct ctl_table *table, int write, + void *buffer, size_t *length, loff_t *ppos) +{ + + return hugetlb_sysctl_handler_common(false, table, write, + buffer, length, ppos); +} + +#ifdef CONFIG_NUMA +int hugetlb_mempolicy_sysctl_handler(struct ctl_table *table, int write, + void *buffer, size_t *length, loff_t *ppos) +{ + return hugetlb_sysctl_handler_common(true, table, write, + buffer, length, ppos); +} +#endif /* CONFIG_NUMA */ + +int hugetlb_overcommit_handler(struct ctl_table *table, int write, + void *buffer, size_t *length, loff_t *ppos) +{ + struct hstate *h = &default_hstate; + unsigned long tmp; + int ret; + + if (!hugepages_supported()) + return -EOPNOTSUPP; + + tmp = h->nr_overcommit_huge_pages; + + if (write && hstate_is_gigantic(h)) + return -EINVAL; + + ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos, + &tmp); + if (ret) + goto out; + + if (write) { + spin_lock(&hugetlb_lock); + h->nr_overcommit_huge_pages = tmp; + spin_unlock(&hugetlb_lock); + } +out: + return ret; +} + +#endif /* CONFIG_SYSCTL */ + +void hugetlb_report_meminfo(struct seq_file *m) +{ + struct hstate *h; + unsigned long total = 0; + + if (!hugepages_supported()) + return; + + for_each_hstate(h) { + unsigned long count = h->nr_huge_pages; + + total += (PAGE_SIZE << huge_page_order(h)) * count; + + if (h == &default_hstate) + seq_printf(m, + "HugePages_Total: %5lu\n" + "HugePages_Free: %5lu\n" + "HugePages_Rsvd: %5lu\n" + "HugePages_Surp: %5lu\n" + "Hugepagesize: %8lu kB\n", + count, + h->free_huge_pages, + h->resv_huge_pages, + h->surplus_huge_pages, + (PAGE_SIZE << huge_page_order(h)) / 1024); + } + + seq_printf(m, "Hugetlb: %8lu kB\n", total / 1024); +} + +int hugetlb_report_node_meminfo(char *buf, int len, int nid) +{ + struct hstate *h = &default_hstate; + + if (!hugepages_supported()) + return 0; + + return sysfs_emit_at(buf, len, + "Node %d HugePages_Total: %5u\n" + "Node %d HugePages_Free: %5u\n" + "Node %d HugePages_Surp: %5u\n", + nid, h->nr_huge_pages_node[nid], + nid, h->free_huge_pages_node[nid], + nid, h->surplus_huge_pages_node[nid]); +} + +void hugetlb_show_meminfo(void) +{ + struct hstate *h; + int nid; + + if (!hugepages_supported()) + return; + + for_each_node_state(nid, N_MEMORY) + for_each_hstate(h) + pr_info("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n", + nid, + h->nr_huge_pages_node[nid], + h->free_huge_pages_node[nid], + h->surplus_huge_pages_node[nid], + 1UL << (huge_page_order(h) + PAGE_SHIFT - 10)); +} + +void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm) +{ + seq_printf(m, "HugetlbPages:\t%8lu kB\n", + atomic_long_read(&mm->hugetlb_usage) << (PAGE_SHIFT - 10)); +} + +/* Return the number pages of memory we physically have, in PAGE_SIZE units. */ +unsigned long hugetlb_total_pages(void) +{ + struct hstate *h; + unsigned long nr_total_pages = 0; + + for_each_hstate(h) + nr_total_pages += h->nr_huge_pages * pages_per_huge_page(h); + return nr_total_pages; +} + +static int hugetlb_acct_memory(struct hstate *h, long delta) +{ + int ret = -ENOMEM; + + spin_lock(&hugetlb_lock); + /* + * When cpuset is configured, it breaks the strict hugetlb page + * reservation as the accounting is done on a global variable. Such + * reservation is completely rubbish in the presence of cpuset because + * the reservation is not checked against page availability for the + * current cpuset. Application can still potentially OOM'ed by kernel + * with lack of free htlb page in cpuset that the task is in. + * Attempt to enforce strict accounting with cpuset is almost + * impossible (or too ugly) because cpuset is too fluid that + * task or memory node can be dynamically moved between cpusets. + * + * The change of semantics for shared hugetlb mapping with cpuset is + * undesirable. However, in order to preserve some of the semantics, + * we fall back to check against current free page availability as + * a best attempt and hopefully to minimize the impact of changing + * semantics that cpuset has. + * + * Apart from cpuset, we also have memory policy mechanism that + * also determines from which node the kernel will allocate memory + * in a NUMA system. So similar to cpuset, we also should consider + * the memory policy of the current task. Similar to the description + * above. + */ + if (delta > 0) { + if (gather_surplus_pages(h, delta) < 0) + goto out; + + if (delta > allowed_mems_nr(h)) { + return_unused_surplus_pages(h, delta); + goto out; + } + } + + ret = 0; + if (delta < 0) + return_unused_surplus_pages(h, (unsigned long) -delta); + +out: + spin_unlock(&hugetlb_lock); + return ret; +} + +static void hugetlb_vm_op_open(struct vm_area_struct *vma) +{ + struct resv_map *resv = vma_resv_map(vma); + + /* + * This new VMA should share its siblings reservation map if present. + * The VMA will only ever have a valid reservation map pointer where + * it is being copied for another still existing VMA. As that VMA + * has a reference to the reservation map it cannot disappear until + * after this open call completes. It is therefore safe to take a + * new reference here without additional locking. + */ + if (resv && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { + resv_map_dup_hugetlb_cgroup_uncharge_info(resv); + kref_get(&resv->refs); + } +} + +static void hugetlb_vm_op_close(struct vm_area_struct *vma) +{ + struct hstate *h = hstate_vma(vma); + struct resv_map *resv = vma_resv_map(vma); + struct hugepage_subpool *spool = subpool_vma(vma); + unsigned long reserve, start, end; + long gbl_reserve; + + if (!resv || !is_vma_resv_set(vma, HPAGE_RESV_OWNER)) + return; + + start = vma_hugecache_offset(h, vma, vma->vm_start); + end = vma_hugecache_offset(h, vma, vma->vm_end); + + reserve = (end - start) - region_count(resv, start, end); + hugetlb_cgroup_uncharge_counter(resv, start, end); + if (reserve) { + /* + * Decrement reserve counts. The global reserve count may be + * adjusted if the subpool has a minimum size. + */ + gbl_reserve = hugepage_subpool_put_pages(spool, reserve); + hugetlb_acct_memory(h, -gbl_reserve); + } + + kref_put(&resv->refs, resv_map_release); +} + +static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr) +{ + if (addr & ~(huge_page_mask(hstate_vma(vma)))) + return -EINVAL; + return 0; +} + +static unsigned long hugetlb_vm_op_pagesize(struct vm_area_struct *vma) +{ + struct hstate *hstate = hstate_vma(vma); + + return 1UL << huge_page_shift(hstate); +} + +/* + * We cannot handle pagefaults against hugetlb pages at all. They cause + * handle_mm_fault() to try to instantiate regular-sized pages in the + * hugegpage VMA. do_page_fault() is supposed to trap this, so BUG is we get + * this far. + */ +static vm_fault_t hugetlb_vm_op_fault(struct vm_fault *vmf) +{ + BUG(); + return 0; +} + +/* + * When a new function is introduced to vm_operations_struct and added + * to hugetlb_vm_ops, please consider adding the function to shm_vm_ops. + * This is because under System V memory model, mappings created via + * shmget/shmat with "huge page" specified are backed by hugetlbfs files, + * their original vm_ops are overwritten with shm_vm_ops. + */ +const struct vm_operations_struct hugetlb_vm_ops = { + .fault = hugetlb_vm_op_fault, + .open = hugetlb_vm_op_open, + .close = hugetlb_vm_op_close, + .split = hugetlb_vm_op_split, + .pagesize = hugetlb_vm_op_pagesize, +}; + +static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page, + int writable) +{ + pte_t entry; + + if (writable) { + entry = huge_pte_mkwrite(huge_pte_mkdirty(mk_huge_pte(page, + vma->vm_page_prot))); + } else { + entry = huge_pte_wrprotect(mk_huge_pte(page, + vma->vm_page_prot)); + } + entry = pte_mkyoung(entry); + entry = pte_mkhuge(entry); + entry = arch_make_huge_pte(entry, vma, page, writable); + + return entry; +} + +static void set_huge_ptep_writable(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep) +{ + pte_t entry; + + entry = huge_pte_mkwrite(huge_pte_mkdirty(huge_ptep_get(ptep))); + if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1)) + update_mmu_cache(vma, address, ptep); +} + +bool is_hugetlb_entry_migration(pte_t pte) +{ + swp_entry_t swp; + + if (huge_pte_none(pte) || pte_present(pte)) + return false; + swp = pte_to_swp_entry(pte); + if (is_migration_entry(swp)) + return true; + else + return false; +} + +static bool is_hugetlb_entry_hwpoisoned(pte_t pte) +{ + swp_entry_t swp; + + if (huge_pte_none(pte) || pte_present(pte)) + return false; + swp = pte_to_swp_entry(pte); + if (is_hwpoison_entry(swp)) + return true; + else + return false; +} + +int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, + struct vm_area_struct *vma) +{ + pte_t *src_pte, *dst_pte, entry, dst_entry; + struct page *ptepage; + unsigned long addr; + int cow; + struct hstate *h = hstate_vma(vma); + unsigned long sz = huge_page_size(h); + struct address_space *mapping = vma->vm_file->f_mapping; + struct mmu_notifier_range range; + int ret = 0; + + cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; + + if (cow) { + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, src, + vma->vm_start, + vma->vm_end); + mmu_notifier_invalidate_range_start(&range); + } else { + /* + * For shared mappings i_mmap_rwsem must be held to call + * huge_pte_alloc, otherwise the returned ptep could go + * away if part of a shared pmd and another thread calls + * huge_pmd_unshare. + */ + i_mmap_lock_read(mapping); + } + + for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) { + spinlock_t *src_ptl, *dst_ptl; + src_pte = huge_pte_offset(src, addr, sz); + if (!src_pte) + continue; + dst_pte = huge_pte_alloc(dst, addr, sz); + if (!dst_pte) { + ret = -ENOMEM; + break; + } + + /* + * If the pagetables are shared don't copy or take references. + * dst_pte == src_pte is the common case of src/dest sharing. + * + * However, src could have 'unshared' and dst shares with + * another vma. If dst_pte !none, this implies sharing. + * Check here before taking page table lock, and once again + * after taking the lock below. + */ + dst_entry = huge_ptep_get(dst_pte); + if ((dst_pte == src_pte) || !huge_pte_none(dst_entry)) + continue; + + dst_ptl = huge_pte_lock(h, dst, dst_pte); + src_ptl = huge_pte_lockptr(h, src, src_pte); + spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); + entry = huge_ptep_get(src_pte); + dst_entry = huge_ptep_get(dst_pte); + if (huge_pte_none(entry) || !huge_pte_none(dst_entry)) { + /* + * Skip if src entry none. Also, skip in the + * unlikely case dst entry !none as this implies + * sharing with another vma. + */ + ; + } else if (unlikely(is_hugetlb_entry_migration(entry) || + is_hugetlb_entry_hwpoisoned(entry))) { + swp_entry_t swp_entry = pte_to_swp_entry(entry); + + if (is_write_migration_entry(swp_entry) && cow) { + /* + * COW mappings require pages in both + * parent and child to be set to read. + */ + make_migration_entry_read(&swp_entry); + entry = swp_entry_to_pte(swp_entry); + set_huge_swap_pte_at(src, addr, src_pte, + entry, sz); + } + set_huge_swap_pte_at(dst, addr, dst_pte, entry, sz); + } else { + if (cow) { + /* + * No need to notify as we are downgrading page + * table protection not changing it to point + * to a new page. + * + * See Documentation/vm/mmu_notifier.rst + */ + huge_ptep_set_wrprotect(src, addr, src_pte); + } + entry = huge_ptep_get(src_pte); + ptepage = pte_page(entry); + get_page(ptepage); + page_dup_rmap(ptepage, true); + set_huge_pte_at(dst, addr, dst_pte, entry); + hugetlb_count_add(pages_per_huge_page(h), dst); + } + spin_unlock(src_ptl); + spin_unlock(dst_ptl); + } + + if (cow) + mmu_notifier_invalidate_range_end(&range); + else + i_mmap_unlock_read(mapping); + + return ret; +} + +void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, + unsigned long start, unsigned long end, + struct page *ref_page) +{ + struct mm_struct *mm = vma->vm_mm; + unsigned long address; + pte_t *ptep; + pte_t pte; + spinlock_t *ptl; + struct page *page; + struct hstate *h = hstate_vma(vma); + unsigned long sz = huge_page_size(h); + struct mmu_notifier_range range; + bool force_flush = false; + + WARN_ON(!is_vm_hugetlb_page(vma)); + BUG_ON(start & ~huge_page_mask(h)); + BUG_ON(end & ~huge_page_mask(h)); + + /* + * This is a hugetlb vma, all the pte entries should point + * to huge page. + */ + tlb_change_page_size(tlb, sz); + tlb_start_vma(tlb, vma); + + /* + * If sharing possible, alert mmu notifiers of worst case. + */ + mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, mm, start, + end); + adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); + mmu_notifier_invalidate_range_start(&range); + address = start; + for (; address < end; address += sz) { + ptep = huge_pte_offset(mm, address, sz); + if (!ptep) + continue; + + ptl = huge_pte_lock(h, mm, ptep); + if (huge_pmd_unshare(mm, vma, &address, ptep)) { + spin_unlock(ptl); + tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE); + force_flush = true; + continue; + } + + pte = huge_ptep_get(ptep); + if (huge_pte_none(pte)) { + spin_unlock(ptl); + continue; + } + + /* + * Migrating hugepage or HWPoisoned hugepage is already + * unmapped and its refcount is dropped, so just clear pte here. + */ + if (unlikely(!pte_present(pte))) { + huge_pte_clear(mm, address, ptep, sz); + spin_unlock(ptl); + continue; + } + + page = pte_page(pte); + /* + * If a reference page is supplied, it is because a specific + * page is being unmapped, not a range. Ensure the page we + * are about to unmap is the actual page of interest. + */ + if (ref_page) { + if (page != ref_page) { + spin_unlock(ptl); + continue; + } + /* + * Mark the VMA as having unmapped its page so that + * future faults in this VMA will fail rather than + * looking like data was lost + */ + set_vma_resv_flags(vma, HPAGE_RESV_UNMAPPED); + } + + pte = huge_ptep_get_and_clear(mm, address, ptep); + tlb_remove_huge_tlb_entry(h, tlb, ptep, address); + if (huge_pte_dirty(pte)) + set_page_dirty(page); + + hugetlb_count_sub(pages_per_huge_page(h), mm); + page_remove_rmap(page, true); + + spin_unlock(ptl); + tlb_remove_page_size(tlb, page, huge_page_size(h)); + /* + * Bail out after unmapping reference page if supplied + */ + if (ref_page) + break; + } + mmu_notifier_invalidate_range_end(&range); + tlb_end_vma(tlb, vma); + + /* + * If we unshared PMDs, the TLB flush was not recorded in mmu_gather. We + * could defer the flush until now, since by holding i_mmap_rwsem we + * guaranteed that the last refernece would not be dropped. But we must + * do the flushing before we return, as otherwise i_mmap_rwsem will be + * dropped and the last reference to the shared PMDs page might be + * dropped as well. + * + * In theory we could defer the freeing of the PMD pages as well, but + * huge_pmd_unshare() relies on the exact page_count for the PMD page to + * detect sharing, so we cannot defer the release of the page either. + * Instead, do flush now. + */ + if (force_flush) + tlb_flush_mmu_tlbonly(tlb); +} + +void __unmap_hugepage_range_final(struct mmu_gather *tlb, + struct vm_area_struct *vma, unsigned long start, + unsigned long end, struct page *ref_page) +{ + __unmap_hugepage_range(tlb, vma, start, end, ref_page); + + /* + * Clear this flag so that x86's huge_pmd_share page_table_shareable + * test will fail on a vma being torn down, and not grab a page table + * on its way out. We're lucky that the flag has such an appropriate + * name, and can in fact be safely cleared here. We could clear it + * before the __unmap_hugepage_range above, but all that's necessary + * is to clear it before releasing the i_mmap_rwsem. This works + * because in the context this is called, the VMA is about to be + * destroyed and the i_mmap_rwsem is held. + */ + vma->vm_flags &= ~VM_MAYSHARE; +} + +void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end, struct page *ref_page) +{ + struct mm_struct *mm; + struct mmu_gather tlb; + unsigned long tlb_start = start; + unsigned long tlb_end = end; + + /* + * If shared PMDs were possibly used within this vma range, adjust + * start/end for worst case tlb flushing. + * Note that we can not be sure if PMDs are shared until we try to + * unmap pages. However, we want to make sure TLB flushing covers + * the largest possible range. + */ + adjust_range_if_pmd_sharing_possible(vma, &tlb_start, &tlb_end); + + mm = vma->vm_mm; + + tlb_gather_mmu(&tlb, mm, tlb_start, tlb_end); + __unmap_hugepage_range(&tlb, vma, start, end, ref_page); + tlb_finish_mmu(&tlb, tlb_start, tlb_end); +} + +/* + * This is called when the original mapper is failing to COW a MAP_PRIVATE + * mappping it owns the reserve page for. The intention is to unmap the page + * from other VMAs and let the children be SIGKILLed if they are faulting the + * same region. + */ +static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, + struct page *page, unsigned long address) +{ + struct hstate *h = hstate_vma(vma); + struct vm_area_struct *iter_vma; + struct address_space *mapping; + pgoff_t pgoff; + + /* + * vm_pgoff is in PAGE_SIZE units, hence the different calculation + * from page cache lookup which is in HPAGE_SIZE units. + */ + address = address & huge_page_mask(h); + pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) + + vma->vm_pgoff; + mapping = vma->vm_file->f_mapping; + + /* + * Take the mapping lock for the duration of the table walk. As + * this mapping should be shared between all the VMAs, + * __unmap_hugepage_range() is called as the lock is already held + */ + i_mmap_lock_write(mapping); + vma_interval_tree_foreach(iter_vma, &mapping->i_mmap, pgoff, pgoff) { + /* Do not unmap the current VMA */ + if (iter_vma == vma) + continue; + + /* + * Shared VMAs have their own reserves and do not affect + * MAP_PRIVATE accounting but it is possible that a shared + * VMA is using the same page so check and skip such VMAs. + */ + if (iter_vma->vm_flags & VM_MAYSHARE) + continue; + + /* + * Unmap the page from other VMAs without their own reserves. + * They get marked to be SIGKILLed if they fault in these + * areas. This is because a future no-page fault on this VMA + * could insert a zeroed page instead of the data existing + * from the time of fork. This would look like data corruption + */ + if (!is_vma_resv_set(iter_vma, HPAGE_RESV_OWNER)) + unmap_hugepage_range(iter_vma, address, + address + huge_page_size(h), page); + } + i_mmap_unlock_write(mapping); +} + +/* + * Hugetlb_cow() should be called with page lock of the original hugepage held. + * Called with hugetlb_instantiation_mutex held and pte_page locked so we + * cannot race with other handlers or page migration. + * Keep the pte_same checks anyway to make transition from the mutex easier. + */ +static vm_fault_t hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, + struct page *pagecache_page, spinlock_t *ptl) +{ + pte_t pte; + struct hstate *h = hstate_vma(vma); + struct page *old_page, *new_page; + int outside_reserve = 0; + vm_fault_t ret = 0; + unsigned long haddr = address & huge_page_mask(h); + struct mmu_notifier_range range; + + pte = huge_ptep_get(ptep); + old_page = pte_page(pte); + +retry_avoidcopy: + /* If no-one else is actually using this page, avoid the copy + * and just make the page writable */ + if (page_mapcount(old_page) == 1 && PageAnon(old_page)) { + page_move_anon_rmap(old_page, vma); + set_huge_ptep_writable(vma, haddr, ptep); + return 0; + } + + /* + * If the process that created a MAP_PRIVATE mapping is about to + * perform a COW due to a shared page count, attempt to satisfy + * the allocation without using the existing reserves. The pagecache + * page is used to determine if the reserve at this address was + * consumed or not. If reserves were used, a partial faulted mapping + * at the time of fork() could consume its reserves on COW instead + * of the full address range. + */ + if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) && + old_page != pagecache_page) + outside_reserve = 1; + + get_page(old_page); + + /* + * Drop page table lock as buddy allocator may be called. It will + * be acquired again before returning to the caller, as expected. + */ + spin_unlock(ptl); + new_page = alloc_huge_page(vma, haddr, outside_reserve); + + if (IS_ERR(new_page)) { + /* + * If a process owning a MAP_PRIVATE mapping fails to COW, + * it is due to references held by a child and an insufficient + * huge page pool. To guarantee the original mappers + * reliability, unmap the page from child processes. The child + * may get SIGKILLed if it later faults. + */ + if (outside_reserve) { + struct address_space *mapping = vma->vm_file->f_mapping; + pgoff_t idx; + u32 hash; + + put_page(old_page); + BUG_ON(huge_pte_none(pte)); + /* + * Drop hugetlb_fault_mutex and i_mmap_rwsem before + * unmapping. unmapping needs to hold i_mmap_rwsem + * in write mode. Dropping i_mmap_rwsem in read mode + * here is OK as COW mappings do not interact with + * PMD sharing. + * + * Reacquire both after unmap operation. + */ + idx = vma_hugecache_offset(h, vma, haddr); + hash = hugetlb_fault_mutex_hash(mapping, idx); + mutex_unlock(&hugetlb_fault_mutex_table[hash]); + i_mmap_unlock_read(mapping); + + unmap_ref_private(mm, vma, old_page, haddr); + + i_mmap_lock_read(mapping); + mutex_lock(&hugetlb_fault_mutex_table[hash]); + spin_lock(ptl); + ptep = huge_pte_offset(mm, haddr, huge_page_size(h)); + if (likely(ptep && + pte_same(huge_ptep_get(ptep), pte))) + goto retry_avoidcopy; + /* + * race occurs while re-acquiring page table + * lock, and our job is done. + */ + return 0; + } + + ret = vmf_error(PTR_ERR(new_page)); + goto out_release_old; + } + + /* + * When the original hugepage is shared one, it does not have + * anon_vma prepared. + */ + if (unlikely(anon_vma_prepare(vma))) { + ret = VM_FAULT_OOM; + goto out_release_all; + } + + copy_user_huge_page(new_page, old_page, address, vma, + pages_per_huge_page(h)); + __SetPageUptodate(new_page); + + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, haddr, + haddr + huge_page_size(h)); + mmu_notifier_invalidate_range_start(&range); + + /* + * Retake the page table lock to check for racing updates + * before the page tables are altered + */ + spin_lock(ptl); + ptep = huge_pte_offset(mm, haddr, huge_page_size(h)); + if (likely(ptep && pte_same(huge_ptep_get(ptep), pte))) { + ClearPagePrivate(new_page); + + /* Break COW */ + huge_ptep_clear_flush(vma, haddr, ptep); + mmu_notifier_invalidate_range(mm, range.start, range.end); + set_huge_pte_at(mm, haddr, ptep, + make_huge_pte(vma, new_page, 1)); + page_remove_rmap(old_page, true); + hugepage_add_new_anon_rmap(new_page, vma, haddr); + set_page_huge_active(new_page); + /* Make the old page be freed below */ + new_page = old_page; + } + spin_unlock(ptl); + mmu_notifier_invalidate_range_end(&range); +out_release_all: + restore_reserve_on_error(h, vma, haddr, new_page); + put_page(new_page); +out_release_old: + put_page(old_page); + + spin_lock(ptl); /* Caller expects lock to be held */ + return ret; +} + +/* Return the pagecache page at a given address within a VMA */ +static struct page *hugetlbfs_pagecache_page(struct hstate *h, + struct vm_area_struct *vma, unsigned long address) +{ + struct address_space *mapping; + pgoff_t idx; + + mapping = vma->vm_file->f_mapping; + idx = vma_hugecache_offset(h, vma, address); + + return find_lock_page(mapping, idx); +} + +/* + * Return whether there is a pagecache page to back given address within VMA. + * Caller follow_hugetlb_page() holds page_table_lock so we cannot lock_page. + */ +static bool hugetlbfs_pagecache_present(struct hstate *h, + struct vm_area_struct *vma, unsigned long address) +{ + struct address_space *mapping; + pgoff_t idx; + struct page *page; + + mapping = vma->vm_file->f_mapping; + idx = vma_hugecache_offset(h, vma, address); + + page = find_get_page(mapping, idx); + if (page) + put_page(page); + return page != NULL; +} + +int huge_add_to_page_cache(struct page *page, struct address_space *mapping, + pgoff_t idx) +{ + struct inode *inode = mapping->host; + struct hstate *h = hstate_inode(inode); + int err = add_to_page_cache(page, mapping, idx, GFP_KERNEL); + + if (err) + return err; + ClearPagePrivate(page); + + /* + * set page dirty so that it will not be removed from cache/file + * by non-hugetlbfs specific code paths. + */ + set_page_dirty(page); + + spin_lock(&inode->i_lock); + inode->i_blocks += blocks_per_huge_page(h); + spin_unlock(&inode->i_lock); + return 0; +} + +static vm_fault_t hugetlb_no_page(struct mm_struct *mm, + struct vm_area_struct *vma, + struct address_space *mapping, pgoff_t idx, + unsigned long address, pte_t *ptep, unsigned int flags) +{ + struct hstate *h = hstate_vma(vma); + vm_fault_t ret = VM_FAULT_SIGBUS; + int anon_rmap = 0; + unsigned long size; + struct page *page; + pte_t new_pte; + spinlock_t *ptl; + unsigned long haddr = address & huge_page_mask(h); + bool new_page = false; + u32 hash = hugetlb_fault_mutex_hash(mapping, idx); + + /* + * Currently, we are forced to kill the process in the event the + * original mapper has unmapped pages from the child due to a failed + * COW. Warn that such a situation has occurred as it may not be obvious + */ + if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) { + pr_warn_ratelimited("PID %d killed due to inadequate hugepage pool\n", + current->pid); + goto out; + } + + /* + * We can not race with truncation due to holding i_mmap_rwsem. + * i_size is modified when holding i_mmap_rwsem, so check here + * once for faults beyond end of file. + */ + size = i_size_read(mapping->host) >> huge_page_shift(h); + if (idx >= size) + goto out; + +retry: + page = find_lock_page(mapping, idx); + if (!page) { + /* + * Check for page in userfault range + */ + if (userfaultfd_missing(vma)) { + struct vm_fault vmf = { + .vma = vma, + .address = haddr, + .flags = flags, + /* + * Hard to debug if it ends up being + * used by a callee that assumes + * something about the other + * uninitialized fields... same as in + * memory.c + */ + }; + + /* + * vma_lock and hugetlb_fault_mutex must be dropped + * before handling userfault. Also mmap_lock will + * be dropped during handling userfault, any vma + * operation should be careful from here. + */ + mutex_unlock(&hugetlb_fault_mutex_table[hash]); + i_mmap_unlock_read(mapping); + return handle_userfault(&vmf, VM_UFFD_MISSING); + } + + page = alloc_huge_page(vma, haddr, 0); + if (IS_ERR(page)) { + /* + * Returning error will result in faulting task being + * sent SIGBUS. The hugetlb fault mutex prevents two + * tasks from racing to fault in the same page which + * could result in false unable to allocate errors. + * Page migration does not take the fault mutex, but + * does a clear then write of pte's under page table + * lock. Page fault code could race with migration, + * notice the clear pte and try to allocate a page + * here. Before returning error, get ptl and make + * sure there really is no pte entry. + */ + ptl = huge_pte_lock(h, mm, ptep); + if (!huge_pte_none(huge_ptep_get(ptep))) { + ret = 0; + spin_unlock(ptl); + goto out; + } + spin_unlock(ptl); + ret = vmf_error(PTR_ERR(page)); + goto out; + } + clear_huge_page(page, address, pages_per_huge_page(h)); + __SetPageUptodate(page); + new_page = true; + + if (vma->vm_flags & VM_MAYSHARE) { + int err = huge_add_to_page_cache(page, mapping, idx); + if (err) { + put_page(page); + if (err == -EEXIST) + goto retry; + goto out; + } + } else { + lock_page(page); + if (unlikely(anon_vma_prepare(vma))) { + ret = VM_FAULT_OOM; + goto backout_unlocked; + } + anon_rmap = 1; + } + } else { + /* + * If memory error occurs between mmap() and fault, some process + * don't have hwpoisoned swap entry for errored virtual address. + * So we need to block hugepage fault by PG_hwpoison bit check. + */ + if (unlikely(PageHWPoison(page))) { + ret = VM_FAULT_HWPOISON_LARGE | + VM_FAULT_SET_HINDEX(hstate_index(h)); + goto backout_unlocked; + } + } + + /* + * If we are going to COW a private mapping later, we examine the + * pending reservations for this page now. This will ensure that + * any allocations necessary to record that reservation occur outside + * the spinlock. + */ + if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { + if (vma_needs_reservation(h, vma, haddr) < 0) { + ret = VM_FAULT_OOM; + goto backout_unlocked; + } + /* Just decrements count, does not deallocate */ + vma_end_reservation(h, vma, haddr); + } + + ptl = huge_pte_lock(h, mm, ptep); + ret = 0; + if (!huge_pte_none(huge_ptep_get(ptep))) + goto backout; + + if (anon_rmap) { + ClearPagePrivate(page); + hugepage_add_new_anon_rmap(page, vma, haddr); + } else + page_dup_rmap(page, true); + new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE) + && (vma->vm_flags & VM_SHARED))); + set_huge_pte_at(mm, haddr, ptep, new_pte); + + hugetlb_count_add(pages_per_huge_page(h), mm); + if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { + /* Optimization, do the COW without a second fault */ + ret = hugetlb_cow(mm, vma, address, ptep, page, ptl); + } + + spin_unlock(ptl); + + /* + * Only make newly allocated pages active. Existing pages found + * in the pagecache could be !page_huge_active() if they have been + * isolated for migration. + */ + if (new_page) + set_page_huge_active(page); + + unlock_page(page); +out: + mutex_unlock(&hugetlb_fault_mutex_table[hash]); + i_mmap_unlock_read(mapping); + return ret; + +backout: + spin_unlock(ptl); +backout_unlocked: + unlock_page(page); + restore_reserve_on_error(h, vma, haddr, page); + put_page(page); + goto out; +} + +#ifdef CONFIG_SMP +u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx) +{ + unsigned long key[2]; + u32 hash; + + key[0] = (unsigned long) mapping; + key[1] = idx; + + hash = jhash2((u32 *)&key, sizeof(key)/(sizeof(u32)), 0); + + return hash & (num_fault_mutexes - 1); +} +#else +/* + * For uniprocesor systems we always use a single mutex, so just + * return 0 and avoid the hashing overhead. + */ +u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx) +{ + return 0; +} +#endif + +vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, unsigned int flags) +{ + pte_t *ptep, entry; + spinlock_t *ptl; + vm_fault_t ret; + u32 hash; + pgoff_t idx; + struct page *page = NULL; + struct page *pagecache_page = NULL; + struct hstate *h = hstate_vma(vma); + struct address_space *mapping; + int need_wait_lock = 0; + unsigned long haddr = address & huge_page_mask(h); + + ptep = huge_pte_offset(mm, haddr, huge_page_size(h)); + if (ptep) { + /* + * Since we hold no locks, ptep could be stale. That is + * OK as we are only making decisions based on content and + * not actually modifying content here. + */ + entry = huge_ptep_get(ptep); + if (unlikely(is_hugetlb_entry_migration(entry))) { + migration_entry_wait_huge(vma, mm, ptep); + return 0; + } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) + return VM_FAULT_HWPOISON_LARGE | + VM_FAULT_SET_HINDEX(hstate_index(h)); + } + + /* + * Acquire i_mmap_rwsem before calling huge_pte_alloc and hold + * until finished with ptep. This serves two purposes: + * 1) It prevents huge_pmd_unshare from being called elsewhere + * and making the ptep no longer valid. + * 2) It synchronizes us with i_size modifications during truncation. + * + * ptep could have already be assigned via huge_pte_offset. That + * is OK, as huge_pte_alloc will return the same value unless + * something has changed. + */ + mapping = vma->vm_file->f_mapping; + i_mmap_lock_read(mapping); + ptep = huge_pte_alloc(mm, haddr, huge_page_size(h)); + if (!ptep) { + i_mmap_unlock_read(mapping); + return VM_FAULT_OOM; + } + + /* + * Serialize hugepage allocation and instantiation, so that we don't + * get spurious allocation failures if two CPUs race to instantiate + * the same page in the page cache. + */ + idx = vma_hugecache_offset(h, vma, haddr); + hash = hugetlb_fault_mutex_hash(mapping, idx); + mutex_lock(&hugetlb_fault_mutex_table[hash]); + + entry = huge_ptep_get(ptep); + if (huge_pte_none(entry)) + /* + * hugetlb_no_page will drop vma lock and hugetlb fault + * mutex internally, which make us return immediately. + */ + return hugetlb_no_page(mm, vma, mapping, idx, address, ptep, flags); + + ret = 0; + + /* + * entry could be a migration/hwpoison entry at this point, so this + * check prevents the kernel from going below assuming that we have + * an active hugepage in pagecache. This goto expects the 2nd page + * fault, and is_hugetlb_entry_(migration|hwpoisoned) check will + * properly handle it. + */ + if (!pte_present(entry)) + goto out_mutex; + + /* + * If we are going to COW the mapping later, we examine the pending + * reservations for this page now. This will ensure that any + * allocations necessary to record that reservation occur outside the + * spinlock. For private mappings, we also lookup the pagecache + * page now as it is used to determine if a reservation has been + * consumed. + */ + if ((flags & FAULT_FLAG_WRITE) && !huge_pte_write(entry)) { + if (vma_needs_reservation(h, vma, haddr) < 0) { + ret = VM_FAULT_OOM; + goto out_mutex; + } + /* Just decrements count, does not deallocate */ + vma_end_reservation(h, vma, haddr); + + if (!(vma->vm_flags & VM_MAYSHARE)) + pagecache_page = hugetlbfs_pagecache_page(h, + vma, haddr); + } + + ptl = huge_pte_lock(h, mm, ptep); + + /* Check for a racing update before calling hugetlb_cow */ + if (unlikely(!pte_same(entry, huge_ptep_get(ptep)))) + goto out_ptl; + + /* + * hugetlb_cow() requires page locks of pte_page(entry) and + * pagecache_page, so here we need take the former one + * when page != pagecache_page or !pagecache_page. + */ + page = pte_page(entry); + if (page != pagecache_page) + if (!trylock_page(page)) { + need_wait_lock = 1; + goto out_ptl; + } + + get_page(page); + + if (flags & FAULT_FLAG_WRITE) { + if (!huge_pte_write(entry)) { + ret = hugetlb_cow(mm, vma, address, ptep, + pagecache_page, ptl); + goto out_put_page; + } + entry = huge_pte_mkdirty(entry); + } + entry = pte_mkyoung(entry); + if (huge_ptep_set_access_flags(vma, haddr, ptep, entry, + flags & FAULT_FLAG_WRITE)) + update_mmu_cache(vma, haddr, ptep); +out_put_page: + if (page != pagecache_page) + unlock_page(page); + put_page(page); +out_ptl: + spin_unlock(ptl); + + if (pagecache_page) { + unlock_page(pagecache_page); + put_page(pagecache_page); + } +out_mutex: + mutex_unlock(&hugetlb_fault_mutex_table[hash]); + i_mmap_unlock_read(mapping); + /* + * Generally it's safe to hold refcount during waiting page lock. But + * here we just wait to defer the next page fault to avoid busy loop and + * the page is not used after unlocked before returning from the current + * page fault. So we are safe from accessing freed page, even if we wait + * here without taking refcount. + */ + if (need_wait_lock) + wait_on_page_locked(page); + return ret; +} + +/* + * Used by userfaultfd UFFDIO_COPY. Based on mcopy_atomic_pte with + * modifications for huge pages. + */ +int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, + pte_t *dst_pte, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + unsigned long src_addr, + struct page **pagep) +{ + struct address_space *mapping; + pgoff_t idx; + unsigned long size; + int vm_shared = dst_vma->vm_flags & VM_SHARED; + struct hstate *h = hstate_vma(dst_vma); + pte_t _dst_pte; + spinlock_t *ptl; + int ret; + struct page *page; + + if (!*pagep) { + /* If a page already exists, then it's UFFDIO_COPY for + * a non-missing case. Return -EEXIST. + */ + if (vm_shared && + hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) { + ret = -EEXIST; + goto out; + } + + page = alloc_huge_page(dst_vma, dst_addr, 0); + if (IS_ERR(page)) { + ret = -ENOMEM; + goto out; + } + + ret = copy_huge_page_from_user(page, + (const void __user *) src_addr, + pages_per_huge_page(h), false); + + /* fallback to copy_from_user outside mmap_lock */ + if (unlikely(ret)) { + ret = -ENOENT; + *pagep = page; + /* don't free the page */ + goto out; + } + } else { + page = *pagep; + *pagep = NULL; + } + + /* + * The memory barrier inside __SetPageUptodate makes sure that + * preceding stores to the page contents become visible before + * the set_pte_at() write. + */ + __SetPageUptodate(page); + + mapping = dst_vma->vm_file->f_mapping; + idx = vma_hugecache_offset(h, dst_vma, dst_addr); + + /* + * If shared, add to page cache + */ + if (vm_shared) { + size = i_size_read(mapping->host) >> huge_page_shift(h); + ret = -EFAULT; + if (idx >= size) + goto out_release_nounlock; + + /* + * Serialization between remove_inode_hugepages() and + * huge_add_to_page_cache() below happens through the + * hugetlb_fault_mutex_table that here must be hold by + * the caller. + */ + ret = huge_add_to_page_cache(page, mapping, idx); + if (ret) + goto out_release_nounlock; + } + + ptl = huge_pte_lockptr(h, dst_mm, dst_pte); + spin_lock(ptl); + + /* + * Recheck the i_size after holding PT lock to make sure not + * to leave any page mapped (as page_mapped()) beyond the end + * of the i_size (remove_inode_hugepages() is strict about + * enforcing that). If we bail out here, we'll also leave a + * page in the radix tree in the vm_shared case beyond the end + * of the i_size, but remove_inode_hugepages() will take care + * of it as soon as we drop the hugetlb_fault_mutex_table. + */ + size = i_size_read(mapping->host) >> huge_page_shift(h); + ret = -EFAULT; + if (idx >= size) + goto out_release_unlock; + + ret = -EEXIST; + if (!huge_pte_none(huge_ptep_get(dst_pte))) + goto out_release_unlock; + + if (vm_shared) { + page_dup_rmap(page, true); + } else { + ClearPagePrivate(page); + hugepage_add_new_anon_rmap(page, dst_vma, dst_addr); + } + + _dst_pte = make_huge_pte(dst_vma, page, dst_vma->vm_flags & VM_WRITE); + if (dst_vma->vm_flags & VM_WRITE) + _dst_pte = huge_pte_mkdirty(_dst_pte); + _dst_pte = pte_mkyoung(_dst_pte); + + set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); + + (void)huge_ptep_set_access_flags(dst_vma, dst_addr, dst_pte, _dst_pte, + dst_vma->vm_flags & VM_WRITE); + hugetlb_count_add(pages_per_huge_page(h), dst_mm); + + /* No need to invalidate - it was non-present before */ + update_mmu_cache(dst_vma, dst_addr, dst_pte); + + spin_unlock(ptl); + set_page_huge_active(page); + if (vm_shared) + unlock_page(page); + ret = 0; +out: + return ret; +out_release_unlock: + spin_unlock(ptl); + if (vm_shared) + unlock_page(page); +out_release_nounlock: + put_page(page); + goto out; +} + +long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, + struct page **pages, struct vm_area_struct **vmas, + unsigned long *position, unsigned long *nr_pages, + long i, unsigned int flags, int *locked) +{ + unsigned long pfn_offset; + unsigned long vaddr = *position; + unsigned long remainder = *nr_pages; + struct hstate *h = hstate_vma(vma); + int err = -EFAULT; + + while (vaddr < vma->vm_end && remainder) { + pte_t *pte; + spinlock_t *ptl = NULL; + int absent; + struct page *page; + + /* + * If we have a pending SIGKILL, don't keep faulting pages and + * potentially allocating memory. + */ + if (fatal_signal_pending(current)) { + remainder = 0; + break; + } + + /* + * Some archs (sparc64, sh*) have multiple pte_ts to + * each hugepage. We have to make sure we get the + * first, for the page indexing below to work. + * + * Note that page table lock is not held when pte is null. + */ + pte = huge_pte_offset(mm, vaddr & huge_page_mask(h), + huge_page_size(h)); + if (pte) + ptl = huge_pte_lock(h, mm, pte); + absent = !pte || huge_pte_none(huge_ptep_get(pte)); + + /* + * When coredumping, it suits get_dump_page if we just return + * an error where there's an empty slot with no huge pagecache + * to back it. This way, we avoid allocating a hugepage, and + * the sparse dumpfile avoids allocating disk blocks, but its + * huge holes still show up with zeroes where they need to be. + */ + if (absent && (flags & FOLL_DUMP) && + !hugetlbfs_pagecache_present(h, vma, vaddr)) { + if (pte) + spin_unlock(ptl); + remainder = 0; + break; + } + + /* + * We need call hugetlb_fault for both hugepages under migration + * (in which case hugetlb_fault waits for the migration,) and + * hwpoisoned hugepages (in which case we need to prevent the + * caller from accessing to them.) In order to do this, we use + * here is_swap_pte instead of is_hugetlb_entry_migration and + * is_hugetlb_entry_hwpoisoned. This is because it simply covers + * both cases, and because we can't follow correct pages + * directly from any kind of swap entries. + */ + if (absent || is_swap_pte(huge_ptep_get(pte)) || + ((flags & FOLL_WRITE) && + !huge_pte_write(huge_ptep_get(pte)))) { + vm_fault_t ret; + unsigned int fault_flags = 0; + + if (pte) + spin_unlock(ptl); + if (flags & FOLL_WRITE) + fault_flags |= FAULT_FLAG_WRITE; + if (locked) + fault_flags |= FAULT_FLAG_ALLOW_RETRY | + FAULT_FLAG_KILLABLE; + if (flags & FOLL_NOWAIT) + fault_flags |= FAULT_FLAG_ALLOW_RETRY | + FAULT_FLAG_RETRY_NOWAIT; + if (flags & FOLL_TRIED) { + /* + * Note: FAULT_FLAG_ALLOW_RETRY and + * FAULT_FLAG_TRIED can co-exist + */ + fault_flags |= FAULT_FLAG_TRIED; + } + ret = hugetlb_fault(mm, vma, vaddr, fault_flags); + if (ret & VM_FAULT_ERROR) { + err = vm_fault_to_errno(ret, flags); + remainder = 0; + break; + } + if (ret & VM_FAULT_RETRY) { + if (locked && + !(fault_flags & FAULT_FLAG_RETRY_NOWAIT)) + *locked = 0; + *nr_pages = 0; + /* + * VM_FAULT_RETRY must not return an + * error, it will return zero + * instead. + * + * No need to update "position" as the + * caller will not check it after + * *nr_pages is set to 0. + */ + return i; + } + continue; + } + + pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT; + page = pte_page(huge_ptep_get(pte)); + + /* + * If subpage information not requested, update counters + * and skip the same_page loop below. + */ + if (!pages && !vmas && !pfn_offset && + (vaddr + huge_page_size(h) < vma->vm_end) && + (remainder >= pages_per_huge_page(h))) { + vaddr += huge_page_size(h); + remainder -= pages_per_huge_page(h); + i += pages_per_huge_page(h); + spin_unlock(ptl); + continue; + } + +same_page: + if (pages) { + pages[i] = mem_map_offset(page, pfn_offset); + /* + * try_grab_page() should always succeed here, because: + * a) we hold the ptl lock, and b) we've just checked + * that the huge page is present in the page tables. If + * the huge page is present, then the tail pages must + * also be present. The ptl prevents the head page and + * tail pages from being rearranged in any way. So this + * page must be available at this point, unless the page + * refcount overflowed: + */ + if (WARN_ON_ONCE(!try_grab_page(pages[i], flags))) { + spin_unlock(ptl); + remainder = 0; + err = -ENOMEM; + break; + } + } + + if (vmas) + vmas[i] = vma; + + vaddr += PAGE_SIZE; + ++pfn_offset; + --remainder; + ++i; + if (vaddr < vma->vm_end && remainder && + pfn_offset < pages_per_huge_page(h)) { + /* + * We use pfn_offset to avoid touching the pageframes + * of this compound page. + */ + goto same_page; + } + spin_unlock(ptl); + } + *nr_pages = remainder; + /* + * setting position is actually required only if remainder is + * not zero but it's faster not to add a "if (remainder)" + * branch. + */ + *position = vaddr; + + return i ? i : err; +} + +#ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE +/* + * ARCHes with special requirements for evicting HUGETLB backing TLB entries can + * implement this. + */ +#define flush_hugetlb_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) +#endif + +unsigned long hugetlb_change_protection(struct vm_area_struct *vma, + unsigned long address, unsigned long end, pgprot_t newprot) +{ + struct mm_struct *mm = vma->vm_mm; + unsigned long start = address; + pte_t *ptep; + pte_t pte; + struct hstate *h = hstate_vma(vma); + unsigned long pages = 0; + bool shared_pmd = false; + struct mmu_notifier_range range; + + /* + * In the case of shared PMDs, the area to flush could be beyond + * start/end. Set range.start/range.end to cover the maximum possible + * range if PMD sharing is possible. + */ + mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_VMA, + 0, vma, mm, start, end); + adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); + + BUG_ON(address >= end); + flush_cache_range(vma, range.start, range.end); + + mmu_notifier_invalidate_range_start(&range); + i_mmap_lock_write(vma->vm_file->f_mapping); + for (; address < end; address += huge_page_size(h)) { + spinlock_t *ptl; + ptep = huge_pte_offset(mm, address, huge_page_size(h)); + if (!ptep) + continue; + ptl = huge_pte_lock(h, mm, ptep); + if (huge_pmd_unshare(mm, vma, &address, ptep)) { + pages++; + spin_unlock(ptl); + shared_pmd = true; + continue; + } + pte = huge_ptep_get(ptep); + if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) { + spin_unlock(ptl); + continue; + } + if (unlikely(is_hugetlb_entry_migration(pte))) { + swp_entry_t entry = pte_to_swp_entry(pte); + + if (is_write_migration_entry(entry)) { + pte_t newpte; + + make_migration_entry_read(&entry); + newpte = swp_entry_to_pte(entry); + set_huge_swap_pte_at(mm, address, ptep, + newpte, huge_page_size(h)); + pages++; + } + spin_unlock(ptl); + continue; + } + if (!huge_pte_none(pte)) { + pte_t old_pte; + + old_pte = huge_ptep_modify_prot_start(vma, address, ptep); + pte = pte_mkhuge(huge_pte_modify(old_pte, newprot)); + pte = arch_make_huge_pte(pte, vma, NULL, 0); + huge_ptep_modify_prot_commit(vma, address, ptep, old_pte, pte); + pages++; + } + spin_unlock(ptl); + } + /* + * Must flush TLB before releasing i_mmap_rwsem: x86's huge_pmd_unshare + * may have cleared our pud entry and done put_page on the page table: + * once we release i_mmap_rwsem, another task can do the final put_page + * and that page table be reused and filled with junk. If we actually + * did unshare a page of pmds, flush the range corresponding to the pud. + */ + if (shared_pmd) + flush_hugetlb_tlb_range(vma, range.start, range.end); + else + flush_hugetlb_tlb_range(vma, start, end); + /* + * No need to call mmu_notifier_invalidate_range() we are downgrading + * page table protection not changing it to point to a new page. + * + * See Documentation/vm/mmu_notifier.rst + */ + i_mmap_unlock_write(vma->vm_file->f_mapping); + mmu_notifier_invalidate_range_end(&range); + + return pages << h->order; +} + +int hugetlb_reserve_pages(struct inode *inode, + long from, long to, + struct vm_area_struct *vma, + vm_flags_t vm_flags) +{ + long ret, chg, add = -1; + struct hstate *h = hstate_inode(inode); + struct hugepage_subpool *spool = subpool_inode(inode); + struct resv_map *resv_map; + struct hugetlb_cgroup *h_cg = NULL; + long gbl_reserve, regions_needed = 0; + + /* This should never happen */ + if (from > to) { + VM_WARN(1, "%s called with a negative range\n", __func__); + return -EINVAL; + } + + /* + * Only apply hugepage reservation if asked. At fault time, an + * attempt will be made for VM_NORESERVE to allocate a page + * without using reserves + */ + if (vm_flags & VM_NORESERVE) + return 0; + + /* + * Shared mappings base their reservation on the number of pages that + * are already allocated on behalf of the file. Private mappings need + * to reserve the full area even if read-only as mprotect() may be + * called to make the mapping read-write. Assume !vma is a shm mapping + */ + if (!vma || vma->vm_flags & VM_MAYSHARE) { + /* + * resv_map can not be NULL as hugetlb_reserve_pages is only + * called for inodes for which resv_maps were created (see + * hugetlbfs_get_inode). + */ + resv_map = inode_resv_map(inode); + + chg = region_chg(resv_map, from, to, ®ions_needed); + + } else { + /* Private mapping. */ + resv_map = resv_map_alloc(); + if (!resv_map) + return -ENOMEM; + + chg = to - from; + + set_vma_resv_map(vma, resv_map); + set_vma_resv_flags(vma, HPAGE_RESV_OWNER); + } + + if (chg < 0) { + ret = chg; + goto out_err; + } + + ret = hugetlb_cgroup_charge_cgroup_rsvd( + hstate_index(h), chg * pages_per_huge_page(h), &h_cg); + + if (ret < 0) { + ret = -ENOMEM; + goto out_err; + } + + if (vma && !(vma->vm_flags & VM_MAYSHARE) && h_cg) { + /* For private mappings, the hugetlb_cgroup uncharge info hangs + * of the resv_map. + */ + resv_map_set_hugetlb_cgroup_uncharge_info(resv_map, h_cg, h); + } + + /* + * There must be enough pages in the subpool for the mapping. If + * the subpool has a minimum size, there may be some global + * reservations already in place (gbl_reserve). + */ + gbl_reserve = hugepage_subpool_get_pages(spool, chg); + if (gbl_reserve < 0) { + ret = -ENOSPC; + goto out_uncharge_cgroup; + } + + /* + * Check enough hugepages are available for the reservation. + * Hand the pages back to the subpool if there are not + */ + ret = hugetlb_acct_memory(h, gbl_reserve); + if (ret < 0) { + goto out_put_pages; + } + + /* + * Account for the reservations made. Shared mappings record regions + * that have reservations as they are shared by multiple VMAs. + * When the last VMA disappears, the region map says how much + * the reservation was and the page cache tells how much of + * the reservation was consumed. Private mappings are per-VMA and + * only the consumed reservations are tracked. When the VMA + * disappears, the original reservation is the VMA size and the + * consumed reservations are stored in the map. Hence, nothing + * else has to be done for private mappings here + */ + if (!vma || vma->vm_flags & VM_MAYSHARE) { + add = region_add(resv_map, from, to, regions_needed, h, h_cg); + + if (unlikely(add < 0)) { + hugetlb_acct_memory(h, -gbl_reserve); + ret = add; + goto out_put_pages; + } else if (unlikely(chg > add)) { + /* + * pages in this range were added to the reserve + * map between region_chg and region_add. This + * indicates a race with alloc_huge_page. Adjust + * the subpool and reserve counts modified above + * based on the difference. + */ + long rsv_adjust; + + /* + * hugetlb_cgroup_uncharge_cgroup_rsvd() will put the + * reference to h_cg->css. See comment below for detail. + */ + hugetlb_cgroup_uncharge_cgroup_rsvd( + hstate_index(h), + (chg - add) * pages_per_huge_page(h), h_cg); + + rsv_adjust = hugepage_subpool_put_pages(spool, + chg - add); + hugetlb_acct_memory(h, -rsv_adjust); + } else if (h_cg) { + /* + * The file_regions will hold their own reference to + * h_cg->css. So we should release the reference held + * via hugetlb_cgroup_charge_cgroup_rsvd() when we are + * done. + */ + hugetlb_cgroup_put_rsvd_cgroup(h_cg); + } + } + return 0; +out_put_pages: + /* put back original number of pages, chg */ + (void)hugepage_subpool_put_pages(spool, chg); +out_uncharge_cgroup: + hugetlb_cgroup_uncharge_cgroup_rsvd(hstate_index(h), + chg * pages_per_huge_page(h), h_cg); +out_err: + if (!vma || vma->vm_flags & VM_MAYSHARE) + /* Only call region_abort if the region_chg succeeded but the + * region_add failed or didn't run. + */ + if (chg >= 0 && add < 0) + region_abort(resv_map, from, to, regions_needed); + if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) + kref_put(&resv_map->refs, resv_map_release); + return ret; +} + +long hugetlb_unreserve_pages(struct inode *inode, long start, long end, + long freed) +{ + struct hstate *h = hstate_inode(inode); + struct resv_map *resv_map = inode_resv_map(inode); + long chg = 0; + struct hugepage_subpool *spool = subpool_inode(inode); + long gbl_reserve; + + /* + * Since this routine can be called in the evict inode path for all + * hugetlbfs inodes, resv_map could be NULL. + */ + if (resv_map) { + chg = region_del(resv_map, start, end); + /* + * region_del() can fail in the rare case where a region + * must be split and another region descriptor can not be + * allocated. If end == LONG_MAX, it will not fail. + */ + if (chg < 0) + return chg; + } + + spin_lock(&inode->i_lock); + inode->i_blocks -= (blocks_per_huge_page(h) * freed); + spin_unlock(&inode->i_lock); + + /* + * If the subpool has a minimum size, the number of global + * reservations to be released may be adjusted. + */ + gbl_reserve = hugepage_subpool_put_pages(spool, (chg - freed)); + hugetlb_acct_memory(h, -gbl_reserve); + + return 0; +} + +#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE +static unsigned long page_table_shareable(struct vm_area_struct *svma, + struct vm_area_struct *vma, + unsigned long addr, pgoff_t idx) +{ + unsigned long saddr = ((idx - svma->vm_pgoff) << PAGE_SHIFT) + + svma->vm_start; + unsigned long sbase = saddr & PUD_MASK; + unsigned long s_end = sbase + PUD_SIZE; + + /* Allow segments to share if only one is marked locked */ + unsigned long vm_flags = vma->vm_flags & VM_LOCKED_CLEAR_MASK; + unsigned long svm_flags = svma->vm_flags & VM_LOCKED_CLEAR_MASK; + + /* + * match the virtual addresses, permission and the alignment of the + * page table page. + */ + if (pmd_index(addr) != pmd_index(saddr) || + vm_flags != svm_flags || + sbase < svma->vm_start || svma->vm_end < s_end) + return 0; + + return saddr; +} + +static bool vma_shareable(struct vm_area_struct *vma, unsigned long addr) +{ + unsigned long base = addr & PUD_MASK; + unsigned long end = base + PUD_SIZE; + + /* + * check on proper vm_flags and page table alignment + */ + if (vma->vm_flags & VM_MAYSHARE && range_in_vma(vma, base, end)) + return true; + return false; +} + +/* + * Determine if start,end range within vma could be mapped by shared pmd. + * If yes, adjust start and end to cover range associated with possible + * shared pmd mappings. + */ +void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, + unsigned long *start, unsigned long *end) +{ + unsigned long v_start = ALIGN(vma->vm_start, PUD_SIZE), + v_end = ALIGN_DOWN(vma->vm_end, PUD_SIZE); + + /* + * vma need span at least one aligned PUD size and the start,end range + * must at least partialy within it. + */ + if (!(vma->vm_flags & VM_MAYSHARE) || !(v_end > v_start) || + (*end <= v_start) || (*start >= v_end)) + return; + + /* Extend the range to be PUD aligned for a worst case scenario */ + if (*start > v_start) + *start = ALIGN_DOWN(*start, PUD_SIZE); + + if (*end < v_end) + *end = ALIGN(*end, PUD_SIZE); +} + +/* + * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc() + * and returns the corresponding pte. While this is not necessary for the + * !shared pmd case because we can allocate the pmd later as well, it makes the + * code much cleaner. + * + * This routine must be called with i_mmap_rwsem held in at least read mode if + * sharing is possible. For hugetlbfs, this prevents removal of any page + * table entries associated with the address space. This is important as we + * are setting up sharing based on existing page table entries (mappings). + * + * NOTE: This routine is only called from huge_pte_alloc. Some callers of + * huge_pte_alloc know that sharing is not possible and do not take + * i_mmap_rwsem as a performance optimization. This is handled by the + * if !vma_shareable check at the beginning of the routine. i_mmap_rwsem is + * only required for subsequent processing. + */ +pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) +{ + struct vm_area_struct *vma = find_vma(mm, addr); + struct address_space *mapping = vma->vm_file->f_mapping; + pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) + + vma->vm_pgoff; + struct vm_area_struct *svma; + unsigned long saddr; + pte_t *spte = NULL; + pte_t *pte; + spinlock_t *ptl; + + if (!vma_shareable(vma, addr)) + return (pte_t *)pmd_alloc(mm, pud, addr); + + i_mmap_assert_locked(mapping); + vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) { + if (svma == vma) + continue; + + saddr = page_table_shareable(svma, vma, addr, idx); + if (saddr) { + spte = huge_pte_offset(svma->vm_mm, saddr, + vma_mmu_pagesize(svma)); + if (spte) { + get_page(virt_to_page(spte)); + break; + } + } + } + + if (!spte) + goto out; + + ptl = huge_pte_lock(hstate_vma(vma), mm, spte); + if (pud_none(*pud)) { + pud_populate(mm, pud, + (pmd_t *)((unsigned long)spte & PAGE_MASK)); + mm_inc_nr_pmds(mm); + } else { + put_page(virt_to_page(spte)); + } + spin_unlock(ptl); +out: + pte = (pte_t *)pmd_alloc(mm, pud, addr); + return pte; +} + +/* + * unmap huge page backed by shared pte. + * + * Hugetlb pte page is ref counted at the time of mapping. If pte is shared + * indicated by page_count > 1, unmap is achieved by clearing pud and + * decrementing the ref count. If count == 1, the pte page is not shared. + * + * Called with page table lock held and i_mmap_rwsem held in write mode. + * + * returns: 1 successfully unmapped a shared pte page + * 0 the underlying pte page is not shared, or it is the last user + */ +int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long *addr, pte_t *ptep) +{ + pgd_t *pgd = pgd_offset(mm, *addr); + p4d_t *p4d = p4d_offset(pgd, *addr); + pud_t *pud = pud_offset(p4d, *addr); + + i_mmap_assert_write_locked(vma->vm_file->f_mapping); + BUG_ON(page_count(virt_to_page(ptep)) == 0); + if (page_count(virt_to_page(ptep)) == 1) + return 0; + + pud_clear(pud); + put_page(virt_to_page(ptep)); + mm_dec_nr_pmds(mm); + /* + * This update of passed address optimizes loops sequentially + * processing addresses in increments of huge page size (PMD_SIZE + * in this case). By clearing the pud, a PUD_SIZE area is unmapped. + * Update address to the 'last page' in the cleared area so that + * calling loop can move to first page past this area. + */ + *addr |= PUD_SIZE - PMD_SIZE; + return 1; +} +#define want_pmd_share() (1) +#else /* !CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ +pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) +{ + return NULL; +} + +int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long *addr, pte_t *ptep) +{ + return 0; +} + +void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, + unsigned long *start, unsigned long *end) +{ +} +#define want_pmd_share() (0) +#endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ + +#ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB +pte_t *huge_pte_alloc(struct mm_struct *mm, + unsigned long addr, unsigned long sz) +{ + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pte_t *pte = NULL; + + pgd = pgd_offset(mm, addr); + p4d = p4d_alloc(mm, pgd, addr); + if (!p4d) + return NULL; + pud = pud_alloc(mm, p4d, addr); + if (pud) { + if (sz == PUD_SIZE) { + pte = (pte_t *)pud; + } else { + BUG_ON(sz != PMD_SIZE); + if (want_pmd_share() && pud_none(*pud)) + pte = huge_pmd_share(mm, addr, pud); + else + pte = (pte_t *)pmd_alloc(mm, pud, addr); + } + } + BUG_ON(pte && pte_present(*pte) && !pte_huge(*pte)); + + return pte; +} + +/* + * huge_pte_offset() - Walk the page table to resolve the hugepage + * entry at address @addr + * + * Return: Pointer to page table entry (PUD or PMD) for + * address @addr, or NULL if a !p*d_present() entry is encountered and the + * size @sz doesn't match the hugepage size at this level of the page + * table. + */ +pte_t *huge_pte_offset(struct mm_struct *mm, + unsigned long addr, unsigned long sz) +{ + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + pgd = pgd_offset(mm, addr); + if (!pgd_present(*pgd)) + return NULL; + p4d = p4d_offset(pgd, addr); + if (!p4d_present(*p4d)) + return NULL; + + pud = pud_offset(p4d, addr); + if (sz == PUD_SIZE) + /* must be pud huge, non-present or none */ + return (pte_t *)pud; + if (!pud_present(*pud)) + return NULL; + /* must have a valid entry and size to go further */ + + pmd = pmd_offset(pud, addr); + /* must be pmd huge, non-present or none */ + return (pte_t *)pmd; +} + +#endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */ + +/* + * These functions are overwritable if your architecture needs its own + * behavior. + */ +struct page * __weak +follow_huge_addr(struct mm_struct *mm, unsigned long address, + int write) +{ + return ERR_PTR(-EINVAL); +} + +struct page * __weak +follow_huge_pd(struct vm_area_struct *vma, + unsigned long address, hugepd_t hpd, int flags, int pdshift) +{ + WARN(1, "hugepd follow called with no support for hugepage directory format\n"); + return NULL; +} + +struct page * __weak +follow_huge_pmd_pte(struct vm_area_struct *vma, unsigned long address, int flags) +{ + struct hstate *h = hstate_vma(vma); + struct mm_struct *mm = vma->vm_mm; + struct page *page = NULL; + spinlock_t *ptl; + pte_t *ptep, pte; + + /* FOLL_GET and FOLL_PIN are mutually exclusive. */ + if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == + (FOLL_PIN | FOLL_GET))) + return NULL; + +retry: + ptep = huge_pte_offset(mm, address, huge_page_size(h)); + if (!ptep) + return NULL; + + ptl = huge_pte_lock(h, mm, ptep); + pte = huge_ptep_get(ptep); + if (pte_present(pte)) { + page = pte_page(pte) + + ((address & ~huge_page_mask(h)) >> PAGE_SHIFT); + /* + * try_grab_page() should always succeed here, because: a) we + * hold the pmd (ptl) lock, and b) we've just checked that the + * huge pmd (head) page is present in the page tables. The ptl + * prevents the head page and tail pages from being rearranged + * in any way. So this page must be available at this point, + * unless the page refcount overflowed: + */ + if (WARN_ON_ONCE(!try_grab_page(page, flags))) { + page = NULL; + goto out; + } + } else { + if (is_hugetlb_entry_migration(pte)) { + spin_unlock(ptl); + __migration_entry_wait(mm, ptep, ptl); + goto retry; + } + /* + * hwpoisoned entry is treated as no_page_table in + * follow_page_mask(). + */ + } +out: + spin_unlock(ptl); + return page; +} + +struct page * __weak +follow_huge_pud(struct mm_struct *mm, unsigned long address, + pud_t *pud, int flags) +{ + if (flags & (FOLL_GET | FOLL_PIN)) + return NULL; + + return pte_page(*(pte_t *)pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT); +} + +struct page * __weak +follow_huge_pgd(struct mm_struct *mm, unsigned long address, pgd_t *pgd, int flags) +{ + if (flags & (FOLL_GET | FOLL_PIN)) + return NULL; + + return pte_page(*(pte_t *)pgd) + ((address & ~PGDIR_MASK) >> PAGE_SHIFT); +} + +int isolate_hugetlb(struct page *page, struct list_head *list) +{ + int ret = 0; + + spin_lock(&hugetlb_lock); + if (!PageHeadHuge(page) || !page_huge_active(page) || + !get_page_unless_zero(page)) { + ret = -EBUSY; + goto unlock; + } + clear_page_huge_active(page); + list_move_tail(&page->lru, list); +unlock: + spin_unlock(&hugetlb_lock); + return ret; +} + +void putback_active_hugepage(struct page *page) +{ + VM_BUG_ON_PAGE(!PageHead(page), page); + spin_lock(&hugetlb_lock); + set_page_huge_active(page); + list_move_tail(&page->lru, &(page_hstate(page))->hugepage_activelist); + spin_unlock(&hugetlb_lock); + put_page(page); +} + +void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason) +{ + struct hstate *h = page_hstate(oldpage); + + hugetlb_cgroup_migrate(oldpage, newpage); + set_page_owner_migrate_reason(newpage, reason); + + /* + * transfer temporary state of the new huge page. This is + * reverse to other transitions because the newpage is going to + * be final while the old one will be freed so it takes over + * the temporary status. + * + * Also note that we have to transfer the per-node surplus state + * here as well otherwise the global surplus count will not match + * the per-node's. + */ + if (PageHugeTemporary(newpage)) { + int old_nid = page_to_nid(oldpage); + int new_nid = page_to_nid(newpage); + + SetPageHugeTemporary(oldpage); + ClearPageHugeTemporary(newpage); + + spin_lock(&hugetlb_lock); + if (h->surplus_huge_pages_node[old_nid]) { + h->surplus_huge_pages_node[old_nid]--; + h->surplus_huge_pages_node[new_nid]++; + } + spin_unlock(&hugetlb_lock); + } +} + +#ifdef CONFIG_CMA +static bool cma_reserve_called __initdata; + +static int __init cmdline_parse_hugetlb_cma(char *p) +{ + hugetlb_cma_size = memparse(p, &p); + return 0; +} + +early_param("hugetlb_cma", cmdline_parse_hugetlb_cma); + +void __init hugetlb_cma_reserve(int order) +{ + unsigned long size, reserved, per_node; + int nid; + + cma_reserve_called = true; + + if (!hugetlb_cma_size) + return; + + if (hugetlb_cma_size < (PAGE_SIZE << order)) { + pr_warn("hugetlb_cma: cma area should be at least %lu MiB\n", + (PAGE_SIZE << order) / SZ_1M); + return; + } + + /* + * If 3 GB area is requested on a machine with 4 numa nodes, + * let's allocate 1 GB on first three nodes and ignore the last one. + */ + per_node = DIV_ROUND_UP(hugetlb_cma_size, nr_online_nodes); + pr_info("hugetlb_cma: reserve %lu MiB, up to %lu MiB per node\n", + hugetlb_cma_size / SZ_1M, per_node / SZ_1M); + + reserved = 0; + for_each_node_state(nid, N_ONLINE) { + int res; + char name[CMA_MAX_NAME]; + + size = min(per_node, hugetlb_cma_size - reserved); + size = round_up(size, PAGE_SIZE << order); + + snprintf(name, sizeof(name), "hugetlb%d", nid); + res = cma_declare_contiguous_nid(0, size, 0, PAGE_SIZE << order, + 0, false, name, + &hugetlb_cma[nid], nid); + if (res) { + pr_warn("hugetlb_cma: reservation failed: err %d, node %d", + res, nid); + continue; + } + + reserved += size; + pr_info("hugetlb_cma: reserved %lu MiB on node %d\n", + size / SZ_1M, nid); + + if (reserved >= hugetlb_cma_size) + break; + } +} + +void __init hugetlb_cma_check(void) +{ + if (!hugetlb_cma_size || cma_reserve_called) + return; + + pr_warn("hugetlb_cma: the option isn't supported by current arch\n"); +} + +#endif /* CONFIG_CMA */ diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c new file mode 100644 index 000000000..1348819f5 --- /dev/null +++ b/mm/hugetlb_cgroup.c @@ -0,0 +1,812 @@ +/* + * + * Copyright IBM Corporation, 2012 + * Author Aneesh Kumar K.V + * + * Cgroup v2 + * Copyright (C) 2019 Red Hat, Inc. + * Author: Giuseppe Scrivano + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2.1 of the GNU Lesser General Public License + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it would be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + * + */ + +#include +#include +#include +#include +#include + +#define MEMFILE_PRIVATE(x, val) (((x) << 16) | (val)) +#define MEMFILE_IDX(val) (((val) >> 16) & 0xffff) +#define MEMFILE_ATTR(val) ((val) & 0xffff) + +#define hugetlb_cgroup_from_counter(counter, idx) \ + container_of(counter, struct hugetlb_cgroup, hugepage[idx]) + +static struct hugetlb_cgroup *root_h_cgroup __read_mostly; + +static inline struct page_counter * +__hugetlb_cgroup_counter_from_cgroup(struct hugetlb_cgroup *h_cg, int idx, + bool rsvd) +{ + if (rsvd) + return &h_cg->rsvd_hugepage[idx]; + return &h_cg->hugepage[idx]; +} + +static inline struct page_counter * +hugetlb_cgroup_counter_from_cgroup(struct hugetlb_cgroup *h_cg, int idx) +{ + return __hugetlb_cgroup_counter_from_cgroup(h_cg, idx, false); +} + +static inline struct page_counter * +hugetlb_cgroup_counter_from_cgroup_rsvd(struct hugetlb_cgroup *h_cg, int idx) +{ + return __hugetlb_cgroup_counter_from_cgroup(h_cg, idx, true); +} + +static inline +struct hugetlb_cgroup *hugetlb_cgroup_from_css(struct cgroup_subsys_state *s) +{ + return s ? container_of(s, struct hugetlb_cgroup, css) : NULL; +} + +static inline +struct hugetlb_cgroup *hugetlb_cgroup_from_task(struct task_struct *task) +{ + return hugetlb_cgroup_from_css(task_css(task, hugetlb_cgrp_id)); +} + +static inline bool hugetlb_cgroup_is_root(struct hugetlb_cgroup *h_cg) +{ + return (h_cg == root_h_cgroup); +} + +static inline struct hugetlb_cgroup * +parent_hugetlb_cgroup(struct hugetlb_cgroup *h_cg) +{ + return hugetlb_cgroup_from_css(h_cg->css.parent); +} + +static inline bool hugetlb_cgroup_have_usage(struct hugetlb_cgroup *h_cg) +{ + int idx; + + for (idx = 0; idx < hugetlb_max_hstate; idx++) { + if (page_counter_read( + hugetlb_cgroup_counter_from_cgroup(h_cg, idx))) + return true; + } + return false; +} + +static void hugetlb_cgroup_init(struct hugetlb_cgroup *h_cgroup, + struct hugetlb_cgroup *parent_h_cgroup) +{ + int idx; + + for (idx = 0; idx < HUGE_MAX_HSTATE; idx++) { + struct page_counter *fault_parent = NULL; + struct page_counter *rsvd_parent = NULL; + unsigned long limit; + int ret; + + if (parent_h_cgroup) { + fault_parent = hugetlb_cgroup_counter_from_cgroup( + parent_h_cgroup, idx); + rsvd_parent = hugetlb_cgroup_counter_from_cgroup_rsvd( + parent_h_cgroup, idx); + } + page_counter_init(hugetlb_cgroup_counter_from_cgroup(h_cgroup, + idx), + fault_parent); + page_counter_init( + hugetlb_cgroup_counter_from_cgroup_rsvd(h_cgroup, idx), + rsvd_parent); + + limit = round_down(PAGE_COUNTER_MAX, + 1 << huge_page_order(&hstates[idx])); + + ret = page_counter_set_max( + hugetlb_cgroup_counter_from_cgroup(h_cgroup, idx), + limit); + VM_BUG_ON(ret); + ret = page_counter_set_max( + hugetlb_cgroup_counter_from_cgroup_rsvd(h_cgroup, idx), + limit); + VM_BUG_ON(ret); + } +} + +static struct cgroup_subsys_state * +hugetlb_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) +{ + struct hugetlb_cgroup *parent_h_cgroup = hugetlb_cgroup_from_css(parent_css); + struct hugetlb_cgroup *h_cgroup; + + h_cgroup = kzalloc(sizeof(*h_cgroup), GFP_KERNEL); + if (!h_cgroup) + return ERR_PTR(-ENOMEM); + + if (!parent_h_cgroup) + root_h_cgroup = h_cgroup; + + hugetlb_cgroup_init(h_cgroup, parent_h_cgroup); + return &h_cgroup->css; +} + +static void hugetlb_cgroup_css_free(struct cgroup_subsys_state *css) +{ + struct hugetlb_cgroup *h_cgroup; + + h_cgroup = hugetlb_cgroup_from_css(css); + kfree(h_cgroup); +} + +/* + * Should be called with hugetlb_lock held. + * Since we are holding hugetlb_lock, pages cannot get moved from + * active list or uncharged from the cgroup, So no need to get + * page reference and test for page active here. This function + * cannot fail. + */ +static void hugetlb_cgroup_move_parent(int idx, struct hugetlb_cgroup *h_cg, + struct page *page) +{ + unsigned int nr_pages; + struct page_counter *counter; + struct hugetlb_cgroup *page_hcg; + struct hugetlb_cgroup *parent = parent_hugetlb_cgroup(h_cg); + + page_hcg = hugetlb_cgroup_from_page(page); + /* + * We can have pages in active list without any cgroup + * ie, hugepage with less than 3 pages. We can safely + * ignore those pages. + */ + if (!page_hcg || page_hcg != h_cg) + goto out; + + nr_pages = compound_nr(page); + if (!parent) { + parent = root_h_cgroup; + /* root has no limit */ + page_counter_charge(&parent->hugepage[idx], nr_pages); + } + counter = &h_cg->hugepage[idx]; + /* Take the pages off the local counter */ + page_counter_cancel(counter, nr_pages); + + set_hugetlb_cgroup(page, parent); +out: + return; +} + +/* + * Force the hugetlb cgroup to empty the hugetlb resources by moving them to + * the parent cgroup. + */ +static void hugetlb_cgroup_css_offline(struct cgroup_subsys_state *css) +{ + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css); + struct hstate *h; + struct page *page; + int idx; + + do { + idx = 0; + for_each_hstate(h) { + spin_lock(&hugetlb_lock); + list_for_each_entry(page, &h->hugepage_activelist, lru) + hugetlb_cgroup_move_parent(idx, h_cg, page); + + spin_unlock(&hugetlb_lock); + idx++; + } + cond_resched(); + } while (hugetlb_cgroup_have_usage(h_cg)); +} + +static inline void hugetlb_event(struct hugetlb_cgroup *hugetlb, int idx, + enum hugetlb_memory_event event) +{ + atomic_long_inc(&hugetlb->events_local[idx][event]); + cgroup_file_notify(&hugetlb->events_local_file[idx]); + + do { + atomic_long_inc(&hugetlb->events[idx][event]); + cgroup_file_notify(&hugetlb->events_file[idx]); + } while ((hugetlb = parent_hugetlb_cgroup(hugetlb)) && + !hugetlb_cgroup_is_root(hugetlb)); +} + +static int __hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, + struct hugetlb_cgroup **ptr, + bool rsvd) +{ + int ret = 0; + struct page_counter *counter; + struct hugetlb_cgroup *h_cg = NULL; + + if (hugetlb_cgroup_disabled()) + goto done; + /* + * We don't charge any cgroup if the compound page have less + * than 3 pages. + */ + if (huge_page_order(&hstates[idx]) < HUGETLB_CGROUP_MIN_ORDER) + goto done; +again: + rcu_read_lock(); + h_cg = hugetlb_cgroup_from_task(current); + if (!css_tryget(&h_cg->css)) { + rcu_read_unlock(); + goto again; + } + rcu_read_unlock(); + + if (!page_counter_try_charge( + __hugetlb_cgroup_counter_from_cgroup(h_cg, idx, rsvd), + nr_pages, &counter)) { + ret = -ENOMEM; + hugetlb_event(h_cg, idx, HUGETLB_MAX); + css_put(&h_cg->css); + goto done; + } + /* Reservations take a reference to the css because they do not get + * reparented. + */ + if (!rsvd) + css_put(&h_cg->css); +done: + *ptr = h_cg; + return ret; +} + +int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, + struct hugetlb_cgroup **ptr) +{ + return __hugetlb_cgroup_charge_cgroup(idx, nr_pages, ptr, false); +} + +int hugetlb_cgroup_charge_cgroup_rsvd(int idx, unsigned long nr_pages, + struct hugetlb_cgroup **ptr) +{ + return __hugetlb_cgroup_charge_cgroup(idx, nr_pages, ptr, true); +} + +/* Should be called with hugetlb_lock held */ +static void __hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, + struct hugetlb_cgroup *h_cg, + struct page *page, bool rsvd) +{ + if (hugetlb_cgroup_disabled() || !h_cg) + return; + + __set_hugetlb_cgroup(page, h_cg, rsvd); + return; +} + +void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, + struct hugetlb_cgroup *h_cg, + struct page *page) +{ + __hugetlb_cgroup_commit_charge(idx, nr_pages, h_cg, page, false); +} + +void hugetlb_cgroup_commit_charge_rsvd(int idx, unsigned long nr_pages, + struct hugetlb_cgroup *h_cg, + struct page *page) +{ + __hugetlb_cgroup_commit_charge(idx, nr_pages, h_cg, page, true); +} + +/* + * Should be called with hugetlb_lock held + */ +static void __hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, + struct page *page, bool rsvd) +{ + struct hugetlb_cgroup *h_cg; + + if (hugetlb_cgroup_disabled()) + return; + lockdep_assert_held(&hugetlb_lock); + h_cg = __hugetlb_cgroup_from_page(page, rsvd); + if (unlikely(!h_cg)) + return; + __set_hugetlb_cgroup(page, NULL, rsvd); + + page_counter_uncharge(__hugetlb_cgroup_counter_from_cgroup(h_cg, idx, + rsvd), + nr_pages); + + if (rsvd) + css_put(&h_cg->css); + + return; +} + +void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, + struct page *page) +{ + __hugetlb_cgroup_uncharge_page(idx, nr_pages, page, false); +} + +void hugetlb_cgroup_uncharge_page_rsvd(int idx, unsigned long nr_pages, + struct page *page) +{ + __hugetlb_cgroup_uncharge_page(idx, nr_pages, page, true); +} + +static void __hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, + struct hugetlb_cgroup *h_cg, + bool rsvd) +{ + if (hugetlb_cgroup_disabled() || !h_cg) + return; + + if (huge_page_order(&hstates[idx]) < HUGETLB_CGROUP_MIN_ORDER) + return; + + page_counter_uncharge(__hugetlb_cgroup_counter_from_cgroup(h_cg, idx, + rsvd), + nr_pages); + + if (rsvd) + css_put(&h_cg->css); +} + +void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, + struct hugetlb_cgroup *h_cg) +{ + __hugetlb_cgroup_uncharge_cgroup(idx, nr_pages, h_cg, false); +} + +void hugetlb_cgroup_uncharge_cgroup_rsvd(int idx, unsigned long nr_pages, + struct hugetlb_cgroup *h_cg) +{ + __hugetlb_cgroup_uncharge_cgroup(idx, nr_pages, h_cg, true); +} + +void hugetlb_cgroup_uncharge_counter(struct resv_map *resv, unsigned long start, + unsigned long end) +{ + if (hugetlb_cgroup_disabled() || !resv || !resv->reservation_counter || + !resv->css) + return; + + page_counter_uncharge(resv->reservation_counter, + (end - start) * resv->pages_per_hpage); + css_put(resv->css); +} + +void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv, + struct file_region *rg, + unsigned long nr_pages, + bool region_del) +{ + if (hugetlb_cgroup_disabled() || !resv || !rg || !nr_pages) + return; + + if (rg->reservation_counter && resv->pages_per_hpage && nr_pages > 0 && + !resv->reservation_counter) { + page_counter_uncharge(rg->reservation_counter, + nr_pages * resv->pages_per_hpage); + /* + * Only do css_put(rg->css) when we delete the entire region + * because one file_region must hold exactly one css reference. + */ + if (region_del) + css_put(rg->css); + } +} + +enum { + RES_USAGE, + RES_RSVD_USAGE, + RES_LIMIT, + RES_RSVD_LIMIT, + RES_MAX_USAGE, + RES_RSVD_MAX_USAGE, + RES_FAILCNT, + RES_RSVD_FAILCNT, +}; + +static u64 hugetlb_cgroup_read_u64(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + struct page_counter *counter; + struct page_counter *rsvd_counter; + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css); + + counter = &h_cg->hugepage[MEMFILE_IDX(cft->private)]; + rsvd_counter = &h_cg->rsvd_hugepage[MEMFILE_IDX(cft->private)]; + + switch (MEMFILE_ATTR(cft->private)) { + case RES_USAGE: + return (u64)page_counter_read(counter) * PAGE_SIZE; + case RES_RSVD_USAGE: + return (u64)page_counter_read(rsvd_counter) * PAGE_SIZE; + case RES_LIMIT: + return (u64)counter->max * PAGE_SIZE; + case RES_RSVD_LIMIT: + return (u64)rsvd_counter->max * PAGE_SIZE; + case RES_MAX_USAGE: + return (u64)counter->watermark * PAGE_SIZE; + case RES_RSVD_MAX_USAGE: + return (u64)rsvd_counter->watermark * PAGE_SIZE; + case RES_FAILCNT: + return counter->failcnt; + case RES_RSVD_FAILCNT: + return rsvd_counter->failcnt; + default: + BUG(); + } +} + +static int hugetlb_cgroup_read_u64_max(struct seq_file *seq, void *v) +{ + int idx; + u64 val; + struct cftype *cft = seq_cft(seq); + unsigned long limit; + struct page_counter *counter; + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(seq_css(seq)); + + idx = MEMFILE_IDX(cft->private); + counter = &h_cg->hugepage[idx]; + + limit = round_down(PAGE_COUNTER_MAX, + 1 << huge_page_order(&hstates[idx])); + + switch (MEMFILE_ATTR(cft->private)) { + case RES_RSVD_USAGE: + counter = &h_cg->rsvd_hugepage[idx]; + fallthrough; + case RES_USAGE: + val = (u64)page_counter_read(counter); + seq_printf(seq, "%llu\n", val * PAGE_SIZE); + break; + case RES_RSVD_LIMIT: + counter = &h_cg->rsvd_hugepage[idx]; + fallthrough; + case RES_LIMIT: + val = (u64)counter->max; + if (val == limit) + seq_puts(seq, "max\n"); + else + seq_printf(seq, "%llu\n", val * PAGE_SIZE); + break; + default: + BUG(); + } + + return 0; +} + +static DEFINE_MUTEX(hugetlb_limit_mutex); + +static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off, + const char *max) +{ + int ret, idx; + unsigned long nr_pages; + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of)); + bool rsvd = false; + + if (hugetlb_cgroup_is_root(h_cg)) /* Can't set limit on root */ + return -EINVAL; + + buf = strstrip(buf); + ret = page_counter_memparse(buf, max, &nr_pages); + if (ret) + return ret; + + idx = MEMFILE_IDX(of_cft(of)->private); + nr_pages = round_down(nr_pages, 1 << huge_page_order(&hstates[idx])); + + switch (MEMFILE_ATTR(of_cft(of)->private)) { + case RES_RSVD_LIMIT: + rsvd = true; + fallthrough; + case RES_LIMIT: + mutex_lock(&hugetlb_limit_mutex); + ret = page_counter_set_max( + __hugetlb_cgroup_counter_from_cgroup(h_cg, idx, rsvd), + nr_pages); + mutex_unlock(&hugetlb_limit_mutex); + break; + default: + ret = -EINVAL; + break; + } + return ret ?: nbytes; +} + +static ssize_t hugetlb_cgroup_write_legacy(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + return hugetlb_cgroup_write(of, buf, nbytes, off, "-1"); +} + +static ssize_t hugetlb_cgroup_write_dfl(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + return hugetlb_cgroup_write(of, buf, nbytes, off, "max"); +} + +static ssize_t hugetlb_cgroup_reset(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + int ret = 0; + struct page_counter *counter, *rsvd_counter; + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of)); + + counter = &h_cg->hugepage[MEMFILE_IDX(of_cft(of)->private)]; + rsvd_counter = &h_cg->rsvd_hugepage[MEMFILE_IDX(of_cft(of)->private)]; + + switch (MEMFILE_ATTR(of_cft(of)->private)) { + case RES_MAX_USAGE: + page_counter_reset_watermark(counter); + break; + case RES_RSVD_MAX_USAGE: + page_counter_reset_watermark(rsvd_counter); + break; + case RES_FAILCNT: + counter->failcnt = 0; + break; + case RES_RSVD_FAILCNT: + rsvd_counter->failcnt = 0; + break; + default: + ret = -EINVAL; + break; + } + return ret ?: nbytes; +} + +static char *mem_fmt(char *buf, int size, unsigned long hsize) +{ + if (hsize >= (1UL << 30)) + snprintf(buf, size, "%luGB", hsize >> 30); + else if (hsize >= (1UL << 20)) + snprintf(buf, size, "%luMB", hsize >> 20); + else + snprintf(buf, size, "%luKB", hsize >> 10); + return buf; +} + +static int __hugetlb_events_show(struct seq_file *seq, bool local) +{ + int idx; + long max; + struct cftype *cft = seq_cft(seq); + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(seq_css(seq)); + + idx = MEMFILE_IDX(cft->private); + + if (local) + max = atomic_long_read(&h_cg->events_local[idx][HUGETLB_MAX]); + else + max = atomic_long_read(&h_cg->events[idx][HUGETLB_MAX]); + + seq_printf(seq, "max %lu\n", max); + + return 0; +} + +static int hugetlb_events_show(struct seq_file *seq, void *v) +{ + return __hugetlb_events_show(seq, false); +} + +static int hugetlb_events_local_show(struct seq_file *seq, void *v) +{ + return __hugetlb_events_show(seq, true); +} + +static void __init __hugetlb_cgroup_file_dfl_init(int idx) +{ + char buf[32]; + struct cftype *cft; + struct hstate *h = &hstates[idx]; + + /* format the size */ + mem_fmt(buf, sizeof(buf), huge_page_size(h)); + + /* Add the limit file */ + cft = &h->cgroup_files_dfl[0]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.max", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_LIMIT); + cft->seq_show = hugetlb_cgroup_read_u64_max; + cft->write = hugetlb_cgroup_write_dfl; + cft->flags = CFTYPE_NOT_ON_ROOT; + + /* Add the reservation limit file */ + cft = &h->cgroup_files_dfl[1]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.rsvd.max", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_RSVD_LIMIT); + cft->seq_show = hugetlb_cgroup_read_u64_max; + cft->write = hugetlb_cgroup_write_dfl; + cft->flags = CFTYPE_NOT_ON_ROOT; + + /* Add the current usage file */ + cft = &h->cgroup_files_dfl[2]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.current", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_USAGE); + cft->seq_show = hugetlb_cgroup_read_u64_max; + cft->flags = CFTYPE_NOT_ON_ROOT; + + /* Add the current reservation usage file */ + cft = &h->cgroup_files_dfl[3]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.rsvd.current", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_RSVD_USAGE); + cft->seq_show = hugetlb_cgroup_read_u64_max; + cft->flags = CFTYPE_NOT_ON_ROOT; + + /* Add the events file */ + cft = &h->cgroup_files_dfl[4]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.events", buf); + cft->private = MEMFILE_PRIVATE(idx, 0); + cft->seq_show = hugetlb_events_show; + cft->file_offset = offsetof(struct hugetlb_cgroup, events_file[idx]); + cft->flags = CFTYPE_NOT_ON_ROOT; + + /* Add the events.local file */ + cft = &h->cgroup_files_dfl[5]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.events.local", buf); + cft->private = MEMFILE_PRIVATE(idx, 0); + cft->seq_show = hugetlb_events_local_show; + cft->file_offset = offsetof(struct hugetlb_cgroup, + events_local_file[idx]); + cft->flags = CFTYPE_NOT_ON_ROOT; + + /* NULL terminate the last cft */ + cft = &h->cgroup_files_dfl[6]; + memset(cft, 0, sizeof(*cft)); + + WARN_ON(cgroup_add_dfl_cftypes(&hugetlb_cgrp_subsys, + h->cgroup_files_dfl)); +} + +static void __init __hugetlb_cgroup_file_legacy_init(int idx) +{ + char buf[32]; + struct cftype *cft; + struct hstate *h = &hstates[idx]; + + /* format the size */ + mem_fmt(buf, sizeof(buf), huge_page_size(h)); + + /* Add the limit file */ + cft = &h->cgroup_files_legacy[0]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.limit_in_bytes", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_LIMIT); + cft->read_u64 = hugetlb_cgroup_read_u64; + cft->write = hugetlb_cgroup_write_legacy; + + /* Add the reservation limit file */ + cft = &h->cgroup_files_legacy[1]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.rsvd.limit_in_bytes", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_RSVD_LIMIT); + cft->read_u64 = hugetlb_cgroup_read_u64; + cft->write = hugetlb_cgroup_write_legacy; + + /* Add the usage file */ + cft = &h->cgroup_files_legacy[2]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.usage_in_bytes", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_USAGE); + cft->read_u64 = hugetlb_cgroup_read_u64; + + /* Add the reservation usage file */ + cft = &h->cgroup_files_legacy[3]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.rsvd.usage_in_bytes", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_RSVD_USAGE); + cft->read_u64 = hugetlb_cgroup_read_u64; + + /* Add the MAX usage file */ + cft = &h->cgroup_files_legacy[4]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.max_usage_in_bytes", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_MAX_USAGE); + cft->write = hugetlb_cgroup_reset; + cft->read_u64 = hugetlb_cgroup_read_u64; + + /* Add the MAX reservation usage file */ + cft = &h->cgroup_files_legacy[5]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.rsvd.max_usage_in_bytes", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_RSVD_MAX_USAGE); + cft->write = hugetlb_cgroup_reset; + cft->read_u64 = hugetlb_cgroup_read_u64; + + /* Add the failcntfile */ + cft = &h->cgroup_files_legacy[6]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.failcnt", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_FAILCNT); + cft->write = hugetlb_cgroup_reset; + cft->read_u64 = hugetlb_cgroup_read_u64; + + /* Add the reservation failcntfile */ + cft = &h->cgroup_files_legacy[7]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.rsvd.failcnt", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_RSVD_FAILCNT); + cft->write = hugetlb_cgroup_reset; + cft->read_u64 = hugetlb_cgroup_read_u64; + + /* NULL terminate the last cft */ + cft = &h->cgroup_files_legacy[8]; + memset(cft, 0, sizeof(*cft)); + + WARN_ON(cgroup_add_legacy_cftypes(&hugetlb_cgrp_subsys, + h->cgroup_files_legacy)); +} + +static void __init __hugetlb_cgroup_file_init(int idx) +{ + __hugetlb_cgroup_file_dfl_init(idx); + __hugetlb_cgroup_file_legacy_init(idx); +} + +void __init hugetlb_cgroup_file_init(void) +{ + struct hstate *h; + + for_each_hstate(h) { + /* + * Add cgroup control files only if the huge page consists + * of more than two normal pages. This is because we use + * page[2].private for storing cgroup details. + */ + if (huge_page_order(h) >= HUGETLB_CGROUP_MIN_ORDER) + __hugetlb_cgroup_file_init(hstate_index(h)); + } +} + +/* + * hugetlb_lock will make sure a parallel cgroup rmdir won't happen + * when we migrate hugepages + */ +void hugetlb_cgroup_migrate(struct page *oldhpage, struct page *newhpage) +{ + struct hugetlb_cgroup *h_cg; + struct hugetlb_cgroup *h_cg_rsvd; + struct hstate *h = page_hstate(oldhpage); + + if (hugetlb_cgroup_disabled()) + return; + + VM_BUG_ON_PAGE(!PageHuge(oldhpage), oldhpage); + spin_lock(&hugetlb_lock); + h_cg = hugetlb_cgroup_from_page(oldhpage); + h_cg_rsvd = hugetlb_cgroup_from_page_rsvd(oldhpage); + set_hugetlb_cgroup(oldhpage, NULL); + set_hugetlb_cgroup_rsvd(oldhpage, NULL); + + /* move the h_cg details to new cgroup */ + set_hugetlb_cgroup(newhpage, h_cg); + set_hugetlb_cgroup_rsvd(newhpage, h_cg_rsvd); + list_move(&newhpage->lru, &h->hugepage_activelist); + spin_unlock(&hugetlb_lock); + return; +} + +static struct cftype hugetlb_files[] = { + {} /* terminate */ +}; + +struct cgroup_subsys hugetlb_cgrp_subsys = { + .css_alloc = hugetlb_cgroup_css_alloc, + .css_offline = hugetlb_cgroup_css_offline, + .css_free = hugetlb_cgroup_css_free, + .dfl_cftypes = hugetlb_files, + .legacy_cftypes = hugetlb_files, +}; diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c new file mode 100644 index 000000000..1ae1ebc2b --- /dev/null +++ b/mm/hwpoison-inject.c @@ -0,0 +1,110 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Inject a hwpoison memory failure on a arbitrary pfn */ +#include +#include +#include +#include +#include +#include +#include +#include "internal.h" + +static struct dentry *hwpoison_dir; + +static int hwpoison_inject(void *data, u64 val) +{ + unsigned long pfn = val; + struct page *p; + struct page *hpage; + int err; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (!pfn_valid(pfn)) + return -ENXIO; + + p = pfn_to_page(pfn); + hpage = compound_head(p); + + if (!hwpoison_filter_enable) + goto inject; + + shake_page(hpage, 0); + /* + * This implies unable to support non-LRU pages. + */ + if (!PageLRU(hpage) && !PageHuge(p)) + return 0; + + /* + * do a racy check to make sure PG_hwpoison will only be set for + * the targeted owner (or on a free page). + * memory_failure() will redo the check reliably inside page lock. + */ + err = hwpoison_filter(hpage); + if (err) + return 0; + +inject: + pr_info("Injecting memory failure at pfn %#lx\n", pfn); + return memory_failure(pfn, 0); +} + +static int hwpoison_unpoison(void *data, u64 val) +{ + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + return unpoison_memory(val); +} + +DEFINE_DEBUGFS_ATTRIBUTE(hwpoison_fops, NULL, hwpoison_inject, "%lli\n"); +DEFINE_DEBUGFS_ATTRIBUTE(unpoison_fops, NULL, hwpoison_unpoison, "%lli\n"); + +static void pfn_inject_exit(void) +{ + debugfs_remove_recursive(hwpoison_dir); +} + +static int pfn_inject_init(void) +{ + hwpoison_dir = debugfs_create_dir("hwpoison", NULL); + + /* + * Note that the below poison/unpoison interfaces do not involve + * hardware status change, hence do not require hardware support. + * They are mainly for testing hwpoison in software level. + */ + debugfs_create_file("corrupt-pfn", 0200, hwpoison_dir, NULL, + &hwpoison_fops); + + debugfs_create_file("unpoison-pfn", 0200, hwpoison_dir, NULL, + &unpoison_fops); + + debugfs_create_u32("corrupt-filter-enable", 0600, hwpoison_dir, + &hwpoison_filter_enable); + + debugfs_create_u32("corrupt-filter-dev-major", 0600, hwpoison_dir, + &hwpoison_filter_dev_major); + + debugfs_create_u32("corrupt-filter-dev-minor", 0600, hwpoison_dir, + &hwpoison_filter_dev_minor); + + debugfs_create_u64("corrupt-filter-flags-mask", 0600, hwpoison_dir, + &hwpoison_filter_flags_mask); + + debugfs_create_u64("corrupt-filter-flags-value", 0600, hwpoison_dir, + &hwpoison_filter_flags_value); + +#ifdef CONFIG_MEMCG + debugfs_create_u64("corrupt-filter-memcg", 0600, hwpoison_dir, + &hwpoison_filter_memcg); +#endif + + return 0; +} + +module_init(pfn_inject_init); +module_exit(pfn_inject_exit); +MODULE_LICENSE("GPL"); diff --git a/mm/init-mm.c b/mm/init-mm.c new file mode 100644 index 000000000..153162669 --- /dev/null +++ b/mm/init-mm.c @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +#ifndef INIT_MM_CONTEXT +#define INIT_MM_CONTEXT(name) +#endif + +/* + * For dynamically allocated mm_structs, there is a dynamically sized cpumask + * at the end of the structure, the size of which depends on the maximum CPU + * number the system can see. That way we allocate only as much memory for + * mm_cpumask() as needed for the hundreds, or thousands of processes that + * a system typically runs. + * + * Since there is only one init_mm in the entire system, keep it simple + * and size this cpu_bitmask to NR_CPUS. + */ +struct mm_struct init_mm = { + .mm_rb = RB_ROOT, + .pgd = swapper_pg_dir, + .mm_users = ATOMIC_INIT(2), + .mm_count = ATOMIC_INIT(1), + .write_protect_seq = SEQCNT_ZERO(init_mm.write_protect_seq), + MMAP_LOCK_INITIALIZER(init_mm) + .page_table_lock = __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock), + .arg_lock = __SPIN_LOCK_UNLOCKED(init_mm.arg_lock), + .mmlist = LIST_HEAD_INIT(init_mm.mmlist), + .user_ns = &init_user_ns, + .cpu_bitmap = CPU_BITS_NONE, + INIT_MM_CONTEXT(init_mm) +}; diff --git a/mm/internal.h b/mm/internal.h new file mode 100644 index 000000000..840b8a330 --- /dev/null +++ b/mm/internal.h @@ -0,0 +1,646 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* internal.h: mm/ internal definitions + * + * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ +#ifndef __MM_INTERNAL_H +#define __MM_INTERNAL_H + +#include +#include +#include +#include + +/* + * The set of flags that only affect watermark checking and reclaim + * behaviour. This is used by the MM to obey the caller constraints + * about IO, FS and watermark checking while ignoring placement + * hints such as HIGHMEM usage. + */ +#define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\ + __GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_NOFAIL|\ + __GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\ + __GFP_ATOMIC) + +/* The GFP flags allowed during early boot */ +#define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS)) + +/* Control allocation cpuset and node placement constraints */ +#define GFP_CONSTRAINT_MASK (__GFP_HARDWALL|__GFP_THISNODE) + +/* Do not use these with a slab allocator */ +#define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK) + +void page_writeback_init(void); + +vm_fault_t do_swap_page(struct vm_fault *vmf); + +void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, + unsigned long floor, unsigned long ceiling); + +static inline bool can_madv_lru_vma(struct vm_area_struct *vma) +{ + return !(vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP)); +} + +void unmap_page_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, + unsigned long addr, unsigned long end, + struct zap_details *details); + +void do_page_cache_ra(struct readahead_control *, unsigned long nr_to_read, + unsigned long lookahead_size); +void force_page_cache_ra(struct readahead_control *, struct file_ra_state *, + unsigned long nr); +static inline void force_page_cache_readahead(struct address_space *mapping, + struct file *file, pgoff_t index, unsigned long nr_to_read) +{ + DEFINE_READAHEAD(ractl, file, mapping, index); + force_page_cache_ra(&ractl, &file->f_ra, nr_to_read); +} + +struct page *find_get_entry(struct address_space *mapping, pgoff_t index); +struct page *find_lock_entry(struct address_space *mapping, pgoff_t index); + +/** + * page_evictable - test whether a page is evictable + * @page: the page to test + * + * Test whether page is evictable--i.e., should be placed on active/inactive + * lists vs unevictable list. + * + * Reasons page might not be evictable: + * (1) page's mapping marked unevictable + * (2) page is part of an mlocked VMA + * + */ +static inline bool page_evictable(struct page *page) +{ + bool ret; + + /* Prevent address_space of inode and swap cache from being freed */ + rcu_read_lock(); + ret = !mapping_unevictable(page_mapping(page)) && !PageMlocked(page); + rcu_read_unlock(); + return ret; +} + +/* + * Turn a non-refcounted page (->_refcount == 0) into refcounted with + * a count of one. + */ +static inline void set_page_refcounted(struct page *page) +{ + VM_BUG_ON_PAGE(PageTail(page), page); + VM_BUG_ON_PAGE(page_ref_count(page), page); + set_page_count(page, 1); +} + +extern unsigned long highest_memmap_pfn; + +/* + * Maximum number of reclaim retries without progress before the OOM + * killer is consider the only way forward. + */ +#define MAX_RECLAIM_RETRIES 16 + +/* + * in mm/vmscan.c: + */ +extern int isolate_lru_page(struct page *page); +extern void putback_lru_page(struct page *page); + +/* + * in mm/rmap.c: + */ +extern pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address); + +/* + * in mm/page_alloc.c + */ + +/* + * Structure for holding the mostly immutable allocation parameters passed + * between functions involved in allocations, including the alloc_pages* + * family of functions. + * + * nodemask, migratetype and highest_zoneidx are initialized only once in + * __alloc_pages_nodemask() and then never change. + * + * zonelist, preferred_zone and highest_zoneidx are set first in + * __alloc_pages_nodemask() for the fast path, and might be later changed + * in __alloc_pages_slowpath(). All other functions pass the whole structure + * by a const pointer. + */ +struct alloc_context { + struct zonelist *zonelist; + nodemask_t *nodemask; + struct zoneref *preferred_zoneref; + int migratetype; + + /* + * highest_zoneidx represents highest usable zone index of + * the allocation request. Due to the nature of the zone, + * memory on lower zone than the highest_zoneidx will be + * protected by lowmem_reserve[highest_zoneidx]. + * + * highest_zoneidx is also used by reclaim/compaction to limit + * the target zone since higher zone than this index cannot be + * usable for this allocation request. + */ + enum zone_type highest_zoneidx; + bool spread_dirty_pages; +}; + +/* + * Locate the struct page for both the matching buddy in our + * pair (buddy1) and the combined O(n+1) page they form (page). + * + * 1) Any buddy B1 will have an order O twin B2 which satisfies + * the following equation: + * B2 = B1 ^ (1 << O) + * For example, if the starting buddy (buddy2) is #8 its order + * 1 buddy is #10: + * B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10 + * + * 2) Any buddy B will have an order O+1 parent P which + * satisfies the following equation: + * P = B & ~(1 << O) + * + * Assumption: *_mem_map is contiguous at least up to MAX_ORDER + */ +static inline unsigned long +__find_buddy_pfn(unsigned long page_pfn, unsigned int order) +{ + return page_pfn ^ (1 << order); +} + +extern struct page *__pageblock_pfn_to_page(unsigned long start_pfn, + unsigned long end_pfn, struct zone *zone); + +static inline struct page *pageblock_pfn_to_page(unsigned long start_pfn, + unsigned long end_pfn, struct zone *zone) +{ + if (zone->contiguous) + return pfn_to_page(start_pfn); + + return __pageblock_pfn_to_page(start_pfn, end_pfn, zone); +} + +extern int __isolate_free_page(struct page *page, unsigned int order); +extern void __putback_isolated_page(struct page *page, unsigned int order, + int mt); +extern void memblock_free_pages(struct page *page, unsigned long pfn, + unsigned int order); +extern void __free_pages_core(struct page *page, unsigned int order); +extern void prep_compound_page(struct page *page, unsigned int order); +extern void post_alloc_hook(struct page *page, unsigned int order, + gfp_t gfp_flags); +extern int user_min_free_kbytes; + +extern void zone_pcp_update(struct zone *zone); +extern void zone_pcp_reset(struct zone *zone); + +#if defined CONFIG_COMPACTION || defined CONFIG_CMA + +/* + * in mm/compaction.c + */ +/* + * compact_control is used to track pages being migrated and the free pages + * they are being migrated to during memory compaction. The free_pfn starts + * at the end of a zone and migrate_pfn begins at the start. Movable pages + * are moved to the end of a zone during a compaction run and the run + * completes when free_pfn <= migrate_pfn + */ +struct compact_control { + struct list_head freepages; /* List of free pages to migrate to */ + struct list_head migratepages; /* List of pages being migrated */ + unsigned int nr_freepages; /* Number of isolated free pages */ + unsigned int nr_migratepages; /* Number of pages to migrate */ + unsigned long free_pfn; /* isolate_freepages search base */ + unsigned long migrate_pfn; /* isolate_migratepages search base */ + unsigned long fast_start_pfn; /* a pfn to start linear scan from */ + struct zone *zone; + unsigned long total_migrate_scanned; + unsigned long total_free_scanned; + unsigned short fast_search_fail;/* failures to use free list searches */ + short search_order; /* order to start a fast search at */ + const gfp_t gfp_mask; /* gfp mask of a direct compactor */ + int order; /* order a direct compactor needs */ + int migratetype; /* migratetype of direct compactor */ + const unsigned int alloc_flags; /* alloc flags of a direct compactor */ + const int highest_zoneidx; /* zone index of a direct compactor */ + enum migrate_mode mode; /* Async or sync migration mode */ + bool ignore_skip_hint; /* Scan blocks even if marked skip */ + bool no_set_skip_hint; /* Don't mark blocks for skipping */ + bool ignore_block_suitable; /* Scan blocks considered unsuitable */ + bool direct_compaction; /* False from kcompactd or /proc/... */ + bool proactive_compaction; /* kcompactd proactive compaction */ + bool whole_zone; /* Whole zone should/has been scanned */ + bool contended; /* Signal lock or sched contention */ + bool rescan; /* Rescanning the same pageblock */ + bool alloc_contig; /* alloc_contig_range allocation */ +}; + +/* + * Used in direct compaction when a page should be taken from the freelists + * immediately when one is created during the free path. + */ +struct capture_control { + struct compact_control *cc; + struct page *page; +}; + +unsigned long +isolate_freepages_range(struct compact_control *cc, + unsigned long start_pfn, unsigned long end_pfn); +unsigned long +isolate_migratepages_range(struct compact_control *cc, + unsigned long low_pfn, unsigned long end_pfn); +int find_suitable_fallback(struct free_area *area, unsigned int order, + int migratetype, bool only_stealable, bool *can_steal); + +#endif + +/* + * This function returns the order of a free page in the buddy system. In + * general, page_zone(page)->lock must be held by the caller to prevent the + * page from being allocated in parallel and returning garbage as the order. + * If a caller does not hold page_zone(page)->lock, it must guarantee that the + * page cannot be allocated or merged in parallel. Alternatively, it must + * handle invalid values gracefully, and use buddy_order_unsafe() below. + */ +static inline unsigned int buddy_order(struct page *page) +{ + /* PageBuddy() must be checked by the caller */ + return page_private(page); +} + +/* + * Like buddy_order(), but for callers who cannot afford to hold the zone lock. + * PageBuddy() should be checked first by the caller to minimize race window, + * and invalid values must be handled gracefully. + * + * READ_ONCE is used so that if the caller assigns the result into a local + * variable and e.g. tests it for valid range before using, the compiler cannot + * decide to remove the variable and inline the page_private(page) multiple + * times, potentially observing different values in the tests and the actual + * use of the result. + */ +#define buddy_order_unsafe(page) READ_ONCE(page_private(page)) + +static inline bool is_cow_mapping(vm_flags_t flags) +{ + return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; +} + +/* + * These three helpers classifies VMAs for virtual memory accounting. + */ + +/* + * Executable code area - executable, not writable, not stack + */ +static inline bool is_exec_mapping(vm_flags_t flags) +{ + return (flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC; +} + +/* + * Stack area - atomatically grows in one direction + * + * VM_GROWSUP / VM_GROWSDOWN VMAs are always private anonymous: + * do_mmap() forbids all other combinations. + */ +static inline bool is_stack_mapping(vm_flags_t flags) +{ + return (flags & VM_STACK) == VM_STACK; +} + +/* + * Data area - private, writable, not stack + */ +static inline bool is_data_mapping(vm_flags_t flags) +{ + return (flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE; +} + +/* mm/util.c */ +void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma, + struct vm_area_struct *prev); +void __vma_unlink_list(struct mm_struct *mm, struct vm_area_struct *vma); + +#ifdef CONFIG_MMU +extern long populate_vma_page_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end, int *nonblocking); +extern void munlock_vma_pages_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end); +static inline void munlock_vma_pages_all(struct vm_area_struct *vma) +{ + munlock_vma_pages_range(vma, vma->vm_start, vma->vm_end); +} + +/* + * must be called with vma's mmap_lock held for read or write, and page locked. + */ +extern void mlock_vma_page(struct page *page); +extern unsigned int munlock_vma_page(struct page *page); + +/* + * Clear the page's PageMlocked(). This can be useful in a situation where + * we want to unconditionally remove a page from the pagecache -- e.g., + * on truncation or freeing. + * + * It is legal to call this function for any page, mlocked or not. + * If called for a page that is still mapped by mlocked vmas, all we do + * is revert to lazy LRU behaviour -- semantics are not broken. + */ +extern void clear_page_mlock(struct page *page); + +/* + * mlock_migrate_page - called only from migrate_misplaced_transhuge_page() + * (because that does not go through the full procedure of migration ptes): + * to migrate the Mlocked page flag; update statistics. + */ +static inline void mlock_migrate_page(struct page *newpage, struct page *page) +{ + if (TestClearPageMlocked(page)) { + int nr_pages = thp_nr_pages(page); + + /* Holding pmd lock, no change in irq context: __mod is safe */ + __mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages); + SetPageMlocked(newpage); + __mod_zone_page_state(page_zone(newpage), NR_MLOCK, nr_pages); + } +} + +extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); + +/* + * At what user virtual address is page expected in vma? + * Returns -EFAULT if all of the page is outside the range of vma. + * If page is a compound head, the entire compound page is considered. + */ +static inline unsigned long +vma_address(struct page *page, struct vm_area_struct *vma) +{ + pgoff_t pgoff; + unsigned long address; + + VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */ + pgoff = page_to_pgoff(page); + if (pgoff >= vma->vm_pgoff) { + address = vma->vm_start + + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); + /* Check for address beyond vma (or wrapped through 0?) */ + if (address < vma->vm_start || address >= vma->vm_end) + address = -EFAULT; + } else if (PageHead(page) && + pgoff + compound_nr(page) - 1 >= vma->vm_pgoff) { + /* Test above avoids possibility of wrap to 0 on 32-bit */ + address = vma->vm_start; + } else { + address = -EFAULT; + } + return address; +} + +/* + * Then at what user virtual address will none of the page be found in vma? + * Assumes that vma_address() already returned a good starting address. + * If page is a compound head, the entire compound page is considered. + */ +static inline unsigned long +vma_address_end(struct page *page, struct vm_area_struct *vma) +{ + pgoff_t pgoff; + unsigned long address; + + VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */ + pgoff = page_to_pgoff(page) + compound_nr(page); + address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); + /* Check for address beyond vma (or wrapped through 0?) */ + if (address < vma->vm_start || address > vma->vm_end) + address = vma->vm_end; + return address; +} + +static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf, + struct file *fpin) +{ + int flags = vmf->flags; + + if (fpin) + return fpin; + + /* + * FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or + * anything, so we only pin the file and drop the mmap_lock if only + * FAULT_FLAG_ALLOW_RETRY is set, while this is the first attempt. + */ + if (fault_flag_allow_retry_first(flags) && + !(flags & FAULT_FLAG_RETRY_NOWAIT)) { + fpin = get_file(vmf->vma->vm_file); + mmap_read_unlock(vmf->vma->vm_mm); + } + return fpin; +} + +#else /* !CONFIG_MMU */ +static inline void clear_page_mlock(struct page *page) { } +static inline void mlock_vma_page(struct page *page) { } +static inline void mlock_migrate_page(struct page *new, struct page *old) { } + +#endif /* !CONFIG_MMU */ + +/* + * Return the mem_map entry representing the 'offset' subpage within + * the maximally aligned gigantic page 'base'. Handle any discontiguity + * in the mem_map at MAX_ORDER_NR_PAGES boundaries. + */ +static inline struct page *mem_map_offset(struct page *base, int offset) +{ + if (unlikely(offset >= MAX_ORDER_NR_PAGES)) + return nth_page(base, offset); + return base + offset; +} + +/* + * Iterator over all subpages within the maximally aligned gigantic + * page 'base'. Handle any discontiguity in the mem_map. + */ +static inline struct page *mem_map_next(struct page *iter, + struct page *base, int offset) +{ + if (unlikely((offset & (MAX_ORDER_NR_PAGES - 1)) == 0)) { + unsigned long pfn = page_to_pfn(base) + offset; + if (!pfn_valid(pfn)) + return NULL; + return pfn_to_page(pfn); + } + return iter + 1; +} + +/* Memory initialisation debug and verification */ +enum mminit_level { + MMINIT_WARNING, + MMINIT_VERIFY, + MMINIT_TRACE +}; + +#ifdef CONFIG_DEBUG_MEMORY_INIT + +extern int mminit_loglevel; + +#define mminit_dprintk(level, prefix, fmt, arg...) \ +do { \ + if (level < mminit_loglevel) { \ + if (level <= MMINIT_WARNING) \ + pr_warn("mminit::" prefix " " fmt, ##arg); \ + else \ + printk(KERN_DEBUG "mminit::" prefix " " fmt, ##arg); \ + } \ +} while (0) + +extern void mminit_verify_pageflags_layout(void); +extern void mminit_verify_zonelist(void); +#else + +static inline void mminit_dprintk(enum mminit_level level, + const char *prefix, const char *fmt, ...) +{ +} + +static inline void mminit_verify_pageflags_layout(void) +{ +} + +static inline void mminit_verify_zonelist(void) +{ +} +#endif /* CONFIG_DEBUG_MEMORY_INIT */ + +/* mminit_validate_memmodel_limits is independent of CONFIG_DEBUG_MEMORY_INIT */ +#if defined(CONFIG_SPARSEMEM) +extern void mminit_validate_memmodel_limits(unsigned long *start_pfn, + unsigned long *end_pfn); +#else +static inline void mminit_validate_memmodel_limits(unsigned long *start_pfn, + unsigned long *end_pfn) +{ +} +#endif /* CONFIG_SPARSEMEM */ + +#define NODE_RECLAIM_NOSCAN -2 +#define NODE_RECLAIM_FULL -1 +#define NODE_RECLAIM_SOME 0 +#define NODE_RECLAIM_SUCCESS 1 + +#ifdef CONFIG_NUMA +extern int node_reclaim(struct pglist_data *, gfp_t, unsigned int); +#else +static inline int node_reclaim(struct pglist_data *pgdat, gfp_t mask, + unsigned int order) +{ + return NODE_RECLAIM_NOSCAN; +} +#endif + +extern int hwpoison_filter(struct page *p); + +extern u32 hwpoison_filter_dev_major; +extern u32 hwpoison_filter_dev_minor; +extern u64 hwpoison_filter_flags_mask; +extern u64 hwpoison_filter_flags_value; +extern u64 hwpoison_filter_memcg; +extern u32 hwpoison_filter_enable; + +extern unsigned long __must_check vm_mmap_pgoff(struct file *, unsigned long, + unsigned long, unsigned long, + unsigned long, unsigned long); + +extern void set_pageblock_order(void); +unsigned int reclaim_clean_pages_from_list(struct zone *zone, + struct list_head *page_list); +/* The ALLOC_WMARK bits are used as an index to zone->watermark */ +#define ALLOC_WMARK_MIN WMARK_MIN +#define ALLOC_WMARK_LOW WMARK_LOW +#define ALLOC_WMARK_HIGH WMARK_HIGH +#define ALLOC_NO_WATERMARKS 0x04 /* don't check watermarks at all */ + +/* Mask to get the watermark bits */ +#define ALLOC_WMARK_MASK (ALLOC_NO_WATERMARKS-1) + +/* + * Only MMU archs have async oom victim reclaim - aka oom_reaper so we + * cannot assume a reduced access to memory reserves is sufficient for + * !MMU + */ +#ifdef CONFIG_MMU +#define ALLOC_OOM 0x08 +#else +#define ALLOC_OOM ALLOC_NO_WATERMARKS +#endif + +#define ALLOC_HARDER 0x10 /* try to alloc harder */ +#define ALLOC_HIGH 0x20 /* __GFP_HIGH set */ +#define ALLOC_CPUSET 0x40 /* check for correct cpuset */ +#define ALLOC_CMA 0x80 /* allow allocations from CMA areas */ +#ifdef CONFIG_ZONE_DMA32 +#define ALLOC_NOFRAGMENT 0x100 /* avoid mixing pageblock types */ +#else +#define ALLOC_NOFRAGMENT 0x0 +#endif +#define ALLOC_KSWAPD 0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */ + +enum ttu_flags; +struct tlbflush_unmap_batch; + + +/* + * only for MM internal work items which do not depend on + * any allocations or locks which might depend on allocations + */ +extern struct workqueue_struct *mm_percpu_wq; + +#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH +void try_to_unmap_flush(void); +void try_to_unmap_flush_dirty(void); +void flush_tlb_batched_pending(struct mm_struct *mm); +#else +static inline void try_to_unmap_flush(void) +{ +} +static inline void try_to_unmap_flush_dirty(void) +{ +} +static inline void flush_tlb_batched_pending(struct mm_struct *mm) +{ +} +#endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ + +extern const struct trace_print_flags pageflag_names[]; +extern const struct trace_print_flags vmaflag_names[]; +extern const struct trace_print_flags gfpflag_names[]; + +static inline bool is_migrate_highatomic(enum migratetype migratetype) +{ + return migratetype == MIGRATE_HIGHATOMIC; +} + +static inline bool is_migrate_highatomic_page(struct page *page) +{ + return get_pageblock_migratetype(page) == MIGRATE_HIGHATOMIC; +} + +void setup_zone_pageset(struct zone *zone); + +struct migration_target_control { + int nid; /* preferred node id */ + nodemask_t *nmask; + gfp_t gfp_mask; +}; + +#endif /* __MM_INTERNAL_H */ diff --git a/mm/interval_tree.c b/mm/interval_tree.c new file mode 100644 index 000000000..11c75fb07 --- /dev/null +++ b/mm/interval_tree.c @@ -0,0 +1,111 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * mm/interval_tree.c - interval tree for mapping->i_mmap + * + * Copyright (C) 2012, Michel Lespinasse + */ + +#include +#include +#include +#include + +static inline unsigned long vma_start_pgoff(struct vm_area_struct *v) +{ + return v->vm_pgoff; +} + +static inline unsigned long vma_last_pgoff(struct vm_area_struct *v) +{ + return v->vm_pgoff + vma_pages(v) - 1; +} + +INTERVAL_TREE_DEFINE(struct vm_area_struct, shared.rb, + unsigned long, shared.rb_subtree_last, + vma_start_pgoff, vma_last_pgoff,, vma_interval_tree) + +/* Insert node immediately after prev in the interval tree */ +void vma_interval_tree_insert_after(struct vm_area_struct *node, + struct vm_area_struct *prev, + struct rb_root_cached *root) +{ + struct rb_node **link; + struct vm_area_struct *parent; + unsigned long last = vma_last_pgoff(node); + + VM_BUG_ON_VMA(vma_start_pgoff(node) != vma_start_pgoff(prev), node); + + if (!prev->shared.rb.rb_right) { + parent = prev; + link = &prev->shared.rb.rb_right; + } else { + parent = rb_entry(prev->shared.rb.rb_right, + struct vm_area_struct, shared.rb); + if (parent->shared.rb_subtree_last < last) + parent->shared.rb_subtree_last = last; + while (parent->shared.rb.rb_left) { + parent = rb_entry(parent->shared.rb.rb_left, + struct vm_area_struct, shared.rb); + if (parent->shared.rb_subtree_last < last) + parent->shared.rb_subtree_last = last; + } + link = &parent->shared.rb.rb_left; + } + + node->shared.rb_subtree_last = last; + rb_link_node(&node->shared.rb, &parent->shared.rb, link); + rb_insert_augmented(&node->shared.rb, &root->rb_root, + &vma_interval_tree_augment); +} + +static inline unsigned long avc_start_pgoff(struct anon_vma_chain *avc) +{ + return vma_start_pgoff(avc->vma); +} + +static inline unsigned long avc_last_pgoff(struct anon_vma_chain *avc) +{ + return vma_last_pgoff(avc->vma); +} + +INTERVAL_TREE_DEFINE(struct anon_vma_chain, rb, unsigned long, rb_subtree_last, + avc_start_pgoff, avc_last_pgoff, + static inline, __anon_vma_interval_tree) + +void anon_vma_interval_tree_insert(struct anon_vma_chain *node, + struct rb_root_cached *root) +{ +#ifdef CONFIG_DEBUG_VM_RB + node->cached_vma_start = avc_start_pgoff(node); + node->cached_vma_last = avc_last_pgoff(node); +#endif + __anon_vma_interval_tree_insert(node, root); +} + +void anon_vma_interval_tree_remove(struct anon_vma_chain *node, + struct rb_root_cached *root) +{ + __anon_vma_interval_tree_remove(node, root); +} + +struct anon_vma_chain * +anon_vma_interval_tree_iter_first(struct rb_root_cached *root, + unsigned long first, unsigned long last) +{ + return __anon_vma_interval_tree_iter_first(root, first, last); +} + +struct anon_vma_chain * +anon_vma_interval_tree_iter_next(struct anon_vma_chain *node, + unsigned long first, unsigned long last) +{ + return __anon_vma_interval_tree_iter_next(node, first, last); +} + +#ifdef CONFIG_DEBUG_VM_RB +void anon_vma_interval_tree_verify(struct anon_vma_chain *node) +{ + WARN_ON_ONCE(node->cached_vma_start != avc_start_pgoff(node)); + WARN_ON_ONCE(node->cached_vma_last != avc_last_pgoff(node)); +} +#endif diff --git a/mm/ioremap.c b/mm/ioremap.c new file mode 100644 index 000000000..5fa1ab41d --- /dev/null +++ b/mm/ioremap.c @@ -0,0 +1,289 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Re-map IO memory to kernel address space so that we can access it. + * This is needed for high PCI addresses that aren't mapped in the + * 640k-1MB IO memory area on PC's + * + * (C) Copyright 1995 1996 Linus Torvalds + */ +#include +#include +#include +#include +#include +#include + +#include "pgalloc-track.h" + +#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP +static int __read_mostly ioremap_p4d_capable; +static int __read_mostly ioremap_pud_capable; +static int __read_mostly ioremap_pmd_capable; +static int __read_mostly ioremap_huge_disabled; + +static int __init set_nohugeiomap(char *str) +{ + ioremap_huge_disabled = 1; + return 0; +} +early_param("nohugeiomap", set_nohugeiomap); + +void __init ioremap_huge_init(void) +{ + if (!ioremap_huge_disabled) { + if (arch_ioremap_p4d_supported()) + ioremap_p4d_capable = 1; + if (arch_ioremap_pud_supported()) + ioremap_pud_capable = 1; + if (arch_ioremap_pmd_supported()) + ioremap_pmd_capable = 1; + } +} + +static inline int ioremap_p4d_enabled(void) +{ + return ioremap_p4d_capable; +} + +static inline int ioremap_pud_enabled(void) +{ + return ioremap_pud_capable; +} + +static inline int ioremap_pmd_enabled(void) +{ + return ioremap_pmd_capable; +} + +#else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */ +static inline int ioremap_p4d_enabled(void) { return 0; } +static inline int ioremap_pud_enabled(void) { return 0; } +static inline int ioremap_pmd_enabled(void) { return 0; } +#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ + +static int ioremap_pte_range(pmd_t *pmd, unsigned long addr, + unsigned long end, phys_addr_t phys_addr, pgprot_t prot, + pgtbl_mod_mask *mask) +{ + pte_t *pte; + u64 pfn; + + pfn = phys_addr >> PAGE_SHIFT; + pte = pte_alloc_kernel_track(pmd, addr, mask); + if (!pte) + return -ENOMEM; + do { + BUG_ON(!pte_none(*pte)); + set_pte_at(&init_mm, addr, pte, pfn_pte(pfn, prot)); + pfn++; + } while (pte++, addr += PAGE_SIZE, addr != end); + *mask |= PGTBL_PTE_MODIFIED; + return 0; +} + +static int ioremap_try_huge_pmd(pmd_t *pmd, unsigned long addr, + unsigned long end, phys_addr_t phys_addr, + pgprot_t prot) +{ + if (!ioremap_pmd_enabled()) + return 0; + + if ((end - addr) != PMD_SIZE) + return 0; + + if (!IS_ALIGNED(addr, PMD_SIZE)) + return 0; + + if (!IS_ALIGNED(phys_addr, PMD_SIZE)) + return 0; + + if (pmd_present(*pmd) && !pmd_free_pte_page(pmd, addr)) + return 0; + + return pmd_set_huge(pmd, phys_addr, prot); +} + +static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr, + unsigned long end, phys_addr_t phys_addr, pgprot_t prot, + pgtbl_mod_mask *mask) +{ + pmd_t *pmd; + unsigned long next; + + pmd = pmd_alloc_track(&init_mm, pud, addr, mask); + if (!pmd) + return -ENOMEM; + do { + next = pmd_addr_end(addr, end); + + if (ioremap_try_huge_pmd(pmd, addr, next, phys_addr, prot)) { + *mask |= PGTBL_PMD_MODIFIED; + continue; + } + + if (ioremap_pte_range(pmd, addr, next, phys_addr, prot, mask)) + return -ENOMEM; + } while (pmd++, phys_addr += (next - addr), addr = next, addr != end); + return 0; +} + +static int ioremap_try_huge_pud(pud_t *pud, unsigned long addr, + unsigned long end, phys_addr_t phys_addr, + pgprot_t prot) +{ + if (!ioremap_pud_enabled()) + return 0; + + if ((end - addr) != PUD_SIZE) + return 0; + + if (!IS_ALIGNED(addr, PUD_SIZE)) + return 0; + + if (!IS_ALIGNED(phys_addr, PUD_SIZE)) + return 0; + + if (pud_present(*pud) && !pud_free_pmd_page(pud, addr)) + return 0; + + return pud_set_huge(pud, phys_addr, prot); +} + +static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr, + unsigned long end, phys_addr_t phys_addr, pgprot_t prot, + pgtbl_mod_mask *mask) +{ + pud_t *pud; + unsigned long next; + + pud = pud_alloc_track(&init_mm, p4d, addr, mask); + if (!pud) + return -ENOMEM; + do { + next = pud_addr_end(addr, end); + + if (ioremap_try_huge_pud(pud, addr, next, phys_addr, prot)) { + *mask |= PGTBL_PUD_MODIFIED; + continue; + } + + if (ioremap_pmd_range(pud, addr, next, phys_addr, prot, mask)) + return -ENOMEM; + } while (pud++, phys_addr += (next - addr), addr = next, addr != end); + return 0; +} + +static int ioremap_try_huge_p4d(p4d_t *p4d, unsigned long addr, + unsigned long end, phys_addr_t phys_addr, + pgprot_t prot) +{ + if (!ioremap_p4d_enabled()) + return 0; + + if ((end - addr) != P4D_SIZE) + return 0; + + if (!IS_ALIGNED(addr, P4D_SIZE)) + return 0; + + if (!IS_ALIGNED(phys_addr, P4D_SIZE)) + return 0; + + if (p4d_present(*p4d) && !p4d_free_pud_page(p4d, addr)) + return 0; + + return p4d_set_huge(p4d, phys_addr, prot); +} + +static inline int ioremap_p4d_range(pgd_t *pgd, unsigned long addr, + unsigned long end, phys_addr_t phys_addr, pgprot_t prot, + pgtbl_mod_mask *mask) +{ + p4d_t *p4d; + unsigned long next; + + p4d = p4d_alloc_track(&init_mm, pgd, addr, mask); + if (!p4d) + return -ENOMEM; + do { + next = p4d_addr_end(addr, end); + + if (ioremap_try_huge_p4d(p4d, addr, next, phys_addr, prot)) { + *mask |= PGTBL_P4D_MODIFIED; + continue; + } + + if (ioremap_pud_range(p4d, addr, next, phys_addr, prot, mask)) + return -ENOMEM; + } while (p4d++, phys_addr += (next - addr), addr = next, addr != end); + return 0; +} + +int ioremap_page_range(unsigned long addr, + unsigned long end, phys_addr_t phys_addr, pgprot_t prot) +{ + pgd_t *pgd; + unsigned long start; + unsigned long next; + int err; + pgtbl_mod_mask mask = 0; + + might_sleep(); + BUG_ON(addr >= end); + + start = addr; + pgd = pgd_offset_k(addr); + do { + next = pgd_addr_end(addr, end); + err = ioremap_p4d_range(pgd, addr, next, phys_addr, prot, + &mask); + if (err) + break; + } while (pgd++, phys_addr += (next - addr), addr = next, addr != end); + + flush_cache_vmap(start, end); + + if (mask & ARCH_PAGE_TABLE_SYNC_MASK) + arch_sync_kernel_mappings(start, end); + + return err; +} + +#ifdef CONFIG_GENERIC_IOREMAP +void __iomem *ioremap_prot(phys_addr_t addr, size_t size, unsigned long prot) +{ + unsigned long offset, vaddr; + phys_addr_t last_addr; + struct vm_struct *area; + + /* Disallow wrap-around or zero size */ + last_addr = addr + size - 1; + if (!size || last_addr < addr) + return NULL; + + /* Page-align mappings */ + offset = addr & (~PAGE_MASK); + addr -= offset; + size = PAGE_ALIGN(size + offset); + + area = get_vm_area_caller(size, VM_IOREMAP, + __builtin_return_address(0)); + if (!area) + return NULL; + vaddr = (unsigned long)area->addr; + + if (ioremap_page_range(vaddr, vaddr + size, addr, __pgprot(prot))) { + free_vm_area(area); + return NULL; + } + + return (void __iomem *)(vaddr + offset); +} +EXPORT_SYMBOL(ioremap_prot); + +void iounmap(volatile void __iomem *addr) +{ + vunmap((void *)((unsigned long)addr & PAGE_MASK)); +} +EXPORT_SYMBOL(iounmap); +#endif /* CONFIG_GENERIC_IOREMAP */ diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile new file mode 100644 index 000000000..370d970e5 --- /dev/null +++ b/mm/kasan/Makefile @@ -0,0 +1,34 @@ +# SPDX-License-Identifier: GPL-2.0 +KASAN_SANITIZE := n +UBSAN_SANITIZE := n +KCOV_INSTRUMENT := n + +# Disable ftrace to avoid recursion. +CFLAGS_REMOVE_common.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_generic.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_generic_report.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_init.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_quarantine.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_report.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_tags.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_tags_report.o = $(CC_FLAGS_FTRACE) + +# Function splitter causes unnecessary splits in __asan_load1/__asan_store1 +# see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63533 +CC_FLAGS_KASAN_RUNTIME := $(call cc-option, -fno-conserve-stack) +CC_FLAGS_KASAN_RUNTIME += -fno-stack-protector +# Disable branch tracing to avoid recursion. +CC_FLAGS_KASAN_RUNTIME += -DDISABLE_BRANCH_PROFILING + +CFLAGS_common.o := $(CC_FLAGS_KASAN_RUNTIME) +CFLAGS_generic.o := $(CC_FLAGS_KASAN_RUNTIME) +CFLAGS_generic_report.o := $(CC_FLAGS_KASAN_RUNTIME) +CFLAGS_init.o := $(CC_FLAGS_KASAN_RUNTIME) +CFLAGS_quarantine.o := $(CC_FLAGS_KASAN_RUNTIME) +CFLAGS_report.o := $(CC_FLAGS_KASAN_RUNTIME) +CFLAGS_tags.o := $(CC_FLAGS_KASAN_RUNTIME) +CFLAGS_tags_report.o := $(CC_FLAGS_KASAN_RUNTIME) + +obj-$(CONFIG_KASAN) := common.o init.o report.o +obj-$(CONFIG_KASAN_GENERIC) += generic.o generic_report.o quarantine.o +obj-$(CONFIG_KASAN_SW_TAGS) += tags.o tags_report.o diff --git a/mm/kasan/common.c b/mm/kasan/common.c new file mode 100644 index 000000000..950fd372a --- /dev/null +++ b/mm/kasan/common.c @@ -0,0 +1,931 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This file contains common generic and tag-based KASAN code. + * + * Copyright (c) 2014 Samsung Electronics Co., Ltd. + * Author: Andrey Ryabinin + * + * Some code borrowed from https://github.com/xairy/kasan-prototype by + * Andrey Konovalov + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include "kasan.h" +#include "../slab.h" + +depot_stack_handle_t kasan_save_stack(gfp_t flags) +{ + unsigned long entries[KASAN_STACK_DEPTH]; + unsigned int nr_entries; + + nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0); + nr_entries = filter_irq_stacks(entries, nr_entries); + return stack_depot_save(entries, nr_entries, flags); +} + +void kasan_set_track(struct kasan_track *track, gfp_t flags) +{ + track->pid = current->pid; + track->stack = kasan_save_stack(flags); +} + +void kasan_enable_current(void) +{ + current->kasan_depth++; +} + +void kasan_disable_current(void) +{ + current->kasan_depth--; +} + +bool __kasan_check_read(const volatile void *p, unsigned int size) +{ + return check_memory_region((unsigned long)p, size, false, _RET_IP_); +} +EXPORT_SYMBOL(__kasan_check_read); + +bool __kasan_check_write(const volatile void *p, unsigned int size) +{ + return check_memory_region((unsigned long)p, size, true, _RET_IP_); +} +EXPORT_SYMBOL(__kasan_check_write); + +#undef memset +void *memset(void *addr, int c, size_t len) +{ + if (!check_memory_region((unsigned long)addr, len, true, _RET_IP_)) + return NULL; + + return __memset(addr, c, len); +} + +#ifdef __HAVE_ARCH_MEMMOVE +#undef memmove +void *memmove(void *dest, const void *src, size_t len) +{ + if (!check_memory_region((unsigned long)src, len, false, _RET_IP_) || + !check_memory_region((unsigned long)dest, len, true, _RET_IP_)) + return NULL; + + return __memmove(dest, src, len); +} +#endif + +#undef memcpy +void *memcpy(void *dest, const void *src, size_t len) +{ + if (!check_memory_region((unsigned long)src, len, false, _RET_IP_) || + !check_memory_region((unsigned long)dest, len, true, _RET_IP_)) + return NULL; + + return __memcpy(dest, src, len); +} + +/* + * Poisons the shadow memory for 'size' bytes starting from 'addr'. + * Memory addresses should be aligned to KASAN_SHADOW_SCALE_SIZE. + */ +void kasan_poison_shadow(const void *address, size_t size, u8 value) +{ + void *shadow_start, *shadow_end; + + /* + * Perform shadow offset calculation based on untagged address, as + * some of the callers (e.g. kasan_poison_object_data) pass tagged + * addresses to this function. + */ + address = reset_tag(address); + + shadow_start = kasan_mem_to_shadow(address); + shadow_end = kasan_mem_to_shadow(address + size); + + __memset(shadow_start, value, shadow_end - shadow_start); +} + +void kasan_unpoison_shadow(const void *address, size_t size) +{ + u8 tag = get_tag(address); + + /* + * Perform shadow offset calculation based on untagged address, as + * some of the callers (e.g. kasan_unpoison_object_data) pass tagged + * addresses to this function. + */ + address = reset_tag(address); + + kasan_poison_shadow(address, size, tag); + + if (size & KASAN_SHADOW_MASK) { + u8 *shadow = (u8 *)kasan_mem_to_shadow(address + size); + + if (IS_ENABLED(CONFIG_KASAN_SW_TAGS)) + *shadow = tag; + else + *shadow = size & KASAN_SHADOW_MASK; + } +} + +static void __kasan_unpoison_stack(struct task_struct *task, const void *sp) +{ + void *base = task_stack_page(task); + size_t size = sp - base; + + kasan_unpoison_shadow(base, size); +} + +/* Unpoison the entire stack for a task. */ +void kasan_unpoison_task_stack(struct task_struct *task) +{ + __kasan_unpoison_stack(task, task_stack_page(task) + THREAD_SIZE); +} + +/* Unpoison the stack for the current task beyond a watermark sp value. */ +asmlinkage void kasan_unpoison_task_stack_below(const void *watermark) +{ + /* + * Calculate the task stack base address. Avoid using 'current' + * because this function is called by early resume code which hasn't + * yet set up the percpu register (%gs). + */ + void *base = (void *)((unsigned long)watermark & ~(THREAD_SIZE - 1)); + + kasan_unpoison_shadow(base, watermark - base); +} + +void kasan_alloc_pages(struct page *page, unsigned int order) +{ + u8 tag; + unsigned long i; + + if (unlikely(PageHighMem(page))) + return; + + tag = random_tag(); + for (i = 0; i < (1 << order); i++) + page_kasan_tag_set(page + i, tag); + kasan_unpoison_shadow(page_address(page), PAGE_SIZE << order); +} + +void kasan_free_pages(struct page *page, unsigned int order) +{ + if (likely(!PageHighMem(page))) + kasan_poison_shadow(page_address(page), + PAGE_SIZE << order, + KASAN_FREE_PAGE); +} + +/* + * Adaptive redzone policy taken from the userspace AddressSanitizer runtime. + * For larger allocations larger redzones are used. + */ +static inline unsigned int optimal_redzone(unsigned int object_size) +{ + if (IS_ENABLED(CONFIG_KASAN_SW_TAGS)) + return 0; + + return + object_size <= 64 - 16 ? 16 : + object_size <= 128 - 32 ? 32 : + object_size <= 512 - 64 ? 64 : + object_size <= 4096 - 128 ? 128 : + object_size <= (1 << 14) - 256 ? 256 : + object_size <= (1 << 15) - 512 ? 512 : + object_size <= (1 << 16) - 1024 ? 1024 : 2048; +} + +void kasan_cache_create(struct kmem_cache *cache, unsigned int *size, + slab_flags_t *flags) +{ + unsigned int orig_size = *size; + unsigned int redzone_size; + int redzone_adjust; + + /* Add alloc meta. */ + cache->kasan_info.alloc_meta_offset = *size; + *size += sizeof(struct kasan_alloc_meta); + + /* Add free meta. */ + if (IS_ENABLED(CONFIG_KASAN_GENERIC) && + (cache->flags & SLAB_TYPESAFE_BY_RCU || cache->ctor || + cache->object_size < sizeof(struct kasan_free_meta))) { + cache->kasan_info.free_meta_offset = *size; + *size += sizeof(struct kasan_free_meta); + } + + redzone_size = optimal_redzone(cache->object_size); + redzone_adjust = redzone_size - (*size - cache->object_size); + if (redzone_adjust > 0) + *size += redzone_adjust; + + *size = min_t(unsigned int, KMALLOC_MAX_SIZE, + max(*size, cache->object_size + redzone_size)); + + /* + * If the metadata doesn't fit, don't enable KASAN at all. + */ + if (*size <= cache->kasan_info.alloc_meta_offset || + *size <= cache->kasan_info.free_meta_offset) { + cache->kasan_info.alloc_meta_offset = 0; + cache->kasan_info.free_meta_offset = 0; + *size = orig_size; + return; + } + + *flags |= SLAB_KASAN; +} + +size_t kasan_metadata_size(struct kmem_cache *cache) +{ + return (cache->kasan_info.alloc_meta_offset ? + sizeof(struct kasan_alloc_meta) : 0) + + (cache->kasan_info.free_meta_offset ? + sizeof(struct kasan_free_meta) : 0); +} + +struct kasan_alloc_meta *get_alloc_info(struct kmem_cache *cache, + const void *object) +{ + return (void *)object + cache->kasan_info.alloc_meta_offset; +} + +struct kasan_free_meta *get_free_info(struct kmem_cache *cache, + const void *object) +{ + BUILD_BUG_ON(sizeof(struct kasan_free_meta) > 32); + return (void *)object + cache->kasan_info.free_meta_offset; +} + +void kasan_poison_slab(struct page *page) +{ + unsigned long i; + + for (i = 0; i < compound_nr(page); i++) + page_kasan_tag_reset(page + i); + kasan_poison_shadow(page_address(page), page_size(page), + KASAN_KMALLOC_REDZONE); +} + +void kasan_unpoison_object_data(struct kmem_cache *cache, void *object) +{ + kasan_unpoison_shadow(object, cache->object_size); +} + +void kasan_poison_object_data(struct kmem_cache *cache, void *object) +{ + kasan_poison_shadow(object, + round_up(cache->object_size, KASAN_SHADOW_SCALE_SIZE), + KASAN_KMALLOC_REDZONE); +} + +/* + * This function assigns a tag to an object considering the following: + * 1. A cache might have a constructor, which might save a pointer to a slab + * object somewhere (e.g. in the object itself). We preassign a tag for + * each object in caches with constructors during slab creation and reuse + * the same tag each time a particular object is allocated. + * 2. A cache might be SLAB_TYPESAFE_BY_RCU, which means objects can be + * accessed after being freed. We preassign tags for objects in these + * caches as well. + * 3. For SLAB allocator we can't preassign tags randomly since the freelist + * is stored as an array of indexes instead of a linked list. Assign tags + * based on objects indexes, so that objects that are next to each other + * get different tags. + */ +static u8 assign_tag(struct kmem_cache *cache, const void *object, + bool init, bool keep_tag) +{ + /* + * 1. When an object is kmalloc()'ed, two hooks are called: + * kasan_slab_alloc() and kasan_kmalloc(). We assign the + * tag only in the first one. + * 2. We reuse the same tag for krealloc'ed objects. + */ + if (keep_tag) + return get_tag(object); + + /* + * If the cache neither has a constructor nor has SLAB_TYPESAFE_BY_RCU + * set, assign a tag when the object is being allocated (init == false). + */ + if (!cache->ctor && !(cache->flags & SLAB_TYPESAFE_BY_RCU)) + return init ? KASAN_TAG_KERNEL : random_tag(); + + /* For caches that either have a constructor or SLAB_TYPESAFE_BY_RCU: */ +#ifdef CONFIG_SLAB + /* For SLAB assign tags based on the object index in the freelist. */ + return (u8)obj_to_index(cache, virt_to_page(object), (void *)object); +#else + /* + * For SLUB assign a random tag during slab creation, otherwise reuse + * the already assigned tag. + */ + return init ? random_tag() : get_tag(object); +#endif +} + +void * __must_check kasan_init_slab_obj(struct kmem_cache *cache, + const void *object) +{ + struct kasan_alloc_meta *alloc_info; + + if (!(cache->flags & SLAB_KASAN)) + return (void *)object; + + alloc_info = get_alloc_info(cache, object); + __memset(alloc_info, 0, sizeof(*alloc_info)); + + if (IS_ENABLED(CONFIG_KASAN_SW_TAGS)) + object = set_tag(object, + assign_tag(cache, object, true, false)); + + return (void *)object; +} + +static inline bool shadow_invalid(u8 tag, s8 shadow_byte) +{ + if (IS_ENABLED(CONFIG_KASAN_GENERIC)) + return shadow_byte < 0 || + shadow_byte >= KASAN_SHADOW_SCALE_SIZE; + + /* else CONFIG_KASAN_SW_TAGS: */ + if ((u8)shadow_byte == KASAN_TAG_INVALID) + return true; + if ((tag != KASAN_TAG_KERNEL) && (tag != (u8)shadow_byte)) + return true; + + return false; +} + +static bool __kasan_slab_free(struct kmem_cache *cache, void *object, + unsigned long ip, bool quarantine) +{ + s8 shadow_byte; + u8 tag; + void *tagged_object; + unsigned long rounded_up_size; + + tag = get_tag(object); + tagged_object = object; + object = reset_tag(object); + + if (unlikely(nearest_obj(cache, virt_to_head_page(object), object) != + object)) { + kasan_report_invalid_free(tagged_object, ip); + return true; + } + + /* RCU slabs could be legally used after free within the RCU period */ + if (unlikely(cache->flags & SLAB_TYPESAFE_BY_RCU)) + return false; + + shadow_byte = READ_ONCE(*(s8 *)kasan_mem_to_shadow(object)); + if (shadow_invalid(tag, shadow_byte)) { + kasan_report_invalid_free(tagged_object, ip); + return true; + } + + rounded_up_size = round_up(cache->object_size, KASAN_SHADOW_SCALE_SIZE); + kasan_poison_shadow(object, rounded_up_size, KASAN_KMALLOC_FREE); + + if ((IS_ENABLED(CONFIG_KASAN_GENERIC) && !quarantine) || + unlikely(!(cache->flags & SLAB_KASAN))) + return false; + + kasan_set_free_info(cache, object, tag); + + quarantine_put(get_free_info(cache, object), cache); + + return IS_ENABLED(CONFIG_KASAN_GENERIC); +} + +bool kasan_slab_free(struct kmem_cache *cache, void *object, unsigned long ip) +{ + return __kasan_slab_free(cache, object, ip, true); +} + +static void *__kasan_kmalloc(struct kmem_cache *cache, const void *object, + size_t size, gfp_t flags, bool keep_tag) +{ + unsigned long redzone_start; + unsigned long redzone_end; + u8 tag = 0xff; + + if (gfpflags_allow_blocking(flags)) + quarantine_reduce(); + + if (unlikely(object == NULL)) + return NULL; + + redzone_start = round_up((unsigned long)(object + size), + KASAN_SHADOW_SCALE_SIZE); + redzone_end = round_up((unsigned long)object + cache->object_size, + KASAN_SHADOW_SCALE_SIZE); + + if (IS_ENABLED(CONFIG_KASAN_SW_TAGS)) + tag = assign_tag(cache, object, false, keep_tag); + + /* Tag is ignored in set_tag without CONFIG_KASAN_SW_TAGS */ + kasan_unpoison_shadow(set_tag(object, tag), size); + kasan_poison_shadow((void *)redzone_start, redzone_end - redzone_start, + KASAN_KMALLOC_REDZONE); + + if (cache->flags & SLAB_KASAN) + kasan_set_track(&get_alloc_info(cache, object)->alloc_track, flags); + + return set_tag(object, tag); +} + +void * __must_check kasan_slab_alloc(struct kmem_cache *cache, void *object, + gfp_t flags) +{ + return __kasan_kmalloc(cache, object, cache->object_size, flags, false); +} + +void * __must_check kasan_kmalloc(struct kmem_cache *cache, const void *object, + size_t size, gfp_t flags) +{ + return __kasan_kmalloc(cache, object, size, flags, true); +} +EXPORT_SYMBOL(kasan_kmalloc); + +void * __must_check kasan_kmalloc_large(const void *ptr, size_t size, + gfp_t flags) +{ + struct page *page; + unsigned long redzone_start; + unsigned long redzone_end; + + if (gfpflags_allow_blocking(flags)) + quarantine_reduce(); + + if (unlikely(ptr == NULL)) + return NULL; + + page = virt_to_page(ptr); + redzone_start = round_up((unsigned long)(ptr + size), + KASAN_SHADOW_SCALE_SIZE); + redzone_end = (unsigned long)ptr + page_size(page); + + kasan_unpoison_shadow(ptr, size); + kasan_poison_shadow((void *)redzone_start, redzone_end - redzone_start, + KASAN_PAGE_REDZONE); + + return (void *)ptr; +} + +void * __must_check kasan_krealloc(const void *object, size_t size, gfp_t flags) +{ + struct page *page; + + if (unlikely(object == ZERO_SIZE_PTR)) + return (void *)object; + + page = virt_to_head_page(object); + + if (unlikely(!PageSlab(page))) + return kasan_kmalloc_large(object, size, flags); + else + return __kasan_kmalloc(page->slab_cache, object, size, + flags, true); +} + +void kasan_poison_kfree(void *ptr, unsigned long ip) +{ + struct page *page; + + page = virt_to_head_page(ptr); + + if (unlikely(!PageSlab(page))) { + if (ptr != page_address(page)) { + kasan_report_invalid_free(ptr, ip); + return; + } + kasan_poison_shadow(ptr, page_size(page), KASAN_FREE_PAGE); + } else { + __kasan_slab_free(page->slab_cache, ptr, ip, false); + } +} + +void kasan_kfree_large(void *ptr, unsigned long ip) +{ + if (ptr != page_address(virt_to_head_page(ptr))) + kasan_report_invalid_free(ptr, ip); + /* The object will be poisoned by page_alloc. */ +} + +#ifndef CONFIG_KASAN_VMALLOC +int kasan_module_alloc(void *addr, size_t size) +{ + void *ret; + size_t scaled_size; + size_t shadow_size; + unsigned long shadow_start; + + shadow_start = (unsigned long)kasan_mem_to_shadow(addr); + scaled_size = (size + KASAN_SHADOW_MASK) >> KASAN_SHADOW_SCALE_SHIFT; + shadow_size = round_up(scaled_size, PAGE_SIZE); + + if (WARN_ON(!PAGE_ALIGNED(shadow_start))) + return -EINVAL; + + ret = __vmalloc_node_range(shadow_size, 1, shadow_start, + shadow_start + shadow_size, + GFP_KERNEL, + PAGE_KERNEL, VM_NO_GUARD, NUMA_NO_NODE, + __builtin_return_address(0)); + + if (ret) { + __memset(ret, KASAN_SHADOW_INIT, shadow_size); + find_vm_area(addr)->flags |= VM_KASAN; + kmemleak_ignore(ret); + return 0; + } + + return -ENOMEM; +} + +void kasan_free_shadow(const struct vm_struct *vm) +{ + if (vm->flags & VM_KASAN) + vfree(kasan_mem_to_shadow(vm->addr)); +} +#endif + +#ifdef CONFIG_MEMORY_HOTPLUG +static bool shadow_mapped(unsigned long addr) +{ + pgd_t *pgd = pgd_offset_k(addr); + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + if (pgd_none(*pgd)) + return false; + p4d = p4d_offset(pgd, addr); + if (p4d_none(*p4d)) + return false; + pud = pud_offset(p4d, addr); + if (pud_none(*pud)) + return false; + + /* + * We can't use pud_large() or pud_huge(), the first one is + * arch-specific, the last one depends on HUGETLB_PAGE. So let's abuse + * pud_bad(), if pud is bad then it's bad because it's huge. + */ + if (pud_bad(*pud)) + return true; + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) + return false; + + if (pmd_bad(*pmd)) + return true; + pte = pte_offset_kernel(pmd, addr); + return !pte_none(*pte); +} + +static int __meminit kasan_mem_notifier(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct memory_notify *mem_data = data; + unsigned long nr_shadow_pages, start_kaddr, shadow_start; + unsigned long shadow_end, shadow_size; + + nr_shadow_pages = mem_data->nr_pages >> KASAN_SHADOW_SCALE_SHIFT; + start_kaddr = (unsigned long)pfn_to_kaddr(mem_data->start_pfn); + shadow_start = (unsigned long)kasan_mem_to_shadow((void *)start_kaddr); + shadow_size = nr_shadow_pages << PAGE_SHIFT; + shadow_end = shadow_start + shadow_size; + + if (WARN_ON(mem_data->nr_pages % KASAN_SHADOW_SCALE_SIZE) || + WARN_ON(start_kaddr % (KASAN_SHADOW_SCALE_SIZE << PAGE_SHIFT))) + return NOTIFY_BAD; + + switch (action) { + case MEM_GOING_ONLINE: { + void *ret; + + /* + * If shadow is mapped already than it must have been mapped + * during the boot. This could happen if we onlining previously + * offlined memory. + */ + if (shadow_mapped(shadow_start)) + return NOTIFY_OK; + + ret = __vmalloc_node_range(shadow_size, PAGE_SIZE, shadow_start, + shadow_end, GFP_KERNEL, + PAGE_KERNEL, VM_NO_GUARD, + pfn_to_nid(mem_data->start_pfn), + __builtin_return_address(0)); + if (!ret) + return NOTIFY_BAD; + + kmemleak_ignore(ret); + return NOTIFY_OK; + } + case MEM_CANCEL_ONLINE: + case MEM_OFFLINE: { + struct vm_struct *vm; + + /* + * shadow_start was either mapped during boot by kasan_init() + * or during memory online by __vmalloc_node_range(). + * In the latter case we can use vfree() to free shadow. + * Non-NULL result of the find_vm_area() will tell us if + * that was the second case. + * + * Currently it's not possible to free shadow mapped + * during boot by kasan_init(). It's because the code + * to do that hasn't been written yet. So we'll just + * leak the memory. + */ + vm = find_vm_area((void *)shadow_start); + if (vm) + vfree((void *)shadow_start); + } + } + + return NOTIFY_OK; +} + +static int __init kasan_memhotplug_init(void) +{ + hotplug_memory_notifier(kasan_mem_notifier, 0); + + return 0; +} + +core_initcall(kasan_memhotplug_init); +#endif + +#ifdef CONFIG_KASAN_VMALLOC +static int kasan_populate_vmalloc_pte(pte_t *ptep, unsigned long addr, + void *unused) +{ + unsigned long page; + pte_t pte; + + if (likely(!pte_none(*ptep))) + return 0; + + page = __get_free_page(GFP_KERNEL); + if (!page) + return -ENOMEM; + + memset((void *)page, KASAN_VMALLOC_INVALID, PAGE_SIZE); + pte = pfn_pte(PFN_DOWN(__pa(page)), PAGE_KERNEL); + + spin_lock(&init_mm.page_table_lock); + if (likely(pte_none(*ptep))) { + set_pte_at(&init_mm, addr, ptep, pte); + page = 0; + } + spin_unlock(&init_mm.page_table_lock); + if (page) + free_page(page); + return 0; +} + +int kasan_populate_vmalloc(unsigned long addr, unsigned long size) +{ + unsigned long shadow_start, shadow_end; + int ret; + + if (!is_vmalloc_or_module_addr((void *)addr)) + return 0; + + shadow_start = (unsigned long)kasan_mem_to_shadow((void *)addr); + shadow_start = ALIGN_DOWN(shadow_start, PAGE_SIZE); + shadow_end = (unsigned long)kasan_mem_to_shadow((void *)addr + size); + shadow_end = ALIGN(shadow_end, PAGE_SIZE); + + ret = apply_to_page_range(&init_mm, shadow_start, + shadow_end - shadow_start, + kasan_populate_vmalloc_pte, NULL); + if (ret) + return ret; + + flush_cache_vmap(shadow_start, shadow_end); + + /* + * We need to be careful about inter-cpu effects here. Consider: + * + * CPU#0 CPU#1 + * WRITE_ONCE(p, vmalloc(100)); while (x = READ_ONCE(p)) ; + * p[99] = 1; + * + * With compiler instrumentation, that ends up looking like this: + * + * CPU#0 CPU#1 + * // vmalloc() allocates memory + * // let a = area->addr + * // we reach kasan_populate_vmalloc + * // and call kasan_unpoison_shadow: + * STORE shadow(a), unpoison_val + * ... + * STORE shadow(a+99), unpoison_val x = LOAD p + * // rest of vmalloc process + * STORE p, a LOAD shadow(x+99) + * + * If there is no barrier between the end of unpoisioning the shadow + * and the store of the result to p, the stores could be committed + * in a different order by CPU#0, and CPU#1 could erroneously observe + * poison in the shadow. + * + * We need some sort of barrier between the stores. + * + * In the vmalloc() case, this is provided by a smp_wmb() in + * clear_vm_uninitialized_flag(). In the per-cpu allocator and in + * get_vm_area() and friends, the caller gets shadow allocated but + * doesn't have any pages mapped into the virtual address space that + * has been reserved. Mapping those pages in will involve taking and + * releasing a page-table lock, which will provide the barrier. + */ + + return 0; +} + +/* + * Poison the shadow for a vmalloc region. Called as part of the + * freeing process at the time the region is freed. + */ +void kasan_poison_vmalloc(const void *start, unsigned long size) +{ + if (!is_vmalloc_or_module_addr(start)) + return; + + size = round_up(size, KASAN_SHADOW_SCALE_SIZE); + kasan_poison_shadow(start, size, KASAN_VMALLOC_INVALID); +} + +void kasan_unpoison_vmalloc(const void *start, unsigned long size) +{ + if (!is_vmalloc_or_module_addr(start)) + return; + + kasan_unpoison_shadow(start, size); +} + +static int kasan_depopulate_vmalloc_pte(pte_t *ptep, unsigned long addr, + void *unused) +{ + unsigned long page; + + page = (unsigned long)__va(pte_pfn(*ptep) << PAGE_SHIFT); + + spin_lock(&init_mm.page_table_lock); + + if (likely(!pte_none(*ptep))) { + pte_clear(&init_mm, addr, ptep); + free_page(page); + } + spin_unlock(&init_mm.page_table_lock); + + return 0; +} + +/* + * Release the backing for the vmalloc region [start, end), which + * lies within the free region [free_region_start, free_region_end). + * + * This can be run lazily, long after the region was freed. It runs + * under vmap_area_lock, so it's not safe to interact with the vmalloc/vmap + * infrastructure. + * + * How does this work? + * ------------------- + * + * We have a region that is page aligned, labelled as A. + * That might not map onto the shadow in a way that is page-aligned: + * + * start end + * v v + * |????????|????????|AAAAAAAA|AA....AA|AAAAAAAA|????????| < vmalloc + * -------- -------- -------- -------- -------- + * | | | | | + * | | | /-------/ | + * \-------\|/------/ |/---------------/ + * ||| || + * |??AAAAAA|AAAAAAAA|AA??????| < shadow + * (1) (2) (3) + * + * First we align the start upwards and the end downwards, so that the + * shadow of the region aligns with shadow page boundaries. In the + * example, this gives us the shadow page (2). This is the shadow entirely + * covered by this allocation. + * + * Then we have the tricky bits. We want to know if we can free the + * partially covered shadow pages - (1) and (3) in the example. For this, + * we are given the start and end of the free region that contains this + * allocation. Extending our previous example, we could have: + * + * free_region_start free_region_end + * | start end | + * v v v v + * |FFFFFFFF|FFFFFFFF|AAAAAAAA|AA....AA|AAAAAAAA|FFFFFFFF| < vmalloc + * -------- -------- -------- -------- -------- + * | | | | | + * | | | /-------/ | + * \-------\|/------/ |/---------------/ + * ||| || + * |FFAAAAAA|AAAAAAAA|AAF?????| < shadow + * (1) (2) (3) + * + * Once again, we align the start of the free region up, and the end of + * the free region down so that the shadow is page aligned. So we can free + * page (1) - we know no allocation currently uses anything in that page, + * because all of it is in the vmalloc free region. But we cannot free + * page (3), because we can't be sure that the rest of it is unused. + * + * We only consider pages that contain part of the original region for + * freeing: we don't try to free other pages from the free region or we'd + * end up trying to free huge chunks of virtual address space. + * + * Concurrency + * ----------- + * + * How do we know that we're not freeing a page that is simultaneously + * being used for a fresh allocation in kasan_populate_vmalloc(_pte)? + * + * We _can_ have kasan_release_vmalloc and kasan_populate_vmalloc running + * at the same time. While we run under free_vmap_area_lock, the population + * code does not. + * + * free_vmap_area_lock instead operates to ensure that the larger range + * [free_region_start, free_region_end) is safe: because __alloc_vmap_area and + * the per-cpu region-finding algorithm both run under free_vmap_area_lock, + * no space identified as free will become used while we are running. This + * means that so long as we are careful with alignment and only free shadow + * pages entirely covered by the free region, we will not run in to any + * trouble - any simultaneous allocations will be for disjoint regions. + */ +void kasan_release_vmalloc(unsigned long start, unsigned long end, + unsigned long free_region_start, + unsigned long free_region_end) +{ + void *shadow_start, *shadow_end; + unsigned long region_start, region_end; + unsigned long size; + + region_start = ALIGN(start, PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE); + region_end = ALIGN_DOWN(end, PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE); + + free_region_start = ALIGN(free_region_start, + PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE); + + if (start != region_start && + free_region_start < region_start) + region_start -= PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE; + + free_region_end = ALIGN_DOWN(free_region_end, + PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE); + + if (end != region_end && + free_region_end > region_end) + region_end += PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE; + + shadow_start = kasan_mem_to_shadow((void *)region_start); + shadow_end = kasan_mem_to_shadow((void *)region_end); + + if (shadow_end > shadow_start) { + size = shadow_end - shadow_start; + apply_to_existing_page_range(&init_mm, + (unsigned long)shadow_start, + size, kasan_depopulate_vmalloc_pte, + NULL); + flush_tlb_kernel_range((unsigned long)shadow_start, + (unsigned long)shadow_end); + } +} +#endif diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c new file mode 100644 index 000000000..248264b9c --- /dev/null +++ b/mm/kasan/generic.c @@ -0,0 +1,369 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This file contains core generic KASAN code. + * + * Copyright (c) 2014 Samsung Electronics Co., Ltd. + * Author: Andrey Ryabinin + * + * Some code borrowed from https://github.com/xairy/kasan-prototype by + * Andrey Konovalov + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "kasan.h" +#include "../slab.h" + +/* + * All functions below always inlined so compiler could + * perform better optimizations in each of __asan_loadX/__assn_storeX + * depending on memory access size X. + */ + +static __always_inline bool memory_is_poisoned_1(unsigned long addr) +{ + s8 shadow_value = *(s8 *)kasan_mem_to_shadow((void *)addr); + + if (unlikely(shadow_value)) { + s8 last_accessible_byte = addr & KASAN_SHADOW_MASK; + return unlikely(last_accessible_byte >= shadow_value); + } + + return false; +} + +static __always_inline bool memory_is_poisoned_2_4_8(unsigned long addr, + unsigned long size) +{ + u8 *shadow_addr = (u8 *)kasan_mem_to_shadow((void *)addr); + + /* + * Access crosses 8(shadow size)-byte boundary. Such access maps + * into 2 shadow bytes, so we need to check them both. + */ + if (unlikely(((addr + size - 1) & KASAN_SHADOW_MASK) < size - 1)) + return *shadow_addr || memory_is_poisoned_1(addr + size - 1); + + return memory_is_poisoned_1(addr + size - 1); +} + +static __always_inline bool memory_is_poisoned_16(unsigned long addr) +{ + u16 *shadow_addr = (u16 *)kasan_mem_to_shadow((void *)addr); + + /* Unaligned 16-bytes access maps into 3 shadow bytes. */ + if (unlikely(!IS_ALIGNED(addr, KASAN_SHADOW_SCALE_SIZE))) + return *shadow_addr || memory_is_poisoned_1(addr + 15); + + return *shadow_addr; +} + +static __always_inline unsigned long bytes_is_nonzero(const u8 *start, + size_t size) +{ + while (size) { + if (unlikely(*start)) + return (unsigned long)start; + start++; + size--; + } + + return 0; +} + +static __always_inline unsigned long memory_is_nonzero(const void *start, + const void *end) +{ + unsigned int words; + unsigned long ret; + unsigned int prefix = (unsigned long)start % 8; + + if (end - start <= 16) + return bytes_is_nonzero(start, end - start); + + if (prefix) { + prefix = 8 - prefix; + ret = bytes_is_nonzero(start, prefix); + if (unlikely(ret)) + return ret; + start += prefix; + } + + words = (end - start) / 8; + while (words) { + if (unlikely(*(u64 *)start)) + return bytes_is_nonzero(start, 8); + start += 8; + words--; + } + + return bytes_is_nonzero(start, (end - start) % 8); +} + +static __always_inline bool memory_is_poisoned_n(unsigned long addr, + size_t size) +{ + unsigned long ret; + + ret = memory_is_nonzero(kasan_mem_to_shadow((void *)addr), + kasan_mem_to_shadow((void *)addr + size - 1) + 1); + + if (unlikely(ret)) { + unsigned long last_byte = addr + size - 1; + s8 *last_shadow = (s8 *)kasan_mem_to_shadow((void *)last_byte); + + if (unlikely(ret != (unsigned long)last_shadow || + ((long)(last_byte & KASAN_SHADOW_MASK) >= *last_shadow))) + return true; + } + return false; +} + +static __always_inline bool memory_is_poisoned(unsigned long addr, size_t size) +{ + if (__builtin_constant_p(size)) { + switch (size) { + case 1: + return memory_is_poisoned_1(addr); + case 2: + case 4: + case 8: + return memory_is_poisoned_2_4_8(addr, size); + case 16: + return memory_is_poisoned_16(addr); + default: + BUILD_BUG(); + } + } + + return memory_is_poisoned_n(addr, size); +} + +static __always_inline bool check_memory_region_inline(unsigned long addr, + size_t size, bool write, + unsigned long ret_ip) +{ + if (unlikely(size == 0)) + return true; + + if (unlikely(addr + size < addr)) + return !kasan_report(addr, size, write, ret_ip); + + if (unlikely((void *)addr < + kasan_shadow_to_mem((void *)KASAN_SHADOW_START))) { + return !kasan_report(addr, size, write, ret_ip); + } + + if (likely(!memory_is_poisoned(addr, size))) + return true; + + return !kasan_report(addr, size, write, ret_ip); +} + +bool check_memory_region(unsigned long addr, size_t size, bool write, + unsigned long ret_ip) +{ + return check_memory_region_inline(addr, size, write, ret_ip); +} + +void kasan_cache_shrink(struct kmem_cache *cache) +{ + quarantine_remove_cache(cache); +} + +void kasan_cache_shutdown(struct kmem_cache *cache) +{ + if (!__kmem_cache_empty(cache)) + quarantine_remove_cache(cache); +} + +static void register_global(struct kasan_global *global) +{ + size_t aligned_size = round_up(global->size, KASAN_SHADOW_SCALE_SIZE); + + kasan_unpoison_shadow(global->beg, global->size); + + kasan_poison_shadow(global->beg + aligned_size, + global->size_with_redzone - aligned_size, + KASAN_GLOBAL_REDZONE); +} + +void __asan_register_globals(struct kasan_global *globals, size_t size) +{ + int i; + + for (i = 0; i < size; i++) + register_global(&globals[i]); +} +EXPORT_SYMBOL(__asan_register_globals); + +void __asan_unregister_globals(struct kasan_global *globals, size_t size) +{ +} +EXPORT_SYMBOL(__asan_unregister_globals); + +#define DEFINE_ASAN_LOAD_STORE(size) \ + void __asan_load##size(unsigned long addr) \ + { \ + check_memory_region_inline(addr, size, false, _RET_IP_);\ + } \ + EXPORT_SYMBOL(__asan_load##size); \ + __alias(__asan_load##size) \ + void __asan_load##size##_noabort(unsigned long); \ + EXPORT_SYMBOL(__asan_load##size##_noabort); \ + void __asan_store##size(unsigned long addr) \ + { \ + check_memory_region_inline(addr, size, true, _RET_IP_); \ + } \ + EXPORT_SYMBOL(__asan_store##size); \ + __alias(__asan_store##size) \ + void __asan_store##size##_noabort(unsigned long); \ + EXPORT_SYMBOL(__asan_store##size##_noabort) + +DEFINE_ASAN_LOAD_STORE(1); +DEFINE_ASAN_LOAD_STORE(2); +DEFINE_ASAN_LOAD_STORE(4); +DEFINE_ASAN_LOAD_STORE(8); +DEFINE_ASAN_LOAD_STORE(16); + +void __asan_loadN(unsigned long addr, size_t size) +{ + check_memory_region(addr, size, false, _RET_IP_); +} +EXPORT_SYMBOL(__asan_loadN); + +__alias(__asan_loadN) +void __asan_loadN_noabort(unsigned long, size_t); +EXPORT_SYMBOL(__asan_loadN_noabort); + +void __asan_storeN(unsigned long addr, size_t size) +{ + check_memory_region(addr, size, true, _RET_IP_); +} +EXPORT_SYMBOL(__asan_storeN); + +__alias(__asan_storeN) +void __asan_storeN_noabort(unsigned long, size_t); +EXPORT_SYMBOL(__asan_storeN_noabort); + +/* to shut up compiler complaints */ +void __asan_handle_no_return(void) {} +EXPORT_SYMBOL(__asan_handle_no_return); + +/* Emitted by compiler to poison alloca()ed objects. */ +void __asan_alloca_poison(unsigned long addr, size_t size) +{ + size_t rounded_up_size = round_up(size, KASAN_SHADOW_SCALE_SIZE); + size_t padding_size = round_up(size, KASAN_ALLOCA_REDZONE_SIZE) - + rounded_up_size; + size_t rounded_down_size = round_down(size, KASAN_SHADOW_SCALE_SIZE); + + const void *left_redzone = (const void *)(addr - + KASAN_ALLOCA_REDZONE_SIZE); + const void *right_redzone = (const void *)(addr + rounded_up_size); + + WARN_ON(!IS_ALIGNED(addr, KASAN_ALLOCA_REDZONE_SIZE)); + + kasan_unpoison_shadow((const void *)(addr + rounded_down_size), + size - rounded_down_size); + kasan_poison_shadow(left_redzone, KASAN_ALLOCA_REDZONE_SIZE, + KASAN_ALLOCA_LEFT); + kasan_poison_shadow(right_redzone, + padding_size + KASAN_ALLOCA_REDZONE_SIZE, + KASAN_ALLOCA_RIGHT); +} +EXPORT_SYMBOL(__asan_alloca_poison); + +/* Emitted by compiler to unpoison alloca()ed areas when the stack unwinds. */ +void __asan_allocas_unpoison(const void *stack_top, const void *stack_bottom) +{ + if (unlikely(!stack_top || stack_top > stack_bottom)) + return; + + kasan_unpoison_shadow(stack_top, stack_bottom - stack_top); +} +EXPORT_SYMBOL(__asan_allocas_unpoison); + +/* Emitted by the compiler to [un]poison local variables. */ +#define DEFINE_ASAN_SET_SHADOW(byte) \ + void __asan_set_shadow_##byte(const void *addr, size_t size) \ + { \ + __memset((void *)addr, 0x##byte, size); \ + } \ + EXPORT_SYMBOL(__asan_set_shadow_##byte) + +DEFINE_ASAN_SET_SHADOW(00); +DEFINE_ASAN_SET_SHADOW(f1); +DEFINE_ASAN_SET_SHADOW(f2); +DEFINE_ASAN_SET_SHADOW(f3); +DEFINE_ASAN_SET_SHADOW(f5); +DEFINE_ASAN_SET_SHADOW(f8); + +void kasan_record_aux_stack(void *addr) +{ + struct page *page = kasan_addr_to_page(addr); + struct kmem_cache *cache; + struct kasan_alloc_meta *alloc_info; + void *object; + + if (!(page && PageSlab(page))) + return; + + cache = page->slab_cache; + object = nearest_obj(cache, page, addr); + alloc_info = get_alloc_info(cache, object); + + /* + * record the last two call_rcu() call stacks. + */ + alloc_info->aux_stack[1] = alloc_info->aux_stack[0]; + alloc_info->aux_stack[0] = kasan_save_stack(GFP_NOWAIT); +} + +void kasan_set_free_info(struct kmem_cache *cache, + void *object, u8 tag) +{ + struct kasan_free_meta *free_meta; + + free_meta = get_free_info(cache, object); + kasan_set_track(&free_meta->free_track, GFP_NOWAIT); + + /* + * the object was freed and has free track set + */ + *(u8 *)kasan_mem_to_shadow(object) = KASAN_KMALLOC_FREETRACK; +} + +struct kasan_track *kasan_get_free_track(struct kmem_cache *cache, + void *object, u8 tag) +{ + if (*(u8 *)kasan_mem_to_shadow(object) != KASAN_KMALLOC_FREETRACK) + return NULL; + return &get_free_info(cache, object)->free_track; +} diff --git a/mm/kasan/generic_report.c b/mm/kasan/generic_report.c new file mode 100644 index 000000000..a38c7a9e1 --- /dev/null +++ b/mm/kasan/generic_report.c @@ -0,0 +1,165 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This file contains generic KASAN specific error reporting code. + * + * Copyright (c) 2014 Samsung Electronics Co., Ltd. + * Author: Andrey Ryabinin + * + * Some code borrowed from https://github.com/xairy/kasan-prototype by + * Andrey Konovalov + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "kasan.h" +#include "../slab.h" + +void *find_first_bad_addr(void *addr, size_t size) +{ + void *p = addr; + + while (p < addr + size && !(*(u8 *)kasan_mem_to_shadow(p))) + p += KASAN_SHADOW_SCALE_SIZE; + return p; +} + +static const char *get_shadow_bug_type(struct kasan_access_info *info) +{ + const char *bug_type = "unknown-crash"; + u8 *shadow_addr; + + shadow_addr = (u8 *)kasan_mem_to_shadow(info->first_bad_addr); + + /* + * If shadow byte value is in [0, KASAN_SHADOW_SCALE_SIZE) we can look + * at the next shadow byte to determine the type of the bad access. + */ + if (*shadow_addr > 0 && *shadow_addr <= KASAN_SHADOW_SCALE_SIZE - 1) + shadow_addr++; + + switch (*shadow_addr) { + case 0 ... KASAN_SHADOW_SCALE_SIZE - 1: + /* + * In theory it's still possible to see these shadow values + * due to a data race in the kernel code. + */ + bug_type = "out-of-bounds"; + break; + case KASAN_PAGE_REDZONE: + case KASAN_KMALLOC_REDZONE: + bug_type = "slab-out-of-bounds"; + break; + case KASAN_GLOBAL_REDZONE: + bug_type = "global-out-of-bounds"; + break; + case KASAN_STACK_LEFT: + case KASAN_STACK_MID: + case KASAN_STACK_RIGHT: + case KASAN_STACK_PARTIAL: + bug_type = "stack-out-of-bounds"; + break; + case KASAN_FREE_PAGE: + case KASAN_KMALLOC_FREE: + case KASAN_KMALLOC_FREETRACK: + bug_type = "use-after-free"; + break; + case KASAN_ALLOCA_LEFT: + case KASAN_ALLOCA_RIGHT: + bug_type = "alloca-out-of-bounds"; + break; + case KASAN_VMALLOC_INVALID: + bug_type = "vmalloc-out-of-bounds"; + break; + } + + return bug_type; +} + +static const char *get_wild_bug_type(struct kasan_access_info *info) +{ + const char *bug_type = "unknown-crash"; + + if ((unsigned long)info->access_addr < PAGE_SIZE) + bug_type = "null-ptr-deref"; + else if ((unsigned long)info->access_addr < TASK_SIZE) + bug_type = "user-memory-access"; + else + bug_type = "wild-memory-access"; + + return bug_type; +} + +const char *get_bug_type(struct kasan_access_info *info) +{ + /* + * If access_size is a negative number, then it has reason to be + * defined as out-of-bounds bug type. + * + * Casting negative numbers to size_t would indeed turn up as + * a large size_t and its value will be larger than ULONG_MAX/2, + * so that this can qualify as out-of-bounds. + */ + if (info->access_addr + info->access_size < info->access_addr) + return "out-of-bounds"; + + if (addr_has_shadow(info->access_addr)) + return get_shadow_bug_type(info); + return get_wild_bug_type(info); +} + +#define DEFINE_ASAN_REPORT_LOAD(size) \ +void __asan_report_load##size##_noabort(unsigned long addr) \ +{ \ + kasan_report(addr, size, false, _RET_IP_); \ +} \ +EXPORT_SYMBOL(__asan_report_load##size##_noabort) + +#define DEFINE_ASAN_REPORT_STORE(size) \ +void __asan_report_store##size##_noabort(unsigned long addr) \ +{ \ + kasan_report(addr, size, true, _RET_IP_); \ +} \ +EXPORT_SYMBOL(__asan_report_store##size##_noabort) + +DEFINE_ASAN_REPORT_LOAD(1); +DEFINE_ASAN_REPORT_LOAD(2); +DEFINE_ASAN_REPORT_LOAD(4); +DEFINE_ASAN_REPORT_LOAD(8); +DEFINE_ASAN_REPORT_LOAD(16); +DEFINE_ASAN_REPORT_STORE(1); +DEFINE_ASAN_REPORT_STORE(2); +DEFINE_ASAN_REPORT_STORE(4); +DEFINE_ASAN_REPORT_STORE(8); +DEFINE_ASAN_REPORT_STORE(16); + +void __asan_report_load_n_noabort(unsigned long addr, size_t size) +{ + kasan_report(addr, size, false, _RET_IP_); +} +EXPORT_SYMBOL(__asan_report_load_n_noabort); + +void __asan_report_store_n_noabort(unsigned long addr, size_t size) +{ + kasan_report(addr, size, true, _RET_IP_); +} +EXPORT_SYMBOL(__asan_report_store_n_noabort); diff --git a/mm/kasan/init.c b/mm/kasan/init.c new file mode 100644 index 000000000..b8c6ec172 --- /dev/null +++ b/mm/kasan/init.c @@ -0,0 +1,497 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This file contains some kasan initialization code. + * + * Copyright (c) 2015 Samsung Electronics Co., Ltd. + * Author: Andrey Ryabinin + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include "kasan.h" + +/* + * This page serves two purposes: + * - It used as early shadow memory. The entire shadow region populated + * with this page, before we will be able to setup normal shadow memory. + * - Latter it reused it as zero shadow to cover large ranges of memory + * that allowed to access, but not handled by kasan (vmalloc/vmemmap ...). + */ +unsigned char kasan_early_shadow_page[PAGE_SIZE] __page_aligned_bss; + +#if CONFIG_PGTABLE_LEVELS > 4 +p4d_t kasan_early_shadow_p4d[MAX_PTRS_PER_P4D] __page_aligned_bss; +static inline bool kasan_p4d_table(pgd_t pgd) +{ + return pgd_page(pgd) == virt_to_page(lm_alias(kasan_early_shadow_p4d)); +} +#else +static inline bool kasan_p4d_table(pgd_t pgd) +{ + return false; +} +#endif +#if CONFIG_PGTABLE_LEVELS > 3 +pud_t kasan_early_shadow_pud[PTRS_PER_PUD] __page_aligned_bss; +static inline bool kasan_pud_table(p4d_t p4d) +{ + return p4d_page(p4d) == virt_to_page(lm_alias(kasan_early_shadow_pud)); +} +#else +static inline bool kasan_pud_table(p4d_t p4d) +{ + return false; +} +#endif +#if CONFIG_PGTABLE_LEVELS > 2 +pmd_t kasan_early_shadow_pmd[PTRS_PER_PMD] __page_aligned_bss; +static inline bool kasan_pmd_table(pud_t pud) +{ + return pud_page(pud) == virt_to_page(lm_alias(kasan_early_shadow_pmd)); +} +#else +static inline bool kasan_pmd_table(pud_t pud) +{ + return false; +} +#endif +pte_t kasan_early_shadow_pte[PTRS_PER_PTE] __page_aligned_bss; + +static inline bool kasan_pte_table(pmd_t pmd) +{ + return pmd_page(pmd) == virt_to_page(lm_alias(kasan_early_shadow_pte)); +} + +static inline bool kasan_early_shadow_page_entry(pte_t pte) +{ + return pte_page(pte) == virt_to_page(lm_alias(kasan_early_shadow_page)); +} + +static __init void *early_alloc(size_t size, int node) +{ + void *ptr = memblock_alloc_try_nid(size, size, __pa(MAX_DMA_ADDRESS), + MEMBLOCK_ALLOC_ACCESSIBLE, node); + + if (!ptr) + panic("%s: Failed to allocate %zu bytes align=%zx nid=%d from=%llx\n", + __func__, size, size, node, (u64)__pa(MAX_DMA_ADDRESS)); + + return ptr; +} + +static void __ref zero_pte_populate(pmd_t *pmd, unsigned long addr, + unsigned long end) +{ + pte_t *pte = pte_offset_kernel(pmd, addr); + pte_t zero_pte; + + zero_pte = pfn_pte(PFN_DOWN(__pa_symbol(kasan_early_shadow_page)), + PAGE_KERNEL); + zero_pte = pte_wrprotect(zero_pte); + + while (addr + PAGE_SIZE <= end) { + set_pte_at(&init_mm, addr, pte, zero_pte); + addr += PAGE_SIZE; + pte = pte_offset_kernel(pmd, addr); + } +} + +static int __ref zero_pmd_populate(pud_t *pud, unsigned long addr, + unsigned long end) +{ + pmd_t *pmd = pmd_offset(pud, addr); + unsigned long next; + + do { + next = pmd_addr_end(addr, end); + + if (IS_ALIGNED(addr, PMD_SIZE) && end - addr >= PMD_SIZE) { + pmd_populate_kernel(&init_mm, pmd, + lm_alias(kasan_early_shadow_pte)); + continue; + } + + if (pmd_none(*pmd)) { + pte_t *p; + + if (slab_is_available()) + p = pte_alloc_one_kernel(&init_mm); + else + p = early_alloc(PAGE_SIZE, NUMA_NO_NODE); + if (!p) + return -ENOMEM; + + pmd_populate_kernel(&init_mm, pmd, p); + } + zero_pte_populate(pmd, addr, next); + } while (pmd++, addr = next, addr != end); + + return 0; +} + +static int __ref zero_pud_populate(p4d_t *p4d, unsigned long addr, + unsigned long end) +{ + pud_t *pud = pud_offset(p4d, addr); + unsigned long next; + + do { + next = pud_addr_end(addr, end); + if (IS_ALIGNED(addr, PUD_SIZE) && end - addr >= PUD_SIZE) { + pmd_t *pmd; + + pud_populate(&init_mm, pud, + lm_alias(kasan_early_shadow_pmd)); + pmd = pmd_offset(pud, addr); + pmd_populate_kernel(&init_mm, pmd, + lm_alias(kasan_early_shadow_pte)); + continue; + } + + if (pud_none(*pud)) { + pmd_t *p; + + if (slab_is_available()) { + p = pmd_alloc(&init_mm, pud, addr); + if (!p) + return -ENOMEM; + } else { + pud_populate(&init_mm, pud, + early_alloc(PAGE_SIZE, NUMA_NO_NODE)); + } + } + zero_pmd_populate(pud, addr, next); + } while (pud++, addr = next, addr != end); + + return 0; +} + +static int __ref zero_p4d_populate(pgd_t *pgd, unsigned long addr, + unsigned long end) +{ + p4d_t *p4d = p4d_offset(pgd, addr); + unsigned long next; + + do { + next = p4d_addr_end(addr, end); + if (IS_ALIGNED(addr, P4D_SIZE) && end - addr >= P4D_SIZE) { + pud_t *pud; + pmd_t *pmd; + + p4d_populate(&init_mm, p4d, + lm_alias(kasan_early_shadow_pud)); + pud = pud_offset(p4d, addr); + pud_populate(&init_mm, pud, + lm_alias(kasan_early_shadow_pmd)); + pmd = pmd_offset(pud, addr); + pmd_populate_kernel(&init_mm, pmd, + lm_alias(kasan_early_shadow_pte)); + continue; + } + + if (p4d_none(*p4d)) { + pud_t *p; + + if (slab_is_available()) { + p = pud_alloc(&init_mm, p4d, addr); + if (!p) + return -ENOMEM; + } else { + p4d_populate(&init_mm, p4d, + early_alloc(PAGE_SIZE, NUMA_NO_NODE)); + } + } + zero_pud_populate(p4d, addr, next); + } while (p4d++, addr = next, addr != end); + + return 0; +} + +/** + * kasan_populate_early_shadow - populate shadow memory region with + * kasan_early_shadow_page + * @shadow_start - start of the memory range to populate + * @shadow_end - end of the memory range to populate + */ +int __ref kasan_populate_early_shadow(const void *shadow_start, + const void *shadow_end) +{ + unsigned long addr = (unsigned long)shadow_start; + unsigned long end = (unsigned long)shadow_end; + pgd_t *pgd = pgd_offset_k(addr); + unsigned long next; + + do { + next = pgd_addr_end(addr, end); + + if (IS_ALIGNED(addr, PGDIR_SIZE) && end - addr >= PGDIR_SIZE) { + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + /* + * kasan_early_shadow_pud should be populated with pmds + * at this moment. + * [pud,pmd]_populate*() below needed only for + * 3,2 - level page tables where we don't have + * puds,pmds, so pgd_populate(), pud_populate() + * is noops. + */ + pgd_populate(&init_mm, pgd, + lm_alias(kasan_early_shadow_p4d)); + p4d = p4d_offset(pgd, addr); + p4d_populate(&init_mm, p4d, + lm_alias(kasan_early_shadow_pud)); + pud = pud_offset(p4d, addr); + pud_populate(&init_mm, pud, + lm_alias(kasan_early_shadow_pmd)); + pmd = pmd_offset(pud, addr); + pmd_populate_kernel(&init_mm, pmd, + lm_alias(kasan_early_shadow_pte)); + continue; + } + + if (pgd_none(*pgd)) { + p4d_t *p; + + if (slab_is_available()) { + p = p4d_alloc(&init_mm, pgd, addr); + if (!p) + return -ENOMEM; + } else { + pgd_populate(&init_mm, pgd, + early_alloc(PAGE_SIZE, NUMA_NO_NODE)); + } + } + zero_p4d_populate(pgd, addr, next); + } while (pgd++, addr = next, addr != end); + + return 0; +} + +static void kasan_free_pte(pte_t *pte_start, pmd_t *pmd) +{ + pte_t *pte; + int i; + + for (i = 0; i < PTRS_PER_PTE; i++) { + pte = pte_start + i; + if (!pte_none(*pte)) + return; + } + + pte_free_kernel(&init_mm, (pte_t *)page_to_virt(pmd_page(*pmd))); + pmd_clear(pmd); +} + +static void kasan_free_pmd(pmd_t *pmd_start, pud_t *pud) +{ + pmd_t *pmd; + int i; + + for (i = 0; i < PTRS_PER_PMD; i++) { + pmd = pmd_start + i; + if (!pmd_none(*pmd)) + return; + } + + pmd_free(&init_mm, (pmd_t *)page_to_virt(pud_page(*pud))); + pud_clear(pud); +} + +static void kasan_free_pud(pud_t *pud_start, p4d_t *p4d) +{ + pud_t *pud; + int i; + + for (i = 0; i < PTRS_PER_PUD; i++) { + pud = pud_start + i; + if (!pud_none(*pud)) + return; + } + + pud_free(&init_mm, (pud_t *)page_to_virt(p4d_page(*p4d))); + p4d_clear(p4d); +} + +static void kasan_free_p4d(p4d_t *p4d_start, pgd_t *pgd) +{ + p4d_t *p4d; + int i; + + for (i = 0; i < PTRS_PER_P4D; i++) { + p4d = p4d_start + i; + if (!p4d_none(*p4d)) + return; + } + + p4d_free(&init_mm, (p4d_t *)page_to_virt(pgd_page(*pgd))); + pgd_clear(pgd); +} + +static void kasan_remove_pte_table(pte_t *pte, unsigned long addr, + unsigned long end) +{ + unsigned long next; + + for (; addr < end; addr = next, pte++) { + next = (addr + PAGE_SIZE) & PAGE_MASK; + if (next > end) + next = end; + + if (!pte_present(*pte)) + continue; + + if (WARN_ON(!kasan_early_shadow_page_entry(*pte))) + continue; + pte_clear(&init_mm, addr, pte); + } +} + +static void kasan_remove_pmd_table(pmd_t *pmd, unsigned long addr, + unsigned long end) +{ + unsigned long next; + + for (; addr < end; addr = next, pmd++) { + pte_t *pte; + + next = pmd_addr_end(addr, end); + + if (!pmd_present(*pmd)) + continue; + + if (kasan_pte_table(*pmd)) { + if (IS_ALIGNED(addr, PMD_SIZE) && + IS_ALIGNED(next, PMD_SIZE)) { + pmd_clear(pmd); + continue; + } + } + pte = pte_offset_kernel(pmd, addr); + kasan_remove_pte_table(pte, addr, next); + kasan_free_pte(pte_offset_kernel(pmd, 0), pmd); + } +} + +static void kasan_remove_pud_table(pud_t *pud, unsigned long addr, + unsigned long end) +{ + unsigned long next; + + for (; addr < end; addr = next, pud++) { + pmd_t *pmd, *pmd_base; + + next = pud_addr_end(addr, end); + + if (!pud_present(*pud)) + continue; + + if (kasan_pmd_table(*pud)) { + if (IS_ALIGNED(addr, PUD_SIZE) && + IS_ALIGNED(next, PUD_SIZE)) { + pud_clear(pud); + continue; + } + } + pmd = pmd_offset(pud, addr); + pmd_base = pmd_offset(pud, 0); + kasan_remove_pmd_table(pmd, addr, next); + kasan_free_pmd(pmd_base, pud); + } +} + +static void kasan_remove_p4d_table(p4d_t *p4d, unsigned long addr, + unsigned long end) +{ + unsigned long next; + + for (; addr < end; addr = next, p4d++) { + pud_t *pud; + + next = p4d_addr_end(addr, end); + + if (!p4d_present(*p4d)) + continue; + + if (kasan_pud_table(*p4d)) { + if (IS_ALIGNED(addr, P4D_SIZE) && + IS_ALIGNED(next, P4D_SIZE)) { + p4d_clear(p4d); + continue; + } + } + pud = pud_offset(p4d, addr); + kasan_remove_pud_table(pud, addr, next); + kasan_free_pud(pud_offset(p4d, 0), p4d); + } +} + +void kasan_remove_zero_shadow(void *start, unsigned long size) +{ + unsigned long addr, end, next; + pgd_t *pgd; + + addr = (unsigned long)kasan_mem_to_shadow(start); + end = addr + (size >> KASAN_SHADOW_SCALE_SHIFT); + + if (WARN_ON((unsigned long)start % + (KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE)) || + WARN_ON(size % (KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE))) + return; + + for (; addr < end; addr = next) { + p4d_t *p4d; + + next = pgd_addr_end(addr, end); + + pgd = pgd_offset_k(addr); + if (!pgd_present(*pgd)) + continue; + + if (kasan_p4d_table(*pgd)) { + if (IS_ALIGNED(addr, PGDIR_SIZE) && + IS_ALIGNED(next, PGDIR_SIZE)) { + pgd_clear(pgd); + continue; + } + } + + p4d = p4d_offset(pgd, addr); + kasan_remove_p4d_table(p4d, addr, next); + kasan_free_p4d(p4d_offset(pgd, 0), pgd); + } +} + +int kasan_add_zero_shadow(void *start, unsigned long size) +{ + int ret; + void *shadow_start, *shadow_end; + + shadow_start = kasan_mem_to_shadow(start); + shadow_end = shadow_start + (size >> KASAN_SHADOW_SCALE_SHIFT); + + if (WARN_ON((unsigned long)start % + (KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE)) || + WARN_ON(size % (KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE))) + return -EINVAL; + + ret = kasan_populate_early_shadow(shadow_start, shadow_end); + if (ret) + kasan_remove_zero_shadow(start, size); + return ret; +} diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h new file mode 100644 index 000000000..ac4994567 --- /dev/null +++ b/mm/kasan/kasan.h @@ -0,0 +1,299 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __MM_KASAN_KASAN_H +#define __MM_KASAN_KASAN_H + +#include +#include + +#define KASAN_SHADOW_SCALE_SIZE (1UL << KASAN_SHADOW_SCALE_SHIFT) +#define KASAN_SHADOW_MASK (KASAN_SHADOW_SCALE_SIZE - 1) + +#define KASAN_TAG_KERNEL 0xFF /* native kernel pointers tag */ +#define KASAN_TAG_INVALID 0xFE /* inaccessible memory tag */ +#define KASAN_TAG_MAX 0xFD /* maximum value for random tags */ + +#ifdef CONFIG_KASAN_GENERIC +#define KASAN_FREE_PAGE 0xFF /* page was freed */ +#define KASAN_PAGE_REDZONE 0xFE /* redzone for kmalloc_large allocations */ +#define KASAN_KMALLOC_REDZONE 0xFC /* redzone inside slub object */ +#define KASAN_KMALLOC_FREE 0xFB /* object was freed (kmem_cache_free/kfree) */ +#define KASAN_KMALLOC_FREETRACK 0xFA /* object was freed and has free track set */ +#else +#define KASAN_FREE_PAGE KASAN_TAG_INVALID +#define KASAN_PAGE_REDZONE KASAN_TAG_INVALID +#define KASAN_KMALLOC_REDZONE KASAN_TAG_INVALID +#define KASAN_KMALLOC_FREE KASAN_TAG_INVALID +#define KASAN_KMALLOC_FREETRACK KASAN_TAG_INVALID +#endif + +#define KASAN_GLOBAL_REDZONE 0xF9 /* redzone for global variable */ +#define KASAN_VMALLOC_INVALID 0xF8 /* unallocated space in vmapped page */ + +/* + * Stack redzone shadow values + * (Those are compiler's ABI, don't change them) + */ +#define KASAN_STACK_LEFT 0xF1 +#define KASAN_STACK_MID 0xF2 +#define KASAN_STACK_RIGHT 0xF3 +#define KASAN_STACK_PARTIAL 0xF4 + +/* + * alloca redzone shadow values + */ +#define KASAN_ALLOCA_LEFT 0xCA +#define KASAN_ALLOCA_RIGHT 0xCB + +#define KASAN_ALLOCA_REDZONE_SIZE 32 + +/* + * Stack frame marker (compiler ABI). + */ +#define KASAN_CURRENT_STACK_FRAME_MAGIC 0x41B58AB3 + +/* Don't break randconfig/all*config builds */ +#ifndef KASAN_ABI_VERSION +#define KASAN_ABI_VERSION 1 +#endif + +struct kasan_access_info { + const void *access_addr; + const void *first_bad_addr; + size_t access_size; + bool is_write; + unsigned long ip; +}; + +/* The layout of struct dictated by compiler */ +struct kasan_source_location { + const char *filename; + int line_no; + int column_no; +}; + +/* The layout of struct dictated by compiler */ +struct kasan_global { + const void *beg; /* Address of the beginning of the global variable. */ + size_t size; /* Size of the global variable. */ + size_t size_with_redzone; /* Size of the variable + size of the red zone. 32 bytes aligned */ + const void *name; + const void *module_name; /* Name of the module where the global variable is declared. */ + unsigned long has_dynamic_init; /* This needed for C++ */ +#if KASAN_ABI_VERSION >= 4 + struct kasan_source_location *location; +#endif +#if KASAN_ABI_VERSION >= 5 + char *odr_indicator; +#endif +}; + +/** + * Structures to keep alloc and free tracks * + */ + +#define KASAN_STACK_DEPTH 64 + +struct kasan_track { + u32 pid; + depot_stack_handle_t stack; +}; + +#ifdef CONFIG_KASAN_SW_TAGS_IDENTIFY +#define KASAN_NR_FREE_STACKS 5 +#else +#define KASAN_NR_FREE_STACKS 1 +#endif + +struct kasan_alloc_meta { + struct kasan_track alloc_track; +#ifdef CONFIG_KASAN_GENERIC + /* + * call_rcu() call stack is stored into struct kasan_alloc_meta. + * The free stack is stored into struct kasan_free_meta. + */ + depot_stack_handle_t aux_stack[2]; +#else + struct kasan_track free_track[KASAN_NR_FREE_STACKS]; +#endif +#ifdef CONFIG_KASAN_SW_TAGS_IDENTIFY + u8 free_pointer_tag[KASAN_NR_FREE_STACKS]; + u8 free_track_idx; +#endif +}; + +struct qlist_node { + struct qlist_node *next; +}; +struct kasan_free_meta { + /* This field is used while the object is in the quarantine. + * Otherwise it might be used for the allocator freelist. + */ + struct qlist_node quarantine_link; +#ifdef CONFIG_KASAN_GENERIC + struct kasan_track free_track; +#endif +}; + +struct kasan_alloc_meta *get_alloc_info(struct kmem_cache *cache, + const void *object); +struct kasan_free_meta *get_free_info(struct kmem_cache *cache, + const void *object); + +static inline const void *kasan_shadow_to_mem(const void *shadow_addr) +{ + return (void *)(((unsigned long)shadow_addr - KASAN_SHADOW_OFFSET) + << KASAN_SHADOW_SCALE_SHIFT); +} + +static inline bool addr_has_shadow(const void *addr) +{ + return (addr >= kasan_shadow_to_mem((void *)KASAN_SHADOW_START)); +} + +void kasan_poison_shadow(const void *address, size_t size, u8 value); + +/** + * check_memory_region - Check memory region, and report if invalid access. + * @addr: the accessed address + * @size: the accessed size + * @write: true if access is a write access + * @ret_ip: return address + * @return: true if access was valid, false if invalid + */ +bool check_memory_region(unsigned long addr, size_t size, bool write, + unsigned long ret_ip); + +void *find_first_bad_addr(void *addr, size_t size); +const char *get_bug_type(struct kasan_access_info *info); + +bool kasan_report(unsigned long addr, size_t size, + bool is_write, unsigned long ip); +void kasan_report_invalid_free(void *object, unsigned long ip); + +struct page *kasan_addr_to_page(const void *addr); + +depot_stack_handle_t kasan_save_stack(gfp_t flags); +void kasan_set_track(struct kasan_track *track, gfp_t flags); +void kasan_set_free_info(struct kmem_cache *cache, void *object, u8 tag); +struct kasan_track *kasan_get_free_track(struct kmem_cache *cache, + void *object, u8 tag); + +#if defined(CONFIG_KASAN_GENERIC) && \ + (defined(CONFIG_SLAB) || defined(CONFIG_SLUB)) +void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache); +void quarantine_reduce(void); +void quarantine_remove_cache(struct kmem_cache *cache); +#else +static inline void quarantine_put(struct kasan_free_meta *info, + struct kmem_cache *cache) { } +static inline void quarantine_reduce(void) { } +static inline void quarantine_remove_cache(struct kmem_cache *cache) { } +#endif + +#ifdef CONFIG_KASAN_SW_TAGS + +void print_tags(u8 addr_tag, const void *addr); + +u8 random_tag(void); + +#else + +static inline void print_tags(u8 addr_tag, const void *addr) { } + +static inline u8 random_tag(void) +{ + return 0; +} + +#endif + +#ifndef arch_kasan_set_tag +static inline const void *arch_kasan_set_tag(const void *addr, u8 tag) +{ + return addr; +} +#endif +#ifndef arch_kasan_reset_tag +#define arch_kasan_reset_tag(addr) ((void *)(addr)) +#endif +#ifndef arch_kasan_get_tag +#define arch_kasan_get_tag(addr) 0 +#endif + +#define set_tag(addr, tag) ((void *)arch_kasan_set_tag((addr), (tag))) +#define reset_tag(addr) ((void *)arch_kasan_reset_tag(addr)) +#define get_tag(addr) arch_kasan_get_tag(addr) + +/* + * Exported functions for interfaces called from assembly or from generated + * code. Declarations here to avoid warning about missing declarations. + */ +asmlinkage void kasan_unpoison_task_stack_below(const void *watermark); +void __asan_register_globals(struct kasan_global *globals, size_t size); +void __asan_unregister_globals(struct kasan_global *globals, size_t size); +void __asan_handle_no_return(void); +void __asan_alloca_poison(unsigned long addr, size_t size); +void __asan_allocas_unpoison(const void *stack_top, const void *stack_bottom); + +void __asan_load1(unsigned long addr); +void __asan_store1(unsigned long addr); +void __asan_load2(unsigned long addr); +void __asan_store2(unsigned long addr); +void __asan_load4(unsigned long addr); +void __asan_store4(unsigned long addr); +void __asan_load8(unsigned long addr); +void __asan_store8(unsigned long addr); +void __asan_load16(unsigned long addr); +void __asan_store16(unsigned long addr); +void __asan_loadN(unsigned long addr, size_t size); +void __asan_storeN(unsigned long addr, size_t size); + +void __asan_load1_noabort(unsigned long addr); +void __asan_store1_noabort(unsigned long addr); +void __asan_load2_noabort(unsigned long addr); +void __asan_store2_noabort(unsigned long addr); +void __asan_load4_noabort(unsigned long addr); +void __asan_store4_noabort(unsigned long addr); +void __asan_load8_noabort(unsigned long addr); +void __asan_store8_noabort(unsigned long addr); +void __asan_load16_noabort(unsigned long addr); +void __asan_store16_noabort(unsigned long addr); +void __asan_loadN_noabort(unsigned long addr, size_t size); +void __asan_storeN_noabort(unsigned long addr, size_t size); + +void __asan_report_load1_noabort(unsigned long addr); +void __asan_report_store1_noabort(unsigned long addr); +void __asan_report_load2_noabort(unsigned long addr); +void __asan_report_store2_noabort(unsigned long addr); +void __asan_report_load4_noabort(unsigned long addr); +void __asan_report_store4_noabort(unsigned long addr); +void __asan_report_load8_noabort(unsigned long addr); +void __asan_report_store8_noabort(unsigned long addr); +void __asan_report_load16_noabort(unsigned long addr); +void __asan_report_store16_noabort(unsigned long addr); +void __asan_report_load_n_noabort(unsigned long addr, size_t size); +void __asan_report_store_n_noabort(unsigned long addr, size_t size); + +void __asan_set_shadow_00(const void *addr, size_t size); +void __asan_set_shadow_f1(const void *addr, size_t size); +void __asan_set_shadow_f2(const void *addr, size_t size); +void __asan_set_shadow_f3(const void *addr, size_t size); +void __asan_set_shadow_f5(const void *addr, size_t size); +void __asan_set_shadow_f8(const void *addr, size_t size); + +void __hwasan_load1_noabort(unsigned long addr); +void __hwasan_store1_noabort(unsigned long addr); +void __hwasan_load2_noabort(unsigned long addr); +void __hwasan_store2_noabort(unsigned long addr); +void __hwasan_load4_noabort(unsigned long addr); +void __hwasan_store4_noabort(unsigned long addr); +void __hwasan_load8_noabort(unsigned long addr); +void __hwasan_store8_noabort(unsigned long addr); +void __hwasan_load16_noabort(unsigned long addr); +void __hwasan_store16_noabort(unsigned long addr); +void __hwasan_loadN_noabort(unsigned long addr, size_t size); +void __hwasan_storeN_noabort(unsigned long addr, size_t size); + +void __hwasan_tag_memory(unsigned long addr, u8 tag, unsigned long size); + +#endif diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c new file mode 100644 index 000000000..622193846 --- /dev/null +++ b/mm/kasan/quarantine.c @@ -0,0 +1,376 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KASAN quarantine. + * + * Author: Alexander Potapenko + * Copyright (C) 2016 Google, Inc. + * + * Based on code by Dmitry Chernenkov. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "../slab.h" +#include "kasan.h" + +/* Data structure and operations for quarantine queues. */ + +/* + * Each queue is a signle-linked list, which also stores the total size of + * objects inside of it. + */ +struct qlist_head { + struct qlist_node *head; + struct qlist_node *tail; + size_t bytes; + bool offline; +}; + +#define QLIST_INIT { NULL, NULL, 0 } + +static bool qlist_empty(struct qlist_head *q) +{ + return !q->head; +} + +static void qlist_init(struct qlist_head *q) +{ + q->head = q->tail = NULL; + q->bytes = 0; +} + +static void qlist_put(struct qlist_head *q, struct qlist_node *qlink, + size_t size) +{ + if (unlikely(qlist_empty(q))) + q->head = qlink; + else + q->tail->next = qlink; + q->tail = qlink; + qlink->next = NULL; + q->bytes += size; +} + +static void qlist_move_all(struct qlist_head *from, struct qlist_head *to) +{ + if (unlikely(qlist_empty(from))) + return; + + if (qlist_empty(to)) { + *to = *from; + qlist_init(from); + return; + } + + to->tail->next = from->head; + to->tail = from->tail; + to->bytes += from->bytes; + + qlist_init(from); +} + +#define QUARANTINE_PERCPU_SIZE (1 << 20) +#define QUARANTINE_BATCHES \ + (1024 > 4 * CONFIG_NR_CPUS ? 1024 : 4 * CONFIG_NR_CPUS) + +/* + * The object quarantine consists of per-cpu queues and a global queue, + * guarded by quarantine_lock. + */ +static DEFINE_PER_CPU(struct qlist_head, cpu_quarantine); + +/* Round-robin FIFO array of batches. */ +static struct qlist_head global_quarantine[QUARANTINE_BATCHES]; +static int quarantine_head; +static int quarantine_tail; +/* Total size of all objects in global_quarantine across all batches. */ +static unsigned long quarantine_size; +static DEFINE_RAW_SPINLOCK(quarantine_lock); +DEFINE_STATIC_SRCU(remove_cache_srcu); + +/* Maximum size of the global queue. */ +static unsigned long quarantine_max_size; + +/* + * Target size of a batch in global_quarantine. + * Usually equal to QUARANTINE_PERCPU_SIZE unless we have too much RAM. + */ +static unsigned long quarantine_batch_size; + +/* + * The fraction of physical memory the quarantine is allowed to occupy. + * Quarantine doesn't support memory shrinker with SLAB allocator, so we keep + * the ratio low to avoid OOM. + */ +#define QUARANTINE_FRACTION 32 + +static struct kmem_cache *qlink_to_cache(struct qlist_node *qlink) +{ + return virt_to_head_page(qlink)->slab_cache; +} + +static void *qlink_to_object(struct qlist_node *qlink, struct kmem_cache *cache) +{ + struct kasan_free_meta *free_info = + container_of(qlink, struct kasan_free_meta, + quarantine_link); + + return ((void *)free_info) - cache->kasan_info.free_meta_offset; +} + +static void qlink_free(struct qlist_node *qlink, struct kmem_cache *cache) +{ + void *object = qlink_to_object(qlink, cache); + unsigned long flags; + + if (IS_ENABLED(CONFIG_SLAB)) + local_irq_save(flags); + + *(u8 *)kasan_mem_to_shadow(object) = KASAN_KMALLOC_FREE; + ___cache_free(cache, object, _THIS_IP_); + + if (IS_ENABLED(CONFIG_SLAB)) + local_irq_restore(flags); +} + +static void qlist_free_all(struct qlist_head *q, struct kmem_cache *cache) +{ + struct qlist_node *qlink; + + if (unlikely(qlist_empty(q))) + return; + + qlink = q->head; + while (qlink) { + struct kmem_cache *obj_cache = + cache ? cache : qlink_to_cache(qlink); + struct qlist_node *next = qlink->next; + + qlink_free(qlink, obj_cache); + qlink = next; + } + qlist_init(q); +} + +void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache) +{ + unsigned long flags; + struct qlist_head *q; + struct qlist_head temp = QLIST_INIT; + + /* + * Note: irq must be disabled until after we move the batch to the + * global quarantine. Otherwise quarantine_remove_cache() can miss + * some objects belonging to the cache if they are in our local temp + * list. quarantine_remove_cache() executes on_each_cpu() at the + * beginning which ensures that it either sees the objects in per-cpu + * lists or in the global quarantine. + */ + local_irq_save(flags); + + q = this_cpu_ptr(&cpu_quarantine); + if (q->offline) { + local_irq_restore(flags); + return; + } + qlist_put(q, &info->quarantine_link, cache->size); + if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE)) { + qlist_move_all(q, &temp); + + raw_spin_lock(&quarantine_lock); + WRITE_ONCE(quarantine_size, quarantine_size + temp.bytes); + qlist_move_all(&temp, &global_quarantine[quarantine_tail]); + if (global_quarantine[quarantine_tail].bytes >= + READ_ONCE(quarantine_batch_size)) { + int new_tail; + + new_tail = quarantine_tail + 1; + if (new_tail == QUARANTINE_BATCHES) + new_tail = 0; + if (new_tail != quarantine_head) + quarantine_tail = new_tail; + } + raw_spin_unlock(&quarantine_lock); + } + + local_irq_restore(flags); +} + +void quarantine_reduce(void) +{ + size_t total_size, new_quarantine_size, percpu_quarantines; + unsigned long flags; + int srcu_idx; + struct qlist_head to_free = QLIST_INIT; + + if (likely(READ_ONCE(quarantine_size) <= + READ_ONCE(quarantine_max_size))) + return; + + /* + * srcu critical section ensures that quarantine_remove_cache() + * will not miss objects belonging to the cache while they are in our + * local to_free list. srcu is chosen because (1) it gives us private + * grace period domain that does not interfere with anything else, + * and (2) it allows synchronize_srcu() to return without waiting + * if there are no pending read critical sections (which is the + * expected case). + */ + srcu_idx = srcu_read_lock(&remove_cache_srcu); + raw_spin_lock_irqsave(&quarantine_lock, flags); + + /* + * Update quarantine size in case of hotplug. Allocate a fraction of + * the installed memory to quarantine minus per-cpu queue limits. + */ + total_size = (totalram_pages() << PAGE_SHIFT) / + QUARANTINE_FRACTION; + percpu_quarantines = QUARANTINE_PERCPU_SIZE * num_online_cpus(); + new_quarantine_size = (total_size < percpu_quarantines) ? + 0 : total_size - percpu_quarantines; + WRITE_ONCE(quarantine_max_size, new_quarantine_size); + /* Aim at consuming at most 1/2 of slots in quarantine. */ + WRITE_ONCE(quarantine_batch_size, max((size_t)QUARANTINE_PERCPU_SIZE, + 2 * total_size / QUARANTINE_BATCHES)); + + if (likely(quarantine_size > quarantine_max_size)) { + qlist_move_all(&global_quarantine[quarantine_head], &to_free); + WRITE_ONCE(quarantine_size, quarantine_size - to_free.bytes); + quarantine_head++; + if (quarantine_head == QUARANTINE_BATCHES) + quarantine_head = 0; + } + + raw_spin_unlock_irqrestore(&quarantine_lock, flags); + + qlist_free_all(&to_free, NULL); + srcu_read_unlock(&remove_cache_srcu, srcu_idx); +} + +static void qlist_move_cache(struct qlist_head *from, + struct qlist_head *to, + struct kmem_cache *cache) +{ + struct qlist_node *curr; + + if (unlikely(qlist_empty(from))) + return; + + curr = from->head; + qlist_init(from); + while (curr) { + struct qlist_node *next = curr->next; + struct kmem_cache *obj_cache = qlink_to_cache(curr); + + if (obj_cache == cache) + qlist_put(to, curr, obj_cache->size); + else + qlist_put(from, curr, obj_cache->size); + + curr = next; + } +} + +static void per_cpu_remove_cache(void *arg) +{ + struct kmem_cache *cache = arg; + struct qlist_head to_free = QLIST_INIT; + struct qlist_head *q; + + q = this_cpu_ptr(&cpu_quarantine); + /* + * Ensure the ordering between the writing to q->offline and + * per_cpu_remove_cache. Prevent cpu_quarantine from being corrupted + * by interrupt. + */ + if (READ_ONCE(q->offline)) + return; + qlist_move_cache(q, &to_free, cache); + qlist_free_all(&to_free, cache); +} + +/* Free all quarantined objects belonging to cache. */ +void quarantine_remove_cache(struct kmem_cache *cache) +{ + unsigned long flags, i; + struct qlist_head to_free = QLIST_INIT; + + /* + * Must be careful to not miss any objects that are being moved from + * per-cpu list to the global quarantine in quarantine_put(), + * nor objects being freed in quarantine_reduce(). on_each_cpu() + * achieves the first goal, while synchronize_srcu() achieves the + * second. + */ + on_each_cpu(per_cpu_remove_cache, cache, 1); + + raw_spin_lock_irqsave(&quarantine_lock, flags); + for (i = 0; i < QUARANTINE_BATCHES; i++) { + if (qlist_empty(&global_quarantine[i])) + continue; + qlist_move_cache(&global_quarantine[i], &to_free, cache); + /* Scanning whole quarantine can take a while. */ + raw_spin_unlock_irqrestore(&quarantine_lock, flags); + cond_resched(); + raw_spin_lock_irqsave(&quarantine_lock, flags); + } + raw_spin_unlock_irqrestore(&quarantine_lock, flags); + + qlist_free_all(&to_free, cache); + + synchronize_srcu(&remove_cache_srcu); +} + +static int kasan_cpu_online(unsigned int cpu) +{ + this_cpu_ptr(&cpu_quarantine)->offline = false; + return 0; +} + +static int kasan_cpu_offline(unsigned int cpu) +{ + struct qlist_head *q; + + q = this_cpu_ptr(&cpu_quarantine); + /* Ensure the ordering between the writing to q->offline and + * qlist_free_all. Otherwise, cpu_quarantine may be corrupted + * by interrupt. + */ + WRITE_ONCE(q->offline, true); + barrier(); + qlist_free_all(q, NULL); + return 0; +} + +static int __init kasan_cpu_quarantine_init(void) +{ + int ret = 0; + + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mm/kasan:online", + kasan_cpu_online, kasan_cpu_offline); + if (ret < 0) + pr_err("kasan cpu quarantine register failed [%d]\n", ret); + return ret; +} +late_initcall(kasan_cpu_quarantine_init); diff --git a/mm/kasan/report.c b/mm/kasan/report.c new file mode 100644 index 000000000..98b08807c --- /dev/null +++ b/mm/kasan/report.c @@ -0,0 +1,599 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This file contains common generic and tag-based KASAN error reporting code. + * + * Copyright (c) 2014 Samsung Electronics Co., Ltd. + * Author: Andrey Ryabinin + * + * Some code borrowed from https://github.com/xairy/kasan-prototype by + * Andrey Konovalov + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include + +#include "kasan.h" +#include "../slab.h" + +/* Shadow layout customization. */ +#define SHADOW_BYTES_PER_BLOCK 1 +#define SHADOW_BLOCKS_PER_ROW 16 +#define SHADOW_BYTES_PER_ROW (SHADOW_BLOCKS_PER_ROW * SHADOW_BYTES_PER_BLOCK) +#define SHADOW_ROWS_AROUND_ADDR 2 + +static unsigned long kasan_flags; + +#define KASAN_BIT_REPORTED 0 +#define KASAN_BIT_MULTI_SHOT 1 + +bool kasan_save_enable_multi_shot(void) +{ + return test_and_set_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags); +} +EXPORT_SYMBOL_GPL(kasan_save_enable_multi_shot); + +void kasan_restore_multi_shot(bool enabled) +{ + if (!enabled) + clear_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags); +} +EXPORT_SYMBOL_GPL(kasan_restore_multi_shot); + +static int __init kasan_set_multi_shot(char *str) +{ + set_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags); + return 1; +} +__setup("kasan_multi_shot", kasan_set_multi_shot); + +static void print_error_description(struct kasan_access_info *info) +{ + pr_err("BUG: KASAN: %s in %pS\n", + get_bug_type(info), (void *)info->ip); + pr_err("%s of size %zu at addr %px by task %s/%d\n", + info->is_write ? "Write" : "Read", info->access_size, + info->access_addr, current->comm, task_pid_nr(current)); +} + +static DEFINE_SPINLOCK(report_lock); + +static void start_report(unsigned long *flags) +{ + /* + * Make sure we don't end up in loop. + */ + kasan_disable_current(); + spin_lock_irqsave(&report_lock, *flags); + pr_err("==================================================================\n"); +} + +static void end_report(unsigned long *flags) +{ + pr_err("==================================================================\n"); + add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); + spin_unlock_irqrestore(&report_lock, *flags); + if (!test_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags)) + check_panic_on_warn("KASAN"); + kasan_enable_current(); +} + +static void print_stack(depot_stack_handle_t stack) +{ + unsigned long *entries; + unsigned int nr_entries; + + nr_entries = stack_depot_fetch(stack, &entries); + stack_trace_print(entries, nr_entries, 0); +} + +static void print_track(struct kasan_track *track, const char *prefix) +{ + pr_err("%s by task %u:\n", prefix, track->pid); + if (track->stack) { + print_stack(track->stack); + } else { + pr_err("(stack is not available)\n"); + } +} + +struct page *kasan_addr_to_page(const void *addr) +{ + if ((addr >= (void *)PAGE_OFFSET) && + (addr < high_memory)) + return virt_to_head_page(addr); + return NULL; +} + +static void describe_object_addr(struct kmem_cache *cache, void *object, + const void *addr) +{ + unsigned long access_addr = (unsigned long)addr; + unsigned long object_addr = (unsigned long)object; + const char *rel_type; + int rel_bytes; + + pr_err("The buggy address belongs to the object at %px\n" + " which belongs to the cache %s of size %d\n", + object, cache->name, cache->object_size); + + if (!addr) + return; + + if (access_addr < object_addr) { + rel_type = "to the left"; + rel_bytes = object_addr - access_addr; + } else if (access_addr >= object_addr + cache->object_size) { + rel_type = "to the right"; + rel_bytes = access_addr - (object_addr + cache->object_size); + } else { + rel_type = "inside"; + rel_bytes = access_addr - object_addr; + } + + pr_err("The buggy address is located %d bytes %s of\n" + " %d-byte region [%px, %px)\n", + rel_bytes, rel_type, cache->object_size, (void *)object_addr, + (void *)(object_addr + cache->object_size)); +} + +static void describe_object(struct kmem_cache *cache, void *object, + const void *addr, u8 tag) +{ + struct kasan_alloc_meta *alloc_info = get_alloc_info(cache, object); + + if (cache->flags & SLAB_KASAN) { + struct kasan_track *free_track; + + print_track(&alloc_info->alloc_track, "Allocated"); + pr_err("\n"); + free_track = kasan_get_free_track(cache, object, tag); + if (free_track) { + print_track(free_track, "Freed"); + pr_err("\n"); + } + +#ifdef CONFIG_KASAN_GENERIC + if (alloc_info->aux_stack[0]) { + pr_err("Last call_rcu():\n"); + print_stack(alloc_info->aux_stack[0]); + pr_err("\n"); + } + if (alloc_info->aux_stack[1]) { + pr_err("Second to last call_rcu():\n"); + print_stack(alloc_info->aux_stack[1]); + pr_err("\n"); + } +#endif + } + + describe_object_addr(cache, object, addr); +} + +static inline bool kernel_or_module_addr(const void *addr) +{ + if (addr >= (void *)_stext && addr < (void *)_end) + return true; + if (is_module_address((unsigned long)addr)) + return true; + return false; +} + +static inline bool init_task_stack_addr(const void *addr) +{ + return addr >= (void *)&init_thread_union.stack && + (addr <= (void *)&init_thread_union.stack + + sizeof(init_thread_union.stack)); +} + +static bool __must_check tokenize_frame_descr(const char **frame_descr, + char *token, size_t max_tok_len, + unsigned long *value) +{ + const char *sep = strchr(*frame_descr, ' '); + + if (sep == NULL) + sep = *frame_descr + strlen(*frame_descr); + + if (token != NULL) { + const size_t tok_len = sep - *frame_descr; + + if (tok_len + 1 > max_tok_len) { + pr_err("KASAN internal error: frame description too long: %s\n", + *frame_descr); + return false; + } + + /* Copy token (+ 1 byte for '\0'). */ + strlcpy(token, *frame_descr, tok_len + 1); + } + + /* Advance frame_descr past separator. */ + *frame_descr = sep + 1; + + if (value != NULL && kstrtoul(token, 10, value)) { + pr_err("KASAN internal error: not a valid number: %s\n", token); + return false; + } + + return true; +} + +static void print_decoded_frame_descr(const char *frame_descr) +{ + /* + * We need to parse the following string: + * "n alloc_1 alloc_2 ... alloc_n" + * where alloc_i looks like + * "offset size len name" + * or "offset size len name:line". + */ + + char token[64]; + unsigned long num_objects; + + if (!tokenize_frame_descr(&frame_descr, token, sizeof(token), + &num_objects)) + return; + + pr_err("\n"); + pr_err("this frame has %lu %s:\n", num_objects, + num_objects == 1 ? "object" : "objects"); + + while (num_objects--) { + unsigned long offset; + unsigned long size; + + /* access offset */ + if (!tokenize_frame_descr(&frame_descr, token, sizeof(token), + &offset)) + return; + /* access size */ + if (!tokenize_frame_descr(&frame_descr, token, sizeof(token), + &size)) + return; + /* name length (unused) */ + if (!tokenize_frame_descr(&frame_descr, NULL, 0, NULL)) + return; + /* object name */ + if (!tokenize_frame_descr(&frame_descr, token, sizeof(token), + NULL)) + return; + + /* Strip line number; without filename it's not very helpful. */ + strreplace(token, ':', '\0'); + + /* Finally, print object information. */ + pr_err(" [%lu, %lu) '%s'", offset, offset + size, token); + } +} + +static bool __must_check get_address_stack_frame_info(const void *addr, + unsigned long *offset, + const char **frame_descr, + const void **frame_pc) +{ + unsigned long aligned_addr; + unsigned long mem_ptr; + const u8 *shadow_bottom; + const u8 *shadow_ptr; + const unsigned long *frame; + + BUILD_BUG_ON(IS_ENABLED(CONFIG_STACK_GROWSUP)); + + /* + * NOTE: We currently only support printing frame information for + * accesses to the task's own stack. + */ + if (!object_is_on_stack(addr)) + return false; + + aligned_addr = round_down((unsigned long)addr, sizeof(long)); + mem_ptr = round_down(aligned_addr, KASAN_SHADOW_SCALE_SIZE); + shadow_ptr = kasan_mem_to_shadow((void *)aligned_addr); + shadow_bottom = kasan_mem_to_shadow(end_of_stack(current)); + + while (shadow_ptr >= shadow_bottom && *shadow_ptr != KASAN_STACK_LEFT) { + shadow_ptr--; + mem_ptr -= KASAN_SHADOW_SCALE_SIZE; + } + + while (shadow_ptr >= shadow_bottom && *shadow_ptr == KASAN_STACK_LEFT) { + shadow_ptr--; + mem_ptr -= KASAN_SHADOW_SCALE_SIZE; + } + + if (shadow_ptr < shadow_bottom) + return false; + + frame = (const unsigned long *)(mem_ptr + KASAN_SHADOW_SCALE_SIZE); + if (frame[0] != KASAN_CURRENT_STACK_FRAME_MAGIC) { + pr_err("KASAN internal error: frame info validation failed; invalid marker: %lu\n", + frame[0]); + return false; + } + + *offset = (unsigned long)addr - (unsigned long)frame; + *frame_descr = (const char *)frame[1]; + *frame_pc = (void *)frame[2]; + + return true; +} + +static void print_address_stack_frame(const void *addr) +{ + unsigned long offset; + const char *frame_descr; + const void *frame_pc; + + if (IS_ENABLED(CONFIG_KASAN_SW_TAGS)) + return; + + if (!get_address_stack_frame_info(addr, &offset, &frame_descr, + &frame_pc)) + return; + + /* + * get_address_stack_frame_info only returns true if the given addr is + * on the current task's stack. + */ + pr_err("\n"); + pr_err("addr %px is located in stack of task %s/%d at offset %lu in frame:\n", + addr, current->comm, task_pid_nr(current), offset); + pr_err(" %pS\n", frame_pc); + + if (!frame_descr) + return; + + print_decoded_frame_descr(frame_descr); +} + +static void print_address_description(void *addr, u8 tag) +{ + struct page *page = kasan_addr_to_page(addr); + + dump_stack(); + pr_err("\n"); + + if (page && PageSlab(page)) { + struct kmem_cache *cache = page->slab_cache; + void *object = nearest_obj(cache, page, addr); + + describe_object(cache, object, addr, tag); + } + + if (kernel_or_module_addr(addr) && !init_task_stack_addr(addr)) { + pr_err("The buggy address belongs to the variable:\n"); + pr_err(" %pS\n", addr); + } + + if (page) { + pr_err("The buggy address belongs to the page:\n"); + dump_page(page, "kasan: bad access detected"); + } + + print_address_stack_frame(addr); +} + +static bool row_is_guilty(const void *row, const void *guilty) +{ + return (row <= guilty) && (guilty < row + SHADOW_BYTES_PER_ROW); +} + +static int shadow_pointer_offset(const void *row, const void *shadow) +{ + /* The length of ">ff00ff00ff00ff00: " is + * 3 + (BITS_PER_LONG/8)*2 chars. + */ + return 3 + (BITS_PER_LONG/8)*2 + (shadow - row)*2 + + (shadow - row) / SHADOW_BYTES_PER_BLOCK + 1; +} + +static void print_shadow_for_address(const void *addr) +{ + int i; + const void *shadow = kasan_mem_to_shadow(addr); + const void *shadow_row; + + shadow_row = (void *)round_down((unsigned long)shadow, + SHADOW_BYTES_PER_ROW) + - SHADOW_ROWS_AROUND_ADDR * SHADOW_BYTES_PER_ROW; + + pr_err("Memory state around the buggy address:\n"); + + for (i = -SHADOW_ROWS_AROUND_ADDR; i <= SHADOW_ROWS_AROUND_ADDR; i++) { + const void *kaddr = kasan_shadow_to_mem(shadow_row); + char buffer[4 + (BITS_PER_LONG/8)*2]; + char shadow_buf[SHADOW_BYTES_PER_ROW]; + + snprintf(buffer, sizeof(buffer), + (i == 0) ? ">%px: " : " %px: ", kaddr); + /* + * We should not pass a shadow pointer to generic + * function, because generic functions may try to + * access kasan mapping for the passed address. + */ + memcpy(shadow_buf, shadow_row, SHADOW_BYTES_PER_ROW); + print_hex_dump(KERN_ERR, buffer, + DUMP_PREFIX_NONE, SHADOW_BYTES_PER_ROW, 1, + shadow_buf, SHADOW_BYTES_PER_ROW, 0); + + if (row_is_guilty(shadow_row, shadow)) + pr_err("%*c\n", + shadow_pointer_offset(shadow_row, shadow), + '^'); + + shadow_row += SHADOW_BYTES_PER_ROW; + } +} + +static bool report_enabled(void) +{ + if (current->kasan_depth) + return false; + if (test_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags)) + return true; + return !test_and_set_bit(KASAN_BIT_REPORTED, &kasan_flags); +} + +#if IS_ENABLED(CONFIG_KUNIT) +static void kasan_update_kunit_status(struct kunit *cur_test) +{ + struct kunit_resource *resource; + struct kunit_kasan_expectation *kasan_data; + + resource = kunit_find_named_resource(cur_test, "kasan_data"); + + if (!resource) { + kunit_set_failure(cur_test); + return; + } + + kasan_data = (struct kunit_kasan_expectation *)resource->data; + kasan_data->report_found = true; + kunit_put_resource(resource); +} +#endif /* IS_ENABLED(CONFIG_KUNIT) */ + +void kasan_report_invalid_free(void *object, unsigned long ip) +{ + unsigned long flags; + u8 tag = get_tag(object); + + object = reset_tag(object); + +#if IS_ENABLED(CONFIG_KUNIT) + if (current->kunit_test) + kasan_update_kunit_status(current->kunit_test); +#endif /* IS_ENABLED(CONFIG_KUNIT) */ + + start_report(&flags); + pr_err("BUG: KASAN: double-free or invalid-free in %pS\n", (void *)ip); + print_tags(tag, object); + pr_err("\n"); + print_address_description(object, tag); + pr_err("\n"); + print_shadow_for_address(object); + end_report(&flags); +} + +static void __kasan_report(unsigned long addr, size_t size, bool is_write, + unsigned long ip) +{ + struct kasan_access_info info; + void *tagged_addr; + void *untagged_addr; + unsigned long flags; + +#if IS_ENABLED(CONFIG_KUNIT) + if (current->kunit_test) + kasan_update_kunit_status(current->kunit_test); +#endif /* IS_ENABLED(CONFIG_KUNIT) */ + + disable_trace_on_warning(); + + tagged_addr = (void *)addr; + untagged_addr = reset_tag(tagged_addr); + + info.access_addr = tagged_addr; + if (addr_has_shadow(untagged_addr)) + info.first_bad_addr = find_first_bad_addr(tagged_addr, size); + else + info.first_bad_addr = untagged_addr; + info.access_size = size; + info.is_write = is_write; + info.ip = ip; + + start_report(&flags); + + print_error_description(&info); + if (addr_has_shadow(untagged_addr)) + print_tags(get_tag(tagged_addr), info.first_bad_addr); + pr_err("\n"); + + if (addr_has_shadow(untagged_addr)) { + print_address_description(untagged_addr, get_tag(tagged_addr)); + pr_err("\n"); + print_shadow_for_address(info.first_bad_addr); + } else { + dump_stack(); + } + + end_report(&flags); +} + +bool kasan_report(unsigned long addr, size_t size, bool is_write, + unsigned long ip) +{ + unsigned long flags = user_access_save(); + bool ret = false; + + if (likely(report_enabled())) { + __kasan_report(addr, size, is_write, ip); + ret = true; + } + + user_access_restore(flags); + + return ret; +} + +/* + * With CONFIG_KASAN, accesses to bogus pointers (outside the high + * canonical half of the address space) cause out-of-bounds shadow memory reads + * before the actual access. For addresses in the low canonical half of the + * address space, as well as most non-canonical addresses, that out-of-bounds + * shadow memory access lands in the non-canonical part of the address space. + * Help the user figure out what the original bogus pointer was. + */ +void kasan_non_canonical_hook(unsigned long addr) +{ + unsigned long orig_addr; + const char *bug_type; + + if (addr < KASAN_SHADOW_OFFSET) + return; + + orig_addr = (addr - KASAN_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT; + /* + * For faults near the shadow address for NULL, we can be fairly certain + * that this is a KASAN shadow memory access. + * For faults that correspond to shadow for low canonical addresses, we + * can still be pretty sure - that shadow region is a fairly narrow + * chunk of the non-canonical address space. + * But faults that look like shadow for non-canonical addresses are a + * really large chunk of the address space. In that case, we still + * print the decoded address, but make it clear that this is not + * necessarily what's actually going on. + */ + if (orig_addr < PAGE_SIZE) + bug_type = "null-ptr-deref"; + else if (orig_addr < TASK_SIZE) + bug_type = "probably user-memory-access"; + else + bug_type = "maybe wild-memory-access"; + pr_alert("KASAN: %s in range [0x%016lx-0x%016lx]\n", bug_type, + orig_addr, orig_addr + KASAN_SHADOW_MASK); +} diff --git a/mm/kasan/tags.c b/mm/kasan/tags.c new file mode 100644 index 000000000..e02a36a51 --- /dev/null +++ b/mm/kasan/tags.c @@ -0,0 +1,200 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This file contains core tag-based KASAN code. + * + * Copyright (c) 2018 Google, Inc. + * Author: Andrey Konovalov + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "kasan.h" +#include "../slab.h" + +static DEFINE_PER_CPU(u32, prng_state); + +void kasan_init_tags(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + per_cpu(prng_state, cpu) = (u32)get_cycles(); +} + +/* + * If a preemption happens between this_cpu_read and this_cpu_write, the only + * side effect is that we'll give a few allocated in different contexts objects + * the same tag. Since tag-based KASAN is meant to be used a probabilistic + * bug-detection debug feature, this doesn't have significant negative impact. + * + * Ideally the tags use strong randomness to prevent any attempts to predict + * them during explicit exploit attempts. But strong randomness is expensive, + * and we did an intentional trade-off to use a PRNG. This non-atomic RMW + * sequence has in fact positive effect, since interrupts that randomly skew + * PRNG at unpredictable points do only good. + */ +u8 random_tag(void) +{ + u32 state = this_cpu_read(prng_state); + + state = 1664525 * state + 1013904223; + this_cpu_write(prng_state, state); + + return (u8)(state % (KASAN_TAG_MAX + 1)); +} + +void *kasan_reset_tag(const void *addr) +{ + return reset_tag(addr); +} + +bool check_memory_region(unsigned long addr, size_t size, bool write, + unsigned long ret_ip) +{ + u8 tag; + u8 *shadow_first, *shadow_last, *shadow; + void *untagged_addr; + + if (unlikely(size == 0)) + return true; + + if (unlikely(addr + size < addr)) + return !kasan_report(addr, size, write, ret_ip); + + tag = get_tag((const void *)addr); + + /* + * Ignore accesses for pointers tagged with 0xff (native kernel + * pointer tag) to suppress false positives caused by kmap. + * + * Some kernel code was written to account for archs that don't keep + * high memory mapped all the time, but rather map and unmap particular + * pages when needed. Instead of storing a pointer to the kernel memory, + * this code saves the address of the page structure and offset within + * that page for later use. Those pages are then mapped and unmapped + * with kmap/kunmap when necessary and virt_to_page is used to get the + * virtual address of the page. For arm64 (that keeps the high memory + * mapped all the time), kmap is turned into a page_address call. + + * The issue is that with use of the page_address + virt_to_page + * sequence the top byte value of the original pointer gets lost (gets + * set to KASAN_TAG_KERNEL (0xFF)). + */ + if (tag == KASAN_TAG_KERNEL) + return true; + + untagged_addr = reset_tag((const void *)addr); + if (unlikely(untagged_addr < + kasan_shadow_to_mem((void *)KASAN_SHADOW_START))) { + return !kasan_report(addr, size, write, ret_ip); + } + shadow_first = kasan_mem_to_shadow(untagged_addr); + shadow_last = kasan_mem_to_shadow(untagged_addr + size - 1); + for (shadow = shadow_first; shadow <= shadow_last; shadow++) { + if (*shadow != tag) { + return !kasan_report(addr, size, write, ret_ip); + } + } + + return true; +} + +#define DEFINE_HWASAN_LOAD_STORE(size) \ + void __hwasan_load##size##_noabort(unsigned long addr) \ + { \ + check_memory_region(addr, size, false, _RET_IP_); \ + } \ + EXPORT_SYMBOL(__hwasan_load##size##_noabort); \ + void __hwasan_store##size##_noabort(unsigned long addr) \ + { \ + check_memory_region(addr, size, true, _RET_IP_); \ + } \ + EXPORT_SYMBOL(__hwasan_store##size##_noabort) + +DEFINE_HWASAN_LOAD_STORE(1); +DEFINE_HWASAN_LOAD_STORE(2); +DEFINE_HWASAN_LOAD_STORE(4); +DEFINE_HWASAN_LOAD_STORE(8); +DEFINE_HWASAN_LOAD_STORE(16); + +void __hwasan_loadN_noabort(unsigned long addr, unsigned long size) +{ + check_memory_region(addr, size, false, _RET_IP_); +} +EXPORT_SYMBOL(__hwasan_loadN_noabort); + +void __hwasan_storeN_noabort(unsigned long addr, unsigned long size) +{ + check_memory_region(addr, size, true, _RET_IP_); +} +EXPORT_SYMBOL(__hwasan_storeN_noabort); + +void __hwasan_tag_memory(unsigned long addr, u8 tag, unsigned long size) +{ + kasan_poison_shadow((void *)addr, size, tag); +} +EXPORT_SYMBOL(__hwasan_tag_memory); + +void kasan_set_free_info(struct kmem_cache *cache, + void *object, u8 tag) +{ + struct kasan_alloc_meta *alloc_meta; + u8 idx = 0; + + alloc_meta = get_alloc_info(cache, object); + +#ifdef CONFIG_KASAN_SW_TAGS_IDENTIFY + idx = alloc_meta->free_track_idx; + alloc_meta->free_pointer_tag[idx] = tag; + alloc_meta->free_track_idx = (idx + 1) % KASAN_NR_FREE_STACKS; +#endif + + kasan_set_track(&alloc_meta->free_track[idx], GFP_NOWAIT); +} + +struct kasan_track *kasan_get_free_track(struct kmem_cache *cache, + void *object, u8 tag) +{ + struct kasan_alloc_meta *alloc_meta; + int i = 0; + + alloc_meta = get_alloc_info(cache, object); + +#ifdef CONFIG_KASAN_SW_TAGS_IDENTIFY + for (i = 0; i < KASAN_NR_FREE_STACKS; i++) { + if (alloc_meta->free_pointer_tag[i] == tag) + break; + } + if (i == KASAN_NR_FREE_STACKS) + i = alloc_meta->free_track_idx; +#endif + + return &alloc_meta->free_track[i]; +} diff --git a/mm/kasan/tags_report.c b/mm/kasan/tags_report.c new file mode 100644 index 000000000..bee43717d --- /dev/null +++ b/mm/kasan/tags_report.c @@ -0,0 +1,93 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This file contains tag-based KASAN specific error reporting code. + * + * Copyright (c) 2014 Samsung Electronics Co., Ltd. + * Author: Andrey Ryabinin + * + * Some code borrowed from https://github.com/xairy/kasan-prototype by + * Andrey Konovalov + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "kasan.h" +#include "../slab.h" + +const char *get_bug_type(struct kasan_access_info *info) +{ +#ifdef CONFIG_KASAN_SW_TAGS_IDENTIFY + struct kasan_alloc_meta *alloc_meta; + struct kmem_cache *cache; + struct page *page; + const void *addr; + void *object; + u8 tag; + int i; + + tag = get_tag(info->access_addr); + addr = reset_tag(info->access_addr); + page = kasan_addr_to_page(addr); + if (page && PageSlab(page)) { + cache = page->slab_cache; + object = nearest_obj(cache, page, (void *)addr); + alloc_meta = get_alloc_info(cache, object); + + for (i = 0; i < KASAN_NR_FREE_STACKS; i++) + if (alloc_meta->free_pointer_tag[i] == tag) + return "use-after-free"; + return "out-of-bounds"; + } + +#endif + /* + * If access_size is a negative number, then it has reason to be + * defined as out-of-bounds bug type. + * + * Casting negative numbers to size_t would indeed turn up as + * a large size_t and its value will be larger than ULONG_MAX/2, + * so that this can qualify as out-of-bounds. + */ + if (info->access_addr + info->access_size < info->access_addr) + return "out-of-bounds"; + + return "invalid-access"; +} + +void *find_first_bad_addr(void *addr, size_t size) +{ + u8 tag = get_tag(addr); + void *p = reset_tag(addr); + void *end = p + size; + + while (p < end && tag == *(u8 *)kasan_mem_to_shadow(p)) + p += KASAN_SHADOW_SCALE_SIZE; + return p; +} + +void print_tags(u8 addr_tag, const void *addr) +{ + u8 *shadow = (u8 *)kasan_mem_to_shadow(addr); + + pr_err("Pointer tag: [%02x], memory tag: [%02x]\n", addr_tag, *shadow); +} diff --git a/mm/khugepaged.c b/mm/khugepaged.c new file mode 100644 index 000000000..28e18777e --- /dev/null +++ b/mm/khugepaged.c @@ -0,0 +1,2400 @@ +// SPDX-License-Identifier: GPL-2.0 +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include "internal.h" + +enum scan_result { + SCAN_FAIL, + SCAN_SUCCEED, + SCAN_PMD_NULL, + SCAN_EXCEED_NONE_PTE, + SCAN_EXCEED_SWAP_PTE, + SCAN_EXCEED_SHARED_PTE, + SCAN_PTE_NON_PRESENT, + SCAN_PTE_UFFD_WP, + SCAN_PAGE_RO, + SCAN_LACK_REFERENCED_PAGE, + SCAN_PAGE_NULL, + SCAN_SCAN_ABORT, + SCAN_PAGE_COUNT, + SCAN_PAGE_LRU, + SCAN_PAGE_LOCK, + SCAN_PAGE_ANON, + SCAN_PAGE_COMPOUND, + SCAN_ANY_PROCESS, + SCAN_VMA_NULL, + SCAN_VMA_CHECK, + SCAN_ADDRESS_RANGE, + SCAN_SWAP_CACHE_PAGE, + SCAN_DEL_PAGE_LRU, + SCAN_ALLOC_HUGE_PAGE_FAIL, + SCAN_CGROUP_CHARGE_FAIL, + SCAN_TRUNCATED, + SCAN_PAGE_HAS_PRIVATE, +}; + +#define CREATE_TRACE_POINTS +#include + +static struct task_struct *khugepaged_thread __read_mostly; +static DEFINE_MUTEX(khugepaged_mutex); + +/* default scan 8*512 pte (or vmas) every 30 second */ +static unsigned int khugepaged_pages_to_scan __read_mostly; +static unsigned int khugepaged_pages_collapsed; +static unsigned int khugepaged_full_scans; +static unsigned int khugepaged_scan_sleep_millisecs __read_mostly = 10000; +/* during fragmentation poll the hugepage allocator once every minute */ +static unsigned int khugepaged_alloc_sleep_millisecs __read_mostly = 60000; +static unsigned long khugepaged_sleep_expire; +static DEFINE_SPINLOCK(khugepaged_mm_lock); +static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait); +/* + * default collapse hugepages if there is at least one pte mapped like + * it would have happened if the vma was large enough during page + * fault. + */ +static unsigned int khugepaged_max_ptes_none __read_mostly; +static unsigned int khugepaged_max_ptes_swap __read_mostly; +static unsigned int khugepaged_max_ptes_shared __read_mostly; + +#define MM_SLOTS_HASH_BITS 10 +static __read_mostly DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS); + +static struct kmem_cache *mm_slot_cache __read_mostly; + +#define MAX_PTE_MAPPED_THP 8 + +/** + * struct mm_slot - hash lookup from mm to mm_slot + * @hash: hash collision list + * @mm_node: khugepaged scan list headed in khugepaged_scan.mm_head + * @mm: the mm that this information is valid for + */ +struct mm_slot { + struct hlist_node hash; + struct list_head mm_node; + struct mm_struct *mm; + + /* pte-mapped THP in this mm */ + int nr_pte_mapped_thp; + unsigned long pte_mapped_thp[MAX_PTE_MAPPED_THP]; +}; + +/** + * struct khugepaged_scan - cursor for scanning + * @mm_head: the head of the mm list to scan + * @mm_slot: the current mm_slot we are scanning + * @address: the next address inside that to be scanned + * + * There is only the one khugepaged_scan instance of this cursor structure. + */ +struct khugepaged_scan { + struct list_head mm_head; + struct mm_slot *mm_slot; + unsigned long address; +}; + +static struct khugepaged_scan khugepaged_scan = { + .mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head), +}; + +#ifdef CONFIG_SYSFS +static ssize_t scan_sleep_millisecs_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", khugepaged_scan_sleep_millisecs); +} + +static ssize_t scan_sleep_millisecs_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + unsigned long msecs; + int err; + + err = kstrtoul(buf, 10, &msecs); + if (err || msecs > UINT_MAX) + return -EINVAL; + + khugepaged_scan_sleep_millisecs = msecs; + khugepaged_sleep_expire = 0; + wake_up_interruptible(&khugepaged_wait); + + return count; +} +static struct kobj_attribute scan_sleep_millisecs_attr = + __ATTR(scan_sleep_millisecs, 0644, scan_sleep_millisecs_show, + scan_sleep_millisecs_store); + +static ssize_t alloc_sleep_millisecs_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", khugepaged_alloc_sleep_millisecs); +} + +static ssize_t alloc_sleep_millisecs_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + unsigned long msecs; + int err; + + err = kstrtoul(buf, 10, &msecs); + if (err || msecs > UINT_MAX) + return -EINVAL; + + khugepaged_alloc_sleep_millisecs = msecs; + khugepaged_sleep_expire = 0; + wake_up_interruptible(&khugepaged_wait); + + return count; +} +static struct kobj_attribute alloc_sleep_millisecs_attr = + __ATTR(alloc_sleep_millisecs, 0644, alloc_sleep_millisecs_show, + alloc_sleep_millisecs_store); + +static ssize_t pages_to_scan_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", khugepaged_pages_to_scan); +} +static ssize_t pages_to_scan_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err; + unsigned long pages; + + err = kstrtoul(buf, 10, &pages); + if (err || !pages || pages > UINT_MAX) + return -EINVAL; + + khugepaged_pages_to_scan = pages; + + return count; +} +static struct kobj_attribute pages_to_scan_attr = + __ATTR(pages_to_scan, 0644, pages_to_scan_show, + pages_to_scan_store); + +static ssize_t pages_collapsed_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", khugepaged_pages_collapsed); +} +static struct kobj_attribute pages_collapsed_attr = + __ATTR_RO(pages_collapsed); + +static ssize_t full_scans_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", khugepaged_full_scans); +} +static struct kobj_attribute full_scans_attr = + __ATTR_RO(full_scans); + +static ssize_t khugepaged_defrag_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return single_hugepage_flag_show(kobj, attr, buf, + TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); +} +static ssize_t khugepaged_defrag_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + return single_hugepage_flag_store(kobj, attr, buf, count, + TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); +} +static struct kobj_attribute khugepaged_defrag_attr = + __ATTR(defrag, 0644, khugepaged_defrag_show, + khugepaged_defrag_store); + +/* + * max_ptes_none controls if khugepaged should collapse hugepages over + * any unmapped ptes in turn potentially increasing the memory + * footprint of the vmas. When max_ptes_none is 0 khugepaged will not + * reduce the available free memory in the system as it + * runs. Increasing max_ptes_none will instead potentially reduce the + * free memory in the system during the khugepaged scan. + */ +static ssize_t khugepaged_max_ptes_none_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", khugepaged_max_ptes_none); +} +static ssize_t khugepaged_max_ptes_none_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err; + unsigned long max_ptes_none; + + err = kstrtoul(buf, 10, &max_ptes_none); + if (err || max_ptes_none > HPAGE_PMD_NR-1) + return -EINVAL; + + khugepaged_max_ptes_none = max_ptes_none; + + return count; +} +static struct kobj_attribute khugepaged_max_ptes_none_attr = + __ATTR(max_ptes_none, 0644, khugepaged_max_ptes_none_show, + khugepaged_max_ptes_none_store); + +static ssize_t khugepaged_max_ptes_swap_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", khugepaged_max_ptes_swap); +} + +static ssize_t khugepaged_max_ptes_swap_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err; + unsigned long max_ptes_swap; + + err = kstrtoul(buf, 10, &max_ptes_swap); + if (err || max_ptes_swap > HPAGE_PMD_NR-1) + return -EINVAL; + + khugepaged_max_ptes_swap = max_ptes_swap; + + return count; +} + +static struct kobj_attribute khugepaged_max_ptes_swap_attr = + __ATTR(max_ptes_swap, 0644, khugepaged_max_ptes_swap_show, + khugepaged_max_ptes_swap_store); + +static ssize_t khugepaged_max_ptes_shared_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", khugepaged_max_ptes_shared); +} + +static ssize_t khugepaged_max_ptes_shared_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err; + unsigned long max_ptes_shared; + + err = kstrtoul(buf, 10, &max_ptes_shared); + if (err || max_ptes_shared > HPAGE_PMD_NR-1) + return -EINVAL; + + khugepaged_max_ptes_shared = max_ptes_shared; + + return count; +} + +static struct kobj_attribute khugepaged_max_ptes_shared_attr = + __ATTR(max_ptes_shared, 0644, khugepaged_max_ptes_shared_show, + khugepaged_max_ptes_shared_store); + +static struct attribute *khugepaged_attr[] = { + &khugepaged_defrag_attr.attr, + &khugepaged_max_ptes_none_attr.attr, + &khugepaged_max_ptes_swap_attr.attr, + &khugepaged_max_ptes_shared_attr.attr, + &pages_to_scan_attr.attr, + &pages_collapsed_attr.attr, + &full_scans_attr.attr, + &scan_sleep_millisecs_attr.attr, + &alloc_sleep_millisecs_attr.attr, + NULL, +}; + +struct attribute_group khugepaged_attr_group = { + .attrs = khugepaged_attr, + .name = "khugepaged", +}; +#endif /* CONFIG_SYSFS */ + +int hugepage_madvise(struct vm_area_struct *vma, + unsigned long *vm_flags, int advice) +{ + switch (advice) { + case MADV_HUGEPAGE: +#ifdef CONFIG_S390 + /* + * qemu blindly sets MADV_HUGEPAGE on all allocations, but s390 + * can't handle this properly after s390_enable_sie, so we simply + * ignore the madvise to prevent qemu from causing a SIGSEGV. + */ + if (mm_has_pgste(vma->vm_mm)) + return 0; +#endif + *vm_flags &= ~VM_NOHUGEPAGE; + *vm_flags |= VM_HUGEPAGE; + /* + * If the vma become good for khugepaged to scan, + * register it here without waiting a page fault that + * may not happen any time soon. + */ + if (!(*vm_flags & VM_NO_KHUGEPAGED) && + khugepaged_enter_vma_merge(vma, *vm_flags)) + return -ENOMEM; + break; + case MADV_NOHUGEPAGE: + *vm_flags &= ~VM_HUGEPAGE; + *vm_flags |= VM_NOHUGEPAGE; + /* + * Setting VM_NOHUGEPAGE will prevent khugepaged from scanning + * this vma even if we leave the mm registered in khugepaged if + * it got registered before VM_NOHUGEPAGE was set. + */ + break; + } + + return 0; +} + +int __init khugepaged_init(void) +{ + mm_slot_cache = kmem_cache_create("khugepaged_mm_slot", + sizeof(struct mm_slot), + __alignof__(struct mm_slot), 0, NULL); + if (!mm_slot_cache) + return -ENOMEM; + + khugepaged_pages_to_scan = HPAGE_PMD_NR * 8; + khugepaged_max_ptes_none = HPAGE_PMD_NR - 1; + khugepaged_max_ptes_swap = HPAGE_PMD_NR / 8; + khugepaged_max_ptes_shared = HPAGE_PMD_NR / 2; + + return 0; +} + +void __init khugepaged_destroy(void) +{ + kmem_cache_destroy(mm_slot_cache); +} + +static inline struct mm_slot *alloc_mm_slot(void) +{ + if (!mm_slot_cache) /* initialization failed */ + return NULL; + return kmem_cache_zalloc(mm_slot_cache, GFP_KERNEL); +} + +static inline void free_mm_slot(struct mm_slot *mm_slot) +{ + kmem_cache_free(mm_slot_cache, mm_slot); +} + +static struct mm_slot *get_mm_slot(struct mm_struct *mm) +{ + struct mm_slot *mm_slot; + + hash_for_each_possible(mm_slots_hash, mm_slot, hash, (unsigned long)mm) + if (mm == mm_slot->mm) + return mm_slot; + + return NULL; +} + +static void insert_to_mm_slots_hash(struct mm_struct *mm, + struct mm_slot *mm_slot) +{ + mm_slot->mm = mm; + hash_add(mm_slots_hash, &mm_slot->hash, (long)mm); +} + +static inline int khugepaged_test_exit(struct mm_struct *mm) +{ + return atomic_read(&mm->mm_users) == 0; +} + +static bool hugepage_vma_check(struct vm_area_struct *vma, + unsigned long vm_flags) +{ + if (!transhuge_vma_enabled(vma, vm_flags)) + return false; + + if (vma->vm_file && !IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - + vma->vm_pgoff, HPAGE_PMD_NR)) + return false; + + /* Enabled via shmem mount options or sysfs settings. */ + if (shmem_file(vma->vm_file)) + return shmem_huge_enabled(vma); + + /* THP settings require madvise. */ + if (!(vm_flags & VM_HUGEPAGE) && !khugepaged_always()) + return false; + + /* Only regular file is valid */ + if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && vma->vm_file && + (vm_flags & VM_DENYWRITE)) { + struct inode *inode = vma->vm_file->f_inode; + + return S_ISREG(inode->i_mode); + } + + if (!vma->anon_vma || vma->vm_ops) + return false; + if (vma_is_temporary_stack(vma)) + return false; + return !(vm_flags & VM_NO_KHUGEPAGED); +} + +int __khugepaged_enter(struct mm_struct *mm) +{ + struct mm_slot *mm_slot; + int wakeup; + + mm_slot = alloc_mm_slot(); + if (!mm_slot) + return -ENOMEM; + + /* __khugepaged_exit() must not run from under us */ + VM_BUG_ON_MM(atomic_read(&mm->mm_users) == 0, mm); + if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags))) { + free_mm_slot(mm_slot); + return 0; + } + + spin_lock(&khugepaged_mm_lock); + insert_to_mm_slots_hash(mm, mm_slot); + /* + * Insert just behind the scanning cursor, to let the area settle + * down a little. + */ + wakeup = list_empty(&khugepaged_scan.mm_head); + list_add_tail(&mm_slot->mm_node, &khugepaged_scan.mm_head); + spin_unlock(&khugepaged_mm_lock); + + mmgrab(mm); + if (wakeup) + wake_up_interruptible(&khugepaged_wait); + + return 0; +} + +int khugepaged_enter_vma_merge(struct vm_area_struct *vma, + unsigned long vm_flags) +{ + unsigned long hstart, hend; + + /* + * khugepaged only supports read-only files for non-shmem files. + * khugepaged does not yet work on special mappings. And + * file-private shmem THP is not supported. + */ + if (!hugepage_vma_check(vma, vm_flags)) + return 0; + + hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; + hend = vma->vm_end & HPAGE_PMD_MASK; + if (hstart < hend) + return khugepaged_enter(vma, vm_flags); + return 0; +} + +void __khugepaged_exit(struct mm_struct *mm) +{ + struct mm_slot *mm_slot; + int free = 0; + + spin_lock(&khugepaged_mm_lock); + mm_slot = get_mm_slot(mm); + if (mm_slot && khugepaged_scan.mm_slot != mm_slot) { + hash_del(&mm_slot->hash); + list_del(&mm_slot->mm_node); + free = 1; + } + spin_unlock(&khugepaged_mm_lock); + + if (free) { + clear_bit(MMF_VM_HUGEPAGE, &mm->flags); + free_mm_slot(mm_slot); + mmdrop(mm); + } else if (mm_slot) { + /* + * This is required to serialize against + * khugepaged_test_exit() (which is guaranteed to run + * under mmap sem read mode). Stop here (after we + * return all pagetables will be destroyed) until + * khugepaged has finished working on the pagetables + * under the mmap_lock. + */ + mmap_write_lock(mm); + mmap_write_unlock(mm); + } +} + +static void release_pte_page(struct page *page) +{ + mod_node_page_state(page_pgdat(page), + NR_ISOLATED_ANON + page_is_file_lru(page), + -compound_nr(page)); + unlock_page(page); + putback_lru_page(page); +} + +static void release_pte_pages(pte_t *pte, pte_t *_pte, + struct list_head *compound_pagelist) +{ + struct page *page, *tmp; + + while (--_pte >= pte) { + pte_t pteval = *_pte; + + page = pte_page(pteval); + if (!pte_none(pteval) && !is_zero_pfn(pte_pfn(pteval)) && + !PageCompound(page)) + release_pte_page(page); + } + + list_for_each_entry_safe(page, tmp, compound_pagelist, lru) { + list_del(&page->lru); + release_pte_page(page); + } +} + +static bool is_refcount_suitable(struct page *page) +{ + int expected_refcount; + + expected_refcount = total_mapcount(page); + if (PageSwapCache(page)) + expected_refcount += compound_nr(page); + + return page_count(page) == expected_refcount; +} + +static int __collapse_huge_page_isolate(struct vm_area_struct *vma, + unsigned long address, + pte_t *pte, + struct list_head *compound_pagelist) +{ + struct page *page = NULL; + pte_t *_pte; + int none_or_zero = 0, shared = 0, result = 0, referenced = 0; + bool writable = false; + + for (_pte = pte; _pte < pte+HPAGE_PMD_NR; + _pte++, address += PAGE_SIZE) { + pte_t pteval = *_pte; + if (pte_none(pteval) || (pte_present(pteval) && + is_zero_pfn(pte_pfn(pteval)))) { + if (!userfaultfd_armed(vma) && + ++none_or_zero <= khugepaged_max_ptes_none) { + continue; + } else { + result = SCAN_EXCEED_NONE_PTE; + goto out; + } + } + if (!pte_present(pteval)) { + result = SCAN_PTE_NON_PRESENT; + goto out; + } + if (pte_uffd_wp(pteval)) { + result = SCAN_PTE_UFFD_WP; + goto out; + } + page = vm_normal_page(vma, address, pteval); + if (unlikely(!page)) { + result = SCAN_PAGE_NULL; + goto out; + } + + VM_BUG_ON_PAGE(!PageAnon(page), page); + + if (page_mapcount(page) > 1 && + ++shared > khugepaged_max_ptes_shared) { + result = SCAN_EXCEED_SHARED_PTE; + goto out; + } + + if (PageCompound(page)) { + struct page *p; + page = compound_head(page); + + /* + * Check if we have dealt with the compound page + * already + */ + list_for_each_entry(p, compound_pagelist, lru) { + if (page == p) + goto next; + } + } + + /* + * We can do it before isolate_lru_page because the + * page can't be freed from under us. NOTE: PG_lock + * is needed to serialize against split_huge_page + * when invoked from the VM. + */ + if (!trylock_page(page)) { + result = SCAN_PAGE_LOCK; + goto out; + } + + /* + * Check if the page has any GUP (or other external) pins. + * + * The page table that maps the page has been already unlinked + * from the page table tree and this process cannot get + * an additinal pin on the page. + * + * New pins can come later if the page is shared across fork, + * but not from this process. The other process cannot write to + * the page, only trigger CoW. + */ + if (!is_refcount_suitable(page)) { + unlock_page(page); + result = SCAN_PAGE_COUNT; + goto out; + } + if (!pte_write(pteval) && PageSwapCache(page) && + !reuse_swap_page(page, NULL)) { + /* + * Page is in the swap cache and cannot be re-used. + * It cannot be collapsed into a THP. + */ + unlock_page(page); + result = SCAN_SWAP_CACHE_PAGE; + goto out; + } + + /* + * Isolate the page to avoid collapsing an hugepage + * currently in use by the VM. + */ + if (isolate_lru_page(page)) { + unlock_page(page); + result = SCAN_DEL_PAGE_LRU; + goto out; + } + mod_node_page_state(page_pgdat(page), + NR_ISOLATED_ANON + page_is_file_lru(page), + compound_nr(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(PageLRU(page), page); + + if (PageCompound(page)) + list_add_tail(&page->lru, compound_pagelist); +next: + /* There should be enough young pte to collapse the page */ + if (pte_young(pteval) || + page_is_young(page) || PageReferenced(page) || + mmu_notifier_test_young(vma->vm_mm, address)) + referenced++; + + if (pte_write(pteval)) + writable = true; + } + + if (unlikely(!writable)) { + result = SCAN_PAGE_RO; + } else if (unlikely(!referenced)) { + result = SCAN_LACK_REFERENCED_PAGE; + } else { + result = SCAN_SUCCEED; + trace_mm_collapse_huge_page_isolate(page, none_or_zero, + referenced, writable, result); + return 1; + } +out: + release_pte_pages(pte, _pte, compound_pagelist); + trace_mm_collapse_huge_page_isolate(page, none_or_zero, + referenced, writable, result); + return 0; +} + +static void __collapse_huge_page_copy(pte_t *pte, struct page *page, + struct vm_area_struct *vma, + unsigned long address, + spinlock_t *ptl, + struct list_head *compound_pagelist) +{ + struct page *src_page, *tmp; + pte_t *_pte; + for (_pte = pte; _pte < pte + HPAGE_PMD_NR; + _pte++, page++, address += PAGE_SIZE) { + pte_t pteval = *_pte; + + if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { + clear_user_highpage(page, address); + add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1); + if (is_zero_pfn(pte_pfn(pteval))) { + /* + * ptl mostly unnecessary. + */ + spin_lock(ptl); + /* + * paravirt calls inside pte_clear here are + * superfluous. + */ + pte_clear(vma->vm_mm, address, _pte); + spin_unlock(ptl); + } + } else { + src_page = pte_page(pteval); + copy_user_highpage(page, src_page, address, vma); + if (!PageCompound(src_page)) + release_pte_page(src_page); + /* + * ptl mostly unnecessary, but preempt has to + * be disabled to update the per-cpu stats + * inside page_remove_rmap(). + */ + spin_lock(ptl); + /* + * paravirt calls inside pte_clear here are + * superfluous. + */ + pte_clear(vma->vm_mm, address, _pte); + page_remove_rmap(src_page, false); + spin_unlock(ptl); + free_page_and_swap_cache(src_page); + } + } + + list_for_each_entry_safe(src_page, tmp, compound_pagelist, lru) { + list_del(&src_page->lru); + release_pte_page(src_page); + } +} + +static void khugepaged_alloc_sleep(void) +{ + DEFINE_WAIT(wait); + + add_wait_queue(&khugepaged_wait, &wait); + freezable_schedule_timeout_interruptible( + msecs_to_jiffies(khugepaged_alloc_sleep_millisecs)); + remove_wait_queue(&khugepaged_wait, &wait); +} + +static int khugepaged_node_load[MAX_NUMNODES]; + +static bool khugepaged_scan_abort(int nid) +{ + int i; + + /* + * If node_reclaim_mode is disabled, then no extra effort is made to + * allocate memory locally. + */ + if (!node_reclaim_mode) + return false; + + /* If there is a count for this node already, it must be acceptable */ + if (khugepaged_node_load[nid]) + return false; + + for (i = 0; i < MAX_NUMNODES; i++) { + if (!khugepaged_node_load[i]) + continue; + if (node_distance(nid, i) > node_reclaim_distance) + return true; + } + return false; +} + +/* Defrag for khugepaged will enter direct reclaim/compaction if necessary */ +static inline gfp_t alloc_hugepage_khugepaged_gfpmask(void) +{ + return khugepaged_defrag() ? GFP_TRANSHUGE : GFP_TRANSHUGE_LIGHT; +} + +#ifdef CONFIG_NUMA +static int khugepaged_find_target_node(void) +{ + static int last_khugepaged_target_node = NUMA_NO_NODE; + int nid, target_node = 0, max_value = 0; + + /* find first node with max normal pages hit */ + for (nid = 0; nid < MAX_NUMNODES; nid++) + if (khugepaged_node_load[nid] > max_value) { + max_value = khugepaged_node_load[nid]; + target_node = nid; + } + + /* do some balance if several nodes have the same hit record */ + if (target_node <= last_khugepaged_target_node) + for (nid = last_khugepaged_target_node + 1; nid < MAX_NUMNODES; + nid++) + if (max_value == khugepaged_node_load[nid]) { + target_node = nid; + break; + } + + last_khugepaged_target_node = target_node; + return target_node; +} + +static bool khugepaged_prealloc_page(struct page **hpage, bool *wait) +{ + if (IS_ERR(*hpage)) { + if (!*wait) + return false; + + *wait = false; + *hpage = NULL; + khugepaged_alloc_sleep(); + } else if (*hpage) { + put_page(*hpage); + *hpage = NULL; + } + + return true; +} + +static struct page * +khugepaged_alloc_page(struct page **hpage, gfp_t gfp, int node) +{ + VM_BUG_ON_PAGE(*hpage, *hpage); + + *hpage = __alloc_pages_node(node, gfp, HPAGE_PMD_ORDER); + if (unlikely(!*hpage)) { + count_vm_event(THP_COLLAPSE_ALLOC_FAILED); + *hpage = ERR_PTR(-ENOMEM); + return NULL; + } + + prep_transhuge_page(*hpage); + count_vm_event(THP_COLLAPSE_ALLOC); + return *hpage; +} +#else +static int khugepaged_find_target_node(void) +{ + return 0; +} + +static inline struct page *alloc_khugepaged_hugepage(void) +{ + struct page *page; + + page = alloc_pages(alloc_hugepage_khugepaged_gfpmask(), + HPAGE_PMD_ORDER); + if (page) + prep_transhuge_page(page); + return page; +} + +static struct page *khugepaged_alloc_hugepage(bool *wait) +{ + struct page *hpage; + + do { + hpage = alloc_khugepaged_hugepage(); + if (!hpage) { + count_vm_event(THP_COLLAPSE_ALLOC_FAILED); + if (!*wait) + return NULL; + + *wait = false; + khugepaged_alloc_sleep(); + } else + count_vm_event(THP_COLLAPSE_ALLOC); + } while (unlikely(!hpage) && likely(khugepaged_enabled())); + + return hpage; +} + +static bool khugepaged_prealloc_page(struct page **hpage, bool *wait) +{ + /* + * If the hpage allocated earlier was briefly exposed in page cache + * before collapse_file() failed, it is possible that racing lookups + * have not yet completed, and would then be unpleasantly surprised by + * finding the hpage reused for the same mapping at a different offset. + * Just release the previous allocation if there is any danger of that. + */ + if (*hpage && page_count(*hpage) > 1) { + put_page(*hpage); + *hpage = NULL; + } + + if (!*hpage) + *hpage = khugepaged_alloc_hugepage(wait); + + if (unlikely(!*hpage)) + return false; + + return true; +} + +static struct page * +khugepaged_alloc_page(struct page **hpage, gfp_t gfp, int node) +{ + VM_BUG_ON(!*hpage); + + return *hpage; +} +#endif + +/* + * If mmap_lock temporarily dropped, revalidate vma + * before taking mmap_lock. + * Return 0 if succeeds, otherwise return none-zero + * value (scan code). + */ + +static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address, + struct vm_area_struct **vmap) +{ + struct vm_area_struct *vma; + unsigned long hstart, hend; + + if (unlikely(khugepaged_test_exit(mm))) + return SCAN_ANY_PROCESS; + + *vmap = vma = find_vma(mm, address); + if (!vma) + return SCAN_VMA_NULL; + + hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; + hend = vma->vm_end & HPAGE_PMD_MASK; + if (address < hstart || address + HPAGE_PMD_SIZE > hend) + return SCAN_ADDRESS_RANGE; + if (!hugepage_vma_check(vma, vma->vm_flags)) + return SCAN_VMA_CHECK; + /* Anon VMA expected */ + if (!vma->anon_vma || vma->vm_ops) + return SCAN_VMA_CHECK; + return 0; +} + +/* + * Bring missing pages in from swap, to complete THP collapse. + * Only done if khugepaged_scan_pmd believes it is worthwhile. + * + * Called and returns without pte mapped or spinlocks held, + * but with mmap_lock held to protect against vma changes. + */ + +static bool __collapse_huge_page_swapin(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long address, pmd_t *pmd, + int referenced) +{ + int swapped_in = 0; + vm_fault_t ret = 0; + struct vm_fault vmf = { + .vma = vma, + .address = address, + .flags = FAULT_FLAG_ALLOW_RETRY, + .pmd = pmd, + .pgoff = linear_page_index(vma, address), + }; + + vmf.pte = pte_offset_map(pmd, address); + for (; vmf.address < address + HPAGE_PMD_NR*PAGE_SIZE; + vmf.pte++, vmf.address += PAGE_SIZE) { + vmf.orig_pte = *vmf.pte; + if (!is_swap_pte(vmf.orig_pte)) + continue; + swapped_in++; + ret = do_swap_page(&vmf); + + /* do_swap_page returns VM_FAULT_RETRY with released mmap_lock */ + if (ret & VM_FAULT_RETRY) { + mmap_read_lock(mm); + if (hugepage_vma_revalidate(mm, address, &vmf.vma)) { + /* vma is no longer available, don't continue to swapin */ + trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0); + return false; + } + /* check if the pmd is still valid */ + if (mm_find_pmd(mm, address) != pmd) { + trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0); + return false; + } + } + if (ret & VM_FAULT_ERROR) { + trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0); + return false; + } + /* pte is unmapped now, we need to map it */ + vmf.pte = pte_offset_map(pmd, vmf.address); + } + vmf.pte--; + pte_unmap(vmf.pte); + + /* Drain LRU add pagevec to remove extra pin on the swapped in pages */ + if (swapped_in) + lru_add_drain(); + + trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 1); + return true; +} + +static void collapse_huge_page(struct mm_struct *mm, + unsigned long address, + struct page **hpage, + int node, int referenced, int unmapped) +{ + LIST_HEAD(compound_pagelist); + pmd_t *pmd, _pmd; + pte_t *pte; + pgtable_t pgtable; + struct page *new_page; + spinlock_t *pmd_ptl, *pte_ptl; + int isolated = 0, result = 0; + struct vm_area_struct *vma; + struct mmu_notifier_range range; + gfp_t gfp; + + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + + /* Only allocate from the target node */ + gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_THISNODE; + + /* + * Before allocating the hugepage, release the mmap_lock read lock. + * The allocation can take potentially a long time if it involves + * sync compaction, and we do not need to hold the mmap_lock during + * that. We will recheck the vma after taking it again in write mode. + */ + mmap_read_unlock(mm); + new_page = khugepaged_alloc_page(hpage, gfp, node); + if (!new_page) { + result = SCAN_ALLOC_HUGE_PAGE_FAIL; + goto out_nolock; + } + + if (unlikely(mem_cgroup_charge(new_page, mm, gfp))) { + result = SCAN_CGROUP_CHARGE_FAIL; + goto out_nolock; + } + count_memcg_page_event(new_page, THP_COLLAPSE_ALLOC); + + mmap_read_lock(mm); + result = hugepage_vma_revalidate(mm, address, &vma); + if (result) { + mmap_read_unlock(mm); + goto out_nolock; + } + + pmd = mm_find_pmd(mm, address); + if (!pmd) { + result = SCAN_PMD_NULL; + mmap_read_unlock(mm); + goto out_nolock; + } + + /* + * __collapse_huge_page_swapin always returns with mmap_lock locked. + * If it fails, we release mmap_lock and jump out_nolock. + * Continuing to collapse causes inconsistency. + */ + if (unmapped && !__collapse_huge_page_swapin(mm, vma, address, + pmd, referenced)) { + mmap_read_unlock(mm); + goto out_nolock; + } + + mmap_read_unlock(mm); + /* + * Prevent all access to pagetables with the exception of + * gup_fast later handled by the ptep_clear_flush and the VM + * handled by the anon_vma lock + PG_lock. + */ + mmap_write_lock(mm); + result = hugepage_vma_revalidate(mm, address, &vma); + if (result) + goto out; + /* check if the pmd is still valid */ + if (mm_find_pmd(mm, address) != pmd) + goto out; + + anon_vma_lock_write(vma->anon_vma); + + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm, + address, address + HPAGE_PMD_SIZE); + mmu_notifier_invalidate_range_start(&range); + + pte = pte_offset_map(pmd, address); + pte_ptl = pte_lockptr(mm, pmd); + + pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */ + /* + * This removes any huge TLB entry from the CPU so we won't allow + * huge and small TLB entries for the same virtual address to + * avoid the risk of CPU bugs in that area. + * + * Parallel fast GUP is fine since fast GUP will back off when + * it detects PMD is changed. + */ + _pmd = pmdp_collapse_flush(vma, address, pmd); + spin_unlock(pmd_ptl); + mmu_notifier_invalidate_range_end(&range); + tlb_remove_table_sync_one(); + + spin_lock(pte_ptl); + isolated = __collapse_huge_page_isolate(vma, address, pte, + &compound_pagelist); + spin_unlock(pte_ptl); + + if (unlikely(!isolated)) { + pte_unmap(pte); + spin_lock(pmd_ptl); + BUG_ON(!pmd_none(*pmd)); + /* + * We can only use set_pmd_at when establishing + * hugepmds and never for establishing regular pmds that + * points to regular pagetables. Use pmd_populate for that + */ + pmd_populate(mm, pmd, pmd_pgtable(_pmd)); + spin_unlock(pmd_ptl); + anon_vma_unlock_write(vma->anon_vma); + result = SCAN_FAIL; + goto out; + } + + /* + * All pages are isolated and locked so anon_vma rmap + * can't run anymore. + */ + anon_vma_unlock_write(vma->anon_vma); + + __collapse_huge_page_copy(pte, new_page, vma, address, pte_ptl, + &compound_pagelist); + pte_unmap(pte); + __SetPageUptodate(new_page); + pgtable = pmd_pgtable(_pmd); + + _pmd = mk_huge_pmd(new_page, vma->vm_page_prot); + _pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma); + + /* + * spin_lock() below is not the equivalent of smp_wmb(), so + * this is needed to avoid the copy_huge_page writes to become + * visible after the set_pmd_at() write. + */ + smp_wmb(); + + spin_lock(pmd_ptl); + BUG_ON(!pmd_none(*pmd)); + page_add_new_anon_rmap(new_page, vma, address, true); + lru_cache_add_inactive_or_unevictable(new_page, vma); + pgtable_trans_huge_deposit(mm, pmd, pgtable); + set_pmd_at(mm, address, pmd, _pmd); + update_mmu_cache_pmd(vma, address, pmd); + spin_unlock(pmd_ptl); + + *hpage = NULL; + + khugepaged_pages_collapsed++; + result = SCAN_SUCCEED; +out_up_write: + mmap_write_unlock(mm); +out_nolock: + if (!IS_ERR_OR_NULL(*hpage)) + mem_cgroup_uncharge(*hpage); + trace_mm_collapse_huge_page(mm, isolated, result); + return; +out: + goto out_up_write; +} + +static int khugepaged_scan_pmd(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long address, + struct page **hpage) +{ + pmd_t *pmd; + pte_t *pte, *_pte; + int ret = 0, result = 0, referenced = 0; + int none_or_zero = 0, shared = 0; + struct page *page = NULL; + unsigned long _address; + spinlock_t *ptl; + int node = NUMA_NO_NODE, unmapped = 0; + bool writable = false; + + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + + pmd = mm_find_pmd(mm, address); + if (!pmd) { + result = SCAN_PMD_NULL; + goto out; + } + + memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load)); + pte = pte_offset_map_lock(mm, pmd, address, &ptl); + for (_address = address, _pte = pte; _pte < pte+HPAGE_PMD_NR; + _pte++, _address += PAGE_SIZE) { + pte_t pteval = *_pte; + if (is_swap_pte(pteval)) { + if (++unmapped <= khugepaged_max_ptes_swap) { + /* + * Always be strict with uffd-wp + * enabled swap entries. Please see + * comment below for pte_uffd_wp(). + */ + if (pte_swp_uffd_wp(pteval)) { + result = SCAN_PTE_UFFD_WP; + goto out_unmap; + } + continue; + } else { + result = SCAN_EXCEED_SWAP_PTE; + goto out_unmap; + } + } + if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { + if (!userfaultfd_armed(vma) && + ++none_or_zero <= khugepaged_max_ptes_none) { + continue; + } else { + result = SCAN_EXCEED_NONE_PTE; + goto out_unmap; + } + } + if (!pte_present(pteval)) { + result = SCAN_PTE_NON_PRESENT; + goto out_unmap; + } + if (pte_uffd_wp(pteval)) { + /* + * Don't collapse the page if any of the small + * PTEs are armed with uffd write protection. + * Here we can also mark the new huge pmd as + * write protected if any of the small ones is + * marked but that could bring uknown + * userfault messages that falls outside of + * the registered range. So, just be simple. + */ + result = SCAN_PTE_UFFD_WP; + goto out_unmap; + } + if (pte_write(pteval)) + writable = true; + + page = vm_normal_page(vma, _address, pteval); + if (unlikely(!page)) { + result = SCAN_PAGE_NULL; + goto out_unmap; + } + + if (page_mapcount(page) > 1 && + ++shared > khugepaged_max_ptes_shared) { + result = SCAN_EXCEED_SHARED_PTE; + goto out_unmap; + } + + page = compound_head(page); + + /* + * Record which node the original page is from and save this + * information to khugepaged_node_load[]. + * Khupaged will allocate hugepage from the node has the max + * hit record. + */ + node = page_to_nid(page); + if (khugepaged_scan_abort(node)) { + result = SCAN_SCAN_ABORT; + goto out_unmap; + } + khugepaged_node_load[node]++; + if (!PageLRU(page)) { + result = SCAN_PAGE_LRU; + goto out_unmap; + } + if (PageLocked(page)) { + result = SCAN_PAGE_LOCK; + goto out_unmap; + } + if (!PageAnon(page)) { + result = SCAN_PAGE_ANON; + goto out_unmap; + } + + /* + * Check if the page has any GUP (or other external) pins. + * + * Here the check is racy it may see totmal_mapcount > refcount + * in some cases. + * For example, one process with one forked child process. + * The parent has the PMD split due to MADV_DONTNEED, then + * the child is trying unmap the whole PMD, but khugepaged + * may be scanning the parent between the child has + * PageDoubleMap flag cleared and dec the mapcount. So + * khugepaged may see total_mapcount > refcount. + * + * But such case is ephemeral we could always retry collapse + * later. However it may report false positive if the page + * has excessive GUP pins (i.e. 512). Anyway the same check + * will be done again later the risk seems low. + */ + if (!is_refcount_suitable(page)) { + result = SCAN_PAGE_COUNT; + goto out_unmap; + } + if (pte_young(pteval) || + page_is_young(page) || PageReferenced(page) || + mmu_notifier_test_young(vma->vm_mm, address)) + referenced++; + } + if (!writable) { + result = SCAN_PAGE_RO; + } else if (!referenced || (unmapped && referenced < HPAGE_PMD_NR/2)) { + result = SCAN_LACK_REFERENCED_PAGE; + } else { + result = SCAN_SUCCEED; + ret = 1; + } +out_unmap: + pte_unmap_unlock(pte, ptl); + if (ret) { + node = khugepaged_find_target_node(); + /* collapse_huge_page will return with the mmap_lock released */ + collapse_huge_page(mm, address, hpage, node, + referenced, unmapped); + } +out: + trace_mm_khugepaged_scan_pmd(mm, page, writable, referenced, + none_or_zero, result, unmapped); + return ret; +} + +static void collect_mm_slot(struct mm_slot *mm_slot) +{ + struct mm_struct *mm = mm_slot->mm; + + lockdep_assert_held(&khugepaged_mm_lock); + + if (khugepaged_test_exit(mm)) { + /* free mm_slot */ + hash_del(&mm_slot->hash); + list_del(&mm_slot->mm_node); + + /* + * Not strictly needed because the mm exited already. + * + * clear_bit(MMF_VM_HUGEPAGE, &mm->flags); + */ + + /* khugepaged_mm_lock actually not necessary for the below */ + free_mm_slot(mm_slot); + mmdrop(mm); + } +} + +#ifdef CONFIG_SHMEM +/* + * Notify khugepaged that given addr of the mm is pte-mapped THP. Then + * khugepaged should try to collapse the page table. + */ +static int khugepaged_add_pte_mapped_thp(struct mm_struct *mm, + unsigned long addr) +{ + struct mm_slot *mm_slot; + + VM_BUG_ON(addr & ~HPAGE_PMD_MASK); + + spin_lock(&khugepaged_mm_lock); + mm_slot = get_mm_slot(mm); + if (likely(mm_slot && mm_slot->nr_pte_mapped_thp < MAX_PTE_MAPPED_THP)) + mm_slot->pte_mapped_thp[mm_slot->nr_pte_mapped_thp++] = addr; + spin_unlock(&khugepaged_mm_lock); + return 0; +} + +/** + * Try to collapse a pte-mapped THP for mm at address haddr. + * + * This function checks whether all the PTEs in the PMD are pointing to the + * right THP. If so, retract the page table so the THP can refault in with + * as pmd-mapped. + */ +void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr) +{ + unsigned long haddr = addr & HPAGE_PMD_MASK; + struct vm_area_struct *vma = find_vma(mm, haddr); + struct page *hpage; + pte_t *start_pte, *pte; + pmd_t *pmd, _pmd; + spinlock_t *ptl; + int count = 0; + int i; + struct mmu_notifier_range range; + + if (!vma || !vma->vm_file || + vma->vm_start > haddr || vma->vm_end < haddr + HPAGE_PMD_SIZE) + return; + + /* + * This vm_flags may not have VM_HUGEPAGE if the page was not + * collapsed by this mm. But we can still collapse if the page is + * the valid THP. Add extra VM_HUGEPAGE so hugepage_vma_check() + * will not fail the vma for missing VM_HUGEPAGE + */ + if (!hugepage_vma_check(vma, vma->vm_flags | VM_HUGEPAGE)) + return; + + hpage = find_lock_page(vma->vm_file->f_mapping, + linear_page_index(vma, haddr)); + if (!hpage) + return; + + if (!PageHead(hpage)) + goto drop_hpage; + + pmd = mm_find_pmd(mm, haddr); + if (!pmd) + goto drop_hpage; + + /* + * We need to lock the mapping so that from here on, only GUP-fast and + * hardware page walks can access the parts of the page tables that + * we're operating on. + */ + i_mmap_lock_write(vma->vm_file->f_mapping); + + /* + * This spinlock should be unnecessary: Nobody else should be accessing + * the page tables under spinlock protection here, only + * lockless_pages_from_mm() and the hardware page walker can access page + * tables while all the high-level locks are held in write mode. + */ + start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl); + + /* step 1: check all mapped PTEs are to the right huge page */ + for (i = 0, addr = haddr, pte = start_pte; + i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) { + struct page *page; + + /* empty pte, skip */ + if (pte_none(*pte)) + continue; + + /* page swapped out, abort */ + if (!pte_present(*pte)) + goto abort; + + page = vm_normal_page(vma, addr, *pte); + + /* + * Note that uprobe, debugger, or MAP_PRIVATE may change the + * page table, but the new page will not be a subpage of hpage. + */ + if (hpage + i != page) + goto abort; + count++; + } + + /* step 2: adjust rmap */ + for (i = 0, addr = haddr, pte = start_pte; + i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) { + struct page *page; + + if (pte_none(*pte)) + continue; + page = vm_normal_page(vma, addr, *pte); + page_remove_rmap(page, false); + } + + pte_unmap_unlock(start_pte, ptl); + + /* step 3: set proper refcount and mm_counters. */ + if (count) { + page_ref_sub(hpage, count); + add_mm_counter(vma->vm_mm, mm_counter_file(hpage), -count); + } + + /* step 4: collapse pmd */ + /* we make no change to anon, but protect concurrent anon page lookup */ + if (vma->anon_vma) + anon_vma_lock_write(vma->anon_vma); + + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm, haddr, + haddr + HPAGE_PMD_SIZE); + mmu_notifier_invalidate_range_start(&range); + _pmd = pmdp_collapse_flush(vma, haddr, pmd); + mm_dec_nr_ptes(mm); + tlb_remove_table_sync_one(); + mmu_notifier_invalidate_range_end(&range); + pte_free(mm, pmd_pgtable(_pmd)); + + if (vma->anon_vma) + anon_vma_unlock_write(vma->anon_vma); + i_mmap_unlock_write(vma->vm_file->f_mapping); + +drop_hpage: + unlock_page(hpage); + put_page(hpage); + return; + +abort: + pte_unmap_unlock(start_pte, ptl); + i_mmap_unlock_write(vma->vm_file->f_mapping); + goto drop_hpage; +} + +static int khugepaged_collapse_pte_mapped_thps(struct mm_slot *mm_slot) +{ + struct mm_struct *mm = mm_slot->mm; + int i; + + if (likely(mm_slot->nr_pte_mapped_thp == 0)) + return 0; + + if (!mmap_write_trylock(mm)) + return -EBUSY; + + if (unlikely(khugepaged_test_exit(mm))) + goto out; + + for (i = 0; i < mm_slot->nr_pte_mapped_thp; i++) + collapse_pte_mapped_thp(mm, mm_slot->pte_mapped_thp[i]); + +out: + mm_slot->nr_pte_mapped_thp = 0; + mmap_write_unlock(mm); + return 0; +} + +static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff) +{ + struct vm_area_struct *vma; + struct mm_struct *mm; + unsigned long addr; + pmd_t *pmd, _pmd; + + i_mmap_lock_write(mapping); + vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { + /* + * Check vma->anon_vma to exclude MAP_PRIVATE mappings that + * got written to. These VMAs are likely not worth investing + * mmap_write_lock(mm) as PMD-mapping is likely to be split + * later. + * + * Not that vma->anon_vma check is racy: it can be set up after + * the check but before we took mmap_lock by the fault path. + * But page lock would prevent establishing any new ptes of the + * page, so we are safe. + * + * An alternative would be drop the check, but check that page + * table is clear before calling pmdp_collapse_flush() under + * ptl. It has higher chance to recover THP for the VMA, but + * has higher cost too. It would also probably require locking + * the anon_vma. + */ + if (vma->anon_vma) + continue; + addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); + if (addr & ~HPAGE_PMD_MASK) + continue; + if (vma->vm_end < addr + HPAGE_PMD_SIZE) + continue; + mm = vma->vm_mm; + pmd = mm_find_pmd(mm, addr); + if (!pmd) + continue; + /* + * We need exclusive mmap_lock to retract page table. + * + * We use trylock due to lock inversion: we need to acquire + * mmap_lock while holding page lock. Fault path does it in + * reverse order. Trylock is a way to avoid deadlock. + */ + if (mmap_write_trylock(mm)) { + if (!khugepaged_test_exit(mm)) { + struct mmu_notifier_range range; + + mmu_notifier_range_init(&range, + MMU_NOTIFY_CLEAR, 0, + NULL, mm, addr, + addr + HPAGE_PMD_SIZE); + mmu_notifier_invalidate_range_start(&range); + /* assume page table is clear */ + _pmd = pmdp_collapse_flush(vma, addr, pmd); + mm_dec_nr_ptes(mm); + tlb_remove_table_sync_one(); + pte_free(mm, pmd_pgtable(_pmd)); + mmu_notifier_invalidate_range_end(&range); + } + mmap_write_unlock(mm); + } else { + /* Try again later */ + khugepaged_add_pte_mapped_thp(mm, addr); + } + } + i_mmap_unlock_write(mapping); +} + +/** + * collapse_file - collapse filemap/tmpfs/shmem pages into huge one. + * + * Basic scheme is simple, details are more complex: + * - allocate and lock a new huge page; + * - scan page cache replacing old pages with the new one + * + swap/gup in pages if necessary; + * + fill in gaps; + * + keep old pages around in case rollback is required; + * - if replacing succeeds: + * + copy data over; + * + free old pages; + * + unlock huge page; + * - if replacing failed; + * + put all pages back and unfreeze them; + * + restore gaps in the page cache; + * + unlock and free huge page; + */ +static void collapse_file(struct mm_struct *mm, + struct file *file, pgoff_t start, + struct page **hpage, int node) +{ + struct address_space *mapping = file->f_mapping; + gfp_t gfp; + struct page *new_page; + pgoff_t index, end = start + HPAGE_PMD_NR; + LIST_HEAD(pagelist); + XA_STATE_ORDER(xas, &mapping->i_pages, start, HPAGE_PMD_ORDER); + int nr_none = 0, result = SCAN_SUCCEED; + bool is_shmem = shmem_file(file); + + VM_BUG_ON(!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !is_shmem); + VM_BUG_ON(start & (HPAGE_PMD_NR - 1)); + + /* Only allocate from the target node */ + gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_THISNODE; + + new_page = khugepaged_alloc_page(hpage, gfp, node); + if (!new_page) { + result = SCAN_ALLOC_HUGE_PAGE_FAIL; + goto out; + } + + if (unlikely(mem_cgroup_charge(new_page, mm, gfp))) { + result = SCAN_CGROUP_CHARGE_FAIL; + goto out; + } + count_memcg_page_event(new_page, THP_COLLAPSE_ALLOC); + + /* This will be less messy when we use multi-index entries */ + do { + xas_lock_irq(&xas); + xas_create_range(&xas); + if (!xas_error(&xas)) + break; + xas_unlock_irq(&xas); + if (!xas_nomem(&xas, GFP_KERNEL)) { + result = SCAN_FAIL; + goto out; + } + } while (1); + + __SetPageLocked(new_page); + if (is_shmem) + __SetPageSwapBacked(new_page); + new_page->index = start; + new_page->mapping = mapping; + + /* + * At this point the new_page is locked and not up-to-date. + * It's safe to insert it into the page cache, because nobody would + * be able to map it or use it in another way until we unlock it. + */ + + xas_set(&xas, start); + for (index = start; index < end; index++) { + struct page *page = xas_next(&xas); + + VM_BUG_ON(index != xas.xa_index); + if (is_shmem) { + if (!page) { + /* + * Stop if extent has been truncated or + * hole-punched, and is now completely + * empty. + */ + if (index == start) { + if (!xas_next_entry(&xas, end - 1)) { + result = SCAN_TRUNCATED; + goto xa_locked; + } + xas_set(&xas, index); + } + if (!shmem_charge(mapping->host, 1)) { + result = SCAN_FAIL; + goto xa_locked; + } + xas_store(&xas, new_page); + nr_none++; + continue; + } + + if (xa_is_value(page) || !PageUptodate(page)) { + xas_unlock_irq(&xas); + /* swap in or instantiate fallocated page */ + if (shmem_getpage(mapping->host, index, &page, + SGP_NOHUGE)) { + result = SCAN_FAIL; + goto xa_unlocked; + } + } else if (trylock_page(page)) { + get_page(page); + xas_unlock_irq(&xas); + } else { + result = SCAN_PAGE_LOCK; + goto xa_locked; + } + } else { /* !is_shmem */ + if (!page || xa_is_value(page)) { + xas_unlock_irq(&xas); + page_cache_sync_readahead(mapping, &file->f_ra, + file, index, + end - index); + /* drain pagevecs to help isolate_lru_page() */ + lru_add_drain(); + page = find_lock_page(mapping, index); + if (unlikely(page == NULL)) { + result = SCAN_FAIL; + goto xa_unlocked; + } + } else if (PageDirty(page)) { + /* + * khugepaged only works on read-only fd, + * so this page is dirty because it hasn't + * been flushed since first write. There + * won't be new dirty pages. + * + * Trigger async flush here and hope the + * writeback is done when khugepaged + * revisits this page. + * + * This is a one-off situation. We are not + * forcing writeback in loop. + */ + xas_unlock_irq(&xas); + filemap_flush(mapping); + result = SCAN_FAIL; + goto xa_unlocked; + } else if (PageWriteback(page)) { + xas_unlock_irq(&xas); + result = SCAN_FAIL; + goto xa_unlocked; + } else if (trylock_page(page)) { + get_page(page); + xas_unlock_irq(&xas); + } else { + result = SCAN_PAGE_LOCK; + goto xa_locked; + } + } + + /* + * The page must be locked, so we can drop the i_pages lock + * without racing with truncate. + */ + VM_BUG_ON_PAGE(!PageLocked(page), page); + + /* make sure the page is up to date */ + if (unlikely(!PageUptodate(page))) { + result = SCAN_FAIL; + goto out_unlock; + } + + /* + * If file was truncated then extended, or hole-punched, before + * we locked the first page, then a THP might be there already. + */ + if (PageTransCompound(page)) { + result = SCAN_PAGE_COMPOUND; + goto out_unlock; + } + + if (page_mapping(page) != mapping) { + result = SCAN_TRUNCATED; + goto out_unlock; + } + + if (!is_shmem && (PageDirty(page) || + PageWriteback(page))) { + /* + * khugepaged only works on read-only fd, so this + * page is dirty because it hasn't been flushed + * since first write. + */ + result = SCAN_FAIL; + goto out_unlock; + } + + if (isolate_lru_page(page)) { + result = SCAN_DEL_PAGE_LRU; + goto out_unlock; + } + + if (page_has_private(page) && + !try_to_release_page(page, GFP_KERNEL)) { + result = SCAN_PAGE_HAS_PRIVATE; + putback_lru_page(page); + goto out_unlock; + } + + if (page_mapped(page)) + unmap_mapping_pages(mapping, index, 1, false); + + xas_lock_irq(&xas); + xas_set(&xas, index); + + VM_BUG_ON_PAGE(page != xas_load(&xas), page); + VM_BUG_ON_PAGE(page_mapped(page), page); + + /* + * The page is expected to have page_count() == 3: + * - we hold a pin on it; + * - one reference from page cache; + * - one from isolate_lru_page; + */ + if (!page_ref_freeze(page, 3)) { + result = SCAN_PAGE_COUNT; + xas_unlock_irq(&xas); + putback_lru_page(page); + goto out_unlock; + } + + /* + * Add the page to the list to be able to undo the collapse if + * something go wrong. + */ + list_add_tail(&page->lru, &pagelist); + + /* Finally, replace with the new page. */ + xas_store(&xas, new_page); + continue; +out_unlock: + unlock_page(page); + put_page(page); + goto xa_unlocked; + } + + if (is_shmem) + __inc_node_page_state(new_page, NR_SHMEM_THPS); + else { + __inc_node_page_state(new_page, NR_FILE_THPS); + filemap_nr_thps_inc(mapping); + } + + if (nr_none) { + __mod_lruvec_page_state(new_page, NR_FILE_PAGES, nr_none); + if (is_shmem) + __mod_lruvec_page_state(new_page, NR_SHMEM, nr_none); + } + +xa_locked: + xas_unlock_irq(&xas); +xa_unlocked: + + if (result == SCAN_SUCCEED) { + struct page *page, *tmp; + + /* + * Replacing old pages with new one has succeeded, now we + * need to copy the content and free the old pages. + */ + index = start; + list_for_each_entry_safe(page, tmp, &pagelist, lru) { + while (index < page->index) { + clear_highpage(new_page + (index % HPAGE_PMD_NR)); + index++; + } + copy_highpage(new_page + (page->index % HPAGE_PMD_NR), + page); + list_del(&page->lru); + page->mapping = NULL; + page_ref_unfreeze(page, 1); + ClearPageActive(page); + ClearPageUnevictable(page); + unlock_page(page); + put_page(page); + index++; + } + while (index < end) { + clear_highpage(new_page + (index % HPAGE_PMD_NR)); + index++; + } + + SetPageUptodate(new_page); + page_ref_add(new_page, HPAGE_PMD_NR - 1); + if (is_shmem) + set_page_dirty(new_page); + lru_cache_add(new_page); + + /* + * Remove pte page tables, so we can re-fault the page as huge. + */ + retract_page_tables(mapping, start); + *hpage = NULL; + + khugepaged_pages_collapsed++; + } else { + struct page *page; + + /* Something went wrong: roll back page cache changes */ + xas_lock_irq(&xas); + mapping->nrpages -= nr_none; + + if (is_shmem) + shmem_uncharge(mapping->host, nr_none); + + xas_set(&xas, start); + xas_for_each(&xas, page, end - 1) { + page = list_first_entry_or_null(&pagelist, + struct page, lru); + if (!page || xas.xa_index < page->index) { + if (!nr_none) + break; + nr_none--; + /* Put holes back where they were */ + xas_store(&xas, NULL); + continue; + } + + VM_BUG_ON_PAGE(page->index != xas.xa_index, page); + + /* Unfreeze the page. */ + list_del(&page->lru); + page_ref_unfreeze(page, 2); + xas_store(&xas, page); + xas_pause(&xas); + xas_unlock_irq(&xas); + unlock_page(page); + putback_lru_page(page); + xas_lock_irq(&xas); + } + VM_BUG_ON(nr_none); + xas_unlock_irq(&xas); + + new_page->mapping = NULL; + } + + unlock_page(new_page); +out: + VM_BUG_ON(!list_empty(&pagelist)); + if (!IS_ERR_OR_NULL(*hpage)) + mem_cgroup_uncharge(*hpage); + /* TODO: tracepoints */ +} + +static void khugepaged_scan_file(struct mm_struct *mm, + struct file *file, pgoff_t start, struct page **hpage) +{ + struct page *page = NULL; + struct address_space *mapping = file->f_mapping; + XA_STATE(xas, &mapping->i_pages, start); + int present, swap; + int node = NUMA_NO_NODE; + int result = SCAN_SUCCEED; + + present = 0; + swap = 0; + memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load)); + rcu_read_lock(); + xas_for_each(&xas, page, start + HPAGE_PMD_NR - 1) { + if (xas_retry(&xas, page)) + continue; + + if (xa_is_value(page)) { + if (++swap > khugepaged_max_ptes_swap) { + result = SCAN_EXCEED_SWAP_PTE; + break; + } + continue; + } + + if (PageTransCompound(page)) { + result = SCAN_PAGE_COMPOUND; + break; + } + + node = page_to_nid(page); + if (khugepaged_scan_abort(node)) { + result = SCAN_SCAN_ABORT; + break; + } + khugepaged_node_load[node]++; + + if (!PageLRU(page)) { + result = SCAN_PAGE_LRU; + break; + } + + if (page_count(page) != + 1 + page_mapcount(page) + page_has_private(page)) { + result = SCAN_PAGE_COUNT; + break; + } + + /* + * We probably should check if the page is referenced here, but + * nobody would transfer pte_young() to PageReferenced() for us. + * And rmap walk here is just too costly... + */ + + present++; + + if (need_resched()) { + xas_pause(&xas); + cond_resched_rcu(); + } + } + rcu_read_unlock(); + + if (result == SCAN_SUCCEED) { + if (present < HPAGE_PMD_NR - khugepaged_max_ptes_none) { + result = SCAN_EXCEED_NONE_PTE; + } else { + node = khugepaged_find_target_node(); + collapse_file(mm, file, start, hpage, node); + } + } + + /* TODO: tracepoints */ +} +#else +static void khugepaged_scan_file(struct mm_struct *mm, + struct file *file, pgoff_t start, struct page **hpage) +{ + BUILD_BUG(); +} + +static int khugepaged_collapse_pte_mapped_thps(struct mm_slot *mm_slot) +{ + return 0; +} +#endif + +static unsigned int khugepaged_scan_mm_slot(unsigned int pages, + struct page **hpage) + __releases(&khugepaged_mm_lock) + __acquires(&khugepaged_mm_lock) +{ + struct mm_slot *mm_slot; + struct mm_struct *mm; + struct vm_area_struct *vma; + int progress = 0; + + VM_BUG_ON(!pages); + lockdep_assert_held(&khugepaged_mm_lock); + + if (khugepaged_scan.mm_slot) + mm_slot = khugepaged_scan.mm_slot; + else { + mm_slot = list_entry(khugepaged_scan.mm_head.next, + struct mm_slot, mm_node); + khugepaged_scan.address = 0; + khugepaged_scan.mm_slot = mm_slot; + } + spin_unlock(&khugepaged_mm_lock); + khugepaged_collapse_pte_mapped_thps(mm_slot); + + mm = mm_slot->mm; + /* + * Don't wait for semaphore (to avoid long wait times). Just move to + * the next mm on the list. + */ + vma = NULL; + if (unlikely(!mmap_read_trylock(mm))) + goto breakouterloop_mmap_lock; + if (likely(!khugepaged_test_exit(mm))) + vma = find_vma(mm, khugepaged_scan.address); + + progress++; + for (; vma; vma = vma->vm_next) { + unsigned long hstart, hend; + + cond_resched(); + if (unlikely(khugepaged_test_exit(mm))) { + progress++; + break; + } + if (!hugepage_vma_check(vma, vma->vm_flags)) { +skip: + progress++; + continue; + } + hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; + hend = vma->vm_end & HPAGE_PMD_MASK; + if (hstart >= hend) + goto skip; + if (khugepaged_scan.address > hend) + goto skip; + if (khugepaged_scan.address < hstart) + khugepaged_scan.address = hstart; + VM_BUG_ON(khugepaged_scan.address & ~HPAGE_PMD_MASK); + if (shmem_file(vma->vm_file) && !shmem_huge_enabled(vma)) + goto skip; + + while (khugepaged_scan.address < hend) { + int ret; + cond_resched(); + if (unlikely(khugepaged_test_exit(mm))) + goto breakouterloop; + + VM_BUG_ON(khugepaged_scan.address < hstart || + khugepaged_scan.address + HPAGE_PMD_SIZE > + hend); + if (IS_ENABLED(CONFIG_SHMEM) && vma->vm_file) { + struct file *file = get_file(vma->vm_file); + pgoff_t pgoff = linear_page_index(vma, + khugepaged_scan.address); + + mmap_read_unlock(mm); + ret = 1; + khugepaged_scan_file(mm, file, pgoff, hpage); + fput(file); + } else { + ret = khugepaged_scan_pmd(mm, vma, + khugepaged_scan.address, + hpage); + } + /* move to next address */ + khugepaged_scan.address += HPAGE_PMD_SIZE; + progress += HPAGE_PMD_NR; + if (ret) + /* we released mmap_lock so break loop */ + goto breakouterloop_mmap_lock; + if (progress >= pages) + goto breakouterloop; + } + } +breakouterloop: + mmap_read_unlock(mm); /* exit_mmap will destroy ptes after this */ +breakouterloop_mmap_lock: + + spin_lock(&khugepaged_mm_lock); + VM_BUG_ON(khugepaged_scan.mm_slot != mm_slot); + /* + * Release the current mm_slot if this mm is about to die, or + * if we scanned all vmas of this mm. + */ + if (khugepaged_test_exit(mm) || !vma) { + /* + * Make sure that if mm_users is reaching zero while + * khugepaged runs here, khugepaged_exit will find + * mm_slot not pointing to the exiting mm. + */ + if (mm_slot->mm_node.next != &khugepaged_scan.mm_head) { + khugepaged_scan.mm_slot = list_entry( + mm_slot->mm_node.next, + struct mm_slot, mm_node); + khugepaged_scan.address = 0; + } else { + khugepaged_scan.mm_slot = NULL; + khugepaged_full_scans++; + } + + collect_mm_slot(mm_slot); + } + + return progress; +} + +static int khugepaged_has_work(void) +{ + return !list_empty(&khugepaged_scan.mm_head) && + khugepaged_enabled(); +} + +static int khugepaged_wait_event(void) +{ + return !list_empty(&khugepaged_scan.mm_head) || + kthread_should_stop(); +} + +static void khugepaged_do_scan(void) +{ + struct page *hpage = NULL; + unsigned int progress = 0, pass_through_head = 0; + unsigned int pages = khugepaged_pages_to_scan; + bool wait = true; + + barrier(); /* write khugepaged_pages_to_scan to local stack */ + + lru_add_drain_all(); + + while (progress < pages) { + if (!khugepaged_prealloc_page(&hpage, &wait)) + break; + + cond_resched(); + + if (unlikely(kthread_should_stop() || try_to_freeze())) + break; + + spin_lock(&khugepaged_mm_lock); + if (!khugepaged_scan.mm_slot) + pass_through_head++; + if (khugepaged_has_work() && + pass_through_head < 2) + progress += khugepaged_scan_mm_slot(pages - progress, + &hpage); + else + progress = pages; + spin_unlock(&khugepaged_mm_lock); + } + + if (!IS_ERR_OR_NULL(hpage)) + put_page(hpage); +} + +static bool khugepaged_should_wakeup(void) +{ + return kthread_should_stop() || + time_after_eq(jiffies, khugepaged_sleep_expire); +} + +static void khugepaged_wait_work(void) +{ + if (khugepaged_has_work()) { + const unsigned long scan_sleep_jiffies = + msecs_to_jiffies(khugepaged_scan_sleep_millisecs); + + if (!scan_sleep_jiffies) + return; + + khugepaged_sleep_expire = jiffies + scan_sleep_jiffies; + wait_event_freezable_timeout(khugepaged_wait, + khugepaged_should_wakeup(), + scan_sleep_jiffies); + return; + } + + if (khugepaged_enabled()) + wait_event_freezable(khugepaged_wait, khugepaged_wait_event()); +} + +static int khugepaged(void *none) +{ + struct mm_slot *mm_slot; + + set_freezable(); + set_user_nice(current, MAX_NICE); + + while (!kthread_should_stop()) { + khugepaged_do_scan(); + khugepaged_wait_work(); + } + + spin_lock(&khugepaged_mm_lock); + mm_slot = khugepaged_scan.mm_slot; + khugepaged_scan.mm_slot = NULL; + if (mm_slot) + collect_mm_slot(mm_slot); + spin_unlock(&khugepaged_mm_lock); + return 0; +} + +static void set_recommended_min_free_kbytes(void) +{ + struct zone *zone; + int nr_zones = 0; + unsigned long recommended_min; + + for_each_populated_zone(zone) { + /* + * We don't need to worry about fragmentation of + * ZONE_MOVABLE since it only has movable pages. + */ + if (zone_idx(zone) > gfp_zone(GFP_USER)) + continue; + + nr_zones++; + } + + /* Ensure 2 pageblocks are free to assist fragmentation avoidance */ + recommended_min = pageblock_nr_pages * nr_zones * 2; + + /* + * Make sure that on average at least two pageblocks are almost free + * of another type, one for a migratetype to fall back to and a + * second to avoid subsequent fallbacks of other types There are 3 + * MIGRATE_TYPES we care about. + */ + recommended_min += pageblock_nr_pages * nr_zones * + MIGRATE_PCPTYPES * MIGRATE_PCPTYPES; + + /* don't ever allow to reserve more than 5% of the lowmem */ + recommended_min = min(recommended_min, + (unsigned long) nr_free_buffer_pages() / 20); + recommended_min <<= (PAGE_SHIFT-10); + + if (recommended_min > min_free_kbytes) { + if (user_min_free_kbytes >= 0) + pr_info("raising min_free_kbytes from %d to %lu to help transparent hugepage allocations\n", + min_free_kbytes, recommended_min); + + min_free_kbytes = recommended_min; + } + setup_per_zone_wmarks(); +} + +int start_stop_khugepaged(void) +{ + int err = 0; + + mutex_lock(&khugepaged_mutex); + if (khugepaged_enabled()) { + if (!khugepaged_thread) + khugepaged_thread = kthread_run(khugepaged, NULL, + "khugepaged"); + if (IS_ERR(khugepaged_thread)) { + pr_err("khugepaged: kthread_run(khugepaged) failed\n"); + err = PTR_ERR(khugepaged_thread); + khugepaged_thread = NULL; + goto fail; + } + + if (!list_empty(&khugepaged_scan.mm_head)) + wake_up_interruptible(&khugepaged_wait); + + set_recommended_min_free_kbytes(); + } else if (khugepaged_thread) { + kthread_stop(khugepaged_thread); + khugepaged_thread = NULL; + } +fail: + mutex_unlock(&khugepaged_mutex); + return err; +} + +void khugepaged_min_free_kbytes_update(void) +{ + mutex_lock(&khugepaged_mutex); + if (khugepaged_enabled() && khugepaged_thread) + set_recommended_min_free_kbytes(); + mutex_unlock(&khugepaged_mutex); +} diff --git a/mm/kmemleak.c b/mm/kmemleak.c new file mode 100644 index 000000000..4801751cb --- /dev/null +++ b/mm/kmemleak.c @@ -0,0 +1,1995 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * mm/kmemleak.c + * + * Copyright (C) 2008 ARM Limited + * Written by Catalin Marinas + * + * For more information on the algorithm and kmemleak usage, please see + * Documentation/dev-tools/kmemleak.rst. + * + * Notes on locking + * ---------------- + * + * The following locks and mutexes are used by kmemleak: + * + * - kmemleak_lock (raw_spinlock_t): protects the object_list modifications and + * accesses to the object_tree_root. The object_list is the main list + * holding the metadata (struct kmemleak_object) for the allocated memory + * blocks. The object_tree_root is a red black tree used to look-up + * metadata based on a pointer to the corresponding memory block. The + * kmemleak_object structures are added to the object_list and + * object_tree_root in the create_object() function called from the + * kmemleak_alloc() callback and removed in delete_object() called from the + * kmemleak_free() callback + * - kmemleak_object.lock (raw_spinlock_t): protects a kmemleak_object. + * Accesses to the metadata (e.g. count) are protected by this lock. Note + * that some members of this structure may be protected by other means + * (atomic or kmemleak_lock). This lock is also held when scanning the + * corresponding memory block to avoid the kernel freeing it via the + * kmemleak_free() callback. This is less heavyweight than holding a global + * lock like kmemleak_lock during scanning. + * - scan_mutex (mutex): ensures that only one thread may scan the memory for + * unreferenced objects at a time. The gray_list contains the objects which + * are already referenced or marked as false positives and need to be + * scanned. This list is only modified during a scanning episode when the + * scan_mutex is held. At the end of a scan, the gray_list is always empty. + * Note that the kmemleak_object.use_count is incremented when an object is + * added to the gray_list and therefore cannot be freed. This mutex also + * prevents multiple users of the "kmemleak" debugfs file together with + * modifications to the memory scanning parameters including the scan_thread + * pointer + * + * Locks and mutexes are acquired/nested in the following order: + * + * scan_mutex [-> object->lock] -> kmemleak_lock -> other_object->lock (SINGLE_DEPTH_NESTING) + * + * No kmemleak_lock and object->lock nesting is allowed outside scan_mutex + * regions. + * + * The kmemleak_object structures have a use_count incremented or decremented + * using the get_object()/put_object() functions. When the use_count becomes + * 0, this count can no longer be incremented and put_object() schedules the + * kmemleak_object freeing via an RCU callback. All calls to the get_object() + * function must be protected by rcu_read_lock() to avoid accessing a freed + * structure. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +#include +#include +#include + +/* + * Kmemleak configuration and common defines. + */ +#define MAX_TRACE 16 /* stack trace length */ +#define MSECS_MIN_AGE 5000 /* minimum object age for reporting */ +#define SECS_FIRST_SCAN 60 /* delay before the first scan */ +#define SECS_SCAN_WAIT 600 /* subsequent auto scanning delay */ +#define MAX_SCAN_SIZE 4096 /* maximum size of a scanned block */ + +#define BYTES_PER_POINTER sizeof(void *) + +/* GFP bitmask for kmemleak internal allocations */ +#define gfp_kmemleak_mask(gfp) (((gfp) & (GFP_KERNEL | GFP_ATOMIC)) | \ + __GFP_NORETRY | __GFP_NOMEMALLOC | \ + __GFP_NOWARN) + +/* scanning area inside a memory block */ +struct kmemleak_scan_area { + struct hlist_node node; + unsigned long start; + size_t size; +}; + +#define KMEMLEAK_GREY 0 +#define KMEMLEAK_BLACK -1 + +/* + * Structure holding the metadata for each allocated memory block. + * Modifications to such objects should be made while holding the + * object->lock. Insertions or deletions from object_list, gray_list or + * rb_node are already protected by the corresponding locks or mutex (see + * the notes on locking above). These objects are reference-counted + * (use_count) and freed using the RCU mechanism. + */ +struct kmemleak_object { + raw_spinlock_t lock; + unsigned int flags; /* object status flags */ + struct list_head object_list; + struct list_head gray_list; + struct rb_node rb_node; + struct rcu_head rcu; /* object_list lockless traversal */ + /* object usage count; object freed when use_count == 0 */ + atomic_t use_count; + unsigned long pointer; + size_t size; + /* pass surplus references to this pointer */ + unsigned long excess_ref; + /* minimum number of a pointers found before it is considered leak */ + int min_count; + /* the total number of pointers found pointing to this object */ + int count; + /* checksum for detecting modified objects */ + u32 checksum; + /* memory ranges to be scanned inside an object (empty for all) */ + struct hlist_head area_list; + unsigned long trace[MAX_TRACE]; + unsigned int trace_len; + unsigned long jiffies; /* creation timestamp */ + pid_t pid; /* pid of the current task */ + char comm[TASK_COMM_LEN]; /* executable name */ +}; + +/* flag representing the memory block allocation status */ +#define OBJECT_ALLOCATED (1 << 0) +/* flag set after the first reporting of an unreference object */ +#define OBJECT_REPORTED (1 << 1) +/* flag set to not scan the object */ +#define OBJECT_NO_SCAN (1 << 2) +/* flag set to fully scan the object when scan_area allocation failed */ +#define OBJECT_FULL_SCAN (1 << 3) + +#define HEX_PREFIX " " +/* number of bytes to print per line; must be 16 or 32 */ +#define HEX_ROW_SIZE 16 +/* number of bytes to print at a time (1, 2, 4, 8) */ +#define HEX_GROUP_SIZE 1 +/* include ASCII after the hex output */ +#define HEX_ASCII 1 +/* max number of lines to be printed */ +#define HEX_MAX_LINES 2 + +/* the list of all allocated objects */ +static LIST_HEAD(object_list); +/* the list of gray-colored objects (see color_gray comment below) */ +static LIST_HEAD(gray_list); +/* memory pool allocation */ +static struct kmemleak_object mem_pool[CONFIG_DEBUG_KMEMLEAK_MEM_POOL_SIZE]; +static int mem_pool_free_count = ARRAY_SIZE(mem_pool); +static LIST_HEAD(mem_pool_free_list); +/* search tree for object boundaries */ +static struct rb_root object_tree_root = RB_ROOT; +/* protecting the access to object_list and object_tree_root */ +static DEFINE_RAW_SPINLOCK(kmemleak_lock); + +/* allocation caches for kmemleak internal data */ +static struct kmem_cache *object_cache; +static struct kmem_cache *scan_area_cache; + +/* set if tracing memory operations is enabled */ +static int kmemleak_enabled = 1; +/* same as above but only for the kmemleak_free() callback */ +static int kmemleak_free_enabled = 1; +/* set in the late_initcall if there were no errors */ +static int kmemleak_initialized; +/* set if a kmemleak warning was issued */ +static int kmemleak_warning; +/* set if a fatal kmemleak error has occurred */ +static int kmemleak_error; + +/* minimum and maximum address that may be valid pointers */ +static unsigned long min_addr = ULONG_MAX; +static unsigned long max_addr; + +static struct task_struct *scan_thread; +/* used to avoid reporting of recently allocated objects */ +static unsigned long jiffies_min_age; +static unsigned long jiffies_last_scan; +/* delay between automatic memory scannings */ +static signed long jiffies_scan_wait; +/* enables or disables the task stacks scanning */ +static int kmemleak_stack_scan = 1; +/* protects the memory scanning, parameters and debug/kmemleak file access */ +static DEFINE_MUTEX(scan_mutex); +/* setting kmemleak=on, will set this var, skipping the disable */ +static int kmemleak_skip_disable; +/* If there are leaks that can be reported */ +static bool kmemleak_found_leaks; + +static bool kmemleak_verbose; +module_param_named(verbose, kmemleak_verbose, bool, 0600); + +static void kmemleak_disable(void); + +/* + * Print a warning and dump the stack trace. + */ +#define kmemleak_warn(x...) do { \ + pr_warn(x); \ + dump_stack(); \ + kmemleak_warning = 1; \ +} while (0) + +/* + * Macro invoked when a serious kmemleak condition occurred and cannot be + * recovered from. Kmemleak will be disabled and further allocation/freeing + * tracing no longer available. + */ +#define kmemleak_stop(x...) do { \ + kmemleak_warn(x); \ + kmemleak_disable(); \ +} while (0) + +#define warn_or_seq_printf(seq, fmt, ...) do { \ + if (seq) \ + seq_printf(seq, fmt, ##__VA_ARGS__); \ + else \ + pr_warn(fmt, ##__VA_ARGS__); \ +} while (0) + +static void warn_or_seq_hex_dump(struct seq_file *seq, int prefix_type, + int rowsize, int groupsize, const void *buf, + size_t len, bool ascii) +{ + if (seq) + seq_hex_dump(seq, HEX_PREFIX, prefix_type, rowsize, groupsize, + buf, len, ascii); + else + print_hex_dump(KERN_WARNING, pr_fmt(HEX_PREFIX), prefix_type, + rowsize, groupsize, buf, len, ascii); +} + +/* + * Printing of the objects hex dump to the seq file. The number of lines to be + * printed is limited to HEX_MAX_LINES to prevent seq file spamming. The + * actual number of printed bytes depends on HEX_ROW_SIZE. It must be called + * with the object->lock held. + */ +static void hex_dump_object(struct seq_file *seq, + struct kmemleak_object *object) +{ + const u8 *ptr = (const u8 *)object->pointer; + size_t len; + + /* limit the number of lines to HEX_MAX_LINES */ + len = min_t(size_t, object->size, HEX_MAX_LINES * HEX_ROW_SIZE); + + warn_or_seq_printf(seq, " hex dump (first %zu bytes):\n", len); + kasan_disable_current(); + warn_or_seq_hex_dump(seq, DUMP_PREFIX_NONE, HEX_ROW_SIZE, + HEX_GROUP_SIZE, ptr, len, HEX_ASCII); + kasan_enable_current(); +} + +/* + * Object colors, encoded with count and min_count: + * - white - orphan object, not enough references to it (count < min_count) + * - gray - not orphan, not marked as false positive (min_count == 0) or + * sufficient references to it (count >= min_count) + * - black - ignore, it doesn't contain references (e.g. text section) + * (min_count == -1). No function defined for this color. + * Newly created objects don't have any color assigned (object->count == -1) + * before the next memory scan when they become white. + */ +static bool color_white(const struct kmemleak_object *object) +{ + return object->count != KMEMLEAK_BLACK && + object->count < object->min_count; +} + +static bool color_gray(const struct kmemleak_object *object) +{ + return object->min_count != KMEMLEAK_BLACK && + object->count >= object->min_count; +} + +/* + * Objects are considered unreferenced only if their color is white, they have + * not be deleted and have a minimum age to avoid false positives caused by + * pointers temporarily stored in CPU registers. + */ +static bool unreferenced_object(struct kmemleak_object *object) +{ + return (color_white(object) && object->flags & OBJECT_ALLOCATED) && + time_before_eq(object->jiffies + jiffies_min_age, + jiffies_last_scan); +} + +/* + * Printing of the unreferenced objects information to the seq file. The + * print_unreferenced function must be called with the object->lock held. + */ +static void print_unreferenced(struct seq_file *seq, + struct kmemleak_object *object) +{ + int i; + unsigned int msecs_age = jiffies_to_msecs(jiffies - object->jiffies); + + warn_or_seq_printf(seq, "unreferenced object 0x%08lx (size %zu):\n", + object->pointer, object->size); + warn_or_seq_printf(seq, " comm \"%s\", pid %d, jiffies %lu (age %d.%03ds)\n", + object->comm, object->pid, object->jiffies, + msecs_age / 1000, msecs_age % 1000); + hex_dump_object(seq, object); + warn_or_seq_printf(seq, " backtrace:\n"); + + for (i = 0; i < object->trace_len; i++) { + void *ptr = (void *)object->trace[i]; + warn_or_seq_printf(seq, " [<%p>] %pS\n", ptr, ptr); + } +} + +/* + * Print the kmemleak_object information. This function is used mainly for + * debugging special cases when kmemleak operations. It must be called with + * the object->lock held. + */ +static void dump_object_info(struct kmemleak_object *object) +{ + pr_notice("Object 0x%08lx (size %zu):\n", + object->pointer, object->size); + pr_notice(" comm \"%s\", pid %d, jiffies %lu\n", + object->comm, object->pid, object->jiffies); + pr_notice(" min_count = %d\n", object->min_count); + pr_notice(" count = %d\n", object->count); + pr_notice(" flags = 0x%x\n", object->flags); + pr_notice(" checksum = %u\n", object->checksum); + pr_notice(" backtrace:\n"); + stack_trace_print(object->trace, object->trace_len, 4); +} + +/* + * Look-up a memory block metadata (kmemleak_object) in the object search + * tree based on a pointer value. If alias is 0, only values pointing to the + * beginning of the memory block are allowed. The kmemleak_lock must be held + * when calling this function. + */ +static struct kmemleak_object *lookup_object(unsigned long ptr, int alias) +{ + struct rb_node *rb = object_tree_root.rb_node; + + while (rb) { + struct kmemleak_object *object = + rb_entry(rb, struct kmemleak_object, rb_node); + if (ptr < object->pointer) + rb = object->rb_node.rb_left; + else if (object->pointer + object->size <= ptr) + rb = object->rb_node.rb_right; + else if (object->pointer == ptr || alias) + return object; + else { + kmemleak_warn("Found object by alias at 0x%08lx\n", + ptr); + dump_object_info(object); + break; + } + } + return NULL; +} + +/* + * Increment the object use_count. Return 1 if successful or 0 otherwise. Note + * that once an object's use_count reached 0, the RCU freeing was already + * registered and the object should no longer be used. This function must be + * called under the protection of rcu_read_lock(). + */ +static int get_object(struct kmemleak_object *object) +{ + return atomic_inc_not_zero(&object->use_count); +} + +/* + * Memory pool allocation and freeing. kmemleak_lock must not be held. + */ +static struct kmemleak_object *mem_pool_alloc(gfp_t gfp) +{ + unsigned long flags; + struct kmemleak_object *object; + + /* try the slab allocator first */ + if (object_cache) { + object = kmem_cache_alloc(object_cache, gfp_kmemleak_mask(gfp)); + if (object) + return object; + } + + /* slab allocation failed, try the memory pool */ + raw_spin_lock_irqsave(&kmemleak_lock, flags); + object = list_first_entry_or_null(&mem_pool_free_list, + typeof(*object), object_list); + if (object) + list_del(&object->object_list); + else if (mem_pool_free_count) + object = &mem_pool[--mem_pool_free_count]; + else + pr_warn_once("Memory pool empty, consider increasing CONFIG_DEBUG_KMEMLEAK_MEM_POOL_SIZE\n"); + raw_spin_unlock_irqrestore(&kmemleak_lock, flags); + + return object; +} + +/* + * Return the object to either the slab allocator or the memory pool. + */ +static void mem_pool_free(struct kmemleak_object *object) +{ + unsigned long flags; + + if (object < mem_pool || object >= mem_pool + ARRAY_SIZE(mem_pool)) { + kmem_cache_free(object_cache, object); + return; + } + + /* add the object to the memory pool free list */ + raw_spin_lock_irqsave(&kmemleak_lock, flags); + list_add(&object->object_list, &mem_pool_free_list); + raw_spin_unlock_irqrestore(&kmemleak_lock, flags); +} + +/* + * RCU callback to free a kmemleak_object. + */ +static void free_object_rcu(struct rcu_head *rcu) +{ + struct hlist_node *tmp; + struct kmemleak_scan_area *area; + struct kmemleak_object *object = + container_of(rcu, struct kmemleak_object, rcu); + + /* + * Once use_count is 0 (guaranteed by put_object), there is no other + * code accessing this object, hence no need for locking. + */ + hlist_for_each_entry_safe(area, tmp, &object->area_list, node) { + hlist_del(&area->node); + kmem_cache_free(scan_area_cache, area); + } + mem_pool_free(object); +} + +/* + * Decrement the object use_count. Once the count is 0, free the object using + * an RCU callback. Since put_object() may be called via the kmemleak_free() -> + * delete_object() path, the delayed RCU freeing ensures that there is no + * recursive call to the kernel allocator. Lock-less RCU object_list traversal + * is also possible. + */ +static void put_object(struct kmemleak_object *object) +{ + if (!atomic_dec_and_test(&object->use_count)) + return; + + /* should only get here after delete_object was called */ + WARN_ON(object->flags & OBJECT_ALLOCATED); + + /* + * It may be too early for the RCU callbacks, however, there is no + * concurrent object_list traversal when !object_cache and all objects + * came from the memory pool. Free the object directly. + */ + if (object_cache) + call_rcu(&object->rcu, free_object_rcu); + else + free_object_rcu(&object->rcu); +} + +/* + * Look up an object in the object search tree and increase its use_count. + */ +static struct kmemleak_object *find_and_get_object(unsigned long ptr, int alias) +{ + unsigned long flags; + struct kmemleak_object *object; + + rcu_read_lock(); + raw_spin_lock_irqsave(&kmemleak_lock, flags); + object = lookup_object(ptr, alias); + raw_spin_unlock_irqrestore(&kmemleak_lock, flags); + + /* check whether the object is still available */ + if (object && !get_object(object)) + object = NULL; + rcu_read_unlock(); + + return object; +} + +/* + * Remove an object from the object_tree_root and object_list. Must be called + * with the kmemleak_lock held _if_ kmemleak is still enabled. + */ +static void __remove_object(struct kmemleak_object *object) +{ + rb_erase(&object->rb_node, &object_tree_root); + list_del_rcu(&object->object_list); +} + +/* + * Look up an object in the object search tree and remove it from both + * object_tree_root and object_list. The returned object's use_count should be + * at least 1, as initially set by create_object(). + */ +static struct kmemleak_object *find_and_remove_object(unsigned long ptr, int alias) +{ + unsigned long flags; + struct kmemleak_object *object; + + raw_spin_lock_irqsave(&kmemleak_lock, flags); + object = lookup_object(ptr, alias); + if (object) + __remove_object(object); + raw_spin_unlock_irqrestore(&kmemleak_lock, flags); + + return object; +} + +/* + * Save stack trace to the given array of MAX_TRACE size. + */ +static int __save_stack_trace(unsigned long *trace) +{ + return stack_trace_save(trace, MAX_TRACE, 2); +} + +/* + * Create the metadata (struct kmemleak_object) corresponding to an allocated + * memory block and add it to the object_list and object_tree_root. + */ +static struct kmemleak_object *create_object(unsigned long ptr, size_t size, + int min_count, gfp_t gfp) +{ + unsigned long flags; + struct kmemleak_object *object, *parent; + struct rb_node **link, *rb_parent; + unsigned long untagged_ptr; + + object = mem_pool_alloc(gfp); + if (!object) { + pr_warn("Cannot allocate a kmemleak_object structure\n"); + kmemleak_disable(); + return NULL; + } + + INIT_LIST_HEAD(&object->object_list); + INIT_LIST_HEAD(&object->gray_list); + INIT_HLIST_HEAD(&object->area_list); + raw_spin_lock_init(&object->lock); + atomic_set(&object->use_count, 1); + object->flags = OBJECT_ALLOCATED; + object->pointer = ptr; + object->size = size; + object->excess_ref = 0; + object->min_count = min_count; + object->count = 0; /* white color initially */ + object->jiffies = jiffies; + object->checksum = 0; + + /* task information */ + if (in_irq()) { + object->pid = 0; + strncpy(object->comm, "hardirq", sizeof(object->comm)); + } else if (in_serving_softirq()) { + object->pid = 0; + strncpy(object->comm, "softirq", sizeof(object->comm)); + } else { + object->pid = current->pid; + /* + * There is a small chance of a race with set_task_comm(), + * however using get_task_comm() here may cause locking + * dependency issues with current->alloc_lock. In the worst + * case, the command line is not correct. + */ + strncpy(object->comm, current->comm, sizeof(object->comm)); + } + + /* kernel backtrace */ + object->trace_len = __save_stack_trace(object->trace); + + raw_spin_lock_irqsave(&kmemleak_lock, flags); + + untagged_ptr = (unsigned long)kasan_reset_tag((void *)ptr); + min_addr = min(min_addr, untagged_ptr); + max_addr = max(max_addr, untagged_ptr + size); + link = &object_tree_root.rb_node; + rb_parent = NULL; + while (*link) { + rb_parent = *link; + parent = rb_entry(rb_parent, struct kmemleak_object, rb_node); + if (ptr + size <= parent->pointer) + link = &parent->rb_node.rb_left; + else if (parent->pointer + parent->size <= ptr) + link = &parent->rb_node.rb_right; + else { + kmemleak_stop("Cannot insert 0x%lx into the object search tree (overlaps existing)\n", + ptr); + /* + * No need for parent->lock here since "parent" cannot + * be freed while the kmemleak_lock is held. + */ + dump_object_info(parent); + kmem_cache_free(object_cache, object); + object = NULL; + goto out; + } + } + rb_link_node(&object->rb_node, rb_parent, link); + rb_insert_color(&object->rb_node, &object_tree_root); + + list_add_tail_rcu(&object->object_list, &object_list); +out: + raw_spin_unlock_irqrestore(&kmemleak_lock, flags); + return object; +} + +/* + * Mark the object as not allocated and schedule RCU freeing via put_object(). + */ +static void __delete_object(struct kmemleak_object *object) +{ + unsigned long flags; + + WARN_ON(!(object->flags & OBJECT_ALLOCATED)); + WARN_ON(atomic_read(&object->use_count) < 1); + + /* + * Locking here also ensures that the corresponding memory block + * cannot be freed when it is being scanned. + */ + raw_spin_lock_irqsave(&object->lock, flags); + object->flags &= ~OBJECT_ALLOCATED; + raw_spin_unlock_irqrestore(&object->lock, flags); + put_object(object); +} + +/* + * Look up the metadata (struct kmemleak_object) corresponding to ptr and + * delete it. + */ +static void delete_object_full(unsigned long ptr) +{ + struct kmemleak_object *object; + + object = find_and_remove_object(ptr, 0); + if (!object) { +#ifdef DEBUG + kmemleak_warn("Freeing unknown object at 0x%08lx\n", + ptr); +#endif + return; + } + __delete_object(object); +} + +/* + * Look up the metadata (struct kmemleak_object) corresponding to ptr and + * delete it. If the memory block is partially freed, the function may create + * additional metadata for the remaining parts of the block. + */ +static void delete_object_part(unsigned long ptr, size_t size) +{ + struct kmemleak_object *object; + unsigned long start, end; + + object = find_and_remove_object(ptr, 1); + if (!object) { +#ifdef DEBUG + kmemleak_warn("Partially freeing unknown object at 0x%08lx (size %zu)\n", + ptr, size); +#endif + return; + } + + /* + * Create one or two objects that may result from the memory block + * split. Note that partial freeing is only done by free_bootmem() and + * this happens before kmemleak_init() is called. + */ + start = object->pointer; + end = object->pointer + object->size; + if (ptr > start) + create_object(start, ptr - start, object->min_count, + GFP_KERNEL); + if (ptr + size < end) + create_object(ptr + size, end - ptr - size, object->min_count, + GFP_KERNEL); + + __delete_object(object); +} + +static void __paint_it(struct kmemleak_object *object, int color) +{ + object->min_count = color; + if (color == KMEMLEAK_BLACK) + object->flags |= OBJECT_NO_SCAN; +} + +static void paint_it(struct kmemleak_object *object, int color) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&object->lock, flags); + __paint_it(object, color); + raw_spin_unlock_irqrestore(&object->lock, flags); +} + +static void paint_ptr(unsigned long ptr, int color) +{ + struct kmemleak_object *object; + + object = find_and_get_object(ptr, 0); + if (!object) { + kmemleak_warn("Trying to color unknown object at 0x%08lx as %s\n", + ptr, + (color == KMEMLEAK_GREY) ? "Grey" : + (color == KMEMLEAK_BLACK) ? "Black" : "Unknown"); + return; + } + paint_it(object, color); + put_object(object); +} + +/* + * Mark an object permanently as gray-colored so that it can no longer be + * reported as a leak. This is used in general to mark a false positive. + */ +static void make_gray_object(unsigned long ptr) +{ + paint_ptr(ptr, KMEMLEAK_GREY); +} + +/* + * Mark the object as black-colored so that it is ignored from scans and + * reporting. + */ +static void make_black_object(unsigned long ptr) +{ + paint_ptr(ptr, KMEMLEAK_BLACK); +} + +/* + * Add a scanning area to the object. If at least one such area is added, + * kmemleak will only scan these ranges rather than the whole memory block. + */ +static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp) +{ + unsigned long flags; + struct kmemleak_object *object; + struct kmemleak_scan_area *area = NULL; + unsigned long untagged_ptr; + unsigned long untagged_objp; + + object = find_and_get_object(ptr, 1); + if (!object) { + kmemleak_warn("Adding scan area to unknown object at 0x%08lx\n", + ptr); + return; + } + + untagged_ptr = (unsigned long)kasan_reset_tag((void *)ptr); + untagged_objp = (unsigned long)kasan_reset_tag((void *)object->pointer); + + if (scan_area_cache) + area = kmem_cache_alloc(scan_area_cache, gfp_kmemleak_mask(gfp)); + + raw_spin_lock_irqsave(&object->lock, flags); + if (!area) { + pr_warn_once("Cannot allocate a scan area, scanning the full object\n"); + /* mark the object for full scan to avoid false positives */ + object->flags |= OBJECT_FULL_SCAN; + goto out_unlock; + } + if (size == SIZE_MAX) { + size = untagged_objp + object->size - untagged_ptr; + } else if (untagged_ptr + size > untagged_objp + object->size) { + kmemleak_warn("Scan area larger than object 0x%08lx\n", ptr); + dump_object_info(object); + kmem_cache_free(scan_area_cache, area); + goto out_unlock; + } + + INIT_HLIST_NODE(&area->node); + area->start = ptr; + area->size = size; + + hlist_add_head(&area->node, &object->area_list); +out_unlock: + raw_spin_unlock_irqrestore(&object->lock, flags); + put_object(object); +} + +/* + * Any surplus references (object already gray) to 'ptr' are passed to + * 'excess_ref'. This is used in the vmalloc() case where a pointer to + * vm_struct may be used as an alternative reference to the vmalloc'ed object + * (see free_thread_stack()). + */ +static void object_set_excess_ref(unsigned long ptr, unsigned long excess_ref) +{ + unsigned long flags; + struct kmemleak_object *object; + + object = find_and_get_object(ptr, 0); + if (!object) { + kmemleak_warn("Setting excess_ref on unknown object at 0x%08lx\n", + ptr); + return; + } + + raw_spin_lock_irqsave(&object->lock, flags); + object->excess_ref = excess_ref; + raw_spin_unlock_irqrestore(&object->lock, flags); + put_object(object); +} + +/* + * Set the OBJECT_NO_SCAN flag for the object corresponding to the give + * pointer. Such object will not be scanned by kmemleak but references to it + * are searched. + */ +static void object_no_scan(unsigned long ptr) +{ + unsigned long flags; + struct kmemleak_object *object; + + object = find_and_get_object(ptr, 0); + if (!object) { + kmemleak_warn("Not scanning unknown object at 0x%08lx\n", ptr); + return; + } + + raw_spin_lock_irqsave(&object->lock, flags); + object->flags |= OBJECT_NO_SCAN; + raw_spin_unlock_irqrestore(&object->lock, flags); + put_object(object); +} + +/** + * kmemleak_alloc - register a newly allocated object + * @ptr: pointer to beginning of the object + * @size: size of the object + * @min_count: minimum number of references to this object. If during memory + * scanning a number of references less than @min_count is found, + * the object is reported as a memory leak. If @min_count is 0, + * the object is never reported as a leak. If @min_count is -1, + * the object is ignored (not scanned and not reported as a leak) + * @gfp: kmalloc() flags used for kmemleak internal memory allocations + * + * This function is called from the kernel allocators when a new object + * (memory block) is allocated (kmem_cache_alloc, kmalloc etc.). + */ +void __ref kmemleak_alloc(const void *ptr, size_t size, int min_count, + gfp_t gfp) +{ + pr_debug("%s(0x%p, %zu, %d)\n", __func__, ptr, size, min_count); + + if (kmemleak_enabled && ptr && !IS_ERR(ptr)) + create_object((unsigned long)ptr, size, min_count, gfp); +} +EXPORT_SYMBOL_GPL(kmemleak_alloc); + +/** + * kmemleak_alloc_percpu - register a newly allocated __percpu object + * @ptr: __percpu pointer to beginning of the object + * @size: size of the object + * @gfp: flags used for kmemleak internal memory allocations + * + * This function is called from the kernel percpu allocator when a new object + * (memory block) is allocated (alloc_percpu). + */ +void __ref kmemleak_alloc_percpu(const void __percpu *ptr, size_t size, + gfp_t gfp) +{ + unsigned int cpu; + + pr_debug("%s(0x%p, %zu)\n", __func__, ptr, size); + + /* + * Percpu allocations are only scanned and not reported as leaks + * (min_count is set to 0). + */ + if (kmemleak_enabled && ptr && !IS_ERR(ptr)) + for_each_possible_cpu(cpu) + create_object((unsigned long)per_cpu_ptr(ptr, cpu), + size, 0, gfp); +} +EXPORT_SYMBOL_GPL(kmemleak_alloc_percpu); + +/** + * kmemleak_vmalloc - register a newly vmalloc'ed object + * @area: pointer to vm_struct + * @size: size of the object + * @gfp: __vmalloc() flags used for kmemleak internal memory allocations + * + * This function is called from the vmalloc() kernel allocator when a new + * object (memory block) is allocated. + */ +void __ref kmemleak_vmalloc(const struct vm_struct *area, size_t size, gfp_t gfp) +{ + pr_debug("%s(0x%p, %zu)\n", __func__, area, size); + + /* + * A min_count = 2 is needed because vm_struct contains a reference to + * the virtual address of the vmalloc'ed block. + */ + if (kmemleak_enabled) { + create_object((unsigned long)area->addr, size, 2, gfp); + object_set_excess_ref((unsigned long)area, + (unsigned long)area->addr); + } +} +EXPORT_SYMBOL_GPL(kmemleak_vmalloc); + +/** + * kmemleak_free - unregister a previously registered object + * @ptr: pointer to beginning of the object + * + * This function is called from the kernel allocators when an object (memory + * block) is freed (kmem_cache_free, kfree, vfree etc.). + */ +void __ref kmemleak_free(const void *ptr) +{ + pr_debug("%s(0x%p)\n", __func__, ptr); + + if (kmemleak_free_enabled && ptr && !IS_ERR(ptr)) + delete_object_full((unsigned long)ptr); +} +EXPORT_SYMBOL_GPL(kmemleak_free); + +/** + * kmemleak_free_part - partially unregister a previously registered object + * @ptr: pointer to the beginning or inside the object. This also + * represents the start of the range to be freed + * @size: size to be unregistered + * + * This function is called when only a part of a memory block is freed + * (usually from the bootmem allocator). + */ +void __ref kmemleak_free_part(const void *ptr, size_t size) +{ + pr_debug("%s(0x%p)\n", __func__, ptr); + + if (kmemleak_enabled && ptr && !IS_ERR(ptr)) + delete_object_part((unsigned long)ptr, size); +} +EXPORT_SYMBOL_GPL(kmemleak_free_part); + +/** + * kmemleak_free_percpu - unregister a previously registered __percpu object + * @ptr: __percpu pointer to beginning of the object + * + * This function is called from the kernel percpu allocator when an object + * (memory block) is freed (free_percpu). + */ +void __ref kmemleak_free_percpu(const void __percpu *ptr) +{ + unsigned int cpu; + + pr_debug("%s(0x%p)\n", __func__, ptr); + + if (kmemleak_free_enabled && ptr && !IS_ERR(ptr)) + for_each_possible_cpu(cpu) + delete_object_full((unsigned long)per_cpu_ptr(ptr, + cpu)); +} +EXPORT_SYMBOL_GPL(kmemleak_free_percpu); + +/** + * kmemleak_update_trace - update object allocation stack trace + * @ptr: pointer to beginning of the object + * + * Override the object allocation stack trace for cases where the actual + * allocation place is not always useful. + */ +void __ref kmemleak_update_trace(const void *ptr) +{ + struct kmemleak_object *object; + unsigned long flags; + + pr_debug("%s(0x%p)\n", __func__, ptr); + + if (!kmemleak_enabled || IS_ERR_OR_NULL(ptr)) + return; + + object = find_and_get_object((unsigned long)ptr, 1); + if (!object) { +#ifdef DEBUG + kmemleak_warn("Updating stack trace for unknown object at %p\n", + ptr); +#endif + return; + } + + raw_spin_lock_irqsave(&object->lock, flags); + object->trace_len = __save_stack_trace(object->trace); + raw_spin_unlock_irqrestore(&object->lock, flags); + + put_object(object); +} +EXPORT_SYMBOL(kmemleak_update_trace); + +/** + * kmemleak_not_leak - mark an allocated object as false positive + * @ptr: pointer to beginning of the object + * + * Calling this function on an object will cause the memory block to no longer + * be reported as leak and always be scanned. + */ +void __ref kmemleak_not_leak(const void *ptr) +{ + pr_debug("%s(0x%p)\n", __func__, ptr); + + if (kmemleak_enabled && ptr && !IS_ERR(ptr)) + make_gray_object((unsigned long)ptr); +} +EXPORT_SYMBOL(kmemleak_not_leak); + +/** + * kmemleak_ignore - ignore an allocated object + * @ptr: pointer to beginning of the object + * + * Calling this function on an object will cause the memory block to be + * ignored (not scanned and not reported as a leak). This is usually done when + * it is known that the corresponding block is not a leak and does not contain + * any references to other allocated memory blocks. + */ +void __ref kmemleak_ignore(const void *ptr) +{ + pr_debug("%s(0x%p)\n", __func__, ptr); + + if (kmemleak_enabled && ptr && !IS_ERR(ptr)) + make_black_object((unsigned long)ptr); +} +EXPORT_SYMBOL(kmemleak_ignore); + +/** + * kmemleak_scan_area - limit the range to be scanned in an allocated object + * @ptr: pointer to beginning or inside the object. This also + * represents the start of the scan area + * @size: size of the scan area + * @gfp: kmalloc() flags used for kmemleak internal memory allocations + * + * This function is used when it is known that only certain parts of an object + * contain references to other objects. Kmemleak will only scan these areas + * reducing the number false negatives. + */ +void __ref kmemleak_scan_area(const void *ptr, size_t size, gfp_t gfp) +{ + pr_debug("%s(0x%p)\n", __func__, ptr); + + if (kmemleak_enabled && ptr && size && !IS_ERR(ptr)) + add_scan_area((unsigned long)ptr, size, gfp); +} +EXPORT_SYMBOL(kmemleak_scan_area); + +/** + * kmemleak_no_scan - do not scan an allocated object + * @ptr: pointer to beginning of the object + * + * This function notifies kmemleak not to scan the given memory block. Useful + * in situations where it is known that the given object does not contain any + * references to other objects. Kmemleak will not scan such objects reducing + * the number of false negatives. + */ +void __ref kmemleak_no_scan(const void *ptr) +{ + pr_debug("%s(0x%p)\n", __func__, ptr); + + if (kmemleak_enabled && ptr && !IS_ERR(ptr)) + object_no_scan((unsigned long)ptr); +} +EXPORT_SYMBOL(kmemleak_no_scan); + +/** + * kmemleak_alloc_phys - similar to kmemleak_alloc but taking a physical + * address argument + * @phys: physical address of the object + * @size: size of the object + * @min_count: minimum number of references to this object. + * See kmemleak_alloc() + * @gfp: kmalloc() flags used for kmemleak internal memory allocations + */ +void __ref kmemleak_alloc_phys(phys_addr_t phys, size_t size, int min_count, + gfp_t gfp) +{ + if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) + kmemleak_alloc(__va(phys), size, min_count, gfp); +} +EXPORT_SYMBOL(kmemleak_alloc_phys); + +/** + * kmemleak_free_part_phys - similar to kmemleak_free_part but taking a + * physical address argument + * @phys: physical address if the beginning or inside an object. This + * also represents the start of the range to be freed + * @size: size to be unregistered + */ +void __ref kmemleak_free_part_phys(phys_addr_t phys, size_t size) +{ + if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) + kmemleak_free_part(__va(phys), size); +} +EXPORT_SYMBOL(kmemleak_free_part_phys); + +/** + * kmemleak_not_leak_phys - similar to kmemleak_not_leak but taking a physical + * address argument + * @phys: physical address of the object + */ +void __ref kmemleak_not_leak_phys(phys_addr_t phys) +{ + if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) + kmemleak_not_leak(__va(phys)); +} +EXPORT_SYMBOL(kmemleak_not_leak_phys); + +/** + * kmemleak_ignore_phys - similar to kmemleak_ignore but taking a physical + * address argument + * @phys: physical address of the object + */ +void __ref kmemleak_ignore_phys(phys_addr_t phys) +{ + if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) + kmemleak_ignore(__va(phys)); +} +EXPORT_SYMBOL(kmemleak_ignore_phys); + +/* + * Update an object's checksum and return true if it was modified. + */ +static bool update_checksum(struct kmemleak_object *object) +{ + u32 old_csum = object->checksum; + + kasan_disable_current(); + kcsan_disable_current(); + object->checksum = crc32(0, (void *)object->pointer, object->size); + kasan_enable_current(); + kcsan_enable_current(); + + return object->checksum != old_csum; +} + +/* + * Update an object's references. object->lock must be held by the caller. + */ +static void update_refs(struct kmemleak_object *object) +{ + if (!color_white(object)) { + /* non-orphan, ignored or new */ + return; + } + + /* + * Increase the object's reference count (number of pointers to the + * memory block). If this count reaches the required minimum, the + * object's color will become gray and it will be added to the + * gray_list. + */ + object->count++; + if (color_gray(object)) { + /* put_object() called when removing from gray_list */ + WARN_ON(!get_object(object)); + list_add_tail(&object->gray_list, &gray_list); + } +} + +/* + * Memory scanning is a long process and it needs to be interruptable. This + * function checks whether such interrupt condition occurred. + */ +static int scan_should_stop(void) +{ + if (!kmemleak_enabled) + return 1; + + /* + * This function may be called from either process or kthread context, + * hence the need to check for both stop conditions. + */ + if (current->mm) + return signal_pending(current); + else + return kthread_should_stop(); + + return 0; +} + +/* + * Scan a memory block (exclusive range) for valid pointers and add those + * found to the gray list. + */ +static void scan_block(void *_start, void *_end, + struct kmemleak_object *scanned) +{ + unsigned long *ptr; + unsigned long *start = PTR_ALIGN(_start, BYTES_PER_POINTER); + unsigned long *end = _end - (BYTES_PER_POINTER - 1); + unsigned long flags; + unsigned long untagged_ptr; + + raw_spin_lock_irqsave(&kmemleak_lock, flags); + for (ptr = start; ptr < end; ptr++) { + struct kmemleak_object *object; + unsigned long pointer; + unsigned long excess_ref; + + if (scan_should_stop()) + break; + + kasan_disable_current(); + pointer = *ptr; + kasan_enable_current(); + + untagged_ptr = (unsigned long)kasan_reset_tag((void *)pointer); + if (untagged_ptr < min_addr || untagged_ptr >= max_addr) + continue; + + /* + * No need for get_object() here since we hold kmemleak_lock. + * object->use_count cannot be dropped to 0 while the object + * is still present in object_tree_root and object_list + * (with updates protected by kmemleak_lock). + */ + object = lookup_object(pointer, 1); + if (!object) + continue; + if (object == scanned) + /* self referenced, ignore */ + continue; + + /* + * Avoid the lockdep recursive warning on object->lock being + * previously acquired in scan_object(). These locks are + * enclosed by scan_mutex. + */ + raw_spin_lock_nested(&object->lock, SINGLE_DEPTH_NESTING); + /* only pass surplus references (object already gray) */ + if (color_gray(object)) { + excess_ref = object->excess_ref; + /* no need for update_refs() if object already gray */ + } else { + excess_ref = 0; + update_refs(object); + } + raw_spin_unlock(&object->lock); + + if (excess_ref) { + object = lookup_object(excess_ref, 0); + if (!object) + continue; + if (object == scanned) + /* circular reference, ignore */ + continue; + raw_spin_lock_nested(&object->lock, SINGLE_DEPTH_NESTING); + update_refs(object); + raw_spin_unlock(&object->lock); + } + } + raw_spin_unlock_irqrestore(&kmemleak_lock, flags); +} + +/* + * Scan a large memory block in MAX_SCAN_SIZE chunks to reduce the latency. + */ +#ifdef CONFIG_SMP +static void scan_large_block(void *start, void *end) +{ + void *next; + + while (start < end) { + next = min(start + MAX_SCAN_SIZE, end); + scan_block(start, next, NULL); + start = next; + cond_resched(); + } +} +#endif + +/* + * Scan a memory block corresponding to a kmemleak_object. A condition is + * that object->use_count >= 1. + */ +static void scan_object(struct kmemleak_object *object) +{ + struct kmemleak_scan_area *area; + unsigned long flags; + + /* + * Once the object->lock is acquired, the corresponding memory block + * cannot be freed (the same lock is acquired in delete_object). + */ + raw_spin_lock_irqsave(&object->lock, flags); + if (object->flags & OBJECT_NO_SCAN) + goto out; + if (!(object->flags & OBJECT_ALLOCATED)) + /* already freed object */ + goto out; + if (hlist_empty(&object->area_list) || + object->flags & OBJECT_FULL_SCAN) { + void *start = (void *)object->pointer; + void *end = (void *)(object->pointer + object->size); + void *next; + + do { + next = min(start + MAX_SCAN_SIZE, end); + scan_block(start, next, object); + + start = next; + if (start >= end) + break; + + raw_spin_unlock_irqrestore(&object->lock, flags); + cond_resched(); + raw_spin_lock_irqsave(&object->lock, flags); + } while (object->flags & OBJECT_ALLOCATED); + } else + hlist_for_each_entry(area, &object->area_list, node) + scan_block((void *)area->start, + (void *)(area->start + area->size), + object); +out: + raw_spin_unlock_irqrestore(&object->lock, flags); +} + +/* + * Scan the objects already referenced (gray objects). More objects will be + * referenced and, if there are no memory leaks, all the objects are scanned. + */ +static void scan_gray_list(void) +{ + struct kmemleak_object *object, *tmp; + + /* + * The list traversal is safe for both tail additions and removals + * from inside the loop. The kmemleak objects cannot be freed from + * outside the loop because their use_count was incremented. + */ + object = list_entry(gray_list.next, typeof(*object), gray_list); + while (&object->gray_list != &gray_list) { + cond_resched(); + + /* may add new objects to the list */ + if (!scan_should_stop()) + scan_object(object); + + tmp = list_entry(object->gray_list.next, typeof(*object), + gray_list); + + /* remove the object from the list and release it */ + list_del(&object->gray_list); + put_object(object); + + object = tmp; + } + WARN_ON(!list_empty(&gray_list)); +} + +/* + * Scan data sections and all the referenced memory blocks allocated via the + * kernel's standard allocators. This function must be called with the + * scan_mutex held. + */ +static void kmemleak_scan(void) +{ + unsigned long flags; + struct kmemleak_object *object; + struct zone *zone; + int __maybe_unused i; + int new_leaks = 0; + + jiffies_last_scan = jiffies; + + /* prepare the kmemleak_object's */ + rcu_read_lock(); + list_for_each_entry_rcu(object, &object_list, object_list) { + raw_spin_lock_irqsave(&object->lock, flags); +#ifdef DEBUG + /* + * With a few exceptions there should be a maximum of + * 1 reference to any object at this point. + */ + if (atomic_read(&object->use_count) > 1) { + pr_debug("object->use_count = %d\n", + atomic_read(&object->use_count)); + dump_object_info(object); + } +#endif + /* reset the reference count (whiten the object) */ + object->count = 0; + if (color_gray(object) && get_object(object)) + list_add_tail(&object->gray_list, &gray_list); + + raw_spin_unlock_irqrestore(&object->lock, flags); + } + rcu_read_unlock(); + +#ifdef CONFIG_SMP + /* per-cpu sections scanning */ + for_each_possible_cpu(i) + scan_large_block(__per_cpu_start + per_cpu_offset(i), + __per_cpu_end + per_cpu_offset(i)); +#endif + + /* + * Struct page scanning for each node. + */ + get_online_mems(); + for_each_populated_zone(zone) { + unsigned long start_pfn = zone->zone_start_pfn; + unsigned long end_pfn = zone_end_pfn(zone); + unsigned long pfn; + + for (pfn = start_pfn; pfn < end_pfn; pfn++) { + struct page *page = pfn_to_online_page(pfn); + + if (!page) + continue; + + /* only scan pages belonging to this zone */ + if (page_zone(page) != zone) + continue; + /* only scan if page is in use */ + if (page_count(page) == 0) + continue; + scan_block(page, page + 1, NULL); + if (!(pfn & 63)) + cond_resched(); + } + } + put_online_mems(); + + /* + * Scanning the task stacks (may introduce false negatives). + */ + if (kmemleak_stack_scan) { + struct task_struct *p, *g; + + rcu_read_lock(); + for_each_process_thread(g, p) { + void *stack = try_get_task_stack(p); + if (stack) { + scan_block(stack, stack + THREAD_SIZE, NULL); + put_task_stack(p); + } + } + rcu_read_unlock(); + } + + /* + * Scan the objects already referenced from the sections scanned + * above. + */ + scan_gray_list(); + + /* + * Check for new or unreferenced objects modified since the previous + * scan and color them gray until the next scan. + */ + rcu_read_lock(); + list_for_each_entry_rcu(object, &object_list, object_list) { + raw_spin_lock_irqsave(&object->lock, flags); + if (color_white(object) && (object->flags & OBJECT_ALLOCATED) + && update_checksum(object) && get_object(object)) { + /* color it gray temporarily */ + object->count = object->min_count; + list_add_tail(&object->gray_list, &gray_list); + } + raw_spin_unlock_irqrestore(&object->lock, flags); + } + rcu_read_unlock(); + + /* + * Re-scan the gray list for modified unreferenced objects. + */ + scan_gray_list(); + + /* + * If scanning was stopped do not report any new unreferenced objects. + */ + if (scan_should_stop()) + return; + + /* + * Scanning result reporting. + */ + rcu_read_lock(); + list_for_each_entry_rcu(object, &object_list, object_list) { + raw_spin_lock_irqsave(&object->lock, flags); + if (unreferenced_object(object) && + !(object->flags & OBJECT_REPORTED)) { + object->flags |= OBJECT_REPORTED; + + if (kmemleak_verbose) + print_unreferenced(NULL, object); + + new_leaks++; + } + raw_spin_unlock_irqrestore(&object->lock, flags); + } + rcu_read_unlock(); + + if (new_leaks) { + kmemleak_found_leaks = true; + + pr_info("%d new suspected memory leaks (see /sys/kernel/debug/kmemleak)\n", + new_leaks); + } + +} + +/* + * Thread function performing automatic memory scanning. Unreferenced objects + * at the end of a memory scan are reported but only the first time. + */ +static int kmemleak_scan_thread(void *arg) +{ + static int first_run = IS_ENABLED(CONFIG_DEBUG_KMEMLEAK_AUTO_SCAN); + + pr_info("Automatic memory scanning thread started\n"); + set_user_nice(current, 10); + + /* + * Wait before the first scan to allow the system to fully initialize. + */ + if (first_run) { + signed long timeout = msecs_to_jiffies(SECS_FIRST_SCAN * 1000); + first_run = 0; + while (timeout && !kthread_should_stop()) + timeout = schedule_timeout_interruptible(timeout); + } + + while (!kthread_should_stop()) { + signed long timeout = jiffies_scan_wait; + + mutex_lock(&scan_mutex); + kmemleak_scan(); + mutex_unlock(&scan_mutex); + + /* wait before the next scan */ + while (timeout && !kthread_should_stop()) + timeout = schedule_timeout_interruptible(timeout); + } + + pr_info("Automatic memory scanning thread ended\n"); + + return 0; +} + +/* + * Start the automatic memory scanning thread. This function must be called + * with the scan_mutex held. + */ +static void start_scan_thread(void) +{ + if (scan_thread) + return; + scan_thread = kthread_run(kmemleak_scan_thread, NULL, "kmemleak"); + if (IS_ERR(scan_thread)) { + pr_warn("Failed to create the scan thread\n"); + scan_thread = NULL; + } +} + +/* + * Stop the automatic memory scanning thread. + */ +static void stop_scan_thread(void) +{ + if (scan_thread) { + kthread_stop(scan_thread); + scan_thread = NULL; + } +} + +/* + * Iterate over the object_list and return the first valid object at or after + * the required position with its use_count incremented. The function triggers + * a memory scanning when the pos argument points to the first position. + */ +static void *kmemleak_seq_start(struct seq_file *seq, loff_t *pos) +{ + struct kmemleak_object *object; + loff_t n = *pos; + int err; + + err = mutex_lock_interruptible(&scan_mutex); + if (err < 0) + return ERR_PTR(err); + + rcu_read_lock(); + list_for_each_entry_rcu(object, &object_list, object_list) { + if (n-- > 0) + continue; + if (get_object(object)) + goto out; + } + object = NULL; +out: + return object; +} + +/* + * Return the next object in the object_list. The function decrements the + * use_count of the previous object and increases that of the next one. + */ +static void *kmemleak_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct kmemleak_object *prev_obj = v; + struct kmemleak_object *next_obj = NULL; + struct kmemleak_object *obj = prev_obj; + + ++(*pos); + + list_for_each_entry_continue_rcu(obj, &object_list, object_list) { + if (get_object(obj)) { + next_obj = obj; + break; + } + } + + put_object(prev_obj); + return next_obj; +} + +/* + * Decrement the use_count of the last object required, if any. + */ +static void kmemleak_seq_stop(struct seq_file *seq, void *v) +{ + if (!IS_ERR(v)) { + /* + * kmemleak_seq_start may return ERR_PTR if the scan_mutex + * waiting was interrupted, so only release it if !IS_ERR. + */ + rcu_read_unlock(); + mutex_unlock(&scan_mutex); + if (v) + put_object(v); + } +} + +/* + * Print the information for an unreferenced object to the seq file. + */ +static int kmemleak_seq_show(struct seq_file *seq, void *v) +{ + struct kmemleak_object *object = v; + unsigned long flags; + + raw_spin_lock_irqsave(&object->lock, flags); + if ((object->flags & OBJECT_REPORTED) && unreferenced_object(object)) + print_unreferenced(seq, object); + raw_spin_unlock_irqrestore(&object->lock, flags); + return 0; +} + +static const struct seq_operations kmemleak_seq_ops = { + .start = kmemleak_seq_start, + .next = kmemleak_seq_next, + .stop = kmemleak_seq_stop, + .show = kmemleak_seq_show, +}; + +static int kmemleak_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &kmemleak_seq_ops); +} + +static int dump_str_object_info(const char *str) +{ + unsigned long flags; + struct kmemleak_object *object; + unsigned long addr; + + if (kstrtoul(str, 0, &addr)) + return -EINVAL; + object = find_and_get_object(addr, 0); + if (!object) { + pr_info("Unknown object at 0x%08lx\n", addr); + return -EINVAL; + } + + raw_spin_lock_irqsave(&object->lock, flags); + dump_object_info(object); + raw_spin_unlock_irqrestore(&object->lock, flags); + + put_object(object); + return 0; +} + +/* + * We use grey instead of black to ensure we can do future scans on the same + * objects. If we did not do future scans these black objects could + * potentially contain references to newly allocated objects in the future and + * we'd end up with false positives. + */ +static void kmemleak_clear(void) +{ + struct kmemleak_object *object; + unsigned long flags; + + rcu_read_lock(); + list_for_each_entry_rcu(object, &object_list, object_list) { + raw_spin_lock_irqsave(&object->lock, flags); + if ((object->flags & OBJECT_REPORTED) && + unreferenced_object(object)) + __paint_it(object, KMEMLEAK_GREY); + raw_spin_unlock_irqrestore(&object->lock, flags); + } + rcu_read_unlock(); + + kmemleak_found_leaks = false; +} + +static void __kmemleak_do_cleanup(void); + +/* + * File write operation to configure kmemleak at run-time. The following + * commands can be written to the /sys/kernel/debug/kmemleak file: + * off - disable kmemleak (irreversible) + * stack=on - enable the task stacks scanning + * stack=off - disable the tasks stacks scanning + * scan=on - start the automatic memory scanning thread + * scan=off - stop the automatic memory scanning thread + * scan=... - set the automatic memory scanning period in seconds (0 to + * disable it) + * scan - trigger a memory scan + * clear - mark all current reported unreferenced kmemleak objects as + * grey to ignore printing them, or free all kmemleak objects + * if kmemleak has been disabled. + * dump=... - dump information about the object found at the given address + */ +static ssize_t kmemleak_write(struct file *file, const char __user *user_buf, + size_t size, loff_t *ppos) +{ + char buf[64]; + int buf_size; + int ret; + + buf_size = min(size, (sizeof(buf) - 1)); + if (strncpy_from_user(buf, user_buf, buf_size) < 0) + return -EFAULT; + buf[buf_size] = 0; + + ret = mutex_lock_interruptible(&scan_mutex); + if (ret < 0) + return ret; + + if (strncmp(buf, "clear", 5) == 0) { + if (kmemleak_enabled) + kmemleak_clear(); + else + __kmemleak_do_cleanup(); + goto out; + } + + if (!kmemleak_enabled) { + ret = -EPERM; + goto out; + } + + if (strncmp(buf, "off", 3) == 0) + kmemleak_disable(); + else if (strncmp(buf, "stack=on", 8) == 0) + kmemleak_stack_scan = 1; + else if (strncmp(buf, "stack=off", 9) == 0) + kmemleak_stack_scan = 0; + else if (strncmp(buf, "scan=on", 7) == 0) + start_scan_thread(); + else if (strncmp(buf, "scan=off", 8) == 0) + stop_scan_thread(); + else if (strncmp(buf, "scan=", 5) == 0) { + unsigned long secs; + + ret = kstrtoul(buf + 5, 0, &secs); + if (ret < 0) + goto out; + stop_scan_thread(); + if (secs) { + jiffies_scan_wait = msecs_to_jiffies(secs * 1000); + start_scan_thread(); + } + } else if (strncmp(buf, "scan", 4) == 0) + kmemleak_scan(); + else if (strncmp(buf, "dump=", 5) == 0) + ret = dump_str_object_info(buf + 5); + else + ret = -EINVAL; + +out: + mutex_unlock(&scan_mutex); + if (ret < 0) + return ret; + + /* ignore the rest of the buffer, only one command at a time */ + *ppos += size; + return size; +} + +static const struct file_operations kmemleak_fops = { + .owner = THIS_MODULE, + .open = kmemleak_open, + .read = seq_read, + .write = kmemleak_write, + .llseek = seq_lseek, + .release = seq_release, +}; + +static void __kmemleak_do_cleanup(void) +{ + struct kmemleak_object *object, *tmp; + + /* + * Kmemleak has already been disabled, no need for RCU list traversal + * or kmemleak_lock held. + */ + list_for_each_entry_safe(object, tmp, &object_list, object_list) { + __remove_object(object); + __delete_object(object); + } +} + +/* + * Stop the memory scanning thread and free the kmemleak internal objects if + * no previous scan thread (otherwise, kmemleak may still have some useful + * information on memory leaks). + */ +static void kmemleak_do_cleanup(struct work_struct *work) +{ + stop_scan_thread(); + + mutex_lock(&scan_mutex); + /* + * Once it is made sure that kmemleak_scan has stopped, it is safe to no + * longer track object freeing. Ordering of the scan thread stopping and + * the memory accesses below is guaranteed by the kthread_stop() + * function. + */ + kmemleak_free_enabled = 0; + mutex_unlock(&scan_mutex); + + if (!kmemleak_found_leaks) + __kmemleak_do_cleanup(); + else + pr_info("Kmemleak disabled without freeing internal data. Reclaim the memory with \"echo clear > /sys/kernel/debug/kmemleak\".\n"); +} + +static DECLARE_WORK(cleanup_work, kmemleak_do_cleanup); + +/* + * Disable kmemleak. No memory allocation/freeing will be traced once this + * function is called. Disabling kmemleak is an irreversible operation. + */ +static void kmemleak_disable(void) +{ + /* atomically check whether it was already invoked */ + if (cmpxchg(&kmemleak_error, 0, 1)) + return; + + /* stop any memory operation tracing */ + kmemleak_enabled = 0; + + /* check whether it is too early for a kernel thread */ + if (kmemleak_initialized) + schedule_work(&cleanup_work); + else + kmemleak_free_enabled = 0; + + pr_info("Kernel memory leak detector disabled\n"); +} + +/* + * Allow boot-time kmemleak disabling (enabled by default). + */ +static int __init kmemleak_boot_config(char *str) +{ + if (!str) + return -EINVAL; + if (strcmp(str, "off") == 0) + kmemleak_disable(); + else if (strcmp(str, "on") == 0) + kmemleak_skip_disable = 1; + else + return -EINVAL; + return 0; +} +early_param("kmemleak", kmemleak_boot_config); + +/* + * Kmemleak initialization. + */ +void __init kmemleak_init(void) +{ +#ifdef CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF + if (!kmemleak_skip_disable) { + kmemleak_disable(); + return; + } +#endif + + if (kmemleak_error) + return; + + jiffies_min_age = msecs_to_jiffies(MSECS_MIN_AGE); + jiffies_scan_wait = msecs_to_jiffies(SECS_SCAN_WAIT * 1000); + + object_cache = KMEM_CACHE(kmemleak_object, SLAB_NOLEAKTRACE); + scan_area_cache = KMEM_CACHE(kmemleak_scan_area, SLAB_NOLEAKTRACE); + + /* register the data/bss sections */ + create_object((unsigned long)_sdata, _edata - _sdata, + KMEMLEAK_GREY, GFP_ATOMIC); + create_object((unsigned long)__bss_start, __bss_stop - __bss_start, + KMEMLEAK_GREY, GFP_ATOMIC); + /* only register .data..ro_after_init if not within .data */ + if (&__start_ro_after_init < &_sdata || &__end_ro_after_init > &_edata) + create_object((unsigned long)__start_ro_after_init, + __end_ro_after_init - __start_ro_after_init, + KMEMLEAK_GREY, GFP_ATOMIC); +} + +/* + * Late initialization function. + */ +static int __init kmemleak_late_init(void) +{ + kmemleak_initialized = 1; + + debugfs_create_file("kmemleak", 0644, NULL, NULL, &kmemleak_fops); + + if (kmemleak_error) { + /* + * Some error occurred and kmemleak was disabled. There is a + * small chance that kmemleak_disable() was called immediately + * after setting kmemleak_initialized and we may end up with + * two clean-up threads but serialized by scan_mutex. + */ + schedule_work(&cleanup_work); + return -ENOMEM; + } + + if (IS_ENABLED(CONFIG_DEBUG_KMEMLEAK_AUTO_SCAN)) { + mutex_lock(&scan_mutex); + start_scan_thread(); + mutex_unlock(&scan_mutex); + } + + pr_info("Kernel memory leak detector initialized (mem pool available: %d)\n", + mem_pool_free_count); + + return 0; +} +late_initcall(kmemleak_late_init); diff --git a/mm/ksm.c b/mm/ksm.c new file mode 100644 index 000000000..25b8362a4 --- /dev/null +++ b/mm/ksm.c @@ -0,0 +1,3205 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Memory merging support. + * + * This code enables dynamic sharing of identical pages found in different + * memory areas, even if they are not shared by fork() + * + * Copyright (C) 2008-2009 Red Hat, Inc. + * Authors: + * Izik Eidus + * Andrea Arcangeli + * Chris Wright + * Hugh Dickins + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include "internal.h" + +#ifdef CONFIG_NUMA +#define NUMA(x) (x) +#define DO_NUMA(x) do { (x); } while (0) +#else +#define NUMA(x) (0) +#define DO_NUMA(x) do { } while (0) +#endif + +/** + * DOC: Overview + * + * A few notes about the KSM scanning process, + * to make it easier to understand the data structures below: + * + * In order to reduce excessive scanning, KSM sorts the memory pages by their + * contents into a data structure that holds pointers to the pages' locations. + * + * Since the contents of the pages may change at any moment, KSM cannot just + * insert the pages into a normal sorted tree and expect it to find anything. + * Therefore KSM uses two data structures - the stable and the unstable tree. + * + * The stable tree holds pointers to all the merged pages (ksm pages), sorted + * by their contents. Because each such page is write-protected, searching on + * this tree is fully assured to be working (except when pages are unmapped), + * and therefore this tree is called the stable tree. + * + * The stable tree node includes information required for reverse + * mapping from a KSM page to virtual addresses that map this page. + * + * In order to avoid large latencies of the rmap walks on KSM pages, + * KSM maintains two types of nodes in the stable tree: + * + * * the regular nodes that keep the reverse mapping structures in a + * linked list + * * the "chains" that link nodes ("dups") that represent the same + * write protected memory content, but each "dup" corresponds to a + * different KSM page copy of that content + * + * Internally, the regular nodes, "dups" and "chains" are represented + * using the same struct stable_node structure. + * + * In addition to the stable tree, KSM uses a second data structure called the + * unstable tree: this tree holds pointers to pages which have been found to + * be "unchanged for a period of time". The unstable tree sorts these pages + * by their contents, but since they are not write-protected, KSM cannot rely + * upon the unstable tree to work correctly - the unstable tree is liable to + * be corrupted as its contents are modified, and so it is called unstable. + * + * KSM solves this problem by several techniques: + * + * 1) The unstable tree is flushed every time KSM completes scanning all + * memory areas, and then the tree is rebuilt again from the beginning. + * 2) KSM will only insert into the unstable tree, pages whose hash value + * has not changed since the previous scan of all memory areas. + * 3) The unstable tree is a RedBlack Tree - so its balancing is based on the + * colors of the nodes and not on their contents, assuring that even when + * the tree gets "corrupted" it won't get out of balance, so scanning time + * remains the same (also, searching and inserting nodes in an rbtree uses + * the same algorithm, so we have no overhead when we flush and rebuild). + * 4) KSM never flushes the stable tree, which means that even if it were to + * take 10 attempts to find a page in the unstable tree, once it is found, + * it is secured in the stable tree. (When we scan a new page, we first + * compare it against the stable tree, and then against the unstable tree.) + * + * If the merge_across_nodes tunable is unset, then KSM maintains multiple + * stable trees and multiple unstable trees: one of each for each NUMA node. + */ + +/** + * struct mm_slot - ksm information per mm that is being scanned + * @link: link to the mm_slots hash list + * @mm_list: link into the mm_slots list, rooted in ksm_mm_head + * @rmap_list: head for this mm_slot's singly-linked list of rmap_items + * @mm: the mm that this information is valid for + */ +struct mm_slot { + struct hlist_node link; + struct list_head mm_list; + struct rmap_item *rmap_list; + struct mm_struct *mm; +}; + +/** + * struct ksm_scan - cursor for scanning + * @mm_slot: the current mm_slot we are scanning + * @address: the next address inside that to be scanned + * @rmap_list: link to the next rmap to be scanned in the rmap_list + * @seqnr: count of completed full scans (needed when removing unstable node) + * + * There is only the one ksm_scan instance of this cursor structure. + */ +struct ksm_scan { + struct mm_slot *mm_slot; + unsigned long address; + struct rmap_item **rmap_list; + unsigned long seqnr; +}; + +/** + * struct stable_node - node of the stable rbtree + * @node: rb node of this ksm page in the stable tree + * @head: (overlaying parent) &migrate_nodes indicates temporarily on that list + * @hlist_dup: linked into the stable_node->hlist with a stable_node chain + * @list: linked into migrate_nodes, pending placement in the proper node tree + * @hlist: hlist head of rmap_items using this ksm page + * @kpfn: page frame number of this ksm page (perhaps temporarily on wrong nid) + * @chain_prune_time: time of the last full garbage collection + * @rmap_hlist_len: number of rmap_item entries in hlist or STABLE_NODE_CHAIN + * @nid: NUMA node id of stable tree in which linked (may not match kpfn) + */ +struct stable_node { + union { + struct rb_node node; /* when node of stable tree */ + struct { /* when listed for migration */ + struct list_head *head; + struct { + struct hlist_node hlist_dup; + struct list_head list; + }; + }; + }; + struct hlist_head hlist; + union { + unsigned long kpfn; + unsigned long chain_prune_time; + }; + /* + * STABLE_NODE_CHAIN can be any negative number in + * rmap_hlist_len negative range, but better not -1 to be able + * to reliably detect underflows. + */ +#define STABLE_NODE_CHAIN -1024 + int rmap_hlist_len; +#ifdef CONFIG_NUMA + int nid; +#endif +}; + +/** + * struct rmap_item - reverse mapping item for virtual addresses + * @rmap_list: next rmap_item in mm_slot's singly-linked rmap_list + * @anon_vma: pointer to anon_vma for this mm,address, when in stable tree + * @nid: NUMA node id of unstable tree in which linked (may not match page) + * @mm: the memory structure this rmap_item is pointing into + * @address: the virtual address this rmap_item tracks (+ flags in low bits) + * @oldchecksum: previous checksum of the page at that virtual address + * @node: rb node of this rmap_item in the unstable tree + * @head: pointer to stable_node heading this list in the stable tree + * @hlist: link into hlist of rmap_items hanging off that stable_node + */ +struct rmap_item { + struct rmap_item *rmap_list; + union { + struct anon_vma *anon_vma; /* when stable */ +#ifdef CONFIG_NUMA + int nid; /* when node of unstable tree */ +#endif + }; + struct mm_struct *mm; + unsigned long address; /* + low bits used for flags below */ + unsigned int oldchecksum; /* when unstable */ + union { + struct rb_node node; /* when node of unstable tree */ + struct { /* when listed from stable tree */ + struct stable_node *head; + struct hlist_node hlist; + }; + }; +}; + +#define SEQNR_MASK 0x0ff /* low bits of unstable tree seqnr */ +#define UNSTABLE_FLAG 0x100 /* is a node of the unstable tree */ +#define STABLE_FLAG 0x200 /* is listed from the stable tree */ +#define KSM_FLAG_MASK (SEQNR_MASK|UNSTABLE_FLAG|STABLE_FLAG) + /* to mask all the flags */ + +/* The stable and unstable tree heads */ +static struct rb_root one_stable_tree[1] = { RB_ROOT }; +static struct rb_root one_unstable_tree[1] = { RB_ROOT }; +static struct rb_root *root_stable_tree = one_stable_tree; +static struct rb_root *root_unstable_tree = one_unstable_tree; + +/* Recently migrated nodes of stable tree, pending proper placement */ +static LIST_HEAD(migrate_nodes); +#define STABLE_NODE_DUP_HEAD ((struct list_head *)&migrate_nodes.prev) + +#define MM_SLOTS_HASH_BITS 10 +static DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS); + +static struct mm_slot ksm_mm_head = { + .mm_list = LIST_HEAD_INIT(ksm_mm_head.mm_list), +}; +static struct ksm_scan ksm_scan = { + .mm_slot = &ksm_mm_head, +}; + +static struct kmem_cache *rmap_item_cache; +static struct kmem_cache *stable_node_cache; +static struct kmem_cache *mm_slot_cache; + +/* The number of nodes in the stable tree */ +static unsigned long ksm_pages_shared; + +/* The number of page slots additionally sharing those nodes */ +static unsigned long ksm_pages_sharing; + +/* The number of nodes in the unstable tree */ +static unsigned long ksm_pages_unshared; + +/* The number of rmap_items in use: to calculate pages_volatile */ +static unsigned long ksm_rmap_items; + +/* The number of stable_node chains */ +static unsigned long ksm_stable_node_chains; + +/* The number of stable_node dups linked to the stable_node chains */ +static unsigned long ksm_stable_node_dups; + +/* Delay in pruning stale stable_node_dups in the stable_node_chains */ +static int ksm_stable_node_chains_prune_millisecs = 2000; + +/* Maximum number of page slots sharing a stable node */ +static int ksm_max_page_sharing = 256; + +/* Number of pages ksmd should scan in one batch */ +static unsigned int ksm_thread_pages_to_scan = 100; + +/* Milliseconds ksmd should sleep between batches */ +static unsigned int ksm_thread_sleep_millisecs = 20; + +/* Checksum of an empty (zeroed) page */ +static unsigned int zero_checksum __read_mostly; + +/* Whether to merge empty (zeroed) pages with actual zero pages */ +static bool ksm_use_zero_pages __read_mostly; + +#ifdef CONFIG_NUMA +/* Zeroed when merging across nodes is not allowed */ +static unsigned int ksm_merge_across_nodes = 1; +static int ksm_nr_node_ids = 1; +#else +#define ksm_merge_across_nodes 1U +#define ksm_nr_node_ids 1 +#endif + +#define KSM_RUN_STOP 0 +#define KSM_RUN_MERGE 1 +#define KSM_RUN_UNMERGE 2 +#define KSM_RUN_OFFLINE 4 +static unsigned long ksm_run = KSM_RUN_STOP; +static void wait_while_offlining(void); + +static DECLARE_WAIT_QUEUE_HEAD(ksm_thread_wait); +static DECLARE_WAIT_QUEUE_HEAD(ksm_iter_wait); +static DEFINE_MUTEX(ksm_thread_mutex); +static DEFINE_SPINLOCK(ksm_mmlist_lock); + +#define KSM_KMEM_CACHE(__struct, __flags) kmem_cache_create("ksm_"#__struct,\ + sizeof(struct __struct), __alignof__(struct __struct),\ + (__flags), NULL) + +static int __init ksm_slab_init(void) +{ + rmap_item_cache = KSM_KMEM_CACHE(rmap_item, 0); + if (!rmap_item_cache) + goto out; + + stable_node_cache = KSM_KMEM_CACHE(stable_node, 0); + if (!stable_node_cache) + goto out_free1; + + mm_slot_cache = KSM_KMEM_CACHE(mm_slot, 0); + if (!mm_slot_cache) + goto out_free2; + + return 0; + +out_free2: + kmem_cache_destroy(stable_node_cache); +out_free1: + kmem_cache_destroy(rmap_item_cache); +out: + return -ENOMEM; +} + +static void __init ksm_slab_free(void) +{ + kmem_cache_destroy(mm_slot_cache); + kmem_cache_destroy(stable_node_cache); + kmem_cache_destroy(rmap_item_cache); + mm_slot_cache = NULL; +} + +static __always_inline bool is_stable_node_chain(struct stable_node *chain) +{ + return chain->rmap_hlist_len == STABLE_NODE_CHAIN; +} + +static __always_inline bool is_stable_node_dup(struct stable_node *dup) +{ + return dup->head == STABLE_NODE_DUP_HEAD; +} + +static inline void stable_node_chain_add_dup(struct stable_node *dup, + struct stable_node *chain) +{ + VM_BUG_ON(is_stable_node_dup(dup)); + dup->head = STABLE_NODE_DUP_HEAD; + VM_BUG_ON(!is_stable_node_chain(chain)); + hlist_add_head(&dup->hlist_dup, &chain->hlist); + ksm_stable_node_dups++; +} + +static inline void __stable_node_dup_del(struct stable_node *dup) +{ + VM_BUG_ON(!is_stable_node_dup(dup)); + hlist_del(&dup->hlist_dup); + ksm_stable_node_dups--; +} + +static inline void stable_node_dup_del(struct stable_node *dup) +{ + VM_BUG_ON(is_stable_node_chain(dup)); + if (is_stable_node_dup(dup)) + __stable_node_dup_del(dup); + else + rb_erase(&dup->node, root_stable_tree + NUMA(dup->nid)); +#ifdef CONFIG_DEBUG_VM + dup->head = NULL; +#endif +} + +static inline struct rmap_item *alloc_rmap_item(void) +{ + struct rmap_item *rmap_item; + + rmap_item = kmem_cache_zalloc(rmap_item_cache, GFP_KERNEL | + __GFP_NORETRY | __GFP_NOWARN); + if (rmap_item) + ksm_rmap_items++; + return rmap_item; +} + +static inline void free_rmap_item(struct rmap_item *rmap_item) +{ + ksm_rmap_items--; + rmap_item->mm = NULL; /* debug safety */ + kmem_cache_free(rmap_item_cache, rmap_item); +} + +static inline struct stable_node *alloc_stable_node(void) +{ + /* + * The allocation can take too long with GFP_KERNEL when memory is under + * pressure, which may lead to hung task warnings. Adding __GFP_HIGH + * grants access to memory reserves, helping to avoid this problem. + */ + return kmem_cache_alloc(stable_node_cache, GFP_KERNEL | __GFP_HIGH); +} + +static inline void free_stable_node(struct stable_node *stable_node) +{ + VM_BUG_ON(stable_node->rmap_hlist_len && + !is_stable_node_chain(stable_node)); + kmem_cache_free(stable_node_cache, stable_node); +} + +static inline struct mm_slot *alloc_mm_slot(void) +{ + if (!mm_slot_cache) /* initialization failed */ + return NULL; + return kmem_cache_zalloc(mm_slot_cache, GFP_KERNEL); +} + +static inline void free_mm_slot(struct mm_slot *mm_slot) +{ + kmem_cache_free(mm_slot_cache, mm_slot); +} + +static struct mm_slot *get_mm_slot(struct mm_struct *mm) +{ + struct mm_slot *slot; + + hash_for_each_possible(mm_slots_hash, slot, link, (unsigned long)mm) + if (slot->mm == mm) + return slot; + + return NULL; +} + +static void insert_to_mm_slots_hash(struct mm_struct *mm, + struct mm_slot *mm_slot) +{ + mm_slot->mm = mm; + hash_add(mm_slots_hash, &mm_slot->link, (unsigned long)mm); +} + +/* + * ksmd, and unmerge_and_remove_all_rmap_items(), must not touch an mm's + * page tables after it has passed through ksm_exit() - which, if necessary, + * takes mmap_lock briefly to serialize against them. ksm_exit() does not set + * a special flag: they can just back out as soon as mm_users goes to zero. + * ksm_test_exit() is used throughout to make this test for exit: in some + * places for correctness, in some places just to avoid unnecessary work. + */ +static inline bool ksm_test_exit(struct mm_struct *mm) +{ + return atomic_read(&mm->mm_users) == 0; +} + +/* + * We use break_ksm to break COW on a ksm page: it's a stripped down + * + * if (get_user_pages(addr, 1, FOLL_WRITE, &page, NULL) == 1) + * put_page(page); + * + * but taking great care only to touch a ksm page, in a VM_MERGEABLE vma, + * in case the application has unmapped and remapped mm,addr meanwhile. + * Could a ksm page appear anywhere else? Actually yes, in a VM_PFNMAP + * mmap of /dev/mem or /dev/kmem, where we would not want to touch it. + * + * FAULT_FLAG/FOLL_REMOTE are because we do this outside the context + * of the process that owns 'vma'. We also do not want to enforce + * protection keys here anyway. + */ +static int break_ksm(struct vm_area_struct *vma, unsigned long addr) +{ + struct page *page; + vm_fault_t ret = 0; + + do { + cond_resched(); + page = follow_page(vma, addr, + FOLL_GET | FOLL_MIGRATION | FOLL_REMOTE); + if (IS_ERR_OR_NULL(page)) + break; + if (PageKsm(page)) + ret = handle_mm_fault(vma, addr, + FAULT_FLAG_WRITE | FAULT_FLAG_REMOTE, + NULL); + else + ret = VM_FAULT_WRITE; + put_page(page); + } while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | VM_FAULT_OOM))); + /* + * We must loop because handle_mm_fault() may back out if there's + * any difficulty e.g. if pte accessed bit gets updated concurrently. + * + * VM_FAULT_WRITE is what we have been hoping for: it indicates that + * COW has been broken, even if the vma does not permit VM_WRITE; + * but note that a concurrent fault might break PageKsm for us. + * + * VM_FAULT_SIGBUS could occur if we race with truncation of the + * backing file, which also invalidates anonymous pages: that's + * okay, that truncation will have unmapped the PageKsm for us. + * + * VM_FAULT_OOM: at the time of writing (late July 2009), setting + * aside mem_cgroup limits, VM_FAULT_OOM would only be set if the + * current task has TIF_MEMDIE set, and will be OOM killed on return + * to user; and ksmd, having no mm, would never be chosen for that. + * + * But if the mm is in a limited mem_cgroup, then the fault may fail + * with VM_FAULT_OOM even if the current task is not TIF_MEMDIE; and + * even ksmd can fail in this way - though it's usually breaking ksm + * just to undo a merge it made a moment before, so unlikely to oom. + * + * That's a pity: we might therefore have more kernel pages allocated + * than we're counting as nodes in the stable tree; but ksm_do_scan + * will retry to break_cow on each pass, so should recover the page + * in due course. The important thing is to not let VM_MERGEABLE + * be cleared while any such pages might remain in the area. + */ + return (ret & VM_FAULT_OOM) ? -ENOMEM : 0; +} + +static struct vm_area_struct *find_mergeable_vma(struct mm_struct *mm, + unsigned long addr) +{ + struct vm_area_struct *vma; + if (ksm_test_exit(mm)) + return NULL; + vma = find_vma(mm, addr); + if (!vma || vma->vm_start > addr) + return NULL; + if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma) + return NULL; + return vma; +} + +static void break_cow(struct rmap_item *rmap_item) +{ + struct mm_struct *mm = rmap_item->mm; + unsigned long addr = rmap_item->address; + struct vm_area_struct *vma; + + /* + * It is not an accident that whenever we want to break COW + * to undo, we also need to drop a reference to the anon_vma. + */ + put_anon_vma(rmap_item->anon_vma); + + mmap_read_lock(mm); + vma = find_mergeable_vma(mm, addr); + if (vma) + break_ksm(vma, addr); + mmap_read_unlock(mm); +} + +static struct page *get_mergeable_page(struct rmap_item *rmap_item) +{ + struct mm_struct *mm = rmap_item->mm; + unsigned long addr = rmap_item->address; + struct vm_area_struct *vma; + struct page *page; + + mmap_read_lock(mm); + vma = find_mergeable_vma(mm, addr); + if (!vma) + goto out; + + page = follow_page(vma, addr, FOLL_GET); + if (IS_ERR_OR_NULL(page)) + goto out; + if (PageAnon(page)) { + flush_anon_page(vma, page, addr); + flush_dcache_page(page); + } else { + put_page(page); +out: + page = NULL; + } + mmap_read_unlock(mm); + return page; +} + +/* + * This helper is used for getting right index into array of tree roots. + * When merge_across_nodes knob is set to 1, there are only two rb-trees for + * stable and unstable pages from all nodes with roots in index 0. Otherwise, + * every node has its own stable and unstable tree. + */ +static inline int get_kpfn_nid(unsigned long kpfn) +{ + return ksm_merge_across_nodes ? 0 : NUMA(pfn_to_nid(kpfn)); +} + +static struct stable_node *alloc_stable_node_chain(struct stable_node *dup, + struct rb_root *root) +{ + struct stable_node *chain = alloc_stable_node(); + VM_BUG_ON(is_stable_node_chain(dup)); + if (likely(chain)) { + INIT_HLIST_HEAD(&chain->hlist); + chain->chain_prune_time = jiffies; + chain->rmap_hlist_len = STABLE_NODE_CHAIN; +#if defined (CONFIG_DEBUG_VM) && defined(CONFIG_NUMA) + chain->nid = NUMA_NO_NODE; /* debug */ +#endif + ksm_stable_node_chains++; + + /* + * Put the stable node chain in the first dimension of + * the stable tree and at the same time remove the old + * stable node. + */ + rb_replace_node(&dup->node, &chain->node, root); + + /* + * Move the old stable node to the second dimension + * queued in the hlist_dup. The invariant is that all + * dup stable_nodes in the chain->hlist point to pages + * that are write protected and have the exact same + * content. + */ + stable_node_chain_add_dup(dup, chain); + } + return chain; +} + +static inline void free_stable_node_chain(struct stable_node *chain, + struct rb_root *root) +{ + rb_erase(&chain->node, root); + free_stable_node(chain); + ksm_stable_node_chains--; +} + +static void remove_node_from_stable_tree(struct stable_node *stable_node) +{ + struct rmap_item *rmap_item; + + /* check it's not STABLE_NODE_CHAIN or negative */ + BUG_ON(stable_node->rmap_hlist_len < 0); + + hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) { + if (rmap_item->hlist.next) + ksm_pages_sharing--; + else + ksm_pages_shared--; + VM_BUG_ON(stable_node->rmap_hlist_len <= 0); + stable_node->rmap_hlist_len--; + put_anon_vma(rmap_item->anon_vma); + rmap_item->address &= PAGE_MASK; + cond_resched(); + } + + /* + * We need the second aligned pointer of the migrate_nodes + * list_head to stay clear from the rb_parent_color union + * (aligned and different than any node) and also different + * from &migrate_nodes. This will verify that future list.h changes + * don't break STABLE_NODE_DUP_HEAD. Only recent gcc can handle it. + */ +#if defined(GCC_VERSION) && GCC_VERSION >= 40903 + BUILD_BUG_ON(STABLE_NODE_DUP_HEAD <= &migrate_nodes); + BUILD_BUG_ON(STABLE_NODE_DUP_HEAD >= &migrate_nodes + 1); +#endif + + if (stable_node->head == &migrate_nodes) + list_del(&stable_node->list); + else + stable_node_dup_del(stable_node); + free_stable_node(stable_node); +} + +enum get_ksm_page_flags { + GET_KSM_PAGE_NOLOCK, + GET_KSM_PAGE_LOCK, + GET_KSM_PAGE_TRYLOCK +}; + +/* + * get_ksm_page: checks if the page indicated by the stable node + * is still its ksm page, despite having held no reference to it. + * In which case we can trust the content of the page, and it + * returns the gotten page; but if the page has now been zapped, + * remove the stale node from the stable tree and return NULL. + * But beware, the stable node's page might be being migrated. + * + * You would expect the stable_node to hold a reference to the ksm page. + * But if it increments the page's count, swapping out has to wait for + * ksmd to come around again before it can free the page, which may take + * seconds or even minutes: much too unresponsive. So instead we use a + * "keyhole reference": access to the ksm page from the stable node peeps + * out through its keyhole to see if that page still holds the right key, + * pointing back to this stable node. This relies on freeing a PageAnon + * page to reset its page->mapping to NULL, and relies on no other use of + * a page to put something that might look like our key in page->mapping. + * is on its way to being freed; but it is an anomaly to bear in mind. + */ +static struct page *get_ksm_page(struct stable_node *stable_node, + enum get_ksm_page_flags flags) +{ + struct page *page; + void *expected_mapping; + unsigned long kpfn; + + expected_mapping = (void *)((unsigned long)stable_node | + PAGE_MAPPING_KSM); +again: + kpfn = READ_ONCE(stable_node->kpfn); /* Address dependency. */ + page = pfn_to_page(kpfn); + if (READ_ONCE(page->mapping) != expected_mapping) + goto stale; + + /* + * We cannot do anything with the page while its refcount is 0. + * Usually 0 means free, or tail of a higher-order page: in which + * case this node is no longer referenced, and should be freed; + * however, it might mean that the page is under page_ref_freeze(). + * The __remove_mapping() case is easy, again the node is now stale; + * the same is in reuse_ksm_page() case; but if page is swapcache + * in migrate_page_move_mapping(), it might still be our page, + * in which case it's essential to keep the node. + */ + while (!get_page_unless_zero(page)) { + /* + * Another check for page->mapping != expected_mapping would + * work here too. We have chosen the !PageSwapCache test to + * optimize the common case, when the page is or is about to + * be freed: PageSwapCache is cleared (under spin_lock_irq) + * in the ref_freeze section of __remove_mapping(); but Anon + * page->mapping reset to NULL later, in free_pages_prepare(). + */ + if (!PageSwapCache(page)) + goto stale; + cpu_relax(); + } + + if (READ_ONCE(page->mapping) != expected_mapping) { + put_page(page); + goto stale; + } + + if (flags == GET_KSM_PAGE_TRYLOCK) { + if (!trylock_page(page)) { + put_page(page); + return ERR_PTR(-EBUSY); + } + } else if (flags == GET_KSM_PAGE_LOCK) + lock_page(page); + + if (flags != GET_KSM_PAGE_NOLOCK) { + if (READ_ONCE(page->mapping) != expected_mapping) { + unlock_page(page); + put_page(page); + goto stale; + } + } + return page; + +stale: + /* + * We come here from above when page->mapping or !PageSwapCache + * suggests that the node is stale; but it might be under migration. + * We need smp_rmb(), matching the smp_wmb() in ksm_migrate_page(), + * before checking whether node->kpfn has been changed. + */ + smp_rmb(); + if (READ_ONCE(stable_node->kpfn) != kpfn) + goto again; + remove_node_from_stable_tree(stable_node); + return NULL; +} + +/* + * Removing rmap_item from stable or unstable tree. + * This function will clean the information from the stable/unstable tree. + */ +static void remove_rmap_item_from_tree(struct rmap_item *rmap_item) +{ + if (rmap_item->address & STABLE_FLAG) { + struct stable_node *stable_node; + struct page *page; + + stable_node = rmap_item->head; + page = get_ksm_page(stable_node, GET_KSM_PAGE_LOCK); + if (!page) + goto out; + + hlist_del(&rmap_item->hlist); + unlock_page(page); + put_page(page); + + if (!hlist_empty(&stable_node->hlist)) + ksm_pages_sharing--; + else + ksm_pages_shared--; + VM_BUG_ON(stable_node->rmap_hlist_len <= 0); + stable_node->rmap_hlist_len--; + + put_anon_vma(rmap_item->anon_vma); + rmap_item->head = NULL; + rmap_item->address &= PAGE_MASK; + + } else if (rmap_item->address & UNSTABLE_FLAG) { + unsigned char age; + /* + * Usually ksmd can and must skip the rb_erase, because + * root_unstable_tree was already reset to RB_ROOT. + * But be careful when an mm is exiting: do the rb_erase + * if this rmap_item was inserted by this scan, rather + * than left over from before. + */ + age = (unsigned char)(ksm_scan.seqnr - rmap_item->address); + BUG_ON(age > 1); + if (!age) + rb_erase(&rmap_item->node, + root_unstable_tree + NUMA(rmap_item->nid)); + ksm_pages_unshared--; + rmap_item->address &= PAGE_MASK; + } +out: + cond_resched(); /* we're called from many long loops */ +} + +static void remove_trailing_rmap_items(struct mm_slot *mm_slot, + struct rmap_item **rmap_list) +{ + while (*rmap_list) { + struct rmap_item *rmap_item = *rmap_list; + *rmap_list = rmap_item->rmap_list; + remove_rmap_item_from_tree(rmap_item); + free_rmap_item(rmap_item); + } +} + +/* + * Though it's very tempting to unmerge rmap_items from stable tree rather + * than check every pte of a given vma, the locking doesn't quite work for + * that - an rmap_item is assigned to the stable tree after inserting ksm + * page and upping mmap_lock. Nor does it fit with the way we skip dup'ing + * rmap_items from parent to child at fork time (so as not to waste time + * if exit comes before the next scan reaches it). + * + * Similarly, although we'd like to remove rmap_items (so updating counts + * and freeing memory) when unmerging an area, it's easier to leave that + * to the next pass of ksmd - consider, for example, how ksmd might be + * in cmp_and_merge_page on one of the rmap_items we would be removing. + */ +static int unmerge_ksm_pages(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + unsigned long addr; + int err = 0; + + for (addr = start; addr < end && !err; addr += PAGE_SIZE) { + if (ksm_test_exit(vma->vm_mm)) + break; + if (signal_pending(current)) + err = -ERESTARTSYS; + else + err = break_ksm(vma, addr); + } + return err; +} + +static inline struct stable_node *page_stable_node(struct page *page) +{ + return PageKsm(page) ? page_rmapping(page) : NULL; +} + +static inline void set_page_stable_node(struct page *page, + struct stable_node *stable_node) +{ + page->mapping = (void *)((unsigned long)stable_node | PAGE_MAPPING_KSM); +} + +#ifdef CONFIG_SYSFS +/* + * Only called through the sysfs control interface: + */ +static int remove_stable_node(struct stable_node *stable_node) +{ + struct page *page; + int err; + + page = get_ksm_page(stable_node, GET_KSM_PAGE_LOCK); + if (!page) { + /* + * get_ksm_page did remove_node_from_stable_tree itself. + */ + return 0; + } + + /* + * Page could be still mapped if this races with __mmput() running in + * between ksm_exit() and exit_mmap(). Just refuse to let + * merge_across_nodes/max_page_sharing be switched. + */ + err = -EBUSY; + if (!page_mapped(page)) { + /* + * The stable node did not yet appear stale to get_ksm_page(), + * since that allows for an unmapped ksm page to be recognized + * right up until it is freed; but the node is safe to remove. + * This page might be in a pagevec waiting to be freed, + * or it might be PageSwapCache (perhaps under writeback), + * or it might have been removed from swapcache a moment ago. + */ + set_page_stable_node(page, NULL); + remove_node_from_stable_tree(stable_node); + err = 0; + } + + unlock_page(page); + put_page(page); + return err; +} + +static int remove_stable_node_chain(struct stable_node *stable_node, + struct rb_root *root) +{ + struct stable_node *dup; + struct hlist_node *hlist_safe; + + if (!is_stable_node_chain(stable_node)) { + VM_BUG_ON(is_stable_node_dup(stable_node)); + if (remove_stable_node(stable_node)) + return true; + else + return false; + } + + hlist_for_each_entry_safe(dup, hlist_safe, + &stable_node->hlist, hlist_dup) { + VM_BUG_ON(!is_stable_node_dup(dup)); + if (remove_stable_node(dup)) + return true; + } + BUG_ON(!hlist_empty(&stable_node->hlist)); + free_stable_node_chain(stable_node, root); + return false; +} + +static int remove_all_stable_nodes(void) +{ + struct stable_node *stable_node, *next; + int nid; + int err = 0; + + for (nid = 0; nid < ksm_nr_node_ids; nid++) { + while (root_stable_tree[nid].rb_node) { + stable_node = rb_entry(root_stable_tree[nid].rb_node, + struct stable_node, node); + if (remove_stable_node_chain(stable_node, + root_stable_tree + nid)) { + err = -EBUSY; + break; /* proceed to next nid */ + } + cond_resched(); + } + } + list_for_each_entry_safe(stable_node, next, &migrate_nodes, list) { + if (remove_stable_node(stable_node)) + err = -EBUSY; + cond_resched(); + } + return err; +} + +static int unmerge_and_remove_all_rmap_items(void) +{ + struct mm_slot *mm_slot; + struct mm_struct *mm; + struct vm_area_struct *vma; + int err = 0; + + spin_lock(&ksm_mmlist_lock); + ksm_scan.mm_slot = list_entry(ksm_mm_head.mm_list.next, + struct mm_slot, mm_list); + spin_unlock(&ksm_mmlist_lock); + + for (mm_slot = ksm_scan.mm_slot; + mm_slot != &ksm_mm_head; mm_slot = ksm_scan.mm_slot) { + mm = mm_slot->mm; + mmap_read_lock(mm); + for (vma = mm->mmap; vma; vma = vma->vm_next) { + if (ksm_test_exit(mm)) + break; + if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma) + continue; + err = unmerge_ksm_pages(vma, + vma->vm_start, vma->vm_end); + if (err) + goto error; + } + + remove_trailing_rmap_items(mm_slot, &mm_slot->rmap_list); + mmap_read_unlock(mm); + + spin_lock(&ksm_mmlist_lock); + ksm_scan.mm_slot = list_entry(mm_slot->mm_list.next, + struct mm_slot, mm_list); + if (ksm_test_exit(mm)) { + hash_del(&mm_slot->link); + list_del(&mm_slot->mm_list); + spin_unlock(&ksm_mmlist_lock); + + free_mm_slot(mm_slot); + clear_bit(MMF_VM_MERGEABLE, &mm->flags); + mmdrop(mm); + } else + spin_unlock(&ksm_mmlist_lock); + } + + /* Clean up stable nodes, but don't worry if some are still busy */ + remove_all_stable_nodes(); + ksm_scan.seqnr = 0; + return 0; + +error: + mmap_read_unlock(mm); + spin_lock(&ksm_mmlist_lock); + ksm_scan.mm_slot = &ksm_mm_head; + spin_unlock(&ksm_mmlist_lock); + return err; +} +#endif /* CONFIG_SYSFS */ + +static u32 calc_checksum(struct page *page) +{ + u32 checksum; + void *addr = kmap_atomic(page); + checksum = xxhash(addr, PAGE_SIZE, 0); + kunmap_atomic(addr); + return checksum; +} + +static int write_protect_page(struct vm_area_struct *vma, struct page *page, + pte_t *orig_pte) +{ + struct mm_struct *mm = vma->vm_mm; + struct page_vma_mapped_walk pvmw = { + .page = page, + .vma = vma, + }; + int swapped; + int err = -EFAULT; + struct mmu_notifier_range range; + + pvmw.address = page_address_in_vma(page, vma); + if (pvmw.address == -EFAULT) + goto out; + + BUG_ON(PageTransCompound(page)); + + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, + pvmw.address, + pvmw.address + PAGE_SIZE); + mmu_notifier_invalidate_range_start(&range); + + if (!page_vma_mapped_walk(&pvmw)) + goto out_mn; + if (WARN_ONCE(!pvmw.pte, "Unexpected PMD mapping?")) + goto out_unlock; + + if (pte_write(*pvmw.pte) || pte_dirty(*pvmw.pte) || + (pte_protnone(*pvmw.pte) && pte_savedwrite(*pvmw.pte)) || + mm_tlb_flush_pending(mm)) { + pte_t entry; + + swapped = PageSwapCache(page); + flush_cache_page(vma, pvmw.address, page_to_pfn(page)); + /* + * Ok this is tricky, when get_user_pages_fast() run it doesn't + * take any lock, therefore the check that we are going to make + * with the pagecount against the mapcount is racey and + * O_DIRECT can happen right after the check. + * So we clear the pte and flush the tlb before the check + * this assure us that no O_DIRECT can happen after the check + * or in the middle of the check. + * + * No need to notify as we are downgrading page table to read + * only not changing it to point to a new page. + * + * See Documentation/vm/mmu_notifier.rst + */ + entry = ptep_clear_flush(vma, pvmw.address, pvmw.pte); + /* + * Check that no O_DIRECT or similar I/O is in progress on the + * page + */ + if (page_mapcount(page) + 1 + swapped != page_count(page)) { + set_pte_at(mm, pvmw.address, pvmw.pte, entry); + goto out_unlock; + } + if (pte_dirty(entry)) + set_page_dirty(page); + + if (pte_protnone(entry)) + entry = pte_mkclean(pte_clear_savedwrite(entry)); + else + entry = pte_mkclean(pte_wrprotect(entry)); + set_pte_at_notify(mm, pvmw.address, pvmw.pte, entry); + } + *orig_pte = *pvmw.pte; + err = 0; + +out_unlock: + page_vma_mapped_walk_done(&pvmw); +out_mn: + mmu_notifier_invalidate_range_end(&range); +out: + return err; +} + +/** + * replace_page - replace page in vma by new ksm page + * @vma: vma that holds the pte pointing to page + * @page: the page we are replacing by kpage + * @kpage: the ksm page we replace page by + * @orig_pte: the original value of the pte + * + * Returns 0 on success, -EFAULT on failure. + */ +static int replace_page(struct vm_area_struct *vma, struct page *page, + struct page *kpage, pte_t orig_pte) +{ + struct mm_struct *mm = vma->vm_mm; + pmd_t *pmd; + pte_t *ptep; + pte_t newpte; + spinlock_t *ptl; + unsigned long addr; + int err = -EFAULT; + struct mmu_notifier_range range; + + addr = page_address_in_vma(page, vma); + if (addr == -EFAULT) + goto out; + + pmd = mm_find_pmd(mm, addr); + if (!pmd) + goto out; + + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, addr, + addr + PAGE_SIZE); + mmu_notifier_invalidate_range_start(&range); + + ptep = pte_offset_map_lock(mm, pmd, addr, &ptl); + if (!pte_same(*ptep, orig_pte)) { + pte_unmap_unlock(ptep, ptl); + goto out_mn; + } + + /* + * No need to check ksm_use_zero_pages here: we can only have a + * zero_page here if ksm_use_zero_pages was enabled already. + */ + if (!is_zero_pfn(page_to_pfn(kpage))) { + get_page(kpage); + page_add_anon_rmap(kpage, vma, addr, false); + newpte = mk_pte(kpage, vma->vm_page_prot); + } else { + newpte = pte_mkspecial(pfn_pte(page_to_pfn(kpage), + vma->vm_page_prot)); + /* + * We're replacing an anonymous page with a zero page, which is + * not anonymous. We need to do proper accounting otherwise we + * will get wrong values in /proc, and a BUG message in dmesg + * when tearing down the mm. + */ + dec_mm_counter(mm, MM_ANONPAGES); + } + + flush_cache_page(vma, addr, pte_pfn(*ptep)); + /* + * No need to notify as we are replacing a read only page with another + * read only page with the same content. + * + * See Documentation/vm/mmu_notifier.rst + */ + ptep_clear_flush(vma, addr, ptep); + set_pte_at_notify(mm, addr, ptep, newpte); + + page_remove_rmap(page, false); + if (!page_mapped(page)) + try_to_free_swap(page); + put_page(page); + + pte_unmap_unlock(ptep, ptl); + err = 0; +out_mn: + mmu_notifier_invalidate_range_end(&range); +out: + return err; +} + +/* + * try_to_merge_one_page - take two pages and merge them into one + * @vma: the vma that holds the pte pointing to page + * @page: the PageAnon page that we want to replace with kpage + * @kpage: the PageKsm page that we want to map instead of page, + * or NULL the first time when we want to use page as kpage. + * + * This function returns 0 if the pages were merged, -EFAULT otherwise. + */ +static int try_to_merge_one_page(struct vm_area_struct *vma, + struct page *page, struct page *kpage) +{ + pte_t orig_pte = __pte(0); + int err = -EFAULT; + + if (page == kpage) /* ksm page forked */ + return 0; + + if (!PageAnon(page)) + goto out; + + /* + * We need the page lock to read a stable PageSwapCache in + * write_protect_page(). We use trylock_page() instead of + * lock_page() because we don't want to wait here - we + * prefer to continue scanning and merging different pages, + * then come back to this page when it is unlocked. + */ + if (!trylock_page(page)) + goto out; + + if (PageTransCompound(page)) { + if (split_huge_page(page)) + goto out_unlock; + } + + /* + * If this anonymous page is mapped only here, its pte may need + * to be write-protected. If it's mapped elsewhere, all of its + * ptes are necessarily already write-protected. But in either + * case, we need to lock and check page_count is not raised. + */ + if (write_protect_page(vma, page, &orig_pte) == 0) { + if (!kpage) { + /* + * While we hold page lock, upgrade page from + * PageAnon+anon_vma to PageKsm+NULL stable_node: + * stable_tree_insert() will update stable_node. + */ + set_page_stable_node(page, NULL); + mark_page_accessed(page); + /* + * Page reclaim just frees a clean page with no dirty + * ptes: make sure that the ksm page would be swapped. + */ + if (!PageDirty(page)) + SetPageDirty(page); + err = 0; + } else if (pages_identical(page, kpage)) + err = replace_page(vma, page, kpage, orig_pte); + } + + if ((vma->vm_flags & VM_LOCKED) && kpage && !err) { + munlock_vma_page(page); + if (!PageMlocked(kpage)) { + unlock_page(page); + lock_page(kpage); + mlock_vma_page(kpage); + page = kpage; /* for final unlock */ + } + } + +out_unlock: + unlock_page(page); +out: + return err; +} + +/* + * try_to_merge_with_ksm_page - like try_to_merge_two_pages, + * but no new kernel page is allocated: kpage must already be a ksm page. + * + * This function returns 0 if the pages were merged, -EFAULT otherwise. + */ +static int try_to_merge_with_ksm_page(struct rmap_item *rmap_item, + struct page *page, struct page *kpage) +{ + struct mm_struct *mm = rmap_item->mm; + struct vm_area_struct *vma; + int err = -EFAULT; + + mmap_read_lock(mm); + vma = find_mergeable_vma(mm, rmap_item->address); + if (!vma) + goto out; + + err = try_to_merge_one_page(vma, page, kpage); + if (err) + goto out; + + /* Unstable nid is in union with stable anon_vma: remove first */ + remove_rmap_item_from_tree(rmap_item); + + /* Must get reference to anon_vma while still holding mmap_lock */ + rmap_item->anon_vma = vma->anon_vma; + get_anon_vma(vma->anon_vma); +out: + mmap_read_unlock(mm); + return err; +} + +/* + * try_to_merge_two_pages - take two identical pages and prepare them + * to be merged into one page. + * + * This function returns the kpage if we successfully merged two identical + * pages into one ksm page, NULL otherwise. + * + * Note that this function upgrades page to ksm page: if one of the pages + * is already a ksm page, try_to_merge_with_ksm_page should be used. + */ +static struct page *try_to_merge_two_pages(struct rmap_item *rmap_item, + struct page *page, + struct rmap_item *tree_rmap_item, + struct page *tree_page) +{ + int err; + + err = try_to_merge_with_ksm_page(rmap_item, page, NULL); + if (!err) { + err = try_to_merge_with_ksm_page(tree_rmap_item, + tree_page, page); + /* + * If that fails, we have a ksm page with only one pte + * pointing to it: so break it. + */ + if (err) + break_cow(rmap_item); + } + return err ? NULL : page; +} + +static __always_inline +bool __is_page_sharing_candidate(struct stable_node *stable_node, int offset) +{ + VM_BUG_ON(stable_node->rmap_hlist_len < 0); + /* + * Check that at least one mapping still exists, otherwise + * there's no much point to merge and share with this + * stable_node, as the underlying tree_page of the other + * sharer is going to be freed soon. + */ + return stable_node->rmap_hlist_len && + stable_node->rmap_hlist_len + offset < ksm_max_page_sharing; +} + +static __always_inline +bool is_page_sharing_candidate(struct stable_node *stable_node) +{ + return __is_page_sharing_candidate(stable_node, 0); +} + +static struct page *stable_node_dup(struct stable_node **_stable_node_dup, + struct stable_node **_stable_node, + struct rb_root *root, + bool prune_stale_stable_nodes) +{ + struct stable_node *dup, *found = NULL, *stable_node = *_stable_node; + struct hlist_node *hlist_safe; + struct page *_tree_page, *tree_page = NULL; + int nr = 0; + int found_rmap_hlist_len; + + if (!prune_stale_stable_nodes || + time_before(jiffies, stable_node->chain_prune_time + + msecs_to_jiffies( + ksm_stable_node_chains_prune_millisecs))) + prune_stale_stable_nodes = false; + else + stable_node->chain_prune_time = jiffies; + + hlist_for_each_entry_safe(dup, hlist_safe, + &stable_node->hlist, hlist_dup) { + cond_resched(); + /* + * We must walk all stable_node_dup to prune the stale + * stable nodes during lookup. + * + * get_ksm_page can drop the nodes from the + * stable_node->hlist if they point to freed pages + * (that's why we do a _safe walk). The "dup" + * stable_node parameter itself will be freed from + * under us if it returns NULL. + */ + _tree_page = get_ksm_page(dup, GET_KSM_PAGE_NOLOCK); + if (!_tree_page) + continue; + nr += 1; + if (is_page_sharing_candidate(dup)) { + if (!found || + dup->rmap_hlist_len > found_rmap_hlist_len) { + if (found) + put_page(tree_page); + found = dup; + found_rmap_hlist_len = found->rmap_hlist_len; + tree_page = _tree_page; + + /* skip put_page for found dup */ + if (!prune_stale_stable_nodes) + break; + continue; + } + } + put_page(_tree_page); + } + + if (found) { + /* + * nr is counting all dups in the chain only if + * prune_stale_stable_nodes is true, otherwise we may + * break the loop at nr == 1 even if there are + * multiple entries. + */ + if (prune_stale_stable_nodes && nr == 1) { + /* + * If there's not just one entry it would + * corrupt memory, better BUG_ON. In KSM + * context with no lock held it's not even + * fatal. + */ + BUG_ON(stable_node->hlist.first->next); + + /* + * There's just one entry and it is below the + * deduplication limit so drop the chain. + */ + rb_replace_node(&stable_node->node, &found->node, + root); + free_stable_node(stable_node); + ksm_stable_node_chains--; + ksm_stable_node_dups--; + /* + * NOTE: the caller depends on the stable_node + * to be equal to stable_node_dup if the chain + * was collapsed. + */ + *_stable_node = found; + /* + * Just for robustneess as stable_node is + * otherwise left as a stable pointer, the + * compiler shall optimize it away at build + * time. + */ + stable_node = NULL; + } else if (stable_node->hlist.first != &found->hlist_dup && + __is_page_sharing_candidate(found, 1)) { + /* + * If the found stable_node dup can accept one + * more future merge (in addition to the one + * that is underway) and is not at the head of + * the chain, put it there so next search will + * be quicker in the !prune_stale_stable_nodes + * case. + * + * NOTE: it would be inaccurate to use nr > 1 + * instead of checking the hlist.first pointer + * directly, because in the + * prune_stale_stable_nodes case "nr" isn't + * the position of the found dup in the chain, + * but the total number of dups in the chain. + */ + hlist_del(&found->hlist_dup); + hlist_add_head(&found->hlist_dup, + &stable_node->hlist); + } + } + + *_stable_node_dup = found; + return tree_page; +} + +static struct stable_node *stable_node_dup_any(struct stable_node *stable_node, + struct rb_root *root) +{ + if (!is_stable_node_chain(stable_node)) + return stable_node; + if (hlist_empty(&stable_node->hlist)) { + free_stable_node_chain(stable_node, root); + return NULL; + } + return hlist_entry(stable_node->hlist.first, + typeof(*stable_node), hlist_dup); +} + +/* + * Like for get_ksm_page, this function can free the *_stable_node and + * *_stable_node_dup if the returned tree_page is NULL. + * + * It can also free and overwrite *_stable_node with the found + * stable_node_dup if the chain is collapsed (in which case + * *_stable_node will be equal to *_stable_node_dup like if the chain + * never existed). It's up to the caller to verify tree_page is not + * NULL before dereferencing *_stable_node or *_stable_node_dup. + * + * *_stable_node_dup is really a second output parameter of this + * function and will be overwritten in all cases, the caller doesn't + * need to initialize it. + */ +static struct page *__stable_node_chain(struct stable_node **_stable_node_dup, + struct stable_node **_stable_node, + struct rb_root *root, + bool prune_stale_stable_nodes) +{ + struct stable_node *stable_node = *_stable_node; + if (!is_stable_node_chain(stable_node)) { + if (is_page_sharing_candidate(stable_node)) { + *_stable_node_dup = stable_node; + return get_ksm_page(stable_node, GET_KSM_PAGE_NOLOCK); + } + /* + * _stable_node_dup set to NULL means the stable_node + * reached the ksm_max_page_sharing limit. + */ + *_stable_node_dup = NULL; + return NULL; + } + return stable_node_dup(_stable_node_dup, _stable_node, root, + prune_stale_stable_nodes); +} + +static __always_inline struct page *chain_prune(struct stable_node **s_n_d, + struct stable_node **s_n, + struct rb_root *root) +{ + return __stable_node_chain(s_n_d, s_n, root, true); +} + +static __always_inline struct page *chain(struct stable_node **s_n_d, + struct stable_node *s_n, + struct rb_root *root) +{ + struct stable_node *old_stable_node = s_n; + struct page *tree_page; + + tree_page = __stable_node_chain(s_n_d, &s_n, root, false); + /* not pruning dups so s_n cannot have changed */ + VM_BUG_ON(s_n != old_stable_node); + return tree_page; +} + +/* + * stable_tree_search - search for page inside the stable tree + * + * This function checks if there is a page inside the stable tree + * with identical content to the page that we are scanning right now. + * + * This function returns the stable tree node of identical content if found, + * NULL otherwise. + */ +static struct page *stable_tree_search(struct page *page) +{ + int nid; + struct rb_root *root; + struct rb_node **new; + struct rb_node *parent; + struct stable_node *stable_node, *stable_node_dup, *stable_node_any; + struct stable_node *page_node; + + page_node = page_stable_node(page); + if (page_node && page_node->head != &migrate_nodes) { + /* ksm page forked */ + get_page(page); + return page; + } + + nid = get_kpfn_nid(page_to_pfn(page)); + root = root_stable_tree + nid; +again: + new = &root->rb_node; + parent = NULL; + + while (*new) { + struct page *tree_page; + int ret; + + cond_resched(); + stable_node = rb_entry(*new, struct stable_node, node); + stable_node_any = NULL; + tree_page = chain_prune(&stable_node_dup, &stable_node, root); + /* + * NOTE: stable_node may have been freed by + * chain_prune() if the returned stable_node_dup is + * not NULL. stable_node_dup may have been inserted in + * the rbtree instead as a regular stable_node (in + * order to collapse the stable_node chain if a single + * stable_node dup was found in it). In such case the + * stable_node is overwritten by the calleee to point + * to the stable_node_dup that was collapsed in the + * stable rbtree and stable_node will be equal to + * stable_node_dup like if the chain never existed. + */ + if (!stable_node_dup) { + /* + * Either all stable_node dups were full in + * this stable_node chain, or this chain was + * empty and should be rb_erased. + */ + stable_node_any = stable_node_dup_any(stable_node, + root); + if (!stable_node_any) { + /* rb_erase just run */ + goto again; + } + /* + * Take any of the stable_node dups page of + * this stable_node chain to let the tree walk + * continue. All KSM pages belonging to the + * stable_node dups in a stable_node chain + * have the same content and they're + * write protected at all times. Any will work + * fine to continue the walk. + */ + tree_page = get_ksm_page(stable_node_any, + GET_KSM_PAGE_NOLOCK); + } + VM_BUG_ON(!stable_node_dup ^ !!stable_node_any); + if (!tree_page) { + /* + * If we walked over a stale stable_node, + * get_ksm_page() will call rb_erase() and it + * may rebalance the tree from under us. So + * restart the search from scratch. Returning + * NULL would be safe too, but we'd generate + * false negative insertions just because some + * stable_node was stale. + */ + goto again; + } + + ret = memcmp_pages(page, tree_page); + put_page(tree_page); + + parent = *new; + if (ret < 0) + new = &parent->rb_left; + else if (ret > 0) + new = &parent->rb_right; + else { + if (page_node) { + VM_BUG_ON(page_node->head != &migrate_nodes); + /* + * Test if the migrated page should be merged + * into a stable node dup. If the mapcount is + * 1 we can migrate it with another KSM page + * without adding it to the chain. + */ + if (page_mapcount(page) > 1) + goto chain_append; + } + + if (!stable_node_dup) { + /* + * If the stable_node is a chain and + * we got a payload match in memcmp + * but we cannot merge the scanned + * page in any of the existing + * stable_node dups because they're + * all full, we need to wait the + * scanned page to find itself a match + * in the unstable tree to create a + * brand new KSM page to add later to + * the dups of this stable_node. + */ + return NULL; + } + + /* + * Lock and unlock the stable_node's page (which + * might already have been migrated) so that page + * migration is sure to notice its raised count. + * It would be more elegant to return stable_node + * than kpage, but that involves more changes. + */ + tree_page = get_ksm_page(stable_node_dup, + GET_KSM_PAGE_TRYLOCK); + + if (PTR_ERR(tree_page) == -EBUSY) + return ERR_PTR(-EBUSY); + + if (unlikely(!tree_page)) + /* + * The tree may have been rebalanced, + * so re-evaluate parent and new. + */ + goto again; + unlock_page(tree_page); + + if (get_kpfn_nid(stable_node_dup->kpfn) != + NUMA(stable_node_dup->nid)) { + put_page(tree_page); + goto replace; + } + return tree_page; + } + } + + if (!page_node) + return NULL; + + list_del(&page_node->list); + DO_NUMA(page_node->nid = nid); + rb_link_node(&page_node->node, parent, new); + rb_insert_color(&page_node->node, root); +out: + if (is_page_sharing_candidate(page_node)) { + get_page(page); + return page; + } else + return NULL; + +replace: + /* + * If stable_node was a chain and chain_prune collapsed it, + * stable_node has been updated to be the new regular + * stable_node. A collapse of the chain is indistinguishable + * from the case there was no chain in the stable + * rbtree. Otherwise stable_node is the chain and + * stable_node_dup is the dup to replace. + */ + if (stable_node_dup == stable_node) { + VM_BUG_ON(is_stable_node_chain(stable_node_dup)); + VM_BUG_ON(is_stable_node_dup(stable_node_dup)); + /* there is no chain */ + if (page_node) { + VM_BUG_ON(page_node->head != &migrate_nodes); + list_del(&page_node->list); + DO_NUMA(page_node->nid = nid); + rb_replace_node(&stable_node_dup->node, + &page_node->node, + root); + if (is_page_sharing_candidate(page_node)) + get_page(page); + else + page = NULL; + } else { + rb_erase(&stable_node_dup->node, root); + page = NULL; + } + } else { + VM_BUG_ON(!is_stable_node_chain(stable_node)); + __stable_node_dup_del(stable_node_dup); + if (page_node) { + VM_BUG_ON(page_node->head != &migrate_nodes); + list_del(&page_node->list); + DO_NUMA(page_node->nid = nid); + stable_node_chain_add_dup(page_node, stable_node); + if (is_page_sharing_candidate(page_node)) + get_page(page); + else + page = NULL; + } else { + page = NULL; + } + } + stable_node_dup->head = &migrate_nodes; + list_add(&stable_node_dup->list, stable_node_dup->head); + return page; + +chain_append: + /* stable_node_dup could be null if it reached the limit */ + if (!stable_node_dup) + stable_node_dup = stable_node_any; + /* + * If stable_node was a chain and chain_prune collapsed it, + * stable_node has been updated to be the new regular + * stable_node. A collapse of the chain is indistinguishable + * from the case there was no chain in the stable + * rbtree. Otherwise stable_node is the chain and + * stable_node_dup is the dup to replace. + */ + if (stable_node_dup == stable_node) { + VM_BUG_ON(is_stable_node_chain(stable_node_dup)); + VM_BUG_ON(is_stable_node_dup(stable_node_dup)); + /* chain is missing so create it */ + stable_node = alloc_stable_node_chain(stable_node_dup, + root); + if (!stable_node) + return NULL; + } + /* + * Add this stable_node dup that was + * migrated to the stable_node chain + * of the current nid for this page + * content. + */ + VM_BUG_ON(!is_stable_node_chain(stable_node)); + VM_BUG_ON(!is_stable_node_dup(stable_node_dup)); + VM_BUG_ON(page_node->head != &migrate_nodes); + list_del(&page_node->list); + DO_NUMA(page_node->nid = nid); + stable_node_chain_add_dup(page_node, stable_node); + goto out; +} + +/* + * stable_tree_insert - insert stable tree node pointing to new ksm page + * into the stable tree. + * + * This function returns the stable tree node just allocated on success, + * NULL otherwise. + */ +static struct stable_node *stable_tree_insert(struct page *kpage) +{ + int nid; + unsigned long kpfn; + struct rb_root *root; + struct rb_node **new; + struct rb_node *parent; + struct stable_node *stable_node, *stable_node_dup, *stable_node_any; + bool need_chain = false; + + kpfn = page_to_pfn(kpage); + nid = get_kpfn_nid(kpfn); + root = root_stable_tree + nid; +again: + parent = NULL; + new = &root->rb_node; + + while (*new) { + struct page *tree_page; + int ret; + + cond_resched(); + stable_node = rb_entry(*new, struct stable_node, node); + stable_node_any = NULL; + tree_page = chain(&stable_node_dup, stable_node, root); + if (!stable_node_dup) { + /* + * Either all stable_node dups were full in + * this stable_node chain, or this chain was + * empty and should be rb_erased. + */ + stable_node_any = stable_node_dup_any(stable_node, + root); + if (!stable_node_any) { + /* rb_erase just run */ + goto again; + } + /* + * Take any of the stable_node dups page of + * this stable_node chain to let the tree walk + * continue. All KSM pages belonging to the + * stable_node dups in a stable_node chain + * have the same content and they're + * write protected at all times. Any will work + * fine to continue the walk. + */ + tree_page = get_ksm_page(stable_node_any, + GET_KSM_PAGE_NOLOCK); + } + VM_BUG_ON(!stable_node_dup ^ !!stable_node_any); + if (!tree_page) { + /* + * If we walked over a stale stable_node, + * get_ksm_page() will call rb_erase() and it + * may rebalance the tree from under us. So + * restart the search from scratch. Returning + * NULL would be safe too, but we'd generate + * false negative insertions just because some + * stable_node was stale. + */ + goto again; + } + + ret = memcmp_pages(kpage, tree_page); + put_page(tree_page); + + parent = *new; + if (ret < 0) + new = &parent->rb_left; + else if (ret > 0) + new = &parent->rb_right; + else { + need_chain = true; + break; + } + } + + stable_node_dup = alloc_stable_node(); + if (!stable_node_dup) + return NULL; + + INIT_HLIST_HEAD(&stable_node_dup->hlist); + stable_node_dup->kpfn = kpfn; + set_page_stable_node(kpage, stable_node_dup); + stable_node_dup->rmap_hlist_len = 0; + DO_NUMA(stable_node_dup->nid = nid); + if (!need_chain) { + rb_link_node(&stable_node_dup->node, parent, new); + rb_insert_color(&stable_node_dup->node, root); + } else { + if (!is_stable_node_chain(stable_node)) { + struct stable_node *orig = stable_node; + /* chain is missing so create it */ + stable_node = alloc_stable_node_chain(orig, root); + if (!stable_node) { + free_stable_node(stable_node_dup); + return NULL; + } + } + stable_node_chain_add_dup(stable_node_dup, stable_node); + } + + return stable_node_dup; +} + +/* + * unstable_tree_search_insert - search for identical page, + * else insert rmap_item into the unstable tree. + * + * This function searches for a page in the unstable tree identical to the + * page currently being scanned; and if no identical page is found in the + * tree, we insert rmap_item as a new object into the unstable tree. + * + * This function returns pointer to rmap_item found to be identical + * to the currently scanned page, NULL otherwise. + * + * This function does both searching and inserting, because they share + * the same walking algorithm in an rbtree. + */ +static +struct rmap_item *unstable_tree_search_insert(struct rmap_item *rmap_item, + struct page *page, + struct page **tree_pagep) +{ + struct rb_node **new; + struct rb_root *root; + struct rb_node *parent = NULL; + int nid; + + nid = get_kpfn_nid(page_to_pfn(page)); + root = root_unstable_tree + nid; + new = &root->rb_node; + + while (*new) { + struct rmap_item *tree_rmap_item; + struct page *tree_page; + int ret; + + cond_resched(); + tree_rmap_item = rb_entry(*new, struct rmap_item, node); + tree_page = get_mergeable_page(tree_rmap_item); + if (!tree_page) + return NULL; + + /* + * Don't substitute a ksm page for a forked page. + */ + if (page == tree_page) { + put_page(tree_page); + return NULL; + } + + ret = memcmp_pages(page, tree_page); + + parent = *new; + if (ret < 0) { + put_page(tree_page); + new = &parent->rb_left; + } else if (ret > 0) { + put_page(tree_page); + new = &parent->rb_right; + } else if (!ksm_merge_across_nodes && + page_to_nid(tree_page) != nid) { + /* + * If tree_page has been migrated to another NUMA node, + * it will be flushed out and put in the right unstable + * tree next time: only merge with it when across_nodes. + */ + put_page(tree_page); + return NULL; + } else { + *tree_pagep = tree_page; + return tree_rmap_item; + } + } + + rmap_item->address |= UNSTABLE_FLAG; + rmap_item->address |= (ksm_scan.seqnr & SEQNR_MASK); + DO_NUMA(rmap_item->nid = nid); + rb_link_node(&rmap_item->node, parent, new); + rb_insert_color(&rmap_item->node, root); + + ksm_pages_unshared++; + return NULL; +} + +/* + * stable_tree_append - add another rmap_item to the linked list of + * rmap_items hanging off a given node of the stable tree, all sharing + * the same ksm page. + */ +static void stable_tree_append(struct rmap_item *rmap_item, + struct stable_node *stable_node, + bool max_page_sharing_bypass) +{ + /* + * rmap won't find this mapping if we don't insert the + * rmap_item in the right stable_node + * duplicate. page_migration could break later if rmap breaks, + * so we can as well crash here. We really need to check for + * rmap_hlist_len == STABLE_NODE_CHAIN, but we can as well check + * for other negative values as an underflow if detected here + * for the first time (and not when decreasing rmap_hlist_len) + * would be sign of memory corruption in the stable_node. + */ + BUG_ON(stable_node->rmap_hlist_len < 0); + + stable_node->rmap_hlist_len++; + if (!max_page_sharing_bypass) + /* possibly non fatal but unexpected overflow, only warn */ + WARN_ON_ONCE(stable_node->rmap_hlist_len > + ksm_max_page_sharing); + + rmap_item->head = stable_node; + rmap_item->address |= STABLE_FLAG; + hlist_add_head(&rmap_item->hlist, &stable_node->hlist); + + if (rmap_item->hlist.next) + ksm_pages_sharing++; + else + ksm_pages_shared++; +} + +/* + * cmp_and_merge_page - first see if page can be merged into the stable tree; + * if not, compare checksum to previous and if it's the same, see if page can + * be inserted into the unstable tree, or merged with a page already there and + * both transferred to the stable tree. + * + * @page: the page that we are searching identical page to. + * @rmap_item: the reverse mapping into the virtual address of this page + */ +static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item) +{ + struct mm_struct *mm = rmap_item->mm; + struct rmap_item *tree_rmap_item; + struct page *tree_page = NULL; + struct stable_node *stable_node; + struct page *kpage; + unsigned int checksum; + int err; + bool max_page_sharing_bypass = false; + + stable_node = page_stable_node(page); + if (stable_node) { + if (stable_node->head != &migrate_nodes && + get_kpfn_nid(READ_ONCE(stable_node->kpfn)) != + NUMA(stable_node->nid)) { + stable_node_dup_del(stable_node); + stable_node->head = &migrate_nodes; + list_add(&stable_node->list, stable_node->head); + } + if (stable_node->head != &migrate_nodes && + rmap_item->head == stable_node) + return; + /* + * If it's a KSM fork, allow it to go over the sharing limit + * without warnings. + */ + if (!is_page_sharing_candidate(stable_node)) + max_page_sharing_bypass = true; + } + + /* We first start with searching the page inside the stable tree */ + kpage = stable_tree_search(page); + if (kpage == page && rmap_item->head == stable_node) { + put_page(kpage); + return; + } + + remove_rmap_item_from_tree(rmap_item); + + if (kpage) { + if (PTR_ERR(kpage) == -EBUSY) + return; + + err = try_to_merge_with_ksm_page(rmap_item, page, kpage); + if (!err) { + /* + * The page was successfully merged: + * add its rmap_item to the stable tree. + */ + lock_page(kpage); + stable_tree_append(rmap_item, page_stable_node(kpage), + max_page_sharing_bypass); + unlock_page(kpage); + } + put_page(kpage); + return; + } + + /* + * If the hash value of the page has changed from the last time + * we calculated it, this page is changing frequently: therefore we + * don't want to insert it in the unstable tree, and we don't want + * to waste our time searching for something identical to it there. + */ + checksum = calc_checksum(page); + if (rmap_item->oldchecksum != checksum) { + rmap_item->oldchecksum = checksum; + return; + } + + /* + * Same checksum as an empty page. We attempt to merge it with the + * appropriate zero page if the user enabled this via sysfs. + */ + if (ksm_use_zero_pages && (checksum == zero_checksum)) { + struct vm_area_struct *vma; + + mmap_read_lock(mm); + vma = find_mergeable_vma(mm, rmap_item->address); + if (vma) { + err = try_to_merge_one_page(vma, page, + ZERO_PAGE(rmap_item->address)); + } else { + /* + * If the vma is out of date, we do not need to + * continue. + */ + err = 0; + } + mmap_read_unlock(mm); + /* + * In case of failure, the page was not really empty, so we + * need to continue. Otherwise we're done. + */ + if (!err) + return; + } + tree_rmap_item = + unstable_tree_search_insert(rmap_item, page, &tree_page); + if (tree_rmap_item) { + bool split; + + kpage = try_to_merge_two_pages(rmap_item, page, + tree_rmap_item, tree_page); + /* + * If both pages we tried to merge belong to the same compound + * page, then we actually ended up increasing the reference + * count of the same compound page twice, and split_huge_page + * failed. + * Here we set a flag if that happened, and we use it later to + * try split_huge_page again. Since we call put_page right + * afterwards, the reference count will be correct and + * split_huge_page should succeed. + */ + split = PageTransCompound(page) + && compound_head(page) == compound_head(tree_page); + put_page(tree_page); + if (kpage) { + /* + * The pages were successfully merged: insert new + * node in the stable tree and add both rmap_items. + */ + lock_page(kpage); + stable_node = stable_tree_insert(kpage); + if (stable_node) { + stable_tree_append(tree_rmap_item, stable_node, + false); + stable_tree_append(rmap_item, stable_node, + false); + } + unlock_page(kpage); + + /* + * If we fail to insert the page into the stable tree, + * we will have 2 virtual addresses that are pointing + * to a ksm page left outside the stable tree, + * in which case we need to break_cow on both. + */ + if (!stable_node) { + break_cow(tree_rmap_item); + break_cow(rmap_item); + } + } else if (split) { + /* + * We are here if we tried to merge two pages and + * failed because they both belonged to the same + * compound page. We will split the page now, but no + * merging will take place. + * We do not want to add the cost of a full lock; if + * the page is locked, it is better to skip it and + * perhaps try again later. + */ + if (!trylock_page(page)) + return; + split_huge_page(page); + unlock_page(page); + } + } +} + +static struct rmap_item *get_next_rmap_item(struct mm_slot *mm_slot, + struct rmap_item **rmap_list, + unsigned long addr) +{ + struct rmap_item *rmap_item; + + while (*rmap_list) { + rmap_item = *rmap_list; + if ((rmap_item->address & PAGE_MASK) == addr) + return rmap_item; + if (rmap_item->address > addr) + break; + *rmap_list = rmap_item->rmap_list; + remove_rmap_item_from_tree(rmap_item); + free_rmap_item(rmap_item); + } + + rmap_item = alloc_rmap_item(); + if (rmap_item) { + /* It has already been zeroed */ + rmap_item->mm = mm_slot->mm; + rmap_item->address = addr; + rmap_item->rmap_list = *rmap_list; + *rmap_list = rmap_item; + } + return rmap_item; +} + +static struct rmap_item *scan_get_next_rmap_item(struct page **page) +{ + struct mm_struct *mm; + struct mm_slot *slot; + struct vm_area_struct *vma; + struct rmap_item *rmap_item; + int nid; + + if (list_empty(&ksm_mm_head.mm_list)) + return NULL; + + slot = ksm_scan.mm_slot; + if (slot == &ksm_mm_head) { + /* + * A number of pages can hang around indefinitely on per-cpu + * pagevecs, raised page count preventing write_protect_page + * from merging them. Though it doesn't really matter much, + * it is puzzling to see some stuck in pages_volatile until + * other activity jostles them out, and they also prevented + * LTP's KSM test from succeeding deterministically; so drain + * them here (here rather than on entry to ksm_do_scan(), + * so we don't IPI too often when pages_to_scan is set low). + */ + lru_add_drain_all(); + + /* + * Whereas stale stable_nodes on the stable_tree itself + * get pruned in the regular course of stable_tree_search(), + * those moved out to the migrate_nodes list can accumulate: + * so prune them once before each full scan. + */ + if (!ksm_merge_across_nodes) { + struct stable_node *stable_node, *next; + struct page *page; + + list_for_each_entry_safe(stable_node, next, + &migrate_nodes, list) { + page = get_ksm_page(stable_node, + GET_KSM_PAGE_NOLOCK); + if (page) + put_page(page); + cond_resched(); + } + } + + for (nid = 0; nid < ksm_nr_node_ids; nid++) + root_unstable_tree[nid] = RB_ROOT; + + spin_lock(&ksm_mmlist_lock); + slot = list_entry(slot->mm_list.next, struct mm_slot, mm_list); + ksm_scan.mm_slot = slot; + spin_unlock(&ksm_mmlist_lock); + /* + * Although we tested list_empty() above, a racing __ksm_exit + * of the last mm on the list may have removed it since then. + */ + if (slot == &ksm_mm_head) + return NULL; +next_mm: + ksm_scan.address = 0; + ksm_scan.rmap_list = &slot->rmap_list; + } + + mm = slot->mm; + mmap_read_lock(mm); + if (ksm_test_exit(mm)) + vma = NULL; + else + vma = find_vma(mm, ksm_scan.address); + + for (; vma; vma = vma->vm_next) { + if (!(vma->vm_flags & VM_MERGEABLE)) + continue; + if (ksm_scan.address < vma->vm_start) + ksm_scan.address = vma->vm_start; + if (!vma->anon_vma) + ksm_scan.address = vma->vm_end; + + while (ksm_scan.address < vma->vm_end) { + if (ksm_test_exit(mm)) + break; + *page = follow_page(vma, ksm_scan.address, FOLL_GET); + if (IS_ERR_OR_NULL(*page)) { + ksm_scan.address += PAGE_SIZE; + cond_resched(); + continue; + } + if (PageAnon(*page)) { + flush_anon_page(vma, *page, ksm_scan.address); + flush_dcache_page(*page); + rmap_item = get_next_rmap_item(slot, + ksm_scan.rmap_list, ksm_scan.address); + if (rmap_item) { + ksm_scan.rmap_list = + &rmap_item->rmap_list; + ksm_scan.address += PAGE_SIZE; + } else + put_page(*page); + mmap_read_unlock(mm); + return rmap_item; + } + put_page(*page); + ksm_scan.address += PAGE_SIZE; + cond_resched(); + } + } + + if (ksm_test_exit(mm)) { + ksm_scan.address = 0; + ksm_scan.rmap_list = &slot->rmap_list; + } + /* + * Nuke all the rmap_items that are above this current rmap: + * because there were no VM_MERGEABLE vmas with such addresses. + */ + remove_trailing_rmap_items(slot, ksm_scan.rmap_list); + + spin_lock(&ksm_mmlist_lock); + ksm_scan.mm_slot = list_entry(slot->mm_list.next, + struct mm_slot, mm_list); + if (ksm_scan.address == 0) { + /* + * We've completed a full scan of all vmas, holding mmap_lock + * throughout, and found no VM_MERGEABLE: so do the same as + * __ksm_exit does to remove this mm from all our lists now. + * This applies either when cleaning up after __ksm_exit + * (but beware: we can reach here even before __ksm_exit), + * or when all VM_MERGEABLE areas have been unmapped (and + * mmap_lock then protects against race with MADV_MERGEABLE). + */ + hash_del(&slot->link); + list_del(&slot->mm_list); + spin_unlock(&ksm_mmlist_lock); + + free_mm_slot(slot); + clear_bit(MMF_VM_MERGEABLE, &mm->flags); + mmap_read_unlock(mm); + mmdrop(mm); + } else { + mmap_read_unlock(mm); + /* + * mmap_read_unlock(mm) first because after + * spin_unlock(&ksm_mmlist_lock) run, the "mm" may + * already have been freed under us by __ksm_exit() + * because the "mm_slot" is still hashed and + * ksm_scan.mm_slot doesn't point to it anymore. + */ + spin_unlock(&ksm_mmlist_lock); + } + + /* Repeat until we've completed scanning the whole list */ + slot = ksm_scan.mm_slot; + if (slot != &ksm_mm_head) + goto next_mm; + + ksm_scan.seqnr++; + return NULL; +} + +/** + * ksm_do_scan - the ksm scanner main worker function. + * @scan_npages: number of pages we want to scan before we return. + */ +static void ksm_do_scan(unsigned int scan_npages) +{ + struct rmap_item *rmap_item; + struct page *page; + + while (scan_npages-- && likely(!freezing(current))) { + cond_resched(); + rmap_item = scan_get_next_rmap_item(&page); + if (!rmap_item) + return; + cmp_and_merge_page(page, rmap_item); + put_page(page); + } +} + +static int ksmd_should_run(void) +{ + return (ksm_run & KSM_RUN_MERGE) && !list_empty(&ksm_mm_head.mm_list); +} + +static int ksm_scan_thread(void *nothing) +{ + unsigned int sleep_ms; + + set_freezable(); + set_user_nice(current, 5); + + while (!kthread_should_stop()) { + mutex_lock(&ksm_thread_mutex); + wait_while_offlining(); + if (ksmd_should_run()) + ksm_do_scan(ksm_thread_pages_to_scan); + mutex_unlock(&ksm_thread_mutex); + + try_to_freeze(); + + if (ksmd_should_run()) { + sleep_ms = READ_ONCE(ksm_thread_sleep_millisecs); + wait_event_interruptible_timeout(ksm_iter_wait, + sleep_ms != READ_ONCE(ksm_thread_sleep_millisecs), + msecs_to_jiffies(sleep_ms)); + } else { + wait_event_freezable(ksm_thread_wait, + ksmd_should_run() || kthread_should_stop()); + } + } + return 0; +} + +int ksm_madvise(struct vm_area_struct *vma, unsigned long start, + unsigned long end, int advice, unsigned long *vm_flags) +{ + struct mm_struct *mm = vma->vm_mm; + int err; + + switch (advice) { + case MADV_MERGEABLE: + /* + * Be somewhat over-protective for now! + */ + if (*vm_flags & (VM_MERGEABLE | VM_SHARED | VM_MAYSHARE | + VM_PFNMAP | VM_IO | VM_DONTEXPAND | + VM_HUGETLB | VM_MIXEDMAP)) + return 0; /* just ignore the advice */ + + if (vma_is_dax(vma)) + return 0; + +#ifdef VM_SAO + if (*vm_flags & VM_SAO) + return 0; +#endif +#ifdef VM_SPARC_ADI + if (*vm_flags & VM_SPARC_ADI) + return 0; +#endif + + if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) { + err = __ksm_enter(mm); + if (err) + return err; + } + + *vm_flags |= VM_MERGEABLE; + break; + + case MADV_UNMERGEABLE: + if (!(*vm_flags & VM_MERGEABLE)) + return 0; /* just ignore the advice */ + + if (vma->anon_vma) { + err = unmerge_ksm_pages(vma, start, end); + if (err) + return err; + } + + *vm_flags &= ~VM_MERGEABLE; + break; + } + + return 0; +} +EXPORT_SYMBOL_GPL(ksm_madvise); + +int __ksm_enter(struct mm_struct *mm) +{ + struct mm_slot *mm_slot; + int needs_wakeup; + + mm_slot = alloc_mm_slot(); + if (!mm_slot) + return -ENOMEM; + + /* Check ksm_run too? Would need tighter locking */ + needs_wakeup = list_empty(&ksm_mm_head.mm_list); + + spin_lock(&ksm_mmlist_lock); + insert_to_mm_slots_hash(mm, mm_slot); + /* + * When KSM_RUN_MERGE (or KSM_RUN_STOP), + * insert just behind the scanning cursor, to let the area settle + * down a little; when fork is followed by immediate exec, we don't + * want ksmd to waste time setting up and tearing down an rmap_list. + * + * But when KSM_RUN_UNMERGE, it's important to insert ahead of its + * scanning cursor, otherwise KSM pages in newly forked mms will be + * missed: then we might as well insert at the end of the list. + */ + if (ksm_run & KSM_RUN_UNMERGE) + list_add_tail(&mm_slot->mm_list, &ksm_mm_head.mm_list); + else + list_add_tail(&mm_slot->mm_list, &ksm_scan.mm_slot->mm_list); + spin_unlock(&ksm_mmlist_lock); + + set_bit(MMF_VM_MERGEABLE, &mm->flags); + mmgrab(mm); + + if (needs_wakeup) + wake_up_interruptible(&ksm_thread_wait); + + return 0; +} + +void __ksm_exit(struct mm_struct *mm) +{ + struct mm_slot *mm_slot; + int easy_to_free = 0; + + /* + * This process is exiting: if it's straightforward (as is the + * case when ksmd was never running), free mm_slot immediately. + * But if it's at the cursor or has rmap_items linked to it, use + * mmap_lock to synchronize with any break_cows before pagetables + * are freed, and leave the mm_slot on the list for ksmd to free. + * Beware: ksm may already have noticed it exiting and freed the slot. + */ + + spin_lock(&ksm_mmlist_lock); + mm_slot = get_mm_slot(mm); + if (mm_slot && ksm_scan.mm_slot != mm_slot) { + if (!mm_slot->rmap_list) { + hash_del(&mm_slot->link); + list_del(&mm_slot->mm_list); + easy_to_free = 1; + } else { + list_move(&mm_slot->mm_list, + &ksm_scan.mm_slot->mm_list); + } + } + spin_unlock(&ksm_mmlist_lock); + + if (easy_to_free) { + free_mm_slot(mm_slot); + clear_bit(MMF_VM_MERGEABLE, &mm->flags); + mmdrop(mm); + } else if (mm_slot) { + mmap_write_lock(mm); + mmap_write_unlock(mm); + } +} + +struct page *ksm_might_need_to_copy(struct page *page, + struct vm_area_struct *vma, unsigned long address) +{ + struct anon_vma *anon_vma = page_anon_vma(page); + struct page *new_page; + + if (PageKsm(page)) { + if (page_stable_node(page) && + !(ksm_run & KSM_RUN_UNMERGE)) + return page; /* no need to copy it */ + } else if (!anon_vma) { + return page; /* no need to copy it */ + } else if (anon_vma->root == vma->anon_vma->root && + page->index == linear_page_index(vma, address)) { + return page; /* still no need to copy it */ + } + if (!PageUptodate(page)) + return page; /* let do_swap_page report the error */ + + new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); + if (new_page && mem_cgroup_charge(new_page, vma->vm_mm, GFP_KERNEL)) { + put_page(new_page); + new_page = NULL; + } + if (new_page) { + copy_user_highpage(new_page, page, address, vma); + + SetPageDirty(new_page); + __SetPageUptodate(new_page); + __SetPageLocked(new_page); + } + + return new_page; +} + +void rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc) +{ + struct stable_node *stable_node; + struct rmap_item *rmap_item; + int search_new_forks = 0; + + VM_BUG_ON_PAGE(!PageKsm(page), page); + + /* + * Rely on the page lock to protect against concurrent modifications + * to that page's node of the stable tree. + */ + VM_BUG_ON_PAGE(!PageLocked(page), page); + + stable_node = page_stable_node(page); + if (!stable_node) + return; +again: + hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) { + struct anon_vma *anon_vma = rmap_item->anon_vma; + struct anon_vma_chain *vmac; + struct vm_area_struct *vma; + + cond_resched(); + anon_vma_lock_read(anon_vma); + anon_vma_interval_tree_foreach(vmac, &anon_vma->rb_root, + 0, ULONG_MAX) { + unsigned long addr; + + cond_resched(); + vma = vmac->vma; + + /* Ignore the stable/unstable/sqnr flags */ + addr = rmap_item->address & ~KSM_FLAG_MASK; + + if (addr < vma->vm_start || addr >= vma->vm_end) + continue; + /* + * Initially we examine only the vma which covers this + * rmap_item; but later, if there is still work to do, + * we examine covering vmas in other mms: in case they + * were forked from the original since ksmd passed. + */ + if ((rmap_item->mm == vma->vm_mm) == search_new_forks) + continue; + + if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) + continue; + + if (!rwc->rmap_one(page, vma, addr, rwc->arg)) { + anon_vma_unlock_read(anon_vma); + return; + } + if (rwc->done && rwc->done(page)) { + anon_vma_unlock_read(anon_vma); + return; + } + } + anon_vma_unlock_read(anon_vma); + } + if (!search_new_forks++) + goto again; +} + +#ifdef CONFIG_MIGRATION +void ksm_migrate_page(struct page *newpage, struct page *oldpage) +{ + struct stable_node *stable_node; + + VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage); + VM_BUG_ON_PAGE(!PageLocked(newpage), newpage); + VM_BUG_ON_PAGE(newpage->mapping != oldpage->mapping, newpage); + + stable_node = page_stable_node(newpage); + if (stable_node) { + VM_BUG_ON_PAGE(stable_node->kpfn != page_to_pfn(oldpage), oldpage); + stable_node->kpfn = page_to_pfn(newpage); + /* + * newpage->mapping was set in advance; now we need smp_wmb() + * to make sure that the new stable_node->kpfn is visible + * to get_ksm_page() before it can see that oldpage->mapping + * has gone stale (or that PageSwapCache has been cleared). + */ + smp_wmb(); + set_page_stable_node(oldpage, NULL); + } +} +#endif /* CONFIG_MIGRATION */ + +#ifdef CONFIG_MEMORY_HOTREMOVE +static void wait_while_offlining(void) +{ + while (ksm_run & KSM_RUN_OFFLINE) { + mutex_unlock(&ksm_thread_mutex); + wait_on_bit(&ksm_run, ilog2(KSM_RUN_OFFLINE), + TASK_UNINTERRUPTIBLE); + mutex_lock(&ksm_thread_mutex); + } +} + +static bool stable_node_dup_remove_range(struct stable_node *stable_node, + unsigned long start_pfn, + unsigned long end_pfn) +{ + if (stable_node->kpfn >= start_pfn && + stable_node->kpfn < end_pfn) { + /* + * Don't get_ksm_page, page has already gone: + * which is why we keep kpfn instead of page* + */ + remove_node_from_stable_tree(stable_node); + return true; + } + return false; +} + +static bool stable_node_chain_remove_range(struct stable_node *stable_node, + unsigned long start_pfn, + unsigned long end_pfn, + struct rb_root *root) +{ + struct stable_node *dup; + struct hlist_node *hlist_safe; + + if (!is_stable_node_chain(stable_node)) { + VM_BUG_ON(is_stable_node_dup(stable_node)); + return stable_node_dup_remove_range(stable_node, start_pfn, + end_pfn); + } + + hlist_for_each_entry_safe(dup, hlist_safe, + &stable_node->hlist, hlist_dup) { + VM_BUG_ON(!is_stable_node_dup(dup)); + stable_node_dup_remove_range(dup, start_pfn, end_pfn); + } + if (hlist_empty(&stable_node->hlist)) { + free_stable_node_chain(stable_node, root); + return true; /* notify caller that tree was rebalanced */ + } else + return false; +} + +static void ksm_check_stable_tree(unsigned long start_pfn, + unsigned long end_pfn) +{ + struct stable_node *stable_node, *next; + struct rb_node *node; + int nid; + + for (nid = 0; nid < ksm_nr_node_ids; nid++) { + node = rb_first(root_stable_tree + nid); + while (node) { + stable_node = rb_entry(node, struct stable_node, node); + if (stable_node_chain_remove_range(stable_node, + start_pfn, end_pfn, + root_stable_tree + + nid)) + node = rb_first(root_stable_tree + nid); + else + node = rb_next(node); + cond_resched(); + } + } + list_for_each_entry_safe(stable_node, next, &migrate_nodes, list) { + if (stable_node->kpfn >= start_pfn && + stable_node->kpfn < end_pfn) + remove_node_from_stable_tree(stable_node); + cond_resched(); + } +} + +static int ksm_memory_callback(struct notifier_block *self, + unsigned long action, void *arg) +{ + struct memory_notify *mn = arg; + + switch (action) { + case MEM_GOING_OFFLINE: + /* + * Prevent ksm_do_scan(), unmerge_and_remove_all_rmap_items() + * and remove_all_stable_nodes() while memory is going offline: + * it is unsafe for them to touch the stable tree at this time. + * But unmerge_ksm_pages(), rmap lookups and other entry points + * which do not need the ksm_thread_mutex are all safe. + */ + mutex_lock(&ksm_thread_mutex); + ksm_run |= KSM_RUN_OFFLINE; + mutex_unlock(&ksm_thread_mutex); + break; + + case MEM_OFFLINE: + /* + * Most of the work is done by page migration; but there might + * be a few stable_nodes left over, still pointing to struct + * pages which have been offlined: prune those from the tree, + * otherwise get_ksm_page() might later try to access a + * non-existent struct page. + */ + ksm_check_stable_tree(mn->start_pfn, + mn->start_pfn + mn->nr_pages); + fallthrough; + case MEM_CANCEL_OFFLINE: + mutex_lock(&ksm_thread_mutex); + ksm_run &= ~KSM_RUN_OFFLINE; + mutex_unlock(&ksm_thread_mutex); + + smp_mb(); /* wake_up_bit advises this */ + wake_up_bit(&ksm_run, ilog2(KSM_RUN_OFFLINE)); + break; + } + return NOTIFY_OK; +} +#else +static void wait_while_offlining(void) +{ +} +#endif /* CONFIG_MEMORY_HOTREMOVE */ + +#ifdef CONFIG_SYSFS +/* + * This all compiles without CONFIG_SYSFS, but is a waste of space. + */ + +#define KSM_ATTR_RO(_name) \ + static struct kobj_attribute _name##_attr = __ATTR_RO(_name) +#define KSM_ATTR(_name) \ + static struct kobj_attribute _name##_attr = \ + __ATTR(_name, 0644, _name##_show, _name##_store) + +static ssize_t sleep_millisecs_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%u\n", ksm_thread_sleep_millisecs); +} + +static ssize_t sleep_millisecs_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + unsigned long msecs; + int err; + + err = kstrtoul(buf, 10, &msecs); + if (err || msecs > UINT_MAX) + return -EINVAL; + + ksm_thread_sleep_millisecs = msecs; + wake_up_interruptible(&ksm_iter_wait); + + return count; +} +KSM_ATTR(sleep_millisecs); + +static ssize_t pages_to_scan_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%u\n", ksm_thread_pages_to_scan); +} + +static ssize_t pages_to_scan_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err; + unsigned long nr_pages; + + err = kstrtoul(buf, 10, &nr_pages); + if (err || nr_pages > UINT_MAX) + return -EINVAL; + + ksm_thread_pages_to_scan = nr_pages; + + return count; +} +KSM_ATTR(pages_to_scan); + +static ssize_t run_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%lu\n", ksm_run); +} + +static ssize_t run_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err; + unsigned long flags; + + err = kstrtoul(buf, 10, &flags); + if (err || flags > UINT_MAX) + return -EINVAL; + if (flags > KSM_RUN_UNMERGE) + return -EINVAL; + + /* + * KSM_RUN_MERGE sets ksmd running, and 0 stops it running. + * KSM_RUN_UNMERGE stops it running and unmerges all rmap_items, + * breaking COW to free the pages_shared (but leaves mm_slots + * on the list for when ksmd may be set running again). + */ + + mutex_lock(&ksm_thread_mutex); + wait_while_offlining(); + if (ksm_run != flags) { + ksm_run = flags; + if (flags & KSM_RUN_UNMERGE) { + set_current_oom_origin(); + err = unmerge_and_remove_all_rmap_items(); + clear_current_oom_origin(); + if (err) { + ksm_run = KSM_RUN_STOP; + count = err; + } + } + } + mutex_unlock(&ksm_thread_mutex); + + if (flags & KSM_RUN_MERGE) + wake_up_interruptible(&ksm_thread_wait); + + return count; +} +KSM_ATTR(run); + +#ifdef CONFIG_NUMA +static ssize_t merge_across_nodes_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%u\n", ksm_merge_across_nodes); +} + +static ssize_t merge_across_nodes_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err; + unsigned long knob; + + err = kstrtoul(buf, 10, &knob); + if (err) + return err; + if (knob > 1) + return -EINVAL; + + mutex_lock(&ksm_thread_mutex); + wait_while_offlining(); + if (ksm_merge_across_nodes != knob) { + if (ksm_pages_shared || remove_all_stable_nodes()) + err = -EBUSY; + else if (root_stable_tree == one_stable_tree) { + struct rb_root *buf; + /* + * This is the first time that we switch away from the + * default of merging across nodes: must now allocate + * a buffer to hold as many roots as may be needed. + * Allocate stable and unstable together: + * MAXSMP NODES_SHIFT 10 will use 16kB. + */ + buf = kcalloc(nr_node_ids + nr_node_ids, sizeof(*buf), + GFP_KERNEL); + /* Let us assume that RB_ROOT is NULL is zero */ + if (!buf) + err = -ENOMEM; + else { + root_stable_tree = buf; + root_unstable_tree = buf + nr_node_ids; + /* Stable tree is empty but not the unstable */ + root_unstable_tree[0] = one_unstable_tree[0]; + } + } + if (!err) { + ksm_merge_across_nodes = knob; + ksm_nr_node_ids = knob ? 1 : nr_node_ids; + } + } + mutex_unlock(&ksm_thread_mutex); + + return err ? err : count; +} +KSM_ATTR(merge_across_nodes); +#endif + +static ssize_t use_zero_pages_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%u\n", ksm_use_zero_pages); +} +static ssize_t use_zero_pages_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err; + bool value; + + err = kstrtobool(buf, &value); + if (err) + return -EINVAL; + + ksm_use_zero_pages = value; + + return count; +} +KSM_ATTR(use_zero_pages); + +static ssize_t max_page_sharing_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%u\n", ksm_max_page_sharing); +} + +static ssize_t max_page_sharing_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err; + int knob; + + err = kstrtoint(buf, 10, &knob); + if (err) + return err; + /* + * When a KSM page is created it is shared by 2 mappings. This + * being a signed comparison, it implicitly verifies it's not + * negative. + */ + if (knob < 2) + return -EINVAL; + + if (READ_ONCE(ksm_max_page_sharing) == knob) + return count; + + mutex_lock(&ksm_thread_mutex); + wait_while_offlining(); + if (ksm_max_page_sharing != knob) { + if (ksm_pages_shared || remove_all_stable_nodes()) + err = -EBUSY; + else + ksm_max_page_sharing = knob; + } + mutex_unlock(&ksm_thread_mutex); + + return err ? err : count; +} +KSM_ATTR(max_page_sharing); + +static ssize_t pages_shared_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%lu\n", ksm_pages_shared); +} +KSM_ATTR_RO(pages_shared); + +static ssize_t pages_sharing_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%lu\n", ksm_pages_sharing); +} +KSM_ATTR_RO(pages_sharing); + +static ssize_t pages_unshared_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%lu\n", ksm_pages_unshared); +} +KSM_ATTR_RO(pages_unshared); + +static ssize_t pages_volatile_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + long ksm_pages_volatile; + + ksm_pages_volatile = ksm_rmap_items - ksm_pages_shared + - ksm_pages_sharing - ksm_pages_unshared; + /* + * It was not worth any locking to calculate that statistic, + * but it might therefore sometimes be negative: conceal that. + */ + if (ksm_pages_volatile < 0) + ksm_pages_volatile = 0; + return sprintf(buf, "%ld\n", ksm_pages_volatile); +} +KSM_ATTR_RO(pages_volatile); + +static ssize_t stable_node_dups_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%lu\n", ksm_stable_node_dups); +} +KSM_ATTR_RO(stable_node_dups); + +static ssize_t stable_node_chains_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%lu\n", ksm_stable_node_chains); +} +KSM_ATTR_RO(stable_node_chains); + +static ssize_t +stable_node_chains_prune_millisecs_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", ksm_stable_node_chains_prune_millisecs); +} + +static ssize_t +stable_node_chains_prune_millisecs_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + unsigned long msecs; + int err; + + err = kstrtoul(buf, 10, &msecs); + if (err || msecs > UINT_MAX) + return -EINVAL; + + ksm_stable_node_chains_prune_millisecs = msecs; + + return count; +} +KSM_ATTR(stable_node_chains_prune_millisecs); + +static ssize_t full_scans_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%lu\n", ksm_scan.seqnr); +} +KSM_ATTR_RO(full_scans); + +static struct attribute *ksm_attrs[] = { + &sleep_millisecs_attr.attr, + &pages_to_scan_attr.attr, + &run_attr.attr, + &pages_shared_attr.attr, + &pages_sharing_attr.attr, + &pages_unshared_attr.attr, + &pages_volatile_attr.attr, + &full_scans_attr.attr, +#ifdef CONFIG_NUMA + &merge_across_nodes_attr.attr, +#endif + &max_page_sharing_attr.attr, + &stable_node_chains_attr.attr, + &stable_node_dups_attr.attr, + &stable_node_chains_prune_millisecs_attr.attr, + &use_zero_pages_attr.attr, + NULL, +}; + +static const struct attribute_group ksm_attr_group = { + .attrs = ksm_attrs, + .name = "ksm", +}; +#endif /* CONFIG_SYSFS */ + +static int __init ksm_init(void) +{ + struct task_struct *ksm_thread; + int err; + + /* The correct value depends on page size and endianness */ + zero_checksum = calc_checksum(ZERO_PAGE(0)); + /* Default to false for backwards compatibility */ + ksm_use_zero_pages = false; + + err = ksm_slab_init(); + if (err) + goto out; + + ksm_thread = kthread_run(ksm_scan_thread, NULL, "ksmd"); + if (IS_ERR(ksm_thread)) { + pr_err("ksm: creating kthread failed\n"); + err = PTR_ERR(ksm_thread); + goto out_free; + } + +#ifdef CONFIG_SYSFS + err = sysfs_create_group(mm_kobj, &ksm_attr_group); + if (err) { + pr_err("ksm: register sysfs failed\n"); + kthread_stop(ksm_thread); + goto out_free; + } +#else + ksm_run = KSM_RUN_MERGE; /* no way for user to start it */ + +#endif /* CONFIG_SYSFS */ + +#ifdef CONFIG_MEMORY_HOTREMOVE + /* There is no significance to this priority 100 */ + hotplug_memory_notifier(ksm_memory_callback, 100); +#endif + return 0; + +out_free: + ksm_slab_free(); +out: + return err; +} +subsys_initcall(ksm_init); diff --git a/mm/list_lru.c b/mm/list_lru.c new file mode 100644 index 000000000..fe2300816 --- /dev/null +++ b/mm/list_lru.c @@ -0,0 +1,649 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2013 Red Hat, Inc. and Parallels Inc. All rights reserved. + * Authors: David Chinner and Glauber Costa + * + * Generic LRU infrastructure + */ +#include +#include +#include +#include +#include +#include +#include +#include "slab.h" + +#ifdef CONFIG_MEMCG_KMEM +static LIST_HEAD(list_lrus); +static DEFINE_MUTEX(list_lrus_mutex); + +static void list_lru_register(struct list_lru *lru) +{ + mutex_lock(&list_lrus_mutex); + list_add(&lru->list, &list_lrus); + mutex_unlock(&list_lrus_mutex); +} + +static void list_lru_unregister(struct list_lru *lru) +{ + mutex_lock(&list_lrus_mutex); + list_del(&lru->list); + mutex_unlock(&list_lrus_mutex); +} + +static int lru_shrinker_id(struct list_lru *lru) +{ + return lru->shrinker_id; +} + +static inline bool list_lru_memcg_aware(struct list_lru *lru) +{ + return lru->memcg_aware; +} + +static inline struct list_lru_one * +list_lru_from_memcg_idx(struct list_lru_node *nlru, int idx) +{ + struct list_lru_memcg *memcg_lrus; + /* + * Either lock or RCU protects the array of per cgroup lists + * from relocation (see memcg_update_list_lru_node). + */ + memcg_lrus = rcu_dereference_check(nlru->memcg_lrus, + lockdep_is_held(&nlru->lock)); + if (memcg_lrus && idx >= 0) + return memcg_lrus->lru[idx]; + return &nlru->lru; +} + +static inline struct list_lru_one * +list_lru_from_kmem(struct list_lru_node *nlru, void *ptr, + struct mem_cgroup **memcg_ptr) +{ + struct list_lru_one *l = &nlru->lru; + struct mem_cgroup *memcg = NULL; + + if (!nlru->memcg_lrus) + goto out; + + memcg = mem_cgroup_from_obj(ptr); + if (!memcg) + goto out; + + l = list_lru_from_memcg_idx(nlru, memcg_cache_id(memcg)); +out: + if (memcg_ptr) + *memcg_ptr = memcg; + return l; +} +#else +static void list_lru_register(struct list_lru *lru) +{ +} + +static void list_lru_unregister(struct list_lru *lru) +{ +} + +static int lru_shrinker_id(struct list_lru *lru) +{ + return -1; +} + +static inline bool list_lru_memcg_aware(struct list_lru *lru) +{ + return false; +} + +static inline struct list_lru_one * +list_lru_from_memcg_idx(struct list_lru_node *nlru, int idx) +{ + return &nlru->lru; +} + +static inline struct list_lru_one * +list_lru_from_kmem(struct list_lru_node *nlru, void *ptr, + struct mem_cgroup **memcg_ptr) +{ + if (memcg_ptr) + *memcg_ptr = NULL; + return &nlru->lru; +} +#endif /* CONFIG_MEMCG_KMEM */ + +bool list_lru_add(struct list_lru *lru, struct list_head *item) +{ + int nid = page_to_nid(virt_to_page(item)); + struct list_lru_node *nlru = &lru->node[nid]; + struct mem_cgroup *memcg; + struct list_lru_one *l; + + spin_lock(&nlru->lock); + if (list_empty(item)) { + l = list_lru_from_kmem(nlru, item, &memcg); + list_add_tail(item, &l->list); + /* Set shrinker bit if the first element was added */ + if (!l->nr_items++) + memcg_set_shrinker_bit(memcg, nid, + lru_shrinker_id(lru)); + nlru->nr_items++; + spin_unlock(&nlru->lock); + return true; + } + spin_unlock(&nlru->lock); + return false; +} +EXPORT_SYMBOL_GPL(list_lru_add); + +bool list_lru_del(struct list_lru *lru, struct list_head *item) +{ + int nid = page_to_nid(virt_to_page(item)); + struct list_lru_node *nlru = &lru->node[nid]; + struct list_lru_one *l; + + spin_lock(&nlru->lock); + if (!list_empty(item)) { + l = list_lru_from_kmem(nlru, item, NULL); + list_del_init(item); + l->nr_items--; + nlru->nr_items--; + spin_unlock(&nlru->lock); + return true; + } + spin_unlock(&nlru->lock); + return false; +} +EXPORT_SYMBOL_GPL(list_lru_del); + +void list_lru_isolate(struct list_lru_one *list, struct list_head *item) +{ + list_del_init(item); + list->nr_items--; +} +EXPORT_SYMBOL_GPL(list_lru_isolate); + +void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item, + struct list_head *head) +{ + list_move(item, head); + list->nr_items--; +} +EXPORT_SYMBOL_GPL(list_lru_isolate_move); + +unsigned long list_lru_count_one(struct list_lru *lru, + int nid, struct mem_cgroup *memcg) +{ + struct list_lru_node *nlru = &lru->node[nid]; + struct list_lru_one *l; + unsigned long count; + + rcu_read_lock(); + l = list_lru_from_memcg_idx(nlru, memcg_cache_id(memcg)); + count = READ_ONCE(l->nr_items); + rcu_read_unlock(); + + return count; +} +EXPORT_SYMBOL_GPL(list_lru_count_one); + +unsigned long list_lru_count_node(struct list_lru *lru, int nid) +{ + struct list_lru_node *nlru; + + nlru = &lru->node[nid]; + return nlru->nr_items; +} +EXPORT_SYMBOL_GPL(list_lru_count_node); + +static unsigned long +__list_lru_walk_one(struct list_lru_node *nlru, int memcg_idx, + list_lru_walk_cb isolate, void *cb_arg, + unsigned long *nr_to_walk) +{ + + struct list_lru_one *l; + struct list_head *item, *n; + unsigned long isolated = 0; + + l = list_lru_from_memcg_idx(nlru, memcg_idx); +restart: + list_for_each_safe(item, n, &l->list) { + enum lru_status ret; + + /* + * decrement nr_to_walk first so that we don't livelock if we + * get stuck on large numbers of LRU_RETRY items + */ + if (!*nr_to_walk) + break; + --*nr_to_walk; + + ret = isolate(item, l, &nlru->lock, cb_arg); + switch (ret) { + case LRU_REMOVED_RETRY: + assert_spin_locked(&nlru->lock); + fallthrough; + case LRU_REMOVED: + isolated++; + nlru->nr_items--; + /* + * If the lru lock has been dropped, our list + * traversal is now invalid and so we have to + * restart from scratch. + */ + if (ret == LRU_REMOVED_RETRY) + goto restart; + break; + case LRU_ROTATE: + list_move_tail(item, &l->list); + break; + case LRU_SKIP: + break; + case LRU_RETRY: + /* + * The lru lock has been dropped, our list traversal is + * now invalid and so we have to restart from scratch. + */ + assert_spin_locked(&nlru->lock); + goto restart; + default: + BUG(); + } + } + return isolated; +} + +unsigned long +list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg, + list_lru_walk_cb isolate, void *cb_arg, + unsigned long *nr_to_walk) +{ + struct list_lru_node *nlru = &lru->node[nid]; + unsigned long ret; + + spin_lock(&nlru->lock); + ret = __list_lru_walk_one(nlru, memcg_cache_id(memcg), isolate, cb_arg, + nr_to_walk); + spin_unlock(&nlru->lock); + return ret; +} +EXPORT_SYMBOL_GPL(list_lru_walk_one); + +unsigned long +list_lru_walk_one_irq(struct list_lru *lru, int nid, struct mem_cgroup *memcg, + list_lru_walk_cb isolate, void *cb_arg, + unsigned long *nr_to_walk) +{ + struct list_lru_node *nlru = &lru->node[nid]; + unsigned long ret; + + spin_lock_irq(&nlru->lock); + ret = __list_lru_walk_one(nlru, memcg_cache_id(memcg), isolate, cb_arg, + nr_to_walk); + spin_unlock_irq(&nlru->lock); + return ret; +} + +unsigned long list_lru_walk_node(struct list_lru *lru, int nid, + list_lru_walk_cb isolate, void *cb_arg, + unsigned long *nr_to_walk) +{ + long isolated = 0; + int memcg_idx; + + isolated += list_lru_walk_one(lru, nid, NULL, isolate, cb_arg, + nr_to_walk); + if (*nr_to_walk > 0 && list_lru_memcg_aware(lru)) { + for_each_memcg_cache_index(memcg_idx) { + struct list_lru_node *nlru = &lru->node[nid]; + + spin_lock(&nlru->lock); + isolated += __list_lru_walk_one(nlru, memcg_idx, + isolate, cb_arg, + nr_to_walk); + spin_unlock(&nlru->lock); + + if (*nr_to_walk <= 0) + break; + } + } + return isolated; +} +EXPORT_SYMBOL_GPL(list_lru_walk_node); + +static void init_one_lru(struct list_lru_one *l) +{ + INIT_LIST_HEAD(&l->list); + l->nr_items = 0; +} + +#ifdef CONFIG_MEMCG_KMEM +static void __memcg_destroy_list_lru_node(struct list_lru_memcg *memcg_lrus, + int begin, int end) +{ + int i; + + for (i = begin; i < end; i++) + kfree(memcg_lrus->lru[i]); +} + +static int __memcg_init_list_lru_node(struct list_lru_memcg *memcg_lrus, + int begin, int end) +{ + int i; + + for (i = begin; i < end; i++) { + struct list_lru_one *l; + + l = kmalloc(sizeof(struct list_lru_one), GFP_KERNEL); + if (!l) + goto fail; + + init_one_lru(l); + memcg_lrus->lru[i] = l; + } + return 0; +fail: + __memcg_destroy_list_lru_node(memcg_lrus, begin, i); + return -ENOMEM; +} + +static int memcg_init_list_lru_node(struct list_lru_node *nlru) +{ + struct list_lru_memcg *memcg_lrus; + int size = memcg_nr_cache_ids; + + memcg_lrus = kvmalloc(sizeof(*memcg_lrus) + + size * sizeof(void *), GFP_KERNEL); + if (!memcg_lrus) + return -ENOMEM; + + if (__memcg_init_list_lru_node(memcg_lrus, 0, size)) { + kvfree(memcg_lrus); + return -ENOMEM; + } + RCU_INIT_POINTER(nlru->memcg_lrus, memcg_lrus); + + return 0; +} + +static void memcg_destroy_list_lru_node(struct list_lru_node *nlru) +{ + struct list_lru_memcg *memcg_lrus; + /* + * This is called when shrinker has already been unregistered, + * and nobody can use it. So, there is no need to use kvfree_rcu_local(). + */ + memcg_lrus = rcu_dereference_protected(nlru->memcg_lrus, true); + __memcg_destroy_list_lru_node(memcg_lrus, 0, memcg_nr_cache_ids); + kvfree(memcg_lrus); +} + +static void kvfree_rcu_local(struct rcu_head *head) +{ + struct list_lru_memcg *mlru; + + mlru = container_of(head, struct list_lru_memcg, rcu); + kvfree(mlru); +} + +static int memcg_update_list_lru_node(struct list_lru_node *nlru, + int old_size, int new_size) +{ + struct list_lru_memcg *old, *new; + + BUG_ON(old_size > new_size); + + old = rcu_dereference_protected(nlru->memcg_lrus, + lockdep_is_held(&list_lrus_mutex)); + new = kvmalloc(sizeof(*new) + new_size * sizeof(void *), GFP_KERNEL); + if (!new) + return -ENOMEM; + + if (__memcg_init_list_lru_node(new, old_size, new_size)) { + kvfree(new); + return -ENOMEM; + } + + memcpy(&new->lru, &old->lru, old_size * sizeof(void *)); + + /* + * The locking below allows readers that hold nlru->lock avoid taking + * rcu_read_lock (see list_lru_from_memcg_idx). + * + * Since list_lru_{add,del} may be called under an IRQ-safe lock, + * we have to use IRQ-safe primitives here to avoid deadlock. + */ + spin_lock_irq(&nlru->lock); + rcu_assign_pointer(nlru->memcg_lrus, new); + spin_unlock_irq(&nlru->lock); + + call_rcu(&old->rcu, kvfree_rcu_local); + return 0; +} + +static void memcg_cancel_update_list_lru_node(struct list_lru_node *nlru, + int old_size, int new_size) +{ + struct list_lru_memcg *memcg_lrus; + + memcg_lrus = rcu_dereference_protected(nlru->memcg_lrus, + lockdep_is_held(&list_lrus_mutex)); + /* do not bother shrinking the array back to the old size, because we + * cannot handle allocation failures here */ + __memcg_destroy_list_lru_node(memcg_lrus, old_size, new_size); +} + +static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) +{ + int i; + + lru->memcg_aware = memcg_aware; + + if (!memcg_aware) + return 0; + + for_each_node(i) { + if (memcg_init_list_lru_node(&lru->node[i])) + goto fail; + } + return 0; +fail: + for (i = i - 1; i >= 0; i--) { + if (!lru->node[i].memcg_lrus) + continue; + memcg_destroy_list_lru_node(&lru->node[i]); + } + return -ENOMEM; +} + +static void memcg_destroy_list_lru(struct list_lru *lru) +{ + int i; + + if (!list_lru_memcg_aware(lru)) + return; + + for_each_node(i) + memcg_destroy_list_lru_node(&lru->node[i]); +} + +static int memcg_update_list_lru(struct list_lru *lru, + int old_size, int new_size) +{ + int i; + + if (!list_lru_memcg_aware(lru)) + return 0; + + for_each_node(i) { + if (memcg_update_list_lru_node(&lru->node[i], + old_size, new_size)) + goto fail; + } + return 0; +fail: + for (i = i - 1; i >= 0; i--) { + if (!lru->node[i].memcg_lrus) + continue; + + memcg_cancel_update_list_lru_node(&lru->node[i], + old_size, new_size); + } + return -ENOMEM; +} + +static void memcg_cancel_update_list_lru(struct list_lru *lru, + int old_size, int new_size) +{ + int i; + + if (!list_lru_memcg_aware(lru)) + return; + + for_each_node(i) + memcg_cancel_update_list_lru_node(&lru->node[i], + old_size, new_size); +} + +int memcg_update_all_list_lrus(int new_size) +{ + int ret = 0; + struct list_lru *lru; + int old_size = memcg_nr_cache_ids; + + mutex_lock(&list_lrus_mutex); + list_for_each_entry(lru, &list_lrus, list) { + ret = memcg_update_list_lru(lru, old_size, new_size); + if (ret) + goto fail; + } +out: + mutex_unlock(&list_lrus_mutex); + return ret; +fail: + list_for_each_entry_continue_reverse(lru, &list_lrus, list) + memcg_cancel_update_list_lru(lru, old_size, new_size); + goto out; +} + +static void memcg_drain_list_lru_node(struct list_lru *lru, int nid, + int src_idx, struct mem_cgroup *dst_memcg) +{ + struct list_lru_node *nlru = &lru->node[nid]; + int dst_idx = dst_memcg->kmemcg_id; + struct list_lru_one *src, *dst; + + /* + * Since list_lru_{add,del} may be called under an IRQ-safe lock, + * we have to use IRQ-safe primitives here to avoid deadlock. + */ + spin_lock_irq(&nlru->lock); + + src = list_lru_from_memcg_idx(nlru, src_idx); + dst = list_lru_from_memcg_idx(nlru, dst_idx); + + list_splice_init(&src->list, &dst->list); + + if (src->nr_items) { + dst->nr_items += src->nr_items; + memcg_set_shrinker_bit(dst_memcg, nid, lru_shrinker_id(lru)); + src->nr_items = 0; + } + + spin_unlock_irq(&nlru->lock); +} + +static void memcg_drain_list_lru(struct list_lru *lru, + int src_idx, struct mem_cgroup *dst_memcg) +{ + int i; + + if (!list_lru_memcg_aware(lru)) + return; + + for_each_node(i) + memcg_drain_list_lru_node(lru, i, src_idx, dst_memcg); +} + +void memcg_drain_all_list_lrus(int src_idx, struct mem_cgroup *dst_memcg) +{ + struct list_lru *lru; + + mutex_lock(&list_lrus_mutex); + list_for_each_entry(lru, &list_lrus, list) + memcg_drain_list_lru(lru, src_idx, dst_memcg); + mutex_unlock(&list_lrus_mutex); +} +#else +static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) +{ + return 0; +} + +static void memcg_destroy_list_lru(struct list_lru *lru) +{ +} +#endif /* CONFIG_MEMCG_KMEM */ + +int __list_lru_init(struct list_lru *lru, bool memcg_aware, + struct lock_class_key *key, struct shrinker *shrinker) +{ + int i; + int err = -ENOMEM; + +#ifdef CONFIG_MEMCG_KMEM + if (shrinker) + lru->shrinker_id = shrinker->id; + else + lru->shrinker_id = -1; +#endif + memcg_get_cache_ids(); + + lru->node = kcalloc(nr_node_ids, sizeof(*lru->node), GFP_KERNEL); + if (!lru->node) + goto out; + + for_each_node(i) { + spin_lock_init(&lru->node[i].lock); + if (key) + lockdep_set_class(&lru->node[i].lock, key); + init_one_lru(&lru->node[i].lru); + } + + err = memcg_init_list_lru(lru, memcg_aware); + if (err) { + kfree(lru->node); + /* Do this so a list_lru_destroy() doesn't crash: */ + lru->node = NULL; + goto out; + } + + list_lru_register(lru); +out: + memcg_put_cache_ids(); + return err; +} +EXPORT_SYMBOL_GPL(__list_lru_init); + +void list_lru_destroy(struct list_lru *lru) +{ + /* Already destroyed or not yet initialized? */ + if (!lru->node) + return; + + memcg_get_cache_ids(); + + list_lru_unregister(lru); + + memcg_destroy_list_lru(lru); + kfree(lru->node); + lru->node = NULL; + +#ifdef CONFIG_MEMCG_KMEM + lru->shrinker_id = -1; +#endif + memcg_put_cache_ids(); +} +EXPORT_SYMBOL_GPL(list_lru_destroy); diff --git a/mm/maccess.c b/mm/maccess.c new file mode 100644 index 000000000..f6ea117a6 --- /dev/null +++ b/mm/maccess.c @@ -0,0 +1,321 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Access kernel or user memory without faulting. + */ +#include +#include +#include + +bool __weak copy_from_kernel_nofault_allowed(const void *unsafe_src, + size_t size) +{ + return true; +} + +#ifdef HAVE_GET_KERNEL_NOFAULT + +#define copy_from_kernel_nofault_loop(dst, src, len, type, err_label) \ + while (len >= sizeof(type)) { \ + __get_kernel_nofault(dst, src, type, err_label); \ + dst += sizeof(type); \ + src += sizeof(type); \ + len -= sizeof(type); \ + } + +long copy_from_kernel_nofault(void *dst, const void *src, size_t size) +{ + if (!copy_from_kernel_nofault_allowed(src, size)) + return -ERANGE; + + pagefault_disable(); + copy_from_kernel_nofault_loop(dst, src, size, u64, Efault); + copy_from_kernel_nofault_loop(dst, src, size, u32, Efault); + copy_from_kernel_nofault_loop(dst, src, size, u16, Efault); + copy_from_kernel_nofault_loop(dst, src, size, u8, Efault); + pagefault_enable(); + return 0; +Efault: + pagefault_enable(); + return -EFAULT; +} +EXPORT_SYMBOL_GPL(copy_from_kernel_nofault); + +#define copy_to_kernel_nofault_loop(dst, src, len, type, err_label) \ + while (len >= sizeof(type)) { \ + __put_kernel_nofault(dst, src, type, err_label); \ + dst += sizeof(type); \ + src += sizeof(type); \ + len -= sizeof(type); \ + } + +long copy_to_kernel_nofault(void *dst, const void *src, size_t size) +{ + pagefault_disable(); + copy_to_kernel_nofault_loop(dst, src, size, u64, Efault); + copy_to_kernel_nofault_loop(dst, src, size, u32, Efault); + copy_to_kernel_nofault_loop(dst, src, size, u16, Efault); + copy_to_kernel_nofault_loop(dst, src, size, u8, Efault); + pagefault_enable(); + return 0; +Efault: + pagefault_enable(); + return -EFAULT; +} + +long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count) +{ + const void *src = unsafe_addr; + + if (unlikely(count <= 0)) + return 0; + if (!copy_from_kernel_nofault_allowed(unsafe_addr, count)) + return -ERANGE; + + pagefault_disable(); + do { + __get_kernel_nofault(dst, src, u8, Efault); + dst++; + src++; + } while (dst[-1] && src - unsafe_addr < count); + pagefault_enable(); + + dst[-1] = '\0'; + return src - unsafe_addr; +Efault: + pagefault_enable(); + dst[0] = '\0'; + return -EFAULT; +} +#else /* HAVE_GET_KERNEL_NOFAULT */ +/** + * copy_from_kernel_nofault(): safely attempt to read from kernel-space + * @dst: pointer to the buffer that shall take the data + * @src: address to read from + * @size: size of the data chunk + * + * Safely read from kernel address @src to the buffer at @dst. If a kernel + * fault happens, handle that and return -EFAULT. If @src is not a valid kernel + * address, return -ERANGE. + * + * We ensure that the copy_from_user is executed in atomic context so that + * do_page_fault() doesn't attempt to take mmap_lock. This makes + * copy_from_kernel_nofault() suitable for use within regions where the caller + * already holds mmap_lock, or other locks which nest inside mmap_lock. + */ +long copy_from_kernel_nofault(void *dst, const void *src, size_t size) +{ + long ret; + mm_segment_t old_fs = get_fs(); + + if (!copy_from_kernel_nofault_allowed(src, size)) + return -ERANGE; + + set_fs(KERNEL_DS); + pagefault_disable(); + ret = __copy_from_user_inatomic(dst, (__force const void __user *)src, + size); + pagefault_enable(); + set_fs(old_fs); + + if (ret) + return -EFAULT; + return 0; +} +EXPORT_SYMBOL_GPL(copy_from_kernel_nofault); + +/** + * copy_to_kernel_nofault(): safely attempt to write to a location + * @dst: address to write to + * @src: pointer to the data that shall be written + * @size: size of the data chunk + * + * Safely write to address @dst from the buffer at @src. If a kernel fault + * happens, handle that and return -EFAULT. + */ +long copy_to_kernel_nofault(void *dst, const void *src, size_t size) +{ + long ret; + mm_segment_t old_fs = get_fs(); + + set_fs(KERNEL_DS); + pagefault_disable(); + ret = __copy_to_user_inatomic((__force void __user *)dst, src, size); + pagefault_enable(); + set_fs(old_fs); + + if (ret) + return -EFAULT; + return 0; +} + +/** + * strncpy_from_kernel_nofault: - Copy a NUL terminated string from unsafe + * address. + * @dst: Destination address, in kernel space. This buffer must be at + * least @count bytes long. + * @unsafe_addr: Unsafe address. + * @count: Maximum number of bytes to copy, including the trailing NUL. + * + * Copies a NUL-terminated string from unsafe address to kernel buffer. + * + * On success, returns the length of the string INCLUDING the trailing NUL. + * + * If access fails, returns -EFAULT (some data may have been copied and the + * trailing NUL added). If @unsafe_addr is not a valid kernel address, return + * -ERANGE. + * + * If @count is smaller than the length of the string, copies @count-1 bytes, + * sets the last byte of @dst buffer to NUL and returns @count. + */ +long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count) +{ + mm_segment_t old_fs = get_fs(); + const void *src = unsafe_addr; + long ret; + + if (unlikely(count <= 0)) + return 0; + if (!copy_from_kernel_nofault_allowed(unsafe_addr, count)) + return -ERANGE; + + set_fs(KERNEL_DS); + pagefault_disable(); + + do { + ret = __get_user(*dst++, (const char __user __force *)src++); + } while (dst[-1] && ret == 0 && src - unsafe_addr < count); + + dst[-1] = '\0'; + pagefault_enable(); + set_fs(old_fs); + + return ret ? -EFAULT : src - unsafe_addr; +} +#endif /* HAVE_GET_KERNEL_NOFAULT */ + +/** + * copy_from_user_nofault(): safely attempt to read from a user-space location + * @dst: pointer to the buffer that shall take the data + * @src: address to read from. This must be a user address. + * @size: size of the data chunk + * + * Safely read from user address @src to the buffer at @dst. If a kernel fault + * happens, handle that and return -EFAULT. + */ +long copy_from_user_nofault(void *dst, const void __user *src, size_t size) +{ + long ret = -EFAULT; + mm_segment_t old_fs = force_uaccess_begin(); + + if (access_ok(src, size)) { + pagefault_disable(); + ret = __copy_from_user_inatomic(dst, src, size); + pagefault_enable(); + } + force_uaccess_end(old_fs); + + if (ret) + return -EFAULT; + return 0; +} +EXPORT_SYMBOL_GPL(copy_from_user_nofault); + +/** + * copy_to_user_nofault(): safely attempt to write to a user-space location + * @dst: address to write to + * @src: pointer to the data that shall be written + * @size: size of the data chunk + * + * Safely write to address @dst from the buffer at @src. If a kernel fault + * happens, handle that and return -EFAULT. + */ +long copy_to_user_nofault(void __user *dst, const void *src, size_t size) +{ + long ret = -EFAULT; + mm_segment_t old_fs = force_uaccess_begin(); + + if (access_ok(dst, size)) { + pagefault_disable(); + ret = __copy_to_user_inatomic(dst, src, size); + pagefault_enable(); + } + force_uaccess_end(old_fs); + + if (ret) + return -EFAULT; + return 0; +} +EXPORT_SYMBOL_GPL(copy_to_user_nofault); + +/** + * strncpy_from_user_nofault: - Copy a NUL terminated string from unsafe user + * address. + * @dst: Destination address, in kernel space. This buffer must be at + * least @count bytes long. + * @unsafe_addr: Unsafe user address. + * @count: Maximum number of bytes to copy, including the trailing NUL. + * + * Copies a NUL-terminated string from unsafe user address to kernel buffer. + * + * On success, returns the length of the string INCLUDING the trailing NUL. + * + * If access fails, returns -EFAULT (some data may have been copied + * and the trailing NUL added). + * + * If @count is smaller than the length of the string, copies @count-1 bytes, + * sets the last byte of @dst buffer to NUL and returns @count. + */ +long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, + long count) +{ + mm_segment_t old_fs; + long ret; + + if (unlikely(count <= 0)) + return 0; + + old_fs = force_uaccess_begin(); + pagefault_disable(); + ret = strncpy_from_user(dst, unsafe_addr, count); + pagefault_enable(); + force_uaccess_end(old_fs); + + if (ret >= count) { + ret = count; + dst[ret - 1] = '\0'; + } else if (ret > 0) { + ret++; + } + + return ret; +} + +/** + * strnlen_user_nofault: - Get the size of a user string INCLUDING final NUL. + * @unsafe_addr: The string to measure. + * @count: Maximum count (including NUL) + * + * Get the size of a NUL-terminated string in user space without pagefault. + * + * Returns the size of the string INCLUDING the terminating NUL. + * + * If the string is too long, returns a number larger than @count. User + * has to check the return value against "> count". + * On exception (or invalid count), returns 0. + * + * Unlike strnlen_user, this can be used from IRQ handler etc. because + * it disables pagefaults. + */ +long strnlen_user_nofault(const void __user *unsafe_addr, long count) +{ + mm_segment_t old_fs; + int ret; + + old_fs = force_uaccess_begin(); + pagefault_disable(); + ret = strnlen_user(unsafe_addr, count); + pagefault_enable(); + force_uaccess_end(old_fs); + + return ret; +} diff --git a/mm/madvise.c b/mm/madvise.c new file mode 100644 index 000000000..f71fc88f0 --- /dev/null +++ b/mm/madvise.c @@ -0,0 +1,1247 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/mm/madvise.c + * + * Copyright (C) 1999 Linus Torvalds + * Copyright (C) 2002 Christoph Hellwig + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "internal.h" + +struct madvise_walk_private { + struct mmu_gather *tlb; + bool pageout; +}; + +/* + * Any behaviour which results in changes to the vma->vm_flags needs to + * take mmap_lock for writing. Others, which simply traverse vmas, need + * to only take it for reading. + */ +static int madvise_need_mmap_write(int behavior) +{ + switch (behavior) { + case MADV_REMOVE: + case MADV_WILLNEED: + case MADV_DONTNEED: + case MADV_COLD: + case MADV_PAGEOUT: + case MADV_FREE: + return 0; + default: + /* be safe, default to 1. list exceptions explicitly */ + return 1; + } +} + +/* + * We can potentially split a vm area into separate + * areas, each area with its own behavior. + */ +static long madvise_behavior(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start, unsigned long end, int behavior) +{ + struct mm_struct *mm = vma->vm_mm; + int error = 0; + pgoff_t pgoff; + unsigned long new_flags = vma->vm_flags; + + switch (behavior) { + case MADV_NORMAL: + new_flags = new_flags & ~VM_RAND_READ & ~VM_SEQ_READ; + break; + case MADV_SEQUENTIAL: + new_flags = (new_flags & ~VM_RAND_READ) | VM_SEQ_READ; + break; + case MADV_RANDOM: + new_flags = (new_flags & ~VM_SEQ_READ) | VM_RAND_READ; + break; + case MADV_DONTFORK: + new_flags |= VM_DONTCOPY; + break; + case MADV_DOFORK: + if (vma->vm_flags & VM_IO) { + error = -EINVAL; + goto out; + } + new_flags &= ~VM_DONTCOPY; + break; + case MADV_WIPEONFORK: + /* MADV_WIPEONFORK is only supported on anonymous memory. */ + if (vma->vm_file || vma->vm_flags & VM_SHARED) { + error = -EINVAL; + goto out; + } + new_flags |= VM_WIPEONFORK; + break; + case MADV_KEEPONFORK: + new_flags &= ~VM_WIPEONFORK; + break; + case MADV_DONTDUMP: + new_flags |= VM_DONTDUMP; + break; + case MADV_DODUMP: + if (!is_vm_hugetlb_page(vma) && new_flags & VM_SPECIAL) { + error = -EINVAL; + goto out; + } + new_flags &= ~VM_DONTDUMP; + break; + case MADV_MERGEABLE: + case MADV_UNMERGEABLE: + error = ksm_madvise(vma, start, end, behavior, &new_flags); + if (error) + goto out_convert_errno; + break; + case MADV_HUGEPAGE: + case MADV_NOHUGEPAGE: + error = hugepage_madvise(vma, &new_flags, behavior); + if (error) + goto out_convert_errno; + break; + } + + if (new_flags == vma->vm_flags) { + *prev = vma; + goto out; + } + + pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); + *prev = vma_merge(mm, *prev, start, end, new_flags, vma->anon_vma, + vma->vm_file, pgoff, vma_policy(vma), + vma->vm_userfaultfd_ctx); + if (*prev) { + vma = *prev; + goto success; + } + + *prev = vma; + + if (start != vma->vm_start) { + if (unlikely(mm->map_count >= sysctl_max_map_count)) { + error = -ENOMEM; + goto out; + } + error = __split_vma(mm, vma, start, 1); + if (error) + goto out_convert_errno; + } + + if (end != vma->vm_end) { + if (unlikely(mm->map_count >= sysctl_max_map_count)) { + error = -ENOMEM; + goto out; + } + error = __split_vma(mm, vma, end, 0); + if (error) + goto out_convert_errno; + } + +success: + /* + * vm_flags is protected by the mmap_lock held in write mode. + */ + vma->vm_flags = new_flags; + +out_convert_errno: + /* + * madvise() returns EAGAIN if kernel resources, such as + * slab, are temporarily unavailable. + */ + if (error == -ENOMEM) + error = -EAGAIN; +out: + return error; +} + +#ifdef CONFIG_SWAP +static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start, + unsigned long end, struct mm_walk *walk) +{ + pte_t *orig_pte; + struct vm_area_struct *vma = walk->private; + unsigned long index; + + if (pmd_none_or_trans_huge_or_clear_bad(pmd)) + return 0; + + for (index = start; index != end; index += PAGE_SIZE) { + pte_t pte; + swp_entry_t entry; + struct page *page; + spinlock_t *ptl; + + orig_pte = pte_offset_map_lock(vma->vm_mm, pmd, start, &ptl); + pte = *(orig_pte + ((index - start) / PAGE_SIZE)); + pte_unmap_unlock(orig_pte, ptl); + + if (pte_present(pte) || pte_none(pte)) + continue; + entry = pte_to_swp_entry(pte); + if (unlikely(non_swap_entry(entry))) + continue; + + page = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE, + vma, index, false); + if (page) + put_page(page); + } + + return 0; +} + +static const struct mm_walk_ops swapin_walk_ops = { + .pmd_entry = swapin_walk_pmd_entry, +}; + +static void force_shm_swapin_readahead(struct vm_area_struct *vma, + unsigned long start, unsigned long end, + struct address_space *mapping) +{ + XA_STATE(xas, &mapping->i_pages, linear_page_index(vma, start)); + pgoff_t end_index = linear_page_index(vma, end + PAGE_SIZE - 1); + struct page *page; + + rcu_read_lock(); + xas_for_each(&xas, page, end_index) { + swp_entry_t swap; + + if (!xa_is_value(page)) + continue; + xas_pause(&xas); + rcu_read_unlock(); + + swap = radix_to_swp_entry(page); + page = read_swap_cache_async(swap, GFP_HIGHUSER_MOVABLE, + NULL, 0, false); + if (page) + put_page(page); + + rcu_read_lock(); + } + rcu_read_unlock(); + + lru_add_drain(); /* Push any new pages onto the LRU now */ +} +#endif /* CONFIG_SWAP */ + +/* + * Schedule all required I/O operations. Do not wait for completion. + */ +static long madvise_willneed(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start, unsigned long end) +{ + struct mm_struct *mm = vma->vm_mm; + struct file *file = vma->vm_file; + loff_t offset; + + *prev = vma; +#ifdef CONFIG_SWAP + if (!file) { + walk_page_range(vma->vm_mm, start, end, &swapin_walk_ops, vma); + lru_add_drain(); /* Push any new pages onto the LRU now */ + return 0; + } + + if (shmem_mapping(file->f_mapping)) { + force_shm_swapin_readahead(vma, start, end, + file->f_mapping); + return 0; + } +#else + if (!file) + return -EBADF; +#endif + + if (IS_DAX(file_inode(file))) { + /* no bad return value, but ignore advice */ + return 0; + } + + /* + * Filesystem's fadvise may need to take various locks. We need to + * explicitly grab a reference because the vma (and hence the + * vma's reference to the file) can go away as soon as we drop + * mmap_lock. + */ + *prev = NULL; /* tell sys_madvise we drop mmap_lock */ + get_file(file); + offset = (loff_t)(start - vma->vm_start) + + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); + mmap_read_unlock(mm); + vfs_fadvise(file, offset, end - start, POSIX_FADV_WILLNEED); + fput(file); + mmap_read_lock(mm); + return 0; +} + +static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, + unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + struct madvise_walk_private *private = walk->private; + struct mmu_gather *tlb = private->tlb; + bool pageout = private->pageout; + struct mm_struct *mm = tlb->mm; + struct vm_area_struct *vma = walk->vma; + pte_t *orig_pte, *pte, ptent; + spinlock_t *ptl; + struct page *page = NULL; + LIST_HEAD(page_list); + + if (fatal_signal_pending(current)) + return -EINTR; + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (pmd_trans_huge(*pmd)) { + pmd_t orig_pmd; + unsigned long next = pmd_addr_end(addr, end); + + tlb_change_page_size(tlb, HPAGE_PMD_SIZE); + ptl = pmd_trans_huge_lock(pmd, vma); + if (!ptl) + return 0; + + orig_pmd = *pmd; + if (is_huge_zero_pmd(orig_pmd)) + goto huge_unlock; + + if (unlikely(!pmd_present(orig_pmd))) { + VM_BUG_ON(thp_migration_supported() && + !is_pmd_migration_entry(orig_pmd)); + goto huge_unlock; + } + + page = pmd_page(orig_pmd); + + /* Do not interfere with other mappings of this page */ + if (page_mapcount(page) != 1) + goto huge_unlock; + + if (next - addr != HPAGE_PMD_SIZE) { + int err; + + get_page(page); + spin_unlock(ptl); + lock_page(page); + err = split_huge_page(page); + unlock_page(page); + put_page(page); + if (!err) + goto regular_page; + return 0; + } + + if (pmd_young(orig_pmd)) { + pmdp_invalidate(vma, addr, pmd); + orig_pmd = pmd_mkold(orig_pmd); + + set_pmd_at(mm, addr, pmd, orig_pmd); + tlb_remove_pmd_tlb_entry(tlb, pmd, addr); + } + + ClearPageReferenced(page); + test_and_clear_page_young(page); + if (pageout) { + if (!isolate_lru_page(page)) { + if (PageUnevictable(page)) + putback_lru_page(page); + else + list_add(&page->lru, &page_list); + } + } else + deactivate_page(page); +huge_unlock: + spin_unlock(ptl); + if (pageout) + reclaim_pages(&page_list); + return 0; + } + +regular_page: + if (pmd_trans_unstable(pmd)) + return 0; +#endif + tlb_change_page_size(tlb, PAGE_SIZE); + orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); + flush_tlb_batched_pending(mm); + arch_enter_lazy_mmu_mode(); + for (; addr < end; pte++, addr += PAGE_SIZE) { + ptent = *pte; + + if (pte_none(ptent)) + continue; + + if (!pte_present(ptent)) + continue; + + page = vm_normal_page(vma, addr, ptent); + if (!page) + continue; + + /* + * Creating a THP page is expensive so split it only if we + * are sure it's worth. Split it if we are only owner. + */ + if (PageTransCompound(page)) { + if (page_mapcount(page) != 1) + break; + get_page(page); + if (!trylock_page(page)) { + put_page(page); + break; + } + pte_unmap_unlock(orig_pte, ptl); + if (split_huge_page(page)) { + unlock_page(page); + put_page(page); + pte_offset_map_lock(mm, pmd, addr, &ptl); + break; + } + unlock_page(page); + put_page(page); + pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + pte--; + addr -= PAGE_SIZE; + continue; + } + + /* + * Do not interfere with other mappings of this page and + * non-LRU page. + */ + if (!PageLRU(page) || page_mapcount(page) != 1) + continue; + + VM_BUG_ON_PAGE(PageTransCompound(page), page); + + if (pte_young(ptent)) { + ptent = ptep_get_and_clear_full(mm, addr, pte, + tlb->fullmm); + ptent = pte_mkold(ptent); + set_pte_at(mm, addr, pte, ptent); + tlb_remove_tlb_entry(tlb, pte, addr); + } + + /* + * We are deactivating a page for accelerating reclaiming. + * VM couldn't reclaim the page unless we clear PG_young. + * As a side effect, it makes confuse idle-page tracking + * because they will miss recent referenced history. + */ + ClearPageReferenced(page); + test_and_clear_page_young(page); + if (pageout) { + if (!isolate_lru_page(page)) { + if (PageUnevictable(page)) + putback_lru_page(page); + else + list_add(&page->lru, &page_list); + } + } else + deactivate_page(page); + } + + arch_leave_lazy_mmu_mode(); + pte_unmap_unlock(orig_pte, ptl); + if (pageout) + reclaim_pages(&page_list); + cond_resched(); + + return 0; +} + +static const struct mm_walk_ops cold_walk_ops = { + .pmd_entry = madvise_cold_or_pageout_pte_range, +}; + +static void madvise_cold_page_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, + unsigned long addr, unsigned long end) +{ + struct madvise_walk_private walk_private = { + .pageout = false, + .tlb = tlb, + }; + + tlb_start_vma(tlb, vma); + walk_page_range(vma->vm_mm, addr, end, &cold_walk_ops, &walk_private); + tlb_end_vma(tlb, vma); +} + +static long madvise_cold(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start_addr, unsigned long end_addr) +{ + struct mm_struct *mm = vma->vm_mm; + struct mmu_gather tlb; + + *prev = vma; + if (!can_madv_lru_vma(vma)) + return -EINVAL; + + lru_add_drain(); + tlb_gather_mmu(&tlb, mm, start_addr, end_addr); + madvise_cold_page_range(&tlb, vma, start_addr, end_addr); + tlb_finish_mmu(&tlb, start_addr, end_addr); + + return 0; +} + +static void madvise_pageout_page_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, + unsigned long addr, unsigned long end) +{ + struct madvise_walk_private walk_private = { + .pageout = true, + .tlb = tlb, + }; + + tlb_start_vma(tlb, vma); + walk_page_range(vma->vm_mm, addr, end, &cold_walk_ops, &walk_private); + tlb_end_vma(tlb, vma); +} + +static inline bool can_do_pageout(struct vm_area_struct *vma) +{ + if (vma_is_anonymous(vma)) + return true; + if (!vma->vm_file) + return false; + /* + * paging out pagecache only for non-anonymous mappings that correspond + * to the files the calling process could (if tried) open for writing; + * otherwise we'd be including shared non-exclusive mappings, which + * opens a side channel. + */ + return inode_owner_or_capable(file_inode(vma->vm_file)) || + inode_permission(file_inode(vma->vm_file), MAY_WRITE) == 0; +} + +static long madvise_pageout(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start_addr, unsigned long end_addr) +{ + struct mm_struct *mm = vma->vm_mm; + struct mmu_gather tlb; + + *prev = vma; + if (!can_madv_lru_vma(vma)) + return -EINVAL; + + if (!can_do_pageout(vma)) + return 0; + + lru_add_drain(); + tlb_gather_mmu(&tlb, mm, start_addr, end_addr); + madvise_pageout_page_range(&tlb, vma, start_addr, end_addr); + tlb_finish_mmu(&tlb, start_addr, end_addr); + + return 0; +} + +static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, + unsigned long end, struct mm_walk *walk) + +{ + struct mmu_gather *tlb = walk->private; + struct mm_struct *mm = tlb->mm; + struct vm_area_struct *vma = walk->vma; + spinlock_t *ptl; + pte_t *orig_pte, *pte, ptent; + struct page *page; + int nr_swap = 0; + unsigned long next; + + next = pmd_addr_end(addr, end); + if (pmd_trans_huge(*pmd)) + if (madvise_free_huge_pmd(tlb, vma, pmd, addr, next)) + goto next; + + if (pmd_trans_unstable(pmd)) + return 0; + + tlb_change_page_size(tlb, PAGE_SIZE); + orig_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + flush_tlb_batched_pending(mm); + arch_enter_lazy_mmu_mode(); + for (; addr != end; pte++, addr += PAGE_SIZE) { + ptent = *pte; + + if (pte_none(ptent)) + continue; + /* + * If the pte has swp_entry, just clear page table to + * prevent swap-in which is more expensive rather than + * (page allocation + zeroing). + */ + if (!pte_present(ptent)) { + swp_entry_t entry; + + entry = pte_to_swp_entry(ptent); + if (non_swap_entry(entry)) + continue; + nr_swap--; + free_swap_and_cache(entry); + pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); + continue; + } + + page = vm_normal_page(vma, addr, ptent); + if (!page) + continue; + + /* + * If pmd isn't transhuge but the page is THP and + * is owned by only this process, split it and + * deactivate all pages. + */ + if (PageTransCompound(page)) { + if (page_mapcount(page) != 1) + goto out; + get_page(page); + if (!trylock_page(page)) { + put_page(page); + goto out; + } + pte_unmap_unlock(orig_pte, ptl); + if (split_huge_page(page)) { + unlock_page(page); + put_page(page); + pte_offset_map_lock(mm, pmd, addr, &ptl); + goto out; + } + unlock_page(page); + put_page(page); + pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + pte--; + addr -= PAGE_SIZE; + continue; + } + + VM_BUG_ON_PAGE(PageTransCompound(page), page); + + if (PageSwapCache(page) || PageDirty(page)) { + if (!trylock_page(page)) + continue; + /* + * If page is shared with others, we couldn't clear + * PG_dirty of the page. + */ + if (page_mapcount(page) != 1) { + unlock_page(page); + continue; + } + + if (PageSwapCache(page) && !try_to_free_swap(page)) { + unlock_page(page); + continue; + } + + ClearPageDirty(page); + unlock_page(page); + } + + if (pte_young(ptent) || pte_dirty(ptent)) { + /* + * Some of architecture(ex, PPC) don't update TLB + * with set_pte_at and tlb_remove_tlb_entry so for + * the portability, remap the pte with old|clean + * after pte clearing. + */ + ptent = ptep_get_and_clear_full(mm, addr, pte, + tlb->fullmm); + + ptent = pte_mkold(ptent); + ptent = pte_mkclean(ptent); + set_pte_at(mm, addr, pte, ptent); + tlb_remove_tlb_entry(tlb, pte, addr); + } + mark_page_lazyfree(page); + } +out: + if (nr_swap) { + if (current->mm == mm) + sync_mm_rss(mm); + + add_mm_counter(mm, MM_SWAPENTS, nr_swap); + } + arch_leave_lazy_mmu_mode(); + pte_unmap_unlock(orig_pte, ptl); + cond_resched(); +next: + return 0; +} + +static const struct mm_walk_ops madvise_free_walk_ops = { + .pmd_entry = madvise_free_pte_range, +}; + +static int madvise_free_single_vma(struct vm_area_struct *vma, + unsigned long start_addr, unsigned long end_addr) +{ + struct mm_struct *mm = vma->vm_mm; + struct mmu_notifier_range range; + struct mmu_gather tlb; + + /* MADV_FREE works for only anon vma at the moment */ + if (!vma_is_anonymous(vma)) + return -EINVAL; + + range.start = max(vma->vm_start, start_addr); + if (range.start >= vma->vm_end) + return -EINVAL; + range.end = min(vma->vm_end, end_addr); + if (range.end <= vma->vm_start) + return -EINVAL; + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, + range.start, range.end); + + lru_add_drain(); + tlb_gather_mmu(&tlb, mm, range.start, range.end); + update_hiwater_rss(mm); + + mmu_notifier_invalidate_range_start(&range); + tlb_start_vma(&tlb, vma); + walk_page_range(vma->vm_mm, range.start, range.end, + &madvise_free_walk_ops, &tlb); + tlb_end_vma(&tlb, vma); + mmu_notifier_invalidate_range_end(&range); + tlb_finish_mmu(&tlb, range.start, range.end); + + return 0; +} + +/* + * Application no longer needs these pages. If the pages are dirty, + * it's OK to just throw them away. The app will be more careful about + * data it wants to keep. Be sure to free swap resources too. The + * zap_page_range call sets things up for shrink_active_list to actually free + * these pages later if no one else has touched them in the meantime, + * although we could add these pages to a global reuse list for + * shrink_active_list to pick up before reclaiming other pages. + * + * NB: This interface discards data rather than pushes it out to swap, + * as some implementations do. This has performance implications for + * applications like large transactional databases which want to discard + * pages in anonymous maps after committing to backing store the data + * that was kept in them. There is no reason to write this data out to + * the swap area if the application is discarding it. + * + * An interface that causes the system to free clean pages and flush + * dirty pages is already available as msync(MS_INVALIDATE). + */ +static long madvise_dontneed_single_vma(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + zap_page_range(vma, start, end - start); + return 0; +} + +static long madvise_dontneed_free(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start, unsigned long end, + int behavior) +{ + struct mm_struct *mm = vma->vm_mm; + + *prev = vma; + if (!can_madv_lru_vma(vma)) + return -EINVAL; + + if (!userfaultfd_remove(vma, start, end)) { + *prev = NULL; /* mmap_lock has been dropped, prev is stale */ + + mmap_read_lock(mm); + vma = find_vma(mm, start); + if (!vma) + return -ENOMEM; + if (start < vma->vm_start) { + /* + * This "vma" under revalidation is the one + * with the lowest vma->vm_start where start + * is also < vma->vm_end. If start < + * vma->vm_start it means an hole materialized + * in the user address space within the + * virtual range passed to MADV_DONTNEED + * or MADV_FREE. + */ + return -ENOMEM; + } + if (!can_madv_lru_vma(vma)) + return -EINVAL; + if (end > vma->vm_end) { + /* + * Don't fail if end > vma->vm_end. If the old + * vma was splitted while the mmap_lock was + * released the effect of the concurrent + * operation may not cause madvise() to + * have an undefined result. There may be an + * adjacent next vma that we'll walk + * next. userfaultfd_remove() will generate an + * UFFD_EVENT_REMOVE repetition on the + * end-vma->vm_end range, but the manager can + * handle a repetition fine. + */ + end = vma->vm_end; + } + VM_WARN_ON(start >= end); + } + + if (behavior == MADV_DONTNEED) + return madvise_dontneed_single_vma(vma, start, end); + else if (behavior == MADV_FREE) + return madvise_free_single_vma(vma, start, end); + else + return -EINVAL; +} + +/* + * Application wants to free up the pages and associated backing store. + * This is effectively punching a hole into the middle of a file. + */ +static long madvise_remove(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start, unsigned long end) +{ + loff_t offset; + int error; + struct file *f; + struct mm_struct *mm = vma->vm_mm; + + *prev = NULL; /* tell sys_madvise we drop mmap_lock */ + + if (vma->vm_flags & VM_LOCKED) + return -EINVAL; + + f = vma->vm_file; + + if (!f || !f->f_mapping || !f->f_mapping->host) { + return -EINVAL; + } + + if ((vma->vm_flags & (VM_SHARED|VM_WRITE)) != (VM_SHARED|VM_WRITE)) + return -EACCES; + + offset = (loff_t)(start - vma->vm_start) + + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); + + /* + * Filesystem's fallocate may need to take i_mutex. We need to + * explicitly grab a reference because the vma (and hence the + * vma's reference to the file) can go away as soon as we drop + * mmap_lock. + */ + get_file(f); + if (userfaultfd_remove(vma, start, end)) { + /* mmap_lock was not released by userfaultfd_remove() */ + mmap_read_unlock(mm); + } + error = vfs_fallocate(f, + FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, + offset, end - start); + fput(f); + mmap_read_lock(mm); + return error; +} + +#ifdef CONFIG_MEMORY_FAILURE +/* + * Error injection support for memory error handling. + */ +static int madvise_inject_error(int behavior, + unsigned long start, unsigned long end) +{ + struct zone *zone; + unsigned long size; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + + for (; start < end; start += size) { + unsigned long pfn; + struct page *page; + int ret; + + ret = get_user_pages_fast(start, 1, 0, &page); + if (ret != 1) + return ret; + pfn = page_to_pfn(page); + + /* + * When soft offlining hugepages, after migrating the page + * we dissolve it, therefore in the second loop "page" will + * no longer be a compound page. + */ + size = page_size(compound_head(page)); + + if (behavior == MADV_SOFT_OFFLINE) { + pr_info("Soft offlining pfn %#lx at process virtual address %#lx\n", + pfn, start); + ret = soft_offline_page(pfn, MF_COUNT_INCREASED); + } else { + pr_info("Injecting memory failure for pfn %#lx at process virtual address %#lx\n", + pfn, start); + ret = memory_failure(pfn, MF_COUNT_INCREASED); + } + + if (ret) + return ret; + } + + /* Ensure that all poisoned pages are removed from per-cpu lists */ + for_each_populated_zone(zone) + drain_all_pages(zone); + + return 0; +} +#endif + +static long +madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev, + unsigned long start, unsigned long end, int behavior) +{ + switch (behavior) { + case MADV_REMOVE: + return madvise_remove(vma, prev, start, end); + case MADV_WILLNEED: + return madvise_willneed(vma, prev, start, end); + case MADV_COLD: + return madvise_cold(vma, prev, start, end); + case MADV_PAGEOUT: + return madvise_pageout(vma, prev, start, end); + case MADV_FREE: + case MADV_DONTNEED: + return madvise_dontneed_free(vma, prev, start, end, behavior); + default: + return madvise_behavior(vma, prev, start, end, behavior); + } +} + +static bool +madvise_behavior_valid(int behavior) +{ + switch (behavior) { + case MADV_DOFORK: + case MADV_DONTFORK: + case MADV_NORMAL: + case MADV_SEQUENTIAL: + case MADV_RANDOM: + case MADV_REMOVE: + case MADV_WILLNEED: + case MADV_DONTNEED: + case MADV_FREE: + case MADV_COLD: + case MADV_PAGEOUT: +#ifdef CONFIG_KSM + case MADV_MERGEABLE: + case MADV_UNMERGEABLE: +#endif +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + case MADV_HUGEPAGE: + case MADV_NOHUGEPAGE: +#endif + case MADV_DONTDUMP: + case MADV_DODUMP: + case MADV_WIPEONFORK: + case MADV_KEEPONFORK: +#ifdef CONFIG_MEMORY_FAILURE + case MADV_SOFT_OFFLINE: + case MADV_HWPOISON: +#endif + return true; + + default: + return false; + } +} + +static bool +process_madvise_behavior_valid(int behavior) +{ + switch (behavior) { + case MADV_COLD: + case MADV_PAGEOUT: + return true; + default: + return false; + } +} + +/* + * The madvise(2) system call. + * + * Applications can use madvise() to advise the kernel how it should + * handle paging I/O in this VM area. The idea is to help the kernel + * use appropriate read-ahead and caching techniques. The information + * provided is advisory only, and can be safely disregarded by the + * kernel without affecting the correct operation of the application. + * + * behavior values: + * MADV_NORMAL - the default behavior is to read clusters. This + * results in some read-ahead and read-behind. + * MADV_RANDOM - the system should read the minimum amount of data + * on any access, since it is unlikely that the appli- + * cation will need more than what it asks for. + * MADV_SEQUENTIAL - pages in the given range will probably be accessed + * once, so they can be aggressively read ahead, and + * can be freed soon after they are accessed. + * MADV_WILLNEED - the application is notifying the system to read + * some pages ahead. + * MADV_DONTNEED - the application is finished with the given range, + * so the kernel can free resources associated with it. + * MADV_FREE - the application marks pages in the given range as lazy free, + * where actual purges are postponed until memory pressure happens. + * MADV_REMOVE - the application wants to free up the given range of + * pages and associated backing store. + * MADV_DONTFORK - omit this area from child's address space when forking: + * typically, to avoid COWing pages pinned by get_user_pages(). + * MADV_DOFORK - cancel MADV_DONTFORK: no longer omit this area when forking. + * MADV_WIPEONFORK - present the child process with zero-filled memory in this + * range after a fork. + * MADV_KEEPONFORK - undo the effect of MADV_WIPEONFORK + * MADV_HWPOISON - trigger memory error handler as if the given memory range + * were corrupted by unrecoverable hardware memory failure. + * MADV_SOFT_OFFLINE - try to soft-offline the given range of memory. + * MADV_MERGEABLE - the application recommends that KSM try to merge pages in + * this area with pages of identical content from other such areas. + * MADV_UNMERGEABLE- cancel MADV_MERGEABLE: no longer merge pages with others. + * MADV_HUGEPAGE - the application wants to back the given range by transparent + * huge pages in the future. Existing pages might be coalesced and + * new pages might be allocated as THP. + * MADV_NOHUGEPAGE - mark the given range as not worth being backed by + * transparent huge pages so the existing pages will not be + * coalesced into THP and new pages will not be allocated as THP. + * MADV_DONTDUMP - the application wants to prevent pages in the given range + * from being included in its core dump. + * MADV_DODUMP - cancel MADV_DONTDUMP: no longer exclude from core dump. + * MADV_COLD - the application is not expected to use this memory soon, + * deactivate pages in this range so that they can be reclaimed + * easily if memory pressure hanppens. + * MADV_PAGEOUT - the application is not expected to use this memory soon, + * page out the pages in this range immediately. + * + * return values: + * zero - success + * -EINVAL - start + len < 0, start is not page-aligned, + * "behavior" is not a valid value, or application + * is attempting to release locked or shared pages, + * or the specified address range includes file, Huge TLB, + * MAP_SHARED or VMPFNMAP range. + * -ENOMEM - addresses in the specified range are not currently + * mapped, or are outside the AS of the process. + * -EIO - an I/O error occurred while paging in data. + * -EBADF - map exists, but area maps something that isn't a file. + * -EAGAIN - a kernel resource was temporarily unavailable. + */ +int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior) +{ + unsigned long end, tmp; + struct vm_area_struct *vma, *prev; + int unmapped_error = 0; + int error = -EINVAL; + int write; + size_t len; + struct blk_plug plug; + + start = untagged_addr(start); + + if (!madvise_behavior_valid(behavior)) + return error; + + if (!PAGE_ALIGNED(start)) + return error; + len = PAGE_ALIGN(len_in); + + /* Check to see whether len was rounded up from small -ve to zero */ + if (len_in && !len) + return error; + + end = start + len; + if (end < start) + return error; + + error = 0; + if (end == start) + return error; + +#ifdef CONFIG_MEMORY_FAILURE + if (behavior == MADV_HWPOISON || behavior == MADV_SOFT_OFFLINE) + return madvise_inject_error(behavior, start, start + len_in); +#endif + + write = madvise_need_mmap_write(behavior); + if (write) { + if (mmap_write_lock_killable(mm)) + return -EINTR; + } else { + mmap_read_lock(mm); + } + + /* + * If the interval [start,end) covers some unmapped address + * ranges, just ignore them, but return -ENOMEM at the end. + * - different from the way of handling in mlock etc. + */ + vma = find_vma_prev(mm, start, &prev); + if (vma && start > vma->vm_start) + prev = vma; + + blk_start_plug(&plug); + for (;;) { + /* Still start < end. */ + error = -ENOMEM; + if (!vma) + goto out; + + /* Here start < (end|vma->vm_end). */ + if (start < vma->vm_start) { + unmapped_error = -ENOMEM; + start = vma->vm_start; + if (start >= end) + goto out; + } + + /* Here vma->vm_start <= start < (end|vma->vm_end) */ + tmp = vma->vm_end; + if (end < tmp) + tmp = end; + + /* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */ + error = madvise_vma(vma, &prev, start, tmp, behavior); + if (error) + goto out; + start = tmp; + if (prev && start < prev->vm_end) + start = prev->vm_end; + error = unmapped_error; + if (start >= end) + goto out; + if (prev) + vma = prev->vm_next; + else /* madvise_remove dropped mmap_lock */ + vma = find_vma(mm, start); + } +out: + blk_finish_plug(&plug); + if (write) + mmap_write_unlock(mm); + else + mmap_read_unlock(mm); + + return error; +} + +SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) +{ + return do_madvise(current->mm, start, len_in, behavior); +} + +SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec, + size_t, vlen, int, behavior, unsigned int, flags) +{ + ssize_t ret; + struct iovec iovstack[UIO_FASTIOV], iovec; + struct iovec *iov = iovstack; + struct iov_iter iter; + struct pid *pid; + struct task_struct *task; + struct mm_struct *mm; + size_t total_len; + unsigned int f_flags; + + if (flags != 0) { + ret = -EINVAL; + goto out; + } + + ret = import_iovec(READ, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); + if (ret < 0) + goto out; + + pid = pidfd_get_pid(pidfd, &f_flags); + if (IS_ERR(pid)) { + ret = PTR_ERR(pid); + goto free_iov; + } + + task = get_pid_task(pid, PIDTYPE_PID); + if (!task) { + ret = -ESRCH; + goto put_pid; + } + + if (!process_madvise_behavior_valid(behavior)) { + ret = -EINVAL; + goto release_task; + } + + /* Require PTRACE_MODE_READ to avoid leaking ASLR metadata. */ + mm = mm_access(task, PTRACE_MODE_READ_FSCREDS); + if (IS_ERR_OR_NULL(mm)) { + ret = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH; + goto release_task; + } + + /* + * Require CAP_SYS_NICE for influencing process performance. Note that + * only non-destructive hints are currently supported. + */ + if (!capable(CAP_SYS_NICE)) { + ret = -EPERM; + goto release_mm; + } + + total_len = iov_iter_count(&iter); + + while (iov_iter_count(&iter)) { + iovec = iov_iter_iovec(&iter); + ret = do_madvise(mm, (unsigned long)iovec.iov_base, + iovec.iov_len, behavior); + if (ret < 0) + break; + iov_iter_advance(&iter, iovec.iov_len); + } + + ret = (total_len - iov_iter_count(&iter)) ? : ret; + +release_mm: + mmput(mm); +release_task: + put_task_struct(task); +put_pid: + put_pid(pid); +free_iov: + kfree(iov); +out: + return ret; +} diff --git a/mm/mapping_dirty_helpers.c b/mm/mapping_dirty_helpers.c new file mode 100644 index 000000000..2c7d03675 --- /dev/null +++ b/mm/mapping_dirty_helpers.c @@ -0,0 +1,349 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include + +/** + * struct wp_walk - Private struct for pagetable walk callbacks + * @range: Range for mmu notifiers + * @tlbflush_start: Address of first modified pte + * @tlbflush_end: Address of last modified pte + 1 + * @total: Total number of modified ptes + */ +struct wp_walk { + struct mmu_notifier_range range; + unsigned long tlbflush_start; + unsigned long tlbflush_end; + unsigned long total; +}; + +/** + * wp_pte - Write-protect a pte + * @pte: Pointer to the pte + * @addr: The virtual page address + * @walk: pagetable walk callback argument + * + * The function write-protects a pte and records the range in + * virtual address space of touched ptes for efficient range TLB flushes. + */ +static int wp_pte(pte_t *pte, unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + struct wp_walk *wpwalk = walk->private; + pte_t ptent = *pte; + + if (pte_write(ptent)) { + pte_t old_pte = ptep_modify_prot_start(walk->vma, addr, pte); + + ptent = pte_wrprotect(old_pte); + ptep_modify_prot_commit(walk->vma, addr, pte, old_pte, ptent); + wpwalk->total++; + wpwalk->tlbflush_start = min(wpwalk->tlbflush_start, addr); + wpwalk->tlbflush_end = max(wpwalk->tlbflush_end, + addr + PAGE_SIZE); + } + + return 0; +} + +/** + * struct clean_walk - Private struct for the clean_record_pte function. + * @base: struct wp_walk we derive from + * @bitmap_pgoff: Address_space Page offset of the first bit in @bitmap + * @bitmap: Bitmap with one bit for each page offset in the address_space range + * covered. + * @start: Address_space page offset of first modified pte relative + * to @bitmap_pgoff + * @end: Address_space page offset of last modified pte relative + * to @bitmap_pgoff + */ +struct clean_walk { + struct wp_walk base; + pgoff_t bitmap_pgoff; + unsigned long *bitmap; + pgoff_t start; + pgoff_t end; +}; + +#define to_clean_walk(_wpwalk) container_of(_wpwalk, struct clean_walk, base) + +/** + * clean_record_pte - Clean a pte and record its address space offset in a + * bitmap + * @pte: Pointer to the pte + * @addr: The virtual page address + * @walk: pagetable walk callback argument + * + * The function cleans a pte and records the range in + * virtual address space of touched ptes for efficient TLB flushes. + * It also records dirty ptes in a bitmap representing page offsets + * in the address_space, as well as the first and last of the bits + * touched. + */ +static int clean_record_pte(pte_t *pte, unsigned long addr, + unsigned long end, struct mm_walk *walk) +{ + struct wp_walk *wpwalk = walk->private; + struct clean_walk *cwalk = to_clean_walk(wpwalk); + pte_t ptent = *pte; + + if (pte_dirty(ptent)) { + pgoff_t pgoff = ((addr - walk->vma->vm_start) >> PAGE_SHIFT) + + walk->vma->vm_pgoff - cwalk->bitmap_pgoff; + pte_t old_pte = ptep_modify_prot_start(walk->vma, addr, pte); + + ptent = pte_mkclean(old_pte); + ptep_modify_prot_commit(walk->vma, addr, pte, old_pte, ptent); + + wpwalk->total++; + wpwalk->tlbflush_start = min(wpwalk->tlbflush_start, addr); + wpwalk->tlbflush_end = max(wpwalk->tlbflush_end, + addr + PAGE_SIZE); + + __set_bit(pgoff, cwalk->bitmap); + cwalk->start = min(cwalk->start, pgoff); + cwalk->end = max(cwalk->end, pgoff + 1); + } + + return 0; +} + +/* + * wp_clean_pmd_entry - The pagewalk pmd callback. + * + * Dirty-tracking should take place on the PTE level, so + * WARN() if encountering a dirty huge pmd. + * Furthermore, never split huge pmds, since that currently + * causes dirty info loss. The pagefault handler should do + * that if needed. + */ +static int wp_clean_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + pmd_t pmdval = pmd_read_atomic(pmd); + + if (!pmd_trans_unstable(&pmdval)) + return 0; + + if (pmd_none(pmdval)) { + walk->action = ACTION_AGAIN; + return 0; + } + + /* Huge pmd, present or migrated */ + walk->action = ACTION_CONTINUE; + if (pmd_trans_huge(pmdval) || pmd_devmap(pmdval)) + WARN_ON(pmd_write(pmdval) || pmd_dirty(pmdval)); + + return 0; +} + +/* + * wp_clean_pud_entry - The pagewalk pud callback. + * + * Dirty-tracking should take place on the PTE level, so + * WARN() if encountering a dirty huge puds. + * Furthermore, never split huge puds, since that currently + * causes dirty info loss. The pagefault handler should do + * that if needed. + */ +static int wp_clean_pud_entry(pud_t *pud, unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + pud_t pudval = READ_ONCE(*pud); + + if (!pud_trans_unstable(&pudval)) + return 0; + + if (pud_none(pudval)) { + walk->action = ACTION_AGAIN; + return 0; + } + + /* Huge pud */ + walk->action = ACTION_CONTINUE; + if (pud_trans_huge(pudval) || pud_devmap(pudval)) + WARN_ON(pud_write(pudval) || pud_dirty(pudval)); + + return 0; +} + +/* + * wp_clean_pre_vma - The pagewalk pre_vma callback. + * + * The pre_vma callback performs the cache flush, stages the tlb flush + * and calls the necessary mmu notifiers. + */ +static int wp_clean_pre_vma(unsigned long start, unsigned long end, + struct mm_walk *walk) +{ + struct wp_walk *wpwalk = walk->private; + + wpwalk->tlbflush_start = end; + wpwalk->tlbflush_end = start; + + mmu_notifier_range_init(&wpwalk->range, MMU_NOTIFY_PROTECTION_PAGE, 0, + walk->vma, walk->mm, start, end); + mmu_notifier_invalidate_range_start(&wpwalk->range); + flush_cache_range(walk->vma, start, end); + + /* + * We're not using tlb_gather_mmu() since typically + * only a small subrange of PTEs are affected, whereas + * tlb_gather_mmu() records the full range. + */ + inc_tlb_flush_pending(walk->mm); + + return 0; +} + +/* + * wp_clean_post_vma - The pagewalk post_vma callback. + * + * The post_vma callback performs the tlb flush and calls necessary mmu + * notifiers. + */ +static void wp_clean_post_vma(struct mm_walk *walk) +{ + struct wp_walk *wpwalk = walk->private; + + if (mm_tlb_flush_nested(walk->mm)) + flush_tlb_range(walk->vma, wpwalk->range.start, + wpwalk->range.end); + else if (wpwalk->tlbflush_end > wpwalk->tlbflush_start) + flush_tlb_range(walk->vma, wpwalk->tlbflush_start, + wpwalk->tlbflush_end); + + mmu_notifier_invalidate_range_end(&wpwalk->range); + dec_tlb_flush_pending(walk->mm); +} + +/* + * wp_clean_test_walk - The pagewalk test_walk callback. + * + * Won't perform dirty-tracking on COW, read-only or HUGETLB vmas. + */ +static int wp_clean_test_walk(unsigned long start, unsigned long end, + struct mm_walk *walk) +{ + unsigned long vm_flags = READ_ONCE(walk->vma->vm_flags); + + /* Skip non-applicable VMAs */ + if ((vm_flags & (VM_SHARED | VM_MAYWRITE | VM_HUGETLB)) != + (VM_SHARED | VM_MAYWRITE)) + return 1; + + return 0; +} + +static const struct mm_walk_ops clean_walk_ops = { + .pte_entry = clean_record_pte, + .pmd_entry = wp_clean_pmd_entry, + .pud_entry = wp_clean_pud_entry, + .test_walk = wp_clean_test_walk, + .pre_vma = wp_clean_pre_vma, + .post_vma = wp_clean_post_vma +}; + +static const struct mm_walk_ops wp_walk_ops = { + .pte_entry = wp_pte, + .pmd_entry = wp_clean_pmd_entry, + .pud_entry = wp_clean_pud_entry, + .test_walk = wp_clean_test_walk, + .pre_vma = wp_clean_pre_vma, + .post_vma = wp_clean_post_vma +}; + +/** + * wp_shared_mapping_range - Write-protect all ptes in an address space range + * @mapping: The address_space we want to write protect + * @first_index: The first page offset in the range + * @nr: Number of incremental page offsets to cover + * + * Note: This function currently skips transhuge page-table entries, since + * it's intended for dirty-tracking on the PTE level. It will warn on + * encountering transhuge write-enabled entries, though, and can easily be + * extended to handle them as well. + * + * Return: The number of ptes actually write-protected. Note that + * already write-protected ptes are not counted. + */ +unsigned long wp_shared_mapping_range(struct address_space *mapping, + pgoff_t first_index, pgoff_t nr) +{ + struct wp_walk wpwalk = { .total = 0 }; + + i_mmap_lock_read(mapping); + WARN_ON(walk_page_mapping(mapping, first_index, nr, &wp_walk_ops, + &wpwalk)); + i_mmap_unlock_read(mapping); + + return wpwalk.total; +} +EXPORT_SYMBOL_GPL(wp_shared_mapping_range); + +/** + * clean_record_shared_mapping_range - Clean and record all ptes in an + * address space range + * @mapping: The address_space we want to clean + * @first_index: The first page offset in the range + * @nr: Number of incremental page offsets to cover + * @bitmap_pgoff: The page offset of the first bit in @bitmap + * @bitmap: Pointer to a bitmap of at least @nr bits. The bitmap needs to + * cover the whole range @first_index..@first_index + @nr. + * @start: Pointer to number of the first set bit in @bitmap. + * is modified as new bits are set by the function. + * @end: Pointer to the number of the last set bit in @bitmap. + * none set. The value is modified as new bits are set by the function. + * + * Note: When this function returns there is no guarantee that a CPU has + * not already dirtied new ptes. However it will not clean any ptes not + * reported in the bitmap. The guarantees are as follows: + * a) All ptes dirty when the function starts executing will end up recorded + * in the bitmap. + * b) All ptes dirtied after that will either remain dirty, be recorded in the + * bitmap or both. + * + * If a caller needs to make sure all dirty ptes are picked up and none + * additional are added, it first needs to write-protect the address-space + * range and make sure new writers are blocked in page_mkwrite() or + * pfn_mkwrite(). And then after a TLB flush following the write-protection + * pick up all dirty bits. + * + * Note: This function currently skips transhuge page-table entries, since + * it's intended for dirty-tracking on the PTE level. It will warn on + * encountering transhuge dirty entries, though, and can easily be extended + * to handle them as well. + * + * Return: The number of dirty ptes actually cleaned. + */ +unsigned long clean_record_shared_mapping_range(struct address_space *mapping, + pgoff_t first_index, pgoff_t nr, + pgoff_t bitmap_pgoff, + unsigned long *bitmap, + pgoff_t *start, + pgoff_t *end) +{ + bool none_set = (*start >= *end); + struct clean_walk cwalk = { + .base = { .total = 0 }, + .bitmap_pgoff = bitmap_pgoff, + .bitmap = bitmap, + .start = none_set ? nr : *start, + .end = none_set ? 0 : *end, + }; + + i_mmap_lock_read(mapping); + WARN_ON(walk_page_mapping(mapping, first_index, nr, &clean_walk_ops, + &cwalk.base)); + i_mmap_unlock_read(mapping); + + *start = cwalk.start; + *end = cwalk.end; + + return cwalk.base.total; +} +EXPORT_SYMBOL_GPL(clean_record_shared_mapping_range); diff --git a/mm/memblock.c b/mm/memblock.c new file mode 100644 index 000000000..f72d53957 --- /dev/null +++ b/mm/memblock.c @@ -0,0 +1,2031 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Procedures for maintaining information about logical memory blocks. + * + * Peter Bergner, IBM Corp. June 2001. + * Copyright (C) 2001 Peter Bergner. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include "internal.h" + +#define INIT_MEMBLOCK_REGIONS 128 +#define INIT_PHYSMEM_REGIONS 4 + +#ifndef INIT_MEMBLOCK_RESERVED_REGIONS +# define INIT_MEMBLOCK_RESERVED_REGIONS INIT_MEMBLOCK_REGIONS +#endif + +/** + * DOC: memblock overview + * + * Memblock is a method of managing memory regions during the early + * boot period when the usual kernel memory allocators are not up and + * running. + * + * Memblock views the system memory as collections of contiguous + * regions. There are several types of these collections: + * + * * ``memory`` - describes the physical memory available to the + * kernel; this may differ from the actual physical memory installed + * in the system, for instance when the memory is restricted with + * ``mem=`` command line parameter + * * ``reserved`` - describes the regions that were allocated + * * ``physmem`` - describes the actual physical memory available during + * boot regardless of the possible restrictions and memory hot(un)plug; + * the ``physmem`` type is only available on some architectures. + * + * Each region is represented by struct memblock_region that + * defines the region extents, its attributes and NUMA node id on NUMA + * systems. Every memory type is described by the struct memblock_type + * which contains an array of memory regions along with + * the allocator metadata. The "memory" and "reserved" types are nicely + * wrapped with struct memblock. This structure is statically + * initialized at build time. The region arrays are initially sized to + * %INIT_MEMBLOCK_REGIONS for "memory" and %INIT_MEMBLOCK_RESERVED_REGIONS + * for "reserved". The region array for "physmem" is initially sized to + * %INIT_PHYSMEM_REGIONS. + * The memblock_allow_resize() enables automatic resizing of the region + * arrays during addition of new regions. This feature should be used + * with care so that memory allocated for the region array will not + * overlap with areas that should be reserved, for example initrd. + * + * The early architecture setup should tell memblock what the physical + * memory layout is by using memblock_add() or memblock_add_node() + * functions. The first function does not assign the region to a NUMA + * node and it is appropriate for UMA systems. Yet, it is possible to + * use it on NUMA systems as well and assign the region to a NUMA node + * later in the setup process using memblock_set_node(). The + * memblock_add_node() performs such an assignment directly. + * + * Once memblock is setup the memory can be allocated using one of the + * API variants: + * + * * memblock_phys_alloc*() - these functions return the **physical** + * address of the allocated memory + * * memblock_alloc*() - these functions return the **virtual** address + * of the allocated memory. + * + * Note, that both API variants use implicit assumptions about allowed + * memory ranges and the fallback methods. Consult the documentation + * of memblock_alloc_internal() and memblock_alloc_range_nid() + * functions for more elaborate description. + * + * As the system boot progresses, the architecture specific mem_init() + * function frees all the memory to the buddy page allocator. + * + * Unless an architecture enables %CONFIG_ARCH_KEEP_MEMBLOCK, the + * memblock data structures (except "physmem") will be discarded after the + * system initialization completes. + */ + +#ifndef CONFIG_NEED_MULTIPLE_NODES +struct pglist_data __refdata contig_page_data; +EXPORT_SYMBOL(contig_page_data); +#endif + +unsigned long max_low_pfn; +unsigned long min_low_pfn; +unsigned long max_pfn; +unsigned long long max_possible_pfn; + +static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock; +static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_RESERVED_REGIONS] __initdata_memblock; +#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP +static struct memblock_region memblock_physmem_init_regions[INIT_PHYSMEM_REGIONS]; +#endif + +struct memblock memblock __initdata_memblock = { + .memory.regions = memblock_memory_init_regions, + .memory.cnt = 1, /* empty dummy entry */ + .memory.max = INIT_MEMBLOCK_REGIONS, + .memory.name = "memory", + + .reserved.regions = memblock_reserved_init_regions, + .reserved.cnt = 1, /* empty dummy entry */ + .reserved.max = INIT_MEMBLOCK_RESERVED_REGIONS, + .reserved.name = "reserved", + + .bottom_up = false, + .current_limit = MEMBLOCK_ALLOC_ANYWHERE, +}; + +#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP +struct memblock_type physmem = { + .regions = memblock_physmem_init_regions, + .cnt = 1, /* empty dummy entry */ + .max = INIT_PHYSMEM_REGIONS, + .name = "physmem", +}; +#endif + +/* + * keep a pointer to &memblock.memory in the text section to use it in + * __next_mem_range() and its helpers. + * For architectures that do not keep memblock data after init, this + * pointer will be reset to NULL at memblock_discard() + */ +static __refdata struct memblock_type *memblock_memory = &memblock.memory; + +#define for_each_memblock_type(i, memblock_type, rgn) \ + for (i = 0, rgn = &memblock_type->regions[0]; \ + i < memblock_type->cnt; \ + i++, rgn = &memblock_type->regions[i]) + +#define memblock_dbg(fmt, ...) \ + do { \ + if (memblock_debug) \ + pr_info(fmt, ##__VA_ARGS__); \ + } while (0) + +static int memblock_debug __initdata_memblock; +static bool system_has_some_mirror __initdata_memblock = false; +static int memblock_can_resize __initdata_memblock; +static int memblock_memory_in_slab __initdata_memblock = 0; +static int memblock_reserved_in_slab __initdata_memblock = 0; + +static enum memblock_flags __init_memblock choose_memblock_flags(void) +{ + return system_has_some_mirror ? MEMBLOCK_MIRROR : MEMBLOCK_NONE; +} + +/* adjust *@size so that (@base + *@size) doesn't overflow, return new size */ +static inline phys_addr_t memblock_cap_size(phys_addr_t base, phys_addr_t *size) +{ + return *size = min(*size, PHYS_ADDR_MAX - base); +} + +/* + * Address comparison utilities + */ +static unsigned long __init_memblock memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1, + phys_addr_t base2, phys_addr_t size2) +{ + return ((base1 < (base2 + size2)) && (base2 < (base1 + size1))); +} + +bool __init_memblock memblock_overlaps_region(struct memblock_type *type, + phys_addr_t base, phys_addr_t size) +{ + unsigned long i; + + memblock_cap_size(base, &size); + + for (i = 0; i < type->cnt; i++) + if (memblock_addrs_overlap(base, size, type->regions[i].base, + type->regions[i].size)) + break; + return i < type->cnt; +} + +/** + * __memblock_find_range_bottom_up - find free area utility in bottom-up + * @start: start of candidate range + * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or + * %MEMBLOCK_ALLOC_ACCESSIBLE + * @size: size of free area to find + * @align: alignment of free area to find + * @nid: nid of the free area to find, %NUMA_NO_NODE for any node + * @flags: pick from blocks based on memory attributes + * + * Utility called from memblock_find_in_range_node(), find free area bottom-up. + * + * Return: + * Found address on success, 0 on failure. + */ +static phys_addr_t __init_memblock +__memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end, + phys_addr_t size, phys_addr_t align, int nid, + enum memblock_flags flags) +{ + phys_addr_t this_start, this_end, cand; + u64 i; + + for_each_free_mem_range(i, nid, flags, &this_start, &this_end, NULL) { + this_start = clamp(this_start, start, end); + this_end = clamp(this_end, start, end); + + cand = round_up(this_start, align); + if (cand < this_end && this_end - cand >= size) + return cand; + } + + return 0; +} + +/** + * __memblock_find_range_top_down - find free area utility, in top-down + * @start: start of candidate range + * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or + * %MEMBLOCK_ALLOC_ACCESSIBLE + * @size: size of free area to find + * @align: alignment of free area to find + * @nid: nid of the free area to find, %NUMA_NO_NODE for any node + * @flags: pick from blocks based on memory attributes + * + * Utility called from memblock_find_in_range_node(), find free area top-down. + * + * Return: + * Found address on success, 0 on failure. + */ +static phys_addr_t __init_memblock +__memblock_find_range_top_down(phys_addr_t start, phys_addr_t end, + phys_addr_t size, phys_addr_t align, int nid, + enum memblock_flags flags) +{ + phys_addr_t this_start, this_end, cand; + u64 i; + + for_each_free_mem_range_reverse(i, nid, flags, &this_start, &this_end, + NULL) { + this_start = clamp(this_start, start, end); + this_end = clamp(this_end, start, end); + + if (this_end < size) + continue; + + cand = round_down(this_end - size, align); + if (cand >= this_start) + return cand; + } + + return 0; +} + +/** + * memblock_find_in_range_node - find free area in given range and node + * @size: size of free area to find + * @align: alignment of free area to find + * @start: start of candidate range + * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or + * %MEMBLOCK_ALLOC_ACCESSIBLE + * @nid: nid of the free area to find, %NUMA_NO_NODE for any node + * @flags: pick from blocks based on memory attributes + * + * Find @size free area aligned to @align in the specified range and node. + * + * Return: + * Found address on success, 0 on failure. + */ +static phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size, + phys_addr_t align, phys_addr_t start, + phys_addr_t end, int nid, + enum memblock_flags flags) +{ + /* pump up @end */ + if (end == MEMBLOCK_ALLOC_ACCESSIBLE || + end == MEMBLOCK_ALLOC_KASAN) + end = memblock.current_limit; + + /* avoid allocating the first page */ + start = max_t(phys_addr_t, start, PAGE_SIZE); + end = max(start, end); + + if (memblock_bottom_up()) + return __memblock_find_range_bottom_up(start, end, size, align, + nid, flags); + else + return __memblock_find_range_top_down(start, end, size, align, + nid, flags); +} + +/** + * memblock_find_in_range - find free area in given range + * @start: start of candidate range + * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or + * %MEMBLOCK_ALLOC_ACCESSIBLE + * @size: size of free area to find + * @align: alignment of free area to find + * + * Find @size free area aligned to @align in the specified range. + * + * Return: + * Found address on success, 0 on failure. + */ +phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start, + phys_addr_t end, phys_addr_t size, + phys_addr_t align) +{ + phys_addr_t ret; + enum memblock_flags flags = choose_memblock_flags(); + +again: + ret = memblock_find_in_range_node(size, align, start, end, + NUMA_NO_NODE, flags); + + if (!ret && (flags & MEMBLOCK_MIRROR)) { + pr_warn("Could not allocate %pap bytes of mirrored memory\n", + &size); + flags &= ~MEMBLOCK_MIRROR; + goto again; + } + + return ret; +} + +static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r) +{ + type->total_size -= type->regions[r].size; + memmove(&type->regions[r], &type->regions[r + 1], + (type->cnt - (r + 1)) * sizeof(type->regions[r])); + type->cnt--; + + /* Special case for empty arrays */ + if (type->cnt == 0) { + WARN_ON(type->total_size != 0); + type->cnt = 1; + type->regions[0].base = 0; + type->regions[0].size = 0; + type->regions[0].flags = 0; + memblock_set_region_node(&type->regions[0], MAX_NUMNODES); + } +} + +#ifndef CONFIG_ARCH_KEEP_MEMBLOCK +/** + * memblock_discard - discard memory and reserved arrays if they were allocated + */ +void __init memblock_discard(void) +{ + phys_addr_t addr, size; + + if (memblock.reserved.regions != memblock_reserved_init_regions) { + addr = __pa(memblock.reserved.regions); + size = PAGE_ALIGN(sizeof(struct memblock_region) * + memblock.reserved.max); + if (memblock_reserved_in_slab) + kfree(memblock.reserved.regions); + else + __memblock_free_late(addr, size); + } + + if (memblock.memory.regions != memblock_memory_init_regions) { + addr = __pa(memblock.memory.regions); + size = PAGE_ALIGN(sizeof(struct memblock_region) * + memblock.memory.max); + if (memblock_memory_in_slab) + kfree(memblock.memory.regions); + else + __memblock_free_late(addr, size); + } + + memblock_memory = NULL; +} +#endif + +/** + * memblock_double_array - double the size of the memblock regions array + * @type: memblock type of the regions array being doubled + * @new_area_start: starting address of memory range to avoid overlap with + * @new_area_size: size of memory range to avoid overlap with + * + * Double the size of the @type regions array. If memblock is being used to + * allocate memory for a new reserved regions array and there is a previously + * allocated memory range [@new_area_start, @new_area_start + @new_area_size] + * waiting to be reserved, ensure the memory used by the new array does + * not overlap. + * + * Return: + * 0 on success, -1 on failure. + */ +static int __init_memblock memblock_double_array(struct memblock_type *type, + phys_addr_t new_area_start, + phys_addr_t new_area_size) +{ + struct memblock_region *new_array, *old_array; + phys_addr_t old_alloc_size, new_alloc_size; + phys_addr_t old_size, new_size, addr, new_end; + int use_slab = slab_is_available(); + int *in_slab; + + /* We don't allow resizing until we know about the reserved regions + * of memory that aren't suitable for allocation + */ + if (!memblock_can_resize) + return -1; + + /* Calculate new doubled size */ + old_size = type->max * sizeof(struct memblock_region); + new_size = old_size << 1; + /* + * We need to allocated new one align to PAGE_SIZE, + * so we can free them completely later. + */ + old_alloc_size = PAGE_ALIGN(old_size); + new_alloc_size = PAGE_ALIGN(new_size); + + /* Retrieve the slab flag */ + if (type == &memblock.memory) + in_slab = &memblock_memory_in_slab; + else + in_slab = &memblock_reserved_in_slab; + + /* Try to find some space for it */ + if (use_slab) { + new_array = kmalloc(new_size, GFP_KERNEL); + addr = new_array ? __pa(new_array) : 0; + } else { + /* only exclude range when trying to double reserved.regions */ + if (type != &memblock.reserved) + new_area_start = new_area_size = 0; + + addr = memblock_find_in_range(new_area_start + new_area_size, + memblock.current_limit, + new_alloc_size, PAGE_SIZE); + if (!addr && new_area_size) + addr = memblock_find_in_range(0, + min(new_area_start, memblock.current_limit), + new_alloc_size, PAGE_SIZE); + + new_array = addr ? __va(addr) : NULL; + } + if (!addr) { + pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n", + type->name, type->max, type->max * 2); + return -1; + } + + new_end = addr + new_size - 1; + memblock_dbg("memblock: %s is doubled to %ld at [%pa-%pa]", + type->name, type->max * 2, &addr, &new_end); + + /* + * Found space, we now need to move the array over before we add the + * reserved region since it may be our reserved array itself that is + * full. + */ + memcpy(new_array, type->regions, old_size); + memset(new_array + type->max, 0, old_size); + old_array = type->regions; + type->regions = new_array; + type->max <<= 1; + + /* Free old array. We needn't free it if the array is the static one */ + if (*in_slab) + kfree(old_array); + else if (old_array != memblock_memory_init_regions && + old_array != memblock_reserved_init_regions) + memblock_free(__pa(old_array), old_alloc_size); + + /* + * Reserve the new array if that comes from the memblock. Otherwise, we + * needn't do it + */ + if (!use_slab) + BUG_ON(memblock_reserve(addr, new_alloc_size)); + + /* Update slab flag */ + *in_slab = use_slab; + + return 0; +} + +/** + * memblock_merge_regions - merge neighboring compatible regions + * @type: memblock type to scan + * + * Scan @type and merge neighboring compatible regions. + */ +static void __init_memblock memblock_merge_regions(struct memblock_type *type) +{ + int i = 0; + + /* cnt never goes below 1 */ + while (i < type->cnt - 1) { + struct memblock_region *this = &type->regions[i]; + struct memblock_region *next = &type->regions[i + 1]; + + if (this->base + this->size != next->base || + memblock_get_region_node(this) != + memblock_get_region_node(next) || + this->flags != next->flags) { + BUG_ON(this->base + this->size > next->base); + i++; + continue; + } + + this->size += next->size; + /* move forward from next + 1, index of which is i + 2 */ + memmove(next, next + 1, (type->cnt - (i + 2)) * sizeof(*next)); + type->cnt--; + } +} + +/** + * memblock_insert_region - insert new memblock region + * @type: memblock type to insert into + * @idx: index for the insertion point + * @base: base address of the new region + * @size: size of the new region + * @nid: node id of the new region + * @flags: flags of the new region + * + * Insert new memblock region [@base, @base + @size) into @type at @idx. + * @type must already have extra room to accommodate the new region. + */ +static void __init_memblock memblock_insert_region(struct memblock_type *type, + int idx, phys_addr_t base, + phys_addr_t size, + int nid, + enum memblock_flags flags) +{ + struct memblock_region *rgn = &type->regions[idx]; + + BUG_ON(type->cnt >= type->max); + memmove(rgn + 1, rgn, (type->cnt - idx) * sizeof(*rgn)); + rgn->base = base; + rgn->size = size; + rgn->flags = flags; + memblock_set_region_node(rgn, nid); + type->cnt++; + type->total_size += size; +} + +/** + * memblock_add_range - add new memblock region + * @type: memblock type to add new region into + * @base: base address of the new region + * @size: size of the new region + * @nid: nid of the new region + * @flags: flags of the new region + * + * Add new memblock region [@base, @base + @size) into @type. The new region + * is allowed to overlap with existing ones - overlaps don't affect already + * existing regions. @type is guaranteed to be minimal (all neighbouring + * compatible regions are merged) after the addition. + * + * Return: + * 0 on success, -errno on failure. + */ +static int __init_memblock memblock_add_range(struct memblock_type *type, + phys_addr_t base, phys_addr_t size, + int nid, enum memblock_flags flags) +{ + bool insert = false; + phys_addr_t obase = base; + phys_addr_t end = base + memblock_cap_size(base, &size); + int idx, nr_new; + struct memblock_region *rgn; + + if (!size) + return 0; + + /* special case for empty array */ + if (type->regions[0].size == 0) { + WARN_ON(type->cnt != 1 || type->total_size); + type->regions[0].base = base; + type->regions[0].size = size; + type->regions[0].flags = flags; + memblock_set_region_node(&type->regions[0], nid); + type->total_size = size; + return 0; + } +repeat: + /* + * The following is executed twice. Once with %false @insert and + * then with %true. The first counts the number of regions needed + * to accommodate the new area. The second actually inserts them. + */ + base = obase; + nr_new = 0; + + for_each_memblock_type(idx, type, rgn) { + phys_addr_t rbase = rgn->base; + phys_addr_t rend = rbase + rgn->size; + + if (rbase >= end) + break; + if (rend <= base) + continue; + /* + * @rgn overlaps. If it separates the lower part of new + * area, insert that portion. + */ + if (rbase > base) { +#ifdef CONFIG_NEED_MULTIPLE_NODES + WARN_ON(nid != memblock_get_region_node(rgn)); +#endif + WARN_ON(flags != rgn->flags); + nr_new++; + if (insert) + memblock_insert_region(type, idx++, base, + rbase - base, nid, + flags); + } + /* area below @rend is dealt with, forget about it */ + base = min(rend, end); + } + + /* insert the remaining portion */ + if (base < end) { + nr_new++; + if (insert) + memblock_insert_region(type, idx, base, end - base, + nid, flags); + } + + if (!nr_new) + return 0; + + /* + * If this was the first round, resize array and repeat for actual + * insertions; otherwise, merge and return. + */ + if (!insert) { + while (type->cnt + nr_new > type->max) + if (memblock_double_array(type, obase, size) < 0) + return -ENOMEM; + insert = true; + goto repeat; + } else { + memblock_merge_regions(type); + return 0; + } +} + +/** + * memblock_add_node - add new memblock region within a NUMA node + * @base: base address of the new region + * @size: size of the new region + * @nid: nid of the new region + * + * Add new memblock region [@base, @base + @size) to the "memory" + * type. See memblock_add_range() description for mode details + * + * Return: + * 0 on success, -errno on failure. + */ +int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size, + int nid) +{ + return memblock_add_range(&memblock.memory, base, size, nid, 0); +} + +/** + * memblock_add - add new memblock region + * @base: base address of the new region + * @size: size of the new region + * + * Add new memblock region [@base, @base + @size) to the "memory" + * type. See memblock_add_range() description for mode details + * + * Return: + * 0 on success, -errno on failure. + */ +int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size) +{ + phys_addr_t end = base + size - 1; + + memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, + &base, &end, (void *)_RET_IP_); + + return memblock_add_range(&memblock.memory, base, size, MAX_NUMNODES, 0); +} + +/** + * memblock_isolate_range - isolate given range into disjoint memblocks + * @type: memblock type to isolate range for + * @base: base of range to isolate + * @size: size of range to isolate + * @start_rgn: out parameter for the start of isolated region + * @end_rgn: out parameter for the end of isolated region + * + * Walk @type and ensure that regions don't cross the boundaries defined by + * [@base, @base + @size). Crossing regions are split at the boundaries, + * which may create at most two more regions. The index of the first + * region inside the range is returned in *@start_rgn and end in *@end_rgn. + * + * Return: + * 0 on success, -errno on failure. + */ +static int __init_memblock memblock_isolate_range(struct memblock_type *type, + phys_addr_t base, phys_addr_t size, + int *start_rgn, int *end_rgn) +{ + phys_addr_t end = base + memblock_cap_size(base, &size); + int idx; + struct memblock_region *rgn; + + *start_rgn = *end_rgn = 0; + + if (!size) + return 0; + + /* we'll create at most two more regions */ + while (type->cnt + 2 > type->max) + if (memblock_double_array(type, base, size) < 0) + return -ENOMEM; + + for_each_memblock_type(idx, type, rgn) { + phys_addr_t rbase = rgn->base; + phys_addr_t rend = rbase + rgn->size; + + if (rbase >= end) + break; + if (rend <= base) + continue; + + if (rbase < base) { + /* + * @rgn intersects from below. Split and continue + * to process the next region - the new top half. + */ + rgn->base = base; + rgn->size -= base - rbase; + type->total_size -= base - rbase; + memblock_insert_region(type, idx, rbase, base - rbase, + memblock_get_region_node(rgn), + rgn->flags); + } else if (rend > end) { + /* + * @rgn intersects from above. Split and redo the + * current region - the new bottom half. + */ + rgn->base = end; + rgn->size -= end - rbase; + type->total_size -= end - rbase; + memblock_insert_region(type, idx--, rbase, end - rbase, + memblock_get_region_node(rgn), + rgn->flags); + } else { + /* @rgn is fully contained, record it */ + if (!*end_rgn) + *start_rgn = idx; + *end_rgn = idx + 1; + } + } + + return 0; +} + +static int __init_memblock memblock_remove_range(struct memblock_type *type, + phys_addr_t base, phys_addr_t size) +{ + int start_rgn, end_rgn; + int i, ret; + + ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn); + if (ret) + return ret; + + for (i = end_rgn - 1; i >= start_rgn; i--) + memblock_remove_region(type, i); + return 0; +} + +int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size) +{ + phys_addr_t end = base + size - 1; + + memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, + &base, &end, (void *)_RET_IP_); + + return memblock_remove_range(&memblock.memory, base, size); +} + +/** + * memblock_free - free boot memory block + * @base: phys starting address of the boot memory block + * @size: size of the boot memory block in bytes + * + * Free boot memory block previously allocated by memblock_alloc_xx() API. + * The freeing memory will not be released to the buddy allocator. + */ +int __init_memblock memblock_free(phys_addr_t base, phys_addr_t size) +{ + phys_addr_t end = base + size - 1; + + memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, + &base, &end, (void *)_RET_IP_); + + kmemleak_free_part_phys(base, size); + return memblock_remove_range(&memblock.reserved, base, size); +} + +int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size) +{ + phys_addr_t end = base + size - 1; + + memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, + &base, &end, (void *)_RET_IP_); + + return memblock_add_range(&memblock.reserved, base, size, MAX_NUMNODES, 0); +} + +#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP +int __init_memblock memblock_physmem_add(phys_addr_t base, phys_addr_t size) +{ + phys_addr_t end = base + size - 1; + + memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, + &base, &end, (void *)_RET_IP_); + + return memblock_add_range(&physmem, base, size, MAX_NUMNODES, 0); +} +#endif + +/** + * memblock_setclr_flag - set or clear flag for a memory region + * @base: base address of the region + * @size: size of the region + * @set: set or clear the flag + * @flag: the flag to udpate + * + * This function isolates region [@base, @base + @size), and sets/clears flag + * + * Return: 0 on success, -errno on failure. + */ +static int __init_memblock memblock_setclr_flag(phys_addr_t base, + phys_addr_t size, int set, int flag) +{ + struct memblock_type *type = &memblock.memory; + int i, ret, start_rgn, end_rgn; + + ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn); + if (ret) + return ret; + + for (i = start_rgn; i < end_rgn; i++) { + struct memblock_region *r = &type->regions[i]; + + if (set) + r->flags |= flag; + else + r->flags &= ~flag; + } + + memblock_merge_regions(type); + return 0; +} + +/** + * memblock_mark_hotplug - Mark hotpluggable memory with flag MEMBLOCK_HOTPLUG. + * @base: the base phys addr of the region + * @size: the size of the region + * + * Return: 0 on success, -errno on failure. + */ +int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size) +{ + return memblock_setclr_flag(base, size, 1, MEMBLOCK_HOTPLUG); +} + +/** + * memblock_clear_hotplug - Clear flag MEMBLOCK_HOTPLUG for a specified region. + * @base: the base phys addr of the region + * @size: the size of the region + * + * Return: 0 on success, -errno on failure. + */ +int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size) +{ + return memblock_setclr_flag(base, size, 0, MEMBLOCK_HOTPLUG); +} + +/** + * memblock_mark_mirror - Mark mirrored memory with flag MEMBLOCK_MIRROR. + * @base: the base phys addr of the region + * @size: the size of the region + * + * Return: 0 on success, -errno on failure. + */ +int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size) +{ + system_has_some_mirror = true; + + return memblock_setclr_flag(base, size, 1, MEMBLOCK_MIRROR); +} + +/** + * memblock_mark_nomap - Mark a memory region with flag MEMBLOCK_NOMAP. + * @base: the base phys addr of the region + * @size: the size of the region + * + * Return: 0 on success, -errno on failure. + */ +int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size) +{ + return memblock_setclr_flag(base, size, 1, MEMBLOCK_NOMAP); +} + +/** + * memblock_clear_nomap - Clear flag MEMBLOCK_NOMAP for a specified region. + * @base: the base phys addr of the region + * @size: the size of the region + * + * Return: 0 on success, -errno on failure. + */ +int __init_memblock memblock_clear_nomap(phys_addr_t base, phys_addr_t size) +{ + return memblock_setclr_flag(base, size, 0, MEMBLOCK_NOMAP); +} + +static bool should_skip_region(struct memblock_type *type, + struct memblock_region *m, + int nid, int flags) +{ + int m_nid = memblock_get_region_node(m); + + /* we never skip regions when iterating memblock.reserved or physmem */ + if (type != memblock_memory) + return false; + + /* only memory regions are associated with nodes, check it */ + if (nid != NUMA_NO_NODE && nid != m_nid) + return true; + + /* skip hotpluggable memory regions if needed */ + if (movable_node_is_enabled() && memblock_is_hotpluggable(m) && + !(flags & MEMBLOCK_HOTPLUG)) + return true; + + /* if we want mirror memory skip non-mirror memory regions */ + if ((flags & MEMBLOCK_MIRROR) && !memblock_is_mirror(m)) + return true; + + /* skip nomap memory unless we were asked for it explicitly */ + if (!(flags & MEMBLOCK_NOMAP) && memblock_is_nomap(m)) + return true; + + return false; +} + +/** + * __next_mem_range - next function for for_each_free_mem_range() etc. + * @idx: pointer to u64 loop variable + * @nid: node selector, %NUMA_NO_NODE for all nodes + * @flags: pick from blocks based on memory attributes + * @type_a: pointer to memblock_type from where the range is taken + * @type_b: pointer to memblock_type which excludes memory from being taken + * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL + * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL + * @out_nid: ptr to int for nid of the range, can be %NULL + * + * Find the first area from *@idx which matches @nid, fill the out + * parameters, and update *@idx for the next iteration. The lower 32bit of + * *@idx contains index into type_a and the upper 32bit indexes the + * areas before each region in type_b. For example, if type_b regions + * look like the following, + * + * 0:[0-16), 1:[32-48), 2:[128-130) + * + * The upper 32bit indexes the following regions. + * + * 0:[0-0), 1:[16-32), 2:[48-128), 3:[130-MAX) + * + * As both region arrays are sorted, the function advances the two indices + * in lockstep and returns each intersection. + */ +void __next_mem_range(u64 *idx, int nid, enum memblock_flags flags, + struct memblock_type *type_a, + struct memblock_type *type_b, phys_addr_t *out_start, + phys_addr_t *out_end, int *out_nid) +{ + int idx_a = *idx & 0xffffffff; + int idx_b = *idx >> 32; + + if (WARN_ONCE(nid == MAX_NUMNODES, + "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n")) + nid = NUMA_NO_NODE; + + for (; idx_a < type_a->cnt; idx_a++) { + struct memblock_region *m = &type_a->regions[idx_a]; + + phys_addr_t m_start = m->base; + phys_addr_t m_end = m->base + m->size; + int m_nid = memblock_get_region_node(m); + + if (should_skip_region(type_a, m, nid, flags)) + continue; + + if (!type_b) { + if (out_start) + *out_start = m_start; + if (out_end) + *out_end = m_end; + if (out_nid) + *out_nid = m_nid; + idx_a++; + *idx = (u32)idx_a | (u64)idx_b << 32; + return; + } + + /* scan areas before each reservation */ + for (; idx_b < type_b->cnt + 1; idx_b++) { + struct memblock_region *r; + phys_addr_t r_start; + phys_addr_t r_end; + + r = &type_b->regions[idx_b]; + r_start = idx_b ? r[-1].base + r[-1].size : 0; + r_end = idx_b < type_b->cnt ? + r->base : PHYS_ADDR_MAX; + + /* + * if idx_b advanced past idx_a, + * break out to advance idx_a + */ + if (r_start >= m_end) + break; + /* if the two regions intersect, we're done */ + if (m_start < r_end) { + if (out_start) + *out_start = + max(m_start, r_start); + if (out_end) + *out_end = min(m_end, r_end); + if (out_nid) + *out_nid = m_nid; + /* + * The region which ends first is + * advanced for the next iteration. + */ + if (m_end <= r_end) + idx_a++; + else + idx_b++; + *idx = (u32)idx_a | (u64)idx_b << 32; + return; + } + } + } + + /* signal end of iteration */ + *idx = ULLONG_MAX; +} + +/** + * __next_mem_range_rev - generic next function for for_each_*_range_rev() + * + * @idx: pointer to u64 loop variable + * @nid: node selector, %NUMA_NO_NODE for all nodes + * @flags: pick from blocks based on memory attributes + * @type_a: pointer to memblock_type from where the range is taken + * @type_b: pointer to memblock_type which excludes memory from being taken + * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL + * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL + * @out_nid: ptr to int for nid of the range, can be %NULL + * + * Finds the next range from type_a which is not marked as unsuitable + * in type_b. + * + * Reverse of __next_mem_range(). + */ +void __init_memblock __next_mem_range_rev(u64 *idx, int nid, + enum memblock_flags flags, + struct memblock_type *type_a, + struct memblock_type *type_b, + phys_addr_t *out_start, + phys_addr_t *out_end, int *out_nid) +{ + int idx_a = *idx & 0xffffffff; + int idx_b = *idx >> 32; + + if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n")) + nid = NUMA_NO_NODE; + + if (*idx == (u64)ULLONG_MAX) { + idx_a = type_a->cnt - 1; + if (type_b != NULL) + idx_b = type_b->cnt; + else + idx_b = 0; + } + + for (; idx_a >= 0; idx_a--) { + struct memblock_region *m = &type_a->regions[idx_a]; + + phys_addr_t m_start = m->base; + phys_addr_t m_end = m->base + m->size; + int m_nid = memblock_get_region_node(m); + + if (should_skip_region(type_a, m, nid, flags)) + continue; + + if (!type_b) { + if (out_start) + *out_start = m_start; + if (out_end) + *out_end = m_end; + if (out_nid) + *out_nid = m_nid; + idx_a--; + *idx = (u32)idx_a | (u64)idx_b << 32; + return; + } + + /* scan areas before each reservation */ + for (; idx_b >= 0; idx_b--) { + struct memblock_region *r; + phys_addr_t r_start; + phys_addr_t r_end; + + r = &type_b->regions[idx_b]; + r_start = idx_b ? r[-1].base + r[-1].size : 0; + r_end = idx_b < type_b->cnt ? + r->base : PHYS_ADDR_MAX; + /* + * if idx_b advanced past idx_a, + * break out to advance idx_a + */ + + if (r_end <= m_start) + break; + /* if the two regions intersect, we're done */ + if (m_end > r_start) { + if (out_start) + *out_start = max(m_start, r_start); + if (out_end) + *out_end = min(m_end, r_end); + if (out_nid) + *out_nid = m_nid; + if (m_start >= r_start) + idx_a--; + else + idx_b--; + *idx = (u32)idx_a | (u64)idx_b << 32; + return; + } + } + } + /* signal end of iteration */ + *idx = ULLONG_MAX; +} + +/* + * Common iterator interface used to define for_each_mem_pfn_range(). + */ +void __init_memblock __next_mem_pfn_range(int *idx, int nid, + unsigned long *out_start_pfn, + unsigned long *out_end_pfn, int *out_nid) +{ + struct memblock_type *type = &memblock.memory; + struct memblock_region *r; + int r_nid; + + while (++*idx < type->cnt) { + r = &type->regions[*idx]; + r_nid = memblock_get_region_node(r); + + if (PFN_UP(r->base) >= PFN_DOWN(r->base + r->size)) + continue; + if (nid == MAX_NUMNODES || nid == r_nid) + break; + } + if (*idx >= type->cnt) { + *idx = -1; + return; + } + + if (out_start_pfn) + *out_start_pfn = PFN_UP(r->base); + if (out_end_pfn) + *out_end_pfn = PFN_DOWN(r->base + r->size); + if (out_nid) + *out_nid = r_nid; +} + +/** + * memblock_set_node - set node ID on memblock regions + * @base: base of area to set node ID for + * @size: size of area to set node ID for + * @type: memblock type to set node ID for + * @nid: node ID to set + * + * Set the nid of memblock @type regions in [@base, @base + @size) to @nid. + * Regions which cross the area boundaries are split as necessary. + * + * Return: + * 0 on success, -errno on failure. + */ +int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size, + struct memblock_type *type, int nid) +{ +#ifdef CONFIG_NEED_MULTIPLE_NODES + int start_rgn, end_rgn; + int i, ret; + + ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn); + if (ret) + return ret; + + for (i = start_rgn; i < end_rgn; i++) + memblock_set_region_node(&type->regions[i], nid); + + memblock_merge_regions(type); +#endif + return 0; +} + +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT +/** + * __next_mem_pfn_range_in_zone - iterator for for_each_*_range_in_zone() + * + * @idx: pointer to u64 loop variable + * @zone: zone in which all of the memory blocks reside + * @out_spfn: ptr to ulong for start pfn of the range, can be %NULL + * @out_epfn: ptr to ulong for end pfn of the range, can be %NULL + * + * This function is meant to be a zone/pfn specific wrapper for the + * for_each_mem_range type iterators. Specifically they are used in the + * deferred memory init routines and as such we were duplicating much of + * this logic throughout the code. So instead of having it in multiple + * locations it seemed like it would make more sense to centralize this to + * one new iterator that does everything they need. + */ +void __init_memblock +__next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, + unsigned long *out_spfn, unsigned long *out_epfn) +{ + int zone_nid = zone_to_nid(zone); + phys_addr_t spa, epa; + int nid; + + __next_mem_range(idx, zone_nid, MEMBLOCK_NONE, + &memblock.memory, &memblock.reserved, + &spa, &epa, &nid); + + while (*idx != U64_MAX) { + unsigned long epfn = PFN_DOWN(epa); + unsigned long spfn = PFN_UP(spa); + + /* + * Verify the end is at least past the start of the zone and + * that we have at least one PFN to initialize. + */ + if (zone->zone_start_pfn < epfn && spfn < epfn) { + /* if we went too far just stop searching */ + if (zone_end_pfn(zone) <= spfn) { + *idx = U64_MAX; + break; + } + + if (out_spfn) + *out_spfn = max(zone->zone_start_pfn, spfn); + if (out_epfn) + *out_epfn = min(zone_end_pfn(zone), epfn); + + return; + } + + __next_mem_range(idx, zone_nid, MEMBLOCK_NONE, + &memblock.memory, &memblock.reserved, + &spa, &epa, &nid); + } + + /* signal end of iteration */ + if (out_spfn) + *out_spfn = ULONG_MAX; + if (out_epfn) + *out_epfn = 0; +} + +#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ + +/** + * memblock_alloc_range_nid - allocate boot memory block + * @size: size of memory block to be allocated in bytes + * @align: alignment of the region and block's size + * @start: the lower bound of the memory region to allocate (phys address) + * @end: the upper bound of the memory region to allocate (phys address) + * @nid: nid of the free area to find, %NUMA_NO_NODE for any node + * @exact_nid: control the allocation fall back to other nodes + * + * The allocation is performed from memory region limited by + * memblock.current_limit if @end == %MEMBLOCK_ALLOC_ACCESSIBLE. + * + * If the specified node can not hold the requested memory and @exact_nid + * is false, the allocation falls back to any node in the system. + * + * For systems with memory mirroring, the allocation is attempted first + * from the regions with mirroring enabled and then retried from any + * memory region. + * + * In addition, function sets the min_count to 0 using kmemleak_alloc_phys for + * allocated boot memory block, so that it is never reported as leaks. + * + * Return: + * Physical address of allocated memory block on success, %0 on failure. + */ +phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size, + phys_addr_t align, phys_addr_t start, + phys_addr_t end, int nid, + bool exact_nid) +{ + enum memblock_flags flags = choose_memblock_flags(); + phys_addr_t found; + + if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n")) + nid = NUMA_NO_NODE; + + if (!align) { + /* Can't use WARNs this early in boot on powerpc */ + dump_stack(); + align = SMP_CACHE_BYTES; + } + +again: + found = memblock_find_in_range_node(size, align, start, end, nid, + flags); + if (found && !memblock_reserve(found, size)) + goto done; + + if (nid != NUMA_NO_NODE && !exact_nid) { + found = memblock_find_in_range_node(size, align, start, + end, NUMA_NO_NODE, + flags); + if (found && !memblock_reserve(found, size)) + goto done; + } + + if (flags & MEMBLOCK_MIRROR) { + flags &= ~MEMBLOCK_MIRROR; + pr_warn("Could not allocate %pap bytes of mirrored memory\n", + &size); + goto again; + } + + return 0; + +done: + /* Skip kmemleak for kasan_init() due to high volume. */ + if (end != MEMBLOCK_ALLOC_KASAN) + /* + * The min_count is set to 0 so that memblock allocated + * blocks are never reported as leaks. This is because many + * of these blocks are only referred via the physical + * address which is not looked up by kmemleak. + */ + kmemleak_alloc_phys(found, size, 0, 0); + + return found; +} + +/** + * memblock_phys_alloc_range - allocate a memory block inside specified range + * @size: size of memory block to be allocated in bytes + * @align: alignment of the region and block's size + * @start: the lower bound of the memory region to allocate (physical address) + * @end: the upper bound of the memory region to allocate (physical address) + * + * Allocate @size bytes in the between @start and @end. + * + * Return: physical address of the allocated memory block on success, + * %0 on failure. + */ +phys_addr_t __init memblock_phys_alloc_range(phys_addr_t size, + phys_addr_t align, + phys_addr_t start, + phys_addr_t end) +{ + return memblock_alloc_range_nid(size, align, start, end, NUMA_NO_NODE, + false); +} + +/** + * memblock_phys_alloc_try_nid - allocate a memory block from specified MUMA node + * @size: size of memory block to be allocated in bytes + * @align: alignment of the region and block's size + * @nid: nid of the free area to find, %NUMA_NO_NODE for any node + * + * Allocates memory block from the specified NUMA node. If the node + * has no available memory, attempts to allocated from any node in the + * system. + * + * Return: physical address of the allocated memory block on success, + * %0 on failure. + */ +phys_addr_t __init memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid) +{ + return memblock_alloc_range_nid(size, align, 0, + MEMBLOCK_ALLOC_ACCESSIBLE, nid, false); +} + +/** + * memblock_alloc_internal - allocate boot memory block + * @size: size of memory block to be allocated in bytes + * @align: alignment of the region and block's size + * @min_addr: the lower bound of the memory region to allocate (phys address) + * @max_addr: the upper bound of the memory region to allocate (phys address) + * @nid: nid of the free area to find, %NUMA_NO_NODE for any node + * @exact_nid: control the allocation fall back to other nodes + * + * Allocates memory block using memblock_alloc_range_nid() and + * converts the returned physical address to virtual. + * + * The @min_addr limit is dropped if it can not be satisfied and the allocation + * will fall back to memory below @min_addr. Other constraints, such + * as node and mirrored memory will be handled again in + * memblock_alloc_range_nid(). + * + * Return: + * Virtual address of allocated memory block on success, NULL on failure. + */ +static void * __init memblock_alloc_internal( + phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, phys_addr_t max_addr, + int nid, bool exact_nid) +{ + phys_addr_t alloc; + + /* + * Detect any accidental use of these APIs after slab is ready, as at + * this moment memblock may be deinitialized already and its + * internal data may be destroyed (after execution of memblock_free_all) + */ + if (WARN_ON_ONCE(slab_is_available())) + return kzalloc_node(size, GFP_NOWAIT, nid); + + if (max_addr > memblock.current_limit) + max_addr = memblock.current_limit; + + alloc = memblock_alloc_range_nid(size, align, min_addr, max_addr, nid, + exact_nid); + + /* retry allocation without lower limit */ + if (!alloc && min_addr) + alloc = memblock_alloc_range_nid(size, align, 0, max_addr, nid, + exact_nid); + + if (!alloc) + return NULL; + + return phys_to_virt(alloc); +} + +/** + * memblock_alloc_exact_nid_raw - allocate boot memory block on the exact node + * without zeroing memory + * @size: size of memory block to be allocated in bytes + * @align: alignment of the region and block's size + * @min_addr: the lower bound of the memory region from where the allocation + * is preferred (phys address) + * @max_addr: the upper bound of the memory region from where the allocation + * is preferred (phys address), or %MEMBLOCK_ALLOC_ACCESSIBLE to + * allocate only from memory limited by memblock.current_limit value + * @nid: nid of the free area to find, %NUMA_NO_NODE for any node + * + * Public function, provides additional debug information (including caller + * info), if enabled. Does not zero allocated memory. + * + * Return: + * Virtual address of allocated memory block on success, NULL on failure. + */ +void * __init memblock_alloc_exact_nid_raw( + phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, phys_addr_t max_addr, + int nid) +{ + void *ptr; + + memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pS\n", + __func__, (u64)size, (u64)align, nid, &min_addr, + &max_addr, (void *)_RET_IP_); + + ptr = memblock_alloc_internal(size, align, + min_addr, max_addr, nid, true); + if (ptr && size > 0) + page_init_poison(ptr, size); + + return ptr; +} + +/** + * memblock_alloc_try_nid_raw - allocate boot memory block without zeroing + * memory and without panicking + * @size: size of memory block to be allocated in bytes + * @align: alignment of the region and block's size + * @min_addr: the lower bound of the memory region from where the allocation + * is preferred (phys address) + * @max_addr: the upper bound of the memory region from where the allocation + * is preferred (phys address), or %MEMBLOCK_ALLOC_ACCESSIBLE to + * allocate only from memory limited by memblock.current_limit value + * @nid: nid of the free area to find, %NUMA_NO_NODE for any node + * + * Public function, provides additional debug information (including caller + * info), if enabled. Does not zero allocated memory, does not panic if request + * cannot be satisfied. + * + * Return: + * Virtual address of allocated memory block on success, NULL on failure. + */ +void * __init memblock_alloc_try_nid_raw( + phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, phys_addr_t max_addr, + int nid) +{ + void *ptr; + + memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pS\n", + __func__, (u64)size, (u64)align, nid, &min_addr, + &max_addr, (void *)_RET_IP_); + + ptr = memblock_alloc_internal(size, align, + min_addr, max_addr, nid, false); + if (ptr && size > 0) + page_init_poison(ptr, size); + + return ptr; +} + +/** + * memblock_alloc_try_nid - allocate boot memory block + * @size: size of memory block to be allocated in bytes + * @align: alignment of the region and block's size + * @min_addr: the lower bound of the memory region from where the allocation + * is preferred (phys address) + * @max_addr: the upper bound of the memory region from where the allocation + * is preferred (phys address), or %MEMBLOCK_ALLOC_ACCESSIBLE to + * allocate only from memory limited by memblock.current_limit value + * @nid: nid of the free area to find, %NUMA_NO_NODE for any node + * + * Public function, provides additional debug information (including caller + * info), if enabled. This function zeroes the allocated memory. + * + * Return: + * Virtual address of allocated memory block on success, NULL on failure. + */ +void * __init memblock_alloc_try_nid( + phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, phys_addr_t max_addr, + int nid) +{ + void *ptr; + + memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pS\n", + __func__, (u64)size, (u64)align, nid, &min_addr, + &max_addr, (void *)_RET_IP_); + ptr = memblock_alloc_internal(size, align, + min_addr, max_addr, nid, false); + if (ptr) + memset(ptr, 0, size); + + return ptr; +} + +/** + * __memblock_free_late - free pages directly to buddy allocator + * @base: phys starting address of the boot memory block + * @size: size of the boot memory block in bytes + * + * This is only useful when the memblock allocator has already been torn + * down, but we are still initializing the system. Pages are released directly + * to the buddy allocator. + */ +void __init __memblock_free_late(phys_addr_t base, phys_addr_t size) +{ + phys_addr_t cursor, end; + + end = base + size - 1; + memblock_dbg("%s: [%pa-%pa] %pS\n", + __func__, &base, &end, (void *)_RET_IP_); + kmemleak_free_part_phys(base, size); + cursor = PFN_UP(base); + end = PFN_DOWN(base + size); + + for (; cursor < end; cursor++) { + memblock_free_pages(pfn_to_page(cursor), cursor, 0); + totalram_pages_inc(); + } +} + +/* + * Remaining API functions + */ + +phys_addr_t __init_memblock memblock_phys_mem_size(void) +{ + return memblock.memory.total_size; +} + +phys_addr_t __init_memblock memblock_reserved_size(void) +{ + return memblock.reserved.total_size; +} + +/* lowest address */ +phys_addr_t __init_memblock memblock_start_of_DRAM(void) +{ + return memblock.memory.regions[0].base; +} + +phys_addr_t __init_memblock memblock_end_of_DRAM(void) +{ + int idx = memblock.memory.cnt - 1; + + return (memblock.memory.regions[idx].base + memblock.memory.regions[idx].size); +} + +static phys_addr_t __init_memblock __find_max_addr(phys_addr_t limit) +{ + phys_addr_t max_addr = PHYS_ADDR_MAX; + struct memblock_region *r; + + /* + * translate the memory @limit size into the max address within one of + * the memory memblock regions, if the @limit exceeds the total size + * of those regions, max_addr will keep original value PHYS_ADDR_MAX + */ + for_each_mem_region(r) { + if (limit <= r->size) { + max_addr = r->base + limit; + break; + } + limit -= r->size; + } + + return max_addr; +} + +void __init memblock_enforce_memory_limit(phys_addr_t limit) +{ + phys_addr_t max_addr; + + if (!limit) + return; + + max_addr = __find_max_addr(limit); + + /* @limit exceeds the total size of the memory, do nothing */ + if (max_addr == PHYS_ADDR_MAX) + return; + + /* truncate both memory and reserved regions */ + memblock_remove_range(&memblock.memory, max_addr, + PHYS_ADDR_MAX); + memblock_remove_range(&memblock.reserved, max_addr, + PHYS_ADDR_MAX); +} + +void __init memblock_cap_memory_range(phys_addr_t base, phys_addr_t size) +{ + int start_rgn, end_rgn; + int i, ret; + + if (!size) + return; + + ret = memblock_isolate_range(&memblock.memory, base, size, + &start_rgn, &end_rgn); + if (ret) + return; + + /* remove all the MAP regions */ + for (i = memblock.memory.cnt - 1; i >= end_rgn; i--) + if (!memblock_is_nomap(&memblock.memory.regions[i])) + memblock_remove_region(&memblock.memory, i); + + for (i = start_rgn - 1; i >= 0; i--) + if (!memblock_is_nomap(&memblock.memory.regions[i])) + memblock_remove_region(&memblock.memory, i); + + /* truncate the reserved regions */ + memblock_remove_range(&memblock.reserved, 0, base); + memblock_remove_range(&memblock.reserved, + base + size, PHYS_ADDR_MAX); +} + +void __init memblock_mem_limit_remove_map(phys_addr_t limit) +{ + phys_addr_t max_addr; + + if (!limit) + return; + + max_addr = __find_max_addr(limit); + + /* @limit exceeds the total size of the memory, do nothing */ + if (max_addr == PHYS_ADDR_MAX) + return; + + memblock_cap_memory_range(0, max_addr); +} + +static int __init_memblock memblock_search(struct memblock_type *type, phys_addr_t addr) +{ + unsigned int left = 0, right = type->cnt; + + do { + unsigned int mid = (right + left) / 2; + + if (addr < type->regions[mid].base) + right = mid; + else if (addr >= (type->regions[mid].base + + type->regions[mid].size)) + left = mid + 1; + else + return mid; + } while (left < right); + return -1; +} + +bool __init_memblock memblock_is_reserved(phys_addr_t addr) +{ + return memblock_search(&memblock.reserved, addr) != -1; +} + +bool __init_memblock memblock_is_memory(phys_addr_t addr) +{ + return memblock_search(&memblock.memory, addr) != -1; +} + +bool __init_memblock memblock_is_map_memory(phys_addr_t addr) +{ + int i = memblock_search(&memblock.memory, addr); + + if (i == -1) + return false; + return !memblock_is_nomap(&memblock.memory.regions[i]); +} + +int __init_memblock memblock_search_pfn_nid(unsigned long pfn, + unsigned long *start_pfn, unsigned long *end_pfn) +{ + struct memblock_type *type = &memblock.memory; + int mid = memblock_search(type, PFN_PHYS(pfn)); + + if (mid == -1) + return -1; + + *start_pfn = PFN_DOWN(type->regions[mid].base); + *end_pfn = PFN_DOWN(type->regions[mid].base + type->regions[mid].size); + + return memblock_get_region_node(&type->regions[mid]); +} + +/** + * memblock_is_region_memory - check if a region is a subset of memory + * @base: base of region to check + * @size: size of region to check + * + * Check if the region [@base, @base + @size) is a subset of a memory block. + * + * Return: + * 0 if false, non-zero if true + */ +bool __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size) +{ + int idx = memblock_search(&memblock.memory, base); + phys_addr_t end = base + memblock_cap_size(base, &size); + + if (idx == -1) + return false; + return (memblock.memory.regions[idx].base + + memblock.memory.regions[idx].size) >= end; +} + +/** + * memblock_is_region_reserved - check if a region intersects reserved memory + * @base: base of region to check + * @size: size of region to check + * + * Check if the region [@base, @base + @size) intersects a reserved + * memory block. + * + * Return: + * True if they intersect, false if not. + */ +bool __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size) +{ + return memblock_overlaps_region(&memblock.reserved, base, size); +} + +void __init_memblock memblock_trim_memory(phys_addr_t align) +{ + phys_addr_t start, end, orig_start, orig_end; + struct memblock_region *r; + + for_each_mem_region(r) { + orig_start = r->base; + orig_end = r->base + r->size; + start = round_up(orig_start, align); + end = round_down(orig_end, align); + + if (start == orig_start && end == orig_end) + continue; + + if (start < end) { + r->base = start; + r->size = end - start; + } else { + memblock_remove_region(&memblock.memory, + r - memblock.memory.regions); + r--; + } + } +} + +void __init_memblock memblock_set_current_limit(phys_addr_t limit) +{ + memblock.current_limit = limit; +} + +phys_addr_t __init_memblock memblock_get_current_limit(void) +{ + return memblock.current_limit; +} + +static void __init_memblock memblock_dump(struct memblock_type *type) +{ + phys_addr_t base, end, size; + enum memblock_flags flags; + int idx; + struct memblock_region *rgn; + + pr_info(" %s.cnt = 0x%lx\n", type->name, type->cnt); + + for_each_memblock_type(idx, type, rgn) { + char nid_buf[32] = ""; + + base = rgn->base; + size = rgn->size; + end = base + size - 1; + flags = rgn->flags; +#ifdef CONFIG_NEED_MULTIPLE_NODES + if (memblock_get_region_node(rgn) != MAX_NUMNODES) + snprintf(nid_buf, sizeof(nid_buf), " on node %d", + memblock_get_region_node(rgn)); +#endif + pr_info(" %s[%#x]\t[%pa-%pa], %pa bytes%s flags: %#x\n", + type->name, idx, &base, &end, &size, nid_buf, flags); + } +} + +static void __init_memblock __memblock_dump_all(void) +{ + pr_info("MEMBLOCK configuration:\n"); + pr_info(" memory size = %pa reserved size = %pa\n", + &memblock.memory.total_size, + &memblock.reserved.total_size); + + memblock_dump(&memblock.memory); + memblock_dump(&memblock.reserved); +#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP + memblock_dump(&physmem); +#endif +} + +void __init_memblock memblock_dump_all(void) +{ + if (memblock_debug) + __memblock_dump_all(); +} + +void __init memblock_allow_resize(void) +{ + memblock_can_resize = 1; +} + +static int __init early_memblock(char *p) +{ + if (p && strstr(p, "debug")) + memblock_debug = 1; + return 0; +} +early_param("memblock", early_memblock); + +static void __init __free_pages_memory(unsigned long start, unsigned long end) +{ + int order; + + while (start < end) { + order = min(MAX_ORDER - 1UL, __ffs(start)); + + while (start + (1UL << order) > end) + order--; + + memblock_free_pages(pfn_to_page(start), start, order); + + start += (1UL << order); + } +} + +static unsigned long __init __free_memory_core(phys_addr_t start, + phys_addr_t end) +{ + unsigned long start_pfn = PFN_UP(start); + unsigned long end_pfn = min_t(unsigned long, + PFN_DOWN(end), max_low_pfn); + + if (start_pfn >= end_pfn) + return 0; + + __free_pages_memory(start_pfn, end_pfn); + + return end_pfn - start_pfn; +} + +static unsigned long __init free_low_memory_core_early(void) +{ + unsigned long count = 0; + phys_addr_t start, end; + u64 i; + + memblock_clear_hotplug(0, -1); + + for_each_reserved_mem_range(i, &start, &end) + reserve_bootmem_region(start, end); + + /* + * We need to use NUMA_NO_NODE instead of NODE_DATA(0)->node_id + * because in some case like Node0 doesn't have RAM installed + * low ram will be on Node1 + */ + for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, + NULL) + count += __free_memory_core(start, end); + + return count; +} + +static int reset_managed_pages_done __initdata; + +void reset_node_managed_pages(pg_data_t *pgdat) +{ + struct zone *z; + + for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++) + atomic_long_set(&z->managed_pages, 0); +} + +void __init reset_all_zones_managed_pages(void) +{ + struct pglist_data *pgdat; + + if (reset_managed_pages_done) + return; + + for_each_online_pgdat(pgdat) + reset_node_managed_pages(pgdat); + + reset_managed_pages_done = 1; +} + +/** + * memblock_free_all - release free pages to the buddy allocator + * + * Return: the number of pages actually released. + */ +unsigned long __init memblock_free_all(void) +{ + unsigned long pages; + + reset_all_zones_managed_pages(); + + pages = free_low_memory_core_early(); + totalram_pages_add(pages); + + return pages; +} + +#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_ARCH_KEEP_MEMBLOCK) + +static int memblock_debug_show(struct seq_file *m, void *private) +{ + struct memblock_type *type = m->private; + struct memblock_region *reg; + int i; + phys_addr_t end; + + for (i = 0; i < type->cnt; i++) { + reg = &type->regions[i]; + end = reg->base + reg->size - 1; + + seq_printf(m, "%4d: ", i); + seq_printf(m, "%pa..%pa\n", ®->base, &end); + } + return 0; +} +DEFINE_SHOW_ATTRIBUTE(memblock_debug); + +static int __init memblock_init_debugfs(void) +{ + struct dentry *root = debugfs_create_dir("memblock", NULL); + + debugfs_create_file("memory", 0444, root, + &memblock.memory, &memblock_debug_fops); + debugfs_create_file("reserved", 0444, root, + &memblock.reserved, &memblock_debug_fops); +#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP + debugfs_create_file("physmem", 0444, root, &physmem, + &memblock_debug_fops); +#endif + + return 0; +} +__initcall(memblock_init_debugfs); + +#endif /* CONFIG_DEBUG_FS */ diff --git a/mm/memcontrol.c b/mm/memcontrol.c new file mode 100644 index 000000000..ddc8ed096 --- /dev/null +++ b/mm/memcontrol.c @@ -0,0 +1,7535 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* memcontrol.c - Memory Controller + * + * Copyright IBM Corporation, 2007 + * Author Balbir Singh + * + * Copyright 2007 OpenVZ SWsoft Inc + * Author: Pavel Emelianov + * + * Memory thresholds + * Copyright (C) 2009 Nokia Corporation + * Author: Kirill A. Shutemov + * + * Kernel Memory Controller + * Copyright (C) 2012 Parallels Inc. and Google Inc. + * Authors: Glauber Costa and Suleiman Souhlal + * + * Native page reclaim + * Charge lifetime sanitation + * Lockless page tracking & accounting + * Unified hierarchy configuration model + * Copyright (C) 2015 Red Hat, Inc., Johannes Weiner + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "internal.h" +#include +#include +#include "slab.h" + +#include + +#include + +struct cgroup_subsys memory_cgrp_subsys __read_mostly; +EXPORT_SYMBOL(memory_cgrp_subsys); + +struct mem_cgroup *root_mem_cgroup __read_mostly; + +/* Active memory cgroup to use from an interrupt context */ +DEFINE_PER_CPU(struct mem_cgroup *, int_active_memcg); + +/* Socket memory accounting disabled? */ +static bool cgroup_memory_nosocket; + +/* Kernel memory accounting disabled? */ +static bool cgroup_memory_nokmem; + +/* Whether the swap controller is active */ +#ifdef CONFIG_MEMCG_SWAP +bool cgroup_memory_noswap __read_mostly; +#else +#define cgroup_memory_noswap 1 +#endif + +#ifdef CONFIG_CGROUP_WRITEBACK +static DECLARE_WAIT_QUEUE_HEAD(memcg_cgwb_frn_waitq); +#endif + +/* Whether legacy memory+swap accounting is active */ +static bool do_memsw_account(void) +{ + return !cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_noswap; +} + +#define THRESHOLDS_EVENTS_TARGET 128 +#define SOFTLIMIT_EVENTS_TARGET 1024 + +/* + * Cgroups above their limits are maintained in a RB-Tree, independent of + * their hierarchy representation + */ + +struct mem_cgroup_tree_per_node { + struct rb_root rb_root; + struct rb_node *rb_rightmost; + spinlock_t lock; +}; + +struct mem_cgroup_tree { + struct mem_cgroup_tree_per_node *rb_tree_per_node[MAX_NUMNODES]; +}; + +static struct mem_cgroup_tree soft_limit_tree __read_mostly; + +/* for OOM */ +struct mem_cgroup_eventfd_list { + struct list_head list; + struct eventfd_ctx *eventfd; +}; + +/* + * cgroup_event represents events which userspace want to receive. + */ +struct mem_cgroup_event { + /* + * memcg which the event belongs to. + */ + struct mem_cgroup *memcg; + /* + * eventfd to signal userspace about the event. + */ + struct eventfd_ctx *eventfd; + /* + * Each of these stored in a list by the cgroup. + */ + struct list_head list; + /* + * register_event() callback will be used to add new userspace + * waiter for changes related to this event. Use eventfd_signal() + * on eventfd to send notification to userspace. + */ + int (*register_event)(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd, const char *args); + /* + * unregister_event() callback will be called when userspace closes + * the eventfd or on cgroup removing. This callback must be set, + * if you want provide notification functionality. + */ + void (*unregister_event)(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd); + /* + * All fields below needed to unregister event when + * userspace closes eventfd. + */ + poll_table pt; + wait_queue_head_t *wqh; + wait_queue_entry_t wait; + struct work_struct remove; +}; + +static void mem_cgroup_threshold(struct mem_cgroup *memcg); +static void mem_cgroup_oom_notify(struct mem_cgroup *memcg); + +/* Stuffs for move charges at task migration. */ +/* + * Types of charges to be moved. + */ +#define MOVE_ANON 0x1U +#define MOVE_FILE 0x2U +#define MOVE_MASK (MOVE_ANON | MOVE_FILE) + +/* "mc" and its members are protected by cgroup_mutex */ +static struct move_charge_struct { + spinlock_t lock; /* for from, to */ + struct mm_struct *mm; + struct mem_cgroup *from; + struct mem_cgroup *to; + unsigned long flags; + unsigned long precharge; + unsigned long moved_charge; + unsigned long moved_swap; + struct task_struct *moving_task; /* a task moving charges */ + wait_queue_head_t waitq; /* a waitq for other context */ +} mc = { + .lock = __SPIN_LOCK_UNLOCKED(mc.lock), + .waitq = __WAIT_QUEUE_HEAD_INITIALIZER(mc.waitq), +}; + +/* + * Maximum loops in mem_cgroup_hierarchical_reclaim(), used for soft + * limit reclaim to prevent infinite loops, if they ever occur. + */ +#define MEM_CGROUP_MAX_RECLAIM_LOOPS 100 +#define MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS 2 + +/* for encoding cft->private value on file */ +enum res_type { + _MEM, + _MEMSWAP, + _OOM_TYPE, + _KMEM, + _TCP, +}; + +#define MEMFILE_PRIVATE(x, val) ((x) << 16 | (val)) +#define MEMFILE_TYPE(val) ((val) >> 16 & 0xffff) +#define MEMFILE_ATTR(val) ((val) & 0xffff) +/* Used for OOM nofiier */ +#define OOM_CONTROL (0) + +/* + * Iteration constructs for visiting all cgroups (under a tree). If + * loops are exited prematurely (break), mem_cgroup_iter_break() must + * be used for reference counting. + */ +#define for_each_mem_cgroup_tree(iter, root) \ + for (iter = mem_cgroup_iter(root, NULL, NULL); \ + iter != NULL; \ + iter = mem_cgroup_iter(root, iter, NULL)) + +#define for_each_mem_cgroup(iter) \ + for (iter = mem_cgroup_iter(NULL, NULL, NULL); \ + iter != NULL; \ + iter = mem_cgroup_iter(NULL, iter, NULL)) + +static inline bool task_is_dying(void) +{ + return tsk_is_oom_victim(current) || fatal_signal_pending(current) || + (current->flags & PF_EXITING); +} + +/* Some nice accessors for the vmpressure. */ +struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg) +{ + if (!memcg) + memcg = root_mem_cgroup; + return &memcg->vmpressure; +} + +struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr) +{ + return &container_of(vmpr, struct mem_cgroup, vmpressure)->css; +} + +#ifdef CONFIG_MEMCG_KMEM +static DEFINE_SPINLOCK(objcg_lock); + +static void obj_cgroup_release(struct percpu_ref *ref) +{ + struct obj_cgroup *objcg = container_of(ref, struct obj_cgroup, refcnt); + struct mem_cgroup *memcg; + unsigned int nr_bytes; + unsigned int nr_pages; + unsigned long flags; + + /* + * At this point all allocated objects are freed, and + * objcg->nr_charged_bytes can't have an arbitrary byte value. + * However, it can be PAGE_SIZE or (x * PAGE_SIZE). + * + * The following sequence can lead to it: + * 1) CPU0: objcg == stock->cached_objcg + * 2) CPU1: we do a small allocation (e.g. 92 bytes), + * PAGE_SIZE bytes are charged + * 3) CPU1: a process from another memcg is allocating something, + * the stock if flushed, + * objcg->nr_charged_bytes = PAGE_SIZE - 92 + * 5) CPU0: we do release this object, + * 92 bytes are added to stock->nr_bytes + * 6) CPU0: stock is flushed, + * 92 bytes are added to objcg->nr_charged_bytes + * + * In the result, nr_charged_bytes == PAGE_SIZE. + * This page will be uncharged in obj_cgroup_release(). + */ + nr_bytes = atomic_read(&objcg->nr_charged_bytes); + WARN_ON_ONCE(nr_bytes & (PAGE_SIZE - 1)); + nr_pages = nr_bytes >> PAGE_SHIFT; + + spin_lock_irqsave(&objcg_lock, flags); + memcg = obj_cgroup_memcg(objcg); + if (nr_pages) + __memcg_kmem_uncharge(memcg, nr_pages); + list_del(&objcg->list); + mem_cgroup_put(memcg); + spin_unlock_irqrestore(&objcg_lock, flags); + + percpu_ref_exit(ref); + kfree_rcu(objcg, rcu); +} + +static struct obj_cgroup *obj_cgroup_alloc(void) +{ + struct obj_cgroup *objcg; + int ret; + + objcg = kzalloc(sizeof(struct obj_cgroup), GFP_KERNEL); + if (!objcg) + return NULL; + + ret = percpu_ref_init(&objcg->refcnt, obj_cgroup_release, 0, + GFP_KERNEL); + if (ret) { + kfree(objcg); + return NULL; + } + INIT_LIST_HEAD(&objcg->list); + return objcg; +} + +static void memcg_reparent_objcgs(struct mem_cgroup *memcg, + struct mem_cgroup *parent) +{ + struct obj_cgroup *objcg, *iter; + + objcg = rcu_replace_pointer(memcg->objcg, NULL, true); + + spin_lock_irq(&objcg_lock); + + /* Move active objcg to the parent's list */ + xchg(&objcg->memcg, parent); + css_get(&parent->css); + list_add(&objcg->list, &parent->objcg_list); + + /* Move already reparented objcgs to the parent's list */ + list_for_each_entry(iter, &memcg->objcg_list, list) { + css_get(&parent->css); + xchg(&iter->memcg, parent); + css_put(&memcg->css); + } + list_splice(&memcg->objcg_list, &parent->objcg_list); + + spin_unlock_irq(&objcg_lock); + + percpu_ref_kill(&objcg->refcnt); +} + +/* + * This will be used as a shrinker list's index. + * The main reason for not using cgroup id for this: + * this works better in sparse environments, where we have a lot of memcgs, + * but only a few kmem-limited. Or also, if we have, for instance, 200 + * memcgs, and none but the 200th is kmem-limited, we'd have to have a + * 200 entry array for that. + * + * The current size of the caches array is stored in memcg_nr_cache_ids. It + * will double each time we have to increase it. + */ +static DEFINE_IDA(memcg_cache_ida); +int memcg_nr_cache_ids; + +/* Protects memcg_nr_cache_ids */ +static DECLARE_RWSEM(memcg_cache_ids_sem); + +void memcg_get_cache_ids(void) +{ + down_read(&memcg_cache_ids_sem); +} + +void memcg_put_cache_ids(void) +{ + up_read(&memcg_cache_ids_sem); +} + +/* + * MIN_SIZE is different than 1, because we would like to avoid going through + * the alloc/free process all the time. In a small machine, 4 kmem-limited + * cgroups is a reasonable guess. In the future, it could be a parameter or + * tunable, but that is strictly not necessary. + * + * MAX_SIZE should be as large as the number of cgrp_ids. Ideally, we could get + * this constant directly from cgroup, but it is understandable that this is + * better kept as an internal representation in cgroup.c. In any case, the + * cgrp_id space is not getting any smaller, and we don't have to necessarily + * increase ours as well if it increases. + */ +#define MEMCG_CACHES_MIN_SIZE 4 +#define MEMCG_CACHES_MAX_SIZE MEM_CGROUP_ID_MAX + +/* + * A lot of the calls to the cache allocation functions are expected to be + * inlined by the compiler. Since the calls to memcg_slab_pre_alloc_hook() are + * conditional to this static branch, we'll have to allow modules that does + * kmem_cache_alloc and the such to see this symbol as well + */ +DEFINE_STATIC_KEY_FALSE(memcg_kmem_enabled_key); +EXPORT_SYMBOL(memcg_kmem_enabled_key); +#endif + +static int memcg_shrinker_map_size; +static DEFINE_MUTEX(memcg_shrinker_map_mutex); + +static void memcg_free_shrinker_map_rcu(struct rcu_head *head) +{ + kvfree(container_of(head, struct memcg_shrinker_map, rcu)); +} + +static int memcg_expand_one_shrinker_map(struct mem_cgroup *memcg, + int size, int old_size) +{ + struct memcg_shrinker_map *new, *old; + int nid; + + lockdep_assert_held(&memcg_shrinker_map_mutex); + + for_each_node(nid) { + old = rcu_dereference_protected( + mem_cgroup_nodeinfo(memcg, nid)->shrinker_map, true); + /* Not yet online memcg */ + if (!old) + return 0; + + new = kvmalloc_node(sizeof(*new) + size, GFP_KERNEL, nid); + if (!new) + return -ENOMEM; + + /* Set all old bits, clear all new bits */ + memset(new->map, (int)0xff, old_size); + memset((void *)new->map + old_size, 0, size - old_size); + + rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_map, new); + call_rcu(&old->rcu, memcg_free_shrinker_map_rcu); + } + + return 0; +} + +static void memcg_free_shrinker_maps(struct mem_cgroup *memcg) +{ + struct mem_cgroup_per_node *pn; + struct memcg_shrinker_map *map; + int nid; + + if (mem_cgroup_is_root(memcg)) + return; + + for_each_node(nid) { + pn = mem_cgroup_nodeinfo(memcg, nid); + map = rcu_dereference_protected(pn->shrinker_map, true); + if (map) + kvfree(map); + rcu_assign_pointer(pn->shrinker_map, NULL); + } +} + +static int memcg_alloc_shrinker_maps(struct mem_cgroup *memcg) +{ + struct memcg_shrinker_map *map; + int nid, size, ret = 0; + + if (mem_cgroup_is_root(memcg)) + return 0; + + mutex_lock(&memcg_shrinker_map_mutex); + size = memcg_shrinker_map_size; + for_each_node(nid) { + map = kvzalloc_node(sizeof(*map) + size, GFP_KERNEL, nid); + if (!map) { + memcg_free_shrinker_maps(memcg); + ret = -ENOMEM; + break; + } + rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_map, map); + } + mutex_unlock(&memcg_shrinker_map_mutex); + + return ret; +} + +int memcg_expand_shrinker_maps(int new_id) +{ + int size, old_size, ret = 0; + struct mem_cgroup *memcg; + + size = DIV_ROUND_UP(new_id + 1, BITS_PER_LONG) * sizeof(unsigned long); + old_size = memcg_shrinker_map_size; + if (size <= old_size) + return 0; + + mutex_lock(&memcg_shrinker_map_mutex); + if (!root_mem_cgroup) + goto unlock; + + for_each_mem_cgroup(memcg) { + if (mem_cgroup_is_root(memcg)) + continue; + ret = memcg_expand_one_shrinker_map(memcg, size, old_size); + if (ret) { + mem_cgroup_iter_break(NULL, memcg); + goto unlock; + } + } +unlock: + if (!ret) + memcg_shrinker_map_size = size; + mutex_unlock(&memcg_shrinker_map_mutex); + return ret; +} + +void memcg_set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) +{ + if (shrinker_id >= 0 && memcg && !mem_cgroup_is_root(memcg)) { + struct memcg_shrinker_map *map; + + rcu_read_lock(); + map = rcu_dereference(memcg->nodeinfo[nid]->shrinker_map); + /* Pairs with smp mb in shrink_slab() */ + smp_mb__before_atomic(); + set_bit(shrinker_id, map->map); + rcu_read_unlock(); + } +} + +/** + * mem_cgroup_css_from_page - css of the memcg associated with a page + * @page: page of interest + * + * If memcg is bound to the default hierarchy, css of the memcg associated + * with @page is returned. The returned css remains associated with @page + * until it is released. + * + * If memcg is bound to a traditional hierarchy, the css of root_mem_cgroup + * is returned. + */ +struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page) +{ + struct mem_cgroup *memcg; + + memcg = page->mem_cgroup; + + if (!memcg || !cgroup_subsys_on_dfl(memory_cgrp_subsys)) + memcg = root_mem_cgroup; + + return &memcg->css; +} + +/** + * page_cgroup_ino - return inode number of the memcg a page is charged to + * @page: the page + * + * Look up the closest online ancestor of the memory cgroup @page is charged to + * and return its inode number or 0 if @page is not charged to any cgroup. It + * is safe to call this function without holding a reference to @page. + * + * Note, this function is inherently racy, because there is nothing to prevent + * the cgroup inode from getting torn down and potentially reallocated a moment + * after page_cgroup_ino() returns, so it only should be used by callers that + * do not care (such as procfs interfaces). + */ +ino_t page_cgroup_ino(struct page *page) +{ + struct mem_cgroup *memcg; + unsigned long ino = 0; + + rcu_read_lock(); + memcg = page->mem_cgroup; + + /* + * The lowest bit set means that memcg isn't a valid + * memcg pointer, but a obj_cgroups pointer. + * In this case the page is shared and doesn't belong + * to any specific memory cgroup. + */ + if ((unsigned long) memcg & 0x1UL) + memcg = NULL; + + while (memcg && !(memcg->css.flags & CSS_ONLINE)) + memcg = parent_mem_cgroup(memcg); + if (memcg) + ino = cgroup_ino(memcg->css.cgroup); + rcu_read_unlock(); + return ino; +} + +static struct mem_cgroup_per_node * +mem_cgroup_page_nodeinfo(struct mem_cgroup *memcg, struct page *page) +{ + int nid = page_to_nid(page); + + return memcg->nodeinfo[nid]; +} + +static struct mem_cgroup_tree_per_node * +soft_limit_tree_node(int nid) +{ + return soft_limit_tree.rb_tree_per_node[nid]; +} + +static struct mem_cgroup_tree_per_node * +soft_limit_tree_from_page(struct page *page) +{ + int nid = page_to_nid(page); + + return soft_limit_tree.rb_tree_per_node[nid]; +} + +static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_node *mz, + struct mem_cgroup_tree_per_node *mctz, + unsigned long new_usage_in_excess) +{ + struct rb_node **p = &mctz->rb_root.rb_node; + struct rb_node *parent = NULL; + struct mem_cgroup_per_node *mz_node; + bool rightmost = true; + + if (mz->on_tree) + return; + + mz->usage_in_excess = new_usage_in_excess; + if (!mz->usage_in_excess) + return; + while (*p) { + parent = *p; + mz_node = rb_entry(parent, struct mem_cgroup_per_node, + tree_node); + if (mz->usage_in_excess < mz_node->usage_in_excess) { + p = &(*p)->rb_left; + rightmost = false; + } + + /* + * We can't avoid mem cgroups that are over their soft + * limit by the same amount + */ + else if (mz->usage_in_excess >= mz_node->usage_in_excess) + p = &(*p)->rb_right; + } + + if (rightmost) + mctz->rb_rightmost = &mz->tree_node; + + rb_link_node(&mz->tree_node, parent, p); + rb_insert_color(&mz->tree_node, &mctz->rb_root); + mz->on_tree = true; +} + +static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz, + struct mem_cgroup_tree_per_node *mctz) +{ + if (!mz->on_tree) + return; + + if (&mz->tree_node == mctz->rb_rightmost) + mctz->rb_rightmost = rb_prev(&mz->tree_node); + + rb_erase(&mz->tree_node, &mctz->rb_root); + mz->on_tree = false; +} + +static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz, + struct mem_cgroup_tree_per_node *mctz) +{ + unsigned long flags; + + spin_lock_irqsave(&mctz->lock, flags); + __mem_cgroup_remove_exceeded(mz, mctz); + spin_unlock_irqrestore(&mctz->lock, flags); +} + +static unsigned long soft_limit_excess(struct mem_cgroup *memcg) +{ + unsigned long nr_pages = page_counter_read(&memcg->memory); + unsigned long soft_limit = READ_ONCE(memcg->soft_limit); + unsigned long excess = 0; + + if (nr_pages > soft_limit) + excess = nr_pages - soft_limit; + + return excess; +} + +static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) +{ + unsigned long excess; + struct mem_cgroup_per_node *mz; + struct mem_cgroup_tree_per_node *mctz; + + mctz = soft_limit_tree_from_page(page); + if (!mctz) + return; + /* + * Necessary to update all ancestors when hierarchy is used. + * because their event counter is not touched. + */ + for (; memcg; memcg = parent_mem_cgroup(memcg)) { + mz = mem_cgroup_page_nodeinfo(memcg, page); + excess = soft_limit_excess(memcg); + /* + * We have to update the tree if mz is on RB-tree or + * mem is over its softlimit. + */ + if (excess || mz->on_tree) { + unsigned long flags; + + spin_lock_irqsave(&mctz->lock, flags); + /* if on-tree, remove it */ + if (mz->on_tree) + __mem_cgroup_remove_exceeded(mz, mctz); + /* + * Insert again. mz->usage_in_excess will be updated. + * If excess is 0, no tree ops. + */ + __mem_cgroup_insert_exceeded(mz, mctz, excess); + spin_unlock_irqrestore(&mctz->lock, flags); + } + } +} + +static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg) +{ + struct mem_cgroup_tree_per_node *mctz; + struct mem_cgroup_per_node *mz; + int nid; + + for_each_node(nid) { + mz = mem_cgroup_nodeinfo(memcg, nid); + mctz = soft_limit_tree_node(nid); + if (mctz) + mem_cgroup_remove_exceeded(mz, mctz); + } +} + +static struct mem_cgroup_per_node * +__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz) +{ + struct mem_cgroup_per_node *mz; + +retry: + mz = NULL; + if (!mctz->rb_rightmost) + goto done; /* Nothing to reclaim from */ + + mz = rb_entry(mctz->rb_rightmost, + struct mem_cgroup_per_node, tree_node); + /* + * Remove the node now but someone else can add it back, + * we will to add it back at the end of reclaim to its correct + * position in the tree. + */ + __mem_cgroup_remove_exceeded(mz, mctz); + if (!soft_limit_excess(mz->memcg) || + !css_tryget(&mz->memcg->css)) + goto retry; +done: + return mz; +} + +static struct mem_cgroup_per_node * +mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz) +{ + struct mem_cgroup_per_node *mz; + + spin_lock_irq(&mctz->lock); + mz = __mem_cgroup_largest_soft_limit_node(mctz); + spin_unlock_irq(&mctz->lock); + return mz; +} + +/** + * __mod_memcg_state - update cgroup memory statistics + * @memcg: the memory cgroup + * @idx: the stat item - can be enum memcg_stat_item or enum node_stat_item + * @val: delta to add to the counter, can be negative + */ +void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val) +{ + long x, threshold = MEMCG_CHARGE_BATCH; + + if (mem_cgroup_disabled()) + return; + + if (memcg_stat_item_in_bytes(idx)) + threshold <<= PAGE_SHIFT; + + x = val + __this_cpu_read(memcg->vmstats_percpu->stat[idx]); + if (unlikely(abs(x) > threshold)) { + struct mem_cgroup *mi; + + /* + * Batch local counters to keep them in sync with + * the hierarchical ones. + */ + __this_cpu_add(memcg->vmstats_local->stat[idx], x); + for (mi = memcg; mi; mi = parent_mem_cgroup(mi)) + atomic_long_add(x, &mi->vmstats[idx]); + x = 0; + } + __this_cpu_write(memcg->vmstats_percpu->stat[idx], x); +} + +static struct mem_cgroup_per_node * +parent_nodeinfo(struct mem_cgroup_per_node *pn, int nid) +{ + struct mem_cgroup *parent; + + parent = parent_mem_cgroup(pn->memcg); + if (!parent) + return NULL; + return mem_cgroup_nodeinfo(parent, nid); +} + +void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, + int val) +{ + struct mem_cgroup_per_node *pn; + struct mem_cgroup *memcg; + long x, threshold = MEMCG_CHARGE_BATCH; + + pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); + memcg = pn->memcg; + + /* Update memcg */ + __mod_memcg_state(memcg, idx, val); + + /* Update lruvec */ + __this_cpu_add(pn->lruvec_stat_local->count[idx], val); + + if (vmstat_item_in_bytes(idx)) + threshold <<= PAGE_SHIFT; + + x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]); + if (unlikely(abs(x) > threshold)) { + pg_data_t *pgdat = lruvec_pgdat(lruvec); + struct mem_cgroup_per_node *pi; + + for (pi = pn; pi; pi = parent_nodeinfo(pi, pgdat->node_id)) + atomic_long_add(x, &pi->lruvec_stat[idx]); + x = 0; + } + __this_cpu_write(pn->lruvec_stat_cpu->count[idx], x); +} + +/** + * __mod_lruvec_state - update lruvec memory statistics + * @lruvec: the lruvec + * @idx: the stat item + * @val: delta to add to the counter, can be negative + * + * The lruvec is the intersection of the NUMA node and a cgroup. This + * function updates the all three counters that are affected by a + * change of state at this level: per-node, per-cgroup, per-lruvec. + */ +void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, + int val) +{ + /* Update node */ + __mod_node_page_state(lruvec_pgdat(lruvec), idx, val); + + /* Update memcg and lruvec */ + if (!mem_cgroup_disabled()) + __mod_memcg_lruvec_state(lruvec, idx, val); +} + +void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val) +{ + pg_data_t *pgdat = page_pgdat(virt_to_page(p)); + struct mem_cgroup *memcg; + struct lruvec *lruvec; + + rcu_read_lock(); + memcg = mem_cgroup_from_obj(p); + + /* + * Untracked pages have no memcg, no lruvec. Update only the + * node. If we reparent the slab objects to the root memcg, + * when we free the slab object, we need to update the per-memcg + * vmstats to keep it correct for the root memcg. + */ + if (!memcg) { + __mod_node_page_state(pgdat, idx, val); + } else { + lruvec = mem_cgroup_lruvec(memcg, pgdat); + __mod_lruvec_state(lruvec, idx, val); + } + rcu_read_unlock(); +} + +void mod_memcg_obj_state(void *p, int idx, int val) +{ + struct mem_cgroup *memcg; + + rcu_read_lock(); + memcg = mem_cgroup_from_obj(p); + if (memcg) + mod_memcg_state(memcg, idx, val); + rcu_read_unlock(); +} + +/** + * __count_memcg_events - account VM events in a cgroup + * @memcg: the memory cgroup + * @idx: the event item + * @count: the number of events that occured + */ +void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, + unsigned long count) +{ + unsigned long x; + + if (mem_cgroup_disabled()) + return; + + x = count + __this_cpu_read(memcg->vmstats_percpu->events[idx]); + if (unlikely(x > MEMCG_CHARGE_BATCH)) { + struct mem_cgroup *mi; + + /* + * Batch local counters to keep them in sync with + * the hierarchical ones. + */ + __this_cpu_add(memcg->vmstats_local->events[idx], x); + for (mi = memcg; mi; mi = parent_mem_cgroup(mi)) + atomic_long_add(x, &mi->vmevents[idx]); + x = 0; + } + __this_cpu_write(memcg->vmstats_percpu->events[idx], x); +} + +static unsigned long memcg_events(struct mem_cgroup *memcg, int event) +{ + return atomic_long_read(&memcg->vmevents[event]); +} + +static unsigned long memcg_events_local(struct mem_cgroup *memcg, int event) +{ + long x = 0; + int cpu; + + for_each_possible_cpu(cpu) + x += per_cpu(memcg->vmstats_local->events[event], cpu); + return x; +} + +static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, + struct page *page, + int nr_pages) +{ + /* pagein of a big page is an event. So, ignore page size */ + if (nr_pages > 0) + __count_memcg_events(memcg, PGPGIN, 1); + else { + __count_memcg_events(memcg, PGPGOUT, 1); + nr_pages = -nr_pages; /* for event */ + } + + __this_cpu_add(memcg->vmstats_percpu->nr_page_events, nr_pages); +} + +static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg, + enum mem_cgroup_events_target target) +{ + unsigned long val, next; + + val = __this_cpu_read(memcg->vmstats_percpu->nr_page_events); + next = __this_cpu_read(memcg->vmstats_percpu->targets[target]); + /* from time_after() in jiffies.h */ + if ((long)(next - val) < 0) { + switch (target) { + case MEM_CGROUP_TARGET_THRESH: + next = val + THRESHOLDS_EVENTS_TARGET; + break; + case MEM_CGROUP_TARGET_SOFTLIMIT: + next = val + SOFTLIMIT_EVENTS_TARGET; + break; + default: + break; + } + __this_cpu_write(memcg->vmstats_percpu->targets[target], next); + return true; + } + return false; +} + +/* + * Check events in order. + * + */ +static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) +{ + /* threshold event is triggered in finer grain than soft limit */ + if (unlikely(mem_cgroup_event_ratelimit(memcg, + MEM_CGROUP_TARGET_THRESH))) { + bool do_softlimit; + + do_softlimit = mem_cgroup_event_ratelimit(memcg, + MEM_CGROUP_TARGET_SOFTLIMIT); + mem_cgroup_threshold(memcg); + if (unlikely(do_softlimit)) + mem_cgroup_update_tree(memcg, page); + } +} + +struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) +{ + /* + * mm_update_next_owner() may clear mm->owner to NULL + * if it races with swapoff, page migration, etc. + * So this can be called with p == NULL. + */ + if (unlikely(!p)) + return NULL; + + return mem_cgroup_from_css(task_css(p, memory_cgrp_id)); +} +EXPORT_SYMBOL(mem_cgroup_from_task); + +/** + * get_mem_cgroup_from_mm: Obtain a reference on given mm_struct's memcg. + * @mm: mm from which memcg should be extracted. It can be NULL. + * + * Obtain a reference on mm->memcg and returns it if successful. Otherwise + * root_mem_cgroup is returned. However if mem_cgroup is disabled, NULL is + * returned. + */ +struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) +{ + struct mem_cgroup *memcg; + + if (mem_cgroup_disabled()) + return NULL; + + rcu_read_lock(); + do { + /* + * Page cache insertions can happen withou an + * actual mm context, e.g. during disk probing + * on boot, loopback IO, acct() writes etc. + */ + if (unlikely(!mm)) + memcg = root_mem_cgroup; + else { + memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); + if (unlikely(!memcg)) + memcg = root_mem_cgroup; + } + } while (!css_tryget(&memcg->css)); + rcu_read_unlock(); + return memcg; +} +EXPORT_SYMBOL(get_mem_cgroup_from_mm); + +/** + * get_mem_cgroup_from_page: Obtain a reference on given page's memcg. + * @page: page from which memcg should be extracted. + * + * Obtain a reference on page->memcg and returns it if successful. Otherwise + * root_mem_cgroup is returned. + */ +struct mem_cgroup *get_mem_cgroup_from_page(struct page *page) +{ + struct mem_cgroup *memcg = page->mem_cgroup; + + if (mem_cgroup_disabled()) + return NULL; + + rcu_read_lock(); + /* Page should not get uncharged and freed memcg under us. */ + if (!memcg || WARN_ON_ONCE(!css_tryget(&memcg->css))) + memcg = root_mem_cgroup; + rcu_read_unlock(); + return memcg; +} +EXPORT_SYMBOL(get_mem_cgroup_from_page); + +static __always_inline struct mem_cgroup *active_memcg(void) +{ + if (in_interrupt()) + return this_cpu_read(int_active_memcg); + else + return current->active_memcg; +} + +static __always_inline struct mem_cgroup *get_active_memcg(void) +{ + struct mem_cgroup *memcg; + + rcu_read_lock(); + memcg = active_memcg(); + /* remote memcg must hold a ref. */ + if (memcg && WARN_ON_ONCE(!css_tryget(&memcg->css))) + memcg = root_mem_cgroup; + rcu_read_unlock(); + + return memcg; +} + +static __always_inline bool memcg_kmem_bypass(void) +{ + /* Allow remote memcg charging from any context. */ + if (unlikely(active_memcg())) + return false; + + /* Memcg to charge can't be determined. */ + if (in_interrupt() || !current->mm || (current->flags & PF_KTHREAD)) + return true; + + return false; +} + +/** + * If active memcg is set, do not fallback to current->mm->memcg. + */ +static __always_inline struct mem_cgroup *get_mem_cgroup_from_current(void) +{ + if (memcg_kmem_bypass()) + return NULL; + + if (unlikely(active_memcg())) + return get_active_memcg(); + + return get_mem_cgroup_from_mm(current->mm); +} + +/** + * mem_cgroup_iter - iterate over memory cgroup hierarchy + * @root: hierarchy root + * @prev: previously returned memcg, NULL on first invocation + * @reclaim: cookie for shared reclaim walks, NULL for full walks + * + * Returns references to children of the hierarchy below @root, or + * @root itself, or %NULL after a full round-trip. + * + * Caller must pass the return value in @prev on subsequent + * invocations for reference counting, or use mem_cgroup_iter_break() + * to cancel a hierarchy walk before the round-trip is complete. + * + * Reclaimers can specify a node in @reclaim to divide up the memcgs + * in the hierarchy among all concurrent reclaimers operating on the + * same node. + */ +struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, + struct mem_cgroup *prev, + struct mem_cgroup_reclaim_cookie *reclaim) +{ + struct mem_cgroup_reclaim_iter *iter; + struct cgroup_subsys_state *css = NULL; + struct mem_cgroup *memcg = NULL; + struct mem_cgroup *pos = NULL; + + if (mem_cgroup_disabled()) + return NULL; + + if (!root) + root = root_mem_cgroup; + + if (prev && !reclaim) + pos = prev; + + if (!root->use_hierarchy && root != root_mem_cgroup) { + if (prev) + goto out; + return root; + } + + rcu_read_lock(); + + if (reclaim) { + struct mem_cgroup_per_node *mz; + + mz = mem_cgroup_nodeinfo(root, reclaim->pgdat->node_id); + iter = &mz->iter; + + if (prev && reclaim->generation != iter->generation) + goto out_unlock; + + while (1) { + pos = READ_ONCE(iter->position); + if (!pos || css_tryget(&pos->css)) + break; + /* + * css reference reached zero, so iter->position will + * be cleared by ->css_released. However, we should not + * rely on this happening soon, because ->css_released + * is called from a work queue, and by busy-waiting we + * might block it. So we clear iter->position right + * away. + */ + (void)cmpxchg(&iter->position, pos, NULL); + } + } + + if (pos) + css = &pos->css; + + for (;;) { + css = css_next_descendant_pre(css, &root->css); + if (!css) { + /* + * Reclaimers share the hierarchy walk, and a + * new one might jump in right at the end of + * the hierarchy - make sure they see at least + * one group and restart from the beginning. + */ + if (!prev) + continue; + break; + } + + /* + * Verify the css and acquire a reference. The root + * is provided by the caller, so we know it's alive + * and kicking, and don't take an extra reference. + */ + memcg = mem_cgroup_from_css(css); + + if (css == &root->css) + break; + + if (css_tryget(css)) + break; + + memcg = NULL; + } + + if (reclaim) { + /* + * The position could have already been updated by a competing + * thread, so check that the value hasn't changed since we read + * it to avoid reclaiming from the same cgroup twice. + */ + (void)cmpxchg(&iter->position, pos, memcg); + + if (pos) + css_put(&pos->css); + + if (!memcg) + iter->generation++; + else if (!prev) + reclaim->generation = iter->generation; + } + +out_unlock: + rcu_read_unlock(); +out: + if (prev && prev != root) + css_put(&prev->css); + + return memcg; +} + +/** + * mem_cgroup_iter_break - abort a hierarchy walk prematurely + * @root: hierarchy root + * @prev: last visited hierarchy member as returned by mem_cgroup_iter() + */ +void mem_cgroup_iter_break(struct mem_cgroup *root, + struct mem_cgroup *prev) +{ + if (!root) + root = root_mem_cgroup; + if (prev && prev != root) + css_put(&prev->css); +} + +static void __invalidate_reclaim_iterators(struct mem_cgroup *from, + struct mem_cgroup *dead_memcg) +{ + struct mem_cgroup_reclaim_iter *iter; + struct mem_cgroup_per_node *mz; + int nid; + + for_each_node(nid) { + mz = mem_cgroup_nodeinfo(from, nid); + iter = &mz->iter; + cmpxchg(&iter->position, dead_memcg, NULL); + } +} + +static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg) +{ + struct mem_cgroup *memcg = dead_memcg; + struct mem_cgroup *last; + + do { + __invalidate_reclaim_iterators(memcg, dead_memcg); + last = memcg; + } while ((memcg = parent_mem_cgroup(memcg))); + + /* + * When cgruop1 non-hierarchy mode is used, + * parent_mem_cgroup() does not walk all the way up to the + * cgroup root (root_mem_cgroup). So we have to handle + * dead_memcg from cgroup root separately. + */ + if (last != root_mem_cgroup) + __invalidate_reclaim_iterators(root_mem_cgroup, + dead_memcg); +} + +/** + * mem_cgroup_scan_tasks - iterate over tasks of a memory cgroup hierarchy + * @memcg: hierarchy root + * @fn: function to call for each task + * @arg: argument passed to @fn + * + * This function iterates over tasks attached to @memcg or to any of its + * descendants and calls @fn for each task. If @fn returns a non-zero + * value, the function breaks the iteration loop and returns the value. + * Otherwise, it will iterate over all tasks and return 0. + * + * This function must not be called for the root memory cgroup. + */ +int mem_cgroup_scan_tasks(struct mem_cgroup *memcg, + int (*fn)(struct task_struct *, void *), void *arg) +{ + struct mem_cgroup *iter; + int ret = 0; + + BUG_ON(memcg == root_mem_cgroup); + + for_each_mem_cgroup_tree(iter, memcg) { + struct css_task_iter it; + struct task_struct *task; + + css_task_iter_start(&iter->css, CSS_TASK_ITER_PROCS, &it); + while (!ret && (task = css_task_iter_next(&it))) + ret = fn(task, arg); + css_task_iter_end(&it); + if (ret) { + mem_cgroup_iter_break(memcg, iter); + break; + } + } + return ret; +} + +/** + * mem_cgroup_page_lruvec - return lruvec for isolating/putting an LRU page + * @page: the page + * @pgdat: pgdat of the page + * + * This function relies on page->mem_cgroup being stable - see the + * access rules in commit_charge(). + */ +struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgdat) +{ + struct mem_cgroup_per_node *mz; + struct mem_cgroup *memcg; + struct lruvec *lruvec; + + if (mem_cgroup_disabled()) { + lruvec = &pgdat->__lruvec; + goto out; + } + + memcg = page->mem_cgroup; + /* + * Swapcache readahead pages are added to the LRU - and + * possibly migrated - before they are charged. + */ + if (!memcg) + memcg = root_mem_cgroup; + + mz = mem_cgroup_page_nodeinfo(memcg, page); + lruvec = &mz->lruvec; +out: + /* + * Since a node can be onlined after the mem_cgroup was created, + * we have to be prepared to initialize lruvec->zone here; + * and if offlined then reonlined, we need to reinitialize it. + */ + if (unlikely(lruvec->pgdat != pgdat)) + lruvec->pgdat = pgdat; + return lruvec; +} + +/** + * mem_cgroup_update_lru_size - account for adding or removing an lru page + * @lruvec: mem_cgroup per zone lru vector + * @lru: index of lru list the page is sitting on + * @zid: zone id of the accounted pages + * @nr_pages: positive when adding or negative when removing + * + * This function must be called under lru_lock, just before a page is added + * to or just after a page is removed from an lru list (that ordering being + * so as to allow it to check that lru_size 0 is consistent with list_empty). + */ +void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, + int zid, int nr_pages) +{ + struct mem_cgroup_per_node *mz; + unsigned long *lru_size; + long size; + + if (mem_cgroup_disabled()) + return; + + mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); + lru_size = &mz->lru_zone_size[zid][lru]; + + if (nr_pages < 0) + *lru_size += nr_pages; + + size = *lru_size; + if (WARN_ONCE(size < 0, + "%s(%p, %d, %d): lru_size %ld\n", + __func__, lruvec, lru, nr_pages, size)) { + VM_BUG_ON(1); + *lru_size = 0; + } + + if (nr_pages > 0) + *lru_size += nr_pages; +} + +/** + * mem_cgroup_margin - calculate chargeable space of a memory cgroup + * @memcg: the memory cgroup + * + * Returns the maximum amount of memory @mem can be charged with, in + * pages. + */ +static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg) +{ + unsigned long margin = 0; + unsigned long count; + unsigned long limit; + + count = page_counter_read(&memcg->memory); + limit = READ_ONCE(memcg->memory.max); + if (count < limit) + margin = limit - count; + + if (do_memsw_account()) { + count = page_counter_read(&memcg->memsw); + limit = READ_ONCE(memcg->memsw.max); + if (count < limit) + margin = min(margin, limit - count); + else + margin = 0; + } + + return margin; +} + +/* + * A routine for checking "mem" is under move_account() or not. + * + * Checking a cgroup is mc.from or mc.to or under hierarchy of + * moving cgroups. This is for waiting at high-memory pressure + * caused by "move". + */ +static bool mem_cgroup_under_move(struct mem_cgroup *memcg) +{ + struct mem_cgroup *from; + struct mem_cgroup *to; + bool ret = false; + /* + * Unlike task_move routines, we access mc.to, mc.from not under + * mutual exclusion by cgroup_mutex. Here, we take spinlock instead. + */ + spin_lock(&mc.lock); + from = mc.from; + to = mc.to; + if (!from) + goto unlock; + + ret = mem_cgroup_is_descendant(from, memcg) || + mem_cgroup_is_descendant(to, memcg); +unlock: + spin_unlock(&mc.lock); + return ret; +} + +static bool mem_cgroup_wait_acct_move(struct mem_cgroup *memcg) +{ + if (mc.moving_task && current != mc.moving_task) { + if (mem_cgroup_under_move(memcg)) { + DEFINE_WAIT(wait); + prepare_to_wait(&mc.waitq, &wait, TASK_INTERRUPTIBLE); + /* moving charge context might have finished. */ + if (mc.moving_task) + schedule(); + finish_wait(&mc.waitq, &wait); + return true; + } + } + return false; +} + +struct memory_stat { + const char *name; + unsigned int ratio; + unsigned int idx; +}; + +static struct memory_stat memory_stats[] = { + { "anon", PAGE_SIZE, NR_ANON_MAPPED }, + { "file", PAGE_SIZE, NR_FILE_PAGES }, + { "kernel_stack", 1024, NR_KERNEL_STACK_KB }, + { "percpu", 1, MEMCG_PERCPU_B }, + { "sock", PAGE_SIZE, MEMCG_SOCK }, + { "shmem", PAGE_SIZE, NR_SHMEM }, + { "file_mapped", PAGE_SIZE, NR_FILE_MAPPED }, + { "file_dirty", PAGE_SIZE, NR_FILE_DIRTY }, + { "file_writeback", PAGE_SIZE, NR_WRITEBACK }, +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + /* + * The ratio will be initialized in memory_stats_init(). Because + * on some architectures, the macro of HPAGE_PMD_SIZE is not + * constant(e.g. powerpc). + */ + { "anon_thp", 0, NR_ANON_THPS }, +#endif + { "inactive_anon", PAGE_SIZE, NR_INACTIVE_ANON }, + { "active_anon", PAGE_SIZE, NR_ACTIVE_ANON }, + { "inactive_file", PAGE_SIZE, NR_INACTIVE_FILE }, + { "active_file", PAGE_SIZE, NR_ACTIVE_FILE }, + { "unevictable", PAGE_SIZE, NR_UNEVICTABLE }, + + /* + * Note: The slab_reclaimable and slab_unreclaimable must be + * together and slab_reclaimable must be in front. + */ + { "slab_reclaimable", 1, NR_SLAB_RECLAIMABLE_B }, + { "slab_unreclaimable", 1, NR_SLAB_UNRECLAIMABLE_B }, + + /* The memory events */ + { "workingset_refault_anon", 1, WORKINGSET_REFAULT_ANON }, + { "workingset_refault_file", 1, WORKINGSET_REFAULT_FILE }, + { "workingset_activate_anon", 1, WORKINGSET_ACTIVATE_ANON }, + { "workingset_activate_file", 1, WORKINGSET_ACTIVATE_FILE }, + { "workingset_restore_anon", 1, WORKINGSET_RESTORE_ANON }, + { "workingset_restore_file", 1, WORKINGSET_RESTORE_FILE }, + { "workingset_nodereclaim", 1, WORKINGSET_NODERECLAIM }, +}; + +static int __init memory_stats_init(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(memory_stats); i++) { +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (memory_stats[i].idx == NR_ANON_THPS) + memory_stats[i].ratio = HPAGE_PMD_SIZE; +#endif + VM_BUG_ON(!memory_stats[i].ratio); + VM_BUG_ON(memory_stats[i].idx >= MEMCG_NR_STAT); + } + + return 0; +} +pure_initcall(memory_stats_init); + +static char *memory_stat_format(struct mem_cgroup *memcg) +{ + struct seq_buf s; + int i; + + seq_buf_init(&s, kmalloc(PAGE_SIZE, GFP_KERNEL), PAGE_SIZE); + if (!s.buffer) + return NULL; + + /* + * Provide statistics on the state of the memory subsystem as + * well as cumulative event counters that show past behavior. + * + * This list is ordered following a combination of these gradients: + * 1) generic big picture -> specifics and details + * 2) reflecting userspace activity -> reflecting kernel heuristics + * + * Current memory state: + */ + + for (i = 0; i < ARRAY_SIZE(memory_stats); i++) { + u64 size; + + size = memcg_page_state(memcg, memory_stats[i].idx); + size *= memory_stats[i].ratio; + seq_buf_printf(&s, "%s %llu\n", memory_stats[i].name, size); + + if (unlikely(memory_stats[i].idx == NR_SLAB_UNRECLAIMABLE_B)) { + size = memcg_page_state(memcg, NR_SLAB_RECLAIMABLE_B) + + memcg_page_state(memcg, NR_SLAB_UNRECLAIMABLE_B); + seq_buf_printf(&s, "slab %llu\n", size); + } + } + + /* Accumulated memory events */ + + seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGFAULT), + memcg_events(memcg, PGFAULT)); + seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGMAJFAULT), + memcg_events(memcg, PGMAJFAULT)); + seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGREFILL), + memcg_events(memcg, PGREFILL)); + seq_buf_printf(&s, "pgscan %lu\n", + memcg_events(memcg, PGSCAN_KSWAPD) + + memcg_events(memcg, PGSCAN_DIRECT)); + seq_buf_printf(&s, "pgsteal %lu\n", + memcg_events(memcg, PGSTEAL_KSWAPD) + + memcg_events(memcg, PGSTEAL_DIRECT)); + seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGACTIVATE), + memcg_events(memcg, PGACTIVATE)); + seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGDEACTIVATE), + memcg_events(memcg, PGDEACTIVATE)); + seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGLAZYFREE), + memcg_events(memcg, PGLAZYFREE)); + seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGLAZYFREED), + memcg_events(memcg, PGLAZYFREED)); + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + seq_buf_printf(&s, "%s %lu\n", vm_event_name(THP_FAULT_ALLOC), + memcg_events(memcg, THP_FAULT_ALLOC)); + seq_buf_printf(&s, "%s %lu\n", vm_event_name(THP_COLLAPSE_ALLOC), + memcg_events(memcg, THP_COLLAPSE_ALLOC)); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + + /* The above should easily fit into one page */ + WARN_ON_ONCE(seq_buf_has_overflowed(&s)); + + return s.buffer; +} + +#define K(x) ((x) << (PAGE_SHIFT-10)) +/** + * mem_cgroup_print_oom_context: Print OOM information relevant to + * memory controller. + * @memcg: The memory cgroup that went over limit + * @p: Task that is going to be killed + * + * NOTE: @memcg and @p's mem_cgroup can be different when hierarchy is + * enabled + */ +void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p) +{ + rcu_read_lock(); + + if (memcg) { + pr_cont(",oom_memcg="); + pr_cont_cgroup_path(memcg->css.cgroup); + } else + pr_cont(",global_oom"); + if (p) { + pr_cont(",task_memcg="); + pr_cont_cgroup_path(task_cgroup(p, memory_cgrp_id)); + } + rcu_read_unlock(); +} + +/** + * mem_cgroup_print_oom_meminfo: Print OOM memory information relevant to + * memory controller. + * @memcg: The memory cgroup that went over limit + */ +void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg) +{ + char *buf; + + pr_info("memory: usage %llukB, limit %llukB, failcnt %lu\n", + K((u64)page_counter_read(&memcg->memory)), + K((u64)READ_ONCE(memcg->memory.max)), memcg->memory.failcnt); + if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) + pr_info("swap: usage %llukB, limit %llukB, failcnt %lu\n", + K((u64)page_counter_read(&memcg->swap)), + K((u64)READ_ONCE(memcg->swap.max)), memcg->swap.failcnt); + else { + pr_info("memory+swap: usage %llukB, limit %llukB, failcnt %lu\n", + K((u64)page_counter_read(&memcg->memsw)), + K((u64)memcg->memsw.max), memcg->memsw.failcnt); + pr_info("kmem: usage %llukB, limit %llukB, failcnt %lu\n", + K((u64)page_counter_read(&memcg->kmem)), + K((u64)memcg->kmem.max), memcg->kmem.failcnt); + } + + pr_info("Memory cgroup stats for "); + pr_cont_cgroup_path(memcg->css.cgroup); + pr_cont(":"); + buf = memory_stat_format(memcg); + if (!buf) + return; + pr_info("%s", buf); + kfree(buf); +} + +/* + * Return the memory (and swap, if configured) limit for a memcg. + */ +unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg) +{ + unsigned long max = READ_ONCE(memcg->memory.max); + + if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) { + if (mem_cgroup_swappiness(memcg)) + max += min(READ_ONCE(memcg->swap.max), + (unsigned long)total_swap_pages); + } else { /* v1 */ + if (mem_cgroup_swappiness(memcg)) { + /* Calculate swap excess capacity from memsw limit */ + unsigned long swap = READ_ONCE(memcg->memsw.max) - max; + + max += min(swap, (unsigned long)total_swap_pages); + } + } + return max; +} + +unsigned long mem_cgroup_size(struct mem_cgroup *memcg) +{ + return page_counter_read(&memcg->memory); +} + +static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, + int order) +{ + struct oom_control oc = { + .zonelist = NULL, + .nodemask = NULL, + .memcg = memcg, + .gfp_mask = gfp_mask, + .order = order, + }; + bool ret = true; + + if (mutex_lock_killable(&oom_lock)) + return true; + + if (mem_cgroup_margin(memcg) >= (1 << order)) + goto unlock; + + /* + * A few threads which were not waiting at mutex_lock_killable() can + * fail to bail out. Therefore, check again after holding oom_lock. + */ + ret = task_is_dying() || out_of_memory(&oc); + +unlock: + mutex_unlock(&oom_lock); + return ret; +} + +static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg, + pg_data_t *pgdat, + gfp_t gfp_mask, + unsigned long *total_scanned) +{ + struct mem_cgroup *victim = NULL; + int total = 0; + int loop = 0; + unsigned long excess; + unsigned long nr_scanned; + struct mem_cgroup_reclaim_cookie reclaim = { + .pgdat = pgdat, + }; + + excess = soft_limit_excess(root_memcg); + + while (1) { + victim = mem_cgroup_iter(root_memcg, victim, &reclaim); + if (!victim) { + loop++; + if (loop >= 2) { + /* + * If we have not been able to reclaim + * anything, it might because there are + * no reclaimable pages under this hierarchy + */ + if (!total) + break; + /* + * We want to do more targeted reclaim. + * excess >> 2 is not to excessive so as to + * reclaim too much, nor too less that we keep + * coming back to reclaim from this cgroup + */ + if (total >= (excess >> 2) || + (loop > MEM_CGROUP_MAX_RECLAIM_LOOPS)) + break; + } + continue; + } + total += mem_cgroup_shrink_node(victim, gfp_mask, false, + pgdat, &nr_scanned); + *total_scanned += nr_scanned; + if (!soft_limit_excess(root_memcg)) + break; + } + mem_cgroup_iter_break(root_memcg, victim); + return total; +} + +#ifdef CONFIG_LOCKDEP +static struct lockdep_map memcg_oom_lock_dep_map = { + .name = "memcg_oom_lock", +}; +#endif + +static DEFINE_SPINLOCK(memcg_oom_lock); + +/* + * Check OOM-Killer is already running under our hierarchy. + * If someone is running, return false. + */ +static bool mem_cgroup_oom_trylock(struct mem_cgroup *memcg) +{ + struct mem_cgroup *iter, *failed = NULL; + + spin_lock(&memcg_oom_lock); + + for_each_mem_cgroup_tree(iter, memcg) { + if (iter->oom_lock) { + /* + * this subtree of our hierarchy is already locked + * so we cannot give a lock. + */ + failed = iter; + mem_cgroup_iter_break(memcg, iter); + break; + } else + iter->oom_lock = true; + } + + if (failed) { + /* + * OK, we failed to lock the whole subtree so we have + * to clean up what we set up to the failing subtree + */ + for_each_mem_cgroup_tree(iter, memcg) { + if (iter == failed) { + mem_cgroup_iter_break(memcg, iter); + break; + } + iter->oom_lock = false; + } + } else + mutex_acquire(&memcg_oom_lock_dep_map, 0, 1, _RET_IP_); + + spin_unlock(&memcg_oom_lock); + + return !failed; +} + +static void mem_cgroup_oom_unlock(struct mem_cgroup *memcg) +{ + struct mem_cgroup *iter; + + spin_lock(&memcg_oom_lock); + mutex_release(&memcg_oom_lock_dep_map, _RET_IP_); + for_each_mem_cgroup_tree(iter, memcg) + iter->oom_lock = false; + spin_unlock(&memcg_oom_lock); +} + +static void mem_cgroup_mark_under_oom(struct mem_cgroup *memcg) +{ + struct mem_cgroup *iter; + + spin_lock(&memcg_oom_lock); + for_each_mem_cgroup_tree(iter, memcg) + iter->under_oom++; + spin_unlock(&memcg_oom_lock); +} + +static void mem_cgroup_unmark_under_oom(struct mem_cgroup *memcg) +{ + struct mem_cgroup *iter; + + /* + * Be careful about under_oom underflows becase a child memcg + * could have been added after mem_cgroup_mark_under_oom. + */ + spin_lock(&memcg_oom_lock); + for_each_mem_cgroup_tree(iter, memcg) + if (iter->under_oom > 0) + iter->under_oom--; + spin_unlock(&memcg_oom_lock); +} + +static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq); + +struct oom_wait_info { + struct mem_cgroup *memcg; + wait_queue_entry_t wait; +}; + +static int memcg_oom_wake_function(wait_queue_entry_t *wait, + unsigned mode, int sync, void *arg) +{ + struct mem_cgroup *wake_memcg = (struct mem_cgroup *)arg; + struct mem_cgroup *oom_wait_memcg; + struct oom_wait_info *oom_wait_info; + + oom_wait_info = container_of(wait, struct oom_wait_info, wait); + oom_wait_memcg = oom_wait_info->memcg; + + if (!mem_cgroup_is_descendant(wake_memcg, oom_wait_memcg) && + !mem_cgroup_is_descendant(oom_wait_memcg, wake_memcg)) + return 0; + return autoremove_wake_function(wait, mode, sync, arg); +} + +static void memcg_oom_recover(struct mem_cgroup *memcg) +{ + /* + * For the following lockless ->under_oom test, the only required + * guarantee is that it must see the state asserted by an OOM when + * this function is called as a result of userland actions + * triggered by the notification of the OOM. This is trivially + * achieved by invoking mem_cgroup_mark_under_oom() before + * triggering notification. + */ + if (memcg && memcg->under_oom) + __wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, memcg); +} + +enum oom_status { + OOM_SUCCESS, + OOM_FAILED, + OOM_ASYNC, + OOM_SKIPPED +}; + +static enum oom_status mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order) +{ + enum oom_status ret; + bool locked; + + if (order > PAGE_ALLOC_COSTLY_ORDER) + return OOM_SKIPPED; + + memcg_memory_event(memcg, MEMCG_OOM); + + /* + * We are in the middle of the charge context here, so we + * don't want to block when potentially sitting on a callstack + * that holds all kinds of filesystem and mm locks. + * + * cgroup1 allows disabling the OOM killer and waiting for outside + * handling until the charge can succeed; remember the context and put + * the task to sleep at the end of the page fault when all locks are + * released. + * + * On the other hand, in-kernel OOM killer allows for an async victim + * memory reclaim (oom_reaper) and that means that we are not solely + * relying on the oom victim to make a forward progress and we can + * invoke the oom killer here. + * + * Please note that mem_cgroup_out_of_memory might fail to find a + * victim and then we have to bail out from the charge path. + */ + if (memcg->oom_kill_disable) { + if (!current->in_user_fault) + return OOM_SKIPPED; + css_get(&memcg->css); + current->memcg_in_oom = memcg; + current->memcg_oom_gfp_mask = mask; + current->memcg_oom_order = order; + + return OOM_ASYNC; + } + + mem_cgroup_mark_under_oom(memcg); + + locked = mem_cgroup_oom_trylock(memcg); + + if (locked) + mem_cgroup_oom_notify(memcg); + + mem_cgroup_unmark_under_oom(memcg); + if (mem_cgroup_out_of_memory(memcg, mask, order)) + ret = OOM_SUCCESS; + else + ret = OOM_FAILED; + + if (locked) + mem_cgroup_oom_unlock(memcg); + + return ret; +} + +/** + * mem_cgroup_oom_synchronize - complete memcg OOM handling + * @handle: actually kill/wait or just clean up the OOM state + * + * This has to be called at the end of a page fault if the memcg OOM + * handler was enabled. + * + * Memcg supports userspace OOM handling where failed allocations must + * sleep on a waitqueue until the userspace task resolves the + * situation. Sleeping directly in the charge context with all kinds + * of locks held is not a good idea, instead we remember an OOM state + * in the task and mem_cgroup_oom_synchronize() has to be called at + * the end of the page fault to complete the OOM handling. + * + * Returns %true if an ongoing memcg OOM situation was detected and + * completed, %false otherwise. + */ +bool mem_cgroup_oom_synchronize(bool handle) +{ + struct mem_cgroup *memcg = current->memcg_in_oom; + struct oom_wait_info owait; + bool locked; + + /* OOM is global, do not handle */ + if (!memcg) + return false; + + if (!handle) + goto cleanup; + + owait.memcg = memcg; + owait.wait.flags = 0; + owait.wait.func = memcg_oom_wake_function; + owait.wait.private = current; + INIT_LIST_HEAD(&owait.wait.entry); + + prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE); + mem_cgroup_mark_under_oom(memcg); + + locked = mem_cgroup_oom_trylock(memcg); + + if (locked) + mem_cgroup_oom_notify(memcg); + + if (locked && !memcg->oom_kill_disable) { + mem_cgroup_unmark_under_oom(memcg); + finish_wait(&memcg_oom_waitq, &owait.wait); + mem_cgroup_out_of_memory(memcg, current->memcg_oom_gfp_mask, + current->memcg_oom_order); + } else { + schedule(); + mem_cgroup_unmark_under_oom(memcg); + finish_wait(&memcg_oom_waitq, &owait.wait); + } + + if (locked) { + mem_cgroup_oom_unlock(memcg); + /* + * There is no guarantee that an OOM-lock contender + * sees the wakeups triggered by the OOM kill + * uncharges. Wake any sleepers explicitely. + */ + memcg_oom_recover(memcg); + } +cleanup: + current->memcg_in_oom = NULL; + css_put(&memcg->css); + return true; +} + +/** + * mem_cgroup_get_oom_group - get a memory cgroup to clean up after OOM + * @victim: task to be killed by the OOM killer + * @oom_domain: memcg in case of memcg OOM, NULL in case of system-wide OOM + * + * Returns a pointer to a memory cgroup, which has to be cleaned up + * by killing all belonging OOM-killable tasks. + * + * Caller has to call mem_cgroup_put() on the returned non-NULL memcg. + */ +struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim, + struct mem_cgroup *oom_domain) +{ + struct mem_cgroup *oom_group = NULL; + struct mem_cgroup *memcg; + + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) + return NULL; + + if (!oom_domain) + oom_domain = root_mem_cgroup; + + rcu_read_lock(); + + memcg = mem_cgroup_from_task(victim); + if (memcg == root_mem_cgroup) + goto out; + + /* + * If the victim task has been asynchronously moved to a different + * memory cgroup, we might end up killing tasks outside oom_domain. + * In this case it's better to ignore memory.group.oom. + */ + if (unlikely(!mem_cgroup_is_descendant(memcg, oom_domain))) + goto out; + + /* + * Traverse the memory cgroup hierarchy from the victim task's + * cgroup up to the OOMing cgroup (or root) to find the + * highest-level memory cgroup with oom.group set. + */ + for (; memcg; memcg = parent_mem_cgroup(memcg)) { + if (memcg->oom_group) + oom_group = memcg; + + if (memcg == oom_domain) + break; + } + + if (oom_group) + css_get(&oom_group->css); +out: + rcu_read_unlock(); + + return oom_group; +} + +void mem_cgroup_print_oom_group(struct mem_cgroup *memcg) +{ + pr_info("Tasks in "); + pr_cont_cgroup_path(memcg->css.cgroup); + pr_cont(" are going to be killed due to memory.oom.group set\n"); +} + +/** + * lock_page_memcg - lock a page->mem_cgroup binding + * @page: the page + * + * This function protects unlocked LRU pages from being moved to + * another cgroup. + * + * It ensures lifetime of the returned memcg. Caller is responsible + * for the lifetime of the page; __unlock_page_memcg() is available + * when @page might get freed inside the locked section. + */ +struct mem_cgroup *lock_page_memcg(struct page *page) +{ + struct page *head = compound_head(page); /* rmap on tail pages */ + struct mem_cgroup *memcg; + unsigned long flags; + + /* + * The RCU lock is held throughout the transaction. The fast + * path can get away without acquiring the memcg->move_lock + * because page moving starts with an RCU grace period. + * + * The RCU lock also protects the memcg from being freed when + * the page state that is going to change is the only thing + * preventing the page itself from being freed. E.g. writeback + * doesn't hold a page reference and relies on PG_writeback to + * keep off truncation, migration and so forth. + */ + rcu_read_lock(); + + if (mem_cgroup_disabled()) + return NULL; +again: + memcg = head->mem_cgroup; + if (unlikely(!memcg)) + return NULL; + + if (atomic_read(&memcg->moving_account) <= 0) + return memcg; + + spin_lock_irqsave(&memcg->move_lock, flags); + if (memcg != head->mem_cgroup) { + spin_unlock_irqrestore(&memcg->move_lock, flags); + goto again; + } + + /* + * When charge migration first begins, we can have locked and + * unlocked page stat updates happening concurrently. Track + * the task who has the lock for unlock_page_memcg(). + */ + memcg->move_lock_task = current; + memcg->move_lock_flags = flags; + + return memcg; +} +EXPORT_SYMBOL(lock_page_memcg); + +/** + * __unlock_page_memcg - unlock and unpin a memcg + * @memcg: the memcg + * + * Unlock and unpin a memcg returned by lock_page_memcg(). + */ +void __unlock_page_memcg(struct mem_cgroup *memcg) +{ + if (memcg && memcg->move_lock_task == current) { + unsigned long flags = memcg->move_lock_flags; + + memcg->move_lock_task = NULL; + memcg->move_lock_flags = 0; + + spin_unlock_irqrestore(&memcg->move_lock, flags); + } + + rcu_read_unlock(); +} + +/** + * unlock_page_memcg - unlock a page->mem_cgroup binding + * @page: the page + */ +void unlock_page_memcg(struct page *page) +{ + struct page *head = compound_head(page); + + __unlock_page_memcg(head->mem_cgroup); +} +EXPORT_SYMBOL(unlock_page_memcg); + +struct memcg_stock_pcp { + struct mem_cgroup *cached; /* this never be root cgroup */ + unsigned int nr_pages; + +#ifdef CONFIG_MEMCG_KMEM + struct obj_cgroup *cached_objcg; + unsigned int nr_bytes; +#endif + + struct work_struct work; + unsigned long flags; +#define FLUSHING_CACHED_CHARGE 0 +}; +static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock); +static DEFINE_MUTEX(percpu_charge_mutex); + +#ifdef CONFIG_MEMCG_KMEM +static void drain_obj_stock(struct memcg_stock_pcp *stock); +static bool obj_stock_flush_required(struct memcg_stock_pcp *stock, + struct mem_cgroup *root_memcg); + +#else +static inline void drain_obj_stock(struct memcg_stock_pcp *stock) +{ +} +static bool obj_stock_flush_required(struct memcg_stock_pcp *stock, + struct mem_cgroup *root_memcg) +{ + return false; +} +#endif + +/** + * consume_stock: Try to consume stocked charge on this cpu. + * @memcg: memcg to consume from. + * @nr_pages: how many pages to charge. + * + * The charges will only happen if @memcg matches the current cpu's memcg + * stock, and at least @nr_pages are available in that stock. Failure to + * service an allocation will refill the stock. + * + * returns true if successful, false otherwise. + */ +static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages) +{ + struct memcg_stock_pcp *stock; + unsigned long flags; + bool ret = false; + + if (nr_pages > MEMCG_CHARGE_BATCH) + return ret; + + local_irq_save(flags); + + stock = this_cpu_ptr(&memcg_stock); + if (memcg == stock->cached && stock->nr_pages >= nr_pages) { + stock->nr_pages -= nr_pages; + ret = true; + } + + local_irq_restore(flags); + + return ret; +} + +/* + * Returns stocks cached in percpu and reset cached information. + */ +static void drain_stock(struct memcg_stock_pcp *stock) +{ + struct mem_cgroup *old = stock->cached; + + if (!old) + return; + + if (stock->nr_pages) { + page_counter_uncharge(&old->memory, stock->nr_pages); + if (do_memsw_account()) + page_counter_uncharge(&old->memsw, stock->nr_pages); + stock->nr_pages = 0; + } + + css_put(&old->css); + stock->cached = NULL; +} + +static void drain_local_stock(struct work_struct *dummy) +{ + struct memcg_stock_pcp *stock; + unsigned long flags; + + /* + * The only protection from memory hotplug vs. drain_stock races is + * that we always operate on local CPU stock here with IRQ disabled + */ + local_irq_save(flags); + + stock = this_cpu_ptr(&memcg_stock); + drain_obj_stock(stock); + drain_stock(stock); + clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags); + + local_irq_restore(flags); +} + +/* + * Cache charges(val) to local per_cpu area. + * This will be consumed by consume_stock() function, later. + */ +static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages) +{ + struct memcg_stock_pcp *stock; + unsigned long flags; + + local_irq_save(flags); + + stock = this_cpu_ptr(&memcg_stock); + if (stock->cached != memcg) { /* reset if necessary */ + drain_stock(stock); + css_get(&memcg->css); + stock->cached = memcg; + } + stock->nr_pages += nr_pages; + + if (stock->nr_pages > MEMCG_CHARGE_BATCH) + drain_stock(stock); + + local_irq_restore(flags); +} + +/* + * Drains all per-CPU charge caches for given root_memcg resp. subtree + * of the hierarchy under it. + */ +static void drain_all_stock(struct mem_cgroup *root_memcg) +{ + int cpu, curcpu; + + /* If someone's already draining, avoid adding running more workers. */ + if (!mutex_trylock(&percpu_charge_mutex)) + return; + /* + * Notify other cpus that system-wide "drain" is running + * We do not care about races with the cpu hotplug because cpu down + * as well as workers from this path always operate on the local + * per-cpu data. CPU up doesn't touch memcg_stock at all. + */ + curcpu = get_cpu(); + for_each_online_cpu(cpu) { + struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu); + struct mem_cgroup *memcg; + bool flush = false; + + rcu_read_lock(); + memcg = stock->cached; + if (memcg && stock->nr_pages && + mem_cgroup_is_descendant(memcg, root_memcg)) + flush = true; + if (obj_stock_flush_required(stock, root_memcg)) + flush = true; + rcu_read_unlock(); + + if (flush && + !test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags)) { + if (cpu == curcpu) + drain_local_stock(&stock->work); + else + schedule_work_on(cpu, &stock->work); + } + } + put_cpu(); + mutex_unlock(&percpu_charge_mutex); +} + +static int memcg_hotplug_cpu_dead(unsigned int cpu) +{ + struct memcg_stock_pcp *stock; + struct mem_cgroup *memcg, *mi; + + stock = &per_cpu(memcg_stock, cpu); + drain_stock(stock); + + for_each_mem_cgroup(memcg) { + int i; + + for (i = 0; i < MEMCG_NR_STAT; i++) { + int nid; + long x; + + x = this_cpu_xchg(memcg->vmstats_percpu->stat[i], 0); + if (x) + for (mi = memcg; mi; mi = parent_mem_cgroup(mi)) + atomic_long_add(x, &memcg->vmstats[i]); + + if (i >= NR_VM_NODE_STAT_ITEMS) + continue; + + for_each_node(nid) { + struct mem_cgroup_per_node *pn; + + pn = mem_cgroup_nodeinfo(memcg, nid); + x = this_cpu_xchg(pn->lruvec_stat_cpu->count[i], 0); + if (x) + do { + atomic_long_add(x, &pn->lruvec_stat[i]); + } while ((pn = parent_nodeinfo(pn, nid))); + } + } + + for (i = 0; i < NR_VM_EVENT_ITEMS; i++) { + long x; + + x = this_cpu_xchg(memcg->vmstats_percpu->events[i], 0); + if (x) + for (mi = memcg; mi; mi = parent_mem_cgroup(mi)) + atomic_long_add(x, &memcg->vmevents[i]); + } + } + + return 0; +} + +static unsigned long reclaim_high(struct mem_cgroup *memcg, + unsigned int nr_pages, + gfp_t gfp_mask) +{ + unsigned long nr_reclaimed = 0; + + do { + unsigned long pflags; + + if (page_counter_read(&memcg->memory) <= + READ_ONCE(memcg->memory.high)) + continue; + + memcg_memory_event(memcg, MEMCG_HIGH); + + psi_memstall_enter(&pflags); + nr_reclaimed += try_to_free_mem_cgroup_pages(memcg, nr_pages, + gfp_mask, true); + psi_memstall_leave(&pflags); + } while ((memcg = parent_mem_cgroup(memcg)) && + !mem_cgroup_is_root(memcg)); + + return nr_reclaimed; +} + +static void high_work_func(struct work_struct *work) +{ + struct mem_cgroup *memcg; + + memcg = container_of(work, struct mem_cgroup, high_work); + reclaim_high(memcg, MEMCG_CHARGE_BATCH, GFP_KERNEL); +} + +/* + * Clamp the maximum sleep time per allocation batch to 2 seconds. This is + * enough to still cause a significant slowdown in most cases, while still + * allowing diagnostics and tracing to proceed without becoming stuck. + */ +#define MEMCG_MAX_HIGH_DELAY_JIFFIES (2UL*HZ) + +/* + * When calculating the delay, we use these either side of the exponentiation to + * maintain precision and scale to a reasonable number of jiffies (see the table + * below. + * + * - MEMCG_DELAY_PRECISION_SHIFT: Extra precision bits while translating the + * overage ratio to a delay. + * - MEMCG_DELAY_SCALING_SHIFT: The number of bits to scale down the + * proposed penalty in order to reduce to a reasonable number of jiffies, and + * to produce a reasonable delay curve. + * + * MEMCG_DELAY_SCALING_SHIFT just happens to be a number that produces a + * reasonable delay curve compared to precision-adjusted overage, not + * penalising heavily at first, but still making sure that growth beyond the + * limit penalises misbehaviour cgroups by slowing them down exponentially. For + * example, with a high of 100 megabytes: + * + * +-------+------------------------+ + * | usage | time to allocate in ms | + * +-------+------------------------+ + * | 100M | 0 | + * | 101M | 6 | + * | 102M | 25 | + * | 103M | 57 | + * | 104M | 102 | + * | 105M | 159 | + * | 106M | 230 | + * | 107M | 313 | + * | 108M | 409 | + * | 109M | 518 | + * | 110M | 639 | + * | 111M | 774 | + * | 112M | 921 | + * | 113M | 1081 | + * | 114M | 1254 | + * | 115M | 1439 | + * | 116M | 1638 | + * | 117M | 1849 | + * | 118M | 2000 | + * | 119M | 2000 | + * | 120M | 2000 | + * +-------+------------------------+ + */ + #define MEMCG_DELAY_PRECISION_SHIFT 20 + #define MEMCG_DELAY_SCALING_SHIFT 14 + +static u64 calculate_overage(unsigned long usage, unsigned long high) +{ + u64 overage; + + if (usage <= high) + return 0; + + /* + * Prevent division by 0 in overage calculation by acting as if + * it was a threshold of 1 page + */ + high = max(high, 1UL); + + overage = usage - high; + overage <<= MEMCG_DELAY_PRECISION_SHIFT; + return div64_u64(overage, high); +} + +static u64 mem_find_max_overage(struct mem_cgroup *memcg) +{ + u64 overage, max_overage = 0; + + do { + overage = calculate_overage(page_counter_read(&memcg->memory), + READ_ONCE(memcg->memory.high)); + max_overage = max(overage, max_overage); + } while ((memcg = parent_mem_cgroup(memcg)) && + !mem_cgroup_is_root(memcg)); + + return max_overage; +} + +static u64 swap_find_max_overage(struct mem_cgroup *memcg) +{ + u64 overage, max_overage = 0; + + do { + overage = calculate_overage(page_counter_read(&memcg->swap), + READ_ONCE(memcg->swap.high)); + if (overage) + memcg_memory_event(memcg, MEMCG_SWAP_HIGH); + max_overage = max(overage, max_overage); + } while ((memcg = parent_mem_cgroup(memcg)) && + !mem_cgroup_is_root(memcg)); + + return max_overage; +} + +/* + * Get the number of jiffies that we should penalise a mischievous cgroup which + * is exceeding its memory.high by checking both it and its ancestors. + */ +static unsigned long calculate_high_delay(struct mem_cgroup *memcg, + unsigned int nr_pages, + u64 max_overage) +{ + unsigned long penalty_jiffies; + + if (!max_overage) + return 0; + + /* + * We use overage compared to memory.high to calculate the number of + * jiffies to sleep (penalty_jiffies). Ideally this value should be + * fairly lenient on small overages, and increasingly harsh when the + * memcg in question makes it clear that it has no intention of stopping + * its crazy behaviour, so we exponentially increase the delay based on + * overage amount. + */ + penalty_jiffies = max_overage * max_overage * HZ; + penalty_jiffies >>= MEMCG_DELAY_PRECISION_SHIFT; + penalty_jiffies >>= MEMCG_DELAY_SCALING_SHIFT; + + /* + * Factor in the task's own contribution to the overage, such that four + * N-sized allocations are throttled approximately the same as one + * 4N-sized allocation. + * + * MEMCG_CHARGE_BATCH pages is nominal, so work out how much smaller or + * larger the current charge patch is than that. + */ + return penalty_jiffies * nr_pages / MEMCG_CHARGE_BATCH; +} + +/* + * Scheduled by try_charge() to be executed from the userland return path + * and reclaims memory over the high limit. + */ +void mem_cgroup_handle_over_high(void) +{ + unsigned long penalty_jiffies; + unsigned long pflags; + unsigned long nr_reclaimed; + unsigned int nr_pages = current->memcg_nr_pages_over_high; + int nr_retries = MAX_RECLAIM_RETRIES; + struct mem_cgroup *memcg; + bool in_retry = false; + + if (likely(!nr_pages)) + return; + + memcg = get_mem_cgroup_from_mm(current->mm); + current->memcg_nr_pages_over_high = 0; + +retry_reclaim: + /* + * The allocating task should reclaim at least the batch size, but for + * subsequent retries we only want to do what's necessary to prevent oom + * or breaching resource isolation. + * + * This is distinct from memory.max or page allocator behaviour because + * memory.high is currently batched, whereas memory.max and the page + * allocator run every time an allocation is made. + */ + nr_reclaimed = reclaim_high(memcg, + in_retry ? SWAP_CLUSTER_MAX : nr_pages, + GFP_KERNEL); + + /* + * memory.high is breached and reclaim is unable to keep up. Throttle + * allocators proactively to slow down excessive growth. + */ + penalty_jiffies = calculate_high_delay(memcg, nr_pages, + mem_find_max_overage(memcg)); + + penalty_jiffies += calculate_high_delay(memcg, nr_pages, + swap_find_max_overage(memcg)); + + /* + * Clamp the max delay per usermode return so as to still keep the + * application moving forwards and also permit diagnostics, albeit + * extremely slowly. + */ + penalty_jiffies = min(penalty_jiffies, MEMCG_MAX_HIGH_DELAY_JIFFIES); + + /* + * Don't sleep if the amount of jiffies this memcg owes us is so low + * that it's not even worth doing, in an attempt to be nice to those who + * go only a small amount over their memory.high value and maybe haven't + * been aggressively reclaimed enough yet. + */ + if (penalty_jiffies <= HZ / 100) + goto out; + + /* + * If reclaim is making forward progress but we're still over + * memory.high, we want to encourage that rather than doing allocator + * throttling. + */ + if (nr_reclaimed || nr_retries--) { + in_retry = true; + goto retry_reclaim; + } + + /* + * If we exit early, we're guaranteed to die (since + * schedule_timeout_killable sets TASK_KILLABLE). This means we don't + * need to account for any ill-begotten jiffies to pay them off later. + */ + psi_memstall_enter(&pflags); + schedule_timeout_killable(penalty_jiffies); + psi_memstall_leave(&pflags); + +out: + css_put(&memcg->css); +} + +static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask, + unsigned int nr_pages) +{ + unsigned int batch = max(MEMCG_CHARGE_BATCH, nr_pages); + int nr_retries = MAX_RECLAIM_RETRIES; + struct mem_cgroup *mem_over_limit; + struct page_counter *counter; + enum oom_status oom_status; + unsigned long nr_reclaimed; + bool passed_oom = false; + bool may_swap = true; + bool drained = false; + unsigned long pflags; + + if (mem_cgroup_is_root(memcg)) + return 0; +retry: + if (consume_stock(memcg, nr_pages)) + return 0; + + if (!do_memsw_account() || + page_counter_try_charge(&memcg->memsw, batch, &counter)) { + if (page_counter_try_charge(&memcg->memory, batch, &counter)) + goto done_restock; + if (do_memsw_account()) + page_counter_uncharge(&memcg->memsw, batch); + mem_over_limit = mem_cgroup_from_counter(counter, memory); + } else { + mem_over_limit = mem_cgroup_from_counter(counter, memsw); + may_swap = false; + } + + if (batch > nr_pages) { + batch = nr_pages; + goto retry; + } + + /* + * Memcg doesn't have a dedicated reserve for atomic + * allocations. But like the global atomic pool, we need to + * put the burden of reclaim on regular allocation requests + * and let these go through as privileged allocations. + */ + if (gfp_mask & __GFP_ATOMIC) + goto force; + + /* + * Prevent unbounded recursion when reclaim operations need to + * allocate memory. This might exceed the limits temporarily, + * but we prefer facilitating memory reclaim and getting back + * under the limit over triggering OOM kills in these cases. + */ + if (unlikely(current->flags & PF_MEMALLOC)) + goto force; + + if (unlikely(task_in_memcg_oom(current))) + goto nomem; + + if (!gfpflags_allow_blocking(gfp_mask)) + goto nomem; + + memcg_memory_event(mem_over_limit, MEMCG_MAX); + + psi_memstall_enter(&pflags); + nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages, + gfp_mask, may_swap); + psi_memstall_leave(&pflags); + + if (mem_cgroup_margin(mem_over_limit) >= nr_pages) + goto retry; + + if (!drained) { + drain_all_stock(mem_over_limit); + drained = true; + goto retry; + } + + if (gfp_mask & __GFP_NORETRY) + goto nomem; + /* + * Even though the limit is exceeded at this point, reclaim + * may have been able to free some pages. Retry the charge + * before killing the task. + * + * Only for regular pages, though: huge pages are rather + * unlikely to succeed so close to the limit, and we fall back + * to regular pages anyway in case of failure. + */ + if (nr_reclaimed && nr_pages <= (1 << PAGE_ALLOC_COSTLY_ORDER)) + goto retry; + /* + * At task move, charge accounts can be doubly counted. So, it's + * better to wait until the end of task_move if something is going on. + */ + if (mem_cgroup_wait_acct_move(mem_over_limit)) + goto retry; + + if (nr_retries--) + goto retry; + + if (gfp_mask & __GFP_RETRY_MAYFAIL) + goto nomem; + + if (gfp_mask & __GFP_NOFAIL) + goto force; + + /* Avoid endless loop for tasks bypassed by the oom killer */ + if (passed_oom && task_is_dying()) + goto nomem; + + /* + * keep retrying as long as the memcg oom killer is able to make + * a forward progress or bypass the charge if the oom killer + * couldn't make any progress. + */ + oom_status = mem_cgroup_oom(mem_over_limit, gfp_mask, + get_order(nr_pages * PAGE_SIZE)); + if (oom_status == OOM_SUCCESS) { + passed_oom = true; + nr_retries = MAX_RECLAIM_RETRIES; + goto retry; + } +nomem: + if (!(gfp_mask & __GFP_NOFAIL)) + return -ENOMEM; +force: + /* + * The allocation either can't fail or will lead to more memory + * being freed very soon. Allow memory usage go over the limit + * temporarily by force charging it. + */ + page_counter_charge(&memcg->memory, nr_pages); + if (do_memsw_account()) + page_counter_charge(&memcg->memsw, nr_pages); + + return 0; + +done_restock: + if (batch > nr_pages) + refill_stock(memcg, batch - nr_pages); + + /* + * If the hierarchy is above the normal consumption range, schedule + * reclaim on returning to userland. We can perform reclaim here + * if __GFP_RECLAIM but let's always punt for simplicity and so that + * GFP_KERNEL can consistently be used during reclaim. @memcg is + * not recorded as it most likely matches current's and won't + * change in the meantime. As high limit is checked again before + * reclaim, the cost of mismatch is negligible. + */ + do { + bool mem_high, swap_high; + + mem_high = page_counter_read(&memcg->memory) > + READ_ONCE(memcg->memory.high); + swap_high = page_counter_read(&memcg->swap) > + READ_ONCE(memcg->swap.high); + + /* Don't bother a random interrupted task */ + if (in_interrupt()) { + if (mem_high) { + schedule_work(&memcg->high_work); + break; + } + continue; + } + + if (mem_high || swap_high) { + /* + * The allocating tasks in this cgroup will need to do + * reclaim or be throttled to prevent further growth + * of the memory or swap footprints. + * + * Target some best-effort fairness between the tasks, + * and distribute reclaim work and delay penalties + * based on how much each task is actually allocating. + */ + current->memcg_nr_pages_over_high += batch; + set_notify_resume(current); + break; + } + } while ((memcg = parent_mem_cgroup(memcg))); + + return 0; +} + +#if defined(CONFIG_MEMCG_KMEM) || defined(CONFIG_MMU) +static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) +{ + if (mem_cgroup_is_root(memcg)) + return; + + page_counter_uncharge(&memcg->memory, nr_pages); + if (do_memsw_account()) + page_counter_uncharge(&memcg->memsw, nr_pages); +} +#endif + +static void commit_charge(struct page *page, struct mem_cgroup *memcg) +{ + VM_BUG_ON_PAGE(page->mem_cgroup, page); + /* + * Any of the following ensures page->mem_cgroup stability: + * + * - the page lock + * - LRU isolation + * - lock_page_memcg() + * - exclusive reference + */ + page->mem_cgroup = memcg; +} + +#ifdef CONFIG_MEMCG_KMEM +/* + * The allocated objcg pointers array is not accounted directly. + * Moreover, it should not come from DMA buffer and is not readily + * reclaimable. So those GFP bits should be masked off. + */ +#define OBJCGS_CLEAR_MASK (__GFP_DMA | __GFP_RECLAIMABLE | \ + __GFP_ACCOUNT | __GFP_NOFAIL) + +int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s, + gfp_t gfp) +{ + unsigned int objects = objs_per_slab_page(s, page); + void *vec; + + gfp &= ~OBJCGS_CLEAR_MASK; + vec = kcalloc_node(objects, sizeof(struct obj_cgroup *), gfp, + page_to_nid(page)); + if (!vec) + return -ENOMEM; + + if (cmpxchg(&page->obj_cgroups, NULL, + (struct obj_cgroup **) ((unsigned long)vec | 0x1UL))) + kfree(vec); + else + kmemleak_not_leak(vec); + + return 0; +} + +/* + * Returns a pointer to the memory cgroup to which the kernel object is charged. + * + * The caller must ensure the memcg lifetime, e.g. by taking rcu_read_lock(), + * cgroup_mutex, etc. + */ +struct mem_cgroup *mem_cgroup_from_obj(void *p) +{ + struct page *page; + + if (mem_cgroup_disabled()) + return NULL; + + page = virt_to_head_page(p); + + /* + * If page->mem_cgroup is set, it's either a simple mem_cgroup pointer + * or a pointer to obj_cgroup vector. In the latter case the lowest + * bit of the pointer is set. + * The page->mem_cgroup pointer can be asynchronously changed + * from NULL to (obj_cgroup_vec | 0x1UL), but can't be changed + * from a valid memcg pointer to objcg vector or back. + */ + if (!page->mem_cgroup) + return NULL; + + /* + * Slab objects are accounted individually, not per-page. + * Memcg membership data for each individual object is saved in + * the page->obj_cgroups. + */ + if (page_has_obj_cgroups(page)) { + struct obj_cgroup *objcg; + unsigned int off; + + off = obj_to_index(page->slab_cache, page, p); + objcg = page_obj_cgroups(page)[off]; + if (objcg) + return obj_cgroup_memcg(objcg); + + return NULL; + } + + /* All other pages use page->mem_cgroup */ + return page->mem_cgroup; +} + +__always_inline struct obj_cgroup *get_obj_cgroup_from_current(void) +{ + struct obj_cgroup *objcg = NULL; + struct mem_cgroup *memcg; + + if (memcg_kmem_bypass()) + return NULL; + + rcu_read_lock(); + if (unlikely(active_memcg())) + memcg = active_memcg(); + else + memcg = mem_cgroup_from_task(current); + + for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg)) { + objcg = rcu_dereference(memcg->objcg); + if (objcg && obj_cgroup_tryget(objcg)) + break; + objcg = NULL; + } + rcu_read_unlock(); + + return objcg; +} + +static int memcg_alloc_cache_id(void) +{ + int id, size; + int err; + + id = ida_simple_get(&memcg_cache_ida, + 0, MEMCG_CACHES_MAX_SIZE, GFP_KERNEL); + if (id < 0) + return id; + + if (id < memcg_nr_cache_ids) + return id; + + /* + * There's no space for the new id in memcg_caches arrays, + * so we have to grow them. + */ + down_write(&memcg_cache_ids_sem); + + size = 2 * (id + 1); + if (size < MEMCG_CACHES_MIN_SIZE) + size = MEMCG_CACHES_MIN_SIZE; + else if (size > MEMCG_CACHES_MAX_SIZE) + size = MEMCG_CACHES_MAX_SIZE; + + err = memcg_update_all_list_lrus(size); + if (!err) + memcg_nr_cache_ids = size; + + up_write(&memcg_cache_ids_sem); + + if (err) { + ida_simple_remove(&memcg_cache_ida, id); + return err; + } + return id; +} + +static void memcg_free_cache_id(int id) +{ + ida_simple_remove(&memcg_cache_ida, id); +} + +/** + * __memcg_kmem_charge: charge a number of kernel pages to a memcg + * @memcg: memory cgroup to charge + * @gfp: reclaim mode + * @nr_pages: number of pages to charge + * + * Returns 0 on success, an error code on failure. + */ +int __memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp, + unsigned int nr_pages) +{ + struct page_counter *counter; + int ret; + + ret = try_charge(memcg, gfp, nr_pages); + if (ret) + return ret; + + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && + !page_counter_try_charge(&memcg->kmem, nr_pages, &counter)) { + + /* + * Enforce __GFP_NOFAIL allocation because callers are not + * prepared to see failures and likely do not have any failure + * handling code. + */ + if (gfp & __GFP_NOFAIL) { + page_counter_charge(&memcg->kmem, nr_pages); + return 0; + } + cancel_charge(memcg, nr_pages); + return -ENOMEM; + } + return 0; +} + +/** + * __memcg_kmem_uncharge: uncharge a number of kernel pages from a memcg + * @memcg: memcg to uncharge + * @nr_pages: number of pages to uncharge + */ +void __memcg_kmem_uncharge(struct mem_cgroup *memcg, unsigned int nr_pages) +{ + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) + page_counter_uncharge(&memcg->kmem, nr_pages); + + refill_stock(memcg, nr_pages); +} + +/** + * __memcg_kmem_charge_page: charge a kmem page to the current memory cgroup + * @page: page to charge + * @gfp: reclaim mode + * @order: allocation order + * + * Returns 0 on success, an error code on failure. + */ +int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) +{ + struct mem_cgroup *memcg; + int ret = 0; + + memcg = get_mem_cgroup_from_current(); + if (memcg && !mem_cgroup_is_root(memcg)) { + ret = __memcg_kmem_charge(memcg, gfp, 1 << order); + if (!ret) { + page->mem_cgroup = memcg; + __SetPageKmemcg(page); + return 0; + } + css_put(&memcg->css); + } + return ret; +} + +/** + * __memcg_kmem_uncharge_page: uncharge a kmem page + * @page: page to uncharge + * @order: allocation order + */ +void __memcg_kmem_uncharge_page(struct page *page, int order) +{ + struct mem_cgroup *memcg = page->mem_cgroup; + unsigned int nr_pages = 1 << order; + + if (!memcg) + return; + + VM_BUG_ON_PAGE(mem_cgroup_is_root(memcg), page); + __memcg_kmem_uncharge(memcg, nr_pages); + page->mem_cgroup = NULL; + css_put(&memcg->css); + + /* slab pages do not have PageKmemcg flag set */ + if (PageKmemcg(page)) + __ClearPageKmemcg(page); +} + +static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes) +{ + struct memcg_stock_pcp *stock; + unsigned long flags; + bool ret = false; + + local_irq_save(flags); + + stock = this_cpu_ptr(&memcg_stock); + if (objcg == stock->cached_objcg && stock->nr_bytes >= nr_bytes) { + stock->nr_bytes -= nr_bytes; + ret = true; + } + + local_irq_restore(flags); + + return ret; +} + +static void drain_obj_stock(struct memcg_stock_pcp *stock) +{ + struct obj_cgroup *old = stock->cached_objcg; + + if (!old) + return; + + if (stock->nr_bytes) { + unsigned int nr_pages = stock->nr_bytes >> PAGE_SHIFT; + unsigned int nr_bytes = stock->nr_bytes & (PAGE_SIZE - 1); + + if (nr_pages) { + struct mem_cgroup *memcg; + + rcu_read_lock(); +retry: + memcg = obj_cgroup_memcg(old); + if (unlikely(!css_tryget(&memcg->css))) + goto retry; + rcu_read_unlock(); + + __memcg_kmem_uncharge(memcg, nr_pages); + css_put(&memcg->css); + } + + /* + * The leftover is flushed to the centralized per-memcg value. + * On the next attempt to refill obj stock it will be moved + * to a per-cpu stock (probably, on an other CPU), see + * refill_obj_stock(). + * + * How often it's flushed is a trade-off between the memory + * limit enforcement accuracy and potential CPU contention, + * so it might be changed in the future. + */ + atomic_add(nr_bytes, &old->nr_charged_bytes); + stock->nr_bytes = 0; + } + + obj_cgroup_put(old); + stock->cached_objcg = NULL; +} + +static bool obj_stock_flush_required(struct memcg_stock_pcp *stock, + struct mem_cgroup *root_memcg) +{ + struct mem_cgroup *memcg; + + if (stock->cached_objcg) { + memcg = obj_cgroup_memcg(stock->cached_objcg); + if (memcg && mem_cgroup_is_descendant(memcg, root_memcg)) + return true; + } + + return false; +} + +static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes) +{ + struct memcg_stock_pcp *stock; + unsigned long flags; + + local_irq_save(flags); + + stock = this_cpu_ptr(&memcg_stock); + if (stock->cached_objcg != objcg) { /* reset if necessary */ + drain_obj_stock(stock); + obj_cgroup_get(objcg); + stock->cached_objcg = objcg; + stock->nr_bytes = atomic_xchg(&objcg->nr_charged_bytes, 0); + } + stock->nr_bytes += nr_bytes; + + if (stock->nr_bytes > PAGE_SIZE) + drain_obj_stock(stock); + + local_irq_restore(flags); +} + +int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size) +{ + struct mem_cgroup *memcg; + unsigned int nr_pages, nr_bytes; + int ret; + + if (consume_obj_stock(objcg, size)) + return 0; + + /* + * In theory, memcg->nr_charged_bytes can have enough + * pre-charged bytes to satisfy the allocation. However, + * flushing memcg->nr_charged_bytes requires two atomic + * operations, and memcg->nr_charged_bytes can't be big, + * so it's better to ignore it and try grab some new pages. + * memcg->nr_charged_bytes will be flushed in + * refill_obj_stock(), called from this function or + * independently later. + */ + rcu_read_lock(); +retry: + memcg = obj_cgroup_memcg(objcg); + if (unlikely(!css_tryget(&memcg->css))) + goto retry; + rcu_read_unlock(); + + nr_pages = size >> PAGE_SHIFT; + nr_bytes = size & (PAGE_SIZE - 1); + + if (nr_bytes) + nr_pages += 1; + + ret = __memcg_kmem_charge(memcg, gfp, nr_pages); + if (!ret && nr_bytes) + refill_obj_stock(objcg, PAGE_SIZE - nr_bytes); + + css_put(&memcg->css); + return ret; +} + +void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size) +{ + refill_obj_stock(objcg, size); +} + +#endif /* CONFIG_MEMCG_KMEM */ + +/* + * Because head->mem_cgroup is not set on tails, set it now. + */ +void split_page_memcg(struct page *head, unsigned int nr) +{ + struct mem_cgroup *memcg = head->mem_cgroup; + int kmemcg = PageKmemcg(head); + int i; + + if (mem_cgroup_disabled() || !memcg) + return; + + for (i = 1; i < nr; i++) { + head[i].mem_cgroup = memcg; + if (kmemcg) + __SetPageKmemcg(head + i); + } + css_get_many(&memcg->css, nr - 1); +} + +#ifdef CONFIG_MEMCG_SWAP +/** + * mem_cgroup_move_swap_account - move swap charge and swap_cgroup's record. + * @entry: swap entry to be moved + * @from: mem_cgroup which the entry is moved from + * @to: mem_cgroup which the entry is moved to + * + * It succeeds only when the swap_cgroup's record for this entry is the same + * as the mem_cgroup's id of @from. + * + * Returns 0 on success, -EINVAL on failure. + * + * The caller must have charged to @to, IOW, called page_counter_charge() about + * both res and memsw, and called css_get(). + */ +static int mem_cgroup_move_swap_account(swp_entry_t entry, + struct mem_cgroup *from, struct mem_cgroup *to) +{ + unsigned short old_id, new_id; + + old_id = mem_cgroup_id(from); + new_id = mem_cgroup_id(to); + + if (swap_cgroup_cmpxchg(entry, old_id, new_id) == old_id) { + mod_memcg_state(from, MEMCG_SWAP, -1); + mod_memcg_state(to, MEMCG_SWAP, 1); + return 0; + } + return -EINVAL; +} +#else +static inline int mem_cgroup_move_swap_account(swp_entry_t entry, + struct mem_cgroup *from, struct mem_cgroup *to) +{ + return -EINVAL; +} +#endif + +static DEFINE_MUTEX(memcg_max_mutex); + +static int mem_cgroup_resize_max(struct mem_cgroup *memcg, + unsigned long max, bool memsw) +{ + bool enlarge = false; + bool drained = false; + int ret; + bool limits_invariant; + struct page_counter *counter = memsw ? &memcg->memsw : &memcg->memory; + + do { + if (signal_pending(current)) { + ret = -EINTR; + break; + } + + mutex_lock(&memcg_max_mutex); + /* + * Make sure that the new limit (memsw or memory limit) doesn't + * break our basic invariant rule memory.max <= memsw.max. + */ + limits_invariant = memsw ? max >= READ_ONCE(memcg->memory.max) : + max <= memcg->memsw.max; + if (!limits_invariant) { + mutex_unlock(&memcg_max_mutex); + ret = -EINVAL; + break; + } + if (max > counter->max) + enlarge = true; + ret = page_counter_set_max(counter, max); + mutex_unlock(&memcg_max_mutex); + + if (!ret) + break; + + if (!drained) { + drain_all_stock(memcg); + drained = true; + continue; + } + + if (!try_to_free_mem_cgroup_pages(memcg, 1, + GFP_KERNEL, !memsw)) { + ret = -EBUSY; + break; + } + } while (true); + + if (!ret && enlarge) + memcg_oom_recover(memcg); + + return ret; +} + +unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, + gfp_t gfp_mask, + unsigned long *total_scanned) +{ + unsigned long nr_reclaimed = 0; + struct mem_cgroup_per_node *mz, *next_mz = NULL; + unsigned long reclaimed; + int loop = 0; + struct mem_cgroup_tree_per_node *mctz; + unsigned long excess; + unsigned long nr_scanned; + + if (order > 0) + return 0; + + mctz = soft_limit_tree_node(pgdat->node_id); + + /* + * Do not even bother to check the largest node if the root + * is empty. Do it lockless to prevent lock bouncing. Races + * are acceptable as soft limit is best effort anyway. + */ + if (!mctz || RB_EMPTY_ROOT(&mctz->rb_root)) + return 0; + + /* + * This loop can run a while, specially if mem_cgroup's continuously + * keep exceeding their soft limit and putting the system under + * pressure + */ + do { + if (next_mz) + mz = next_mz; + else + mz = mem_cgroup_largest_soft_limit_node(mctz); + if (!mz) + break; + + nr_scanned = 0; + reclaimed = mem_cgroup_soft_reclaim(mz->memcg, pgdat, + gfp_mask, &nr_scanned); + nr_reclaimed += reclaimed; + *total_scanned += nr_scanned; + spin_lock_irq(&mctz->lock); + __mem_cgroup_remove_exceeded(mz, mctz); + + /* + * If we failed to reclaim anything from this memory cgroup + * it is time to move on to the next cgroup + */ + next_mz = NULL; + if (!reclaimed) + next_mz = __mem_cgroup_largest_soft_limit_node(mctz); + + excess = soft_limit_excess(mz->memcg); + /* + * One school of thought says that we should not add + * back the node to the tree if reclaim returns 0. + * But our reclaim could return 0, simply because due + * to priority we are exposing a smaller subset of + * memory to reclaim from. Consider this as a longer + * term TODO. + */ + /* If excess == 0, no tree ops */ + __mem_cgroup_insert_exceeded(mz, mctz, excess); + spin_unlock_irq(&mctz->lock); + css_put(&mz->memcg->css); + loop++; + /* + * Could not reclaim anything and there are no more + * mem cgroups to try or we seem to be looping without + * reclaiming anything. + */ + if (!nr_reclaimed && + (next_mz == NULL || + loop > MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS)) + break; + } while (!nr_reclaimed); + if (next_mz) + css_put(&next_mz->memcg->css); + return nr_reclaimed; +} + +/* + * Test whether @memcg has children, dead or alive. Note that this + * function doesn't care whether @memcg has use_hierarchy enabled and + * returns %true if there are child csses according to the cgroup + * hierarchy. Testing use_hierarchy is the caller's responsibility. + */ +static inline bool memcg_has_children(struct mem_cgroup *memcg) +{ + bool ret; + + rcu_read_lock(); + ret = css_next_child(NULL, &memcg->css); + rcu_read_unlock(); + return ret; +} + +/* + * Reclaims as many pages from the given memcg as possible. + * + * Caller is responsible for holding css reference for memcg. + */ +static int mem_cgroup_force_empty(struct mem_cgroup *memcg) +{ + int nr_retries = MAX_RECLAIM_RETRIES; + + /* we call try-to-free pages for make this cgroup empty */ + lru_add_drain_all(); + + drain_all_stock(memcg); + + /* try to free all pages in this cgroup */ + while (nr_retries && page_counter_read(&memcg->memory)) { + int progress; + + if (signal_pending(current)) + return -EINTR; + + progress = try_to_free_mem_cgroup_pages(memcg, 1, + GFP_KERNEL, true); + if (!progress) { + nr_retries--; + /* maybe some writeback is necessary */ + congestion_wait(BLK_RW_ASYNC, HZ/10); + } + + } + + return 0; +} + +static ssize_t mem_cgroup_force_empty_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + + if (mem_cgroup_is_root(memcg)) + return -EINVAL; + return mem_cgroup_force_empty(memcg) ?: nbytes; +} + +static u64 mem_cgroup_hierarchy_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return mem_cgroup_from_css(css)->use_hierarchy; +} + +static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css, + struct cftype *cft, u64 val) +{ + int retval = 0; + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct mem_cgroup *parent_memcg = mem_cgroup_from_css(memcg->css.parent); + + if (memcg->use_hierarchy == val) + return 0; + + /* + * If parent's use_hierarchy is set, we can't make any modifications + * in the child subtrees. If it is unset, then the change can + * occur, provided the current cgroup has no children. + * + * For the root cgroup, parent_mem is NULL, we allow value to be + * set if there are no children. + */ + if ((!parent_memcg || !parent_memcg->use_hierarchy) && + (val == 1 || val == 0)) { + if (!memcg_has_children(memcg)) + memcg->use_hierarchy = val; + else + retval = -EBUSY; + } else + retval = -EINVAL; + + return retval; +} + +static unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) +{ + unsigned long val; + + if (mem_cgroup_is_root(memcg)) { + val = memcg_page_state(memcg, NR_FILE_PAGES) + + memcg_page_state(memcg, NR_ANON_MAPPED); + if (swap) + val += memcg_page_state(memcg, MEMCG_SWAP); + } else { + if (!swap) + val = page_counter_read(&memcg->memory); + else + val = page_counter_read(&memcg->memsw); + } + return val; +} + +enum { + RES_USAGE, + RES_LIMIT, + RES_MAX_USAGE, + RES_FAILCNT, + RES_SOFT_LIMIT, +}; + +static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct page_counter *counter; + + switch (MEMFILE_TYPE(cft->private)) { + case _MEM: + counter = &memcg->memory; + break; + case _MEMSWAP: + counter = &memcg->memsw; + break; + case _KMEM: + counter = &memcg->kmem; + break; + case _TCP: + counter = &memcg->tcpmem; + break; + default: + BUG(); + } + + switch (MEMFILE_ATTR(cft->private)) { + case RES_USAGE: + if (counter == &memcg->memory) + return (u64)mem_cgroup_usage(memcg, false) * PAGE_SIZE; + if (counter == &memcg->memsw) + return (u64)mem_cgroup_usage(memcg, true) * PAGE_SIZE; + return (u64)page_counter_read(counter) * PAGE_SIZE; + case RES_LIMIT: + return (u64)counter->max * PAGE_SIZE; + case RES_MAX_USAGE: + return (u64)counter->watermark * PAGE_SIZE; + case RES_FAILCNT: + return counter->failcnt; + case RES_SOFT_LIMIT: + return (u64)memcg->soft_limit * PAGE_SIZE; + default: + BUG(); + } +} + +static void memcg_flush_percpu_vmstats(struct mem_cgroup *memcg) +{ + unsigned long stat[MEMCG_NR_STAT] = {0}; + struct mem_cgroup *mi; + int node, cpu, i; + + for_each_online_cpu(cpu) + for (i = 0; i < MEMCG_NR_STAT; i++) + stat[i] += per_cpu(memcg->vmstats_percpu->stat[i], cpu); + + for (mi = memcg; mi; mi = parent_mem_cgroup(mi)) + for (i = 0; i < MEMCG_NR_STAT; i++) + atomic_long_add(stat[i], &mi->vmstats[i]); + + for_each_node(node) { + struct mem_cgroup_per_node *pn = memcg->nodeinfo[node]; + struct mem_cgroup_per_node *pi; + + for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) + stat[i] = 0; + + for_each_online_cpu(cpu) + for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) + stat[i] += per_cpu( + pn->lruvec_stat_cpu->count[i], cpu); + + for (pi = pn; pi; pi = parent_nodeinfo(pi, node)) + for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) + atomic_long_add(stat[i], &pi->lruvec_stat[i]); + } +} + +static void memcg_flush_percpu_vmevents(struct mem_cgroup *memcg) +{ + unsigned long events[NR_VM_EVENT_ITEMS]; + struct mem_cgroup *mi; + int cpu, i; + + for (i = 0; i < NR_VM_EVENT_ITEMS; i++) + events[i] = 0; + + for_each_online_cpu(cpu) + for (i = 0; i < NR_VM_EVENT_ITEMS; i++) + events[i] += per_cpu(memcg->vmstats_percpu->events[i], + cpu); + + for (mi = memcg; mi; mi = parent_mem_cgroup(mi)) + for (i = 0; i < NR_VM_EVENT_ITEMS; i++) + atomic_long_add(events[i], &mi->vmevents[i]); +} + +#ifdef CONFIG_MEMCG_KMEM +static int memcg_online_kmem(struct mem_cgroup *memcg) +{ + struct obj_cgroup *objcg; + int memcg_id; + + if (cgroup_memory_nokmem) + return 0; + + BUG_ON(memcg->kmemcg_id >= 0); + BUG_ON(memcg->kmem_state); + + memcg_id = memcg_alloc_cache_id(); + if (memcg_id < 0) + return memcg_id; + + objcg = obj_cgroup_alloc(); + if (!objcg) { + memcg_free_cache_id(memcg_id); + return -ENOMEM; + } + objcg->memcg = memcg; + rcu_assign_pointer(memcg->objcg, objcg); + + static_branch_enable(&memcg_kmem_enabled_key); + + /* + * A memory cgroup is considered kmem-online as soon as it gets + * kmemcg_id. Setting the id after enabling static branching will + * guarantee no one starts accounting before all call sites are + * patched. + */ + memcg->kmemcg_id = memcg_id; + memcg->kmem_state = KMEM_ONLINE; + + return 0; +} + +static void memcg_offline_kmem(struct mem_cgroup *memcg) +{ + struct cgroup_subsys_state *css; + struct mem_cgroup *parent, *child; + int kmemcg_id; + + if (memcg->kmem_state != KMEM_ONLINE) + return; + + memcg->kmem_state = KMEM_ALLOCATED; + + parent = parent_mem_cgroup(memcg); + if (!parent) + parent = root_mem_cgroup; + + memcg_reparent_objcgs(memcg, parent); + + kmemcg_id = memcg->kmemcg_id; + BUG_ON(kmemcg_id < 0); + + /* + * Change kmemcg_id of this cgroup and all its descendants to the + * parent's id, and then move all entries from this cgroup's list_lrus + * to ones of the parent. After we have finished, all list_lrus + * corresponding to this cgroup are guaranteed to remain empty. The + * ordering is imposed by list_lru_node->lock taken by + * memcg_drain_all_list_lrus(). + */ + rcu_read_lock(); /* can be called from css_free w/o cgroup_mutex */ + css_for_each_descendant_pre(css, &memcg->css) { + child = mem_cgroup_from_css(css); + BUG_ON(child->kmemcg_id != kmemcg_id); + child->kmemcg_id = parent->kmemcg_id; + if (!memcg->use_hierarchy) + break; + } + rcu_read_unlock(); + + memcg_drain_all_list_lrus(kmemcg_id, parent); + + memcg_free_cache_id(kmemcg_id); +} + +static void memcg_free_kmem(struct mem_cgroup *memcg) +{ + /* css_alloc() failed, offlining didn't happen */ + if (unlikely(memcg->kmem_state == KMEM_ONLINE)) + memcg_offline_kmem(memcg); +} +#else +static int memcg_online_kmem(struct mem_cgroup *memcg) +{ + return 0; +} +static void memcg_offline_kmem(struct mem_cgroup *memcg) +{ +} +static void memcg_free_kmem(struct mem_cgroup *memcg) +{ +} +#endif /* CONFIG_MEMCG_KMEM */ + +static int memcg_update_kmem_max(struct mem_cgroup *memcg, + unsigned long max) +{ + int ret; + + mutex_lock(&memcg_max_mutex); + ret = page_counter_set_max(&memcg->kmem, max); + mutex_unlock(&memcg_max_mutex); + return ret; +} + +static int memcg_update_tcp_max(struct mem_cgroup *memcg, unsigned long max) +{ + int ret; + + mutex_lock(&memcg_max_mutex); + + ret = page_counter_set_max(&memcg->tcpmem, max); + if (ret) + goto out; + + if (!memcg->tcpmem_active) { + /* + * The active flag needs to be written after the static_key + * update. This is what guarantees that the socket activation + * function is the last one to run. See mem_cgroup_sk_alloc() + * for details, and note that we don't mark any socket as + * belonging to this memcg until that flag is up. + * + * We need to do this, because static_keys will span multiple + * sites, but we can't control their order. If we mark a socket + * as accounted, but the accounting functions are not patched in + * yet, we'll lose accounting. + * + * We never race with the readers in mem_cgroup_sk_alloc(), + * because when this value change, the code to process it is not + * patched in yet. + */ + static_branch_inc(&memcg_sockets_enabled_key); + memcg->tcpmem_active = true; + } +out: + mutex_unlock(&memcg_max_mutex); + return ret; +} + +/* + * The user of this function is... + * RES_LIMIT. + */ +static ssize_t mem_cgroup_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + unsigned long nr_pages; + int ret; + + buf = strstrip(buf); + ret = page_counter_memparse(buf, "-1", &nr_pages); + if (ret) + return ret; + + switch (MEMFILE_ATTR(of_cft(of)->private)) { + case RES_LIMIT: + if (mem_cgroup_is_root(memcg)) { /* Can't set limit on root */ + ret = -EINVAL; + break; + } + switch (MEMFILE_TYPE(of_cft(of)->private)) { + case _MEM: + ret = mem_cgroup_resize_max(memcg, nr_pages, false); + break; + case _MEMSWAP: + ret = mem_cgroup_resize_max(memcg, nr_pages, true); + break; + case _KMEM: + pr_warn_once("kmem.limit_in_bytes is deprecated and will be removed. " + "Please report your usecase to linux-mm@kvack.org if you " + "depend on this functionality.\n"); + ret = memcg_update_kmem_max(memcg, nr_pages); + break; + case _TCP: + ret = memcg_update_tcp_max(memcg, nr_pages); + break; + } + break; + case RES_SOFT_LIMIT: + memcg->soft_limit = nr_pages; + ret = 0; + break; + } + return ret ?: nbytes; +} + +static ssize_t mem_cgroup_reset(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + struct page_counter *counter; + + switch (MEMFILE_TYPE(of_cft(of)->private)) { + case _MEM: + counter = &memcg->memory; + break; + case _MEMSWAP: + counter = &memcg->memsw; + break; + case _KMEM: + counter = &memcg->kmem; + break; + case _TCP: + counter = &memcg->tcpmem; + break; + default: + BUG(); + } + + switch (MEMFILE_ATTR(of_cft(of)->private)) { + case RES_MAX_USAGE: + page_counter_reset_watermark(counter); + break; + case RES_FAILCNT: + counter->failcnt = 0; + break; + default: + BUG(); + } + + return nbytes; +} + +static u64 mem_cgroup_move_charge_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return mem_cgroup_from_css(css)->move_charge_at_immigrate; +} + +#ifdef CONFIG_MMU +static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css, + struct cftype *cft, u64 val) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + + pr_warn_once("Cgroup memory moving (move_charge_at_immigrate) is deprecated. " + "Please report your usecase to linux-mm@kvack.org if you " + "depend on this functionality.\n"); + + if (val & ~MOVE_MASK) + return -EINVAL; + + /* + * No kind of locking is needed in here, because ->can_attach() will + * check this value once in the beginning of the process, and then carry + * on with stale data. This means that changes to this value will only + * affect task migrations starting after the change. + */ + memcg->move_charge_at_immigrate = val; + return 0; +} +#else +static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css, + struct cftype *cft, u64 val) +{ + return -ENOSYS; +} +#endif + +#ifdef CONFIG_NUMA + +#define LRU_ALL_FILE (BIT(LRU_INACTIVE_FILE) | BIT(LRU_ACTIVE_FILE)) +#define LRU_ALL_ANON (BIT(LRU_INACTIVE_ANON) | BIT(LRU_ACTIVE_ANON)) +#define LRU_ALL ((1 << NR_LRU_LISTS) - 1) + +static unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, + int nid, unsigned int lru_mask, bool tree) +{ + struct lruvec *lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(nid)); + unsigned long nr = 0; + enum lru_list lru; + + VM_BUG_ON((unsigned)nid >= nr_node_ids); + + for_each_lru(lru) { + if (!(BIT(lru) & lru_mask)) + continue; + if (tree) + nr += lruvec_page_state(lruvec, NR_LRU_BASE + lru); + else + nr += lruvec_page_state_local(lruvec, NR_LRU_BASE + lru); + } + return nr; +} + +static unsigned long mem_cgroup_nr_lru_pages(struct mem_cgroup *memcg, + unsigned int lru_mask, + bool tree) +{ + unsigned long nr = 0; + enum lru_list lru; + + for_each_lru(lru) { + if (!(BIT(lru) & lru_mask)) + continue; + if (tree) + nr += memcg_page_state(memcg, NR_LRU_BASE + lru); + else + nr += memcg_page_state_local(memcg, NR_LRU_BASE + lru); + } + return nr; +} + +static int memcg_numa_stat_show(struct seq_file *m, void *v) +{ + struct numa_stat { + const char *name; + unsigned int lru_mask; + }; + + static const struct numa_stat stats[] = { + { "total", LRU_ALL }, + { "file", LRU_ALL_FILE }, + { "anon", LRU_ALL_ANON }, + { "unevictable", BIT(LRU_UNEVICTABLE) }, + }; + const struct numa_stat *stat; + int nid; + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); + + for (stat = stats; stat < stats + ARRAY_SIZE(stats); stat++) { + seq_printf(m, "%s=%lu", stat->name, + mem_cgroup_nr_lru_pages(memcg, stat->lru_mask, + false)); + for_each_node_state(nid, N_MEMORY) + seq_printf(m, " N%d=%lu", nid, + mem_cgroup_node_nr_lru_pages(memcg, nid, + stat->lru_mask, false)); + seq_putc(m, '\n'); + } + + for (stat = stats; stat < stats + ARRAY_SIZE(stats); stat++) { + + seq_printf(m, "hierarchical_%s=%lu", stat->name, + mem_cgroup_nr_lru_pages(memcg, stat->lru_mask, + true)); + for_each_node_state(nid, N_MEMORY) + seq_printf(m, " N%d=%lu", nid, + mem_cgroup_node_nr_lru_pages(memcg, nid, + stat->lru_mask, true)); + seq_putc(m, '\n'); + } + + return 0; +} +#endif /* CONFIG_NUMA */ + +static const unsigned int memcg1_stats[] = { + NR_FILE_PAGES, + NR_ANON_MAPPED, +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + NR_ANON_THPS, +#endif + NR_SHMEM, + NR_FILE_MAPPED, + NR_FILE_DIRTY, + NR_WRITEBACK, + MEMCG_SWAP, +}; + +static const char *const memcg1_stat_names[] = { + "cache", + "rss", +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + "rss_huge", +#endif + "shmem", + "mapped_file", + "dirty", + "writeback", + "swap", +}; + +/* Universal VM events cgroup1 shows, original sort order */ +static const unsigned int memcg1_events[] = { + PGPGIN, + PGPGOUT, + PGFAULT, + PGMAJFAULT, +}; + +static int memcg_stat_show(struct seq_file *m, void *v) +{ + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); + unsigned long memory, memsw; + struct mem_cgroup *mi; + unsigned int i; + + BUILD_BUG_ON(ARRAY_SIZE(memcg1_stat_names) != ARRAY_SIZE(memcg1_stats)); + + for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) { + unsigned long nr; + + if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account()) + continue; + nr = memcg_page_state_local(memcg, memcg1_stats[i]); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (memcg1_stats[i] == NR_ANON_THPS) + nr *= HPAGE_PMD_NR; +#endif + seq_printf(m, "%s %lu\n", memcg1_stat_names[i], nr * PAGE_SIZE); + } + + for (i = 0; i < ARRAY_SIZE(memcg1_events); i++) + seq_printf(m, "%s %lu\n", vm_event_name(memcg1_events[i]), + memcg_events_local(memcg, memcg1_events[i])); + + for (i = 0; i < NR_LRU_LISTS; i++) + seq_printf(m, "%s %lu\n", lru_list_name(i), + memcg_page_state_local(memcg, NR_LRU_BASE + i) * + PAGE_SIZE); + + /* Hierarchical information */ + memory = memsw = PAGE_COUNTER_MAX; + for (mi = memcg; mi; mi = parent_mem_cgroup(mi)) { + memory = min(memory, READ_ONCE(mi->memory.max)); + memsw = min(memsw, READ_ONCE(mi->memsw.max)); + } + seq_printf(m, "hierarchical_memory_limit %llu\n", + (u64)memory * PAGE_SIZE); + if (do_memsw_account()) + seq_printf(m, "hierarchical_memsw_limit %llu\n", + (u64)memsw * PAGE_SIZE); + + for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) { + unsigned long nr; + + if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account()) + continue; + nr = memcg_page_state(memcg, memcg1_stats[i]); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (memcg1_stats[i] == NR_ANON_THPS) + nr *= HPAGE_PMD_NR; +#endif + seq_printf(m, "total_%s %llu\n", memcg1_stat_names[i], + (u64)nr * PAGE_SIZE); + } + + for (i = 0; i < ARRAY_SIZE(memcg1_events); i++) + seq_printf(m, "total_%s %llu\n", + vm_event_name(memcg1_events[i]), + (u64)memcg_events(memcg, memcg1_events[i])); + + for (i = 0; i < NR_LRU_LISTS; i++) + seq_printf(m, "total_%s %llu\n", lru_list_name(i), + (u64)memcg_page_state(memcg, NR_LRU_BASE + i) * + PAGE_SIZE); + +#ifdef CONFIG_DEBUG_VM + { + pg_data_t *pgdat; + struct mem_cgroup_per_node *mz; + unsigned long anon_cost = 0; + unsigned long file_cost = 0; + + for_each_online_pgdat(pgdat) { + mz = mem_cgroup_nodeinfo(memcg, pgdat->node_id); + + anon_cost += mz->lruvec.anon_cost; + file_cost += mz->lruvec.file_cost; + } + seq_printf(m, "anon_cost %lu\n", anon_cost); + seq_printf(m, "file_cost %lu\n", file_cost); + } +#endif + + return 0; +} + +static u64 mem_cgroup_swappiness_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + + return mem_cgroup_swappiness(memcg); +} + +static int mem_cgroup_swappiness_write(struct cgroup_subsys_state *css, + struct cftype *cft, u64 val) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + + if (val > 100) + return -EINVAL; + + if (css->parent) + memcg->swappiness = val; + else + vm_swappiness = val; + + return 0; +} + +static void __mem_cgroup_threshold(struct mem_cgroup *memcg, bool swap) +{ + struct mem_cgroup_threshold_ary *t; + unsigned long usage; + int i; + + rcu_read_lock(); + if (!swap) + t = rcu_dereference(memcg->thresholds.primary); + else + t = rcu_dereference(memcg->memsw_thresholds.primary); + + if (!t) + goto unlock; + + usage = mem_cgroup_usage(memcg, swap); + + /* + * current_threshold points to threshold just below or equal to usage. + * If it's not true, a threshold was crossed after last + * call of __mem_cgroup_threshold(). + */ + i = t->current_threshold; + + /* + * Iterate backward over array of thresholds starting from + * current_threshold and check if a threshold is crossed. + * If none of thresholds below usage is crossed, we read + * only one element of the array here. + */ + for (; i >= 0 && unlikely(t->entries[i].threshold > usage); i--) + eventfd_signal(t->entries[i].eventfd, 1); + + /* i = current_threshold + 1 */ + i++; + + /* + * Iterate forward over array of thresholds starting from + * current_threshold+1 and check if a threshold is crossed. + * If none of thresholds above usage is crossed, we read + * only one element of the array here. + */ + for (; i < t->size && unlikely(t->entries[i].threshold <= usage); i++) + eventfd_signal(t->entries[i].eventfd, 1); + + /* Update current_threshold */ + t->current_threshold = i - 1; +unlock: + rcu_read_unlock(); +} + +static void mem_cgroup_threshold(struct mem_cgroup *memcg) +{ + while (memcg) { + __mem_cgroup_threshold(memcg, false); + if (do_memsw_account()) + __mem_cgroup_threshold(memcg, true); + + memcg = parent_mem_cgroup(memcg); + } +} + +static int compare_thresholds(const void *a, const void *b) +{ + const struct mem_cgroup_threshold *_a = a; + const struct mem_cgroup_threshold *_b = b; + + if (_a->threshold > _b->threshold) + return 1; + + if (_a->threshold < _b->threshold) + return -1; + + return 0; +} + +static int mem_cgroup_oom_notify_cb(struct mem_cgroup *memcg) +{ + struct mem_cgroup_eventfd_list *ev; + + spin_lock(&memcg_oom_lock); + + list_for_each_entry(ev, &memcg->oom_notify, list) + eventfd_signal(ev->eventfd, 1); + + spin_unlock(&memcg_oom_lock); + return 0; +} + +static void mem_cgroup_oom_notify(struct mem_cgroup *memcg) +{ + struct mem_cgroup *iter; + + for_each_mem_cgroup_tree(iter, memcg) + mem_cgroup_oom_notify_cb(iter); +} + +static int __mem_cgroup_usage_register_event(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd, const char *args, enum res_type type) +{ + struct mem_cgroup_thresholds *thresholds; + struct mem_cgroup_threshold_ary *new; + unsigned long threshold; + unsigned long usage; + int i, size, ret; + + ret = page_counter_memparse(args, "-1", &threshold); + if (ret) + return ret; + + mutex_lock(&memcg->thresholds_lock); + + if (type == _MEM) { + thresholds = &memcg->thresholds; + usage = mem_cgroup_usage(memcg, false); + } else if (type == _MEMSWAP) { + thresholds = &memcg->memsw_thresholds; + usage = mem_cgroup_usage(memcg, true); + } else + BUG(); + + /* Check if a threshold crossed before adding a new one */ + if (thresholds->primary) + __mem_cgroup_threshold(memcg, type == _MEMSWAP); + + size = thresholds->primary ? thresholds->primary->size + 1 : 1; + + /* Allocate memory for new array of thresholds */ + new = kmalloc(struct_size(new, entries, size), GFP_KERNEL); + if (!new) { + ret = -ENOMEM; + goto unlock; + } + new->size = size; + + /* Copy thresholds (if any) to new array */ + if (thresholds->primary) + memcpy(new->entries, thresholds->primary->entries, + flex_array_size(new, entries, size - 1)); + + /* Add new threshold */ + new->entries[size - 1].eventfd = eventfd; + new->entries[size - 1].threshold = threshold; + + /* Sort thresholds. Registering of new threshold isn't time-critical */ + sort(new->entries, size, sizeof(*new->entries), + compare_thresholds, NULL); + + /* Find current threshold */ + new->current_threshold = -1; + for (i = 0; i < size; i++) { + if (new->entries[i].threshold <= usage) { + /* + * new->current_threshold will not be used until + * rcu_assign_pointer(), so it's safe to increment + * it here. + */ + ++new->current_threshold; + } else + break; + } + + /* Free old spare buffer and save old primary buffer as spare */ + kfree(thresholds->spare); + thresholds->spare = thresholds->primary; + + rcu_assign_pointer(thresholds->primary, new); + + /* To be sure that nobody uses thresholds */ + synchronize_rcu(); + +unlock: + mutex_unlock(&memcg->thresholds_lock); + + return ret; +} + +static int mem_cgroup_usage_register_event(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd, const char *args) +{ + return __mem_cgroup_usage_register_event(memcg, eventfd, args, _MEM); +} + +static int memsw_cgroup_usage_register_event(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd, const char *args) +{ + return __mem_cgroup_usage_register_event(memcg, eventfd, args, _MEMSWAP); +} + +static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd, enum res_type type) +{ + struct mem_cgroup_thresholds *thresholds; + struct mem_cgroup_threshold_ary *new; + unsigned long usage; + int i, j, size, entries; + + mutex_lock(&memcg->thresholds_lock); + + if (type == _MEM) { + thresholds = &memcg->thresholds; + usage = mem_cgroup_usage(memcg, false); + } else if (type == _MEMSWAP) { + thresholds = &memcg->memsw_thresholds; + usage = mem_cgroup_usage(memcg, true); + } else + BUG(); + + if (!thresholds->primary) + goto unlock; + + /* Check if a threshold crossed before removing */ + __mem_cgroup_threshold(memcg, type == _MEMSWAP); + + /* Calculate new number of threshold */ + size = entries = 0; + for (i = 0; i < thresholds->primary->size; i++) { + if (thresholds->primary->entries[i].eventfd != eventfd) + size++; + else + entries++; + } + + new = thresholds->spare; + + /* If no items related to eventfd have been cleared, nothing to do */ + if (!entries) + goto unlock; + + /* Set thresholds array to NULL if we don't have thresholds */ + if (!size) { + kfree(new); + new = NULL; + goto swap_buffers; + } + + new->size = size; + + /* Copy thresholds and find current threshold */ + new->current_threshold = -1; + for (i = 0, j = 0; i < thresholds->primary->size; i++) { + if (thresholds->primary->entries[i].eventfd == eventfd) + continue; + + new->entries[j] = thresholds->primary->entries[i]; + if (new->entries[j].threshold <= usage) { + /* + * new->current_threshold will not be used + * until rcu_assign_pointer(), so it's safe to increment + * it here. + */ + ++new->current_threshold; + } + j++; + } + +swap_buffers: + /* Swap primary and spare array */ + thresholds->spare = thresholds->primary; + + rcu_assign_pointer(thresholds->primary, new); + + /* To be sure that nobody uses thresholds */ + synchronize_rcu(); + + /* If all events are unregistered, free the spare array */ + if (!new) { + kfree(thresholds->spare); + thresholds->spare = NULL; + } +unlock: + mutex_unlock(&memcg->thresholds_lock); +} + +static void mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd) +{ + return __mem_cgroup_usage_unregister_event(memcg, eventfd, _MEM); +} + +static void memsw_cgroup_usage_unregister_event(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd) +{ + return __mem_cgroup_usage_unregister_event(memcg, eventfd, _MEMSWAP); +} + +static int mem_cgroup_oom_register_event(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd, const char *args) +{ + struct mem_cgroup_eventfd_list *event; + + event = kmalloc(sizeof(*event), GFP_KERNEL); + if (!event) + return -ENOMEM; + + spin_lock(&memcg_oom_lock); + + event->eventfd = eventfd; + list_add(&event->list, &memcg->oom_notify); + + /* already in OOM ? */ + if (memcg->under_oom) + eventfd_signal(eventfd, 1); + spin_unlock(&memcg_oom_lock); + + return 0; +} + +static void mem_cgroup_oom_unregister_event(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd) +{ + struct mem_cgroup_eventfd_list *ev, *tmp; + + spin_lock(&memcg_oom_lock); + + list_for_each_entry_safe(ev, tmp, &memcg->oom_notify, list) { + if (ev->eventfd == eventfd) { + list_del(&ev->list); + kfree(ev); + } + } + + spin_unlock(&memcg_oom_lock); +} + +static int mem_cgroup_oom_control_read(struct seq_file *sf, void *v) +{ + struct mem_cgroup *memcg = mem_cgroup_from_seq(sf); + + seq_printf(sf, "oom_kill_disable %d\n", memcg->oom_kill_disable); + seq_printf(sf, "under_oom %d\n", (bool)memcg->under_oom); + seq_printf(sf, "oom_kill %lu\n", + atomic_long_read(&memcg->memory_events[MEMCG_OOM_KILL])); + return 0; +} + +static int mem_cgroup_oom_control_write(struct cgroup_subsys_state *css, + struct cftype *cft, u64 val) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + + /* cannot set to root cgroup and only 0 and 1 are allowed */ + if (!css->parent || !((val == 0) || (val == 1))) + return -EINVAL; + + memcg->oom_kill_disable = val; + if (!val) + memcg_oom_recover(memcg); + + return 0; +} + +#ifdef CONFIG_CGROUP_WRITEBACK + +#include + +static int memcg_wb_domain_init(struct mem_cgroup *memcg, gfp_t gfp) +{ + return wb_domain_init(&memcg->cgwb_domain, gfp); +} + +static void memcg_wb_domain_exit(struct mem_cgroup *memcg) +{ + wb_domain_exit(&memcg->cgwb_domain); +} + +static void memcg_wb_domain_size_changed(struct mem_cgroup *memcg) +{ + wb_domain_size_changed(&memcg->cgwb_domain); +} + +struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css); + + if (!memcg->css.parent) + return NULL; + + return &memcg->cgwb_domain; +} + +/* + * idx can be of type enum memcg_stat_item or node_stat_item. + * Keep in sync with memcg_exact_page(). + */ +static unsigned long memcg_exact_page_state(struct mem_cgroup *memcg, int idx) +{ + long x = atomic_long_read(&memcg->vmstats[idx]); + int cpu; + + for_each_online_cpu(cpu) + x += per_cpu_ptr(memcg->vmstats_percpu, cpu)->stat[idx]; + if (x < 0) + x = 0; + return x; +} + +/** + * mem_cgroup_wb_stats - retrieve writeback related stats from its memcg + * @wb: bdi_writeback in question + * @pfilepages: out parameter for number of file pages + * @pheadroom: out parameter for number of allocatable pages according to memcg + * @pdirty: out parameter for number of dirty pages + * @pwriteback: out parameter for number of pages under writeback + * + * Determine the numbers of file, headroom, dirty, and writeback pages in + * @wb's memcg. File, dirty and writeback are self-explanatory. Headroom + * is a bit more involved. + * + * A memcg's headroom is "min(max, high) - used". In the hierarchy, the + * headroom is calculated as the lowest headroom of itself and the + * ancestors. Note that this doesn't consider the actual amount of + * available memory in the system. The caller should further cap + * *@pheadroom accordingly. + */ +void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, + unsigned long *pheadroom, unsigned long *pdirty, + unsigned long *pwriteback) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css); + struct mem_cgroup *parent; + + *pdirty = memcg_exact_page_state(memcg, NR_FILE_DIRTY); + + *pwriteback = memcg_exact_page_state(memcg, NR_WRITEBACK); + *pfilepages = memcg_exact_page_state(memcg, NR_INACTIVE_FILE) + + memcg_exact_page_state(memcg, NR_ACTIVE_FILE); + *pheadroom = PAGE_COUNTER_MAX; + + while ((parent = parent_mem_cgroup(memcg))) { + unsigned long ceiling = min(READ_ONCE(memcg->memory.max), + READ_ONCE(memcg->memory.high)); + unsigned long used = page_counter_read(&memcg->memory); + + *pheadroom = min(*pheadroom, ceiling - min(ceiling, used)); + memcg = parent; + } +} + +/* + * Foreign dirty flushing + * + * There's an inherent mismatch between memcg and writeback. The former + * trackes ownership per-page while the latter per-inode. This was a + * deliberate design decision because honoring per-page ownership in the + * writeback path is complicated, may lead to higher CPU and IO overheads + * and deemed unnecessary given that write-sharing an inode across + * different cgroups isn't a common use-case. + * + * Combined with inode majority-writer ownership switching, this works well + * enough in most cases but there are some pathological cases. For + * example, let's say there are two cgroups A and B which keep writing to + * different but confined parts of the same inode. B owns the inode and + * A's memory is limited far below B's. A's dirty ratio can rise enough to + * trigger balance_dirty_pages() sleeps but B's can be low enough to avoid + * triggering background writeback. A will be slowed down without a way to + * make writeback of the dirty pages happen. + * + * Conditions like the above can lead to a cgroup getting repatedly and + * severely throttled after making some progress after each + * dirty_expire_interval while the underyling IO device is almost + * completely idle. + * + * Solving this problem completely requires matching the ownership tracking + * granularities between memcg and writeback in either direction. However, + * the more egregious behaviors can be avoided by simply remembering the + * most recent foreign dirtying events and initiating remote flushes on + * them when local writeback isn't enough to keep the memory clean enough. + * + * The following two functions implement such mechanism. When a foreign + * page - a page whose memcg and writeback ownerships don't match - is + * dirtied, mem_cgroup_track_foreign_dirty() records the inode owning + * bdi_writeback on the page owning memcg. When balance_dirty_pages() + * decides that the memcg needs to sleep due to high dirty ratio, it calls + * mem_cgroup_flush_foreign() which queues writeback on the recorded + * foreign bdi_writebacks which haven't expired. Both the numbers of + * recorded bdi_writebacks and concurrent in-flight foreign writebacks are + * limited to MEMCG_CGWB_FRN_CNT. + * + * The mechanism only remembers IDs and doesn't hold any object references. + * As being wrong occasionally doesn't matter, updates and accesses to the + * records are lockless and racy. + */ +void mem_cgroup_track_foreign_dirty_slowpath(struct page *page, + struct bdi_writeback *wb) +{ + struct mem_cgroup *memcg = page->mem_cgroup; + struct memcg_cgwb_frn *frn; + u64 now = get_jiffies_64(); + u64 oldest_at = now; + int oldest = -1; + int i; + + trace_track_foreign_dirty(page, wb); + + /* + * Pick the slot to use. If there is already a slot for @wb, keep + * using it. If not replace the oldest one which isn't being + * written out. + */ + for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++) { + frn = &memcg->cgwb_frn[i]; + if (frn->bdi_id == wb->bdi->id && + frn->memcg_id == wb->memcg_css->id) + break; + if (time_before64(frn->at, oldest_at) && + atomic_read(&frn->done.cnt) == 1) { + oldest = i; + oldest_at = frn->at; + } + } + + if (i < MEMCG_CGWB_FRN_CNT) { + /* + * Re-using an existing one. Update timestamp lazily to + * avoid making the cacheline hot. We want them to be + * reasonably up-to-date and significantly shorter than + * dirty_expire_interval as that's what expires the record. + * Use the shorter of 1s and dirty_expire_interval / 8. + */ + unsigned long update_intv = + min_t(unsigned long, HZ, + msecs_to_jiffies(dirty_expire_interval * 10) / 8); + + if (time_before64(frn->at, now - update_intv)) + frn->at = now; + } else if (oldest >= 0) { + /* replace the oldest free one */ + frn = &memcg->cgwb_frn[oldest]; + frn->bdi_id = wb->bdi->id; + frn->memcg_id = wb->memcg_css->id; + frn->at = now; + } +} + +/* issue foreign writeback flushes for recorded foreign dirtying events */ +void mem_cgroup_flush_foreign(struct bdi_writeback *wb) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css); + unsigned long intv = msecs_to_jiffies(dirty_expire_interval * 10); + u64 now = jiffies_64; + int i; + + for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++) { + struct memcg_cgwb_frn *frn = &memcg->cgwb_frn[i]; + + /* + * If the record is older than dirty_expire_interval, + * writeback on it has already started. No need to kick it + * off again. Also, don't start a new one if there's + * already one in flight. + */ + if (time_after64(frn->at, now - intv) && + atomic_read(&frn->done.cnt) == 1) { + frn->at = 0; + trace_flush_foreign(wb, frn->bdi_id, frn->memcg_id); + cgroup_writeback_by_id(frn->bdi_id, frn->memcg_id, 0, + WB_REASON_FOREIGN_FLUSH, + &frn->done); + } + } +} + +#else /* CONFIG_CGROUP_WRITEBACK */ + +static int memcg_wb_domain_init(struct mem_cgroup *memcg, gfp_t gfp) +{ + return 0; +} + +static void memcg_wb_domain_exit(struct mem_cgroup *memcg) +{ +} + +static void memcg_wb_domain_size_changed(struct mem_cgroup *memcg) +{ +} + +#endif /* CONFIG_CGROUP_WRITEBACK */ + +/* + * DO NOT USE IN NEW FILES. + * + * "cgroup.event_control" implementation. + * + * This is way over-engineered. It tries to support fully configurable + * events for each user. Such level of flexibility is completely + * unnecessary especially in the light of the planned unified hierarchy. + * + * Please deprecate this and replace with something simpler if at all + * possible. + */ + +/* + * Unregister event and free resources. + * + * Gets called from workqueue. + */ +static void memcg_event_remove(struct work_struct *work) +{ + struct mem_cgroup_event *event = + container_of(work, struct mem_cgroup_event, remove); + struct mem_cgroup *memcg = event->memcg; + + remove_wait_queue(event->wqh, &event->wait); + + event->unregister_event(memcg, event->eventfd); + + /* Notify userspace the event is going away. */ + eventfd_signal(event->eventfd, 1); + + eventfd_ctx_put(event->eventfd); + kfree(event); + css_put(&memcg->css); +} + +/* + * Gets called on EPOLLHUP on eventfd when user closes it. + * + * Called with wqh->lock held and interrupts disabled. + */ +static int memcg_event_wake(wait_queue_entry_t *wait, unsigned mode, + int sync, void *key) +{ + struct mem_cgroup_event *event = + container_of(wait, struct mem_cgroup_event, wait); + struct mem_cgroup *memcg = event->memcg; + __poll_t flags = key_to_poll(key); + + if (flags & EPOLLHUP) { + /* + * If the event has been detached at cgroup removal, we + * can simply return knowing the other side will cleanup + * for us. + * + * We can't race against event freeing since the other + * side will require wqh->lock via remove_wait_queue(), + * which we hold. + */ + spin_lock(&memcg->event_list_lock); + if (!list_empty(&event->list)) { + list_del_init(&event->list); + /* + * We are in atomic context, but cgroup_event_remove() + * may sleep, so we have to call it in workqueue. + */ + schedule_work(&event->remove); + } + spin_unlock(&memcg->event_list_lock); + } + + return 0; +} + +static void memcg_event_ptable_queue_proc(struct file *file, + wait_queue_head_t *wqh, poll_table *pt) +{ + struct mem_cgroup_event *event = + container_of(pt, struct mem_cgroup_event, pt); + + event->wqh = wqh; + add_wait_queue(wqh, &event->wait); +} + +/* + * DO NOT USE IN NEW FILES. + * + * Parse input and register new cgroup event handler. + * + * Input must be in format ' '. + * Interpretation of args is defined by control file implementation. + */ +static ssize_t memcg_write_event_control(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct cgroup_subsys_state *css = of_css(of); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct mem_cgroup_event *event; + struct cgroup_subsys_state *cfile_css; + unsigned int efd, cfd; + struct fd efile; + struct fd cfile; + struct dentry *cdentry; + const char *name; + char *endp; + int ret; + + buf = strstrip(buf); + + efd = simple_strtoul(buf, &endp, 10); + if (*endp != ' ') + return -EINVAL; + buf = endp + 1; + + cfd = simple_strtoul(buf, &endp, 10); + if ((*endp != ' ') && (*endp != '\0')) + return -EINVAL; + buf = endp + 1; + + event = kzalloc(sizeof(*event), GFP_KERNEL); + if (!event) + return -ENOMEM; + + event->memcg = memcg; + INIT_LIST_HEAD(&event->list); + init_poll_funcptr(&event->pt, memcg_event_ptable_queue_proc); + init_waitqueue_func_entry(&event->wait, memcg_event_wake); + INIT_WORK(&event->remove, memcg_event_remove); + + efile = fdget(efd); + if (!efile.file) { + ret = -EBADF; + goto out_kfree; + } + + event->eventfd = eventfd_ctx_fileget(efile.file); + if (IS_ERR(event->eventfd)) { + ret = PTR_ERR(event->eventfd); + goto out_put_efile; + } + + cfile = fdget(cfd); + if (!cfile.file) { + ret = -EBADF; + goto out_put_eventfd; + } + + /* the process need read permission on control file */ + /* AV: shouldn't we check that it's been opened for read instead? */ + ret = inode_permission(file_inode(cfile.file), MAY_READ); + if (ret < 0) + goto out_put_cfile; + + /* + * The control file must be a regular cgroup1 file. As a regular cgroup + * file can't be renamed, it's safe to access its name afterwards. + */ + cdentry = cfile.file->f_path.dentry; + if (cdentry->d_sb->s_type != &cgroup_fs_type || !d_is_reg(cdentry)) { + ret = -EINVAL; + goto out_put_cfile; + } + + /* + * Determine the event callbacks and set them in @event. This used + * to be done via struct cftype but cgroup core no longer knows + * about these events. The following is crude but the whole thing + * is for compatibility anyway. + * + * DO NOT ADD NEW FILES. + */ + name = cdentry->d_name.name; + + if (!strcmp(name, "memory.usage_in_bytes")) { + event->register_event = mem_cgroup_usage_register_event; + event->unregister_event = mem_cgroup_usage_unregister_event; + } else if (!strcmp(name, "memory.oom_control")) { + event->register_event = mem_cgroup_oom_register_event; + event->unregister_event = mem_cgroup_oom_unregister_event; + } else if (!strcmp(name, "memory.pressure_level")) { + event->register_event = vmpressure_register_event; + event->unregister_event = vmpressure_unregister_event; + } else if (!strcmp(name, "memory.memsw.usage_in_bytes")) { + event->register_event = memsw_cgroup_usage_register_event; + event->unregister_event = memsw_cgroup_usage_unregister_event; + } else { + ret = -EINVAL; + goto out_put_cfile; + } + + /* + * Verify @cfile should belong to @css. Also, remaining events are + * automatically removed on cgroup destruction but the removal is + * asynchronous, so take an extra ref on @css. + */ + cfile_css = css_tryget_online_from_dir(cdentry->d_parent, + &memory_cgrp_subsys); + ret = -EINVAL; + if (IS_ERR(cfile_css)) + goto out_put_cfile; + if (cfile_css != css) { + css_put(cfile_css); + goto out_put_cfile; + } + + ret = event->register_event(memcg, event->eventfd, buf); + if (ret) + goto out_put_css; + + vfs_poll(efile.file, &event->pt); + + spin_lock(&memcg->event_list_lock); + list_add(&event->list, &memcg->event_list); + spin_unlock(&memcg->event_list_lock); + + fdput(cfile); + fdput(efile); + + return nbytes; + +out_put_css: + css_put(css); +out_put_cfile: + fdput(cfile); +out_put_eventfd: + eventfd_ctx_put(event->eventfd); +out_put_efile: + fdput(efile); +out_kfree: + kfree(event); + + return ret; +} + +static struct cftype mem_cgroup_legacy_files[] = { + { + .name = "usage_in_bytes", + .private = MEMFILE_PRIVATE(_MEM, RES_USAGE), + .read_u64 = mem_cgroup_read_u64, + }, + { + .name = "max_usage_in_bytes", + .private = MEMFILE_PRIVATE(_MEM, RES_MAX_USAGE), + .write = mem_cgroup_reset, + .read_u64 = mem_cgroup_read_u64, + }, + { + .name = "limit_in_bytes", + .private = MEMFILE_PRIVATE(_MEM, RES_LIMIT), + .write = mem_cgroup_write, + .read_u64 = mem_cgroup_read_u64, + }, + { + .name = "soft_limit_in_bytes", + .private = MEMFILE_PRIVATE(_MEM, RES_SOFT_LIMIT), + .write = mem_cgroup_write, + .read_u64 = mem_cgroup_read_u64, + }, + { + .name = "failcnt", + .private = MEMFILE_PRIVATE(_MEM, RES_FAILCNT), + .write = mem_cgroup_reset, + .read_u64 = mem_cgroup_read_u64, + }, + { + .name = "stat", + .seq_show = memcg_stat_show, + }, + { + .name = "force_empty", + .write = mem_cgroup_force_empty_write, + }, + { + .name = "use_hierarchy", + .write_u64 = mem_cgroup_hierarchy_write, + .read_u64 = mem_cgroup_hierarchy_read, + }, + { + .name = "cgroup.event_control", /* XXX: for compat */ + .write = memcg_write_event_control, + .flags = CFTYPE_NO_PREFIX | CFTYPE_WORLD_WRITABLE, + }, + { + .name = "swappiness", + .read_u64 = mem_cgroup_swappiness_read, + .write_u64 = mem_cgroup_swappiness_write, + }, + { + .name = "move_charge_at_immigrate", + .read_u64 = mem_cgroup_move_charge_read, + .write_u64 = mem_cgroup_move_charge_write, + }, + { + .name = "oom_control", + .seq_show = mem_cgroup_oom_control_read, + .write_u64 = mem_cgroup_oom_control_write, + .private = MEMFILE_PRIVATE(_OOM_TYPE, OOM_CONTROL), + }, + { + .name = "pressure_level", + }, +#ifdef CONFIG_NUMA + { + .name = "numa_stat", + .seq_show = memcg_numa_stat_show, + }, +#endif + { + .name = "kmem.limit_in_bytes", + .private = MEMFILE_PRIVATE(_KMEM, RES_LIMIT), + .write = mem_cgroup_write, + .read_u64 = mem_cgroup_read_u64, + }, + { + .name = "kmem.usage_in_bytes", + .private = MEMFILE_PRIVATE(_KMEM, RES_USAGE), + .read_u64 = mem_cgroup_read_u64, + }, + { + .name = "kmem.failcnt", + .private = MEMFILE_PRIVATE(_KMEM, RES_FAILCNT), + .write = mem_cgroup_reset, + .read_u64 = mem_cgroup_read_u64, + }, + { + .name = "kmem.max_usage_in_bytes", + .private = MEMFILE_PRIVATE(_KMEM, RES_MAX_USAGE), + .write = mem_cgroup_reset, + .read_u64 = mem_cgroup_read_u64, + }, +#if defined(CONFIG_MEMCG_KMEM) && \ + (defined(CONFIG_SLAB) || defined(CONFIG_SLUB_DEBUG)) + { + .name = "kmem.slabinfo", + .seq_show = memcg_slab_show, + }, +#endif + { + .name = "kmem.tcp.limit_in_bytes", + .private = MEMFILE_PRIVATE(_TCP, RES_LIMIT), + .write = mem_cgroup_write, + .read_u64 = mem_cgroup_read_u64, + }, + { + .name = "kmem.tcp.usage_in_bytes", + .private = MEMFILE_PRIVATE(_TCP, RES_USAGE), + .read_u64 = mem_cgroup_read_u64, + }, + { + .name = "kmem.tcp.failcnt", + .private = MEMFILE_PRIVATE(_TCP, RES_FAILCNT), + .write = mem_cgroup_reset, + .read_u64 = mem_cgroup_read_u64, + }, + { + .name = "kmem.tcp.max_usage_in_bytes", + .private = MEMFILE_PRIVATE(_TCP, RES_MAX_USAGE), + .write = mem_cgroup_reset, + .read_u64 = mem_cgroup_read_u64, + }, + { }, /* terminate */ +}; + +/* + * Private memory cgroup IDR + * + * Swap-out records and page cache shadow entries need to store memcg + * references in constrained space, so we maintain an ID space that is + * limited to 16 bit (MEM_CGROUP_ID_MAX), limiting the total number of + * memory-controlled cgroups to 64k. + * + * However, there usually are many references to the offline CSS after + * the cgroup has been destroyed, such as page cache or reclaimable + * slab objects, that don't need to hang on to the ID. We want to keep + * those dead CSS from occupying IDs, or we might quickly exhaust the + * relatively small ID space and prevent the creation of new cgroups + * even when there are much fewer than 64k cgroups - possibly none. + * + * Maintain a private 16-bit ID space for memcg, and allow the ID to + * be freed and recycled when it's no longer needed, which is usually + * when the CSS is offlined. + * + * The only exception to that are records of swapped out tmpfs/shmem + * pages that need to be attributed to live ancestors on swapin. But + * those references are manageable from userspace. + */ + +static DEFINE_IDR(mem_cgroup_idr); + +static void mem_cgroup_id_remove(struct mem_cgroup *memcg) +{ + if (memcg->id.id > 0) { + idr_remove(&mem_cgroup_idr, memcg->id.id); + memcg->id.id = 0; + } +} + +static void __maybe_unused mem_cgroup_id_get_many(struct mem_cgroup *memcg, + unsigned int n) +{ + refcount_add(n, &memcg->id.ref); +} + +static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n) +{ + if (refcount_sub_and_test(n, &memcg->id.ref)) { + mem_cgroup_id_remove(memcg); + + /* Memcg ID pins CSS */ + css_put(&memcg->css); + } +} + +static inline void mem_cgroup_id_put(struct mem_cgroup *memcg) +{ + mem_cgroup_id_put_many(memcg, 1); +} + +/** + * mem_cgroup_from_id - look up a memcg from a memcg id + * @id: the memcg id to look up + * + * Caller must hold rcu_read_lock(). + */ +struct mem_cgroup *mem_cgroup_from_id(unsigned short id) +{ + WARN_ON_ONCE(!rcu_read_lock_held()); + return idr_find(&mem_cgroup_idr, id); +} + +static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) +{ + struct mem_cgroup_per_node *pn; + int tmp = node; + /* + * This routine is called against possible nodes. + * But it's BUG to call kmalloc() against offline node. + * + * TODO: this routine can waste much memory for nodes which will + * never be onlined. It's better to use memory hotplug callback + * function. + */ + if (!node_state(node, N_NORMAL_MEMORY)) + tmp = -1; + pn = kzalloc_node(sizeof(*pn), GFP_KERNEL, tmp); + if (!pn) + return 1; + + pn->lruvec_stat_local = alloc_percpu_gfp(struct lruvec_stat, + GFP_KERNEL_ACCOUNT); + if (!pn->lruvec_stat_local) { + kfree(pn); + return 1; + } + + pn->lruvec_stat_cpu = alloc_percpu_gfp(struct lruvec_stat, + GFP_KERNEL_ACCOUNT); + if (!pn->lruvec_stat_cpu) { + free_percpu(pn->lruvec_stat_local); + kfree(pn); + return 1; + } + + lruvec_init(&pn->lruvec); + pn->usage_in_excess = 0; + pn->on_tree = false; + pn->memcg = memcg; + + memcg->nodeinfo[node] = pn; + return 0; +} + +static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) +{ + struct mem_cgroup_per_node *pn = memcg->nodeinfo[node]; + + if (!pn) + return; + + free_percpu(pn->lruvec_stat_cpu); + free_percpu(pn->lruvec_stat_local); + kfree(pn); +} + +static void __mem_cgroup_free(struct mem_cgroup *memcg) +{ + int node; + + for_each_node(node) + free_mem_cgroup_per_node_info(memcg, node); + free_percpu(memcg->vmstats_percpu); + free_percpu(memcg->vmstats_local); + kfree(memcg); +} + +static void mem_cgroup_free(struct mem_cgroup *memcg) +{ + memcg_wb_domain_exit(memcg); + /* + * Flush percpu vmstats and vmevents to guarantee the value correctness + * on parent's and all ancestor levels. + */ + memcg_flush_percpu_vmstats(memcg); + memcg_flush_percpu_vmevents(memcg); + __mem_cgroup_free(memcg); +} + +static struct mem_cgroup *mem_cgroup_alloc(void) +{ + struct mem_cgroup *memcg; + unsigned int size; + int node; + int __maybe_unused i; + long error = -ENOMEM; + + size = sizeof(struct mem_cgroup); + size += nr_node_ids * sizeof(struct mem_cgroup_per_node *); + + memcg = kzalloc(size, GFP_KERNEL); + if (!memcg) + return ERR_PTR(error); + + memcg->id.id = idr_alloc(&mem_cgroup_idr, NULL, + 1, MEM_CGROUP_ID_MAX, + GFP_KERNEL); + if (memcg->id.id < 0) { + error = memcg->id.id; + goto fail; + } + + memcg->vmstats_local = alloc_percpu_gfp(struct memcg_vmstats_percpu, + GFP_KERNEL_ACCOUNT); + if (!memcg->vmstats_local) + goto fail; + + memcg->vmstats_percpu = alloc_percpu_gfp(struct memcg_vmstats_percpu, + GFP_KERNEL_ACCOUNT); + if (!memcg->vmstats_percpu) + goto fail; + + for_each_node(node) + if (alloc_mem_cgroup_per_node_info(memcg, node)) + goto fail; + + if (memcg_wb_domain_init(memcg, GFP_KERNEL)) + goto fail; + + INIT_WORK(&memcg->high_work, high_work_func); + INIT_LIST_HEAD(&memcg->oom_notify); + mutex_init(&memcg->thresholds_lock); + spin_lock_init(&memcg->move_lock); + vmpressure_init(&memcg->vmpressure); + INIT_LIST_HEAD(&memcg->event_list); + spin_lock_init(&memcg->event_list_lock); + memcg->socket_pressure = jiffies; +#ifdef CONFIG_MEMCG_KMEM + memcg->kmemcg_id = -1; + INIT_LIST_HEAD(&memcg->objcg_list); +#endif +#ifdef CONFIG_CGROUP_WRITEBACK + INIT_LIST_HEAD(&memcg->cgwb_list); + for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++) + memcg->cgwb_frn[i].done = + __WB_COMPLETION_INIT(&memcg_cgwb_frn_waitq); +#endif +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + spin_lock_init(&memcg->deferred_split_queue.split_queue_lock); + INIT_LIST_HEAD(&memcg->deferred_split_queue.split_queue); + memcg->deferred_split_queue.split_queue_len = 0; +#endif + idr_replace(&mem_cgroup_idr, memcg, memcg->id.id); + return memcg; +fail: + mem_cgroup_id_remove(memcg); + __mem_cgroup_free(memcg); + return ERR_PTR(error); +} + +static struct cgroup_subsys_state * __ref +mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) +{ + struct mem_cgroup *parent = mem_cgroup_from_css(parent_css); + struct mem_cgroup *memcg, *old_memcg; + long error = -ENOMEM; + + old_memcg = set_active_memcg(parent); + memcg = mem_cgroup_alloc(); + set_active_memcg(old_memcg); + if (IS_ERR(memcg)) + return ERR_CAST(memcg); + + page_counter_set_high(&memcg->memory, PAGE_COUNTER_MAX); + memcg->soft_limit = PAGE_COUNTER_MAX; + page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX); + if (parent) { + memcg->swappiness = mem_cgroup_swappiness(parent); + memcg->oom_kill_disable = parent->oom_kill_disable; + } + if (!parent) { + page_counter_init(&memcg->memory, NULL); + page_counter_init(&memcg->swap, NULL); + page_counter_init(&memcg->kmem, NULL); + page_counter_init(&memcg->tcpmem, NULL); + } else if (parent->use_hierarchy) { + memcg->use_hierarchy = true; + page_counter_init(&memcg->memory, &parent->memory); + page_counter_init(&memcg->swap, &parent->swap); + page_counter_init(&memcg->kmem, &parent->kmem); + page_counter_init(&memcg->tcpmem, &parent->tcpmem); + } else { + page_counter_init(&memcg->memory, &root_mem_cgroup->memory); + page_counter_init(&memcg->swap, &root_mem_cgroup->swap); + page_counter_init(&memcg->kmem, &root_mem_cgroup->kmem); + page_counter_init(&memcg->tcpmem, &root_mem_cgroup->tcpmem); + /* + * Deeper hierachy with use_hierarchy == false doesn't make + * much sense so let cgroup subsystem know about this + * unfortunate state in our controller. + */ + if (parent != root_mem_cgroup) + memory_cgrp_subsys.broken_hierarchy = true; + } + + /* The following stuff does not apply to the root */ + if (!parent) { + root_mem_cgroup = memcg; + return &memcg->css; + } + + error = memcg_online_kmem(memcg); + if (error) + goto fail; + + if (cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_nosocket) + static_branch_inc(&memcg_sockets_enabled_key); + + return &memcg->css; +fail: + mem_cgroup_id_remove(memcg); + mem_cgroup_free(memcg); + return ERR_PTR(error); +} + +static int mem_cgroup_css_online(struct cgroup_subsys_state *css) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + + /* + * A memcg must be visible for memcg_expand_shrinker_maps() + * by the time the maps are allocated. So, we allocate maps + * here, when for_each_mem_cgroup() can't skip it. + */ + if (memcg_alloc_shrinker_maps(memcg)) { + mem_cgroup_id_remove(memcg); + return -ENOMEM; + } + + /* Online state pins memcg ID, memcg ID pins CSS */ + refcount_set(&memcg->id.ref, 1); + css_get(css); + return 0; +} + +static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct mem_cgroup_event *event, *tmp; + + /* + * Unregister events and notify userspace. + * Notify userspace about cgroup removing only after rmdir of cgroup + * directory to avoid race between userspace and kernelspace. + */ + spin_lock(&memcg->event_list_lock); + list_for_each_entry_safe(event, tmp, &memcg->event_list, list) { + list_del_init(&event->list); + schedule_work(&event->remove); + } + spin_unlock(&memcg->event_list_lock); + + page_counter_set_min(&memcg->memory, 0); + page_counter_set_low(&memcg->memory, 0); + + memcg_offline_kmem(memcg); + wb_memcg_offline(memcg); + + drain_all_stock(memcg); + + mem_cgroup_id_put(memcg); +} + +static void mem_cgroup_css_released(struct cgroup_subsys_state *css) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + + invalidate_reclaim_iterators(memcg); +} + +static void mem_cgroup_css_free(struct cgroup_subsys_state *css) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + int __maybe_unused i; + +#ifdef CONFIG_CGROUP_WRITEBACK + for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++) + wb_wait_for_completion(&memcg->cgwb_frn[i].done); +#endif + if (cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_nosocket) + static_branch_dec(&memcg_sockets_enabled_key); + + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_active) + static_branch_dec(&memcg_sockets_enabled_key); + + vmpressure_cleanup(&memcg->vmpressure); + cancel_work_sync(&memcg->high_work); + mem_cgroup_remove_from_trees(memcg); + memcg_free_shrinker_maps(memcg); + memcg_free_kmem(memcg); + mem_cgroup_free(memcg); +} + +/** + * mem_cgroup_css_reset - reset the states of a mem_cgroup + * @css: the target css + * + * Reset the states of the mem_cgroup associated with @css. This is + * invoked when the userland requests disabling on the default hierarchy + * but the memcg is pinned through dependency. The memcg should stop + * applying policies and should revert to the vanilla state as it may be + * made visible again. + * + * The current implementation only resets the essential configurations. + * This needs to be expanded to cover all the visible parts. + */ +static void mem_cgroup_css_reset(struct cgroup_subsys_state *css) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + + page_counter_set_max(&memcg->memory, PAGE_COUNTER_MAX); + page_counter_set_max(&memcg->swap, PAGE_COUNTER_MAX); + page_counter_set_max(&memcg->kmem, PAGE_COUNTER_MAX); + page_counter_set_max(&memcg->tcpmem, PAGE_COUNTER_MAX); + page_counter_set_min(&memcg->memory, 0); + page_counter_set_low(&memcg->memory, 0); + page_counter_set_high(&memcg->memory, PAGE_COUNTER_MAX); + memcg->soft_limit = PAGE_COUNTER_MAX; + page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX); + memcg_wb_domain_size_changed(memcg); +} + +#ifdef CONFIG_MMU +/* Handlers for move charge at task migration. */ +static int mem_cgroup_do_precharge(unsigned long count) +{ + int ret; + + /* Try a single bulk charge without reclaim first, kswapd may wake */ + ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_DIRECT_RECLAIM, count); + if (!ret) { + mc.precharge += count; + return ret; + } + + /* Try charges one by one with reclaim, but do not retry */ + while (count--) { + ret = try_charge(mc.to, GFP_KERNEL | __GFP_NORETRY, 1); + if (ret) + return ret; + mc.precharge++; + cond_resched(); + } + return 0; +} + +union mc_target { + struct page *page; + swp_entry_t ent; +}; + +enum mc_target_type { + MC_TARGET_NONE = 0, + MC_TARGET_PAGE, + MC_TARGET_SWAP, + MC_TARGET_DEVICE, +}; + +static struct page *mc_handle_present_pte(struct vm_area_struct *vma, + unsigned long addr, pte_t ptent) +{ + struct page *page = vm_normal_page(vma, addr, ptent); + + if (!page || !page_mapped(page)) + return NULL; + if (PageAnon(page)) { + if (!(mc.flags & MOVE_ANON)) + return NULL; + } else { + if (!(mc.flags & MOVE_FILE)) + return NULL; + } + if (!get_page_unless_zero(page)) + return NULL; + + return page; +} + +#if defined(CONFIG_SWAP) || defined(CONFIG_DEVICE_PRIVATE) +static struct page *mc_handle_swap_pte(struct vm_area_struct *vma, + pte_t ptent, swp_entry_t *entry) +{ + struct page *page = NULL; + swp_entry_t ent = pte_to_swp_entry(ptent); + + if (!(mc.flags & MOVE_ANON)) + return NULL; + + /* + * Handle MEMORY_DEVICE_PRIVATE which are ZONE_DEVICE page belonging to + * a device and because they are not accessible by CPU they are store + * as special swap entry in the CPU page table. + */ + if (is_device_private_entry(ent)) { + page = device_private_entry_to_page(ent); + /* + * MEMORY_DEVICE_PRIVATE means ZONE_DEVICE page and which have + * a refcount of 1 when free (unlike normal page) + */ + if (!page_ref_add_unless(page, 1, 1)) + return NULL; + return page; + } + + if (non_swap_entry(ent)) + return NULL; + + /* + * Because lookup_swap_cache() updates some statistics counter, + * we call find_get_page() with swapper_space directly. + */ + page = find_get_page(swap_address_space(ent), swp_offset(ent)); + entry->val = ent.val; + + return page; +} +#else +static struct page *mc_handle_swap_pte(struct vm_area_struct *vma, + pte_t ptent, swp_entry_t *entry) +{ + return NULL; +} +#endif + +static struct page *mc_handle_file_pte(struct vm_area_struct *vma, + unsigned long addr, pte_t ptent, swp_entry_t *entry) +{ + if (!vma->vm_file) /* anonymous vma */ + return NULL; + if (!(mc.flags & MOVE_FILE)) + return NULL; + + /* page is moved even if it's not RSS of this task(page-faulted). */ + /* shmem/tmpfs may report page out on swap: account for that too. */ + return find_get_incore_page(vma->vm_file->f_mapping, + linear_page_index(vma, addr)); +} + +/** + * mem_cgroup_move_account - move account of the page + * @page: the page + * @compound: charge the page as compound or small page + * @from: mem_cgroup which the page is moved from. + * @to: mem_cgroup which the page is moved to. @from != @to. + * + * The caller must make sure the page is not on LRU (isolate_page() is useful.) + * + * This function doesn't do "charge" to new cgroup and doesn't do "uncharge" + * from old cgroup. + */ +static int mem_cgroup_move_account(struct page *page, + bool compound, + struct mem_cgroup *from, + struct mem_cgroup *to) +{ + struct lruvec *from_vec, *to_vec; + struct pglist_data *pgdat; + unsigned int nr_pages = compound ? thp_nr_pages(page) : 1; + int ret; + + VM_BUG_ON(from == to); + VM_BUG_ON_PAGE(PageLRU(page), page); + VM_BUG_ON(compound && !PageTransHuge(page)); + + /* + * Prevent mem_cgroup_migrate() from looking at + * page->mem_cgroup of its source page while we change it. + */ + ret = -EBUSY; + if (!trylock_page(page)) + goto out; + + ret = -EINVAL; + if (page->mem_cgroup != from) + goto out_unlock; + + pgdat = page_pgdat(page); + from_vec = mem_cgroup_lruvec(from, pgdat); + to_vec = mem_cgroup_lruvec(to, pgdat); + + lock_page_memcg(page); + + if (PageAnon(page)) { + if (page_mapped(page)) { + __mod_lruvec_state(from_vec, NR_ANON_MAPPED, -nr_pages); + __mod_lruvec_state(to_vec, NR_ANON_MAPPED, nr_pages); + if (PageTransHuge(page)) { + __dec_lruvec_state(from_vec, NR_ANON_THPS); + __inc_lruvec_state(to_vec, NR_ANON_THPS); + } + + } + } else { + __mod_lruvec_state(from_vec, NR_FILE_PAGES, -nr_pages); + __mod_lruvec_state(to_vec, NR_FILE_PAGES, nr_pages); + + if (PageSwapBacked(page)) { + __mod_lruvec_state(from_vec, NR_SHMEM, -nr_pages); + __mod_lruvec_state(to_vec, NR_SHMEM, nr_pages); + } + + if (page_mapped(page)) { + __mod_lruvec_state(from_vec, NR_FILE_MAPPED, -nr_pages); + __mod_lruvec_state(to_vec, NR_FILE_MAPPED, nr_pages); + } + + if (PageDirty(page)) { + struct address_space *mapping = page_mapping(page); + + if (mapping_can_writeback(mapping)) { + __mod_lruvec_state(from_vec, NR_FILE_DIRTY, + -nr_pages); + __mod_lruvec_state(to_vec, NR_FILE_DIRTY, + nr_pages); + } + } + } + + if (PageWriteback(page)) { + __mod_lruvec_state(from_vec, NR_WRITEBACK, -nr_pages); + __mod_lruvec_state(to_vec, NR_WRITEBACK, nr_pages); + } + + /* + * All state has been migrated, let's switch to the new memcg. + * + * It is safe to change page->mem_cgroup here because the page + * is referenced, charged, isolated, and locked: we can't race + * with (un)charging, migration, LRU putback, or anything else + * that would rely on a stable page->mem_cgroup. + * + * Note that lock_page_memcg is a memcg lock, not a page lock, + * to save space. As soon as we switch page->mem_cgroup to a + * new memcg that isn't locked, the above state can change + * concurrently again. Make sure we're truly done with it. + */ + smp_mb(); + + css_get(&to->css); + css_put(&from->css); + + page->mem_cgroup = to; + + __unlock_page_memcg(from); + + ret = 0; + + local_irq_disable(); + mem_cgroup_charge_statistics(to, page, nr_pages); + memcg_check_events(to, page); + mem_cgroup_charge_statistics(from, page, -nr_pages); + memcg_check_events(from, page); + local_irq_enable(); +out_unlock: + unlock_page(page); +out: + return ret; +} + +/** + * get_mctgt_type - get target type of moving charge + * @vma: the vma the pte to be checked belongs + * @addr: the address corresponding to the pte to be checked + * @ptent: the pte to be checked + * @target: the pointer the target page or swap ent will be stored(can be NULL) + * + * Returns + * 0(MC_TARGET_NONE): if the pte is not a target for move charge. + * 1(MC_TARGET_PAGE): if the page corresponding to this pte is a target for + * move charge. if @target is not NULL, the page is stored in target->page + * with extra refcnt got(Callers should handle it). + * 2(MC_TARGET_SWAP): if the swap entry corresponding to this pte is a + * target for charge migration. if @target is not NULL, the entry is stored + * in target->ent. + * 3(MC_TARGET_DEVICE): like MC_TARGET_PAGE but page is MEMORY_DEVICE_PRIVATE + * (so ZONE_DEVICE page and thus not on the lru). + * For now we such page is charge like a regular page would be as for all + * intent and purposes it is just special memory taking the place of a + * regular page. + * + * See Documentations/vm/hmm.txt and include/linux/hmm.h + * + * Called with pte lock held. + */ + +static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma, + unsigned long addr, pte_t ptent, union mc_target *target) +{ + struct page *page = NULL; + enum mc_target_type ret = MC_TARGET_NONE; + swp_entry_t ent = { .val = 0 }; + + if (pte_present(ptent)) + page = mc_handle_present_pte(vma, addr, ptent); + else if (is_swap_pte(ptent)) + page = mc_handle_swap_pte(vma, ptent, &ent); + else if (pte_none(ptent)) + page = mc_handle_file_pte(vma, addr, ptent, &ent); + + if (!page && !ent.val) + return ret; + if (page) { + /* + * Do only loose check w/o serialization. + * mem_cgroup_move_account() checks the page is valid or + * not under LRU exclusion. + */ + if (page->mem_cgroup == mc.from) { + ret = MC_TARGET_PAGE; + if (is_device_private_page(page)) + ret = MC_TARGET_DEVICE; + if (target) + target->page = page; + } + if (!ret || !target) + put_page(page); + } + /* + * There is a swap entry and a page doesn't exist or isn't charged. + * But we cannot move a tail-page in a THP. + */ + if (ent.val && !ret && (!page || !PageTransCompound(page)) && + mem_cgroup_id(mc.from) == lookup_swap_cgroup_id(ent)) { + ret = MC_TARGET_SWAP; + if (target) + target->ent = ent; + } + return ret; +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +/* + * We don't consider PMD mapped swapping or file mapped pages because THP does + * not support them for now. + * Caller should make sure that pmd_trans_huge(pmd) is true. + */ +static enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma, + unsigned long addr, pmd_t pmd, union mc_target *target) +{ + struct page *page = NULL; + enum mc_target_type ret = MC_TARGET_NONE; + + if (unlikely(is_swap_pmd(pmd))) { + VM_BUG_ON(thp_migration_supported() && + !is_pmd_migration_entry(pmd)); + return ret; + } + page = pmd_page(pmd); + VM_BUG_ON_PAGE(!page || !PageHead(page), page); + if (!(mc.flags & MOVE_ANON)) + return ret; + if (page->mem_cgroup == mc.from) { + ret = MC_TARGET_PAGE; + if (target) { + get_page(page); + target->page = page; + } + } + return ret; +} +#else +static inline enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma, + unsigned long addr, pmd_t pmd, union mc_target *target) +{ + return MC_TARGET_NONE; +} +#endif + +static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd, + unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + struct vm_area_struct *vma = walk->vma; + pte_t *pte; + spinlock_t *ptl; + + ptl = pmd_trans_huge_lock(pmd, vma); + if (ptl) { + /* + * Note their can not be MC_TARGET_DEVICE for now as we do not + * support transparent huge page with MEMORY_DEVICE_PRIVATE but + * this might change. + */ + if (get_mctgt_type_thp(vma, addr, *pmd, NULL) == MC_TARGET_PAGE) + mc.precharge += HPAGE_PMD_NR; + spin_unlock(ptl); + return 0; + } + + if (pmd_trans_unstable(pmd)) + return 0; + pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); + for (; addr != end; pte++, addr += PAGE_SIZE) + if (get_mctgt_type(vma, addr, *pte, NULL)) + mc.precharge++; /* increment precharge temporarily */ + pte_unmap_unlock(pte - 1, ptl); + cond_resched(); + + return 0; +} + +static const struct mm_walk_ops precharge_walk_ops = { + .pmd_entry = mem_cgroup_count_precharge_pte_range, +}; + +static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm) +{ + unsigned long precharge; + + mmap_read_lock(mm); + walk_page_range(mm, 0, mm->highest_vm_end, &precharge_walk_ops, NULL); + mmap_read_unlock(mm); + + precharge = mc.precharge; + mc.precharge = 0; + + return precharge; +} + +static int mem_cgroup_precharge_mc(struct mm_struct *mm) +{ + unsigned long precharge = mem_cgroup_count_precharge(mm); + + VM_BUG_ON(mc.moving_task); + mc.moving_task = current; + return mem_cgroup_do_precharge(precharge); +} + +/* cancels all extra charges on mc.from and mc.to, and wakes up all waiters. */ +static void __mem_cgroup_clear_mc(void) +{ + struct mem_cgroup *from = mc.from; + struct mem_cgroup *to = mc.to; + + /* we must uncharge all the leftover precharges from mc.to */ + if (mc.precharge) { + cancel_charge(mc.to, mc.precharge); + mc.precharge = 0; + } + /* + * we didn't uncharge from mc.from at mem_cgroup_move_account(), so + * we must uncharge here. + */ + if (mc.moved_charge) { + cancel_charge(mc.from, mc.moved_charge); + mc.moved_charge = 0; + } + /* we must fixup refcnts and charges */ + if (mc.moved_swap) { + /* uncharge swap account from the old cgroup */ + if (!mem_cgroup_is_root(mc.from)) + page_counter_uncharge(&mc.from->memsw, mc.moved_swap); + + mem_cgroup_id_put_many(mc.from, mc.moved_swap); + + /* + * we charged both to->memory and to->memsw, so we + * should uncharge to->memory. + */ + if (!mem_cgroup_is_root(mc.to)) + page_counter_uncharge(&mc.to->memory, mc.moved_swap); + + mc.moved_swap = 0; + } + memcg_oom_recover(from); + memcg_oom_recover(to); + wake_up_all(&mc.waitq); +} + +static void mem_cgroup_clear_mc(void) +{ + struct mm_struct *mm = mc.mm; + + /* + * we must clear moving_task before waking up waiters at the end of + * task migration. + */ + mc.moving_task = NULL; + __mem_cgroup_clear_mc(); + spin_lock(&mc.lock); + mc.from = NULL; + mc.to = NULL; + mc.mm = NULL; + spin_unlock(&mc.lock); + + mmput(mm); +} + +static int mem_cgroup_can_attach(struct cgroup_taskset *tset) +{ + struct cgroup_subsys_state *css; + struct mem_cgroup *memcg = NULL; /* unneeded init to make gcc happy */ + struct mem_cgroup *from; + struct task_struct *leader, *p; + struct mm_struct *mm; + unsigned long move_flags; + int ret = 0; + + /* charge immigration isn't supported on the default hierarchy */ + if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) + return 0; + + /* + * Multi-process migrations only happen on the default hierarchy + * where charge immigration is not used. Perform charge + * immigration if @tset contains a leader and whine if there are + * multiple. + */ + p = NULL; + cgroup_taskset_for_each_leader(leader, css, tset) { + WARN_ON_ONCE(p); + p = leader; + memcg = mem_cgroup_from_css(css); + } + if (!p) + return 0; + + /* + * We are now commited to this value whatever it is. Changes in this + * tunable will only affect upcoming migrations, not the current one. + * So we need to save it, and keep it going. + */ + move_flags = READ_ONCE(memcg->move_charge_at_immigrate); + if (!move_flags) + return 0; + + from = mem_cgroup_from_task(p); + + VM_BUG_ON(from == memcg); + + mm = get_task_mm(p); + if (!mm) + return 0; + /* We move charges only when we move a owner of the mm */ + if (mm->owner == p) { + VM_BUG_ON(mc.from); + VM_BUG_ON(mc.to); + VM_BUG_ON(mc.precharge); + VM_BUG_ON(mc.moved_charge); + VM_BUG_ON(mc.moved_swap); + + spin_lock(&mc.lock); + mc.mm = mm; + mc.from = from; + mc.to = memcg; + mc.flags = move_flags; + spin_unlock(&mc.lock); + /* We set mc.moving_task later */ + + ret = mem_cgroup_precharge_mc(mm); + if (ret) + mem_cgroup_clear_mc(); + } else { + mmput(mm); + } + return ret; +} + +static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset) +{ + if (mc.to) + mem_cgroup_clear_mc(); +} + +static int mem_cgroup_move_charge_pte_range(pmd_t *pmd, + unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + int ret = 0; + struct vm_area_struct *vma = walk->vma; + pte_t *pte; + spinlock_t *ptl; + enum mc_target_type target_type; + union mc_target target; + struct page *page; + + ptl = pmd_trans_huge_lock(pmd, vma); + if (ptl) { + if (mc.precharge < HPAGE_PMD_NR) { + spin_unlock(ptl); + return 0; + } + target_type = get_mctgt_type_thp(vma, addr, *pmd, &target); + if (target_type == MC_TARGET_PAGE) { + page = target.page; + if (!isolate_lru_page(page)) { + if (!mem_cgroup_move_account(page, true, + mc.from, mc.to)) { + mc.precharge -= HPAGE_PMD_NR; + mc.moved_charge += HPAGE_PMD_NR; + } + putback_lru_page(page); + } + put_page(page); + } else if (target_type == MC_TARGET_DEVICE) { + page = target.page; + if (!mem_cgroup_move_account(page, true, + mc.from, mc.to)) { + mc.precharge -= HPAGE_PMD_NR; + mc.moved_charge += HPAGE_PMD_NR; + } + put_page(page); + } + spin_unlock(ptl); + return 0; + } + + if (pmd_trans_unstable(pmd)) + return 0; +retry: + pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); + for (; addr != end; addr += PAGE_SIZE) { + pte_t ptent = *(pte++); + bool device = false; + swp_entry_t ent; + + if (!mc.precharge) + break; + + switch (get_mctgt_type(vma, addr, ptent, &target)) { + case MC_TARGET_DEVICE: + device = true; + fallthrough; + case MC_TARGET_PAGE: + page = target.page; + /* + * We can have a part of the split pmd here. Moving it + * can be done but it would be too convoluted so simply + * ignore such a partial THP and keep it in original + * memcg. There should be somebody mapping the head. + */ + if (PageTransCompound(page)) + goto put; + if (!device && isolate_lru_page(page)) + goto put; + if (!mem_cgroup_move_account(page, false, + mc.from, mc.to)) { + mc.precharge--; + /* we uncharge from mc.from later. */ + mc.moved_charge++; + } + if (!device) + putback_lru_page(page); +put: /* get_mctgt_type() gets the page */ + put_page(page); + break; + case MC_TARGET_SWAP: + ent = target.ent; + if (!mem_cgroup_move_swap_account(ent, mc.from, mc.to)) { + mc.precharge--; + mem_cgroup_id_get_many(mc.to, 1); + /* we fixup other refcnts and charges later. */ + mc.moved_swap++; + } + break; + default: + break; + } + } + pte_unmap_unlock(pte - 1, ptl); + cond_resched(); + + if (addr != end) { + /* + * We have consumed all precharges we got in can_attach(). + * We try charge one by one, but don't do any additional + * charges to mc.to if we have failed in charge once in attach() + * phase. + */ + ret = mem_cgroup_do_precharge(1); + if (!ret) + goto retry; + } + + return ret; +} + +static const struct mm_walk_ops charge_walk_ops = { + .pmd_entry = mem_cgroup_move_charge_pte_range, +}; + +static void mem_cgroup_move_charge(void) +{ + lru_add_drain_all(); + /* + * Signal lock_page_memcg() to take the memcg's move_lock + * while we're moving its pages to another memcg. Then wait + * for already started RCU-only updates to finish. + */ + atomic_inc(&mc.from->moving_account); + synchronize_rcu(); +retry: + if (unlikely(!mmap_read_trylock(mc.mm))) { + /* + * Someone who are holding the mmap_lock might be waiting in + * waitq. So we cancel all extra charges, wake up all waiters, + * and retry. Because we cancel precharges, we might not be able + * to move enough charges, but moving charge is a best-effort + * feature anyway, so it wouldn't be a big problem. + */ + __mem_cgroup_clear_mc(); + cond_resched(); + goto retry; + } + /* + * When we have consumed all precharges and failed in doing + * additional charge, the page walk just aborts. + */ + walk_page_range(mc.mm, 0, mc.mm->highest_vm_end, &charge_walk_ops, + NULL); + + mmap_read_unlock(mc.mm); + atomic_dec(&mc.from->moving_account); +} + +static void mem_cgroup_move_task(void) +{ + if (mc.to) { + mem_cgroup_move_charge(); + mem_cgroup_clear_mc(); + } +} +#else /* !CONFIG_MMU */ +static int mem_cgroup_can_attach(struct cgroup_taskset *tset) +{ + return 0; +} +static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset) +{ +} +static void mem_cgroup_move_task(void) +{ +} +#endif + +/* + * Cgroup retains root cgroups across [un]mount cycles making it necessary + * to verify whether we're attached to the default hierarchy on each mount + * attempt. + */ +static void mem_cgroup_bind(struct cgroup_subsys_state *root_css) +{ + /* + * use_hierarchy is forced on the default hierarchy. cgroup core + * guarantees that @root doesn't have any children, so turning it + * on for the root memcg is enough. + */ + if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) + root_mem_cgroup->use_hierarchy = true; + else + root_mem_cgroup->use_hierarchy = false; +} + +static int seq_puts_memcg_tunable(struct seq_file *m, unsigned long value) +{ + if (value == PAGE_COUNTER_MAX) + seq_puts(m, "max\n"); + else + seq_printf(m, "%llu\n", (u64)value * PAGE_SIZE); + + return 0; +} + +static u64 memory_current_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + + return (u64)page_counter_read(&memcg->memory) * PAGE_SIZE; +} + +static int memory_min_show(struct seq_file *m, void *v) +{ + return seq_puts_memcg_tunable(m, + READ_ONCE(mem_cgroup_from_seq(m)->memory.min)); +} + +static ssize_t memory_min_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + unsigned long min; + int err; + + buf = strstrip(buf); + err = page_counter_memparse(buf, "max", &min); + if (err) + return err; + + page_counter_set_min(&memcg->memory, min); + + return nbytes; +} + +static int memory_low_show(struct seq_file *m, void *v) +{ + return seq_puts_memcg_tunable(m, + READ_ONCE(mem_cgroup_from_seq(m)->memory.low)); +} + +static ssize_t memory_low_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + unsigned long low; + int err; + + buf = strstrip(buf); + err = page_counter_memparse(buf, "max", &low); + if (err) + return err; + + page_counter_set_low(&memcg->memory, low); + + return nbytes; +} + +static int memory_high_show(struct seq_file *m, void *v) +{ + return seq_puts_memcg_tunable(m, + READ_ONCE(mem_cgroup_from_seq(m)->memory.high)); +} + +static ssize_t memory_high_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + unsigned int nr_retries = MAX_RECLAIM_RETRIES; + bool drained = false; + unsigned long high; + int err; + + buf = strstrip(buf); + err = page_counter_memparse(buf, "max", &high); + if (err) + return err; + + page_counter_set_high(&memcg->memory, high); + + for (;;) { + unsigned long nr_pages = page_counter_read(&memcg->memory); + unsigned long reclaimed; + + if (nr_pages <= high) + break; + + if (signal_pending(current)) + break; + + if (!drained) { + drain_all_stock(memcg); + drained = true; + continue; + } + + reclaimed = try_to_free_mem_cgroup_pages(memcg, nr_pages - high, + GFP_KERNEL, true); + + if (!reclaimed && !nr_retries--) + break; + } + + memcg_wb_domain_size_changed(memcg); + return nbytes; +} + +static int memory_max_show(struct seq_file *m, void *v) +{ + return seq_puts_memcg_tunable(m, + READ_ONCE(mem_cgroup_from_seq(m)->memory.max)); +} + +static ssize_t memory_max_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + unsigned int nr_reclaims = MAX_RECLAIM_RETRIES; + bool drained = false; + unsigned long max; + int err; + + buf = strstrip(buf); + err = page_counter_memparse(buf, "max", &max); + if (err) + return err; + + xchg(&memcg->memory.max, max); + + for (;;) { + unsigned long nr_pages = page_counter_read(&memcg->memory); + + if (nr_pages <= max) + break; + + if (signal_pending(current)) + break; + + if (!drained) { + drain_all_stock(memcg); + drained = true; + continue; + } + + if (nr_reclaims) { + if (!try_to_free_mem_cgroup_pages(memcg, nr_pages - max, + GFP_KERNEL, true)) + nr_reclaims--; + continue; + } + + memcg_memory_event(memcg, MEMCG_OOM); + if (!mem_cgroup_out_of_memory(memcg, GFP_KERNEL, 0)) + break; + } + + memcg_wb_domain_size_changed(memcg); + return nbytes; +} + +static void __memory_events_show(struct seq_file *m, atomic_long_t *events) +{ + seq_printf(m, "low %lu\n", atomic_long_read(&events[MEMCG_LOW])); + seq_printf(m, "high %lu\n", atomic_long_read(&events[MEMCG_HIGH])); + seq_printf(m, "max %lu\n", atomic_long_read(&events[MEMCG_MAX])); + seq_printf(m, "oom %lu\n", atomic_long_read(&events[MEMCG_OOM])); + seq_printf(m, "oom_kill %lu\n", + atomic_long_read(&events[MEMCG_OOM_KILL])); +} + +static int memory_events_show(struct seq_file *m, void *v) +{ + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); + + __memory_events_show(m, memcg->memory_events); + return 0; +} + +static int memory_events_local_show(struct seq_file *m, void *v) +{ + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); + + __memory_events_show(m, memcg->memory_events_local); + return 0; +} + +static int memory_stat_show(struct seq_file *m, void *v) +{ + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); + char *buf; + + buf = memory_stat_format(memcg); + if (!buf) + return -ENOMEM; + seq_puts(m, buf); + kfree(buf); + return 0; +} + +#ifdef CONFIG_NUMA +static int memory_numa_stat_show(struct seq_file *m, void *v) +{ + int i; + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); + + for (i = 0; i < ARRAY_SIZE(memory_stats); i++) { + int nid; + + if (memory_stats[i].idx >= NR_VM_NODE_STAT_ITEMS) + continue; + + seq_printf(m, "%s", memory_stats[i].name); + for_each_node_state(nid, N_MEMORY) { + u64 size; + struct lruvec *lruvec; + + lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(nid)); + size = lruvec_page_state(lruvec, memory_stats[i].idx); + size *= memory_stats[i].ratio; + seq_printf(m, " N%d=%llu", nid, size); + } + seq_putc(m, '\n'); + } + + return 0; +} +#endif + +static int memory_oom_group_show(struct seq_file *m, void *v) +{ + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); + + seq_printf(m, "%d\n", memcg->oom_group); + + return 0; +} + +static ssize_t memory_oom_group_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + int ret, oom_group; + + buf = strstrip(buf); + if (!buf) + return -EINVAL; + + ret = kstrtoint(buf, 0, &oom_group); + if (ret) + return ret; + + if (oom_group != 0 && oom_group != 1) + return -EINVAL; + + memcg->oom_group = oom_group; + + return nbytes; +} + +static struct cftype memory_files[] = { + { + .name = "current", + .flags = CFTYPE_NOT_ON_ROOT, + .read_u64 = memory_current_read, + }, + { + .name = "min", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = memory_min_show, + .write = memory_min_write, + }, + { + .name = "low", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = memory_low_show, + .write = memory_low_write, + }, + { + .name = "high", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = memory_high_show, + .write = memory_high_write, + }, + { + .name = "max", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = memory_max_show, + .write = memory_max_write, + }, + { + .name = "events", + .flags = CFTYPE_NOT_ON_ROOT, + .file_offset = offsetof(struct mem_cgroup, events_file), + .seq_show = memory_events_show, + }, + { + .name = "events.local", + .flags = CFTYPE_NOT_ON_ROOT, + .file_offset = offsetof(struct mem_cgroup, events_local_file), + .seq_show = memory_events_local_show, + }, + { + .name = "stat", + .seq_show = memory_stat_show, + }, +#ifdef CONFIG_NUMA + { + .name = "numa_stat", + .seq_show = memory_numa_stat_show, + }, +#endif + { + .name = "oom.group", + .flags = CFTYPE_NOT_ON_ROOT | CFTYPE_NS_DELEGATABLE, + .seq_show = memory_oom_group_show, + .write = memory_oom_group_write, + }, + { } /* terminate */ +}; + +struct cgroup_subsys memory_cgrp_subsys = { + .css_alloc = mem_cgroup_css_alloc, + .css_online = mem_cgroup_css_online, + .css_offline = mem_cgroup_css_offline, + .css_released = mem_cgroup_css_released, + .css_free = mem_cgroup_css_free, + .css_reset = mem_cgroup_css_reset, + .can_attach = mem_cgroup_can_attach, + .cancel_attach = mem_cgroup_cancel_attach, + .post_attach = mem_cgroup_move_task, + .bind = mem_cgroup_bind, + .dfl_cftypes = memory_files, + .legacy_cftypes = mem_cgroup_legacy_files, + .early_init = 0, +}; + +/* + * This function calculates an individual cgroup's effective + * protection which is derived from its own memory.min/low, its + * parent's and siblings' settings, as well as the actual memory + * distribution in the tree. + * + * The following rules apply to the effective protection values: + * + * 1. At the first level of reclaim, effective protection is equal to + * the declared protection in memory.min and memory.low. + * + * 2. To enable safe delegation of the protection configuration, at + * subsequent levels the effective protection is capped to the + * parent's effective protection. + * + * 3. To make complex and dynamic subtrees easier to configure, the + * user is allowed to overcommit the declared protection at a given + * level. If that is the case, the parent's effective protection is + * distributed to the children in proportion to how much protection + * they have declared and how much of it they are utilizing. + * + * This makes distribution proportional, but also work-conserving: + * if one cgroup claims much more protection than it uses memory, + * the unused remainder is available to its siblings. + * + * 4. Conversely, when the declared protection is undercommitted at a + * given level, the distribution of the larger parental protection + * budget is NOT proportional. A cgroup's protection from a sibling + * is capped to its own memory.min/low setting. + * + * 5. However, to allow protecting recursive subtrees from each other + * without having to declare each individual cgroup's fixed share + * of the ancestor's claim to protection, any unutilized - + * "floating" - protection from up the tree is distributed in + * proportion to each cgroup's *usage*. This makes the protection + * neutral wrt sibling cgroups and lets them compete freely over + * the shared parental protection budget, but it protects the + * subtree as a whole from neighboring subtrees. + * + * Note that 4. and 5. are not in conflict: 4. is about protecting + * against immediate siblings whereas 5. is about protecting against + * neighboring subtrees. + */ +static unsigned long effective_protection(unsigned long usage, + unsigned long parent_usage, + unsigned long setting, + unsigned long parent_effective, + unsigned long siblings_protected) +{ + unsigned long protected; + unsigned long ep; + + protected = min(usage, setting); + /* + * If all cgroups at this level combined claim and use more + * protection then what the parent affords them, distribute + * shares in proportion to utilization. + * + * We are using actual utilization rather than the statically + * claimed protection in order to be work-conserving: claimed + * but unused protection is available to siblings that would + * otherwise get a smaller chunk than what they claimed. + */ + if (siblings_protected > parent_effective) + return protected * parent_effective / siblings_protected; + + /* + * Ok, utilized protection of all children is within what the + * parent affords them, so we know whatever this child claims + * and utilizes is effectively protected. + * + * If there is unprotected usage beyond this value, reclaim + * will apply pressure in proportion to that amount. + * + * If there is unutilized protection, the cgroup will be fully + * shielded from reclaim, but we do return a smaller value for + * protection than what the group could enjoy in theory. This + * is okay. With the overcommit distribution above, effective + * protection is always dependent on how memory is actually + * consumed among the siblings anyway. + */ + ep = protected; + + /* + * If the children aren't claiming (all of) the protection + * afforded to them by the parent, distribute the remainder in + * proportion to the (unprotected) memory of each cgroup. That + * way, cgroups that aren't explicitly prioritized wrt each + * other compete freely over the allowance, but they are + * collectively protected from neighboring trees. + * + * We're using unprotected memory for the weight so that if + * some cgroups DO claim explicit protection, we don't protect + * the same bytes twice. + * + * Check both usage and parent_usage against the respective + * protected values. One should imply the other, but they + * aren't read atomically - make sure the division is sane. + */ + if (!(cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT)) + return ep; + if (parent_effective > siblings_protected && + parent_usage > siblings_protected && + usage > protected) { + unsigned long unclaimed; + + unclaimed = parent_effective - siblings_protected; + unclaimed *= usage - protected; + unclaimed /= parent_usage - siblings_protected; + + ep += unclaimed; + } + + return ep; +} + +/** + * mem_cgroup_protected - check if memory consumption is in the normal range + * @root: the top ancestor of the sub-tree being checked + * @memcg: the memory cgroup to check + * + * WARNING: This function is not stateless! It can only be used as part + * of a top-down tree iteration, not for isolated queries. + */ +void mem_cgroup_calculate_protection(struct mem_cgroup *root, + struct mem_cgroup *memcg) +{ + unsigned long usage, parent_usage; + struct mem_cgroup *parent; + + if (mem_cgroup_disabled()) + return; + + if (!root) + root = root_mem_cgroup; + + /* + * Effective values of the reclaim targets are ignored so they + * can be stale. Have a look at mem_cgroup_protection for more + * details. + * TODO: calculation should be more robust so that we do not need + * that special casing. + */ + if (memcg == root) + return; + + usage = page_counter_read(&memcg->memory); + if (!usage) + return; + + parent = parent_mem_cgroup(memcg); + /* No parent means a non-hierarchical mode on v1 memcg */ + if (!parent) + return; + + if (parent == root) { + memcg->memory.emin = READ_ONCE(memcg->memory.min); + memcg->memory.elow = READ_ONCE(memcg->memory.low); + return; + } + + parent_usage = page_counter_read(&parent->memory); + + WRITE_ONCE(memcg->memory.emin, effective_protection(usage, parent_usage, + READ_ONCE(memcg->memory.min), + READ_ONCE(parent->memory.emin), + atomic_long_read(&parent->memory.children_min_usage))); + + WRITE_ONCE(memcg->memory.elow, effective_protection(usage, parent_usage, + READ_ONCE(memcg->memory.low), + READ_ONCE(parent->memory.elow), + atomic_long_read(&parent->memory.children_low_usage))); +} + +/** + * mem_cgroup_charge - charge a newly allocated page to a cgroup + * @page: page to charge + * @mm: mm context of the victim + * @gfp_mask: reclaim mode + * + * Try to charge @page to the memcg that @mm belongs to, reclaiming + * pages according to @gfp_mask if necessary. + * + * Returns 0 on success. Otherwise, an error code is returned. + */ +int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) +{ + unsigned int nr_pages = thp_nr_pages(page); + struct mem_cgroup *memcg = NULL; + int ret = 0; + + if (mem_cgroup_disabled()) + goto out; + + if (PageSwapCache(page)) { + swp_entry_t ent = { .val = page_private(page), }; + unsigned short id; + + /* + * Every swap fault against a single page tries to charge the + * page, bail as early as possible. shmem_unuse() encounters + * already charged pages, too. page->mem_cgroup is protected + * by the page lock, which serializes swap cache removal, which + * in turn serializes uncharging. + */ + VM_BUG_ON_PAGE(!PageLocked(page), page); + if (compound_head(page)->mem_cgroup) + goto out; + + id = lookup_swap_cgroup_id(ent); + rcu_read_lock(); + memcg = mem_cgroup_from_id(id); + if (memcg && !css_tryget_online(&memcg->css)) + memcg = NULL; + rcu_read_unlock(); + } + + if (!memcg) + memcg = get_mem_cgroup_from_mm(mm); + + ret = try_charge(memcg, gfp_mask, nr_pages); + if (ret) + goto out_put; + + css_get(&memcg->css); + commit_charge(page, memcg); + + local_irq_disable(); + mem_cgroup_charge_statistics(memcg, page, nr_pages); + memcg_check_events(memcg, page); + local_irq_enable(); + + /* + * Cgroup1's unified memory+swap counter has been charged with the + * new swapcache page, finish the transfer by uncharging the swap + * slot. The swap slot would also get uncharged when it dies, but + * it can stick around indefinitely and we'd count the page twice + * the entire time. + * + * Cgroup2 has separate resource counters for memory and swap, + * so this is a non-issue here. Memory and swap charge lifetimes + * correspond 1:1 to page and swap slot lifetimes: we charge the + * page to memory here, and uncharge swap when the slot is freed. + */ + if (do_memsw_account() && PageSwapCache(page)) { + swp_entry_t entry = { .val = page_private(page) }; + /* + * The swap entry might not get freed for a long time, + * let's not wait for it. The page already received a + * memory+swap charge, drop the swap entry duplicate. + */ + mem_cgroup_uncharge_swap(entry, nr_pages); + } + +out_put: + css_put(&memcg->css); +out: + return ret; +} + +struct uncharge_gather { + struct mem_cgroup *memcg; + unsigned long nr_pages; + unsigned long pgpgout; + unsigned long nr_kmem; + struct page *dummy_page; +}; + +static inline void uncharge_gather_clear(struct uncharge_gather *ug) +{ + memset(ug, 0, sizeof(*ug)); +} + +static void uncharge_batch(const struct uncharge_gather *ug) +{ + unsigned long flags; + + if (!mem_cgroup_is_root(ug->memcg)) { + page_counter_uncharge(&ug->memcg->memory, ug->nr_pages); + if (do_memsw_account()) + page_counter_uncharge(&ug->memcg->memsw, ug->nr_pages); + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && ug->nr_kmem) + page_counter_uncharge(&ug->memcg->kmem, ug->nr_kmem); + memcg_oom_recover(ug->memcg); + } + + local_irq_save(flags); + __count_memcg_events(ug->memcg, PGPGOUT, ug->pgpgout); + __this_cpu_add(ug->memcg->vmstats_percpu->nr_page_events, ug->nr_pages); + memcg_check_events(ug->memcg, ug->dummy_page); + local_irq_restore(flags); + + /* drop reference from uncharge_page */ + css_put(&ug->memcg->css); +} + +static void uncharge_page(struct page *page, struct uncharge_gather *ug) +{ + unsigned long nr_pages; + + VM_BUG_ON_PAGE(PageLRU(page), page); + + if (!page->mem_cgroup) + return; + + /* + * Nobody should be changing or seriously looking at + * page->mem_cgroup at this point, we have fully + * exclusive access to the page. + */ + + if (ug->memcg != page->mem_cgroup) { + if (ug->memcg) { + uncharge_batch(ug); + uncharge_gather_clear(ug); + } + ug->memcg = page->mem_cgroup; + + /* pairs with css_put in uncharge_batch */ + css_get(&ug->memcg->css); + } + + nr_pages = compound_nr(page); + ug->nr_pages += nr_pages; + + if (!PageKmemcg(page)) { + ug->pgpgout++; + } else { + ug->nr_kmem += nr_pages; + __ClearPageKmemcg(page); + } + + ug->dummy_page = page; + page->mem_cgroup = NULL; + css_put(&ug->memcg->css); +} + +static void uncharge_list(struct list_head *page_list) +{ + struct uncharge_gather ug; + struct list_head *next; + + uncharge_gather_clear(&ug); + + /* + * Note that the list can be a single page->lru; hence the + * do-while loop instead of a simple list_for_each_entry(). + */ + next = page_list->next; + do { + struct page *page; + + page = list_entry(next, struct page, lru); + next = page->lru.next; + + uncharge_page(page, &ug); + } while (next != page_list); + + if (ug.memcg) + uncharge_batch(&ug); +} + +/** + * mem_cgroup_uncharge - uncharge a page + * @page: page to uncharge + * + * Uncharge a page previously charged with mem_cgroup_charge(). + */ +void mem_cgroup_uncharge(struct page *page) +{ + struct uncharge_gather ug; + + if (mem_cgroup_disabled()) + return; + + /* Don't touch page->lru of any random page, pre-check: */ + if (!page->mem_cgroup) + return; + + uncharge_gather_clear(&ug); + uncharge_page(page, &ug); + uncharge_batch(&ug); +} + +/** + * mem_cgroup_uncharge_list - uncharge a list of page + * @page_list: list of pages to uncharge + * + * Uncharge a list of pages previously charged with + * mem_cgroup_charge(). + */ +void mem_cgroup_uncharge_list(struct list_head *page_list) +{ + if (mem_cgroup_disabled()) + return; + + if (!list_empty(page_list)) + uncharge_list(page_list); +} + +/** + * mem_cgroup_migrate - charge a page's replacement + * @oldpage: currently circulating page + * @newpage: replacement page + * + * Charge @newpage as a replacement page for @oldpage. @oldpage will + * be uncharged upon free. + * + * Both pages must be locked, @newpage->mapping must be set up. + */ +void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) +{ + struct mem_cgroup *memcg; + unsigned int nr_pages; + unsigned long flags; + + VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage); + VM_BUG_ON_PAGE(!PageLocked(newpage), newpage); + VM_BUG_ON_PAGE(PageAnon(oldpage) != PageAnon(newpage), newpage); + VM_BUG_ON_PAGE(PageTransHuge(oldpage) != PageTransHuge(newpage), + newpage); + + if (mem_cgroup_disabled()) + return; + + /* Page cache replacement: new page already charged? */ + if (newpage->mem_cgroup) + return; + + /* Swapcache readahead pages can get replaced before being charged */ + memcg = oldpage->mem_cgroup; + if (!memcg) + return; + + /* Force-charge the new page. The old one will be freed soon */ + nr_pages = thp_nr_pages(newpage); + + page_counter_charge(&memcg->memory, nr_pages); + if (do_memsw_account()) + page_counter_charge(&memcg->memsw, nr_pages); + + css_get(&memcg->css); + commit_charge(newpage, memcg); + + local_irq_save(flags); + mem_cgroup_charge_statistics(memcg, newpage, nr_pages); + memcg_check_events(memcg, newpage); + local_irq_restore(flags); +} + +DEFINE_STATIC_KEY_FALSE(memcg_sockets_enabled_key); +EXPORT_SYMBOL(memcg_sockets_enabled_key); + +void mem_cgroup_sk_alloc(struct sock *sk) +{ + struct mem_cgroup *memcg; + + if (!mem_cgroup_sockets_enabled) + return; + + /* Do not associate the sock with unrelated interrupted task's memcg. */ + if (in_interrupt()) + return; + + rcu_read_lock(); + memcg = mem_cgroup_from_task(current); + if (memcg == root_mem_cgroup) + goto out; + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && !memcg->tcpmem_active) + goto out; + if (css_tryget(&memcg->css)) + sk->sk_memcg = memcg; +out: + rcu_read_unlock(); +} + +void mem_cgroup_sk_free(struct sock *sk) +{ + if (sk->sk_memcg) + css_put(&sk->sk_memcg->css); +} + +/** + * mem_cgroup_charge_skmem - charge socket memory + * @memcg: memcg to charge + * @nr_pages: number of pages to charge + * + * Charges @nr_pages to @memcg. Returns %true if the charge fit within + * @memcg's configured limit, %false if the charge had to be forced. + */ +bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages) +{ + gfp_t gfp_mask = GFP_KERNEL; + + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) { + struct page_counter *fail; + + if (page_counter_try_charge(&memcg->tcpmem, nr_pages, &fail)) { + memcg->tcpmem_pressure = 0; + return true; + } + page_counter_charge(&memcg->tcpmem, nr_pages); + memcg->tcpmem_pressure = 1; + return false; + } + + /* Don't block in the packet receive path */ + if (in_softirq()) + gfp_mask = GFP_NOWAIT; + + mod_memcg_state(memcg, MEMCG_SOCK, nr_pages); + + if (try_charge(memcg, gfp_mask, nr_pages) == 0) + return true; + + try_charge(memcg, gfp_mask|__GFP_NOFAIL, nr_pages); + return false; +} + +/** + * mem_cgroup_uncharge_skmem - uncharge socket memory + * @memcg: memcg to uncharge + * @nr_pages: number of pages to uncharge + */ +void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages) +{ + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) { + page_counter_uncharge(&memcg->tcpmem, nr_pages); + return; + } + + mod_memcg_state(memcg, MEMCG_SOCK, -nr_pages); + + refill_stock(memcg, nr_pages); +} + +static int __init cgroup_memory(char *s) +{ + char *token; + + while ((token = strsep(&s, ",")) != NULL) { + if (!*token) + continue; + if (!strcmp(token, "nosocket")) + cgroup_memory_nosocket = true; + if (!strcmp(token, "nokmem")) + cgroup_memory_nokmem = true; + } + return 1; +} +__setup("cgroup.memory=", cgroup_memory); + +/* + * subsys_initcall() for memory controller. + * + * Some parts like memcg_hotplug_cpu_dead() have to be initialized from this + * context because of lock dependencies (cgroup_lock -> cpu hotplug) but + * basically everything that doesn't depend on a specific mem_cgroup structure + * should be initialized from here. + */ +static int __init mem_cgroup_init(void) +{ + int cpu, node; + + cpuhp_setup_state_nocalls(CPUHP_MM_MEMCQ_DEAD, "mm/memctrl:dead", NULL, + memcg_hotplug_cpu_dead); + + for_each_possible_cpu(cpu) + INIT_WORK(&per_cpu_ptr(&memcg_stock, cpu)->work, + drain_local_stock); + + for_each_node(node) { + struct mem_cgroup_tree_per_node *rtpn; + + rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, + node_online(node) ? node : NUMA_NO_NODE); + + rtpn->rb_root = RB_ROOT; + rtpn->rb_rightmost = NULL; + spin_lock_init(&rtpn->lock); + soft_limit_tree.rb_tree_per_node[node] = rtpn; + } + + return 0; +} +subsys_initcall(mem_cgroup_init); + +#ifdef CONFIG_MEMCG_SWAP +static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg) +{ + while (!refcount_inc_not_zero(&memcg->id.ref)) { + /* + * The root cgroup cannot be destroyed, so it's refcount must + * always be >= 1. + */ + if (WARN_ON_ONCE(memcg == root_mem_cgroup)) { + VM_BUG_ON(1); + break; + } + memcg = parent_mem_cgroup(memcg); + if (!memcg) + memcg = root_mem_cgroup; + } + return memcg; +} + +/** + * mem_cgroup_swapout - transfer a memsw charge to swap + * @page: page whose memsw charge to transfer + * @entry: swap entry to move the charge to + * + * Transfer the memsw charge of @page to @entry. + */ +void mem_cgroup_swapout(struct page *page, swp_entry_t entry) +{ + struct mem_cgroup *memcg, *swap_memcg; + unsigned int nr_entries; + unsigned short oldid; + + VM_BUG_ON_PAGE(PageLRU(page), page); + VM_BUG_ON_PAGE(page_count(page), page); + + if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) + return; + + memcg = page->mem_cgroup; + + /* Readahead page, never charged */ + if (!memcg) + return; + + /* + * In case the memcg owning these pages has been offlined and doesn't + * have an ID allocated to it anymore, charge the closest online + * ancestor for the swap instead and transfer the memory+swap charge. + */ + swap_memcg = mem_cgroup_id_get_online(memcg); + nr_entries = thp_nr_pages(page); + /* Get references for the tail pages, too */ + if (nr_entries > 1) + mem_cgroup_id_get_many(swap_memcg, nr_entries - 1); + oldid = swap_cgroup_record(entry, mem_cgroup_id(swap_memcg), + nr_entries); + VM_BUG_ON_PAGE(oldid, page); + mod_memcg_state(swap_memcg, MEMCG_SWAP, nr_entries); + + page->mem_cgroup = NULL; + + if (!mem_cgroup_is_root(memcg)) + page_counter_uncharge(&memcg->memory, nr_entries); + + if (!cgroup_memory_noswap && memcg != swap_memcg) { + if (!mem_cgroup_is_root(swap_memcg)) + page_counter_charge(&swap_memcg->memsw, nr_entries); + page_counter_uncharge(&memcg->memsw, nr_entries); + } + + /* + * Interrupts should be disabled here because the caller holds the + * i_pages lock which is taken with interrupts-off. It is + * important here to have the interrupts disabled because it is the + * only synchronisation we have for updating the per-CPU variables. + */ + VM_BUG_ON(!irqs_disabled()); + mem_cgroup_charge_statistics(memcg, page, -nr_entries); + memcg_check_events(memcg, page); + + css_put(&memcg->css); +} + +/** + * mem_cgroup_try_charge_swap - try charging swap space for a page + * @page: page being added to swap + * @entry: swap entry to charge + * + * Try to charge @page's memcg for the swap space at @entry. + * + * Returns 0 on success, -ENOMEM on failure. + */ +int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) +{ + unsigned int nr_pages = thp_nr_pages(page); + struct page_counter *counter; + struct mem_cgroup *memcg; + unsigned short oldid; + + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) + return 0; + + memcg = page->mem_cgroup; + + /* Readahead page, never charged */ + if (!memcg) + return 0; + + if (!entry.val) { + memcg_memory_event(memcg, MEMCG_SWAP_FAIL); + return 0; + } + + memcg = mem_cgroup_id_get_online(memcg); + + if (!cgroup_memory_noswap && !mem_cgroup_is_root(memcg) && + !page_counter_try_charge(&memcg->swap, nr_pages, &counter)) { + memcg_memory_event(memcg, MEMCG_SWAP_MAX); + memcg_memory_event(memcg, MEMCG_SWAP_FAIL); + mem_cgroup_id_put(memcg); + return -ENOMEM; + } + + /* Get references for the tail pages, too */ + if (nr_pages > 1) + mem_cgroup_id_get_many(memcg, nr_pages - 1); + oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg), nr_pages); + VM_BUG_ON_PAGE(oldid, page); + mod_memcg_state(memcg, MEMCG_SWAP, nr_pages); + + return 0; +} + +/** + * mem_cgroup_uncharge_swap - uncharge swap space + * @entry: swap entry to uncharge + * @nr_pages: the amount of swap space to uncharge + */ +void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages) +{ + struct mem_cgroup *memcg; + unsigned short id; + + id = swap_cgroup_record(entry, 0, nr_pages); + rcu_read_lock(); + memcg = mem_cgroup_from_id(id); + if (memcg) { + if (!cgroup_memory_noswap && !mem_cgroup_is_root(memcg)) { + if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) + page_counter_uncharge(&memcg->swap, nr_pages); + else + page_counter_uncharge(&memcg->memsw, nr_pages); + } + mod_memcg_state(memcg, MEMCG_SWAP, -nr_pages); + mem_cgroup_id_put_many(memcg, nr_pages); + } + rcu_read_unlock(); +} + +long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg) +{ + long nr_swap_pages = get_nr_swap_pages(); + + if (cgroup_memory_noswap || !cgroup_subsys_on_dfl(memory_cgrp_subsys)) + return nr_swap_pages; + for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg)) + nr_swap_pages = min_t(long, nr_swap_pages, + READ_ONCE(memcg->swap.max) - + page_counter_read(&memcg->swap)); + return nr_swap_pages; +} + +bool mem_cgroup_swap_full(struct page *page) +{ + struct mem_cgroup *memcg; + + VM_BUG_ON_PAGE(!PageLocked(page), page); + + if (vm_swap_full()) + return true; + if (cgroup_memory_noswap || !cgroup_subsys_on_dfl(memory_cgrp_subsys)) + return false; + + memcg = page->mem_cgroup; + if (!memcg) + return false; + + for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg)) { + unsigned long usage = page_counter_read(&memcg->swap); + + if (usage * 2 >= READ_ONCE(memcg->swap.high) || + usage * 2 >= READ_ONCE(memcg->swap.max)) + return true; + } + + return false; +} + +static int __init setup_swap_account(char *s) +{ + if (!strcmp(s, "1")) + cgroup_memory_noswap = 0; + else if (!strcmp(s, "0")) + cgroup_memory_noswap = 1; + return 1; +} +__setup("swapaccount=", setup_swap_account); + +static u64 swap_current_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + + return (u64)page_counter_read(&memcg->swap) * PAGE_SIZE; +} + +static int swap_high_show(struct seq_file *m, void *v) +{ + return seq_puts_memcg_tunable(m, + READ_ONCE(mem_cgroup_from_seq(m)->swap.high)); +} + +static ssize_t swap_high_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + unsigned long high; + int err; + + buf = strstrip(buf); + err = page_counter_memparse(buf, "max", &high); + if (err) + return err; + + page_counter_set_high(&memcg->swap, high); + + return nbytes; +} + +static int swap_max_show(struct seq_file *m, void *v) +{ + return seq_puts_memcg_tunable(m, + READ_ONCE(mem_cgroup_from_seq(m)->swap.max)); +} + +static ssize_t swap_max_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + unsigned long max; + int err; + + buf = strstrip(buf); + err = page_counter_memparse(buf, "max", &max); + if (err) + return err; + + xchg(&memcg->swap.max, max); + + return nbytes; +} + +static int swap_events_show(struct seq_file *m, void *v) +{ + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); + + seq_printf(m, "high %lu\n", + atomic_long_read(&memcg->memory_events[MEMCG_SWAP_HIGH])); + seq_printf(m, "max %lu\n", + atomic_long_read(&memcg->memory_events[MEMCG_SWAP_MAX])); + seq_printf(m, "fail %lu\n", + atomic_long_read(&memcg->memory_events[MEMCG_SWAP_FAIL])); + + return 0; +} + +static struct cftype swap_files[] = { + { + .name = "swap.current", + .flags = CFTYPE_NOT_ON_ROOT, + .read_u64 = swap_current_read, + }, + { + .name = "swap.high", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = swap_high_show, + .write = swap_high_write, + }, + { + .name = "swap.max", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = swap_max_show, + .write = swap_max_write, + }, + { + .name = "swap.events", + .flags = CFTYPE_NOT_ON_ROOT, + .file_offset = offsetof(struct mem_cgroup, swap_events_file), + .seq_show = swap_events_show, + }, + { } /* terminate */ +}; + +static struct cftype memsw_files[] = { + { + .name = "memsw.usage_in_bytes", + .private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE), + .read_u64 = mem_cgroup_read_u64, + }, + { + .name = "memsw.max_usage_in_bytes", + .private = MEMFILE_PRIVATE(_MEMSWAP, RES_MAX_USAGE), + .write = mem_cgroup_reset, + .read_u64 = mem_cgroup_read_u64, + }, + { + .name = "memsw.limit_in_bytes", + .private = MEMFILE_PRIVATE(_MEMSWAP, RES_LIMIT), + .write = mem_cgroup_write, + .read_u64 = mem_cgroup_read_u64, + }, + { + .name = "memsw.failcnt", + .private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT), + .write = mem_cgroup_reset, + .read_u64 = mem_cgroup_read_u64, + }, + { }, /* terminate */ +}; + +/* + * If mem_cgroup_swap_init() is implemented as a subsys_initcall() + * instead of a core_initcall(), this could mean cgroup_memory_noswap still + * remains set to false even when memcg is disabled via "cgroup_disable=memory" + * boot parameter. This may result in premature OOPS inside + * mem_cgroup_get_nr_swap_pages() function in corner cases. + */ +static int __init mem_cgroup_swap_init(void) +{ + /* No memory control -> no swap control */ + if (mem_cgroup_disabled()) + cgroup_memory_noswap = true; + + if (cgroup_memory_noswap) + return 0; + + WARN_ON(cgroup_add_dfl_cftypes(&memory_cgrp_subsys, swap_files)); + WARN_ON(cgroup_add_legacy_cftypes(&memory_cgrp_subsys, memsw_files)); + + return 0; +} +core_initcall(mem_cgroup_swap_init); + +#endif /* CONFIG_MEMCG_SWAP */ diff --git a/mm/memfd.c b/mm/memfd.c new file mode 100644 index 000000000..278e56366 --- /dev/null +++ b/mm/memfd.c @@ -0,0 +1,346 @@ +/* + * memfd_create system call and file sealing support + * + * Code was originally included in shmem.c, and broken out to facilitate + * use by hugetlbfs as well as tmpfs. + * + * This file is released under the GPL. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * We need a tag: a new tag would expand every xa_node by 8 bytes, + * so reuse a tag which we firmly believe is never set or cleared on tmpfs + * or hugetlbfs because they are memory only filesystems. + */ +#define MEMFD_TAG_PINNED PAGECACHE_TAG_TOWRITE +#define LAST_SCAN 4 /* about 150ms max */ + +static void memfd_tag_pins(struct xa_state *xas) +{ + struct page *page; + int latency = 0; + int cache_count; + + lru_add_drain(); + + xas_lock_irq(xas); + xas_for_each(xas, page, ULONG_MAX) { + cache_count = 1; + if (!xa_is_value(page) && + PageTransHuge(page) && !PageHuge(page)) + cache_count = HPAGE_PMD_NR; + + if (!xa_is_value(page) && + page_count(page) - total_mapcount(page) != cache_count) + xas_set_mark(xas, MEMFD_TAG_PINNED); + if (cache_count != 1) + xas_set(xas, page->index + cache_count); + + latency += cache_count; + if (latency < XA_CHECK_SCHED) + continue; + latency = 0; + + xas_pause(xas); + xas_unlock_irq(xas); + cond_resched(); + xas_lock_irq(xas); + } + xas_unlock_irq(xas); +} + +/* + * Setting SEAL_WRITE requires us to verify there's no pending writer. However, + * via get_user_pages(), drivers might have some pending I/O without any active + * user-space mappings (eg., direct-IO, AIO). Therefore, we look at all pages + * and see whether it has an elevated ref-count. If so, we tag them and wait for + * them to be dropped. + * The caller must guarantee that no new user will acquire writable references + * to those pages to avoid races. + */ +static int memfd_wait_for_pins(struct address_space *mapping) +{ + XA_STATE(xas, &mapping->i_pages, 0); + struct page *page; + int error, scan; + + memfd_tag_pins(&xas); + + error = 0; + for (scan = 0; scan <= LAST_SCAN; scan++) { + int latency = 0; + int cache_count; + + if (!xas_marked(&xas, MEMFD_TAG_PINNED)) + break; + + if (!scan) + lru_add_drain_all(); + else if (schedule_timeout_killable((HZ << scan) / 200)) + scan = LAST_SCAN; + + xas_set(&xas, 0); + xas_lock_irq(&xas); + xas_for_each_marked(&xas, page, ULONG_MAX, MEMFD_TAG_PINNED) { + bool clear = true; + + cache_count = 1; + if (!xa_is_value(page) && + PageTransHuge(page) && !PageHuge(page)) + cache_count = HPAGE_PMD_NR; + + if (!xa_is_value(page) && cache_count != + page_count(page) - total_mapcount(page)) { + /* + * On the last scan, we clean up all those tags + * we inserted; but make a note that we still + * found pages pinned. + */ + if (scan == LAST_SCAN) + error = -EBUSY; + else + clear = false; + } + if (clear) + xas_clear_mark(&xas, MEMFD_TAG_PINNED); + + latency += cache_count; + if (latency < XA_CHECK_SCHED) + continue; + latency = 0; + + xas_pause(&xas); + xas_unlock_irq(&xas); + cond_resched(); + xas_lock_irq(&xas); + } + xas_unlock_irq(&xas); + } + + return error; +} + +static unsigned int *memfd_file_seals_ptr(struct file *file) +{ + if (shmem_file(file)) + return &SHMEM_I(file_inode(file))->seals; + +#ifdef CONFIG_HUGETLBFS + if (is_file_hugepages(file)) + return &HUGETLBFS_I(file_inode(file))->seals; +#endif + + return NULL; +} + +#define F_ALL_SEALS (F_SEAL_SEAL | \ + F_SEAL_SHRINK | \ + F_SEAL_GROW | \ + F_SEAL_WRITE | \ + F_SEAL_FUTURE_WRITE) + +static int memfd_add_seals(struct file *file, unsigned int seals) +{ + struct inode *inode = file_inode(file); + unsigned int *file_seals; + int error; + + /* + * SEALING + * Sealing allows multiple parties to share a tmpfs or hugetlbfs file + * but restrict access to a specific subset of file operations. Seals + * can only be added, but never removed. This way, mutually untrusted + * parties can share common memory regions with a well-defined policy. + * A malicious peer can thus never perform unwanted operations on a + * shared object. + * + * Seals are only supported on special tmpfs or hugetlbfs files and + * always affect the whole underlying inode. Once a seal is set, it + * may prevent some kinds of access to the file. Currently, the + * following seals are defined: + * SEAL_SEAL: Prevent further seals from being set on this file + * SEAL_SHRINK: Prevent the file from shrinking + * SEAL_GROW: Prevent the file from growing + * SEAL_WRITE: Prevent write access to the file + * + * As we don't require any trust relationship between two parties, we + * must prevent seals from being removed. Therefore, sealing a file + * only adds a given set of seals to the file, it never touches + * existing seals. Furthermore, the "setting seals"-operation can be + * sealed itself, which basically prevents any further seal from being + * added. + * + * Semantics of sealing are only defined on volatile files. Only + * anonymous tmpfs and hugetlbfs files support sealing. More + * importantly, seals are never written to disk. Therefore, there's + * no plan to support it on other file types. + */ + + if (!(file->f_mode & FMODE_WRITE)) + return -EPERM; + if (seals & ~(unsigned int)F_ALL_SEALS) + return -EINVAL; + + inode_lock(inode); + + file_seals = memfd_file_seals_ptr(file); + if (!file_seals) { + error = -EINVAL; + goto unlock; + } + + if (*file_seals & F_SEAL_SEAL) { + error = -EPERM; + goto unlock; + } + + if ((seals & F_SEAL_WRITE) && !(*file_seals & F_SEAL_WRITE)) { + error = mapping_deny_writable(file->f_mapping); + if (error) + goto unlock; + + error = memfd_wait_for_pins(file->f_mapping); + if (error) { + mapping_allow_writable(file->f_mapping); + goto unlock; + } + } + + *file_seals |= seals; + error = 0; + +unlock: + inode_unlock(inode); + return error; +} + +static int memfd_get_seals(struct file *file) +{ + unsigned int *seals = memfd_file_seals_ptr(file); + + return seals ? *seals : -EINVAL; +} + +long memfd_fcntl(struct file *file, unsigned int cmd, unsigned long arg) +{ + long error; + + switch (cmd) { + case F_ADD_SEALS: + /* disallow upper 32bit */ + if (arg > UINT_MAX) + return -EINVAL; + + error = memfd_add_seals(file, arg); + break; + case F_GET_SEALS: + error = memfd_get_seals(file); + break; + default: + error = -EINVAL; + break; + } + + return error; +} + +#define MFD_NAME_PREFIX "memfd:" +#define MFD_NAME_PREFIX_LEN (sizeof(MFD_NAME_PREFIX) - 1) +#define MFD_NAME_MAX_LEN (NAME_MAX - MFD_NAME_PREFIX_LEN) + +#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB) + +SYSCALL_DEFINE2(memfd_create, + const char __user *, uname, + unsigned int, flags) +{ + unsigned int *file_seals; + struct file *file; + int fd, error; + char *name; + long len; + + if (!(flags & MFD_HUGETLB)) { + if (flags & ~(unsigned int)MFD_ALL_FLAGS) + return -EINVAL; + } else { + /* Allow huge page size encoding in flags. */ + if (flags & ~(unsigned int)(MFD_ALL_FLAGS | + (MFD_HUGE_MASK << MFD_HUGE_SHIFT))) + return -EINVAL; + } + + /* length includes terminating zero */ + len = strnlen_user(uname, MFD_NAME_MAX_LEN + 1); + if (len <= 0) + return -EFAULT; + if (len > MFD_NAME_MAX_LEN + 1) + return -EINVAL; + + name = kmalloc(len + MFD_NAME_PREFIX_LEN, GFP_KERNEL); + if (!name) + return -ENOMEM; + + strcpy(name, MFD_NAME_PREFIX); + if (copy_from_user(&name[MFD_NAME_PREFIX_LEN], uname, len)) { + error = -EFAULT; + goto err_name; + } + + /* terminating-zero may have changed after strnlen_user() returned */ + if (name[len + MFD_NAME_PREFIX_LEN - 1]) { + error = -EFAULT; + goto err_name; + } + + fd = get_unused_fd_flags((flags & MFD_CLOEXEC) ? O_CLOEXEC : 0); + if (fd < 0) { + error = fd; + goto err_name; + } + + if (flags & MFD_HUGETLB) { + struct user_struct *user = NULL; + + file = hugetlb_file_setup(name, 0, VM_NORESERVE, &user, + HUGETLB_ANONHUGE_INODE, + (flags >> MFD_HUGE_SHIFT) & + MFD_HUGE_MASK); + } else + file = shmem_file_setup(name, 0, VM_NORESERVE); + if (IS_ERR(file)) { + error = PTR_ERR(file); + goto err_fd; + } + file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE; + file->f_flags |= O_LARGEFILE; + + if (flags & MFD_ALLOW_SEALING) { + file_seals = memfd_file_seals_ptr(file); + if (file_seals) + *file_seals &= ~F_SEAL_SEAL; + } + + fd_install(fd, file); + kfree(name); + return fd; + +err_fd: + put_unused_fd(fd); +err_name: + kfree(name); + return error; +} diff --git a/mm/memory-failure.c b/mm/memory-failure.c new file mode 100644 index 000000000..f320ff02c --- /dev/null +++ b/mm/memory-failure.c @@ -0,0 +1,1936 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2008, 2009 Intel Corporation + * Authors: Andi Kleen, Fengguang Wu + * + * High level machine check handler. Handles pages reported by the + * hardware as being corrupted usually due to a multi-bit ECC memory or cache + * failure. + * + * In addition there is a "soft offline" entry point that allows stop using + * not-yet-corrupted-by-suspicious pages without killing anything. + * + * Handles page cache pages in various states. The tricky part + * here is that we can access any page asynchronously in respect to + * other VM users, because memory failures could happen anytime and + * anywhere. This could violate some of their assumptions. This is why + * this code has to be extremely careful. Generally it tries to use + * normal locking rules, as in get the standard locks, even if that means + * the error handling takes potentially a long time. + * + * It can be very tempting to add handling for obscure cases here. + * In general any code for handling new cases should only be added iff: + * - You know how to test it. + * - You have a test that can be added to mce-test + * https://git.kernel.org/cgit/utils/cpu/mce/mce-test.git/ + * - The case actually shows up as a frequent (top 10) page state in + * tools/vm/page-types when running a real workload. + * + * There are several operations here with exponential complexity because + * of unsuitable VM data structures. For example the operation to map back + * from RMAP chains to processes has to walk the complete process list and + * has non linear complexity with the number. But since memory corruptions + * are rare we hope to get away with this. This avoids impacting the core + * VM. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "internal.h" +#include "ras/ras_event.h" + +int sysctl_memory_failure_early_kill __read_mostly = 0; + +int sysctl_memory_failure_recovery __read_mostly = 1; + +atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0); + +static bool page_handle_poison(struct page *page, bool hugepage_or_freepage, bool release) +{ + if (hugepage_or_freepage) { + /* + * Doing this check for free pages is also fine since dissolve_free_huge_page + * returns 0 for non-hugetlb pages as well. + */ + if (dissolve_free_huge_page(page) || !take_page_off_buddy(page)) + /* + * We could fail to take off the target page from buddy + * for example due to racy page allocaiton, but that's + * acceptable because soft-offlined page is not broken + * and if someone really want to use it, they should + * take it. + */ + return false; + } + + SetPageHWPoison(page); + if (release) + put_page(page); + page_ref_inc(page); + num_poisoned_pages_inc(); + + return true; +} + +#if defined(CONFIG_HWPOISON_INJECT) || defined(CONFIG_HWPOISON_INJECT_MODULE) + +u32 hwpoison_filter_enable = 0; +u32 hwpoison_filter_dev_major = ~0U; +u32 hwpoison_filter_dev_minor = ~0U; +u64 hwpoison_filter_flags_mask; +u64 hwpoison_filter_flags_value; +EXPORT_SYMBOL_GPL(hwpoison_filter_enable); +EXPORT_SYMBOL_GPL(hwpoison_filter_dev_major); +EXPORT_SYMBOL_GPL(hwpoison_filter_dev_minor); +EXPORT_SYMBOL_GPL(hwpoison_filter_flags_mask); +EXPORT_SYMBOL_GPL(hwpoison_filter_flags_value); + +static int hwpoison_filter_dev(struct page *p) +{ + struct address_space *mapping; + dev_t dev; + + if (hwpoison_filter_dev_major == ~0U && + hwpoison_filter_dev_minor == ~0U) + return 0; + + /* + * page_mapping() does not accept slab pages. + */ + if (PageSlab(p)) + return -EINVAL; + + mapping = page_mapping(p); + if (mapping == NULL || mapping->host == NULL) + return -EINVAL; + + dev = mapping->host->i_sb->s_dev; + if (hwpoison_filter_dev_major != ~0U && + hwpoison_filter_dev_major != MAJOR(dev)) + return -EINVAL; + if (hwpoison_filter_dev_minor != ~0U && + hwpoison_filter_dev_minor != MINOR(dev)) + return -EINVAL; + + return 0; +} + +static int hwpoison_filter_flags(struct page *p) +{ + if (!hwpoison_filter_flags_mask) + return 0; + + if ((stable_page_flags(p) & hwpoison_filter_flags_mask) == + hwpoison_filter_flags_value) + return 0; + else + return -EINVAL; +} + +/* + * This allows stress tests to limit test scope to a collection of tasks + * by putting them under some memcg. This prevents killing unrelated/important + * processes such as /sbin/init. Note that the target task may share clean + * pages with init (eg. libc text), which is harmless. If the target task + * share _dirty_ pages with another task B, the test scheme must make sure B + * is also included in the memcg. At last, due to race conditions this filter + * can only guarantee that the page either belongs to the memcg tasks, or is + * a freed page. + */ +#ifdef CONFIG_MEMCG +u64 hwpoison_filter_memcg; +EXPORT_SYMBOL_GPL(hwpoison_filter_memcg); +static int hwpoison_filter_task(struct page *p) +{ + if (!hwpoison_filter_memcg) + return 0; + + if (page_cgroup_ino(p) != hwpoison_filter_memcg) + return -EINVAL; + + return 0; +} +#else +static int hwpoison_filter_task(struct page *p) { return 0; } +#endif + +int hwpoison_filter(struct page *p) +{ + if (!hwpoison_filter_enable) + return 0; + + if (hwpoison_filter_dev(p)) + return -EINVAL; + + if (hwpoison_filter_flags(p)) + return -EINVAL; + + if (hwpoison_filter_task(p)) + return -EINVAL; + + return 0; +} +#else +int hwpoison_filter(struct page *p) +{ + return 0; +} +#endif + +EXPORT_SYMBOL_GPL(hwpoison_filter); + +/* + * Kill all processes that have a poisoned page mapped and then isolate + * the page. + * + * General strategy: + * Find all processes having the page mapped and kill them. + * But we keep a page reference around so that the page is not + * actually freed yet. + * Then stash the page away + * + * There's no convenient way to get back to mapped processes + * from the VMAs. So do a brute-force search over all + * running processes. + * + * Remember that machine checks are not common (or rather + * if they are common you have other problems), so this shouldn't + * be a performance issue. + * + * Also there are some races possible while we get from the + * error detection to actually handle it. + */ + +struct to_kill { + struct list_head nd; + struct task_struct *tsk; + unsigned long addr; + short size_shift; +}; + +/* + * Send all the processes who have the page mapped a signal. + * ``action optional'' if they are not immediately affected by the error + * ``action required'' if error happened in current execution context + */ +static int kill_proc(struct to_kill *tk, unsigned long pfn, int flags) +{ + struct task_struct *t = tk->tsk; + short addr_lsb = tk->size_shift; + int ret = 0; + + pr_err("Memory failure: %#lx: Sending SIGBUS to %s:%d due to hardware memory corruption\n", + pfn, t->comm, t->pid); + + if (flags & MF_ACTION_REQUIRED) { + WARN_ON_ONCE(t != current); + ret = force_sig_mceerr(BUS_MCEERR_AR, + (void __user *)tk->addr, addr_lsb); + } else { + /* + * Don't use force here, it's convenient if the signal + * can be temporarily blocked. + * This could cause a loop when the user sets SIGBUS + * to SIG_IGN, but hopefully no one will do that? + */ + ret = send_sig_mceerr(BUS_MCEERR_AO, (void __user *)tk->addr, + addr_lsb, t); /* synchronous? */ + } + if (ret < 0) + pr_info("Memory failure: Error sending signal to %s:%d: %d\n", + t->comm, t->pid, ret); + return ret; +} + +/* + * When a unknown page type is encountered drain as many buffers as possible + * in the hope to turn the page into a LRU or free page, which we can handle. + */ +void shake_page(struct page *p, int access) +{ + if (PageHuge(p)) + return; + + if (!PageSlab(p)) { + lru_add_drain_all(); + if (PageLRU(p)) + return; + drain_all_pages(page_zone(p)); + if (PageLRU(p) || is_free_buddy_page(p)) + return; + } + + /* + * Only call shrink_node_slabs here (which would also shrink + * other caches) if access is not potentially fatal. + */ + if (access) + drop_slab_node(page_to_nid(p)); +} +EXPORT_SYMBOL_GPL(shake_page); + +static unsigned long dev_pagemap_mapping_shift(struct page *page, + struct vm_area_struct *vma) +{ + unsigned long address = vma_address(page, vma); + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + pgd = pgd_offset(vma->vm_mm, address); + if (!pgd_present(*pgd)) + return 0; + p4d = p4d_offset(pgd, address); + if (!p4d_present(*p4d)) + return 0; + pud = pud_offset(p4d, address); + if (!pud_present(*pud)) + return 0; + if (pud_devmap(*pud)) + return PUD_SHIFT; + pmd = pmd_offset(pud, address); + if (!pmd_present(*pmd)) + return 0; + if (pmd_devmap(*pmd)) + return PMD_SHIFT; + pte = pte_offset_map(pmd, address); + if (!pte_present(*pte)) + return 0; + if (pte_devmap(*pte)) + return PAGE_SHIFT; + return 0; +} + +/* + * Failure handling: if we can't find or can't kill a process there's + * not much we can do. We just print a message and ignore otherwise. + */ + +/* + * Schedule a process for later kill. + * Uses GFP_ATOMIC allocations to avoid potential recursions in the VM. + */ +static void add_to_kill(struct task_struct *tsk, struct page *p, + struct vm_area_struct *vma, + struct list_head *to_kill) +{ + struct to_kill *tk; + + tk = kmalloc(sizeof(struct to_kill), GFP_ATOMIC); + if (!tk) { + pr_err("Memory failure: Out of memory while machine check handling\n"); + return; + } + + tk->addr = page_address_in_vma(p, vma); + if (is_zone_device_page(p)) + tk->size_shift = dev_pagemap_mapping_shift(p, vma); + else + tk->size_shift = page_shift(compound_head(p)); + + /* + * Send SIGKILL if "tk->addr == -EFAULT". Also, as + * "tk->size_shift" is always non-zero for !is_zone_device_page(), + * so "tk->size_shift == 0" effectively checks no mapping on + * ZONE_DEVICE. Indeed, when a devdax page is mmapped N times + * to a process' address space, it's possible not all N VMAs + * contain mappings for the page, but at least one VMA does. + * Only deliver SIGBUS with payload derived from the VMA that + * has a mapping for the page. + */ + if (tk->addr == -EFAULT) { + pr_info("Memory failure: Unable to find user space address %lx in %s\n", + page_to_pfn(p), tsk->comm); + } else if (tk->size_shift == 0) { + kfree(tk); + return; + } + + get_task_struct(tsk); + tk->tsk = tsk; + list_add_tail(&tk->nd, to_kill); +} + +/* + * Kill the processes that have been collected earlier. + * + * Only do anything when DOIT is set, otherwise just free the list + * (this is used for clean pages which do not need killing) + * Also when FAIL is set do a force kill because something went + * wrong earlier. + */ +static void kill_procs(struct list_head *to_kill, int forcekill, bool fail, + unsigned long pfn, int flags) +{ + struct to_kill *tk, *next; + + list_for_each_entry_safe (tk, next, to_kill, nd) { + if (forcekill) { + /* + * In case something went wrong with munmapping + * make sure the process doesn't catch the + * signal and then access the memory. Just kill it. + */ + if (fail || tk->addr == -EFAULT) { + pr_err("Memory failure: %#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n", + pfn, tk->tsk->comm, tk->tsk->pid); + do_send_sig_info(SIGKILL, SEND_SIG_PRIV, + tk->tsk, PIDTYPE_PID); + } + + /* + * In theory the process could have mapped + * something else on the address in-between. We could + * check for that, but we need to tell the + * process anyways. + */ + else if (kill_proc(tk, pfn, flags) < 0) + pr_err("Memory failure: %#lx: Cannot send advisory machine check signal to %s:%d\n", + pfn, tk->tsk->comm, tk->tsk->pid); + } + put_task_struct(tk->tsk); + kfree(tk); + } +} + +/* + * Find a dedicated thread which is supposed to handle SIGBUS(BUS_MCEERR_AO) + * on behalf of the thread group. Return task_struct of the (first found) + * dedicated thread if found, and return NULL otherwise. + * + * We already hold read_lock(&tasklist_lock) in the caller, so we don't + * have to call rcu_read_lock/unlock() in this function. + */ +static struct task_struct *find_early_kill_thread(struct task_struct *tsk) +{ + struct task_struct *t; + + for_each_thread(tsk, t) { + if (t->flags & PF_MCE_PROCESS) { + if (t->flags & PF_MCE_EARLY) + return t; + } else { + if (sysctl_memory_failure_early_kill) + return t; + } + } + return NULL; +} + +/* + * Determine whether a given process is "early kill" process which expects + * to be signaled when some page under the process is hwpoisoned. + * Return task_struct of the dedicated thread (main thread unless explicitly + * specified) if the process is "early kill," and otherwise returns NULL. + * + * Note that the above is true for Action Optional case, but not for Action + * Required case where SIGBUS should sent only to the current thread. + */ +static struct task_struct *task_early_kill(struct task_struct *tsk, + int force_early) +{ + if (!tsk->mm) + return NULL; + if (force_early) { + /* + * Comparing ->mm here because current task might represent + * a subthread, while tsk always points to the main thread. + */ + if (tsk->mm == current->mm) + return current; + else + return NULL; + } + return find_early_kill_thread(tsk); +} + +/* + * Collect processes when the error hit an anonymous page. + */ +static void collect_procs_anon(struct page *page, struct list_head *to_kill, + int force_early) +{ + struct vm_area_struct *vma; + struct task_struct *tsk; + struct anon_vma *av; + pgoff_t pgoff; + + av = page_lock_anon_vma_read(page); + if (av == NULL) /* Not actually mapped anymore */ + return; + + pgoff = page_to_pgoff(page); + read_lock(&tasklist_lock); + for_each_process (tsk) { + struct anon_vma_chain *vmac; + struct task_struct *t = task_early_kill(tsk, force_early); + + if (!t) + continue; + anon_vma_interval_tree_foreach(vmac, &av->rb_root, + pgoff, pgoff) { + vma = vmac->vma; + if (!page_mapped_in_vma(page, vma)) + continue; + if (vma->vm_mm == t->mm) + add_to_kill(t, page, vma, to_kill); + } + } + read_unlock(&tasklist_lock); + page_unlock_anon_vma_read(av); +} + +/* + * Collect processes when the error hit a file mapped page. + */ +static void collect_procs_file(struct page *page, struct list_head *to_kill, + int force_early) +{ + struct vm_area_struct *vma; + struct task_struct *tsk; + struct address_space *mapping = page->mapping; + pgoff_t pgoff; + + i_mmap_lock_read(mapping); + read_lock(&tasklist_lock); + pgoff = page_to_pgoff(page); + for_each_process(tsk) { + struct task_struct *t = task_early_kill(tsk, force_early); + + if (!t) + continue; + vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, + pgoff) { + /* + * Send early kill signal to tasks where a vma covers + * the page but the corrupted page is not necessarily + * mapped it in its pte. + * Assume applications who requested early kill want + * to be informed of all such data corruptions. + */ + if (vma->vm_mm == t->mm) + add_to_kill(t, page, vma, to_kill); + } + } + read_unlock(&tasklist_lock); + i_mmap_unlock_read(mapping); +} + +/* + * Collect the processes who have the corrupted page mapped to kill. + */ +static void collect_procs(struct page *page, struct list_head *tokill, + int force_early) +{ + if (!page->mapping) + return; + + if (PageAnon(page)) + collect_procs_anon(page, tokill, force_early); + else + collect_procs_file(page, tokill, force_early); +} + +static const char *action_name[] = { + [MF_IGNORED] = "Ignored", + [MF_FAILED] = "Failed", + [MF_DELAYED] = "Delayed", + [MF_RECOVERED] = "Recovered", +}; + +static const char * const action_page_types[] = { + [MF_MSG_KERNEL] = "reserved kernel page", + [MF_MSG_KERNEL_HIGH_ORDER] = "high-order kernel page", + [MF_MSG_SLAB] = "kernel slab page", + [MF_MSG_DIFFERENT_COMPOUND] = "different compound page after locking", + [MF_MSG_POISONED_HUGE] = "huge page already hardware poisoned", + [MF_MSG_HUGE] = "huge page", + [MF_MSG_FREE_HUGE] = "free huge page", + [MF_MSG_NON_PMD_HUGE] = "non-pmd-sized huge page", + [MF_MSG_UNMAP_FAILED] = "unmapping failed page", + [MF_MSG_DIRTY_SWAPCACHE] = "dirty swapcache page", + [MF_MSG_CLEAN_SWAPCACHE] = "clean swapcache page", + [MF_MSG_DIRTY_MLOCKED_LRU] = "dirty mlocked LRU page", + [MF_MSG_CLEAN_MLOCKED_LRU] = "clean mlocked LRU page", + [MF_MSG_DIRTY_UNEVICTABLE_LRU] = "dirty unevictable LRU page", + [MF_MSG_CLEAN_UNEVICTABLE_LRU] = "clean unevictable LRU page", + [MF_MSG_DIRTY_LRU] = "dirty LRU page", + [MF_MSG_CLEAN_LRU] = "clean LRU page", + [MF_MSG_TRUNCATED_LRU] = "already truncated LRU page", + [MF_MSG_BUDDY] = "free buddy page", + [MF_MSG_BUDDY_2ND] = "free buddy page (2nd try)", + [MF_MSG_DAX] = "dax page", + [MF_MSG_UNSPLIT_THP] = "unsplit thp", + [MF_MSG_UNKNOWN] = "unknown page", +}; + +/* + * XXX: It is possible that a page is isolated from LRU cache, + * and then kept in swap cache or failed to remove from page cache. + * The page count will stop it from being freed by unpoison. + * Stress tests should be aware of this memory leak problem. + */ +static int delete_from_lru_cache(struct page *p) +{ + if (!isolate_lru_page(p)) { + /* + * Clear sensible page flags, so that the buddy system won't + * complain when the page is unpoison-and-freed. + */ + ClearPageActive(p); + ClearPageUnevictable(p); + + /* + * Poisoned page might never drop its ref count to 0 so we have + * to uncharge it manually from its memcg. + */ + mem_cgroup_uncharge(p); + + /* + * drop the page count elevated by isolate_lru_page() + */ + put_page(p); + return 0; + } + return -EIO; +} + +static int truncate_error_page(struct page *p, unsigned long pfn, + struct address_space *mapping) +{ + int ret = MF_FAILED; + + if (mapping->a_ops->error_remove_page) { + int err = mapping->a_ops->error_remove_page(mapping, p); + + if (err != 0) { + pr_info("Memory failure: %#lx: Failed to punch page: %d\n", + pfn, err); + } else if (page_has_private(p) && + !try_to_release_page(p, GFP_NOIO)) { + pr_info("Memory failure: %#lx: failed to release buffers\n", + pfn); + } else { + ret = MF_RECOVERED; + } + } else { + /* + * If the file system doesn't support it just invalidate + * This fails on dirty or anything with private pages + */ + if (invalidate_inode_page(p)) + ret = MF_RECOVERED; + else + pr_info("Memory failure: %#lx: Failed to invalidate\n", + pfn); + } + + return ret; +} + +/* + * Error hit kernel page. + * Do nothing, try to be lucky and not touch this instead. For a few cases we + * could be more sophisticated. + */ +static int me_kernel(struct page *p, unsigned long pfn) +{ + return MF_IGNORED; +} + +/* + * Page in unknown state. Do nothing. + */ +static int me_unknown(struct page *p, unsigned long pfn) +{ + pr_err("Memory failure: %#lx: Unknown page state\n", pfn); + return MF_FAILED; +} + +/* + * Clean (or cleaned) page cache page. + */ +static int me_pagecache_clean(struct page *p, unsigned long pfn) +{ + struct address_space *mapping; + + delete_from_lru_cache(p); + + /* + * For anonymous pages we're done the only reference left + * should be the one m_f() holds. + */ + if (PageAnon(p)) + return MF_RECOVERED; + + /* + * Now truncate the page in the page cache. This is really + * more like a "temporary hole punch" + * Don't do this for block devices when someone else + * has a reference, because it could be file system metadata + * and that's not safe to truncate. + */ + mapping = page_mapping(p); + if (!mapping) { + /* + * Page has been teared down in the meanwhile + */ + return MF_FAILED; + } + + /* + * Truncation is a bit tricky. Enable it per file system for now. + * + * Open: to take i_mutex or not for this? Right now we don't. + */ + return truncate_error_page(p, pfn, mapping); +} + +/* + * Dirty pagecache page + * Issues: when the error hit a hole page the error is not properly + * propagated. + */ +static int me_pagecache_dirty(struct page *p, unsigned long pfn) +{ + struct address_space *mapping = page_mapping(p); + + SetPageError(p); + /* TBD: print more information about the file. */ + if (mapping) { + /* + * IO error will be reported by write(), fsync(), etc. + * who check the mapping. + * This way the application knows that something went + * wrong with its dirty file data. + * + * There's one open issue: + * + * The EIO will be only reported on the next IO + * operation and then cleared through the IO map. + * Normally Linux has two mechanisms to pass IO error + * first through the AS_EIO flag in the address space + * and then through the PageError flag in the page. + * Since we drop pages on memory failure handling the + * only mechanism open to use is through AS_AIO. + * + * This has the disadvantage that it gets cleared on + * the first operation that returns an error, while + * the PageError bit is more sticky and only cleared + * when the page is reread or dropped. If an + * application assumes it will always get error on + * fsync, but does other operations on the fd before + * and the page is dropped between then the error + * will not be properly reported. + * + * This can already happen even without hwpoisoned + * pages: first on metadata IO errors (which only + * report through AS_EIO) or when the page is dropped + * at the wrong time. + * + * So right now we assume that the application DTRT on + * the first EIO, but we're not worse than other parts + * of the kernel. + */ + mapping_set_error(mapping, -EIO); + } + + return me_pagecache_clean(p, pfn); +} + +/* + * Clean and dirty swap cache. + * + * Dirty swap cache page is tricky to handle. The page could live both in page + * cache and swap cache(ie. page is freshly swapped in). So it could be + * referenced concurrently by 2 types of PTEs: + * normal PTEs and swap PTEs. We try to handle them consistently by calling + * try_to_unmap(TTU_IGNORE_HWPOISON) to convert the normal PTEs to swap PTEs, + * and then + * - clear dirty bit to prevent IO + * - remove from LRU + * - but keep in the swap cache, so that when we return to it on + * a later page fault, we know the application is accessing + * corrupted data and shall be killed (we installed simple + * interception code in do_swap_page to catch it). + * + * Clean swap cache pages can be directly isolated. A later page fault will + * bring in the known good data from disk. + */ +static int me_swapcache_dirty(struct page *p, unsigned long pfn) +{ + ClearPageDirty(p); + /* Trigger EIO in shmem: */ + ClearPageUptodate(p); + + if (!delete_from_lru_cache(p)) + return MF_DELAYED; + else + return MF_FAILED; +} + +static int me_swapcache_clean(struct page *p, unsigned long pfn) +{ + delete_from_swap_cache(p); + + if (!delete_from_lru_cache(p)) + return MF_RECOVERED; + else + return MF_FAILED; +} + +/* + * Huge pages. Needs work. + * Issues: + * - Error on hugepage is contained in hugepage unit (not in raw page unit.) + * To narrow down kill region to one page, we need to break up pmd. + */ +static int me_huge_page(struct page *p, unsigned long pfn) +{ + int res = 0; + struct page *hpage = compound_head(p); + struct address_space *mapping; + + if (!PageHuge(hpage)) + return MF_DELAYED; + + mapping = page_mapping(hpage); + if (mapping) { + res = truncate_error_page(hpage, pfn, mapping); + } else { + unlock_page(hpage); + /* + * migration entry prevents later access on error anonymous + * hugepage, so we can free and dissolve it into buddy to + * save healthy subpages. + */ + if (PageAnon(hpage)) + put_page(hpage); + dissolve_free_huge_page(p); + res = MF_RECOVERED; + lock_page(hpage); + } + + return res; +} + +/* + * Various page states we can handle. + * + * A page state is defined by its current page->flags bits. + * The table matches them in order and calls the right handler. + * + * This is quite tricky because we can access page at any time + * in its live cycle, so all accesses have to be extremely careful. + * + * This is not complete. More states could be added. + * For any missing state don't attempt recovery. + */ + +#define dirty (1UL << PG_dirty) +#define sc ((1UL << PG_swapcache) | (1UL << PG_swapbacked)) +#define unevict (1UL << PG_unevictable) +#define mlock (1UL << PG_mlocked) +#define lru (1UL << PG_lru) +#define head (1UL << PG_head) +#define slab (1UL << PG_slab) +#define reserved (1UL << PG_reserved) + +static struct page_state { + unsigned long mask; + unsigned long res; + enum mf_action_page_type type; + int (*action)(struct page *p, unsigned long pfn); +} error_states[] = { + { reserved, reserved, MF_MSG_KERNEL, me_kernel }, + /* + * free pages are specially detected outside this table: + * PG_buddy pages only make a small fraction of all free pages. + */ + + /* + * Could in theory check if slab page is free or if we can drop + * currently unused objects without touching them. But just + * treat it as standard kernel for now. + */ + { slab, slab, MF_MSG_SLAB, me_kernel }, + + { head, head, MF_MSG_HUGE, me_huge_page }, + + { sc|dirty, sc|dirty, MF_MSG_DIRTY_SWAPCACHE, me_swapcache_dirty }, + { sc|dirty, sc, MF_MSG_CLEAN_SWAPCACHE, me_swapcache_clean }, + + { mlock|dirty, mlock|dirty, MF_MSG_DIRTY_MLOCKED_LRU, me_pagecache_dirty }, + { mlock|dirty, mlock, MF_MSG_CLEAN_MLOCKED_LRU, me_pagecache_clean }, + + { unevict|dirty, unevict|dirty, MF_MSG_DIRTY_UNEVICTABLE_LRU, me_pagecache_dirty }, + { unevict|dirty, unevict, MF_MSG_CLEAN_UNEVICTABLE_LRU, me_pagecache_clean }, + + { lru|dirty, lru|dirty, MF_MSG_DIRTY_LRU, me_pagecache_dirty }, + { lru|dirty, lru, MF_MSG_CLEAN_LRU, me_pagecache_clean }, + + /* + * Catchall entry: must be at end. + */ + { 0, 0, MF_MSG_UNKNOWN, me_unknown }, +}; + +#undef dirty +#undef sc +#undef unevict +#undef mlock +#undef lru +#undef head +#undef slab +#undef reserved + +/* + * "Dirty/Clean" indication is not 100% accurate due to the possibility of + * setting PG_dirty outside page lock. See also comment above set_page_dirty(). + */ +static void action_result(unsigned long pfn, enum mf_action_page_type type, + enum mf_result result) +{ + trace_memory_failure_event(pfn, type, result); + + pr_err("Memory failure: %#lx: recovery action for %s: %s\n", + pfn, action_page_types[type], action_name[result]); +} + +static int page_action(struct page_state *ps, struct page *p, + unsigned long pfn) +{ + int result; + int count; + + result = ps->action(p, pfn); + + count = page_count(p) - 1; + if (ps->action == me_swapcache_dirty && result == MF_DELAYED) + count--; + if (count > 0) { + pr_err("Memory failure: %#lx: %s still referenced by %d users\n", + pfn, action_page_types[ps->type], count); + result = MF_FAILED; + } + action_result(pfn, ps->type, result); + + /* Could do more checks here if page looks ok */ + /* + * Could adjust zone counters here to correct for the missing page. + */ + + return (result == MF_RECOVERED || result == MF_DELAYED) ? 0 : -EBUSY; +} + +/** + * get_hwpoison_page() - Get refcount for memory error handling: + * @page: raw error page (hit by memory error) + * + * Return: return 0 if failed to grab the refcount, otherwise true (some + * non-zero value.) + */ +static int get_hwpoison_page(struct page *page) +{ + struct page *head = compound_head(page); + + if (!PageHuge(head) && PageTransHuge(head)) { + /* + * Non anonymous thp exists only in allocation/free time. We + * can't handle such a case correctly, so let's give it up. + * This should be better than triggering BUG_ON when kernel + * tries to touch the "partially handled" page. + */ + if (!PageAnon(head)) { + pr_err("Memory failure: %#lx: non anonymous thp\n", + page_to_pfn(page)); + return 0; + } + } + + if (get_page_unless_zero(head)) { + if (head == compound_head(page)) + return 1; + + pr_info("Memory failure: %#lx cannot catch tail\n", + page_to_pfn(page)); + put_page(head); + } + + return 0; +} + +/* + * Do all that is necessary to remove user space mappings. Unmap + * the pages and send SIGBUS to the processes if the data was dirty. + */ +static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, + int flags, struct page **hpagep) +{ + enum ttu_flags ttu = TTU_IGNORE_MLOCK; + struct address_space *mapping; + LIST_HEAD(tokill); + bool unmap_success = true; + int kill = 1, forcekill; + struct page *hpage = *hpagep; + bool mlocked = PageMlocked(hpage); + + /* + * Here we are interested only in user-mapped pages, so skip any + * other types of pages. + */ + if (PageReserved(p) || PageSlab(p)) + return true; + if (!(PageLRU(hpage) || PageHuge(p))) + return true; + + /* + * This check implies we don't kill processes if their pages + * are in the swap cache early. Those are always late kills. + */ + if (!page_mapped(p)) + return true; + + if (PageKsm(p)) { + pr_err("Memory failure: %#lx: can't handle KSM pages.\n", pfn); + return false; + } + + if (PageSwapCache(p)) { + pr_err("Memory failure: %#lx: keeping poisoned page in swap cache\n", + pfn); + ttu |= TTU_IGNORE_HWPOISON; + } + + /* + * Propagate the dirty bit from PTEs to struct page first, because we + * need this to decide if we should kill or just drop the page. + * XXX: the dirty test could be racy: set_page_dirty() may not always + * be called inside page lock (it's recommended but not enforced). + */ + mapping = page_mapping(hpage); + if (!(flags & MF_MUST_KILL) && !PageDirty(hpage) && mapping && + mapping_can_writeback(mapping)) { + if (page_mkclean(hpage)) { + SetPageDirty(hpage); + } else { + kill = 0; + ttu |= TTU_IGNORE_HWPOISON; + pr_info("Memory failure: %#lx: corrupted page was clean: dropped without side effects\n", + pfn); + } + } + + /* + * First collect all the processes that have the page + * mapped in dirty form. This has to be done before try_to_unmap, + * because ttu takes the rmap data structures down. + * + * Error handling: We ignore errors here because + * there's nothing that can be done. + */ + if (kill) + collect_procs(hpage, &tokill, flags & MF_ACTION_REQUIRED); + + if (!PageHuge(hpage)) { + unmap_success = try_to_unmap(hpage, ttu); + } else { + if (!PageAnon(hpage)) { + /* + * For hugetlb pages in shared mappings, try_to_unmap + * could potentially call huge_pmd_unshare. Because of + * this, take semaphore in write mode here and set + * TTU_RMAP_LOCKED to indicate we have taken the lock + * at this higer level. + */ + mapping = hugetlb_page_mapping_lock_write(hpage); + if (mapping) { + unmap_success = try_to_unmap(hpage, + ttu|TTU_RMAP_LOCKED); + i_mmap_unlock_write(mapping); + } else { + pr_info("Memory failure: %#lx: could not lock mapping for mapped huge page\n", pfn); + unmap_success = false; + } + } else { + unmap_success = try_to_unmap(p, ttu); + } + } + if (!unmap_success) + pr_err("Memory failure: %#lx: failed to unmap page (mapcount=%d)\n", + pfn, page_mapcount(p)); + + /* + * try_to_unmap() might put mlocked page in lru cache, so call + * shake_page() again to ensure that it's flushed. + */ + if (mlocked) + shake_page(hpage, 0); + + /* + * Now that the dirty bit has been propagated to the + * struct page and all unmaps done we can decide if + * killing is needed or not. Only kill when the page + * was dirty or the process is not restartable, + * otherwise the tokill list is merely + * freed. When there was a problem unmapping earlier + * use a more force-full uncatchable kill to prevent + * any accesses to the poisoned memory. + */ + forcekill = PageDirty(hpage) || (flags & MF_MUST_KILL); + kill_procs(&tokill, forcekill, !unmap_success, pfn, flags); + + return unmap_success; +} + +static int identify_page_state(unsigned long pfn, struct page *p, + unsigned long page_flags) +{ + struct page_state *ps; + + /* + * The first check uses the current page flags which may not have any + * relevant information. The second check with the saved page flags is + * carried out only if the first check can't determine the page status. + */ + for (ps = error_states;; ps++) + if ((p->flags & ps->mask) == ps->res) + break; + + page_flags |= (p->flags & (1UL << PG_dirty)); + + if (!ps->mask) + for (ps = error_states;; ps++) + if ((page_flags & ps->mask) == ps->res) + break; + return page_action(ps, p, pfn); +} + +static int try_to_split_thp_page(struct page *page, const char *msg) +{ + lock_page(page); + if (!PageAnon(page) || unlikely(split_huge_page(page))) { + unsigned long pfn = page_to_pfn(page); + + unlock_page(page); + if (!PageAnon(page)) + pr_info("%s: %#lx: non anonymous thp\n", msg, pfn); + else + pr_info("%s: %#lx: thp split failed\n", msg, pfn); + put_page(page); + return -EBUSY; + } + unlock_page(page); + + return 0; +} + +static int memory_failure_hugetlb(unsigned long pfn, int flags) +{ + struct page *p = pfn_to_page(pfn); + struct page *head = compound_head(p); + int res; + unsigned long page_flags; + + if (TestSetPageHWPoison(head)) { + pr_err("Memory failure: %#lx: already hardware poisoned\n", + pfn); + return 0; + } + + num_poisoned_pages_inc(); + + if (!(flags & MF_COUNT_INCREASED) && !get_hwpoison_page(p)) { + /* + * Check "filter hit" and "race with other subpage." + */ + lock_page(head); + if (PageHWPoison(head)) { + if ((hwpoison_filter(p) && TestClearPageHWPoison(p)) + || (p != head && TestSetPageHWPoison(head))) { + num_poisoned_pages_dec(); + unlock_page(head); + return 0; + } + } + unlock_page(head); + dissolve_free_huge_page(p); + action_result(pfn, MF_MSG_FREE_HUGE, MF_DELAYED); + return 0; + } + + lock_page(head); + page_flags = head->flags; + + if (!PageHWPoison(head)) { + pr_err("Memory failure: %#lx: just unpoisoned\n", pfn); + num_poisoned_pages_dec(); + unlock_page(head); + put_page(head); + return 0; + } + + /* + * TODO: hwpoison for pud-sized hugetlb doesn't work right now, so + * simply disable it. In order to make it work properly, we need + * make sure that: + * - conversion of a pud that maps an error hugetlb into hwpoison + * entry properly works, and + * - other mm code walking over page table is aware of pud-aligned + * hwpoison entries. + */ + if (huge_page_size(page_hstate(head)) > PMD_SIZE) { + action_result(pfn, MF_MSG_NON_PMD_HUGE, MF_IGNORED); + res = -EBUSY; + goto out; + } + + if (!hwpoison_user_mappings(p, pfn, flags, &head)) { + action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED); + res = -EBUSY; + goto out; + } + + res = identify_page_state(pfn, p, page_flags); +out: + unlock_page(head); + return res; +} + +static int memory_failure_dev_pagemap(unsigned long pfn, int flags, + struct dev_pagemap *pgmap) +{ + struct page *page = pfn_to_page(pfn); + const bool unmap_success = true; + unsigned long size = 0; + struct to_kill *tk; + LIST_HEAD(tokill); + int rc = -EBUSY; + loff_t start; + dax_entry_t cookie; + + if (flags & MF_COUNT_INCREASED) + /* + * Drop the extra refcount in case we come from madvise(). + */ + put_page(page); + + /* device metadata space is not recoverable */ + if (!pgmap_pfn_valid(pgmap, pfn)) { + rc = -ENXIO; + goto out; + } + + /* + * Prevent the inode from being freed while we are interrogating + * the address_space, typically this would be handled by + * lock_page(), but dax pages do not use the page lock. This + * also prevents changes to the mapping of this pfn until + * poison signaling is complete. + */ + cookie = dax_lock_page(page); + if (!cookie) + goto out; + + if (hwpoison_filter(page)) { + rc = 0; + goto unlock; + } + + if (pgmap->type == MEMORY_DEVICE_PRIVATE) { + /* + * TODO: Handle HMM pages which may need coordination + * with device-side memory. + */ + goto unlock; + } + + /* + * Use this flag as an indication that the dax page has been + * remapped UC to prevent speculative consumption of poison. + */ + SetPageHWPoison(page); + + /* + * Unlike System-RAM there is no possibility to swap in a + * different physical page at a given virtual address, so all + * userspace consumption of ZONE_DEVICE memory necessitates + * SIGBUS (i.e. MF_MUST_KILL) + */ + flags |= MF_ACTION_REQUIRED | MF_MUST_KILL; + collect_procs(page, &tokill, flags & MF_ACTION_REQUIRED); + + list_for_each_entry(tk, &tokill, nd) + if (tk->size_shift) + size = max(size, 1UL << tk->size_shift); + if (size) { + /* + * Unmap the largest mapping to avoid breaking up + * device-dax mappings which are constant size. The + * actual size of the mapping being torn down is + * communicated in siginfo, see kill_proc() + */ + start = (page->index << PAGE_SHIFT) & ~(size - 1); + unmap_mapping_range(page->mapping, start, size, 0); + } + kill_procs(&tokill, flags & MF_MUST_KILL, !unmap_success, pfn, flags); + rc = 0; +unlock: + dax_unlock_page(page, cookie); +out: + /* drop pgmap ref acquired in caller */ + put_dev_pagemap(pgmap); + action_result(pfn, MF_MSG_DAX, rc ? MF_FAILED : MF_RECOVERED); + return rc; +} + +/** + * memory_failure - Handle memory failure of a page. + * @pfn: Page Number of the corrupted page + * @flags: fine tune action taken + * + * This function is called by the low level machine check code + * of an architecture when it detects hardware memory corruption + * of a page. It tries its best to recover, which includes + * dropping pages, killing processes etc. + * + * The function is primarily of use for corruptions that + * happen outside the current execution context (e.g. when + * detected by a background scrubber) + * + * Must run in process context (e.g. a work queue) with interrupts + * enabled and no spinlocks hold. + */ +int memory_failure(unsigned long pfn, int flags) +{ + struct page *p; + struct page *hpage; + struct page *orig_head; + struct dev_pagemap *pgmap; + int res; + unsigned long page_flags; + + if (!sysctl_memory_failure_recovery) + panic("Memory failure on page %lx", pfn); + + p = pfn_to_online_page(pfn); + if (!p) { + if (pfn_valid(pfn)) { + pgmap = get_dev_pagemap(pfn, NULL); + if (pgmap) + return memory_failure_dev_pagemap(pfn, flags, + pgmap); + } + pr_err("Memory failure: %#lx: memory outside kernel control\n", + pfn); + return -ENXIO; + } + + if (PageHuge(p)) + return memory_failure_hugetlb(pfn, flags); + if (TestSetPageHWPoison(p)) { + pr_err("Memory failure: %#lx: already hardware poisoned\n", + pfn); + return 0; + } + + orig_head = hpage = compound_head(p); + num_poisoned_pages_inc(); + + /* + * We need/can do nothing about count=0 pages. + * 1) it's a free page, and therefore in safe hand: + * prep_new_page() will be the gate keeper. + * 2) it's part of a non-compound high order page. + * Implies some kernel user: cannot stop them from + * R/W the page; let's pray that the page has been + * used and will be freed some time later. + * In fact it's dangerous to directly bump up page count from 0, + * that may make page_ref_freeze()/page_ref_unfreeze() mismatch. + */ + if (!(flags & MF_COUNT_INCREASED) && !get_hwpoison_page(p)) { + if (is_free_buddy_page(p)) { + action_result(pfn, MF_MSG_BUDDY, MF_DELAYED); + return 0; + } else { + action_result(pfn, MF_MSG_KERNEL_HIGH_ORDER, MF_IGNORED); + return -EBUSY; + } + } + + if (PageTransHuge(hpage)) { + if (try_to_split_thp_page(p, "Memory Failure") < 0) { + action_result(pfn, MF_MSG_UNSPLIT_THP, MF_IGNORED); + return -EBUSY; + } + VM_BUG_ON_PAGE(!page_count(p), p); + } + + /* + * We ignore non-LRU pages for good reasons. + * - PG_locked is only well defined for LRU pages and a few others + * - to avoid races with __SetPageLocked() + * - to avoid races with __SetPageSlab*() (and more non-atomic ops) + * The check (unnecessarily) ignores LRU pages being isolated and + * walked by the page reclaim code, however that's not a big loss. + */ + shake_page(p, 0); + /* shake_page could have turned it free. */ + if (!PageLRU(p) && is_free_buddy_page(p)) { + if (flags & MF_COUNT_INCREASED) + action_result(pfn, MF_MSG_BUDDY, MF_DELAYED); + else + action_result(pfn, MF_MSG_BUDDY_2ND, MF_DELAYED); + return 0; + } + + lock_page(p); + + /* + * The page could have changed compound pages during the locking. + * If this happens just bail out. + */ + if (PageCompound(p) && compound_head(p) != orig_head) { + action_result(pfn, MF_MSG_DIFFERENT_COMPOUND, MF_IGNORED); + res = -EBUSY; + goto out; + } + + /* + * We use page flags to determine what action should be taken, but + * the flags can be modified by the error containment action. One + * example is an mlocked page, where PG_mlocked is cleared by + * page_remove_rmap() in try_to_unmap_one(). So to determine page status + * correctly, we save a copy of the page flags at this time. + */ + page_flags = p->flags; + + /* + * unpoison always clear PG_hwpoison inside page lock + */ + if (!PageHWPoison(p)) { + pr_err("Memory failure: %#lx: just unpoisoned\n", pfn); + num_poisoned_pages_dec(); + unlock_page(p); + put_page(p); + return 0; + } + if (hwpoison_filter(p)) { + if (TestClearPageHWPoison(p)) + num_poisoned_pages_dec(); + unlock_page(p); + put_page(p); + return 0; + } + + /* + * __munlock_pagevec may clear a writeback page's LRU flag without + * page_lock. We need wait writeback completion for this page or it + * may trigger vfs BUG while evict inode. + */ + if (!PageTransTail(p) && !PageLRU(p) && !PageWriteback(p)) + goto identify_page_state; + + /* + * It's very difficult to mess with pages currently under IO + * and in many cases impossible, so we just avoid it here. + */ + wait_on_page_writeback(p); + + /* + * Now take care of user space mappings. + * Abort on fail: __delete_from_page_cache() assumes unmapped page. + */ + if (!hwpoison_user_mappings(p, pfn, flags, &p)) { + action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED); + res = -EBUSY; + goto out; + } + + /* + * Torn down by someone else? + */ + if (PageLRU(p) && !PageSwapCache(p) && p->mapping == NULL) { + action_result(pfn, MF_MSG_TRUNCATED_LRU, MF_IGNORED); + res = -EBUSY; + goto out; + } + +identify_page_state: + res = identify_page_state(pfn, p, page_flags); +out: + unlock_page(p); + return res; +} +EXPORT_SYMBOL_GPL(memory_failure); + +#define MEMORY_FAILURE_FIFO_ORDER 4 +#define MEMORY_FAILURE_FIFO_SIZE (1 << MEMORY_FAILURE_FIFO_ORDER) + +struct memory_failure_entry { + unsigned long pfn; + int flags; +}; + +struct memory_failure_cpu { + DECLARE_KFIFO(fifo, struct memory_failure_entry, + MEMORY_FAILURE_FIFO_SIZE); + spinlock_t lock; + struct work_struct work; +}; + +static DEFINE_PER_CPU(struct memory_failure_cpu, memory_failure_cpu); + +/** + * memory_failure_queue - Schedule handling memory failure of a page. + * @pfn: Page Number of the corrupted page + * @flags: Flags for memory failure handling + * + * This function is called by the low level hardware error handler + * when it detects hardware memory corruption of a page. It schedules + * the recovering of error page, including dropping pages, killing + * processes etc. + * + * The function is primarily of use for corruptions that + * happen outside the current execution context (e.g. when + * detected by a background scrubber) + * + * Can run in IRQ context. + */ +void memory_failure_queue(unsigned long pfn, int flags) +{ + struct memory_failure_cpu *mf_cpu; + unsigned long proc_flags; + struct memory_failure_entry entry = { + .pfn = pfn, + .flags = flags, + }; + + mf_cpu = &get_cpu_var(memory_failure_cpu); + spin_lock_irqsave(&mf_cpu->lock, proc_flags); + if (kfifo_put(&mf_cpu->fifo, entry)) + schedule_work_on(smp_processor_id(), &mf_cpu->work); + else + pr_err("Memory failure: buffer overflow when queuing memory failure at %#lx\n", + pfn); + spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); + put_cpu_var(memory_failure_cpu); +} +EXPORT_SYMBOL_GPL(memory_failure_queue); + +static void memory_failure_work_func(struct work_struct *work) +{ + struct memory_failure_cpu *mf_cpu; + struct memory_failure_entry entry = { 0, }; + unsigned long proc_flags; + int gotten; + + mf_cpu = container_of(work, struct memory_failure_cpu, work); + for (;;) { + spin_lock_irqsave(&mf_cpu->lock, proc_flags); + gotten = kfifo_get(&mf_cpu->fifo, &entry); + spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); + if (!gotten) + break; + if (entry.flags & MF_SOFT_OFFLINE) + soft_offline_page(entry.pfn, entry.flags); + else + memory_failure(entry.pfn, entry.flags); + } +} + +/* + * Process memory_failure work queued on the specified CPU. + * Used to avoid return-to-userspace racing with the memory_failure workqueue. + */ +void memory_failure_queue_kick(int cpu) +{ + struct memory_failure_cpu *mf_cpu; + + mf_cpu = &per_cpu(memory_failure_cpu, cpu); + cancel_work_sync(&mf_cpu->work); + memory_failure_work_func(&mf_cpu->work); +} + +static int __init memory_failure_init(void) +{ + struct memory_failure_cpu *mf_cpu; + int cpu; + + for_each_possible_cpu(cpu) { + mf_cpu = &per_cpu(memory_failure_cpu, cpu); + spin_lock_init(&mf_cpu->lock); + INIT_KFIFO(mf_cpu->fifo); + INIT_WORK(&mf_cpu->work, memory_failure_work_func); + } + + return 0; +} +core_initcall(memory_failure_init); + +#define unpoison_pr_info(fmt, pfn, rs) \ +({ \ + if (__ratelimit(rs)) \ + pr_info(fmt, pfn); \ +}) + +/** + * unpoison_memory - Unpoison a previously poisoned page + * @pfn: Page number of the to be unpoisoned page + * + * Software-unpoison a page that has been poisoned by + * memory_failure() earlier. + * + * This is only done on the software-level, so it only works + * for linux injected failures, not real hardware failures + * + * Returns 0 for success, otherwise -errno. + */ +int unpoison_memory(unsigned long pfn) +{ + struct page *page; + struct page *p; + int freeit = 0; + static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); + + if (!pfn_valid(pfn)) + return -ENXIO; + + p = pfn_to_page(pfn); + page = compound_head(p); + + if (!PageHWPoison(p)) { + unpoison_pr_info("Unpoison: Page was already unpoisoned %#lx\n", + pfn, &unpoison_rs); + return 0; + } + + if (page_count(page) > 1) { + unpoison_pr_info("Unpoison: Someone grabs the hwpoison page %#lx\n", + pfn, &unpoison_rs); + return 0; + } + + if (page_mapped(page)) { + unpoison_pr_info("Unpoison: Someone maps the hwpoison page %#lx\n", + pfn, &unpoison_rs); + return 0; + } + + if (page_mapping(page)) { + unpoison_pr_info("Unpoison: the hwpoison page has non-NULL mapping %#lx\n", + pfn, &unpoison_rs); + return 0; + } + + /* + * unpoison_memory() can encounter thp only when the thp is being + * worked by memory_failure() and the page lock is not held yet. + * In such case, we yield to memory_failure() and make unpoison fail. + */ + if (!PageHuge(page) && PageTransHuge(page)) { + unpoison_pr_info("Unpoison: Memory failure is now running on %#lx\n", + pfn, &unpoison_rs); + return 0; + } + + if (!get_hwpoison_page(p)) { + if (TestClearPageHWPoison(p)) + num_poisoned_pages_dec(); + unpoison_pr_info("Unpoison: Software-unpoisoned free page %#lx\n", + pfn, &unpoison_rs); + return 0; + } + + lock_page(page); + /* + * This test is racy because PG_hwpoison is set outside of page lock. + * That's acceptable because that won't trigger kernel panic. Instead, + * the PG_hwpoison page will be caught and isolated on the entrance to + * the free buddy page pool. + */ + if (TestClearPageHWPoison(page)) { + unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n", + pfn, &unpoison_rs); + num_poisoned_pages_dec(); + freeit = 1; + } + unlock_page(page); + + put_page(page); + if (freeit && !(pfn == my_zero_pfn(0) && page_count(p) == 1)) + put_page(page); + + return 0; +} +EXPORT_SYMBOL(unpoison_memory); + +/* + * Safely get reference count of an arbitrary page. + * Returns 0 for a free page, 1 for an in-use page, -EIO for a page-type we + * cannot handle and -EBUSY if we raced with an allocation. + * We only incremented refcount in case the page was already in-use and it is + * a known type we can handle. + */ +static int get_any_page(struct page *p, int flags) +{ + int ret = 0, pass = 0; + bool count_increased = false; + + if (flags & MF_COUNT_INCREASED) + count_increased = true; + +try_again: + if (!count_increased && !get_hwpoison_page(p)) { + if (page_count(p)) { + /* We raced with an allocation, retry. */ + if (pass++ < 3) + goto try_again; + ret = -EBUSY; + } else if (!PageHuge(p) && !is_free_buddy_page(p)) { + /* We raced with put_page, retry. */ + if (pass++ < 3) + goto try_again; + ret = -EIO; + } + } else { + if (PageHuge(p) || PageLRU(p) || __PageMovable(p)) { + ret = 1; + } else { + /* + * A page we cannot handle. Check whether we can turn + * it into something we can handle. + */ + if (pass++ < 3) { + put_page(p); + shake_page(p, 1); + count_increased = false; + goto try_again; + } + put_page(p); + ret = -EIO; + } + } + + return ret; +} + +static bool isolate_page(struct page *page, struct list_head *pagelist) +{ + bool isolated = false; + bool lru = PageLRU(page); + + if (PageHuge(page)) { + isolated = !isolate_hugetlb(page, pagelist); + } else { + if (lru) + isolated = !isolate_lru_page(page); + else + isolated = !isolate_movable_page(page, ISOLATE_UNEVICTABLE); + + if (isolated) + list_add(&page->lru, pagelist); + } + + if (isolated && lru) + inc_node_page_state(page, NR_ISOLATED_ANON + + page_is_file_lru(page)); + + /* + * If we succeed to isolate the page, we grabbed another refcount on + * the page, so we can safely drop the one we got from get_any_pages(). + * If we failed to isolate the page, it means that we cannot go further + * and we will return an error, so drop the reference we got from + * get_any_pages() as well. + */ + put_page(page); + return isolated; +} + +/* + * __soft_offline_page handles hugetlb-pages and non-hugetlb pages. + * If the page is a non-dirty unmapped page-cache page, it simply invalidates. + * If the page is mapped, it migrates the contents over. + */ +static int __soft_offline_page(struct page *page) +{ + int ret = 0; + unsigned long pfn = page_to_pfn(page); + struct page *hpage = compound_head(page); + char const *msg_page[] = {"page", "hugepage"}; + bool huge = PageHuge(page); + LIST_HEAD(pagelist); + struct migration_target_control mtc = { + .nid = NUMA_NO_NODE, + .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL, + }; + + /* + * Check PageHWPoison again inside page lock because PageHWPoison + * is set by memory_failure() outside page lock. Note that + * memory_failure() also double-checks PageHWPoison inside page lock, + * so there's no race between soft_offline_page() and memory_failure(). + */ + lock_page(page); + if (!PageHuge(page)) + wait_on_page_writeback(page); + if (PageHWPoison(page)) { + unlock_page(page); + put_page(page); + pr_info("soft offline: %#lx page already poisoned\n", pfn); + return 0; + } + + if (!PageHuge(page)) + /* + * Try to invalidate first. This should work for + * non dirty unmapped page cache pages. + */ + ret = invalidate_inode_page(page); + unlock_page(page); + + /* + * RED-PEN would be better to keep it isolated here, but we + * would need to fix isolation locking first. + */ + if (ret) { + pr_info("soft_offline: %#lx: invalidated\n", pfn); + page_handle_poison(page, false, true); + return 0; + } + + if (isolate_page(hpage, &pagelist)) { + ret = migrate_pages(&pagelist, alloc_migration_target, NULL, + (unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_FAILURE); + if (!ret) { + bool release = !huge; + + if (!page_handle_poison(page, huge, release)) + ret = -EBUSY; + } else { + if (!list_empty(&pagelist)) + putback_movable_pages(&pagelist); + + pr_info("soft offline: %#lx: %s migration failed %d, type %lx (%pGp)\n", + pfn, msg_page[huge], ret, page->flags, &page->flags); + if (ret > 0) + ret = -EBUSY; + } + } else { + pr_info("soft offline: %#lx: %s isolation failed, page count %d, type %lx (%pGp)\n", + pfn, msg_page[huge], page_count(page), page->flags, &page->flags); + ret = -EBUSY; + } + return ret; +} + +static int soft_offline_in_use_page(struct page *page) +{ + struct page *hpage = compound_head(page); + + if (!PageHuge(page) && PageTransHuge(hpage)) + if (try_to_split_thp_page(page, "soft offline") < 0) + return -EBUSY; + return __soft_offline_page(page); +} + +static void put_ref_page(struct page *page) +{ + if (page) + put_page(page); +} + +/** + * soft_offline_page - Soft offline a page. + * @pfn: pfn to soft-offline + * @flags: flags. Same as memory_failure(). + * + * Returns 0 on success, otherwise negated errno. + * + * Soft offline a page, by migration or invalidation, + * without killing anything. This is for the case when + * a page is not corrupted yet (so it's still valid to access), + * but has had a number of corrected errors and is better taken + * out. + * + * The actual policy on when to do that is maintained by + * user space. + * + * This should never impact any application or cause data loss, + * however it might take some time. + * + * This is not a 100% solution for all memory, but tries to be + * ``good enough'' for the majority of memory. + */ +int soft_offline_page(unsigned long pfn, int flags) +{ + int ret; + bool try_again = true; + struct page *page, *ref_page = NULL; + + WARN_ON_ONCE(!pfn_valid(pfn) && (flags & MF_COUNT_INCREASED)); + + if (!pfn_valid(pfn)) + return -ENXIO; + if (flags & MF_COUNT_INCREASED) + ref_page = pfn_to_page(pfn); + + /* Only online pages can be soft-offlined (esp., not ZONE_DEVICE). */ + page = pfn_to_online_page(pfn); + if (!page) { + put_ref_page(ref_page); + return -EIO; + } + + if (PageHWPoison(page)) { + pr_info("%s: %#lx page already poisoned\n", __func__, pfn); + put_ref_page(ref_page); + return 0; + } + +retry: + get_online_mems(); + ret = get_any_page(page, flags); + put_online_mems(); + + if (ret > 0) { + ret = soft_offline_in_use_page(page); + } else if (ret == 0) { + if (!page_handle_poison(page, true, false)) { + if (try_again) { + try_again = false; + flags &= ~MF_COUNT_INCREASED; + goto retry; + } + ret = -EBUSY; + } + } else if (ret == -EIO) { + pr_info("%s: %#lx: unknown page type: %lx (%pGp)\n", + __func__, pfn, page->flags, &page->flags); + } + + return ret; +} diff --git a/mm/memory.c b/mm/memory.c new file mode 100644 index 000000000..1d101aeae --- /dev/null +++ b/mm/memory.c @@ -0,0 +1,5343 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/mm/memory.c + * + * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds + */ + +/* + * demand-loading started 01.12.91 - seems it is high on the list of + * things wanted, and it should be easy to implement. - Linus + */ + +/* + * Ok, demand-loading was easy, shared pages a little bit tricker. Shared + * pages started 02.12.91, seems to work. - Linus. + * + * Tested sharing by executing about 30 /bin/sh: under the old kernel it + * would have taken more than the 6M I have free, but it worked well as + * far as I could see. + * + * Also corrected some "invalidate()"s - I wasn't doing enough of them. + */ + +/* + * Real VM (paging to/from disk) started 18.12.91. Much more work and + * thought has to go into this. Oh, well.. + * 19.12.91 - works, somewhat. Sometimes I get faults, don't know why. + * Found it. Everything seems to work now. + * 20.12.91 - Ok, making the swap-device changeable like the root. + */ + +/* + * 05.04.94 - Multi-page memory management added for v1.1. + * Idea by Alex Bligh (alex@cconcepts.co.uk) + * + * 16.07.99 - Support of BIGMEM added by Gerhard Wichert, Siemens AG + * (Gerhard.Wichert@pdb.siemens.de) + * + * Aug/Sep 2004 Changed to four level page tables (Andi Kleen) + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include +#include +#include +#include +#include +#include + +#include "pgalloc-track.h" +#include "internal.h" + +#if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST) +#warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid. +#endif + +#ifndef CONFIG_NEED_MULTIPLE_NODES +/* use the per-pgdat data instead for discontigmem - mbligh */ +unsigned long max_mapnr; +EXPORT_SYMBOL(max_mapnr); + +struct page *mem_map; +EXPORT_SYMBOL(mem_map); +#endif + +/* + * A number of key systems in x86 including ioremap() rely on the assumption + * that high_memory defines the upper bound on direct map memory, then end + * of ZONE_NORMAL. Under CONFIG_DISCONTIG this means that max_low_pfn and + * highstart_pfn must be the same; there must be no gap between ZONE_NORMAL + * and ZONE_HIGHMEM. + */ +void *high_memory; +EXPORT_SYMBOL(high_memory); + +/* + * Randomize the address space (stacks, mmaps, brk, etc.). + * + * ( When CONFIG_COMPAT_BRK=y we exclude brk from randomization, + * as ancient (libc5 based) binaries can segfault. ) + */ +int randomize_va_space __read_mostly = +#ifdef CONFIG_COMPAT_BRK + 1; +#else + 2; +#endif + +#ifndef arch_faults_on_old_pte +static inline bool arch_faults_on_old_pte(void) +{ + /* + * Those arches which don't have hw access flag feature need to + * implement their own helper. By default, "true" means pagefault + * will be hit on old pte. + */ + return true; +} +#endif + +static int __init disable_randmaps(char *s) +{ + randomize_va_space = 0; + return 1; +} +__setup("norandmaps", disable_randmaps); + +unsigned long zero_pfn __read_mostly; +EXPORT_SYMBOL(zero_pfn); + +unsigned long highest_memmap_pfn __read_mostly; + +/* + * CONFIG_MMU architectures set up ZERO_PAGE in their paging_init() + */ +static int __init init_zero_pfn(void) +{ + zero_pfn = page_to_pfn(ZERO_PAGE(0)); + return 0; +} +early_initcall(init_zero_pfn); + +void mm_trace_rss_stat(struct mm_struct *mm, int member, long count) +{ + trace_rss_stat(mm, member, count); +} + +#if defined(SPLIT_RSS_COUNTING) + +void sync_mm_rss(struct mm_struct *mm) +{ + int i; + + for (i = 0; i < NR_MM_COUNTERS; i++) { + if (current->rss_stat.count[i]) { + add_mm_counter(mm, i, current->rss_stat.count[i]); + current->rss_stat.count[i] = 0; + } + } + current->rss_stat.events = 0; +} + +static void add_mm_counter_fast(struct mm_struct *mm, int member, int val) +{ + struct task_struct *task = current; + + if (likely(task->mm == mm)) + task->rss_stat.count[member] += val; + else + add_mm_counter(mm, member, val); +} +#define inc_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, 1) +#define dec_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, -1) + +/* sync counter once per 64 page faults */ +#define TASK_RSS_EVENTS_THRESH (64) +static void check_sync_rss_stat(struct task_struct *task) +{ + if (unlikely(task != current)) + return; + if (unlikely(task->rss_stat.events++ > TASK_RSS_EVENTS_THRESH)) + sync_mm_rss(task->mm); +} +#else /* SPLIT_RSS_COUNTING */ + +#define inc_mm_counter_fast(mm, member) inc_mm_counter(mm, member) +#define dec_mm_counter_fast(mm, member) dec_mm_counter(mm, member) + +static void check_sync_rss_stat(struct task_struct *task) +{ +} + +#endif /* SPLIT_RSS_COUNTING */ + +/* + * Note: this doesn't free the actual pages themselves. That + * has been handled earlier when unmapping all the memory regions. + */ +static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd, + unsigned long addr) +{ + pgtable_t token = pmd_pgtable(*pmd); + pmd_clear(pmd); + pte_free_tlb(tlb, token, addr); + mm_dec_nr_ptes(tlb->mm); +} + +static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, + unsigned long addr, unsigned long end, + unsigned long floor, unsigned long ceiling) +{ + pmd_t *pmd; + unsigned long next; + unsigned long start; + + start = addr; + pmd = pmd_offset(pud, addr); + do { + next = pmd_addr_end(addr, end); + if (pmd_none_or_clear_bad(pmd)) + continue; + free_pte_range(tlb, pmd, addr); + } while (pmd++, addr = next, addr != end); + + start &= PUD_MASK; + if (start < floor) + return; + if (ceiling) { + ceiling &= PUD_MASK; + if (!ceiling) + return; + } + if (end - 1 > ceiling - 1) + return; + + pmd = pmd_offset(pud, start); + pud_clear(pud); + pmd_free_tlb(tlb, pmd, start); + mm_dec_nr_pmds(tlb->mm); +} + +static inline void free_pud_range(struct mmu_gather *tlb, p4d_t *p4d, + unsigned long addr, unsigned long end, + unsigned long floor, unsigned long ceiling) +{ + pud_t *pud; + unsigned long next; + unsigned long start; + + start = addr; + pud = pud_offset(p4d, addr); + do { + next = pud_addr_end(addr, end); + if (pud_none_or_clear_bad(pud)) + continue; + free_pmd_range(tlb, pud, addr, next, floor, ceiling); + } while (pud++, addr = next, addr != end); + + start &= P4D_MASK; + if (start < floor) + return; + if (ceiling) { + ceiling &= P4D_MASK; + if (!ceiling) + return; + } + if (end - 1 > ceiling - 1) + return; + + pud = pud_offset(p4d, start); + p4d_clear(p4d); + pud_free_tlb(tlb, pud, start); + mm_dec_nr_puds(tlb->mm); +} + +static inline void free_p4d_range(struct mmu_gather *tlb, pgd_t *pgd, + unsigned long addr, unsigned long end, + unsigned long floor, unsigned long ceiling) +{ + p4d_t *p4d; + unsigned long next; + unsigned long start; + + start = addr; + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(p4d)) + continue; + free_pud_range(tlb, p4d, addr, next, floor, ceiling); + } while (p4d++, addr = next, addr != end); + + start &= PGDIR_MASK; + if (start < floor) + return; + if (ceiling) { + ceiling &= PGDIR_MASK; + if (!ceiling) + return; + } + if (end - 1 > ceiling - 1) + return; + + p4d = p4d_offset(pgd, start); + pgd_clear(pgd); + p4d_free_tlb(tlb, p4d, start); +} + +/* + * This function frees user-level page tables of a process. + */ +void free_pgd_range(struct mmu_gather *tlb, + unsigned long addr, unsigned long end, + unsigned long floor, unsigned long ceiling) +{ + pgd_t *pgd; + unsigned long next; + + /* + * The next few lines have given us lots of grief... + * + * Why are we testing PMD* at this top level? Because often + * there will be no work to do at all, and we'd prefer not to + * go all the way down to the bottom just to discover that. + * + * Why all these "- 1"s? Because 0 represents both the bottom + * of the address space and the top of it (using -1 for the + * top wouldn't help much: the masks would do the wrong thing). + * The rule is that addr 0 and floor 0 refer to the bottom of + * the address space, but end 0 and ceiling 0 refer to the top + * Comparisons need to use "end - 1" and "ceiling - 1" (though + * that end 0 case should be mythical). + * + * Wherever addr is brought up or ceiling brought down, we must + * be careful to reject "the opposite 0" before it confuses the + * subsequent tests. But what about where end is brought down + * by PMD_SIZE below? no, end can't go down to 0 there. + * + * Whereas we round start (addr) and ceiling down, by different + * masks at different levels, in order to test whether a table + * now has no other vmas using it, so can be freed, we don't + * bother to round floor or end up - the tests don't need that. + */ + + addr &= PMD_MASK; + if (addr < floor) { + addr += PMD_SIZE; + if (!addr) + return; + } + if (ceiling) { + ceiling &= PMD_MASK; + if (!ceiling) + return; + } + if (end - 1 > ceiling - 1) + end -= PMD_SIZE; + if (addr > end - 1) + return; + /* + * We add page table cache pages with PAGE_SIZE, + * (see pte_free_tlb()), flush the tlb if we need + */ + tlb_change_page_size(tlb, PAGE_SIZE); + pgd = pgd_offset(tlb->mm, addr); + do { + next = pgd_addr_end(addr, end); + if (pgd_none_or_clear_bad(pgd)) + continue; + free_p4d_range(tlb, pgd, addr, next, floor, ceiling); + } while (pgd++, addr = next, addr != end); +} + +void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, + unsigned long floor, unsigned long ceiling) +{ + while (vma) { + struct vm_area_struct *next = vma->vm_next; + unsigned long addr = vma->vm_start; + + /* + * Hide vma from rmap and truncate_pagecache before freeing + * pgtables + */ + unlink_anon_vmas(vma); + unlink_file_vma(vma); + + if (is_vm_hugetlb_page(vma)) { + hugetlb_free_pgd_range(tlb, addr, vma->vm_end, + floor, next ? next->vm_start : ceiling); + } else { + /* + * Optimization: gather nearby vmas into one call down + */ + while (next && next->vm_start <= vma->vm_end + PMD_SIZE + && !is_vm_hugetlb_page(next)) { + vma = next; + next = vma->vm_next; + unlink_anon_vmas(vma); + unlink_file_vma(vma); + } + free_pgd_range(tlb, addr, vma->vm_end, + floor, next ? next->vm_start : ceiling); + } + vma = next; + } +} + +int __pte_alloc(struct mm_struct *mm, pmd_t *pmd) +{ + spinlock_t *ptl; + pgtable_t new = pte_alloc_one(mm); + if (!new) + return -ENOMEM; + + /* + * Ensure all pte setup (eg. pte page lock and page clearing) are + * visible before the pte is made visible to other CPUs by being + * put into page tables. + * + * The other side of the story is the pointer chasing in the page + * table walking code (when walking the page table without locking; + * ie. most of the time). Fortunately, these data accesses consist + * of a chain of data-dependent loads, meaning most CPUs (alpha + * being the notable exception) will already guarantee loads are + * seen in-order. See the alpha page table accessors for the + * smp_rmb() barriers in page table walking code. + */ + smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */ + + ptl = pmd_lock(mm, pmd); + if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ + mm_inc_nr_ptes(mm); + pmd_populate(mm, pmd, new); + new = NULL; + } + spin_unlock(ptl); + if (new) + pte_free(mm, new); + return 0; +} + +int __pte_alloc_kernel(pmd_t *pmd) +{ + pte_t *new = pte_alloc_one_kernel(&init_mm); + if (!new) + return -ENOMEM; + + smp_wmb(); /* See comment in __pte_alloc */ + + spin_lock(&init_mm.page_table_lock); + if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ + pmd_populate_kernel(&init_mm, pmd, new); + new = NULL; + } + spin_unlock(&init_mm.page_table_lock); + if (new) + pte_free_kernel(&init_mm, new); + return 0; +} + +static inline void init_rss_vec(int *rss) +{ + memset(rss, 0, sizeof(int) * NR_MM_COUNTERS); +} + +static inline void add_mm_rss_vec(struct mm_struct *mm, int *rss) +{ + int i; + + if (current->mm == mm) + sync_mm_rss(mm); + for (i = 0; i < NR_MM_COUNTERS; i++) + if (rss[i]) + add_mm_counter(mm, i, rss[i]); +} + +/* + * This function is called to print an error when a bad pte + * is found. For example, we might have a PFN-mapped pte in + * a region that doesn't allow it. + * + * The calling function must still handle the error. + */ +static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, + pte_t pte, struct page *page) +{ + pgd_t *pgd = pgd_offset(vma->vm_mm, addr); + p4d_t *p4d = p4d_offset(pgd, addr); + pud_t *pud = pud_offset(p4d, addr); + pmd_t *pmd = pmd_offset(pud, addr); + struct address_space *mapping; + pgoff_t index; + static unsigned long resume; + static unsigned long nr_shown; + static unsigned long nr_unshown; + + /* + * Allow a burst of 60 reports, then keep quiet for that minute; + * or allow a steady drip of one report per second. + */ + if (nr_shown == 60) { + if (time_before(jiffies, resume)) { + nr_unshown++; + return; + } + if (nr_unshown) { + pr_alert("BUG: Bad page map: %lu messages suppressed\n", + nr_unshown); + nr_unshown = 0; + } + nr_shown = 0; + } + if (nr_shown++ == 0) + resume = jiffies + 60 * HZ; + + mapping = vma->vm_file ? vma->vm_file->f_mapping : NULL; + index = linear_page_index(vma, addr); + + pr_alert("BUG: Bad page map in process %s pte:%08llx pmd:%08llx\n", + current->comm, + (long long)pte_val(pte), (long long)pmd_val(*pmd)); + if (page) + dump_page(page, "bad pte"); + pr_alert("addr:%px vm_flags:%08lx anon_vma:%px mapping:%px index:%lx\n", + (void *)addr, vma->vm_flags, vma->anon_vma, mapping, index); + pr_alert("file:%pD fault:%ps mmap:%ps readpage:%ps\n", + vma->vm_file, + vma->vm_ops ? vma->vm_ops->fault : NULL, + vma->vm_file ? vma->vm_file->f_op->mmap : NULL, + mapping ? mapping->a_ops->readpage : NULL); + dump_stack(); + add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); +} + +/* + * vm_normal_page -- This function gets the "struct page" associated with a pte. + * + * "Special" mappings do not wish to be associated with a "struct page" (either + * it doesn't exist, or it exists but they don't want to touch it). In this + * case, NULL is returned here. "Normal" mappings do have a struct page. + * + * There are 2 broad cases. Firstly, an architecture may define a pte_special() + * pte bit, in which case this function is trivial. Secondly, an architecture + * may not have a spare pte bit, which requires a more complicated scheme, + * described below. + * + * A raw VM_PFNMAP mapping (ie. one that is not COWed) is always considered a + * special mapping (even if there are underlying and valid "struct pages"). + * COWed pages of a VM_PFNMAP are always normal. + * + * The way we recognize COWed pages within VM_PFNMAP mappings is through the + * rules set up by "remap_pfn_range()": the vma will have the VM_PFNMAP bit + * set, and the vm_pgoff will point to the first PFN mapped: thus every special + * mapping will always honor the rule + * + * pfn_of_page == vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT) + * + * And for normal mappings this is false. + * + * This restricts such mappings to be a linear translation from virtual address + * to pfn. To get around this restriction, we allow arbitrary mappings so long + * as the vma is not a COW mapping; in that case, we know that all ptes are + * special (because none can have been COWed). + * + * + * In order to support COW of arbitrary special mappings, we have VM_MIXEDMAP. + * + * VM_MIXEDMAP mappings can likewise contain memory with or without "struct + * page" backing, however the difference is that _all_ pages with a struct + * page (that is, those where pfn_valid is true) are refcounted and considered + * normal pages by the VM. The disadvantage is that pages are refcounted + * (which can be slower and simply not an option for some PFNMAP users). The + * advantage is that we don't have to follow the strict linearity rule of + * PFNMAP mappings in order to support COWable mappings. + * + */ +struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, + pte_t pte) +{ + unsigned long pfn = pte_pfn(pte); + + if (IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL)) { + if (likely(!pte_special(pte))) + goto check_pfn; + if (vma->vm_ops && vma->vm_ops->find_special_page) + return vma->vm_ops->find_special_page(vma, addr); + if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) + return NULL; + if (is_zero_pfn(pfn)) + return NULL; + if (pte_devmap(pte)) + return NULL; + + print_bad_pte(vma, addr, pte, NULL); + return NULL; + } + + /* !CONFIG_ARCH_HAS_PTE_SPECIAL case follows: */ + + if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { + if (vma->vm_flags & VM_MIXEDMAP) { + if (!pfn_valid(pfn)) + return NULL; + goto out; + } else { + unsigned long off; + off = (addr - vma->vm_start) >> PAGE_SHIFT; + if (pfn == vma->vm_pgoff + off) + return NULL; + if (!is_cow_mapping(vma->vm_flags)) + return NULL; + } + } + + if (is_zero_pfn(pfn)) + return NULL; + +check_pfn: + if (unlikely(pfn > highest_memmap_pfn)) { + print_bad_pte(vma, addr, pte, NULL); + return NULL; + } + + /* + * NOTE! We still have PageReserved() pages in the page tables. + * eg. VDSO mappings can cause them to exist. + */ +out: + return pfn_to_page(pfn); +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t pmd) +{ + unsigned long pfn = pmd_pfn(pmd); + + /* + * There is no pmd_special() but there may be special pmds, e.g. + * in a direct-access (dax) mapping, so let's just replicate the + * !CONFIG_ARCH_HAS_PTE_SPECIAL case from vm_normal_page() here. + */ + if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { + if (vma->vm_flags & VM_MIXEDMAP) { + if (!pfn_valid(pfn)) + return NULL; + goto out; + } else { + unsigned long off; + off = (addr - vma->vm_start) >> PAGE_SHIFT; + if (pfn == vma->vm_pgoff + off) + return NULL; + if (!is_cow_mapping(vma->vm_flags)) + return NULL; + } + } + + if (pmd_devmap(pmd)) + return NULL; + if (is_huge_zero_pmd(pmd)) + return NULL; + if (unlikely(pfn > highest_memmap_pfn)) + return NULL; + + /* + * NOTE! We still have PageReserved() pages in the page tables. + * eg. VDSO mappings can cause them to exist. + */ +out: + return pfn_to_page(pfn); +} +#endif + +/* + * copy one vm_area from one task to the other. Assumes the page tables + * already present in the new task to be cleared in the whole range + * covered by this vma. + */ + +static unsigned long +copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *dst_vma, + struct vm_area_struct *src_vma, unsigned long addr, int *rss) +{ + unsigned long vm_flags = dst_vma->vm_flags; + pte_t pte = *src_pte; + struct page *page; + swp_entry_t entry = pte_to_swp_entry(pte); + + if (likely(!non_swap_entry(entry))) { + if (swap_duplicate(entry) < 0) + return entry.val; + + /* make sure dst_mm is on swapoff's mmlist. */ + if (unlikely(list_empty(&dst_mm->mmlist))) { + spin_lock(&mmlist_lock); + if (list_empty(&dst_mm->mmlist)) + list_add(&dst_mm->mmlist, + &src_mm->mmlist); + spin_unlock(&mmlist_lock); + } + rss[MM_SWAPENTS]++; + } else if (is_migration_entry(entry)) { + page = migration_entry_to_page(entry); + + rss[mm_counter(page)]++; + + if (is_write_migration_entry(entry) && + is_cow_mapping(vm_flags)) { + /* + * COW mappings require pages in both + * parent and child to be set to read. + */ + make_migration_entry_read(&entry); + pte = swp_entry_to_pte(entry); + if (pte_swp_soft_dirty(*src_pte)) + pte = pte_swp_mksoft_dirty(pte); + if (pte_swp_uffd_wp(*src_pte)) + pte = pte_swp_mkuffd_wp(pte); + set_pte_at(src_mm, addr, src_pte, pte); + } + } else if (is_device_private_entry(entry)) { + page = device_private_entry_to_page(entry); + + /* + * Update rss count even for unaddressable pages, as + * they should treated just like normal pages in this + * respect. + * + * We will likely want to have some new rss counters + * for unaddressable pages, at some point. But for now + * keep things as they are. + */ + get_page(page); + rss[mm_counter(page)]++; + page_dup_rmap(page, false); + + /* + * We do not preserve soft-dirty information, because so + * far, checkpoint/restore is the only feature that + * requires that. And checkpoint/restore does not work + * when a device driver is involved (you cannot easily + * save and restore device driver state). + */ + if (is_write_device_private_entry(entry) && + is_cow_mapping(vm_flags)) { + make_device_private_entry_read(&entry); + pte = swp_entry_to_pte(entry); + if (pte_swp_uffd_wp(*src_pte)) + pte = pte_swp_mkuffd_wp(pte); + set_pte_at(src_mm, addr, src_pte, pte); + } + } + if (!userfaultfd_wp(dst_vma)) + pte = pte_swp_clear_uffd_wp(pte); + set_pte_at(dst_mm, addr, dst_pte, pte); + return 0; +} + +/* + * Copy a present and normal page if necessary. + * + * NOTE! The usual case is that this doesn't need to do + * anything, and can just return a positive value. That + * will let the caller know that it can just increase + * the page refcount and re-use the pte the traditional + * way. + * + * But _if_ we need to copy it because it needs to be + * pinned in the parent (and the child should get its own + * copy rather than just a reference to the same page), + * we'll do that here and return zero to let the caller + * know we're done. + * + * And if we need a pre-allocated page but don't yet have + * one, return a negative error to let the preallocation + * code know so that it can do so outside the page table + * lock. + */ +static inline int +copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, + pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss, + struct page **prealloc, pte_t pte, struct page *page) +{ + struct mm_struct *src_mm = src_vma->vm_mm; + struct page *new_page; + + if (!is_cow_mapping(src_vma->vm_flags)) + return 1; + + /* + * What we want to do is to check whether this page may + * have been pinned by the parent process. If so, + * instead of wrprotect the pte on both sides, we copy + * the page immediately so that we'll always guarantee + * the pinned page won't be randomly replaced in the + * future. + * + * The page pinning checks are just "has this mm ever + * seen pinning", along with the (inexact) check of + * the page count. That might give false positives for + * for pinning, but it will work correctly. + */ + if (likely(!atomic_read(&src_mm->has_pinned))) + return 1; + if (likely(!page_maybe_dma_pinned(page))) + return 1; + + /* + * The vma->anon_vma of the child process may be NULL + * because the entire vma does not contain anonymous pages. + * A BUG will occur when the copy_present_page() passes + * a copy of a non-anonymous page of that vma to the + * page_add_new_anon_rmap() to set up new anonymous rmap. + * Return 1 if the page is not an anonymous page. + */ + if (!PageAnon(page)) + return 1; + + new_page = *prealloc; + if (!new_page) + return -EAGAIN; + + /* + * We have a prealloc page, all good! Take it + * over and copy the page & arm it. + */ + *prealloc = NULL; + copy_user_highpage(new_page, page, addr, src_vma); + __SetPageUptodate(new_page); + page_add_new_anon_rmap(new_page, dst_vma, addr, false); + lru_cache_add_inactive_or_unevictable(new_page, dst_vma); + rss[mm_counter(new_page)]++; + + /* All done, just insert the new page copy in the child */ + pte = mk_pte(new_page, dst_vma->vm_page_prot); + pte = maybe_mkwrite(pte_mkdirty(pte), dst_vma); + if (userfaultfd_pte_wp(dst_vma, *src_pte)) + /* Uffd-wp needs to be delivered to dest pte as well */ + pte = pte_wrprotect(pte_mkuffd_wp(pte)); + set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte); + return 0; +} + +/* + * Copy one pte. Returns 0 if succeeded, or -EAGAIN if one preallocated page + * is required to copy this pte. + */ +static inline int +copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, + pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss, + struct page **prealloc) +{ + struct mm_struct *src_mm = src_vma->vm_mm; + unsigned long vm_flags = src_vma->vm_flags; + pte_t pte = *src_pte; + struct page *page; + + page = vm_normal_page(src_vma, addr, pte); + if (page) { + int retval; + + retval = copy_present_page(dst_vma, src_vma, dst_pte, src_pte, + addr, rss, prealloc, pte, page); + if (retval <= 0) + return retval; + + get_page(page); + page_dup_rmap(page, false); + rss[mm_counter(page)]++; + } + + /* + * If it's a COW mapping, write protect it both + * in the parent and the child + */ + if (is_cow_mapping(vm_flags) && pte_write(pte)) { + ptep_set_wrprotect(src_mm, addr, src_pte); + pte = pte_wrprotect(pte); + } + + /* + * If it's a shared mapping, mark it clean in + * the child + */ + if (vm_flags & VM_SHARED) + pte = pte_mkclean(pte); + pte = pte_mkold(pte); + + if (!userfaultfd_wp(dst_vma)) + pte = pte_clear_uffd_wp(pte); + + set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte); + return 0; +} + +static inline struct page * +page_copy_prealloc(struct mm_struct *src_mm, struct vm_area_struct *vma, + unsigned long addr) +{ + struct page *new_page; + + new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, addr); + if (!new_page) + return NULL; + + if (mem_cgroup_charge(new_page, src_mm, GFP_KERNEL)) { + put_page(new_page); + return NULL; + } + cgroup_throttle_swaprate(new_page, GFP_KERNEL); + + return new_page; +} + +static int +copy_pte_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, + pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, + unsigned long end) +{ + struct mm_struct *dst_mm = dst_vma->vm_mm; + struct mm_struct *src_mm = src_vma->vm_mm; + pte_t *orig_src_pte, *orig_dst_pte; + pte_t *src_pte, *dst_pte; + spinlock_t *src_ptl, *dst_ptl; + int progress, ret = 0; + int rss[NR_MM_COUNTERS]; + swp_entry_t entry = (swp_entry_t){0}; + struct page *prealloc = NULL; + +again: + progress = 0; + init_rss_vec(rss); + + dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl); + if (!dst_pte) { + ret = -ENOMEM; + goto out; + } + src_pte = pte_offset_map(src_pmd, addr); + src_ptl = pte_lockptr(src_mm, src_pmd); + spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); + orig_src_pte = src_pte; + orig_dst_pte = dst_pte; + arch_enter_lazy_mmu_mode(); + + do { + /* + * We are holding two locks at this point - either of them + * could generate latencies in another task on another CPU. + */ + if (progress >= 32) { + progress = 0; + if (need_resched() || + spin_needbreak(src_ptl) || spin_needbreak(dst_ptl)) + break; + } + if (pte_none(*src_pte)) { + progress++; + continue; + } + if (unlikely(!pte_present(*src_pte))) { + entry.val = copy_nonpresent_pte(dst_mm, src_mm, + dst_pte, src_pte, + dst_vma, src_vma, + addr, rss); + if (entry.val) + break; + progress += 8; + continue; + } + /* copy_present_pte() will clear `*prealloc' if consumed */ + ret = copy_present_pte(dst_vma, src_vma, dst_pte, src_pte, + addr, rss, &prealloc); + /* + * If we need a pre-allocated page for this pte, drop the + * locks, allocate, and try again. + */ + if (unlikely(ret == -EAGAIN)) + break; + if (unlikely(prealloc)) { + /* + * pre-alloc page cannot be reused by next time so as + * to strictly follow mempolicy (e.g., alloc_page_vma() + * will allocate page according to address). This + * could only happen if one pinned pte changed. + */ + put_page(prealloc); + prealloc = NULL; + } + progress += 8; + } while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end); + + arch_leave_lazy_mmu_mode(); + spin_unlock(src_ptl); + pte_unmap(orig_src_pte); + add_mm_rss_vec(dst_mm, rss); + pte_unmap_unlock(orig_dst_pte, dst_ptl); + cond_resched(); + + if (entry.val) { + if (add_swap_count_continuation(entry, GFP_KERNEL) < 0) { + ret = -ENOMEM; + goto out; + } + entry.val = 0; + } else if (ret) { + WARN_ON_ONCE(ret != -EAGAIN); + prealloc = page_copy_prealloc(src_mm, src_vma, addr); + if (!prealloc) + return -ENOMEM; + /* We've captured and resolved the error. Reset, try again. */ + ret = 0; + } + if (addr != end) + goto again; +out: + if (unlikely(prealloc)) + put_page(prealloc); + return ret; +} + +static inline int +copy_pmd_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, + pud_t *dst_pud, pud_t *src_pud, unsigned long addr, + unsigned long end) +{ + struct mm_struct *dst_mm = dst_vma->vm_mm; + struct mm_struct *src_mm = src_vma->vm_mm; + pmd_t *src_pmd, *dst_pmd; + unsigned long next; + + dst_pmd = pmd_alloc(dst_mm, dst_pud, addr); + if (!dst_pmd) + return -ENOMEM; + src_pmd = pmd_offset(src_pud, addr); + do { + next = pmd_addr_end(addr, end); + if (is_swap_pmd(*src_pmd) || pmd_trans_huge(*src_pmd) + || pmd_devmap(*src_pmd)) { + int err; + VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, src_vma); + err = copy_huge_pmd(dst_mm, src_mm, dst_pmd, src_pmd, + addr, dst_vma, src_vma); + if (err == -ENOMEM) + return -ENOMEM; + if (!err) + continue; + /* fall through */ + } + if (pmd_none_or_clear_bad(src_pmd)) + continue; + if (copy_pte_range(dst_vma, src_vma, dst_pmd, src_pmd, + addr, next)) + return -ENOMEM; + } while (dst_pmd++, src_pmd++, addr = next, addr != end); + return 0; +} + +static inline int +copy_pud_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, + p4d_t *dst_p4d, p4d_t *src_p4d, unsigned long addr, + unsigned long end) +{ + struct mm_struct *dst_mm = dst_vma->vm_mm; + struct mm_struct *src_mm = src_vma->vm_mm; + pud_t *src_pud, *dst_pud; + unsigned long next; + + dst_pud = pud_alloc(dst_mm, dst_p4d, addr); + if (!dst_pud) + return -ENOMEM; + src_pud = pud_offset(src_p4d, addr); + do { + next = pud_addr_end(addr, end); + if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) { + int err; + + VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, src_vma); + err = copy_huge_pud(dst_mm, src_mm, + dst_pud, src_pud, addr, src_vma); + if (err == -ENOMEM) + return -ENOMEM; + if (!err) + continue; + /* fall through */ + } + if (pud_none_or_clear_bad(src_pud)) + continue; + if (copy_pmd_range(dst_vma, src_vma, dst_pud, src_pud, + addr, next)) + return -ENOMEM; + } while (dst_pud++, src_pud++, addr = next, addr != end); + return 0; +} + +static inline int +copy_p4d_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, + pgd_t *dst_pgd, pgd_t *src_pgd, unsigned long addr, + unsigned long end) +{ + struct mm_struct *dst_mm = dst_vma->vm_mm; + p4d_t *src_p4d, *dst_p4d; + unsigned long next; + + dst_p4d = p4d_alloc(dst_mm, dst_pgd, addr); + if (!dst_p4d) + return -ENOMEM; + src_p4d = p4d_offset(src_pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(src_p4d)) + continue; + if (copy_pud_range(dst_vma, src_vma, dst_p4d, src_p4d, + addr, next)) + return -ENOMEM; + } while (dst_p4d++, src_p4d++, addr = next, addr != end); + return 0; +} + +int +copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) +{ + pgd_t *src_pgd, *dst_pgd; + unsigned long next; + unsigned long addr = src_vma->vm_start; + unsigned long end = src_vma->vm_end; + struct mm_struct *dst_mm = dst_vma->vm_mm; + struct mm_struct *src_mm = src_vma->vm_mm; + struct mmu_notifier_range range; + bool is_cow; + int ret; + + /* + * Don't copy ptes where a page fault will fill them correctly. + * Fork becomes much lighter when there are big shared or private + * readonly mappings. The tradeoff is that copy_page_range is more + * efficient than faulting. + */ + if (!(src_vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) && + !src_vma->anon_vma) + return 0; + + if (is_vm_hugetlb_page(src_vma)) + return copy_hugetlb_page_range(dst_mm, src_mm, src_vma); + + if (unlikely(src_vma->vm_flags & VM_PFNMAP)) { + /* + * We do not free on error cases below as remove_vma + * gets called on error from higher level routine + */ + ret = track_pfn_copy(src_vma); + if (ret) + return ret; + } + + /* + * We need to invalidate the secondary MMU mappings only when + * there could be a permission downgrade on the ptes of the + * parent mm. And a permission downgrade will only happen if + * is_cow_mapping() returns true. + */ + is_cow = is_cow_mapping(src_vma->vm_flags); + + if (is_cow) { + mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, + 0, src_vma, src_mm, addr, end); + mmu_notifier_invalidate_range_start(&range); + /* + * Disabling preemption is not needed for the write side, as + * the read side doesn't spin, but goes to the mmap_lock. + * + * Use the raw variant of the seqcount_t write API to avoid + * lockdep complaining about preemptibility. + */ + mmap_assert_write_locked(src_mm); + raw_write_seqcount_begin(&src_mm->write_protect_seq); + } + + ret = 0; + dst_pgd = pgd_offset(dst_mm, addr); + src_pgd = pgd_offset(src_mm, addr); + do { + next = pgd_addr_end(addr, end); + if (pgd_none_or_clear_bad(src_pgd)) + continue; + if (unlikely(copy_p4d_range(dst_vma, src_vma, dst_pgd, src_pgd, + addr, next))) { + ret = -ENOMEM; + break; + } + } while (dst_pgd++, src_pgd++, addr = next, addr != end); + + if (is_cow) { + raw_write_seqcount_end(&src_mm->write_protect_seq); + mmu_notifier_invalidate_range_end(&range); + } + return ret; +} + +/* Whether we should zap all COWed (private) pages too */ +static inline bool should_zap_cows(struct zap_details *details) +{ + /* By default, zap all pages */ + if (!details) + return true; + + /* Or, we zap COWed pages only if the caller wants to */ + return !details->check_mapping; +} + +static unsigned long zap_pte_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, pmd_t *pmd, + unsigned long addr, unsigned long end, + struct zap_details *details) +{ + struct mm_struct *mm = tlb->mm; + int force_flush = 0; + int rss[NR_MM_COUNTERS]; + spinlock_t *ptl; + pte_t *start_pte; + pte_t *pte; + swp_entry_t entry; + + tlb_change_page_size(tlb, PAGE_SIZE); +again: + init_rss_vec(rss); + start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + pte = start_pte; + flush_tlb_batched_pending(mm); + arch_enter_lazy_mmu_mode(); + do { + pte_t ptent = *pte; + if (pte_none(ptent)) + continue; + + if (need_resched()) + break; + + if (pte_present(ptent)) { + struct page *page; + + page = vm_normal_page(vma, addr, ptent); + if (unlikely(details) && page) { + /* + * unmap_shared_mapping_pages() wants to + * invalidate cache without truncating: + * unmap shared but keep private pages. + */ + if (details->check_mapping && + details->check_mapping != page_rmapping(page)) + continue; + } + ptent = ptep_get_and_clear_full(mm, addr, pte, + tlb->fullmm); + tlb_remove_tlb_entry(tlb, pte, addr); + if (unlikely(!page)) + continue; + + if (!PageAnon(page)) { + if (pte_dirty(ptent)) { + force_flush = 1; + set_page_dirty(page); + } + if (pte_young(ptent) && + likely(!(vma->vm_flags & VM_SEQ_READ))) + mark_page_accessed(page); + } + rss[mm_counter(page)]--; + page_remove_rmap(page, false); + if (unlikely(page_mapcount(page) < 0)) + print_bad_pte(vma, addr, ptent, page); + if (unlikely(__tlb_remove_page(tlb, page))) { + force_flush = 1; + addr += PAGE_SIZE; + break; + } + continue; + } + + entry = pte_to_swp_entry(ptent); + if (is_device_private_entry(entry)) { + struct page *page = device_private_entry_to_page(entry); + + if (unlikely(details && details->check_mapping)) { + /* + * unmap_shared_mapping_pages() wants to + * invalidate cache without truncating: + * unmap shared but keep private pages. + */ + if (details->check_mapping != + page_rmapping(page)) + continue; + } + + pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); + rss[mm_counter(page)]--; + page_remove_rmap(page, false); + put_page(page); + continue; + } + + if (!non_swap_entry(entry)) { + /* Genuine swap entry, hence a private anon page */ + if (!should_zap_cows(details)) + continue; + rss[MM_SWAPENTS]--; + } else if (is_migration_entry(entry)) { + struct page *page; + + page = migration_entry_to_page(entry); + if (details && details->check_mapping && + details->check_mapping != page_rmapping(page)) + continue; + rss[mm_counter(page)]--; + } + if (unlikely(!free_swap_and_cache(entry))) + print_bad_pte(vma, addr, ptent, NULL); + pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); + } while (pte++, addr += PAGE_SIZE, addr != end); + + add_mm_rss_vec(mm, rss); + arch_leave_lazy_mmu_mode(); + + /* Do the actual TLB flush before dropping ptl */ + if (force_flush) + tlb_flush_mmu_tlbonly(tlb); + pte_unmap_unlock(start_pte, ptl); + + /* + * If we forced a TLB flush (either due to running out of + * batch buffers or because we needed to flush dirty TLB + * entries before releasing the ptl), free the batched + * memory too. Restart if we didn't do everything. + */ + if (force_flush) { + force_flush = 0; + tlb_flush_mmu(tlb); + } + + if (addr != end) { + cond_resched(); + goto again; + } + + return addr; +} + +static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, pud_t *pud, + unsigned long addr, unsigned long end, + struct zap_details *details) +{ + pmd_t *pmd; + unsigned long next; + + pmd = pmd_offset(pud, addr); + do { + next = pmd_addr_end(addr, end); + if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) { + if (next - addr != HPAGE_PMD_SIZE) + __split_huge_pmd(vma, pmd, addr, false, NULL); + else if (zap_huge_pmd(tlb, vma, pmd, addr)) + goto next; + /* fall through */ + } else if (details && details->single_page && + PageTransCompound(details->single_page) && + next - addr == HPAGE_PMD_SIZE && pmd_none(*pmd)) { + spinlock_t *ptl = pmd_lock(tlb->mm, pmd); + /* + * Take and drop THP pmd lock so that we cannot return + * prematurely, while zap_huge_pmd() has cleared *pmd, + * but not yet decremented compound_mapcount(). + */ + spin_unlock(ptl); + } + + /* + * Here there can be other concurrent MADV_DONTNEED or + * trans huge page faults running, and if the pmd is + * none or trans huge it can change under us. This is + * because MADV_DONTNEED holds the mmap_lock in read + * mode. + */ + if (pmd_none_or_trans_huge_or_clear_bad(pmd)) + goto next; + next = zap_pte_range(tlb, vma, pmd, addr, next, details); +next: + cond_resched(); + } while (pmd++, addr = next, addr != end); + + return addr; +} + +static inline unsigned long zap_pud_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, p4d_t *p4d, + unsigned long addr, unsigned long end, + struct zap_details *details) +{ + pud_t *pud; + unsigned long next; + + pud = pud_offset(p4d, addr); + do { + next = pud_addr_end(addr, end); + if (pud_trans_huge(*pud) || pud_devmap(*pud)) { + if (next - addr != HPAGE_PUD_SIZE) { + mmap_assert_locked(tlb->mm); + split_huge_pud(vma, pud, addr); + } else if (zap_huge_pud(tlb, vma, pud, addr)) + goto next; + /* fall through */ + } + if (pud_none_or_clear_bad(pud)) + continue; + next = zap_pmd_range(tlb, vma, pud, addr, next, details); +next: + cond_resched(); + } while (pud++, addr = next, addr != end); + + return addr; +} + +static inline unsigned long zap_p4d_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, pgd_t *pgd, + unsigned long addr, unsigned long end, + struct zap_details *details) +{ + p4d_t *p4d; + unsigned long next; + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(p4d)) + continue; + next = zap_pud_range(tlb, vma, p4d, addr, next, details); + } while (p4d++, addr = next, addr != end); + + return addr; +} + +void unmap_page_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, + unsigned long addr, unsigned long end, + struct zap_details *details) +{ + pgd_t *pgd; + unsigned long next; + + BUG_ON(addr >= end); + tlb_start_vma(tlb, vma); + pgd = pgd_offset(vma->vm_mm, addr); + do { + next = pgd_addr_end(addr, end); + if (pgd_none_or_clear_bad(pgd)) + continue; + next = zap_p4d_range(tlb, vma, pgd, addr, next, details); + } while (pgd++, addr = next, addr != end); + tlb_end_vma(tlb, vma); +} + + +static void unmap_single_vma(struct mmu_gather *tlb, + struct vm_area_struct *vma, unsigned long start_addr, + unsigned long end_addr, + struct zap_details *details) +{ + unsigned long start = max(vma->vm_start, start_addr); + unsigned long end; + + if (start >= vma->vm_end) + return; + end = min(vma->vm_end, end_addr); + if (end <= vma->vm_start) + return; + + if (vma->vm_file) + uprobe_munmap(vma, start, end); + + if (unlikely(vma->vm_flags & VM_PFNMAP)) + untrack_pfn(vma, 0, 0); + + if (start != end) { + if (unlikely(is_vm_hugetlb_page(vma))) { + /* + * It is undesirable to test vma->vm_file as it + * should be non-null for valid hugetlb area. + * However, vm_file will be NULL in the error + * cleanup path of mmap_region. When + * hugetlbfs ->mmap method fails, + * mmap_region() nullifies vma->vm_file + * before calling this function to clean up. + * Since no pte has actually been setup, it is + * safe to do nothing in this case. + */ + if (vma->vm_file) { + i_mmap_lock_write(vma->vm_file->f_mapping); + __unmap_hugepage_range_final(tlb, vma, start, end, NULL); + i_mmap_unlock_write(vma->vm_file->f_mapping); + } + } else + unmap_page_range(tlb, vma, start, end, details); + } +} + +/** + * unmap_vmas - unmap a range of memory covered by a list of vma's + * @tlb: address of the caller's struct mmu_gather + * @vma: the starting vma + * @start_addr: virtual address at which to start unmapping + * @end_addr: virtual address at which to end unmapping + * + * Unmap all pages in the vma list. + * + * Only addresses between `start' and `end' will be unmapped. + * + * The VMA list must be sorted in ascending virtual address order. + * + * unmap_vmas() assumes that the caller will flush the whole unmapped address + * range after unmap_vmas() returns. So the only responsibility here is to + * ensure that any thus-far unmapped pages are flushed before unmap_vmas() + * drops the lock and schedules. + */ +void unmap_vmas(struct mmu_gather *tlb, + struct vm_area_struct *vma, unsigned long start_addr, + unsigned long end_addr) +{ + struct mmu_notifier_range range; + + mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm, + start_addr, end_addr); + mmu_notifier_invalidate_range_start(&range); + for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) + unmap_single_vma(tlb, vma, start_addr, end_addr, NULL); + mmu_notifier_invalidate_range_end(&range); +} + +/** + * zap_page_range - remove user pages in a given range + * @vma: vm_area_struct holding the applicable pages + * @start: starting address of pages to zap + * @size: number of bytes to zap + * + * Caller must protect the VMA list + */ +void zap_page_range(struct vm_area_struct *vma, unsigned long start, + unsigned long size) +{ + struct mmu_notifier_range range; + struct mmu_gather tlb; + + lru_add_drain(); + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, + start, start + size); + tlb_gather_mmu(&tlb, vma->vm_mm, start, range.end); + update_hiwater_rss(vma->vm_mm); + mmu_notifier_invalidate_range_start(&range); + for ( ; vma && vma->vm_start < range.end; vma = vma->vm_next) + unmap_single_vma(&tlb, vma, start, range.end, NULL); + mmu_notifier_invalidate_range_end(&range); + tlb_finish_mmu(&tlb, start, range.end); +} + +/** + * zap_page_range_single - remove user pages in a given range + * @vma: vm_area_struct holding the applicable pages + * @address: starting address of pages to zap + * @size: number of bytes to zap + * @details: details of shared cache invalidation + * + * The range must fit into one VMA. + */ +static void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, + unsigned long size, struct zap_details *details) +{ + struct mmu_notifier_range range; + struct mmu_gather tlb; + + lru_add_drain(); + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, + address, address + size); + tlb_gather_mmu(&tlb, vma->vm_mm, address, range.end); + update_hiwater_rss(vma->vm_mm); + mmu_notifier_invalidate_range_start(&range); + unmap_single_vma(&tlb, vma, address, range.end, details); + mmu_notifier_invalidate_range_end(&range); + tlb_finish_mmu(&tlb, address, range.end); +} + +/** + * zap_vma_ptes - remove ptes mapping the vma + * @vma: vm_area_struct holding ptes to be zapped + * @address: starting address of pages to zap + * @size: number of bytes to zap + * + * This function only unmaps ptes assigned to VM_PFNMAP vmas. + * + * The entire address range must be fully contained within the vma. + * + */ +void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, + unsigned long size) +{ + if (address < vma->vm_start || address + size > vma->vm_end || + !(vma->vm_flags & VM_PFNMAP)) + return; + + zap_page_range_single(vma, address, size, NULL); +} +EXPORT_SYMBOL_GPL(zap_vma_ptes); + +static pmd_t *walk_to_pmd(struct mm_struct *mm, unsigned long addr) +{ + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + pgd = pgd_offset(mm, addr); + p4d = p4d_alloc(mm, pgd, addr); + if (!p4d) + return NULL; + pud = pud_alloc(mm, p4d, addr); + if (!pud) + return NULL; + pmd = pmd_alloc(mm, pud, addr); + if (!pmd) + return NULL; + + VM_BUG_ON(pmd_trans_huge(*pmd)); + return pmd; +} + +pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, + spinlock_t **ptl) +{ + pmd_t *pmd = walk_to_pmd(mm, addr); + + if (!pmd) + return NULL; + return pte_alloc_map_lock(mm, pmd, addr, ptl); +} + +static int validate_page_before_insert(struct page *page) +{ + if (PageAnon(page) || PageSlab(page) || page_has_type(page)) + return -EINVAL; + flush_dcache_page(page); + return 0; +} + +static int insert_page_into_pte_locked(struct mm_struct *mm, pte_t *pte, + unsigned long addr, struct page *page, pgprot_t prot) +{ + if (!pte_none(*pte)) + return -EBUSY; + /* Ok, finally just insert the thing.. */ + get_page(page); + inc_mm_counter_fast(mm, mm_counter_file(page)); + page_add_file_rmap(page, false); + set_pte_at(mm, addr, pte, mk_pte(page, prot)); + return 0; +} + +/* + * This is the old fallback for page remapping. + * + * For historical reasons, it only allows reserved pages. Only + * old drivers should use this, and they needed to mark their + * pages reserved for the old functions anyway. + */ +static int insert_page(struct vm_area_struct *vma, unsigned long addr, + struct page *page, pgprot_t prot) +{ + struct mm_struct *mm = vma->vm_mm; + int retval; + pte_t *pte; + spinlock_t *ptl; + + retval = validate_page_before_insert(page); + if (retval) + goto out; + retval = -ENOMEM; + pte = get_locked_pte(mm, addr, &ptl); + if (!pte) + goto out; + retval = insert_page_into_pte_locked(mm, pte, addr, page, prot); + pte_unmap_unlock(pte, ptl); +out: + return retval; +} + +#ifdef pte_index +static int insert_page_in_batch_locked(struct mm_struct *mm, pte_t *pte, + unsigned long addr, struct page *page, pgprot_t prot) +{ + int err; + + if (!page_count(page)) + return -EINVAL; + err = validate_page_before_insert(page); + if (err) + return err; + return insert_page_into_pte_locked(mm, pte, addr, page, prot); +} + +/* insert_pages() amortizes the cost of spinlock operations + * when inserting pages in a loop. Arch *must* define pte_index. + */ +static int insert_pages(struct vm_area_struct *vma, unsigned long addr, + struct page **pages, unsigned long *num, pgprot_t prot) +{ + pmd_t *pmd = NULL; + pte_t *start_pte, *pte; + spinlock_t *pte_lock; + struct mm_struct *const mm = vma->vm_mm; + unsigned long curr_page_idx = 0; + unsigned long remaining_pages_total = *num; + unsigned long pages_to_write_in_pmd; + int ret; +more: + ret = -EFAULT; + pmd = walk_to_pmd(mm, addr); + if (!pmd) + goto out; + + pages_to_write_in_pmd = min_t(unsigned long, + remaining_pages_total, PTRS_PER_PTE - pte_index(addr)); + + /* Allocate the PTE if necessary; takes PMD lock once only. */ + ret = -ENOMEM; + if (pte_alloc(mm, pmd)) + goto out; + + while (pages_to_write_in_pmd) { + int pte_idx = 0; + const int batch_size = min_t(int, pages_to_write_in_pmd, 8); + + start_pte = pte_offset_map_lock(mm, pmd, addr, &pte_lock); + for (pte = start_pte; pte_idx < batch_size; ++pte, ++pte_idx) { + int err = insert_page_in_batch_locked(mm, pte, + addr, pages[curr_page_idx], prot); + if (unlikely(err)) { + pte_unmap_unlock(start_pte, pte_lock); + ret = err; + remaining_pages_total -= pte_idx; + goto out; + } + addr += PAGE_SIZE; + ++curr_page_idx; + } + pte_unmap_unlock(start_pte, pte_lock); + pages_to_write_in_pmd -= batch_size; + remaining_pages_total -= batch_size; + } + if (remaining_pages_total) + goto more; + ret = 0; +out: + *num = remaining_pages_total; + return ret; +} +#endif /* ifdef pte_index */ + +/** + * vm_insert_pages - insert multiple pages into user vma, batching the pmd lock. + * @vma: user vma to map to + * @addr: target start user address of these pages + * @pages: source kernel pages + * @num: in: number of pages to map. out: number of pages that were *not* + * mapped. (0 means all pages were successfully mapped). + * + * Preferred over vm_insert_page() when inserting multiple pages. + * + * In case of error, we may have mapped a subset of the provided + * pages. It is the caller's responsibility to account for this case. + * + * The same restrictions apply as in vm_insert_page(). + */ +int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr, + struct page **pages, unsigned long *num) +{ +#ifdef pte_index + const unsigned long end_addr = addr + (*num * PAGE_SIZE) - 1; + + if (addr < vma->vm_start || end_addr >= vma->vm_end) + return -EFAULT; + if (!(vma->vm_flags & VM_MIXEDMAP)) { + BUG_ON(mmap_read_trylock(vma->vm_mm)); + BUG_ON(vma->vm_flags & VM_PFNMAP); + vma->vm_flags |= VM_MIXEDMAP; + } + /* Defer page refcount checking till we're about to map that page. */ + return insert_pages(vma, addr, pages, num, vma->vm_page_prot); +#else + unsigned long idx = 0, pgcount = *num; + int err = -EINVAL; + + for (; idx < pgcount; ++idx) { + err = vm_insert_page(vma, addr + (PAGE_SIZE * idx), pages[idx]); + if (err) + break; + } + *num = pgcount - idx; + return err; +#endif /* ifdef pte_index */ +} +EXPORT_SYMBOL(vm_insert_pages); + +/** + * vm_insert_page - insert single page into user vma + * @vma: user vma to map to + * @addr: target user address of this page + * @page: source kernel page + * + * This allows drivers to insert individual pages they've allocated + * into a user vma. + * + * The page has to be a nice clean _individual_ kernel allocation. + * If you allocate a compound page, you need to have marked it as + * such (__GFP_COMP), or manually just split the page up yourself + * (see split_page()). + * + * NOTE! Traditionally this was done with "remap_pfn_range()" which + * took an arbitrary page protection parameter. This doesn't allow + * that. Your vma protection will have to be set up correctly, which + * means that if you want a shared writable mapping, you'd better + * ask for a shared writable mapping! + * + * The page does not need to be reserved. + * + * Usually this function is called from f_op->mmap() handler + * under mm->mmap_lock write-lock, so it can change vma->vm_flags. + * Caller must set VM_MIXEDMAP on vma if it wants to call this + * function from other places, for example from page-fault handler. + * + * Return: %0 on success, negative error code otherwise. + */ +int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, + struct page *page) +{ + if (addr < vma->vm_start || addr >= vma->vm_end) + return -EFAULT; + if (!page_count(page)) + return -EINVAL; + if (!(vma->vm_flags & VM_MIXEDMAP)) { + BUG_ON(mmap_read_trylock(vma->vm_mm)); + BUG_ON(vma->vm_flags & VM_PFNMAP); + vma->vm_flags |= VM_MIXEDMAP; + } + return insert_page(vma, addr, page, vma->vm_page_prot); +} +EXPORT_SYMBOL(vm_insert_page); + +/* + * __vm_map_pages - maps range of kernel pages into user vma + * @vma: user vma to map to + * @pages: pointer to array of source kernel pages + * @num: number of pages in page array + * @offset: user's requested vm_pgoff + * + * This allows drivers to map range of kernel pages into a user vma. + * + * Return: 0 on success and error code otherwise. + */ +static int __vm_map_pages(struct vm_area_struct *vma, struct page **pages, + unsigned long num, unsigned long offset) +{ + unsigned long count = vma_pages(vma); + unsigned long uaddr = vma->vm_start; + int ret, i; + + /* Fail if the user requested offset is beyond the end of the object */ + if (offset >= num) + return -ENXIO; + + /* Fail if the user requested size exceeds available object size */ + if (count > num - offset) + return -ENXIO; + + for (i = 0; i < count; i++) { + ret = vm_insert_page(vma, uaddr, pages[offset + i]); + if (ret < 0) + return ret; + uaddr += PAGE_SIZE; + } + + return 0; +} + +/** + * vm_map_pages - maps range of kernel pages starts with non zero offset + * @vma: user vma to map to + * @pages: pointer to array of source kernel pages + * @num: number of pages in page array + * + * Maps an object consisting of @num pages, catering for the user's + * requested vm_pgoff + * + * If we fail to insert any page into the vma, the function will return + * immediately leaving any previously inserted pages present. Callers + * from the mmap handler may immediately return the error as their caller + * will destroy the vma, removing any successfully inserted pages. Other + * callers should make their own arrangements for calling unmap_region(). + * + * Context: Process context. Called by mmap handlers. + * Return: 0 on success and error code otherwise. + */ +int vm_map_pages(struct vm_area_struct *vma, struct page **pages, + unsigned long num) +{ + return __vm_map_pages(vma, pages, num, vma->vm_pgoff); +} +EXPORT_SYMBOL(vm_map_pages); + +/** + * vm_map_pages_zero - map range of kernel pages starts with zero offset + * @vma: user vma to map to + * @pages: pointer to array of source kernel pages + * @num: number of pages in page array + * + * Similar to vm_map_pages(), except that it explicitly sets the offset + * to 0. This function is intended for the drivers that did not consider + * vm_pgoff. + * + * Context: Process context. Called by mmap handlers. + * Return: 0 on success and error code otherwise. + */ +int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages, + unsigned long num) +{ + return __vm_map_pages(vma, pages, num, 0); +} +EXPORT_SYMBOL(vm_map_pages_zero); + +static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr, + pfn_t pfn, pgprot_t prot, bool mkwrite) +{ + struct mm_struct *mm = vma->vm_mm; + pte_t *pte, entry; + spinlock_t *ptl; + + pte = get_locked_pte(mm, addr, &ptl); + if (!pte) + return VM_FAULT_OOM; + if (!pte_none(*pte)) { + if (mkwrite) { + /* + * For read faults on private mappings the PFN passed + * in may not match the PFN we have mapped if the + * mapped PFN is a writeable COW page. In the mkwrite + * case we are creating a writable PTE for a shared + * mapping and we expect the PFNs to match. If they + * don't match, we are likely racing with block + * allocation and mapping invalidation so just skip the + * update. + */ + if (pte_pfn(*pte) != pfn_t_to_pfn(pfn)) { + WARN_ON_ONCE(!is_zero_pfn(pte_pfn(*pte))); + goto out_unlock; + } + entry = pte_mkyoung(*pte); + entry = maybe_mkwrite(pte_mkdirty(entry), vma); + if (ptep_set_access_flags(vma, addr, pte, entry, 1)) + update_mmu_cache(vma, addr, pte); + } + goto out_unlock; + } + + /* Ok, finally just insert the thing.. */ + if (pfn_t_devmap(pfn)) + entry = pte_mkdevmap(pfn_t_pte(pfn, prot)); + else + entry = pte_mkspecial(pfn_t_pte(pfn, prot)); + + if (mkwrite) { + entry = pte_mkyoung(entry); + entry = maybe_mkwrite(pte_mkdirty(entry), vma); + } + + set_pte_at(mm, addr, pte, entry); + update_mmu_cache(vma, addr, pte); /* XXX: why not for insert_page? */ + +out_unlock: + pte_unmap_unlock(pte, ptl); + return VM_FAULT_NOPAGE; +} + +/** + * vmf_insert_pfn_prot - insert single pfn into user vma with specified pgprot + * @vma: user vma to map to + * @addr: target user address of this page + * @pfn: source kernel pfn + * @pgprot: pgprot flags for the inserted page + * + * This is exactly like vmf_insert_pfn(), except that it allows drivers + * to override pgprot on a per-page basis. + * + * This only makes sense for IO mappings, and it makes no sense for + * COW mappings. In general, using multiple vmas is preferable; + * vmf_insert_pfn_prot should only be used if using multiple VMAs is + * impractical. + * + * See vmf_insert_mixed_prot() for a discussion of the implication of using + * a value of @pgprot different from that of @vma->vm_page_prot. + * + * Context: Process context. May allocate using %GFP_KERNEL. + * Return: vm_fault_t value. + */ +vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, pgprot_t pgprot) +{ + /* + * Technically, architectures with pte_special can avoid all these + * restrictions (same for remap_pfn_range). However we would like + * consistency in testing and feature parity among all, so we should + * try to keep these invariants in place for everybody. + */ + BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))); + BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == + (VM_PFNMAP|VM_MIXEDMAP)); + BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); + BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn)); + + if (addr < vma->vm_start || addr >= vma->vm_end) + return VM_FAULT_SIGBUS; + + if (!pfn_modify_allowed(pfn, pgprot)) + return VM_FAULT_SIGBUS; + + track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV)); + + return insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot, + false); +} +EXPORT_SYMBOL(vmf_insert_pfn_prot); + +/** + * vmf_insert_pfn - insert single pfn into user vma + * @vma: user vma to map to + * @addr: target user address of this page + * @pfn: source kernel pfn + * + * Similar to vm_insert_page, this allows drivers to insert individual pages + * they've allocated into a user vma. Same comments apply. + * + * This function should only be called from a vm_ops->fault handler, and + * in that case the handler should return the result of this function. + * + * vma cannot be a COW mapping. + * + * As this is called only for pages that do not currently exist, we + * do not need to flush old virtual caches or the TLB. + * + * Context: Process context. May allocate using %GFP_KERNEL. + * Return: vm_fault_t value. + */ +vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn) +{ + return vmf_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot); +} +EXPORT_SYMBOL(vmf_insert_pfn); + +static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn) +{ + /* these checks mirror the abort conditions in vm_normal_page */ + if (vma->vm_flags & VM_MIXEDMAP) + return true; + if (pfn_t_devmap(pfn)) + return true; + if (pfn_t_special(pfn)) + return true; + if (is_zero_pfn(pfn_t_to_pfn(pfn))) + return true; + return false; +} + +static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma, + unsigned long addr, pfn_t pfn, pgprot_t pgprot, + bool mkwrite) +{ + int err; + + BUG_ON(!vm_mixed_ok(vma, pfn)); + + if (addr < vma->vm_start || addr >= vma->vm_end) + return VM_FAULT_SIGBUS; + + track_pfn_insert(vma, &pgprot, pfn); + + if (!pfn_modify_allowed(pfn_t_to_pfn(pfn), pgprot)) + return VM_FAULT_SIGBUS; + + /* + * If we don't have pte special, then we have to use the pfn_valid() + * based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must* + * refcount the page if pfn_valid is true (hence insert_page rather + * than insert_pfn). If a zero_pfn were inserted into a VM_MIXEDMAP + * without pte special, it would there be refcounted as a normal page. + */ + if (!IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL) && + !pfn_t_devmap(pfn) && pfn_t_valid(pfn)) { + struct page *page; + + /* + * At this point we are committed to insert_page() + * regardless of whether the caller specified flags that + * result in pfn_t_has_page() == false. + */ + page = pfn_to_page(pfn_t_to_pfn(pfn)); + err = insert_page(vma, addr, page, pgprot); + } else { + return insert_pfn(vma, addr, pfn, pgprot, mkwrite); + } + + if (err == -ENOMEM) + return VM_FAULT_OOM; + if (err < 0 && err != -EBUSY) + return VM_FAULT_SIGBUS; + + return VM_FAULT_NOPAGE; +} + +/** + * vmf_insert_mixed_prot - insert single pfn into user vma with specified pgprot + * @vma: user vma to map to + * @addr: target user address of this page + * @pfn: source kernel pfn + * @pgprot: pgprot flags for the inserted page + * + * This is exactly like vmf_insert_mixed(), except that it allows drivers + * to override pgprot on a per-page basis. + * + * Typically this function should be used by drivers to set caching- and + * encryption bits different than those of @vma->vm_page_prot, because + * the caching- or encryption mode may not be known at mmap() time. + * This is ok as long as @vma->vm_page_prot is not used by the core vm + * to set caching and encryption bits for those vmas (except for COW pages). + * This is ensured by core vm only modifying these page table entries using + * functions that don't touch caching- or encryption bits, using pte_modify() + * if needed. (See for example mprotect()). + * Also when new page-table entries are created, this is only done using the + * fault() callback, and never using the value of vma->vm_page_prot, + * except for page-table entries that point to anonymous pages as the result + * of COW. + * + * Context: Process context. May allocate using %GFP_KERNEL. + * Return: vm_fault_t value. + */ +vm_fault_t vmf_insert_mixed_prot(struct vm_area_struct *vma, unsigned long addr, + pfn_t pfn, pgprot_t pgprot) +{ + return __vm_insert_mixed(vma, addr, pfn, pgprot, false); +} +EXPORT_SYMBOL(vmf_insert_mixed_prot); + +vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, + pfn_t pfn) +{ + return __vm_insert_mixed(vma, addr, pfn, vma->vm_page_prot, false); +} +EXPORT_SYMBOL(vmf_insert_mixed); + +/* + * If the insertion of PTE failed because someone else already added a + * different entry in the mean time, we treat that as success as we assume + * the same entry was actually inserted. + */ +vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, + unsigned long addr, pfn_t pfn) +{ + return __vm_insert_mixed(vma, addr, pfn, vma->vm_page_prot, true); +} +EXPORT_SYMBOL(vmf_insert_mixed_mkwrite); + +/* + * maps a range of physical memory into the requested pages. the old + * mappings are removed. any references to nonexistent pages results + * in null mappings (currently treated as "copy-on-access") + */ +static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd, + unsigned long addr, unsigned long end, + unsigned long pfn, pgprot_t prot) +{ + pte_t *pte, *mapped_pte; + spinlock_t *ptl; + int err = 0; + + mapped_pte = pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); + if (!pte) + return -ENOMEM; + arch_enter_lazy_mmu_mode(); + do { + BUG_ON(!pte_none(*pte)); + if (!pfn_modify_allowed(pfn, prot)) { + err = -EACCES; + break; + } + set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot))); + pfn++; + } while (pte++, addr += PAGE_SIZE, addr != end); + arch_leave_lazy_mmu_mode(); + pte_unmap_unlock(mapped_pte, ptl); + return err; +} + +static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud, + unsigned long addr, unsigned long end, + unsigned long pfn, pgprot_t prot) +{ + pmd_t *pmd; + unsigned long next; + int err; + + pfn -= addr >> PAGE_SHIFT; + pmd = pmd_alloc(mm, pud, addr); + if (!pmd) + return -ENOMEM; + VM_BUG_ON(pmd_trans_huge(*pmd)); + do { + next = pmd_addr_end(addr, end); + err = remap_pte_range(mm, pmd, addr, next, + pfn + (addr >> PAGE_SHIFT), prot); + if (err) + return err; + } while (pmd++, addr = next, addr != end); + return 0; +} + +static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d, + unsigned long addr, unsigned long end, + unsigned long pfn, pgprot_t prot) +{ + pud_t *pud; + unsigned long next; + int err; + + pfn -= addr >> PAGE_SHIFT; + pud = pud_alloc(mm, p4d, addr); + if (!pud) + return -ENOMEM; + do { + next = pud_addr_end(addr, end); + err = remap_pmd_range(mm, pud, addr, next, + pfn + (addr >> PAGE_SHIFT), prot); + if (err) + return err; + } while (pud++, addr = next, addr != end); + return 0; +} + +static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd, + unsigned long addr, unsigned long end, + unsigned long pfn, pgprot_t prot) +{ + p4d_t *p4d; + unsigned long next; + int err; + + pfn -= addr >> PAGE_SHIFT; + p4d = p4d_alloc(mm, pgd, addr); + if (!p4d) + return -ENOMEM; + do { + next = p4d_addr_end(addr, end); + err = remap_pud_range(mm, p4d, addr, next, + pfn + (addr >> PAGE_SHIFT), prot); + if (err) + return err; + } while (p4d++, addr = next, addr != end); + return 0; +} + +/** + * remap_pfn_range - remap kernel memory to userspace + * @vma: user vma to map to + * @addr: target page aligned user address to start at + * @pfn: page frame number of kernel physical memory address + * @size: size of mapping area + * @prot: page protection flags for this mapping + * + * Note: this is only safe if the mm semaphore is held when called. + * + * Return: %0 on success, negative error code otherwise. + */ +int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, unsigned long size, pgprot_t prot) +{ + pgd_t *pgd; + unsigned long next; + unsigned long end = addr + PAGE_ALIGN(size); + struct mm_struct *mm = vma->vm_mm; + unsigned long remap_pfn = pfn; + int err; + + if (WARN_ON_ONCE(!PAGE_ALIGNED(addr))) + return -EINVAL; + + /* + * Physically remapped pages are special. Tell the + * rest of the world about it: + * VM_IO tells people not to look at these pages + * (accesses can have side effects). + * VM_PFNMAP tells the core MM that the base pages are just + * raw PFN mappings, and do not have a "struct page" associated + * with them. + * VM_DONTEXPAND + * Disable vma merging and expanding with mremap(). + * VM_DONTDUMP + * Omit vma from core dump, even when VM_IO turned off. + * + * There's a horrible special case to handle copy-on-write + * behaviour that some programs depend on. We mark the "original" + * un-COW'ed pages by matching them up with "vma->vm_pgoff". + * See vm_normal_page() for details. + */ + if (is_cow_mapping(vma->vm_flags)) { + if (addr != vma->vm_start || end != vma->vm_end) + return -EINVAL; + vma->vm_pgoff = pfn; + } + + err = track_pfn_remap(vma, &prot, remap_pfn, addr, PAGE_ALIGN(size)); + if (err) + return -EINVAL; + + vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; + + BUG_ON(addr >= end); + pfn -= addr >> PAGE_SHIFT; + pgd = pgd_offset(mm, addr); + flush_cache_range(vma, addr, end); + do { + next = pgd_addr_end(addr, end); + err = remap_p4d_range(mm, pgd, addr, next, + pfn + (addr >> PAGE_SHIFT), prot); + if (err) + break; + } while (pgd++, addr = next, addr != end); + + if (err) + untrack_pfn(vma, remap_pfn, PAGE_ALIGN(size)); + + return err; +} +EXPORT_SYMBOL(remap_pfn_range); + +/** + * vm_iomap_memory - remap memory to userspace + * @vma: user vma to map to + * @start: start of the physical memory to be mapped + * @len: size of area + * + * This is a simplified io_remap_pfn_range() for common driver use. The + * driver just needs to give us the physical memory range to be mapped, + * we'll figure out the rest from the vma information. + * + * NOTE! Some drivers might want to tweak vma->vm_page_prot first to get + * whatever write-combining details or similar. + * + * Return: %0 on success, negative error code otherwise. + */ +int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len) +{ + unsigned long vm_len, pfn, pages; + + /* Check that the physical memory area passed in looks valid */ + if (start + len < start) + return -EINVAL; + /* + * You *really* shouldn't map things that aren't page-aligned, + * but we've historically allowed it because IO memory might + * just have smaller alignment. + */ + len += start & ~PAGE_MASK; + pfn = start >> PAGE_SHIFT; + pages = (len + ~PAGE_MASK) >> PAGE_SHIFT; + if (pfn + pages < pfn) + return -EINVAL; + + /* We start the mapping 'vm_pgoff' pages into the area */ + if (vma->vm_pgoff > pages) + return -EINVAL; + pfn += vma->vm_pgoff; + pages -= vma->vm_pgoff; + + /* Can we fit all of the mapping? */ + vm_len = vma->vm_end - vma->vm_start; + if (vm_len >> PAGE_SHIFT > pages) + return -EINVAL; + + /* Ok, let it rip */ + return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot); +} +EXPORT_SYMBOL(vm_iomap_memory); + +static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, + unsigned long addr, unsigned long end, + pte_fn_t fn, void *data, bool create, + pgtbl_mod_mask *mask) +{ + pte_t *pte; + int err = 0; + spinlock_t *ptl; + + if (create) { + pte = (mm == &init_mm) ? + pte_alloc_kernel_track(pmd, addr, mask) : + pte_alloc_map_lock(mm, pmd, addr, &ptl); + if (!pte) + return -ENOMEM; + } else { + pte = (mm == &init_mm) ? + pte_offset_kernel(pmd, addr) : + pte_offset_map_lock(mm, pmd, addr, &ptl); + } + + BUG_ON(pmd_huge(*pmd)); + + arch_enter_lazy_mmu_mode(); + + if (fn) { + do { + if (create || !pte_none(*pte)) { + err = fn(pte++, addr, data); + if (err) + break; + } + } while (addr += PAGE_SIZE, addr != end); + } + *mask |= PGTBL_PTE_MODIFIED; + + arch_leave_lazy_mmu_mode(); + + if (mm != &init_mm) + pte_unmap_unlock(pte-1, ptl); + return err; +} + +static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud, + unsigned long addr, unsigned long end, + pte_fn_t fn, void *data, bool create, + pgtbl_mod_mask *mask) +{ + pmd_t *pmd; + unsigned long next; + int err = 0; + + BUG_ON(pud_huge(*pud)); + + if (create) { + pmd = pmd_alloc_track(mm, pud, addr, mask); + if (!pmd) + return -ENOMEM; + } else { + pmd = pmd_offset(pud, addr); + } + do { + next = pmd_addr_end(addr, end); + if (create || !pmd_none_or_clear_bad(pmd)) { + err = apply_to_pte_range(mm, pmd, addr, next, fn, data, + create, mask); + if (err) + break; + } + } while (pmd++, addr = next, addr != end); + return err; +} + +static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d, + unsigned long addr, unsigned long end, + pte_fn_t fn, void *data, bool create, + pgtbl_mod_mask *mask) +{ + pud_t *pud; + unsigned long next; + int err = 0; + + if (create) { + pud = pud_alloc_track(mm, p4d, addr, mask); + if (!pud) + return -ENOMEM; + } else { + pud = pud_offset(p4d, addr); + } + do { + next = pud_addr_end(addr, end); + if (create || !pud_none_or_clear_bad(pud)) { + err = apply_to_pmd_range(mm, pud, addr, next, fn, data, + create, mask); + if (err) + break; + } + } while (pud++, addr = next, addr != end); + return err; +} + +static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd, + unsigned long addr, unsigned long end, + pte_fn_t fn, void *data, bool create, + pgtbl_mod_mask *mask) +{ + p4d_t *p4d; + unsigned long next; + int err = 0; + + if (create) { + p4d = p4d_alloc_track(mm, pgd, addr, mask); + if (!p4d) + return -ENOMEM; + } else { + p4d = p4d_offset(pgd, addr); + } + do { + next = p4d_addr_end(addr, end); + if (create || !p4d_none_or_clear_bad(p4d)) { + err = apply_to_pud_range(mm, p4d, addr, next, fn, data, + create, mask); + if (err) + break; + } + } while (p4d++, addr = next, addr != end); + return err; +} + +static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr, + unsigned long size, pte_fn_t fn, + void *data, bool create) +{ + pgd_t *pgd; + unsigned long start = addr, next; + unsigned long end = addr + size; + pgtbl_mod_mask mask = 0; + int err = 0; + + if (WARN_ON(addr >= end)) + return -EINVAL; + + pgd = pgd_offset(mm, addr); + do { + next = pgd_addr_end(addr, end); + if (!create && pgd_none_or_clear_bad(pgd)) + continue; + err = apply_to_p4d_range(mm, pgd, addr, next, fn, data, create, &mask); + if (err) + break; + } while (pgd++, addr = next, addr != end); + + if (mask & ARCH_PAGE_TABLE_SYNC_MASK) + arch_sync_kernel_mappings(start, start + size); + + return err; +} + +/* + * Scan a region of virtual memory, filling in page tables as necessary + * and calling a provided function on each leaf page table. + */ +int apply_to_page_range(struct mm_struct *mm, unsigned long addr, + unsigned long size, pte_fn_t fn, void *data) +{ + return __apply_to_page_range(mm, addr, size, fn, data, true); +} +EXPORT_SYMBOL_GPL(apply_to_page_range); + +/* + * Scan a region of virtual memory, calling a provided function on + * each leaf page table where it exists. + * + * Unlike apply_to_page_range, this does _not_ fill in page tables + * where they are absent. + */ +int apply_to_existing_page_range(struct mm_struct *mm, unsigned long addr, + unsigned long size, pte_fn_t fn, void *data) +{ + return __apply_to_page_range(mm, addr, size, fn, data, false); +} +EXPORT_SYMBOL_GPL(apply_to_existing_page_range); + +/* + * handle_pte_fault chooses page fault handler according to an entry which was + * read non-atomically. Before making any commitment, on those architectures + * or configurations (e.g. i386 with PAE) which might give a mix of unmatched + * parts, do_swap_page must check under lock before unmapping the pte and + * proceeding (but do_wp_page is only called after already making such a check; + * and do_anonymous_page can safely check later on). + */ +static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd, + pte_t *page_table, pte_t orig_pte) +{ + int same = 1; +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPTION) + if (sizeof(pte_t) > sizeof(unsigned long)) { + spinlock_t *ptl = pte_lockptr(mm, pmd); + spin_lock(ptl); + same = pte_same(*page_table, orig_pte); + spin_unlock(ptl); + } +#endif + pte_unmap(page_table); + return same; +} + +static inline bool cow_user_page(struct page *dst, struct page *src, + struct vm_fault *vmf) +{ + bool ret; + void *kaddr; + void __user *uaddr; + bool locked = false; + struct vm_area_struct *vma = vmf->vma; + struct mm_struct *mm = vma->vm_mm; + unsigned long addr = vmf->address; + + if (likely(src)) { + copy_user_highpage(dst, src, addr, vma); + return true; + } + + /* + * If the source page was a PFN mapping, we don't have + * a "struct page" for it. We do a best-effort copy by + * just copying from the original user address. If that + * fails, we just zero-fill it. Live with it. + */ + kaddr = kmap_atomic(dst); + uaddr = (void __user *)(addr & PAGE_MASK); + + /* + * On architectures with software "accessed" bits, we would + * take a double page fault, so mark it accessed here. + */ + if (arch_faults_on_old_pte() && !pte_young(vmf->orig_pte)) { + pte_t entry; + + vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); + locked = true; + if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) { + /* + * Other thread has already handled the fault + * and update local tlb only + */ + update_mmu_tlb(vma, addr, vmf->pte); + ret = false; + goto pte_unlock; + } + + entry = pte_mkyoung(vmf->orig_pte); + if (ptep_set_access_flags(vma, addr, vmf->pte, entry, 0)) + update_mmu_cache(vma, addr, vmf->pte); + } + + /* + * This really shouldn't fail, because the page is there + * in the page tables. But it might just be unreadable, + * in which case we just give up and fill the result with + * zeroes. + */ + if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { + if (locked) + goto warn; + + /* Re-validate under PTL if the page is still mapped */ + vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); + locked = true; + if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) { + /* The PTE changed under us, update local tlb */ + update_mmu_tlb(vma, addr, vmf->pte); + ret = false; + goto pte_unlock; + } + + /* + * The same page can be mapped back since last copy attempt. + * Try to copy again under PTL. + */ + if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { + /* + * Give a warn in case there can be some obscure + * use-case + */ +warn: + WARN_ON_ONCE(1); + clear_page(kaddr); + } + } + + ret = true; + +pte_unlock: + if (locked) + pte_unmap_unlock(vmf->pte, vmf->ptl); + kunmap_atomic(kaddr); + flush_dcache_page(dst); + + return ret; +} + +static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma) +{ + struct file *vm_file = vma->vm_file; + + if (vm_file) + return mapping_gfp_mask(vm_file->f_mapping) | __GFP_FS | __GFP_IO; + + /* + * Special mappings (e.g. VDSO) do not have any file so fake + * a default GFP_KERNEL for them. + */ + return GFP_KERNEL; +} + +/* + * Notify the address space that the page is about to become writable so that + * it can prohibit this or wait for the page to get into an appropriate state. + * + * We do this without the lock held, so that it can sleep if it needs to. + */ +static vm_fault_t do_page_mkwrite(struct vm_fault *vmf) +{ + vm_fault_t ret; + struct page *page = vmf->page; + unsigned int old_flags = vmf->flags; + + vmf->flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; + + if (vmf->vma->vm_file && + IS_SWAPFILE(vmf->vma->vm_file->f_mapping->host)) + return VM_FAULT_SIGBUS; + + ret = vmf->vma->vm_ops->page_mkwrite(vmf); + /* Restore original flags so that caller is not surprised */ + vmf->flags = old_flags; + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) + return ret; + if (unlikely(!(ret & VM_FAULT_LOCKED))) { + lock_page(page); + if (!page->mapping) { + unlock_page(page); + return 0; /* retry */ + } + ret |= VM_FAULT_LOCKED; + } else + VM_BUG_ON_PAGE(!PageLocked(page), page); + return ret; +} + +/* + * Handle dirtying of a page in shared file mapping on a write fault. + * + * The function expects the page to be locked and unlocks it. + */ +static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + struct address_space *mapping; + struct page *page = vmf->page; + bool dirtied; + bool page_mkwrite = vma->vm_ops && vma->vm_ops->page_mkwrite; + + dirtied = set_page_dirty(page); + VM_BUG_ON_PAGE(PageAnon(page), page); + /* + * Take a local copy of the address_space - page.mapping may be zeroed + * by truncate after unlock_page(). The address_space itself remains + * pinned by vma->vm_file's reference. We rely on unlock_page()'s + * release semantics to prevent the compiler from undoing this copying. + */ + mapping = page_rmapping(page); + unlock_page(page); + + if (!page_mkwrite) + file_update_time(vma->vm_file); + + /* + * Throttle page dirtying rate down to writeback speed. + * + * mapping may be NULL here because some device drivers do not + * set page.mapping but still dirty their pages + * + * Drop the mmap_lock before waiting on IO, if we can. The file + * is pinning the mapping, as per above. + */ + if ((dirtied || page_mkwrite) && mapping) { + struct file *fpin; + + fpin = maybe_unlock_mmap_for_io(vmf, NULL); + balance_dirty_pages_ratelimited(mapping); + if (fpin) { + fput(fpin); + return VM_FAULT_RETRY; + } + } + + return 0; +} + +/* + * Handle write page faults for pages that can be reused in the current vma + * + * This can happen either due to the mapping being with the VM_SHARED flag, + * or due to us being the last reference standing to the page. In either + * case, all we need to do here is to mark the page as writable and update + * any related book-keeping. + */ +static inline void wp_page_reuse(struct vm_fault *vmf) + __releases(vmf->ptl) +{ + struct vm_area_struct *vma = vmf->vma; + struct page *page = vmf->page; + pte_t entry; + /* + * Clear the pages cpupid information as the existing + * information potentially belongs to a now completely + * unrelated process. + */ + if (page) + page_cpupid_xchg_last(page, (1 << LAST_CPUPID_SHIFT) - 1); + + flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); + entry = pte_mkyoung(vmf->orig_pte); + entry = maybe_mkwrite(pte_mkdirty(entry), vma); + if (ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1)) + update_mmu_cache(vma, vmf->address, vmf->pte); + pte_unmap_unlock(vmf->pte, vmf->ptl); + count_vm_event(PGREUSE); +} + +/* + * Handle the case of a page which we actually need to copy to a new page. + * + * Called with mmap_lock locked and the old page referenced, but + * without the ptl held. + * + * High level logic flow: + * + * - Allocate a page, copy the content of the old page to the new one. + * - Handle book keeping and accounting - cgroups, mmu-notifiers, etc. + * - Take the PTL. If the pte changed, bail out and release the allocated page + * - If the pte is still the way we remember it, update the page table and all + * relevant references. This includes dropping the reference the page-table + * held to the old page, as well as updating the rmap. + * - In any case, unlock the PTL and drop the reference we took to the old page. + */ +static vm_fault_t wp_page_copy(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + struct mm_struct *mm = vma->vm_mm; + struct page *old_page = vmf->page; + struct page *new_page = NULL; + pte_t entry; + int page_copied = 0; + struct mmu_notifier_range range; + + if (unlikely(anon_vma_prepare(vma))) + goto oom; + + if (is_zero_pfn(pte_pfn(vmf->orig_pte))) { + new_page = alloc_zeroed_user_highpage_movable(vma, + vmf->address); + if (!new_page) + goto oom; + } else { + new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, + vmf->address); + if (!new_page) + goto oom; + + if (!cow_user_page(new_page, old_page, vmf)) { + /* + * COW failed, if the fault was solved by other, + * it's fine. If not, userspace would re-fault on + * the same address and we will handle the fault + * from the second attempt. + */ + put_page(new_page); + if (old_page) + put_page(old_page); + return 0; + } + } + + if (mem_cgroup_charge(new_page, mm, GFP_KERNEL)) + goto oom_free_new; + cgroup_throttle_swaprate(new_page, GFP_KERNEL); + + __SetPageUptodate(new_page); + + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, + vmf->address & PAGE_MASK, + (vmf->address & PAGE_MASK) + PAGE_SIZE); + mmu_notifier_invalidate_range_start(&range); + + /* + * Re-check the pte - we dropped the lock + */ + vmf->pte = pte_offset_map_lock(mm, vmf->pmd, vmf->address, &vmf->ptl); + if (likely(pte_same(*vmf->pte, vmf->orig_pte))) { + if (old_page) { + if (!PageAnon(old_page)) { + dec_mm_counter_fast(mm, + mm_counter_file(old_page)); + inc_mm_counter_fast(mm, MM_ANONPAGES); + } + } else { + inc_mm_counter_fast(mm, MM_ANONPAGES); + } + flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); + entry = mk_pte(new_page, vma->vm_page_prot); + entry = pte_sw_mkyoung(entry); + entry = maybe_mkwrite(pte_mkdirty(entry), vma); + /* + * Clear the pte entry and flush it first, before updating the + * pte with the new entry. This will avoid a race condition + * seen in the presence of one thread doing SMC and another + * thread doing COW. + */ + ptep_clear_flush_notify(vma, vmf->address, vmf->pte); + page_add_new_anon_rmap(new_page, vma, vmf->address, false); + lru_cache_add_inactive_or_unevictable(new_page, vma); + /* + * We call the notify macro here because, when using secondary + * mmu page tables (such as kvm shadow page tables), we want the + * new page to be mapped directly into the secondary page table. + */ + set_pte_at_notify(mm, vmf->address, vmf->pte, entry); + update_mmu_cache(vma, vmf->address, vmf->pte); + if (old_page) { + /* + * Only after switching the pte to the new page may + * we remove the mapcount here. Otherwise another + * process may come and find the rmap count decremented + * before the pte is switched to the new page, and + * "reuse" the old page writing into it while our pte + * here still points into it and can be read by other + * threads. + * + * The critical issue is to order this + * page_remove_rmap with the ptp_clear_flush above. + * Those stores are ordered by (if nothing else,) + * the barrier present in the atomic_add_negative + * in page_remove_rmap. + * + * Then the TLB flush in ptep_clear_flush ensures that + * no process can access the old page before the + * decremented mapcount is visible. And the old page + * cannot be reused until after the decremented + * mapcount is visible. So transitively, TLBs to + * old page will be flushed before it can be reused. + */ + page_remove_rmap(old_page, false); + } + + /* Free the old page.. */ + new_page = old_page; + page_copied = 1; + } else { + update_mmu_tlb(vma, vmf->address, vmf->pte); + } + + if (new_page) + put_page(new_page); + + pte_unmap_unlock(vmf->pte, vmf->ptl); + /* + * No need to double call mmu_notifier->invalidate_range() callback as + * the above ptep_clear_flush_notify() did already call it. + */ + mmu_notifier_invalidate_range_only_end(&range); + if (old_page) { + /* + * Don't let another task, with possibly unlocked vma, + * keep the mlocked page. + */ + if (page_copied && (vma->vm_flags & VM_LOCKED)) { + lock_page(old_page); /* LRU manipulation */ + if (PageMlocked(old_page)) + munlock_vma_page(old_page); + unlock_page(old_page); + } + put_page(old_page); + } + return page_copied ? VM_FAULT_WRITE : 0; +oom_free_new: + put_page(new_page); +oom: + if (old_page) + put_page(old_page); + return VM_FAULT_OOM; +} + +/** + * finish_mkwrite_fault - finish page fault for a shared mapping, making PTE + * writeable once the page is prepared + * + * @vmf: structure describing the fault + * + * This function handles all that is needed to finish a write page fault in a + * shared mapping due to PTE being read-only once the mapped page is prepared. + * It handles locking of PTE and modifying it. + * + * The function expects the page to be locked or other protection against + * concurrent faults / writeback (such as DAX radix tree locks). + * + * Return: %VM_FAULT_WRITE on success, %0 when PTE got changed before + * we acquired PTE lock. + */ +vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf) +{ + WARN_ON_ONCE(!(vmf->vma->vm_flags & VM_SHARED)); + vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address, + &vmf->ptl); + /* + * We might have raced with another page fault while we released the + * pte_offset_map_lock. + */ + if (!pte_same(*vmf->pte, vmf->orig_pte)) { + update_mmu_tlb(vmf->vma, vmf->address, vmf->pte); + pte_unmap_unlock(vmf->pte, vmf->ptl); + return VM_FAULT_NOPAGE; + } + wp_page_reuse(vmf); + return 0; +} + +/* + * Handle write page faults for VM_MIXEDMAP or VM_PFNMAP for a VM_SHARED + * mapping + */ +static vm_fault_t wp_pfn_shared(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + + if (vma->vm_ops && vma->vm_ops->pfn_mkwrite) { + vm_fault_t ret; + + pte_unmap_unlock(vmf->pte, vmf->ptl); + vmf->flags |= FAULT_FLAG_MKWRITE; + ret = vma->vm_ops->pfn_mkwrite(vmf); + if (ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)) + return ret; + return finish_mkwrite_fault(vmf); + } + wp_page_reuse(vmf); + return VM_FAULT_WRITE; +} + +static vm_fault_t wp_page_shared(struct vm_fault *vmf) + __releases(vmf->ptl) +{ + struct vm_area_struct *vma = vmf->vma; + vm_fault_t ret = VM_FAULT_WRITE; + + get_page(vmf->page); + + if (vma->vm_ops && vma->vm_ops->page_mkwrite) { + vm_fault_t tmp; + + pte_unmap_unlock(vmf->pte, vmf->ptl); + tmp = do_page_mkwrite(vmf); + if (unlikely(!tmp || (tmp & + (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { + put_page(vmf->page); + return tmp; + } + tmp = finish_mkwrite_fault(vmf); + if (unlikely(tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) { + unlock_page(vmf->page); + put_page(vmf->page); + return tmp; + } + } else { + wp_page_reuse(vmf); + lock_page(vmf->page); + } + ret |= fault_dirty_shared_page(vmf); + put_page(vmf->page); + + return ret; +} + +/* + * This routine handles present pages, when users try to write + * to a shared page. It is done by copying the page to a new address + * and decrementing the shared-page counter for the old page. + * + * Note that this routine assumes that the protection checks have been + * done by the caller (the low-level page fault routine in most cases). + * Thus we can safely just mark it writable once we've done any necessary + * COW. + * + * We also mark the page dirty at this point even though the page will + * change only once the write actually happens. This avoids a few races, + * and potentially makes it more efficient. + * + * We enter with non-exclusive mmap_lock (to exclude vma changes, + * but allow concurrent faults), with pte both mapped and locked. + * We return with mmap_lock still held, but pte unmapped and unlocked. + */ +static vm_fault_t do_wp_page(struct vm_fault *vmf) + __releases(vmf->ptl) +{ + struct vm_area_struct *vma = vmf->vma; + + if (userfaultfd_pte_wp(vma, *vmf->pte)) { + pte_unmap_unlock(vmf->pte, vmf->ptl); + return handle_userfault(vmf, VM_UFFD_WP); + } + + /* + * Userfaultfd write-protect can defer flushes. Ensure the TLB + * is flushed in this case before copying. + */ + if (unlikely(userfaultfd_wp(vmf->vma) && + mm_tlb_flush_pending(vmf->vma->vm_mm))) + flush_tlb_page(vmf->vma, vmf->address); + + vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte); + if (!vmf->page) { + /* + * VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a + * VM_PFNMAP VMA. + * + * We should not cow pages in a shared writeable mapping. + * Just mark the pages writable and/or call ops->pfn_mkwrite. + */ + if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) == + (VM_WRITE|VM_SHARED)) + return wp_pfn_shared(vmf); + + pte_unmap_unlock(vmf->pte, vmf->ptl); + return wp_page_copy(vmf); + } + + /* + * Take out anonymous pages first, anonymous shared vmas are + * not dirty accountable. + */ + if (PageAnon(vmf->page)) { + struct page *page = vmf->page; + + /* PageKsm() doesn't necessarily raise the page refcount */ + if (PageKsm(page) || page_count(page) != 1) + goto copy; + if (!trylock_page(page)) + goto copy; + if (PageKsm(page) || page_mapcount(page) != 1 || page_count(page) != 1) { + unlock_page(page); + goto copy; + } + /* + * Ok, we've got the only map reference, and the only + * page count reference, and the page is locked, + * it's dark out, and we're wearing sunglasses. Hit it. + */ + unlock_page(page); + wp_page_reuse(vmf); + return VM_FAULT_WRITE; + } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == + (VM_WRITE|VM_SHARED))) { + return wp_page_shared(vmf); + } +copy: + /* + * Ok, we need to copy. Oh, well.. + */ + get_page(vmf->page); + + pte_unmap_unlock(vmf->pte, vmf->ptl); + return wp_page_copy(vmf); +} + +static void unmap_mapping_range_vma(struct vm_area_struct *vma, + unsigned long start_addr, unsigned long end_addr, + struct zap_details *details) +{ + zap_page_range_single(vma, start_addr, end_addr - start_addr, details); +} + +static inline void unmap_mapping_range_tree(struct rb_root_cached *root, + struct zap_details *details) +{ + struct vm_area_struct *vma; + pgoff_t vba, vea, zba, zea; + + vma_interval_tree_foreach(vma, root, + details->first_index, details->last_index) { + + vba = vma->vm_pgoff; + vea = vba + vma_pages(vma) - 1; + zba = details->first_index; + if (zba < vba) + zba = vba; + zea = details->last_index; + if (zea > vea) + zea = vea; + + unmap_mapping_range_vma(vma, + ((zba - vba) << PAGE_SHIFT) + vma->vm_start, + ((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start, + details); + } +} + +/** + * unmap_mapping_page() - Unmap single page from processes. + * @page: The locked page to be unmapped. + * + * Unmap this page from any userspace process which still has it mmaped. + * Typically, for efficiency, the range of nearby pages has already been + * unmapped by unmap_mapping_pages() or unmap_mapping_range(). But once + * truncation or invalidation holds the lock on a page, it may find that + * the page has been remapped again: and then uses unmap_mapping_page() + * to unmap it finally. + */ +void unmap_mapping_page(struct page *page) +{ + struct address_space *mapping = page->mapping; + struct zap_details details = { }; + + VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON(PageTail(page)); + + details.check_mapping = mapping; + details.first_index = page->index; + details.last_index = page->index + thp_nr_pages(page) - 1; + details.single_page = page; + + i_mmap_lock_write(mapping); + if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) + unmap_mapping_range_tree(&mapping->i_mmap, &details); + i_mmap_unlock_write(mapping); +} + +/** + * unmap_mapping_pages() - Unmap pages from processes. + * @mapping: The address space containing pages to be unmapped. + * @start: Index of first page to be unmapped. + * @nr: Number of pages to be unmapped. 0 to unmap to end of file. + * @even_cows: Whether to unmap even private COWed pages. + * + * Unmap the pages in this address space from any userspace process which + * has them mmaped. Generally, you want to remove COWed pages as well when + * a file is being truncated, but not when invalidating pages from the page + * cache. + */ +void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, + pgoff_t nr, bool even_cows) +{ + struct zap_details details = { }; + + details.check_mapping = even_cows ? NULL : mapping; + details.first_index = start; + details.last_index = start + nr - 1; + if (details.last_index < details.first_index) + details.last_index = ULONG_MAX; + + i_mmap_lock_write(mapping); + if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) + unmap_mapping_range_tree(&mapping->i_mmap, &details); + i_mmap_unlock_write(mapping); +} + +/** + * unmap_mapping_range - unmap the portion of all mmaps in the specified + * address_space corresponding to the specified byte range in the underlying + * file. + * + * @mapping: the address space containing mmaps to be unmapped. + * @holebegin: byte in first page to unmap, relative to the start of + * the underlying file. This will be rounded down to a PAGE_SIZE + * boundary. Note that this is different from truncate_pagecache(), which + * must keep the partial page. In contrast, we must get rid of + * partial pages. + * @holelen: size of prospective hole in bytes. This will be rounded + * up to a PAGE_SIZE boundary. A holelen of zero truncates to the + * end of the file. + * @even_cows: 1 when truncating a file, unmap even private COWed pages; + * but 0 when invalidating pagecache, don't throw away private data. + */ +void unmap_mapping_range(struct address_space *mapping, + loff_t const holebegin, loff_t const holelen, int even_cows) +{ + pgoff_t hba = (pgoff_t)(holebegin) >> PAGE_SHIFT; + pgoff_t hlen = ((pgoff_t)(holelen) + PAGE_SIZE - 1) >> PAGE_SHIFT; + + /* Check for overflow. */ + if (sizeof(holelen) > sizeof(hlen)) { + long long holeend = + (holebegin + holelen + PAGE_SIZE - 1) >> PAGE_SHIFT; + if (holeend & ~(long long)ULONG_MAX) + hlen = ULONG_MAX - hba + 1; + } + + unmap_mapping_pages(mapping, hba, hlen, even_cows); +} +EXPORT_SYMBOL(unmap_mapping_range); + +/* + * We enter with non-exclusive mmap_lock (to exclude vma changes, + * but allow concurrent faults), and pte mapped but not yet locked. + * We return with pte unmapped and unlocked. + * + * We return with the mmap_lock locked or unlocked in the same cases + * as does filemap_fault(). + */ +vm_fault_t do_swap_page(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + struct page *page = NULL, *swapcache; + swp_entry_t entry; + pte_t pte; + int locked; + int exclusive = 0; + vm_fault_t ret = 0; + void *shadow = NULL; + + if (!pte_unmap_same(vma->vm_mm, vmf->pmd, vmf->pte, vmf->orig_pte)) + goto out; + + entry = pte_to_swp_entry(vmf->orig_pte); + if (unlikely(non_swap_entry(entry))) { + if (is_migration_entry(entry)) { + migration_entry_wait(vma->vm_mm, vmf->pmd, + vmf->address); + } else if (is_device_private_entry(entry)) { + vmf->page = device_private_entry_to_page(entry); + ret = vmf->page->pgmap->ops->migrate_to_ram(vmf); + } else if (is_hwpoison_entry(entry)) { + ret = VM_FAULT_HWPOISON; + } else { + print_bad_pte(vma, vmf->address, vmf->orig_pte, NULL); + ret = VM_FAULT_SIGBUS; + } + goto out; + } + + + delayacct_set_flag(DELAYACCT_PF_SWAPIN); + page = lookup_swap_cache(entry, vma, vmf->address); + swapcache = page; + + if (!page) { + struct swap_info_struct *si = swp_swap_info(entry); + + if (data_race(si->flags & SWP_SYNCHRONOUS_IO) && + __swap_count(entry) == 1) { + /* skip swapcache */ + page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, + vmf->address); + if (page) { + int err; + + __SetPageLocked(page); + __SetPageSwapBacked(page); + set_page_private(page, entry.val); + + /* Tell memcg to use swap ownership records */ + SetPageSwapCache(page); + err = mem_cgroup_charge(page, vma->vm_mm, + GFP_KERNEL); + ClearPageSwapCache(page); + if (err) { + ret = VM_FAULT_OOM; + goto out_page; + } + + shadow = get_shadow_from_swap_cache(entry); + if (shadow) + workingset_refault(page, shadow); + + lru_cache_add(page); + swap_readpage(page, true); + } + } else { + page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, + vmf); + swapcache = page; + } + + if (!page) { + /* + * Back out if somebody else faulted in this pte + * while we released the pte lock. + */ + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, + vmf->address, &vmf->ptl); + if (likely(pte_same(*vmf->pte, vmf->orig_pte))) + ret = VM_FAULT_OOM; + delayacct_clear_flag(DELAYACCT_PF_SWAPIN); + goto unlock; + } + + /* Had to read the page from swap area: Major fault */ + ret = VM_FAULT_MAJOR; + count_vm_event(PGMAJFAULT); + count_memcg_event_mm(vma->vm_mm, PGMAJFAULT); + } else if (PageHWPoison(page)) { + /* + * hwpoisoned dirty swapcache pages are kept for killing + * owner processes (which may be unknown at hwpoison time) + */ + ret = VM_FAULT_HWPOISON; + delayacct_clear_flag(DELAYACCT_PF_SWAPIN); + goto out_release; + } + + locked = lock_page_or_retry(page, vma->vm_mm, vmf->flags); + + delayacct_clear_flag(DELAYACCT_PF_SWAPIN); + if (!locked) { + ret |= VM_FAULT_RETRY; + goto out_release; + } + + /* + * Make sure try_to_free_swap or reuse_swap_page or swapoff did not + * release the swapcache from under us. The page pin, and pte_same + * test below, are not enough to exclude that. Even if it is still + * swapcache, we need to check that the page's swap has not changed. + */ + if (unlikely((!PageSwapCache(page) || + page_private(page) != entry.val)) && swapcache) + goto out_page; + + page = ksm_might_need_to_copy(page, vma, vmf->address); + if (unlikely(!page)) { + ret = VM_FAULT_OOM; + page = swapcache; + goto out_page; + } + + cgroup_throttle_swaprate(page, GFP_KERNEL); + + /* + * Back out if somebody else already faulted in this pte. + */ + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, + &vmf->ptl); + if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) + goto out_nomap; + + if (unlikely(!PageUptodate(page))) { + ret = VM_FAULT_SIGBUS; + goto out_nomap; + } + + /* + * The page isn't present yet, go ahead with the fault. + * + * Be careful about the sequence of operations here. + * To get its accounting right, reuse_swap_page() must be called + * while the page is counted on swap but not yet in mapcount i.e. + * before page_add_anon_rmap() and swap_free(); try_to_free_swap() + * must be called after the swap_free(), or it will never succeed. + */ + + inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); + dec_mm_counter_fast(vma->vm_mm, MM_SWAPENTS); + pte = mk_pte(page, vma->vm_page_prot); + if ((vmf->flags & FAULT_FLAG_WRITE) && reuse_swap_page(page, NULL)) { + pte = maybe_mkwrite(pte_mkdirty(pte), vma); + vmf->flags &= ~FAULT_FLAG_WRITE; + ret |= VM_FAULT_WRITE; + exclusive = RMAP_EXCLUSIVE; + } + flush_icache_page(vma, page); + if (pte_swp_soft_dirty(vmf->orig_pte)) + pte = pte_mksoft_dirty(pte); + if (pte_swp_uffd_wp(vmf->orig_pte)) { + pte = pte_mkuffd_wp(pte); + pte = pte_wrprotect(pte); + } + set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte); + arch_do_swap_page(vma->vm_mm, vma, vmf->address, pte, vmf->orig_pte); + vmf->orig_pte = pte; + + /* ksm created a completely new copy */ + if (unlikely(page != swapcache && swapcache)) { + page_add_new_anon_rmap(page, vma, vmf->address, false); + lru_cache_add_inactive_or_unevictable(page, vma); + } else { + do_page_add_anon_rmap(page, vma, vmf->address, exclusive); + } + + swap_free(entry); + if (mem_cgroup_swap_full(page) || + (vma->vm_flags & VM_LOCKED) || PageMlocked(page)) + try_to_free_swap(page); + unlock_page(page); + if (page != swapcache && swapcache) { + /* + * Hold the lock to avoid the swap entry to be reused + * until we take the PT lock for the pte_same() check + * (to avoid false positives from pte_same). For + * further safety release the lock after the swap_free + * so that the swap count won't change under a + * parallel locked swapcache. + */ + unlock_page(swapcache); + put_page(swapcache); + } + + if (vmf->flags & FAULT_FLAG_WRITE) { + ret |= do_wp_page(vmf); + if (ret & VM_FAULT_ERROR) + ret &= VM_FAULT_ERROR; + goto out; + } + + /* No need to invalidate - it was non-present before */ + update_mmu_cache(vma, vmf->address, vmf->pte); +unlock: + pte_unmap_unlock(vmf->pte, vmf->ptl); +out: + return ret; +out_nomap: + pte_unmap_unlock(vmf->pte, vmf->ptl); +out_page: + unlock_page(page); +out_release: + put_page(page); + if (page != swapcache && swapcache) { + unlock_page(swapcache); + put_page(swapcache); + } + return ret; +} + +/* + * We enter with non-exclusive mmap_lock (to exclude vma changes, + * but allow concurrent faults), and pte mapped but not yet locked. + * We return with mmap_lock still held, but pte unmapped and unlocked. + */ +static vm_fault_t do_anonymous_page(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + struct page *page; + vm_fault_t ret = 0; + pte_t entry; + + /* File mapping without ->vm_ops ? */ + if (vma->vm_flags & VM_SHARED) + return VM_FAULT_SIGBUS; + + /* + * Use pte_alloc() instead of pte_alloc_map(). We can't run + * pte_offset_map() on pmds where a huge pmd might be created + * from a different thread. + * + * pte_alloc_map() is safe to use under mmap_write_lock(mm) or when + * parallel threads are excluded by other means. + * + * Here we only have mmap_read_lock(mm). + */ + if (pte_alloc(vma->vm_mm, vmf->pmd)) + return VM_FAULT_OOM; + + /* See the comment in pte_alloc_one_map() */ + if (unlikely(pmd_trans_unstable(vmf->pmd))) + return 0; + + /* Use the zero-page for reads */ + if (!(vmf->flags & FAULT_FLAG_WRITE) && + !mm_forbids_zeropage(vma->vm_mm)) { + entry = pte_mkspecial(pfn_pte(my_zero_pfn(vmf->address), + vma->vm_page_prot)); + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, + vmf->address, &vmf->ptl); + if (!pte_none(*vmf->pte)) { + update_mmu_tlb(vma, vmf->address, vmf->pte); + goto unlock; + } + ret = check_stable_address_space(vma->vm_mm); + if (ret) + goto unlock; + /* Deliver the page fault to userland, check inside PT lock */ + if (userfaultfd_missing(vma)) { + pte_unmap_unlock(vmf->pte, vmf->ptl); + return handle_userfault(vmf, VM_UFFD_MISSING); + } + goto setpte; + } + + /* Allocate our own private page. */ + if (unlikely(anon_vma_prepare(vma))) + goto oom; + page = alloc_zeroed_user_highpage_movable(vma, vmf->address); + if (!page) + goto oom; + + if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL)) + goto oom_free_page; + cgroup_throttle_swaprate(page, GFP_KERNEL); + + /* + * The memory barrier inside __SetPageUptodate makes sure that + * preceding stores to the page contents become visible before + * the set_pte_at() write. + */ + __SetPageUptodate(page); + + entry = mk_pte(page, vma->vm_page_prot); + entry = pte_sw_mkyoung(entry); + if (vma->vm_flags & VM_WRITE) + entry = pte_mkwrite(pte_mkdirty(entry)); + + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, + &vmf->ptl); + if (!pte_none(*vmf->pte)) { + update_mmu_cache(vma, vmf->address, vmf->pte); + goto release; + } + + ret = check_stable_address_space(vma->vm_mm); + if (ret) + goto release; + + /* Deliver the page fault to userland, check inside PT lock */ + if (userfaultfd_missing(vma)) { + pte_unmap_unlock(vmf->pte, vmf->ptl); + put_page(page); + return handle_userfault(vmf, VM_UFFD_MISSING); + } + + inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); + page_add_new_anon_rmap(page, vma, vmf->address, false); + lru_cache_add_inactive_or_unevictable(page, vma); +setpte: + set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); + + /* No need to invalidate - it was non-present before */ + update_mmu_cache(vma, vmf->address, vmf->pte); +unlock: + pte_unmap_unlock(vmf->pte, vmf->ptl); + return ret; +release: + put_page(page); + goto unlock; +oom_free_page: + put_page(page); +oom: + return VM_FAULT_OOM; +} + +/* + * The mmap_lock must have been held on entry, and may have been + * released depending on flags and vma->vm_ops->fault() return value. + * See filemap_fault() and __lock_page_retry(). + */ +static vm_fault_t __do_fault(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + vm_fault_t ret; + + /* + * Preallocate pte before we take page_lock because this might lead to + * deadlocks for memcg reclaim which waits for pages under writeback: + * lock_page(A) + * SetPageWriteback(A) + * unlock_page(A) + * lock_page(B) + * lock_page(B) + * pte_alloc_one + * shrink_page_list + * wait_on_page_writeback(A) + * SetPageWriteback(B) + * unlock_page(B) + * # flush A, B to clear the writeback + */ + if (pmd_none(*vmf->pmd) && !vmf->prealloc_pte) { + vmf->prealloc_pte = pte_alloc_one(vma->vm_mm); + if (!vmf->prealloc_pte) + return VM_FAULT_OOM; + smp_wmb(); /* See comment in __pte_alloc() */ + } + + ret = vma->vm_ops->fault(vmf); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY | + VM_FAULT_DONE_COW))) + return ret; + + if (unlikely(PageHWPoison(vmf->page))) { + struct page *page = vmf->page; + vm_fault_t poisonret = VM_FAULT_HWPOISON; + if (ret & VM_FAULT_LOCKED) { + if (page_mapped(page)) + unmap_mapping_pages(page_mapping(page), + page->index, 1, false); + /* Retry if a clean page was removed from the cache. */ + if (invalidate_inode_page(page)) + poisonret = VM_FAULT_NOPAGE; + unlock_page(page); + } + put_page(page); + vmf->page = NULL; + return poisonret; + } + + if (unlikely(!(ret & VM_FAULT_LOCKED))) + lock_page(vmf->page); + else + VM_BUG_ON_PAGE(!PageLocked(vmf->page), vmf->page); + + return ret; +} + +/* + * The ordering of these checks is important for pmds with _PAGE_DEVMAP set. + * If we check pmd_trans_unstable() first we will trip the bad_pmd() check + * inside of pmd_none_or_trans_huge_or_clear_bad(). This will end up correctly + * returning 1 but not before it spams dmesg with the pmd_clear_bad() output. + */ +static int pmd_devmap_trans_unstable(pmd_t *pmd) +{ + return pmd_devmap(*pmd) || pmd_trans_unstable(pmd); +} + +static vm_fault_t pte_alloc_one_map(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + + if (!pmd_none(*vmf->pmd)) + goto map_pte; + if (vmf->prealloc_pte) { + vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); + if (unlikely(!pmd_none(*vmf->pmd))) { + spin_unlock(vmf->ptl); + goto map_pte; + } + + mm_inc_nr_ptes(vma->vm_mm); + pmd_populate(vma->vm_mm, vmf->pmd, vmf->prealloc_pte); + spin_unlock(vmf->ptl); + vmf->prealloc_pte = NULL; + } else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) { + return VM_FAULT_OOM; + } +map_pte: + /* + * If a huge pmd materialized under us just retry later. Use + * pmd_trans_unstable() via pmd_devmap_trans_unstable() instead of + * pmd_trans_huge() to ensure the pmd didn't become pmd_trans_huge + * under us and then back to pmd_none, as a result of MADV_DONTNEED + * running immediately after a huge pmd fault in a different thread of + * this mm, in turn leading to a misleading pmd_trans_huge() retval. + * All we have to ensure is that it is a regular pmd that we can walk + * with pte_offset_map() and we can do that through an atomic read in + * C, which is what pmd_trans_unstable() provides. + */ + if (pmd_devmap_trans_unstable(vmf->pmd)) + return VM_FAULT_NOPAGE; + + /* + * At this point we know that our vmf->pmd points to a page of ptes + * and it cannot become pmd_none(), pmd_devmap() or pmd_trans_huge() + * for the duration of the fault. If a racing MADV_DONTNEED runs and + * we zap the ptes pointed to by our vmf->pmd, the vmf->ptl will still + * be valid and we will re-check to make sure the vmf->pte isn't + * pte_none() under vmf->ptl protection when we return to + * alloc_set_pte(). + */ + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, + &vmf->ptl); + return 0; +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static void deposit_prealloc_pte(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + + pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, vmf->prealloc_pte); + /* + * We are going to consume the prealloc table, + * count that as nr_ptes. + */ + mm_inc_nr_ptes(vma->vm_mm); + vmf->prealloc_pte = NULL; +} + +static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) +{ + struct vm_area_struct *vma = vmf->vma; + bool write = vmf->flags & FAULT_FLAG_WRITE; + unsigned long haddr = vmf->address & HPAGE_PMD_MASK; + pmd_t entry; + int i; + vm_fault_t ret = VM_FAULT_FALLBACK; + + if (!transhuge_vma_suitable(vma, haddr)) + return ret; + + page = compound_head(page); + if (compound_order(page) != HPAGE_PMD_ORDER) + return ret; + + /* + * Archs like ppc64 need additonal space to store information + * related to pte entry. Use the preallocated table for that. + */ + if (arch_needs_pgtable_deposit() && !vmf->prealloc_pte) { + vmf->prealloc_pte = pte_alloc_one(vma->vm_mm); + if (!vmf->prealloc_pte) + return VM_FAULT_OOM; + smp_wmb(); /* See comment in __pte_alloc() */ + } + + vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); + if (unlikely(!pmd_none(*vmf->pmd))) + goto out; + + for (i = 0; i < HPAGE_PMD_NR; i++) + flush_icache_page(vma, page + i); + + entry = mk_huge_pmd(page, vma->vm_page_prot); + if (write) + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); + + add_mm_counter(vma->vm_mm, mm_counter_file(page), HPAGE_PMD_NR); + page_add_file_rmap(page, true); + /* + * deposit and withdraw with pmd lock held + */ + if (arch_needs_pgtable_deposit()) + deposit_prealloc_pte(vmf); + + set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry); + + update_mmu_cache_pmd(vma, haddr, vmf->pmd); + + /* fault is handled */ + ret = 0; + count_vm_event(THP_FILE_MAPPED); +out: + spin_unlock(vmf->ptl); + return ret; +} +#else +static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) +{ + BUILD_BUG(); + return 0; +} +#endif + +/** + * alloc_set_pte - setup new PTE entry for given page and add reverse page + * mapping. If needed, the function allocates page table or use pre-allocated. + * + * @vmf: fault environment + * @page: page to map + * + * Caller must take care of unlocking vmf->ptl, if vmf->pte is non-NULL on + * return. + * + * Target users are page handler itself and implementations of + * vm_ops->map_pages. + * + * Return: %0 on success, %VM_FAULT_ code in case of error. + */ +vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page) +{ + struct vm_area_struct *vma = vmf->vma; + bool write = vmf->flags & FAULT_FLAG_WRITE; + pte_t entry; + vm_fault_t ret; + + if (pmd_none(*vmf->pmd) && PageTransCompound(page)) { + ret = do_set_pmd(vmf, page); + if (ret != VM_FAULT_FALLBACK) + return ret; + } + + if (!vmf->pte) { + ret = pte_alloc_one_map(vmf); + if (ret) + return ret; + } + + /* Re-check under ptl */ + if (unlikely(!pte_none(*vmf->pte))) { + update_mmu_tlb(vma, vmf->address, vmf->pte); + return VM_FAULT_NOPAGE; + } + + flush_icache_page(vma, page); + entry = mk_pte(page, vma->vm_page_prot); + entry = pte_sw_mkyoung(entry); + if (write) + entry = maybe_mkwrite(pte_mkdirty(entry), vma); + /* copy-on-write page */ + if (write && !(vma->vm_flags & VM_SHARED)) { + inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); + page_add_new_anon_rmap(page, vma, vmf->address, false); + lru_cache_add_inactive_or_unevictable(page, vma); + } else { + inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page)); + page_add_file_rmap(page, false); + } + set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); + + /* no need to invalidate: a not-present page won't be cached */ + update_mmu_cache(vma, vmf->address, vmf->pte); + + return 0; +} + + +/** + * finish_fault - finish page fault once we have prepared the page to fault + * + * @vmf: structure describing the fault + * + * This function handles all that is needed to finish a page fault once the + * page to fault in is prepared. It handles locking of PTEs, inserts PTE for + * given page, adds reverse page mapping, handles memcg charges and LRU + * addition. + * + * The function expects the page to be locked and on success it consumes a + * reference of a page being mapped (for the PTE which maps it). + * + * Return: %0 on success, %VM_FAULT_ code in case of error. + */ +vm_fault_t finish_fault(struct vm_fault *vmf) +{ + struct page *page; + vm_fault_t ret = 0; + + /* Did we COW the page? */ + if ((vmf->flags & FAULT_FLAG_WRITE) && + !(vmf->vma->vm_flags & VM_SHARED)) + page = vmf->cow_page; + else + page = vmf->page; + + /* + * check even for read faults because we might have lost our CoWed + * page + */ + if (!(vmf->vma->vm_flags & VM_SHARED)) + ret = check_stable_address_space(vmf->vma->vm_mm); + if (!ret) + ret = alloc_set_pte(vmf, page); + if (vmf->pte) + pte_unmap_unlock(vmf->pte, vmf->ptl); + return ret; +} + +static unsigned long fault_around_bytes __read_mostly = + rounddown_pow_of_two(65536); + +#ifdef CONFIG_DEBUG_FS +static int fault_around_bytes_get(void *data, u64 *val) +{ + *val = fault_around_bytes; + return 0; +} + +/* + * fault_around_bytes must be rounded down to the nearest page order as it's + * what do_fault_around() expects to see. + */ +static int fault_around_bytes_set(void *data, u64 val) +{ + if (val / PAGE_SIZE > PTRS_PER_PTE) + return -EINVAL; + if (val > PAGE_SIZE) + fault_around_bytes = rounddown_pow_of_two(val); + else + fault_around_bytes = PAGE_SIZE; /* rounddown_pow_of_two(0) is undefined */ + return 0; +} +DEFINE_DEBUGFS_ATTRIBUTE(fault_around_bytes_fops, + fault_around_bytes_get, fault_around_bytes_set, "%llu\n"); + +static int __init fault_around_debugfs(void) +{ + debugfs_create_file_unsafe("fault_around_bytes", 0644, NULL, NULL, + &fault_around_bytes_fops); + return 0; +} +late_initcall(fault_around_debugfs); +#endif + +/* + * do_fault_around() tries to map few pages around the fault address. The hope + * is that the pages will be needed soon and this will lower the number of + * faults to handle. + * + * It uses vm_ops->map_pages() to map the pages, which skips the page if it's + * not ready to be mapped: not up-to-date, locked, etc. + * + * This function is called with the page table lock taken. In the split ptlock + * case the page table lock only protects only those entries which belong to + * the page table corresponding to the fault address. + * + * This function doesn't cross the VMA boundaries, in order to call map_pages() + * only once. + * + * fault_around_bytes defines how many bytes we'll try to map. + * do_fault_around() expects it to be set to a power of two less than or equal + * to PTRS_PER_PTE. + * + * The virtual address of the area that we map is naturally aligned to + * fault_around_bytes rounded down to the machine page size + * (and therefore to page order). This way it's easier to guarantee + * that we don't cross page table boundaries. + */ +static vm_fault_t do_fault_around(struct vm_fault *vmf) +{ + unsigned long address = vmf->address, nr_pages, mask; + pgoff_t start_pgoff = vmf->pgoff; + pgoff_t end_pgoff; + int off; + vm_fault_t ret = 0; + + nr_pages = READ_ONCE(fault_around_bytes) >> PAGE_SHIFT; + mask = ~(nr_pages * PAGE_SIZE - 1) & PAGE_MASK; + + vmf->address = max(address & mask, vmf->vma->vm_start); + off = ((address - vmf->address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); + start_pgoff -= off; + + /* + * end_pgoff is either the end of the page table, the end of + * the vma or nr_pages from start_pgoff, depending what is nearest. + */ + end_pgoff = start_pgoff - + ((vmf->address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) + + PTRS_PER_PTE - 1; + end_pgoff = min3(end_pgoff, vma_pages(vmf->vma) + vmf->vma->vm_pgoff - 1, + start_pgoff + nr_pages - 1); + + if (pmd_none(*vmf->pmd)) { + vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm); + if (!vmf->prealloc_pte) + goto out; + smp_wmb(); /* See comment in __pte_alloc() */ + } + + vmf->vma->vm_ops->map_pages(vmf, start_pgoff, end_pgoff); + + /* Huge page is mapped? Page fault is solved */ + if (pmd_trans_huge(*vmf->pmd)) { + ret = VM_FAULT_NOPAGE; + goto out; + } + + /* ->map_pages() haven't done anything useful. Cold page cache? */ + if (!vmf->pte) + goto out; + + /* check if the page fault is solved */ + vmf->pte -= (vmf->address >> PAGE_SHIFT) - (address >> PAGE_SHIFT); + if (!pte_none(*vmf->pte)) + ret = VM_FAULT_NOPAGE; + pte_unmap_unlock(vmf->pte, vmf->ptl); +out: + vmf->address = address; + vmf->pte = NULL; + return ret; +} + +static vm_fault_t do_read_fault(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + vm_fault_t ret = 0; + + /* + * Let's call ->map_pages() first and use ->fault() as fallback + * if page by the offset is not ready to be mapped (cold cache or + * something). + */ + if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) { + ret = do_fault_around(vmf); + if (ret) + return ret; + } + + ret = __do_fault(vmf); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) + return ret; + + ret |= finish_fault(vmf); + unlock_page(vmf->page); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) + put_page(vmf->page); + return ret; +} + +static vm_fault_t do_cow_fault(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + vm_fault_t ret; + + if (unlikely(anon_vma_prepare(vma))) + return VM_FAULT_OOM; + + vmf->cow_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address); + if (!vmf->cow_page) + return VM_FAULT_OOM; + + if (mem_cgroup_charge(vmf->cow_page, vma->vm_mm, GFP_KERNEL)) { + put_page(vmf->cow_page); + return VM_FAULT_OOM; + } + cgroup_throttle_swaprate(vmf->cow_page, GFP_KERNEL); + + ret = __do_fault(vmf); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) + goto uncharge_out; + if (ret & VM_FAULT_DONE_COW) + return ret; + + copy_user_highpage(vmf->cow_page, vmf->page, vmf->address, vma); + __SetPageUptodate(vmf->cow_page); + + ret |= finish_fault(vmf); + unlock_page(vmf->page); + put_page(vmf->page); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) + goto uncharge_out; + return ret; +uncharge_out: + put_page(vmf->cow_page); + return ret; +} + +static vm_fault_t do_shared_fault(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + vm_fault_t ret, tmp; + + ret = __do_fault(vmf); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) + return ret; + + /* + * Check if the backing address space wants to know that the page is + * about to become writable + */ + if (vma->vm_ops->page_mkwrite) { + unlock_page(vmf->page); + tmp = do_page_mkwrite(vmf); + if (unlikely(!tmp || + (tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { + put_page(vmf->page); + return tmp; + } + } + + ret |= finish_fault(vmf); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | + VM_FAULT_RETRY))) { + unlock_page(vmf->page); + put_page(vmf->page); + return ret; + } + + ret |= fault_dirty_shared_page(vmf); + return ret; +} + +/* + * We enter with non-exclusive mmap_lock (to exclude vma changes, + * but allow concurrent faults). + * The mmap_lock may have been released depending on flags and our + * return value. See filemap_fault() and __lock_page_or_retry(). + * If mmap_lock is released, vma may become invalid (for example + * by other thread calling munmap()). + */ +static vm_fault_t do_fault(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + struct mm_struct *vm_mm = vma->vm_mm; + vm_fault_t ret; + + /* + * The VMA was not fully populated on mmap() or missing VM_DONTEXPAND + */ + if (!vma->vm_ops->fault) { + /* + * If we find a migration pmd entry or a none pmd entry, which + * should never happen, return SIGBUS + */ + if (unlikely(!pmd_present(*vmf->pmd))) + ret = VM_FAULT_SIGBUS; + else { + vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, + vmf->pmd, + vmf->address, + &vmf->ptl); + /* + * Make sure this is not a temporary clearing of pte + * by holding ptl and checking again. A R/M/W update + * of pte involves: take ptl, clearing the pte so that + * we don't have concurrent modification by hardware + * followed by an update. + */ + if (unlikely(pte_none(*vmf->pte))) + ret = VM_FAULT_SIGBUS; + else + ret = VM_FAULT_NOPAGE; + + pte_unmap_unlock(vmf->pte, vmf->ptl); + } + } else if (!(vmf->flags & FAULT_FLAG_WRITE)) + ret = do_read_fault(vmf); + else if (!(vma->vm_flags & VM_SHARED)) + ret = do_cow_fault(vmf); + else + ret = do_shared_fault(vmf); + + /* preallocated pagetable is unused: free it */ + if (vmf->prealloc_pte) { + pte_free(vm_mm, vmf->prealloc_pte); + vmf->prealloc_pte = NULL; + } + return ret; +} + +static int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, + unsigned long addr, int page_nid, + int *flags) +{ + get_page(page); + + count_vm_numa_event(NUMA_HINT_FAULTS); + if (page_nid == numa_node_id()) { + count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL); + *flags |= TNF_FAULT_LOCAL; + } + + return mpol_misplaced(page, vma, addr); +} + +static vm_fault_t do_numa_page(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + struct page *page = NULL; + int page_nid = NUMA_NO_NODE; + int last_cpupid; + int target_nid; + bool migrated = false; + pte_t pte, old_pte; + bool was_writable = pte_savedwrite(vmf->orig_pte); + int flags = 0; + + /* + * The "pte" at this point cannot be used safely without + * validation through pte_unmap_same(). It's of NUMA type but + * the pfn may be screwed if the read is non atomic. + */ + vmf->ptl = pte_lockptr(vma->vm_mm, vmf->pmd); + spin_lock(vmf->ptl); + if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) { + pte_unmap_unlock(vmf->pte, vmf->ptl); + goto out; + } + + /* + * Make it present again, Depending on how arch implementes non + * accessible ptes, some can allow access by kernel mode. + */ + old_pte = ptep_modify_prot_start(vma, vmf->address, vmf->pte); + pte = pte_modify(old_pte, vma->vm_page_prot); + pte = pte_mkyoung(pte); + if (was_writable) + pte = pte_mkwrite(pte); + ptep_modify_prot_commit(vma, vmf->address, vmf->pte, old_pte, pte); + update_mmu_cache(vma, vmf->address, vmf->pte); + + page = vm_normal_page(vma, vmf->address, pte); + if (!page) { + pte_unmap_unlock(vmf->pte, vmf->ptl); + return 0; + } + + /* TODO: handle PTE-mapped THP */ + if (PageCompound(page)) { + pte_unmap_unlock(vmf->pte, vmf->ptl); + return 0; + } + + /* + * Avoid grouping on RO pages in general. RO pages shouldn't hurt as + * much anyway since they can be in shared cache state. This misses + * the case where a mapping is writable but the process never writes + * to it but pte_write gets cleared during protection updates and + * pte_dirty has unpredictable behaviour between PTE scan updates, + * background writeback, dirty balancing and application behaviour. + */ + if (!pte_write(pte)) + flags |= TNF_NO_GROUP; + + /* + * Flag if the page is shared between multiple address spaces. This + * is later used when determining whether to group tasks together + */ + if (page_mapcount(page) > 1 && (vma->vm_flags & VM_SHARED)) + flags |= TNF_SHARED; + + last_cpupid = page_cpupid_last(page); + page_nid = page_to_nid(page); + target_nid = numa_migrate_prep(page, vma, vmf->address, page_nid, + &flags); + pte_unmap_unlock(vmf->pte, vmf->ptl); + if (target_nid == NUMA_NO_NODE) { + put_page(page); + goto out; + } + + /* Migrate to the requested node */ + migrated = migrate_misplaced_page(page, vma, target_nid); + if (migrated) { + page_nid = target_nid; + flags |= TNF_MIGRATED; + } else + flags |= TNF_MIGRATE_FAIL; + +out: + if (page_nid != NUMA_NO_NODE) + task_numa_fault(last_cpupid, page_nid, 1, flags); + return 0; +} + +static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf) +{ + if (vma_is_anonymous(vmf->vma)) + return do_huge_pmd_anonymous_page(vmf); + if (vmf->vma->vm_ops->huge_fault) + return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD); + return VM_FAULT_FALLBACK; +} + +/* `inline' is required to avoid gcc 4.1.2 build error */ +static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd) +{ + if (vma_is_anonymous(vmf->vma)) { + if (userfaultfd_huge_pmd_wp(vmf->vma, orig_pmd)) + return handle_userfault(vmf, VM_UFFD_WP); + return do_huge_pmd_wp_page(vmf, orig_pmd); + } + if (vmf->vma->vm_ops->huge_fault) { + vm_fault_t ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD); + + if (!(ret & VM_FAULT_FALLBACK)) + return ret; + } + + /* COW or write-notify handled on pte level: split pmd. */ + __split_huge_pmd(vmf->vma, vmf->pmd, vmf->address, false, NULL); + + return VM_FAULT_FALLBACK; +} + +static vm_fault_t create_huge_pud(struct vm_fault *vmf) +{ +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ + defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) + /* No support for anonymous transparent PUD pages yet */ + if (vma_is_anonymous(vmf->vma)) + return VM_FAULT_FALLBACK; + if (vmf->vma->vm_ops->huge_fault) + return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + return VM_FAULT_FALLBACK; +} + +static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud) +{ +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ + defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) + /* No support for anonymous transparent PUD pages yet */ + if (vma_is_anonymous(vmf->vma)) + goto split; + if (vmf->vma->vm_ops->huge_fault) { + vm_fault_t ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD); + + if (!(ret & VM_FAULT_FALLBACK)) + return ret; + } +split: + /* COW or write-notify not handled on PUD level: split pud.*/ + __split_huge_pud(vmf->vma, vmf->pud, vmf->address); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE && CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ + return VM_FAULT_FALLBACK; +} + +/* + * These routines also need to handle stuff like marking pages dirty + * and/or accessed for architectures that don't do it in hardware (most + * RISC architectures). The early dirtying is also good on the i386. + * + * There is also a hook called "update_mmu_cache()" that architectures + * with external mmu caches can use to update those (ie the Sparc or + * PowerPC hashed page tables that act as extended TLBs). + * + * We enter with non-exclusive mmap_lock (to exclude vma changes, but allow + * concurrent faults). + * + * The mmap_lock may have been released depending on flags and our return value. + * See filemap_fault() and __lock_page_or_retry(). + */ +static vm_fault_t handle_pte_fault(struct vm_fault *vmf) +{ + pte_t entry; + + if (unlikely(pmd_none(*vmf->pmd))) { + /* + * Leave __pte_alloc() until later: because vm_ops->fault may + * want to allocate huge page, and if we expose page table + * for an instant, it will be difficult to retract from + * concurrent faults and from rmap lookups. + */ + vmf->pte = NULL; + } else { + /* See comment in pte_alloc_one_map() */ + if (pmd_devmap_trans_unstable(vmf->pmd)) + return 0; + /* + * A regular pmd is established and it can't morph into a huge + * pmd from under us anymore at this point because we hold the + * mmap_lock read mode and khugepaged takes it in write mode. + * So now it's safe to run pte_offset_map(). + */ + vmf->pte = pte_offset_map(vmf->pmd, vmf->address); + vmf->orig_pte = *vmf->pte; + + /* + * some architectures can have larger ptes than wordsize, + * e.g.ppc44x-defconfig has CONFIG_PTE_64BIT=y and + * CONFIG_32BIT=y, so READ_ONCE cannot guarantee atomic + * accesses. The code below just needs a consistent view + * for the ifs and we later double check anyway with the + * ptl lock held. So here a barrier will do. + */ + barrier(); + if (pte_none(vmf->orig_pte)) { + pte_unmap(vmf->pte); + vmf->pte = NULL; + } + } + + if (!vmf->pte) { + if (vma_is_anonymous(vmf->vma)) + return do_anonymous_page(vmf); + else + return do_fault(vmf); + } + + if (!pte_present(vmf->orig_pte)) + return do_swap_page(vmf); + + if (pte_protnone(vmf->orig_pte) && vma_is_accessible(vmf->vma)) + return do_numa_page(vmf); + + vmf->ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd); + spin_lock(vmf->ptl); + entry = vmf->orig_pte; + if (unlikely(!pte_same(*vmf->pte, entry))) { + update_mmu_tlb(vmf->vma, vmf->address, vmf->pte); + goto unlock; + } + if (vmf->flags & FAULT_FLAG_WRITE) { + if (!pte_write(entry)) + return do_wp_page(vmf); + entry = pte_mkdirty(entry); + } + entry = pte_mkyoung(entry); + if (ptep_set_access_flags(vmf->vma, vmf->address, vmf->pte, entry, + vmf->flags & FAULT_FLAG_WRITE)) { + update_mmu_cache(vmf->vma, vmf->address, vmf->pte); + } else { + /* Skip spurious TLB flush for retried page fault */ + if (vmf->flags & FAULT_FLAG_TRIED) + goto unlock; + /* + * This is needed only for protection faults but the arch code + * is not yet telling us if this is a protection fault or not. + * This still avoids useless tlb flushes for .text page faults + * with threads. + */ + if (vmf->flags & FAULT_FLAG_WRITE) + flush_tlb_fix_spurious_fault(vmf->vma, vmf->address); + } +unlock: + pte_unmap_unlock(vmf->pte, vmf->ptl); + return 0; +} + +/* + * By the time we get here, we already hold the mm semaphore + * + * The mmap_lock may have been released depending on flags and our + * return value. See filemap_fault() and __lock_page_or_retry(). + */ +static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, + unsigned long address, unsigned int flags) +{ + struct vm_fault vmf = { + .vma = vma, + .address = address & PAGE_MASK, + .flags = flags, + .pgoff = linear_page_index(vma, address), + .gfp_mask = __get_fault_gfp_mask(vma), + }; + unsigned int dirty = flags & FAULT_FLAG_WRITE; + struct mm_struct *mm = vma->vm_mm; + pgd_t *pgd; + p4d_t *p4d; + vm_fault_t ret; + + pgd = pgd_offset(mm, address); + p4d = p4d_alloc(mm, pgd, address); + if (!p4d) + return VM_FAULT_OOM; + + vmf.pud = pud_alloc(mm, p4d, address); + if (!vmf.pud) + return VM_FAULT_OOM; +retry_pud: + if (pud_none(*vmf.pud) && __transparent_hugepage_enabled(vma)) { + ret = create_huge_pud(&vmf); + if (!(ret & VM_FAULT_FALLBACK)) + return ret; + } else { + pud_t orig_pud = *vmf.pud; + + barrier(); + if (pud_trans_huge(orig_pud) || pud_devmap(orig_pud)) { + + /* NUMA case for anonymous PUDs would go here */ + + if (dirty && !pud_write(orig_pud)) { + ret = wp_huge_pud(&vmf, orig_pud); + if (!(ret & VM_FAULT_FALLBACK)) + return ret; + } else { + huge_pud_set_accessed(&vmf, orig_pud); + return 0; + } + } + } + + vmf.pmd = pmd_alloc(mm, vmf.pud, address); + if (!vmf.pmd) + return VM_FAULT_OOM; + + /* Huge pud page fault raced with pmd_alloc? */ + if (pud_trans_unstable(vmf.pud)) + goto retry_pud; + + if (pmd_none(*vmf.pmd) && __transparent_hugepage_enabled(vma)) { + ret = create_huge_pmd(&vmf); + if (!(ret & VM_FAULT_FALLBACK)) + return ret; + } else { + pmd_t orig_pmd = *vmf.pmd; + + barrier(); + if (unlikely(is_swap_pmd(orig_pmd))) { + VM_BUG_ON(thp_migration_supported() && + !is_pmd_migration_entry(orig_pmd)); + if (is_pmd_migration_entry(orig_pmd)) + pmd_migration_entry_wait(mm, vmf.pmd); + return 0; + } + if (pmd_trans_huge(orig_pmd) || pmd_devmap(orig_pmd)) { + if (pmd_protnone(orig_pmd) && vma_is_accessible(vma)) + return do_huge_pmd_numa_page(&vmf, orig_pmd); + + if (dirty && !pmd_write(orig_pmd)) { + ret = wp_huge_pmd(&vmf, orig_pmd); + if (!(ret & VM_FAULT_FALLBACK)) + return ret; + } else { + huge_pmd_set_accessed(&vmf, orig_pmd); + return 0; + } + } + } + + return handle_pte_fault(&vmf); +} + +/** + * mm_account_fault - Do page fault accountings + * + * @regs: the pt_regs struct pointer. When set to NULL, will skip accounting + * of perf event counters, but we'll still do the per-task accounting to + * the task who triggered this page fault. + * @address: the faulted address. + * @flags: the fault flags. + * @ret: the fault retcode. + * + * This will take care of most of the page fault accountings. Meanwhile, it + * will also include the PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN] perf counter + * updates. However note that the handling of PERF_COUNT_SW_PAGE_FAULTS should + * still be in per-arch page fault handlers at the entry of page fault. + */ +static inline void mm_account_fault(struct pt_regs *regs, + unsigned long address, unsigned int flags, + vm_fault_t ret) +{ + bool major; + + /* + * We don't do accounting for some specific faults: + * + * - Unsuccessful faults (e.g. when the address wasn't valid). That + * includes arch_vma_access_permitted() failing before reaching here. + * So this is not a "this many hardware page faults" counter. We + * should use the hw profiling for that. + * + * - Incomplete faults (VM_FAULT_RETRY). They will only be counted + * once they're completed. + */ + if (ret & (VM_FAULT_ERROR | VM_FAULT_RETRY)) + return; + + /* + * We define the fault as a major fault when the final successful fault + * is VM_FAULT_MAJOR, or if it retried (which implies that we couldn't + * handle it immediately previously). + */ + major = (ret & VM_FAULT_MAJOR) || (flags & FAULT_FLAG_TRIED); + + if (major) + current->maj_flt++; + else + current->min_flt++; + + /* + * If the fault is done for GUP, regs will be NULL. We only do the + * accounting for the per thread fault counters who triggered the + * fault, and we skip the perf event updates. + */ + if (!regs) + return; + + if (major) + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address); + else + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address); +} + +/* + * By the time we get here, we already hold the mm semaphore + * + * The mmap_lock may have been released depending on flags and our + * return value. See filemap_fault() and __lock_page_or_retry(). + */ +vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, + unsigned int flags, struct pt_regs *regs) +{ + vm_fault_t ret; + + __set_current_state(TASK_RUNNING); + + count_vm_event(PGFAULT); + count_memcg_event_mm(vma->vm_mm, PGFAULT); + + /* do counter updates before entering really critical section. */ + check_sync_rss_stat(current); + + if (!arch_vma_access_permitted(vma, flags & FAULT_FLAG_WRITE, + flags & FAULT_FLAG_INSTRUCTION, + flags & FAULT_FLAG_REMOTE)) + return VM_FAULT_SIGSEGV; + + /* + * Enable the memcg OOM handling for faults triggered in user + * space. Kernel faults are handled more gracefully. + */ + if (flags & FAULT_FLAG_USER) + mem_cgroup_enter_user_fault(); + + if (unlikely(is_vm_hugetlb_page(vma))) + ret = hugetlb_fault(vma->vm_mm, vma, address, flags); + else + ret = __handle_mm_fault(vma, address, flags); + + if (flags & FAULT_FLAG_USER) { + mem_cgroup_exit_user_fault(); + /* + * The task may have entered a memcg OOM situation but + * if the allocation error was handled gracefully (no + * VM_FAULT_OOM), there is no need to kill anything. + * Just clean up the OOM state peacefully. + */ + if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM)) + mem_cgroup_oom_synchronize(false); + } + + mm_account_fault(regs, address, flags, ret); + + return ret; +} +EXPORT_SYMBOL_GPL(handle_mm_fault); + +#ifndef __PAGETABLE_P4D_FOLDED +/* + * Allocate p4d page table. + * We've already handled the fast-path in-line. + */ +int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) +{ + p4d_t *new = p4d_alloc_one(mm, address); + if (!new) + return -ENOMEM; + + smp_wmb(); /* See comment in __pte_alloc */ + + spin_lock(&mm->page_table_lock); + if (pgd_present(*pgd)) /* Another has populated it */ + p4d_free(mm, new); + else + pgd_populate(mm, pgd, new); + spin_unlock(&mm->page_table_lock); + return 0; +} +#endif /* __PAGETABLE_P4D_FOLDED */ + +#ifndef __PAGETABLE_PUD_FOLDED +/* + * Allocate page upper directory. + * We've already handled the fast-path in-line. + */ +int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) +{ + pud_t *new = pud_alloc_one(mm, address); + if (!new) + return -ENOMEM; + + smp_wmb(); /* See comment in __pte_alloc */ + + spin_lock(&mm->page_table_lock); + if (!p4d_present(*p4d)) { + mm_inc_nr_puds(mm); + p4d_populate(mm, p4d, new); + } else /* Another has populated it */ + pud_free(mm, new); + spin_unlock(&mm->page_table_lock); + return 0; +} +#endif /* __PAGETABLE_PUD_FOLDED */ + +#ifndef __PAGETABLE_PMD_FOLDED +/* + * Allocate page middle directory. + * We've already handled the fast-path in-line. + */ +int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) +{ + spinlock_t *ptl; + pmd_t *new = pmd_alloc_one(mm, address); + if (!new) + return -ENOMEM; + + smp_wmb(); /* See comment in __pte_alloc */ + + ptl = pud_lock(mm, pud); + if (!pud_present(*pud)) { + mm_inc_nr_pmds(mm); + pud_populate(mm, pud, new); + } else /* Another has populated it */ + pmd_free(mm, new); + spin_unlock(ptl); + return 0; +} +#endif /* __PAGETABLE_PMD_FOLDED */ + +int follow_invalidate_pte(struct mm_struct *mm, unsigned long address, + struct mmu_notifier_range *range, pte_t **ptepp, + pmd_t **pmdpp, spinlock_t **ptlp) +{ + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *ptep; + + pgd = pgd_offset(mm, address); + if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) + goto out; + + p4d = p4d_offset(pgd, address); + if (p4d_none(*p4d) || unlikely(p4d_bad(*p4d))) + goto out; + + pud = pud_offset(p4d, address); + if (pud_none(*pud) || unlikely(pud_bad(*pud))) + goto out; + + pmd = pmd_offset(pud, address); + VM_BUG_ON(pmd_trans_huge(*pmd)); + + if (pmd_huge(*pmd)) { + if (!pmdpp) + goto out; + + if (range) { + mmu_notifier_range_init(range, MMU_NOTIFY_CLEAR, 0, + NULL, mm, address & PMD_MASK, + (address & PMD_MASK) + PMD_SIZE); + mmu_notifier_invalidate_range_start(range); + } + *ptlp = pmd_lock(mm, pmd); + if (pmd_huge(*pmd)) { + *pmdpp = pmd; + return 0; + } + spin_unlock(*ptlp); + if (range) + mmu_notifier_invalidate_range_end(range); + } + + if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) + goto out; + + if (range) { + mmu_notifier_range_init(range, MMU_NOTIFY_CLEAR, 0, NULL, mm, + address & PAGE_MASK, + (address & PAGE_MASK) + PAGE_SIZE); + mmu_notifier_invalidate_range_start(range); + } + ptep = pte_offset_map_lock(mm, pmd, address, ptlp); + if (!pte_present(*ptep)) + goto unlock; + *ptepp = ptep; + return 0; +unlock: + pte_unmap_unlock(ptep, *ptlp); + if (range) + mmu_notifier_invalidate_range_end(range); +out: + return -EINVAL; +} + +/** + * follow_pte - look up PTE at a user virtual address + * @mm: the mm_struct of the target address space + * @address: user virtual address + * @ptepp: location to store found PTE + * @ptlp: location to store the lock for the PTE + * + * On a successful return, the pointer to the PTE is stored in @ptepp; + * the corresponding lock is taken and its location is stored in @ptlp. + * The contents of the PTE are only stable until @ptlp is released; + * any further use, if any, must be protected against invalidation + * with MMU notifiers. + * + * Only IO mappings and raw PFN mappings are allowed. The mmap semaphore + * should be taken for read. + * + * KVM uses this function. While it is arguably less bad than ``follow_pfn``, + * it is not a good general-purpose API. + * + * Return: zero on success, -ve otherwise. + */ +int follow_pte(struct mm_struct *mm, unsigned long address, + pte_t **ptepp, spinlock_t **ptlp) +{ + return follow_invalidate_pte(mm, address, NULL, ptepp, NULL, ptlp); +} +EXPORT_SYMBOL_GPL(follow_pte); + +/** + * follow_pfn - look up PFN at a user virtual address + * @vma: memory mapping + * @address: user virtual address + * @pfn: location to store found PFN + * + * Only IO mappings and raw PFN mappings are allowed. + * + * This function does not allow the caller to read the permissions + * of the PTE. Do not use it. + * + * Return: zero and the pfn at @pfn on success, -ve otherwise. + */ +int follow_pfn(struct vm_area_struct *vma, unsigned long address, + unsigned long *pfn) +{ + int ret = -EINVAL; + spinlock_t *ptl; + pte_t *ptep; + + if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) + return ret; + + ret = follow_pte(vma->vm_mm, address, &ptep, &ptl); + if (ret) + return ret; + *pfn = pte_pfn(*ptep); + pte_unmap_unlock(ptep, ptl); + return 0; +} +EXPORT_SYMBOL(follow_pfn); + +#ifdef CONFIG_HAVE_IOREMAP_PROT +int follow_phys(struct vm_area_struct *vma, + unsigned long address, unsigned int flags, + unsigned long *prot, resource_size_t *phys) +{ + int ret = -EINVAL; + pte_t *ptep, pte; + spinlock_t *ptl; + + if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) + goto out; + + if (follow_pte(vma->vm_mm, address, &ptep, &ptl)) + goto out; + pte = *ptep; + + if ((flags & FOLL_WRITE) && !pte_write(pte)) + goto unlock; + + *prot = pgprot_val(pte_pgprot(pte)); + *phys = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT; + + ret = 0; +unlock: + pte_unmap_unlock(ptep, ptl); +out: + return ret; +} + +int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, + void *buf, int len, int write) +{ + resource_size_t phys_addr; + unsigned long prot = 0; + void __iomem *maddr; + int offset = addr & (PAGE_SIZE-1); + + if (follow_phys(vma, addr, write, &prot, &phys_addr)) + return -EINVAL; + + maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot); + if (!maddr) + return -ENOMEM; + + if (write) + memcpy_toio(maddr + offset, buf, len); + else + memcpy_fromio(buf, maddr + offset, len); + iounmap(maddr); + + return len; +} +EXPORT_SYMBOL_GPL(generic_access_phys); +#endif + +/* + * Access another process' address space as given in mm. If non-NULL, use the + * given task for page fault accounting. + */ +int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, + unsigned long addr, void *buf, int len, unsigned int gup_flags) +{ + struct vm_area_struct *vma; + void *old_buf = buf; + int write = gup_flags & FOLL_WRITE; + + if (mmap_read_lock_killable(mm)) + return 0; + + /* ignore errors, just check how much was successfully transferred */ + while (len) { + int bytes, ret, offset; + void *maddr; + struct page *page = NULL; + + ret = get_user_pages_remote(mm, addr, 1, + gup_flags, &page, &vma, NULL); + if (ret <= 0) { +#ifndef CONFIG_HAVE_IOREMAP_PROT + break; +#else + /* + * Check if this is a VM_IO | VM_PFNMAP VMA, which + * we can access using slightly different code. + */ + vma = find_vma(mm, addr); + if (!vma || vma->vm_start > addr) + break; + if (vma->vm_ops && vma->vm_ops->access) + ret = vma->vm_ops->access(vma, addr, buf, + len, write); + if (ret <= 0) + break; + bytes = ret; +#endif + } else { + bytes = len; + offset = addr & (PAGE_SIZE-1); + if (bytes > PAGE_SIZE-offset) + bytes = PAGE_SIZE-offset; + + maddr = kmap(page); + if (write) { + copy_to_user_page(vma, page, addr, + maddr + offset, buf, bytes); + set_page_dirty_lock(page); + } else { + copy_from_user_page(vma, page, addr, + buf, maddr + offset, bytes); + } + kunmap(page); + put_page(page); + } + len -= bytes; + buf += bytes; + addr += bytes; + } + mmap_read_unlock(mm); + + return buf - old_buf; +} + +/** + * access_remote_vm - access another process' address space + * @mm: the mm_struct of the target address space + * @addr: start address to access + * @buf: source or destination buffer + * @len: number of bytes to transfer + * @gup_flags: flags modifying lookup behaviour + * + * The caller must hold a reference on @mm. + * + * Return: number of bytes copied from source to destination. + */ +int access_remote_vm(struct mm_struct *mm, unsigned long addr, + void *buf, int len, unsigned int gup_flags) +{ + return __access_remote_vm(NULL, mm, addr, buf, len, gup_flags); +} + +/* + * Access another process' address space. + * Source/target buffer must be kernel space, + * Do not walk the page table directly, use get_user_pages + */ +int access_process_vm(struct task_struct *tsk, unsigned long addr, + void *buf, int len, unsigned int gup_flags) +{ + struct mm_struct *mm; + int ret; + + mm = get_task_mm(tsk); + if (!mm) + return 0; + + ret = __access_remote_vm(tsk, mm, addr, buf, len, gup_flags); + + mmput(mm); + + return ret; +} +EXPORT_SYMBOL_GPL(access_process_vm); + +/* + * Print the name of a VMA. + */ +void print_vma_addr(char *prefix, unsigned long ip) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + + /* + * we might be running from an atomic context so we cannot sleep + */ + if (!mmap_read_trylock(mm)) + return; + + vma = find_vma(mm, ip); + if (vma && vma->vm_file) { + struct file *f = vma->vm_file; + char *buf = (char *)__get_free_page(GFP_NOWAIT); + if (buf) { + char *p; + + p = file_path(f, buf, PAGE_SIZE); + if (IS_ERR(p)) + p = "?"; + printk("%s%s[%lx+%lx]", prefix, kbasename(p), + vma->vm_start, + vma->vm_end - vma->vm_start); + free_page((unsigned long)buf); + } + } + mmap_read_unlock(mm); +} + +#if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP) +void __might_fault(const char *file, int line) +{ + /* + * Some code (nfs/sunrpc) uses socket ops on kernel memory while + * holding the mmap_lock, this is safe because kernel memory doesn't + * get paged out, therefore we'll never actually fault, and the + * below annotations will generate false positives. + */ + if (uaccess_kernel()) + return; + if (pagefault_disabled()) + return; + __might_sleep(file, line, 0); +#if defined(CONFIG_DEBUG_ATOMIC_SLEEP) + if (current->mm) + might_lock_read(¤t->mm->mmap_lock); +#endif +} +EXPORT_SYMBOL(__might_fault); +#endif + +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) +/* + * Process all subpages of the specified huge page with the specified + * operation. The target subpage will be processed last to keep its + * cache lines hot. + */ +static inline void process_huge_page( + unsigned long addr_hint, unsigned int pages_per_huge_page, + void (*process_subpage)(unsigned long addr, int idx, void *arg), + void *arg) +{ + int i, n, base, l; + unsigned long addr = addr_hint & + ~(((unsigned long)pages_per_huge_page << PAGE_SHIFT) - 1); + + /* Process target subpage last to keep its cache lines hot */ + might_sleep(); + n = (addr_hint - addr) / PAGE_SIZE; + if (2 * n <= pages_per_huge_page) { + /* If target subpage in first half of huge page */ + base = 0; + l = n; + /* Process subpages at the end of huge page */ + for (i = pages_per_huge_page - 1; i >= 2 * n; i--) { + cond_resched(); + process_subpage(addr + i * PAGE_SIZE, i, arg); + } + } else { + /* If target subpage in second half of huge page */ + base = pages_per_huge_page - 2 * (pages_per_huge_page - n); + l = pages_per_huge_page - n; + /* Process subpages at the begin of huge page */ + for (i = 0; i < base; i++) { + cond_resched(); + process_subpage(addr + i * PAGE_SIZE, i, arg); + } + } + /* + * Process remaining subpages in left-right-left-right pattern + * towards the target subpage + */ + for (i = 0; i < l; i++) { + int left_idx = base + i; + int right_idx = base + 2 * l - 1 - i; + + cond_resched(); + process_subpage(addr + left_idx * PAGE_SIZE, left_idx, arg); + cond_resched(); + process_subpage(addr + right_idx * PAGE_SIZE, right_idx, arg); + } +} + +static void clear_gigantic_page(struct page *page, + unsigned long addr, + unsigned int pages_per_huge_page) +{ + int i; + struct page *p = page; + + might_sleep(); + for (i = 0; i < pages_per_huge_page; + i++, p = mem_map_next(p, page, i)) { + cond_resched(); + clear_user_highpage(p, addr + i * PAGE_SIZE); + } +} + +static void clear_subpage(unsigned long addr, int idx, void *arg) +{ + struct page *page = arg; + + clear_user_highpage(page + idx, addr); +} + +void clear_huge_page(struct page *page, + unsigned long addr_hint, unsigned int pages_per_huge_page) +{ + unsigned long addr = addr_hint & + ~(((unsigned long)pages_per_huge_page << PAGE_SHIFT) - 1); + + if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) { + clear_gigantic_page(page, addr, pages_per_huge_page); + return; + } + + process_huge_page(addr_hint, pages_per_huge_page, clear_subpage, page); +} + +static void copy_user_gigantic_page(struct page *dst, struct page *src, + unsigned long addr, + struct vm_area_struct *vma, + unsigned int pages_per_huge_page) +{ + int i; + struct page *dst_base = dst; + struct page *src_base = src; + + for (i = 0; i < pages_per_huge_page; ) { + cond_resched(); + copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma); + + i++; + dst = mem_map_next(dst, dst_base, i); + src = mem_map_next(src, src_base, i); + } +} + +struct copy_subpage_arg { + struct page *dst; + struct page *src; + struct vm_area_struct *vma; +}; + +static void copy_subpage(unsigned long addr, int idx, void *arg) +{ + struct copy_subpage_arg *copy_arg = arg; + + copy_user_highpage(copy_arg->dst + idx, copy_arg->src + idx, + addr, copy_arg->vma); +} + +void copy_user_huge_page(struct page *dst, struct page *src, + unsigned long addr_hint, struct vm_area_struct *vma, + unsigned int pages_per_huge_page) +{ + unsigned long addr = addr_hint & + ~(((unsigned long)pages_per_huge_page << PAGE_SHIFT) - 1); + struct copy_subpage_arg arg = { + .dst = dst, + .src = src, + .vma = vma, + }; + + if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) { + copy_user_gigantic_page(dst, src, addr, vma, + pages_per_huge_page); + return; + } + + process_huge_page(addr_hint, pages_per_huge_page, copy_subpage, &arg); +} + +long copy_huge_page_from_user(struct page *dst_page, + const void __user *usr_src, + unsigned int pages_per_huge_page, + bool allow_pagefault) +{ + void *src = (void *)usr_src; + void *page_kaddr; + unsigned long i, rc = 0; + unsigned long ret_val = pages_per_huge_page * PAGE_SIZE; + struct page *subpage = dst_page; + + for (i = 0; i < pages_per_huge_page; + i++, subpage = mem_map_next(subpage, dst_page, i)) { + if (allow_pagefault) + page_kaddr = kmap(subpage); + else + page_kaddr = kmap_atomic(subpage); + rc = copy_from_user(page_kaddr, + (const void __user *)(src + i * PAGE_SIZE), + PAGE_SIZE); + if (allow_pagefault) + kunmap(subpage); + else + kunmap_atomic(page_kaddr); + + ret_val -= (PAGE_SIZE - rc); + if (rc) + break; + + flush_dcache_page(subpage); + + cond_resched(); + } + return ret_val; +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ + +#if USE_SPLIT_PTE_PTLOCKS && ALLOC_SPLIT_PTLOCKS + +static struct kmem_cache *page_ptl_cachep; + +void __init ptlock_cache_init(void) +{ + page_ptl_cachep = kmem_cache_create("page->ptl", sizeof(spinlock_t), 0, + SLAB_PANIC, NULL); +} + +bool ptlock_alloc(struct page *page) +{ + spinlock_t *ptl; + + ptl = kmem_cache_alloc(page_ptl_cachep, GFP_KERNEL); + if (!ptl) + return false; + page->ptl = ptl; + return true; +} + +void ptlock_free(struct page *page) +{ + kmem_cache_free(page_ptl_cachep, page->ptl); +} +#endif diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c new file mode 100644 index 000000000..553b0705d --- /dev/null +++ b/mm/memory_hotplug.c @@ -0,0 +1,1906 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/mm/memory_hotplug.c + * + * Copyright (C) + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "internal.h" +#include "shuffle.h" + +/* + * online_page_callback contains pointer to current page onlining function. + * Initially it is generic_online_page(). If it is required it could be + * changed by calling set_online_page_callback() for callback registration + * and restore_online_page_callback() for generic callback restore. + */ + +static online_page_callback_t online_page_callback = generic_online_page; +static DEFINE_MUTEX(online_page_callback_lock); + +DEFINE_STATIC_PERCPU_RWSEM(mem_hotplug_lock); + +void get_online_mems(void) +{ + percpu_down_read(&mem_hotplug_lock); +} + +void put_online_mems(void) +{ + percpu_up_read(&mem_hotplug_lock); +} + +bool movable_node_enabled = false; + +#ifndef CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE +int memhp_default_online_type = MMOP_OFFLINE; +#else +int memhp_default_online_type = MMOP_ONLINE; +#endif + +static int __init setup_memhp_default_state(char *str) +{ + const int online_type = memhp_online_type_from_str(str); + + if (online_type >= 0) + memhp_default_online_type = online_type; + + return 1; +} +__setup("memhp_default_state=", setup_memhp_default_state); + +void mem_hotplug_begin(void) +{ + cpus_read_lock(); + percpu_down_write(&mem_hotplug_lock); +} + +void mem_hotplug_done(void) +{ + percpu_up_write(&mem_hotplug_lock); + cpus_read_unlock(); +} + +u64 max_mem_size = U64_MAX; + +/* add this memory to iomem resource */ +static struct resource *register_memory_resource(u64 start, u64 size, + const char *resource_name) +{ + struct resource *res; + unsigned long flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + + if (strcmp(resource_name, "System RAM")) + flags |= IORESOURCE_SYSRAM_DRIVER_MANAGED; + + /* + * Make sure value parsed from 'mem=' only restricts memory adding + * while booting, so that memory hotplug won't be impacted. Please + * refer to document of 'mem=' in kernel-parameters.txt for more + * details. + */ + if (start + size > max_mem_size && system_state < SYSTEM_RUNNING) + return ERR_PTR(-E2BIG); + + /* + * Request ownership of the new memory range. This might be + * a child of an existing resource that was present but + * not marked as busy. + */ + res = __request_region(&iomem_resource, start, size, + resource_name, flags); + + if (!res) { + pr_debug("Unable to reserve System RAM region: %016llx->%016llx\n", + start, start + size); + return ERR_PTR(-EEXIST); + } + return res; +} + +static void release_memory_resource(struct resource *res) +{ + if (!res) + return; + release_resource(res); + kfree(res); +} + +#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +void get_page_bootmem(unsigned long info, struct page *page, + unsigned long type) +{ + page->freelist = (void *)type; + SetPagePrivate(page); + set_page_private(page, info); + page_ref_inc(page); +} + +void put_page_bootmem(struct page *page) +{ + unsigned long type; + + type = (unsigned long) page->freelist; + BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE || + type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE); + + if (page_ref_dec_return(page) == 1) { + page->freelist = NULL; + ClearPagePrivate(page); + set_page_private(page, 0); + INIT_LIST_HEAD(&page->lru); + free_reserved_page(page); + } +} + +#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE +#ifndef CONFIG_SPARSEMEM_VMEMMAP +static void register_page_bootmem_info_section(unsigned long start_pfn) +{ + unsigned long mapsize, section_nr, i; + struct mem_section *ms; + struct page *page, *memmap; + struct mem_section_usage *usage; + + section_nr = pfn_to_section_nr(start_pfn); + ms = __nr_to_section(section_nr); + + /* Get section's memmap address */ + memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr); + + /* + * Get page for the memmap's phys address + * XXX: need more consideration for sparse_vmemmap... + */ + page = virt_to_page(memmap); + mapsize = sizeof(struct page) * PAGES_PER_SECTION; + mapsize = PAGE_ALIGN(mapsize) >> PAGE_SHIFT; + + /* remember memmap's page */ + for (i = 0; i < mapsize; i++, page++) + get_page_bootmem(section_nr, page, SECTION_INFO); + + usage = ms->usage; + page = virt_to_page(usage); + + mapsize = PAGE_ALIGN(mem_section_usage_size()) >> PAGE_SHIFT; + + for (i = 0; i < mapsize; i++, page++) + get_page_bootmem(section_nr, page, MIX_SECTION_INFO); + +} +#else /* CONFIG_SPARSEMEM_VMEMMAP */ +static void register_page_bootmem_info_section(unsigned long start_pfn) +{ + unsigned long mapsize, section_nr, i; + struct mem_section *ms; + struct page *page, *memmap; + struct mem_section_usage *usage; + + section_nr = pfn_to_section_nr(start_pfn); + ms = __nr_to_section(section_nr); + + memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr); + + register_page_bootmem_memmap(section_nr, memmap, PAGES_PER_SECTION); + + usage = ms->usage; + page = virt_to_page(usage); + + mapsize = PAGE_ALIGN(mem_section_usage_size()) >> PAGE_SHIFT; + + for (i = 0; i < mapsize; i++, page++) + get_page_bootmem(section_nr, page, MIX_SECTION_INFO); +} +#endif /* !CONFIG_SPARSEMEM_VMEMMAP */ + +void __init register_page_bootmem_info_node(struct pglist_data *pgdat) +{ + unsigned long i, pfn, end_pfn, nr_pages; + int node = pgdat->node_id; + struct page *page; + + nr_pages = PAGE_ALIGN(sizeof(struct pglist_data)) >> PAGE_SHIFT; + page = virt_to_page(pgdat); + + for (i = 0; i < nr_pages; i++, page++) + get_page_bootmem(node, page, NODE_INFO); + + pfn = pgdat->node_start_pfn; + end_pfn = pgdat_end_pfn(pgdat); + + /* register section info */ + for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) { + /* + * Some platforms can assign the same pfn to multiple nodes - on + * node0 as well as nodeN. To avoid registering a pfn against + * multiple nodes we check that this pfn does not already + * reside in some other nodes. + */ + if (pfn_valid(pfn) && (early_pfn_to_nid(pfn) == node)) + register_page_bootmem_info_section(pfn); + } +} +#endif /* CONFIG_HAVE_BOOTMEM_INFO_NODE */ + +static int check_pfn_span(unsigned long pfn, unsigned long nr_pages, + const char *reason) +{ + /* + * Disallow all operations smaller than a sub-section and only + * allow operations smaller than a section for + * SPARSEMEM_VMEMMAP. Note that check_hotplug_memory_range() + * enforces a larger memory_block_size_bytes() granularity for + * memory that will be marked online, so this check should only + * fire for direct arch_{add,remove}_memory() users outside of + * add_memory_resource(). + */ + unsigned long min_align; + + if (IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP)) + min_align = PAGES_PER_SUBSECTION; + else + min_align = PAGES_PER_SECTION; + if (!IS_ALIGNED(pfn, min_align) + || !IS_ALIGNED(nr_pages, min_align)) { + WARN(1, "Misaligned __%s_pages start: %#lx end: #%lx\n", + reason, pfn, pfn + nr_pages - 1); + return -EINVAL; + } + return 0; +} + +static int check_hotplug_memory_addressable(unsigned long pfn, + unsigned long nr_pages) +{ + const u64 max_addr = PFN_PHYS(pfn + nr_pages) - 1; + + if (max_addr >> MAX_PHYSMEM_BITS) { + const u64 max_allowed = (1ull << (MAX_PHYSMEM_BITS + 1)) - 1; + WARN(1, + "Hotplugged memory exceeds maximum addressable address, range=%#llx-%#llx, maximum=%#llx\n", + (u64)PFN_PHYS(pfn), max_addr, max_allowed); + return -E2BIG; + } + + return 0; +} + +/* + * Reasonably generic function for adding memory. It is + * expected that archs that support memory hotplug will + * call this function after deciding the zone to which to + * add the new pages. + */ +int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages, + struct mhp_params *params) +{ + const unsigned long end_pfn = pfn + nr_pages; + unsigned long cur_nr_pages; + int err; + struct vmem_altmap *altmap = params->altmap; + + if (WARN_ON_ONCE(!params->pgprot.pgprot)) + return -EINVAL; + + err = check_hotplug_memory_addressable(pfn, nr_pages); + if (err) + return err; + + if (altmap) { + /* + * Validate altmap is within bounds of the total request + */ + if (altmap->base_pfn != pfn + || vmem_altmap_offset(altmap) > nr_pages) { + pr_warn_once("memory add fail, invalid altmap\n"); + return -EINVAL; + } + altmap->alloc = 0; + } + + err = check_pfn_span(pfn, nr_pages, "add"); + if (err) + return err; + + for (; pfn < end_pfn; pfn += cur_nr_pages) { + /* Select all remaining pages up to the next section boundary */ + cur_nr_pages = min(end_pfn - pfn, + SECTION_ALIGN_UP(pfn + 1) - pfn); + err = sparse_add_section(nid, pfn, cur_nr_pages, altmap); + if (err) + break; + cond_resched(); + } + vmemmap_populate_print_last(); + return err; +} + +/* find the smallest valid pfn in the range [start_pfn, end_pfn) */ +static unsigned long find_smallest_section_pfn(int nid, struct zone *zone, + unsigned long start_pfn, + unsigned long end_pfn) +{ + for (; start_pfn < end_pfn; start_pfn += PAGES_PER_SUBSECTION) { + if (unlikely(!pfn_to_online_page(start_pfn))) + continue; + + if (unlikely(pfn_to_nid(start_pfn) != nid)) + continue; + + if (zone != page_zone(pfn_to_page(start_pfn))) + continue; + + return start_pfn; + } + + return 0; +} + +/* find the biggest valid pfn in the range [start_pfn, end_pfn). */ +static unsigned long find_biggest_section_pfn(int nid, struct zone *zone, + unsigned long start_pfn, + unsigned long end_pfn) +{ + unsigned long pfn; + + /* pfn is the end pfn of a memory section. */ + pfn = end_pfn - 1; + for (; pfn >= start_pfn; pfn -= PAGES_PER_SUBSECTION) { + if (unlikely(!pfn_to_online_page(pfn))) + continue; + + if (unlikely(pfn_to_nid(pfn) != nid)) + continue; + + if (zone != page_zone(pfn_to_page(pfn))) + continue; + + return pfn; + } + + return 0; +} + +static void shrink_zone_span(struct zone *zone, unsigned long start_pfn, + unsigned long end_pfn) +{ + unsigned long pfn; + int nid = zone_to_nid(zone); + + zone_span_writelock(zone); + if (zone->zone_start_pfn == start_pfn) { + /* + * If the section is smallest section in the zone, it need + * shrink zone->zone_start_pfn and zone->zone_spanned_pages. + * In this case, we find second smallest valid mem_section + * for shrinking zone. + */ + pfn = find_smallest_section_pfn(nid, zone, end_pfn, + zone_end_pfn(zone)); + if (pfn) { + zone->spanned_pages = zone_end_pfn(zone) - pfn; + zone->zone_start_pfn = pfn; + } else { + zone->zone_start_pfn = 0; + zone->spanned_pages = 0; + } + } else if (zone_end_pfn(zone) == end_pfn) { + /* + * If the section is biggest section in the zone, it need + * shrink zone->spanned_pages. + * In this case, we find second biggest valid mem_section for + * shrinking zone. + */ + pfn = find_biggest_section_pfn(nid, zone, zone->zone_start_pfn, + start_pfn); + if (pfn) + zone->spanned_pages = pfn - zone->zone_start_pfn + 1; + else { + zone->zone_start_pfn = 0; + zone->spanned_pages = 0; + } + } + zone_span_writeunlock(zone); +} + +static void update_pgdat_span(struct pglist_data *pgdat) +{ + unsigned long node_start_pfn = 0, node_end_pfn = 0; + struct zone *zone; + + for (zone = pgdat->node_zones; + zone < pgdat->node_zones + MAX_NR_ZONES; zone++) { + unsigned long zone_end_pfn = zone->zone_start_pfn + + zone->spanned_pages; + + /* No need to lock the zones, they can't change. */ + if (!zone->spanned_pages) + continue; + if (!node_end_pfn) { + node_start_pfn = zone->zone_start_pfn; + node_end_pfn = zone_end_pfn; + continue; + } + + if (zone_end_pfn > node_end_pfn) + node_end_pfn = zone_end_pfn; + if (zone->zone_start_pfn < node_start_pfn) + node_start_pfn = zone->zone_start_pfn; + } + + pgdat->node_start_pfn = node_start_pfn; + pgdat->node_spanned_pages = node_end_pfn - node_start_pfn; +} + +void __ref remove_pfn_range_from_zone(struct zone *zone, + unsigned long start_pfn, + unsigned long nr_pages) +{ + const unsigned long end_pfn = start_pfn + nr_pages; + struct pglist_data *pgdat = zone->zone_pgdat; + unsigned long pfn, cur_nr_pages, flags; + + /* Poison struct pages because they are now uninitialized again. */ + for (pfn = start_pfn; pfn < end_pfn; pfn += cur_nr_pages) { + cond_resched(); + + /* Select all remaining pages up to the next section boundary */ + cur_nr_pages = + min(end_pfn - pfn, SECTION_ALIGN_UP(pfn + 1) - pfn); + page_init_poison(pfn_to_page(pfn), + sizeof(struct page) * cur_nr_pages); + } + +#ifdef CONFIG_ZONE_DEVICE + /* + * Zone shrinking code cannot properly deal with ZONE_DEVICE. So + * we will not try to shrink the zones - which is okay as + * set_zone_contiguous() cannot deal with ZONE_DEVICE either way. + */ + if (zone_idx(zone) == ZONE_DEVICE) + return; +#endif + + clear_zone_contiguous(zone); + + pgdat_resize_lock(zone->zone_pgdat, &flags); + shrink_zone_span(zone, start_pfn, start_pfn + nr_pages); + update_pgdat_span(pgdat); + pgdat_resize_unlock(zone->zone_pgdat, &flags); + + set_zone_contiguous(zone); +} + +static void __remove_section(unsigned long pfn, unsigned long nr_pages, + unsigned long map_offset, + struct vmem_altmap *altmap) +{ + struct mem_section *ms = __pfn_to_section(pfn); + + if (WARN_ON_ONCE(!valid_section(ms))) + return; + + sparse_remove_section(ms, pfn, nr_pages, map_offset, altmap); +} + +/** + * __remove_pages() - remove sections of pages + * @pfn: starting pageframe (must be aligned to start of a section) + * @nr_pages: number of pages to remove (must be multiple of section size) + * @altmap: alternative device page map or %NULL if default memmap is used + * + * Generic helper function to remove section mappings and sysfs entries + * for the section of the memory we are removing. Caller needs to make + * sure that pages are marked reserved and zones are adjust properly by + * calling offline_pages(). + */ +void __remove_pages(unsigned long pfn, unsigned long nr_pages, + struct vmem_altmap *altmap) +{ + const unsigned long end_pfn = pfn + nr_pages; + unsigned long cur_nr_pages; + unsigned long map_offset = 0; + + map_offset = vmem_altmap_offset(altmap); + + if (check_pfn_span(pfn, nr_pages, "remove")) + return; + + for (; pfn < end_pfn; pfn += cur_nr_pages) { + cond_resched(); + /* Select all remaining pages up to the next section boundary */ + cur_nr_pages = min(end_pfn - pfn, + SECTION_ALIGN_UP(pfn + 1) - pfn); + __remove_section(pfn, cur_nr_pages, map_offset, altmap); + map_offset = 0; + } +} + +int set_online_page_callback(online_page_callback_t callback) +{ + int rc = -EINVAL; + + get_online_mems(); + mutex_lock(&online_page_callback_lock); + + if (online_page_callback == generic_online_page) { + online_page_callback = callback; + rc = 0; + } + + mutex_unlock(&online_page_callback_lock); + put_online_mems(); + + return rc; +} +EXPORT_SYMBOL_GPL(set_online_page_callback); + +int restore_online_page_callback(online_page_callback_t callback) +{ + int rc = -EINVAL; + + get_online_mems(); + mutex_lock(&online_page_callback_lock); + + if (online_page_callback == callback) { + online_page_callback = generic_online_page; + rc = 0; + } + + mutex_unlock(&online_page_callback_lock); + put_online_mems(); + + return rc; +} +EXPORT_SYMBOL_GPL(restore_online_page_callback); + +void generic_online_page(struct page *page, unsigned int order) +{ + /* + * Freeing the page with debug_pagealloc enabled will try to unmap it, + * so we should map it first. This is better than introducing a special + * case in page freeing fast path. + */ + if (debug_pagealloc_enabled_static()) + kernel_map_pages(page, 1 << order, 1); + __free_pages_core(page, order); + totalram_pages_add(1UL << order); +#ifdef CONFIG_HIGHMEM + if (PageHighMem(page)) + totalhigh_pages_add(1UL << order); +#endif +} +EXPORT_SYMBOL_GPL(generic_online_page); + +static void online_pages_range(unsigned long start_pfn, unsigned long nr_pages) +{ + const unsigned long end_pfn = start_pfn + nr_pages; + unsigned long pfn; + + /* + * Online the pages in MAX_ORDER - 1 aligned chunks. The callback might + * decide to not expose all pages to the buddy (e.g., expose them + * later). We account all pages as being online and belonging to this + * zone ("present"). + */ + for (pfn = start_pfn; pfn < end_pfn; pfn += MAX_ORDER_NR_PAGES) + (*online_page_callback)(pfn_to_page(pfn), MAX_ORDER - 1); + + /* mark all involved sections as online */ + online_mem_sections(start_pfn, end_pfn); +} + +/* check which state of node_states will be changed when online memory */ +static void node_states_check_changes_online(unsigned long nr_pages, + struct zone *zone, struct memory_notify *arg) +{ + int nid = zone_to_nid(zone); + + arg->status_change_nid = NUMA_NO_NODE; + arg->status_change_nid_normal = NUMA_NO_NODE; + arg->status_change_nid_high = NUMA_NO_NODE; + + if (!node_state(nid, N_MEMORY)) + arg->status_change_nid = nid; + if (zone_idx(zone) <= ZONE_NORMAL && !node_state(nid, N_NORMAL_MEMORY)) + arg->status_change_nid_normal = nid; +#ifdef CONFIG_HIGHMEM + if (zone_idx(zone) <= ZONE_HIGHMEM && !node_state(nid, N_HIGH_MEMORY)) + arg->status_change_nid_high = nid; +#endif +} + +static void node_states_set_node(int node, struct memory_notify *arg) +{ + if (arg->status_change_nid_normal >= 0) + node_set_state(node, N_NORMAL_MEMORY); + + if (arg->status_change_nid_high >= 0) + node_set_state(node, N_HIGH_MEMORY); + + if (arg->status_change_nid >= 0) + node_set_state(node, N_MEMORY); +} + +static void __meminit resize_zone_range(struct zone *zone, unsigned long start_pfn, + unsigned long nr_pages) +{ + unsigned long old_end_pfn = zone_end_pfn(zone); + + if (zone_is_empty(zone) || start_pfn < zone->zone_start_pfn) + zone->zone_start_pfn = start_pfn; + + zone->spanned_pages = max(start_pfn + nr_pages, old_end_pfn) - zone->zone_start_pfn; +} + +static void __meminit resize_pgdat_range(struct pglist_data *pgdat, unsigned long start_pfn, + unsigned long nr_pages) +{ + unsigned long old_end_pfn = pgdat_end_pfn(pgdat); + + if (!pgdat->node_spanned_pages || start_pfn < pgdat->node_start_pfn) + pgdat->node_start_pfn = start_pfn; + + pgdat->node_spanned_pages = max(start_pfn + nr_pages, old_end_pfn) - pgdat->node_start_pfn; + +} +/* + * Associate the pfn range with the given zone, initializing the memmaps + * and resizing the pgdat/zone data to span the added pages. After this + * call, all affected pages are PG_reserved. + * + * All aligned pageblocks are initialized to the specified migratetype + * (usually MIGRATE_MOVABLE). Besides setting the migratetype, no related + * zone stats (e.g., nr_isolate_pageblock) are touched. + */ +void __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, + unsigned long nr_pages, + struct vmem_altmap *altmap, int migratetype) +{ + struct pglist_data *pgdat = zone->zone_pgdat; + int nid = pgdat->node_id; + unsigned long flags; + + clear_zone_contiguous(zone); + + /* TODO Huh pgdat is irqsave while zone is not. It used to be like that before */ + pgdat_resize_lock(pgdat, &flags); + zone_span_writelock(zone); + if (zone_is_empty(zone)) + init_currently_empty_zone(zone, start_pfn, nr_pages); + resize_zone_range(zone, start_pfn, nr_pages); + zone_span_writeunlock(zone); + resize_pgdat_range(pgdat, start_pfn, nr_pages); + pgdat_resize_unlock(pgdat, &flags); + + /* + * TODO now we have a visible range of pages which are not associated + * with their zone properly. Not nice but set_pfnblock_flags_mask + * expects the zone spans the pfn range. All the pages in the range + * are reserved so nobody should be touching them so we should be safe + */ + memmap_init_zone(nr_pages, nid, zone_idx(zone), start_pfn, 0, + MEMINIT_HOTPLUG, altmap, migratetype); + + set_zone_contiguous(zone); +} + +/* + * Returns a default kernel memory zone for the given pfn range. + * If no kernel zone covers this pfn range it will automatically go + * to the ZONE_NORMAL. + */ +static struct zone *default_kernel_zone_for_pfn(int nid, unsigned long start_pfn, + unsigned long nr_pages) +{ + struct pglist_data *pgdat = NODE_DATA(nid); + int zid; + + for (zid = 0; zid <= ZONE_NORMAL; zid++) { + struct zone *zone = &pgdat->node_zones[zid]; + + if (zone_intersects(zone, start_pfn, nr_pages)) + return zone; + } + + return &pgdat->node_zones[ZONE_NORMAL]; +} + +static inline struct zone *default_zone_for_pfn(int nid, unsigned long start_pfn, + unsigned long nr_pages) +{ + struct zone *kernel_zone = default_kernel_zone_for_pfn(nid, start_pfn, + nr_pages); + struct zone *movable_zone = &NODE_DATA(nid)->node_zones[ZONE_MOVABLE]; + bool in_kernel = zone_intersects(kernel_zone, start_pfn, nr_pages); + bool in_movable = zone_intersects(movable_zone, start_pfn, nr_pages); + + /* + * We inherit the existing zone in a simple case where zones do not + * overlap in the given range + */ + if (in_kernel ^ in_movable) + return (in_kernel) ? kernel_zone : movable_zone; + + /* + * If the range doesn't belong to any zone or two zones overlap in the + * given range then we use movable zone only if movable_node is + * enabled because we always online to a kernel zone by default. + */ + return movable_node_enabled ? movable_zone : kernel_zone; +} + +struct zone *zone_for_pfn_range(int online_type, int nid, + unsigned long start_pfn, unsigned long nr_pages) +{ + if (online_type == MMOP_ONLINE_KERNEL) + return default_kernel_zone_for_pfn(nid, start_pfn, nr_pages); + + if (online_type == MMOP_ONLINE_MOVABLE) + return &NODE_DATA(nid)->node_zones[ZONE_MOVABLE]; + + return default_zone_for_pfn(nid, start_pfn, nr_pages); +} + +int __ref online_pages(unsigned long pfn, unsigned long nr_pages, + int online_type, int nid) +{ + unsigned long flags; + struct zone *zone; + int need_zonelists_rebuild = 0; + int ret; + struct memory_notify arg; + + /* We can only online full sections (e.g., SECTION_IS_ONLINE) */ + if (WARN_ON_ONCE(!nr_pages || + !IS_ALIGNED(pfn | nr_pages, PAGES_PER_SECTION))) + return -EINVAL; + + mem_hotplug_begin(); + + /* associate pfn range with the zone */ + zone = zone_for_pfn_range(online_type, nid, pfn, nr_pages); + move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_ISOLATE); + + arg.start_pfn = pfn; + arg.nr_pages = nr_pages; + node_states_check_changes_online(nr_pages, zone, &arg); + + ret = memory_notify(MEM_GOING_ONLINE, &arg); + ret = notifier_to_errno(ret); + if (ret) + goto failed_addition; + + /* + * Fixup the number of isolated pageblocks before marking the sections + * onlining, such that undo_isolate_page_range() works correctly. + */ + spin_lock_irqsave(&zone->lock, flags); + zone->nr_isolate_pageblock += nr_pages / pageblock_nr_pages; + spin_unlock_irqrestore(&zone->lock, flags); + + /* + * If this zone is not populated, then it is not in zonelist. + * This means the page allocator ignores this zone. + * So, zonelist must be updated after online. + */ + if (!populated_zone(zone)) { + need_zonelists_rebuild = 1; + setup_zone_pageset(zone); + } + + online_pages_range(pfn, nr_pages); + zone->present_pages += nr_pages; + + pgdat_resize_lock(zone->zone_pgdat, &flags); + zone->zone_pgdat->node_present_pages += nr_pages; + pgdat_resize_unlock(zone->zone_pgdat, &flags); + + node_states_set_node(nid, &arg); + if (need_zonelists_rebuild) + build_all_zonelists(NULL); + zone_pcp_update(zone); + + /* Basic onlining is complete, allow allocation of onlined pages. */ + undo_isolate_page_range(pfn, pfn + nr_pages, MIGRATE_MOVABLE); + + /* + * Freshly onlined pages aren't shuffled (e.g., all pages are placed to + * the tail of the freelist when undoing isolation). Shuffle the whole + * zone to make sure the just onlined pages are properly distributed + * across the whole freelist - to create an initial shuffle. + */ + shuffle_zone(zone); + + init_per_zone_wmark_min(); + + kswapd_run(nid); + kcompactd_run(nid); + + writeback_set_ratelimit(); + + memory_notify(MEM_ONLINE, &arg); + mem_hotplug_done(); + return 0; + +failed_addition: + pr_debug("online_pages [mem %#010llx-%#010llx] failed\n", + (unsigned long long) pfn << PAGE_SHIFT, + (((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1); + memory_notify(MEM_CANCEL_ONLINE, &arg); + remove_pfn_range_from_zone(zone, pfn, nr_pages); + mem_hotplug_done(); + return ret; +} +#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ + +static void reset_node_present_pages(pg_data_t *pgdat) +{ + struct zone *z; + + for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++) + z->present_pages = 0; + + pgdat->node_present_pages = 0; +} + +/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */ +static pg_data_t __ref *hotadd_new_pgdat(int nid) +{ + struct pglist_data *pgdat; + + pgdat = NODE_DATA(nid); + if (!pgdat) { + pgdat = arch_alloc_nodedata(nid); + if (!pgdat) + return NULL; + + pgdat->per_cpu_nodestats = + alloc_percpu(struct per_cpu_nodestat); + arch_refresh_nodedata(nid, pgdat); + } else { + int cpu; + /* + * Reset the nr_zones, order and highest_zoneidx before reuse. + * Note that kswapd will init kswapd_highest_zoneidx properly + * when it starts in the near future. + */ + pgdat->nr_zones = 0; + pgdat->kswapd_order = 0; + pgdat->kswapd_highest_zoneidx = 0; + for_each_online_cpu(cpu) { + struct per_cpu_nodestat *p; + + p = per_cpu_ptr(pgdat->per_cpu_nodestats, cpu); + memset(p, 0, sizeof(*p)); + } + } + + /* we can use NODE_DATA(nid) from here */ + pgdat->node_id = nid; + pgdat->node_start_pfn = 0; + + /* init node's zones as empty zones, we don't have any present pages.*/ + free_area_init_core_hotplug(nid); + + /* + * The node we allocated has no zone fallback lists. For avoiding + * to access not-initialized zonelist, build here. + */ + build_all_zonelists(pgdat); + + /* + * When memory is hot-added, all the memory is in offline state. So + * clear all zones' present_pages because they will be updated in + * online_pages() and offline_pages(). + */ + reset_node_managed_pages(pgdat); + reset_node_present_pages(pgdat); + + return pgdat; +} + +static void rollback_node_hotadd(int nid) +{ + pg_data_t *pgdat = NODE_DATA(nid); + + arch_refresh_nodedata(nid, NULL); + free_percpu(pgdat->per_cpu_nodestats); + arch_free_nodedata(pgdat); +} + + +/** + * try_online_node - online a node if offlined + * @nid: the node ID + * @set_node_online: Whether we want to online the node + * called by cpu_up() to online a node without onlined memory. + * + * Returns: + * 1 -> a new node has been allocated + * 0 -> the node is already online + * -ENOMEM -> the node could not be allocated + */ +static int __try_online_node(int nid, bool set_node_online) +{ + pg_data_t *pgdat; + int ret = 1; + + if (node_online(nid)) + return 0; + + pgdat = hotadd_new_pgdat(nid); + if (!pgdat) { + pr_err("Cannot online node %d due to NULL pgdat\n", nid); + ret = -ENOMEM; + goto out; + } + + if (set_node_online) { + node_set_online(nid); + ret = register_one_node(nid); + BUG_ON(ret); + } +out: + return ret; +} + +/* + * Users of this function always want to online/register the node + */ +int try_online_node(int nid) +{ + int ret; + + mem_hotplug_begin(); + ret = __try_online_node(nid, true); + mem_hotplug_done(); + return ret; +} + +static int check_hotplug_memory_range(u64 start, u64 size) +{ + /* memory range must be block size aligned */ + if (!size || !IS_ALIGNED(start, memory_block_size_bytes()) || + !IS_ALIGNED(size, memory_block_size_bytes())) { + pr_err("Block size [%#lx] unaligned hotplug range: start %#llx, size %#llx", + memory_block_size_bytes(), start, size); + return -EINVAL; + } + + return 0; +} + +static int online_memory_block(struct memory_block *mem, void *arg) +{ + mem->online_type = memhp_default_online_type; + return device_online(&mem->dev); +} + +/* + * NOTE: The caller must call lock_device_hotplug() to serialize hotplug + * and online/offline operations (triggered e.g. by sysfs). + * + * we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG + */ +int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) +{ + struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) }; + u64 start, size; + bool new_node = false; + int ret; + + start = res->start; + size = resource_size(res); + + ret = check_hotplug_memory_range(start, size); + if (ret) + return ret; + + if (!node_possible(nid)) { + WARN(1, "node %d was absent from the node_possible_map\n", nid); + return -EINVAL; + } + + mem_hotplug_begin(); + + if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) + memblock_add_node(start, size, nid); + + ret = __try_online_node(nid, false); + if (ret < 0) + goto error; + new_node = ret; + + /* call arch's memory hotadd */ + ret = arch_add_memory(nid, start, size, ¶ms); + if (ret < 0) + goto error; + + /* create memory block devices after memory was added */ + ret = create_memory_block_devices(start, size); + if (ret) { + arch_remove_memory(nid, start, size, NULL); + goto error; + } + + if (new_node) { + /* If sysfs file of new node can't be created, cpu on the node + * can't be hot-added. There is no rollback way now. + * So, check by BUG_ON() to catch it reluctantly.. + * We online node here. We can't roll back from here. + */ + node_set_online(nid); + ret = __register_one_node(nid); + BUG_ON(ret); + } + + /* link memory sections under this node.*/ + link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1), + MEMINIT_HOTPLUG); + + /* create new memmap entry */ + if (!strcmp(res->name, "System RAM")) + firmware_map_add_hotplug(start, start + size, "System RAM"); + + /* device_online() will take the lock when calling online_pages() */ + mem_hotplug_done(); + + /* + * In case we're allowed to merge the resource, flag it and trigger + * merging now that adding succeeded. + */ + if (mhp_flags & MEMHP_MERGE_RESOURCE) + merge_system_ram_resource(res); + + /* online pages if requested */ + if (memhp_default_online_type != MMOP_OFFLINE) + walk_memory_blocks(start, size, NULL, online_memory_block); + + return ret; +error: + /* rollback pgdat allocation and others */ + if (new_node) + rollback_node_hotadd(nid); + if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) + memblock_remove(start, size); + mem_hotplug_done(); + return ret; +} + +/* requires device_hotplug_lock, see add_memory_resource() */ +int __ref __add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags) +{ + struct resource *res; + int ret; + + res = register_memory_resource(start, size, "System RAM"); + if (IS_ERR(res)) + return PTR_ERR(res); + + ret = add_memory_resource(nid, res, mhp_flags); + if (ret < 0) + release_memory_resource(res); + return ret; +} + +int add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags) +{ + int rc; + + lock_device_hotplug(); + rc = __add_memory(nid, start, size, mhp_flags); + unlock_device_hotplug(); + + return rc; +} +EXPORT_SYMBOL_GPL(add_memory); + +/* + * Add special, driver-managed memory to the system as system RAM. Such + * memory is not exposed via the raw firmware-provided memmap as system + * RAM, instead, it is detected and added by a driver - during cold boot, + * after a reboot, and after kexec. + * + * Reasons why this memory should not be used for the initial memmap of a + * kexec kernel or for placing kexec images: + * - The booting kernel is in charge of determining how this memory will be + * used (e.g., use persistent memory as system RAM) + * - Coordination with a hypervisor is required before this memory + * can be used (e.g., inaccessible parts). + * + * For this memory, no entries in /sys/firmware/memmap ("raw firmware-provided + * memory map") are created. Also, the created memory resource is flagged + * with IORESOURCE_SYSRAM_DRIVER_MANAGED, so in-kernel users can special-case + * this memory as well (esp., not place kexec images onto it). + * + * The resource_name (visible via /proc/iomem) has to have the format + * "System RAM ($DRIVER)". + */ +int add_memory_driver_managed(int nid, u64 start, u64 size, + const char *resource_name, mhp_t mhp_flags) +{ + struct resource *res; + int rc; + + if (!resource_name || + strstr(resource_name, "System RAM (") != resource_name || + resource_name[strlen(resource_name) - 1] != ')') + return -EINVAL; + + lock_device_hotplug(); + + res = register_memory_resource(start, size, resource_name); + if (IS_ERR(res)) { + rc = PTR_ERR(res); + goto out_unlock; + } + + rc = add_memory_resource(nid, res, mhp_flags); + if (rc < 0) + release_memory_resource(res); + +out_unlock: + unlock_device_hotplug(); + return rc; +} +EXPORT_SYMBOL_GPL(add_memory_driver_managed); + +#ifdef CONFIG_MEMORY_HOTREMOVE +/* + * Confirm all pages in a range [start, end) belong to the same zone (skipping + * memory holes). When true, return the zone. + */ +struct zone *test_pages_in_a_zone(unsigned long start_pfn, + unsigned long end_pfn) +{ + unsigned long pfn, sec_end_pfn; + struct zone *zone = NULL; + struct page *page; + int i; + for (pfn = start_pfn, sec_end_pfn = SECTION_ALIGN_UP(start_pfn + 1); + pfn < end_pfn; + pfn = sec_end_pfn, sec_end_pfn += PAGES_PER_SECTION) { + /* Make sure the memory section is present first */ + if (!present_section_nr(pfn_to_section_nr(pfn))) + continue; + for (; pfn < sec_end_pfn && pfn < end_pfn; + pfn += MAX_ORDER_NR_PAGES) { + i = 0; + /* This is just a CONFIG_HOLES_IN_ZONE check.*/ + while ((i < MAX_ORDER_NR_PAGES) && + !pfn_valid_within(pfn + i)) + i++; + if (i == MAX_ORDER_NR_PAGES || pfn + i >= end_pfn) + continue; + /* Check if we got outside of the zone */ + if (zone && !zone_spans_pfn(zone, pfn + i)) + return NULL; + page = pfn_to_page(pfn + i); + if (zone && page_zone(page) != zone) + return NULL; + zone = page_zone(page); + } + } + + return zone; +} + +/* + * Scan pfn range [start,end) to find movable/migratable pages (LRU pages, + * non-lru movable pages and hugepages). Will skip over most unmovable + * pages (esp., pages that can be skipped when offlining), but bail out on + * definitely unmovable pages. + * + * Returns: + * 0 in case a movable page is found and movable_pfn was updated. + * -ENOENT in case no movable page was found. + * -EBUSY in case a definitely unmovable page was found. + */ +static int scan_movable_pages(unsigned long start, unsigned long end, + unsigned long *movable_pfn) +{ + unsigned long pfn; + + for (pfn = start; pfn < end; pfn++) { + struct page *page, *head; + unsigned long skip; + + if (!pfn_valid(pfn)) + continue; + page = pfn_to_page(pfn); + if (PageLRU(page)) + goto found; + if (__PageMovable(page)) + goto found; + + /* + * PageOffline() pages that are not marked __PageMovable() and + * have a reference count > 0 (after MEM_GOING_OFFLINE) are + * definitely unmovable. If their reference count would be 0, + * they could at least be skipped when offlining memory. + */ + if (PageOffline(page) && page_count(page)) + return -EBUSY; + + if (!PageHuge(page)) + continue; + head = compound_head(page); + if (page_huge_active(head)) + goto found; + skip = compound_nr(head) - (pfn - page_to_pfn(head)); + pfn += skip - 1; + } + return -ENOENT; +found: + *movable_pfn = pfn; + return 0; +} + +static int +do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) +{ + unsigned long pfn; + struct page *page, *head; + int ret = 0; + LIST_HEAD(source); + static DEFINE_RATELIMIT_STATE(migrate_rs, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); + + for (pfn = start_pfn; pfn < end_pfn; pfn++) { + if (!pfn_valid(pfn)) + continue; + page = pfn_to_page(pfn); + head = compound_head(page); + + if (PageHuge(page)) { + pfn = page_to_pfn(head) + compound_nr(head) - 1; + isolate_hugetlb(head, &source); + continue; + } else if (PageTransHuge(page)) + pfn = page_to_pfn(head) + thp_nr_pages(page) - 1; + + /* + * HWPoison pages have elevated reference counts so the migration would + * fail on them. It also doesn't make any sense to migrate them in the + * first place. Still try to unmap such a page in case it is still mapped + * (e.g. current hwpoison implementation doesn't unmap KSM pages but keep + * the unmap as the catch all safety net). + */ + if (PageHWPoison(page)) { + if (WARN_ON(PageLRU(page))) + isolate_lru_page(page); + if (page_mapped(page)) + try_to_unmap(page, TTU_IGNORE_MLOCK); + continue; + } + + if (!get_page_unless_zero(page)) + continue; + /* + * We can skip free pages. And we can deal with pages on + * LRU and non-lru movable pages. + */ + if (PageLRU(page)) + ret = isolate_lru_page(page); + else + ret = isolate_movable_page(page, ISOLATE_UNEVICTABLE); + if (!ret) { /* Success */ + list_add_tail(&page->lru, &source); + if (!__PageMovable(page)) + inc_node_page_state(page, NR_ISOLATED_ANON + + page_is_file_lru(page)); + + } else { + if (__ratelimit(&migrate_rs)) { + pr_warn("failed to isolate pfn %lx\n", pfn); + dump_page(page, "isolation failed"); + } + } + put_page(page); + } + if (!list_empty(&source)) { + nodemask_t nmask = node_states[N_MEMORY]; + struct migration_target_control mtc = { + .nmask = &nmask, + .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL, + }; + + /* + * We have checked that migration range is on a single zone so + * we can use the nid of the first page to all the others. + */ + mtc.nid = page_to_nid(list_first_entry(&source, struct page, lru)); + + /* + * try to allocate from a different node but reuse this node + * if there are no other online nodes to be used (e.g. we are + * offlining a part of the only existing node) + */ + node_clear(mtc.nid, nmask); + if (nodes_empty(nmask)) + node_set(mtc.nid, nmask); + ret = migrate_pages(&source, alloc_migration_target, NULL, + (unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_HOTPLUG); + if (ret) { + list_for_each_entry(page, &source, lru) { + if (__ratelimit(&migrate_rs)) { + pr_warn("migrating pfn %lx failed ret:%d\n", + page_to_pfn(page), ret); + dump_page(page, "migration failure"); + } + } + putback_movable_pages(&source); + } + } + + return ret; +} + +static int __init cmdline_parse_movable_node(char *p) +{ + movable_node_enabled = true; + return 0; +} +early_param("movable_node", cmdline_parse_movable_node); + +/* check which state of node_states will be changed when offline memory */ +static void node_states_check_changes_offline(unsigned long nr_pages, + struct zone *zone, struct memory_notify *arg) +{ + struct pglist_data *pgdat = zone->zone_pgdat; + unsigned long present_pages = 0; + enum zone_type zt; + + arg->status_change_nid = NUMA_NO_NODE; + arg->status_change_nid_normal = NUMA_NO_NODE; + arg->status_change_nid_high = NUMA_NO_NODE; + + /* + * Check whether node_states[N_NORMAL_MEMORY] will be changed. + * If the memory to be offline is within the range + * [0..ZONE_NORMAL], and it is the last present memory there, + * the zones in that range will become empty after the offlining, + * thus we can determine that we need to clear the node from + * node_states[N_NORMAL_MEMORY]. + */ + for (zt = 0; zt <= ZONE_NORMAL; zt++) + present_pages += pgdat->node_zones[zt].present_pages; + if (zone_idx(zone) <= ZONE_NORMAL && nr_pages >= present_pages) + arg->status_change_nid_normal = zone_to_nid(zone); + +#ifdef CONFIG_HIGHMEM + /* + * node_states[N_HIGH_MEMORY] contains nodes which + * have normal memory or high memory. + * Here we add the present_pages belonging to ZONE_HIGHMEM. + * If the zone is within the range of [0..ZONE_HIGHMEM), and + * we determine that the zones in that range become empty, + * we need to clear the node for N_HIGH_MEMORY. + */ + present_pages += pgdat->node_zones[ZONE_HIGHMEM].present_pages; + if (zone_idx(zone) <= ZONE_HIGHMEM && nr_pages >= present_pages) + arg->status_change_nid_high = zone_to_nid(zone); +#endif + + /* + * We have accounted the pages from [0..ZONE_NORMAL), and + * in case of CONFIG_HIGHMEM the pages from ZONE_HIGHMEM + * as well. + * Here we count the possible pages from ZONE_MOVABLE. + * If after having accounted all the pages, we see that the nr_pages + * to be offlined is over or equal to the accounted pages, + * we know that the node will become empty, and so, we can clear + * it for N_MEMORY as well. + */ + present_pages += pgdat->node_zones[ZONE_MOVABLE].present_pages; + + if (nr_pages >= present_pages) + arg->status_change_nid = zone_to_nid(zone); +} + +static void node_states_clear_node(int node, struct memory_notify *arg) +{ + if (arg->status_change_nid_normal >= 0) + node_clear_state(node, N_NORMAL_MEMORY); + + if (arg->status_change_nid_high >= 0) + node_clear_state(node, N_HIGH_MEMORY); + + if (arg->status_change_nid >= 0) + node_clear_state(node, N_MEMORY); +} + +static int count_system_ram_pages_cb(unsigned long start_pfn, + unsigned long nr_pages, void *data) +{ + unsigned long *nr_system_ram_pages = data; + + *nr_system_ram_pages += nr_pages; + return 0; +} + +int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages) +{ + const unsigned long end_pfn = start_pfn + nr_pages; + unsigned long pfn, system_ram_pages = 0; + unsigned long flags; + struct zone *zone; + struct memory_notify arg; + int ret, node; + char *reason; + + /* We can only offline full sections (e.g., SECTION_IS_ONLINE) */ + if (WARN_ON_ONCE(!nr_pages || + !IS_ALIGNED(start_pfn | nr_pages, PAGES_PER_SECTION))) + return -EINVAL; + + mem_hotplug_begin(); + + /* + * Don't allow to offline memory blocks that contain holes. + * Consequently, memory blocks with holes can never get onlined + * via the hotplug path - online_pages() - as hotplugged memory has + * no holes. This way, we e.g., don't have to worry about marking + * memory holes PG_reserved, don't need pfn_valid() checks, and can + * avoid using walk_system_ram_range() later. + */ + walk_system_ram_range(start_pfn, nr_pages, &system_ram_pages, + count_system_ram_pages_cb); + if (system_ram_pages != nr_pages) { + ret = -EINVAL; + reason = "memory holes"; + goto failed_removal; + } + + /* This makes hotplug much easier...and readable. + we assume this for now. .*/ + zone = test_pages_in_a_zone(start_pfn, end_pfn); + if (!zone) { + ret = -EINVAL; + reason = "multizone range"; + goto failed_removal; + } + node = zone_to_nid(zone); + + /* set above range as isolated */ + ret = start_isolate_page_range(start_pfn, end_pfn, + MIGRATE_MOVABLE, + MEMORY_OFFLINE | REPORT_FAILURE); + if (ret) { + reason = "failure to isolate range"; + goto failed_removal; + } + + arg.start_pfn = start_pfn; + arg.nr_pages = nr_pages; + node_states_check_changes_offline(nr_pages, zone, &arg); + + ret = memory_notify(MEM_GOING_OFFLINE, &arg); + ret = notifier_to_errno(ret); + if (ret) { + reason = "notifier failure"; + goto failed_removal_isolated; + } + + do { + pfn = start_pfn; + do { + if (signal_pending(current)) { + ret = -EINTR; + reason = "signal backoff"; + goto failed_removal_isolated; + } + + cond_resched(); + lru_add_drain_all(); + + ret = scan_movable_pages(pfn, end_pfn, &pfn); + if (!ret) { + /* + * TODO: fatal migration failures should bail + * out + */ + do_migrate_range(pfn, end_pfn); + } + } while (!ret); + + if (ret != -ENOENT) { + reason = "unmovable page"; + goto failed_removal_isolated; + } + + /* + * Dissolve free hugepages in the memory block before doing + * offlining actually in order to make hugetlbfs's object + * counting consistent. + */ + ret = dissolve_free_huge_pages(start_pfn, end_pfn); + if (ret) { + reason = "failure to dissolve huge pages"; + goto failed_removal_isolated; + } + + /* + * per-cpu pages are drained in start_isolate_page_range, but if + * there are still pages that are not free, make sure that we + * drain again, because when we isolated range we might + * have raced with another thread that was adding pages to pcp + * list. + * + * Forward progress should be still guaranteed because + * pages on the pcp list can only belong to MOVABLE_ZONE + * because has_unmovable_pages explicitly checks for + * PageBuddy on freed pages on other zones. + */ + ret = test_pages_isolated(start_pfn, end_pfn, MEMORY_OFFLINE); + if (ret) + drain_all_pages(zone); + } while (ret); + + /* Mark all sections offline and remove free pages from the buddy. */ + __offline_isolated_pages(start_pfn, end_pfn); + pr_info("Offlined Pages %ld\n", nr_pages); + + /* + * The memory sections are marked offline, and the pageblock flags + * effectively stale; nobody should be touching them. Fixup the number + * of isolated pageblocks, memory onlining will properly revert this. + */ + spin_lock_irqsave(&zone->lock, flags); + zone->nr_isolate_pageblock -= nr_pages / pageblock_nr_pages; + spin_unlock_irqrestore(&zone->lock, flags); + + /* removal success */ + adjust_managed_page_count(pfn_to_page(start_pfn), -nr_pages); + zone->present_pages -= nr_pages; + + pgdat_resize_lock(zone->zone_pgdat, &flags); + zone->zone_pgdat->node_present_pages -= nr_pages; + pgdat_resize_unlock(zone->zone_pgdat, &flags); + + init_per_zone_wmark_min(); + + if (!populated_zone(zone)) { + zone_pcp_reset(zone); + build_all_zonelists(NULL); + } else + zone_pcp_update(zone); + + node_states_clear_node(node, &arg); + if (arg.status_change_nid >= 0) { + kswapd_stop(node); + kcompactd_stop(node); + } + + writeback_set_ratelimit(); + + memory_notify(MEM_OFFLINE, &arg); + remove_pfn_range_from_zone(zone, start_pfn, nr_pages); + mem_hotplug_done(); + return 0; + +failed_removal_isolated: + undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE); + memory_notify(MEM_CANCEL_OFFLINE, &arg); +failed_removal: + pr_debug("memory offlining [mem %#010llx-%#010llx] failed due to %s\n", + (unsigned long long) start_pfn << PAGE_SHIFT, + ((unsigned long long) end_pfn << PAGE_SHIFT) - 1, + reason); + /* pushback to free area */ + mem_hotplug_done(); + return ret; +} + +static int check_memblock_offlined_cb(struct memory_block *mem, void *arg) +{ + int ret = !is_memblock_offlined(mem); + + if (unlikely(ret)) { + phys_addr_t beginpa, endpa; + + beginpa = PFN_PHYS(section_nr_to_pfn(mem->start_section_nr)); + endpa = beginpa + memory_block_size_bytes() - 1; + pr_warn("removing memory fails, because memory [%pa-%pa] is onlined\n", + &beginpa, &endpa); + + return -EBUSY; + } + return 0; +} + +static int check_cpu_on_node(pg_data_t *pgdat) +{ + int cpu; + + for_each_present_cpu(cpu) { + if (cpu_to_node(cpu) == pgdat->node_id) + /* + * the cpu on this node isn't removed, and we can't + * offline this node. + */ + return -EBUSY; + } + + return 0; +} + +static int check_no_memblock_for_node_cb(struct memory_block *mem, void *arg) +{ + int nid = *(int *)arg; + + /* + * If a memory block belongs to multiple nodes, the stored nid is not + * reliable. However, such blocks are always online (e.g., cannot get + * offlined) and, therefore, are still spanned by the node. + */ + return mem->nid == nid ? -EEXIST : 0; +} + +/** + * try_offline_node + * @nid: the node ID + * + * Offline a node if all memory sections and cpus of the node are removed. + * + * NOTE: The caller must call lock_device_hotplug() to serialize hotplug + * and online/offline operations before this call. + */ +void try_offline_node(int nid) +{ + pg_data_t *pgdat = NODE_DATA(nid); + int rc; + + /* + * If the node still spans pages (especially ZONE_DEVICE), don't + * offline it. A node spans memory after move_pfn_range_to_zone(), + * e.g., after the memory block was onlined. + */ + if (pgdat->node_spanned_pages) + return; + + /* + * Especially offline memory blocks might not be spanned by the + * node. They will get spanned by the node once they get onlined. + * However, they link to the node in sysfs and can get onlined later. + */ + rc = for_each_memory_block(&nid, check_no_memblock_for_node_cb); + if (rc) + return; + + if (check_cpu_on_node(pgdat)) + return; + + /* + * all memory/cpu of this node are removed, we can offline this + * node now. + */ + node_set_offline(nid); + unregister_one_node(nid); +} +EXPORT_SYMBOL(try_offline_node); + +static int __ref try_remove_memory(int nid, u64 start, u64 size) +{ + int rc = 0; + + BUG_ON(check_hotplug_memory_range(start, size)); + + /* + * All memory blocks must be offlined before removing memory. Check + * whether all memory blocks in question are offline and return error + * if this is not the case. + */ + rc = walk_memory_blocks(start, size, NULL, check_memblock_offlined_cb); + if (rc) + return rc; + + /* remove memmap entry */ + firmware_map_remove(start, start + size, "System RAM"); + + /* + * Memory block device removal under the device_hotplug_lock is + * a barrier against racing online attempts. + */ + remove_memory_block_devices(start, size); + + mem_hotplug_begin(); + + arch_remove_memory(nid, start, size, NULL); + + if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) { + memblock_free(start, size); + memblock_remove(start, size); + } + + release_mem_region_adjustable(start, size); + + try_offline_node(nid); + + mem_hotplug_done(); + return 0; +} + +/** + * remove_memory + * @nid: the node ID + * @start: physical address of the region to remove + * @size: size of the region to remove + * + * NOTE: The caller must call lock_device_hotplug() to serialize hotplug + * and online/offline operations before this call, as required by + * try_offline_node(). + */ +void __remove_memory(int nid, u64 start, u64 size) +{ + + /* + * trigger BUG() if some memory is not offlined prior to calling this + * function + */ + if (try_remove_memory(nid, start, size)) + BUG(); +} + +/* + * Remove memory if every memory block is offline, otherwise return -EBUSY is + * some memory is not offline + */ +int remove_memory(int nid, u64 start, u64 size) +{ + int rc; + + lock_device_hotplug(); + rc = try_remove_memory(nid, start, size); + unlock_device_hotplug(); + + return rc; +} +EXPORT_SYMBOL_GPL(remove_memory); + +static int try_offline_memory_block(struct memory_block *mem, void *arg) +{ + uint8_t online_type = MMOP_ONLINE_KERNEL; + uint8_t **online_types = arg; + struct page *page; + int rc; + + /* + * Sense the online_type via the zone of the memory block. Offlining + * with multiple zones within one memory block will be rejected + * by offlining code ... so we don't care about that. + */ + page = pfn_to_online_page(section_nr_to_pfn(mem->start_section_nr)); + if (page && zone_idx(page_zone(page)) == ZONE_MOVABLE) + online_type = MMOP_ONLINE_MOVABLE; + + rc = device_offline(&mem->dev); + /* + * Default is MMOP_OFFLINE - change it only if offlining succeeded, + * so try_reonline_memory_block() can do the right thing. + */ + if (!rc) + **online_types = online_type; + + (*online_types)++; + /* Ignore if already offline. */ + return rc < 0 ? rc : 0; +} + +static int try_reonline_memory_block(struct memory_block *mem, void *arg) +{ + uint8_t **online_types = arg; + int rc; + + if (**online_types != MMOP_OFFLINE) { + mem->online_type = **online_types; + rc = device_online(&mem->dev); + if (rc < 0) + pr_warn("%s: Failed to re-online memory: %d", + __func__, rc); + } + + /* Continue processing all remaining memory blocks. */ + (*online_types)++; + return 0; +} + +/* + * Try to offline and remove memory. Might take a long time to finish in case + * memory is still in use. Primarily useful for memory devices that logically + * unplugged all memory (so it's no longer in use) and want to offline + remove + * that memory. + */ +int offline_and_remove_memory(int nid, u64 start, u64 size) +{ + const unsigned long mb_count = size / memory_block_size_bytes(); + uint8_t *online_types, *tmp; + int rc; + + if (!IS_ALIGNED(start, memory_block_size_bytes()) || + !IS_ALIGNED(size, memory_block_size_bytes()) || !size) + return -EINVAL; + + /* + * We'll remember the old online type of each memory block, so we can + * try to revert whatever we did when offlining one memory block fails + * after offlining some others succeeded. + */ + online_types = kmalloc_array(mb_count, sizeof(*online_types), + GFP_KERNEL); + if (!online_types) + return -ENOMEM; + /* + * Initialize all states to MMOP_OFFLINE, so when we abort processing in + * try_offline_memory_block(), we'll skip all unprocessed blocks in + * try_reonline_memory_block(). + */ + memset(online_types, MMOP_OFFLINE, mb_count); + + lock_device_hotplug(); + + tmp = online_types; + rc = walk_memory_blocks(start, size, &tmp, try_offline_memory_block); + + /* + * In case we succeeded to offline all memory, remove it. + * This cannot fail as it cannot get onlined in the meantime. + */ + if (!rc) { + rc = try_remove_memory(nid, start, size); + if (rc) + pr_err("%s: Failed to remove memory: %d", __func__, rc); + } + + /* + * Rollback what we did. While memory onlining might theoretically fail + * (nacked by a notifier), it barely ever happens. + */ + if (rc) { + tmp = online_types; + walk_memory_blocks(start, size, &tmp, + try_reonline_memory_block); + } + unlock_device_hotplug(); + + kfree(online_types); + return rc; +} +EXPORT_SYMBOL_GPL(offline_and_remove_memory); +#endif /* CONFIG_MEMORY_HOTREMOVE */ diff --git a/mm/mempolicy.c b/mm/mempolicy.c new file mode 100644 index 000000000..6c98585f2 --- /dev/null +++ b/mm/mempolicy.c @@ -0,0 +1,3050 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Simple NUMA memory policy for the Linux kernel. + * + * Copyright 2003,2004 Andi Kleen, SuSE Labs. + * (C) Copyright 2005 Christoph Lameter, Silicon Graphics, Inc. + * + * NUMA policy allows the user to give hints in which node(s) memory should + * be allocated. + * + * Support four policies per VMA and per process: + * + * The VMA policy has priority over the process policy for a page fault. + * + * interleave Allocate memory interleaved over a set of nodes, + * with normal fallback if it fails. + * For VMA based allocations this interleaves based on the + * offset into the backing object or offset into the mapping + * for anonymous memory. For process policy an process counter + * is used. + * + * bind Only allocate memory on a specific set of nodes, + * no fallback. + * FIXME: memory is allocated starting with the first node + * to the last. It would be better if bind would truly restrict + * the allocation to memory nodes instead + * + * preferred Try a specific node first before normal fallback. + * As a special case NUMA_NO_NODE here means do the allocation + * on the local CPU. This is normally identical to default, + * but useful to set in a VMA when you have a non default + * process policy. + * + * default Allocate on the local node first, or when on a VMA + * use the process policy. This is what Linux always did + * in a NUMA aware kernel and still does by, ahem, default. + * + * The process policy is applied for most non interrupt memory allocations + * in that process' context. Interrupts ignore the policies and always + * try to allocate on the local CPU. The VMA policy is only applied for memory + * allocations for a VMA in the VM. + * + * Currently there are a few corner cases in swapping where the policy + * is not applied, but the majority should be handled. When process policy + * is used it is not remembered over swap outs/swap ins. + * + * Only the highest zone in the zone hierarchy gets policied. Allocations + * requesting a lower zone just use default policy. This implies that + * on systems with highmem kernel lowmem allocation don't get policied. + * Same with GFP_DMA allocations. + * + * For shmfs/tmpfs/hugetlbfs shared memory the policy is shared between + * all users and remembered even when nobody has memory mapped. + */ + +/* Notebook: + fix mmap readahead to honour policy and enable policy for any page cache + object + statistics for bigpages + global policy for page cache? currently it uses process policy. Requires + first item above. + handle mremap for shared memory (currently ignored for the policy) + grows down? + make bind policy root only? It can trigger oom much faster and the + kernel is not always grateful with that. +*/ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include "internal.h" + +/* Internal flags */ +#define MPOL_MF_DISCONTIG_OK (MPOL_MF_INTERNAL << 0) /* Skip checks for continuous vmas */ +#define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1) /* Invert check for nodemask */ + +static struct kmem_cache *policy_cache; +static struct kmem_cache *sn_cache; + +/* Highest zone. An specific allocation for a zone below that is not + policied. */ +enum zone_type policy_zone = 0; + +/* + * run-time system-wide default policy => local allocation + */ +static struct mempolicy default_policy = { + .refcnt = ATOMIC_INIT(1), /* never free it */ + .mode = MPOL_PREFERRED, + .flags = MPOL_F_LOCAL, +}; + +static struct mempolicy preferred_node_policy[MAX_NUMNODES]; + +/** + * numa_map_to_online_node - Find closest online node + * @node: Node id to start the search + * + * Lookup the next closest node by distance if @nid is not online. + */ +int numa_map_to_online_node(int node) +{ + int min_dist = INT_MAX, dist, n, min_node; + + if (node == NUMA_NO_NODE || node_online(node)) + return node; + + min_node = node; + for_each_online_node(n) { + dist = node_distance(node, n); + if (dist < min_dist) { + min_dist = dist; + min_node = n; + } + } + + return min_node; +} +EXPORT_SYMBOL_GPL(numa_map_to_online_node); + +struct mempolicy *get_task_policy(struct task_struct *p) +{ + struct mempolicy *pol = p->mempolicy; + int node; + + if (pol) + return pol; + + node = numa_node_id(); + if (node != NUMA_NO_NODE) { + pol = &preferred_node_policy[node]; + /* preferred_node_policy is not initialised early in boot */ + if (pol->mode) + return pol; + } + + return &default_policy; +} + +static const struct mempolicy_operations { + int (*create)(struct mempolicy *pol, const nodemask_t *nodes); + void (*rebind)(struct mempolicy *pol, const nodemask_t *nodes); +} mpol_ops[MPOL_MAX]; + +static inline int mpol_store_user_nodemask(const struct mempolicy *pol) +{ + return pol->flags & MPOL_MODE_FLAGS; +} + +static void mpol_relative_nodemask(nodemask_t *ret, const nodemask_t *orig, + const nodemask_t *rel) +{ + nodemask_t tmp; + nodes_fold(tmp, *orig, nodes_weight(*rel)); + nodes_onto(*ret, tmp, *rel); +} + +static int mpol_new_interleave(struct mempolicy *pol, const nodemask_t *nodes) +{ + if (nodes_empty(*nodes)) + return -EINVAL; + pol->v.nodes = *nodes; + return 0; +} + +static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes) +{ + if (!nodes) + pol->flags |= MPOL_F_LOCAL; /* local allocation */ + else if (nodes_empty(*nodes)) + return -EINVAL; /* no allowed nodes */ + else + pol->v.preferred_node = first_node(*nodes); + return 0; +} + +static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes) +{ + if (nodes_empty(*nodes)) + return -EINVAL; + pol->v.nodes = *nodes; + return 0; +} + +/* + * mpol_set_nodemask is called after mpol_new() to set up the nodemask, if + * any, for the new policy. mpol_new() has already validated the nodes + * parameter with respect to the policy mode and flags. But, we need to + * handle an empty nodemask with MPOL_PREFERRED here. + * + * Must be called holding task's alloc_lock to protect task's mems_allowed + * and mempolicy. May also be called holding the mmap_lock for write. + */ +static int mpol_set_nodemask(struct mempolicy *pol, + const nodemask_t *nodes, struct nodemask_scratch *nsc) +{ + int ret; + + /* if mode is MPOL_DEFAULT, pol is NULL. This is right. */ + if (pol == NULL) + return 0; + /* Check N_MEMORY */ + nodes_and(nsc->mask1, + cpuset_current_mems_allowed, node_states[N_MEMORY]); + + VM_BUG_ON(!nodes); + if (pol->mode == MPOL_PREFERRED && nodes_empty(*nodes)) + nodes = NULL; /* explicit local allocation */ + else { + if (pol->flags & MPOL_F_RELATIVE_NODES) + mpol_relative_nodemask(&nsc->mask2, nodes, &nsc->mask1); + else + nodes_and(nsc->mask2, *nodes, nsc->mask1); + + if (mpol_store_user_nodemask(pol)) + pol->w.user_nodemask = *nodes; + else + pol->w.cpuset_mems_allowed = + cpuset_current_mems_allowed; + } + + if (nodes) + ret = mpol_ops[pol->mode].create(pol, &nsc->mask2); + else + ret = mpol_ops[pol->mode].create(pol, NULL); + return ret; +} + +/* + * This function just creates a new policy, does some check and simple + * initialization. You must invoke mpol_set_nodemask() to set nodes. + */ +static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, + nodemask_t *nodes) +{ + struct mempolicy *policy; + + pr_debug("setting mode %d flags %d nodes[0] %lx\n", + mode, flags, nodes ? nodes_addr(*nodes)[0] : NUMA_NO_NODE); + + if (mode == MPOL_DEFAULT) { + if (nodes && !nodes_empty(*nodes)) + return ERR_PTR(-EINVAL); + return NULL; + } + VM_BUG_ON(!nodes); + + /* + * MPOL_PREFERRED cannot be used with MPOL_F_STATIC_NODES or + * MPOL_F_RELATIVE_NODES if the nodemask is empty (local allocation). + * All other modes require a valid pointer to a non-empty nodemask. + */ + if (mode == MPOL_PREFERRED) { + if (nodes_empty(*nodes)) { + if (((flags & MPOL_F_STATIC_NODES) || + (flags & MPOL_F_RELATIVE_NODES))) + return ERR_PTR(-EINVAL); + } + } else if (mode == MPOL_LOCAL) { + if (!nodes_empty(*nodes) || + (flags & MPOL_F_STATIC_NODES) || + (flags & MPOL_F_RELATIVE_NODES)) + return ERR_PTR(-EINVAL); + mode = MPOL_PREFERRED; + } else if (nodes_empty(*nodes)) + return ERR_PTR(-EINVAL); + policy = kmem_cache_alloc(policy_cache, GFP_KERNEL); + if (!policy) + return ERR_PTR(-ENOMEM); + atomic_set(&policy->refcnt, 1); + policy->mode = mode; + policy->flags = flags; + + return policy; +} + +/* Slow path of a mpol destructor. */ +void __mpol_put(struct mempolicy *p) +{ + if (!atomic_dec_and_test(&p->refcnt)) + return; + kmem_cache_free(policy_cache, p); +} + +static void mpol_rebind_default(struct mempolicy *pol, const nodemask_t *nodes) +{ +} + +static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes) +{ + nodemask_t tmp; + + if (pol->flags & MPOL_F_STATIC_NODES) + nodes_and(tmp, pol->w.user_nodemask, *nodes); + else if (pol->flags & MPOL_F_RELATIVE_NODES) + mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes); + else { + nodes_remap(tmp, pol->v.nodes,pol->w.cpuset_mems_allowed, + *nodes); + pol->w.cpuset_mems_allowed = *nodes; + } + + if (nodes_empty(tmp)) + tmp = *nodes; + + pol->v.nodes = tmp; +} + +static void mpol_rebind_preferred(struct mempolicy *pol, + const nodemask_t *nodes) +{ + nodemask_t tmp; + + if (pol->flags & MPOL_F_STATIC_NODES) { + int node = first_node(pol->w.user_nodemask); + + if (node_isset(node, *nodes)) { + pol->v.preferred_node = node; + pol->flags &= ~MPOL_F_LOCAL; + } else + pol->flags |= MPOL_F_LOCAL; + } else if (pol->flags & MPOL_F_RELATIVE_NODES) { + mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes); + pol->v.preferred_node = first_node(tmp); + } else if (!(pol->flags & MPOL_F_LOCAL)) { + pol->v.preferred_node = node_remap(pol->v.preferred_node, + pol->w.cpuset_mems_allowed, + *nodes); + pol->w.cpuset_mems_allowed = *nodes; + } +} + +/* + * mpol_rebind_policy - Migrate a policy to a different set of nodes + * + * Per-vma policies are protected by mmap_lock. Allocations using per-task + * policies are protected by task->mems_allowed_seq to prevent a premature + * OOM/allocation failure due to parallel nodemask modification. + */ +static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask) +{ + if (!pol || pol->mode == MPOL_LOCAL) + return; + if (!mpol_store_user_nodemask(pol) && !(pol->flags & MPOL_F_LOCAL) && + nodes_equal(pol->w.cpuset_mems_allowed, *newmask)) + return; + + mpol_ops[pol->mode].rebind(pol, newmask); +} + +/* + * Wrapper for mpol_rebind_policy() that just requires task + * pointer, and updates task mempolicy. + * + * Called with task's alloc_lock held. + */ + +void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new) +{ + mpol_rebind_policy(tsk->mempolicy, new); +} + +/* + * Rebind each vma in mm to new nodemask. + * + * Call holding a reference to mm. Takes mm->mmap_lock during call. + */ + +void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) +{ + struct vm_area_struct *vma; + + mmap_write_lock(mm); + for (vma = mm->mmap; vma; vma = vma->vm_next) + mpol_rebind_policy(vma->vm_policy, new); + mmap_write_unlock(mm); +} + +static const struct mempolicy_operations mpol_ops[MPOL_MAX] = { + [MPOL_DEFAULT] = { + .rebind = mpol_rebind_default, + }, + [MPOL_INTERLEAVE] = { + .create = mpol_new_interleave, + .rebind = mpol_rebind_nodemask, + }, + [MPOL_PREFERRED] = { + .create = mpol_new_preferred, + .rebind = mpol_rebind_preferred, + }, + [MPOL_BIND] = { + .create = mpol_new_bind, + .rebind = mpol_rebind_nodemask, + }, +}; + +static int migrate_page_add(struct page *page, struct list_head *pagelist, + unsigned long flags); + +struct queue_pages { + struct list_head *pagelist; + unsigned long flags; + nodemask_t *nmask; + unsigned long start; + unsigned long end; + struct vm_area_struct *first; +}; + +/* + * Check if the page's nid is in qp->nmask. + * + * If MPOL_MF_INVERT is set in qp->flags, check if the nid is + * in the invert of qp->nmask. + */ +static inline bool queue_pages_required(struct page *page, + struct queue_pages *qp) +{ + int nid = page_to_nid(page); + unsigned long flags = qp->flags; + + return node_isset(nid, *qp->nmask) == !(flags & MPOL_MF_INVERT); +} + +/* + * queue_pages_pmd() has four possible return values: + * 0 - pages are placed on the right node or queued successfully. + * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were + * specified. + * 2 - THP was split. + * -EIO - is migration entry or only MPOL_MF_STRICT was specified and an + * existing page was already on a node that does not follow the + * policy. + */ +static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, + unsigned long end, struct mm_walk *walk) + __releases(ptl) +{ + int ret = 0; + struct page *page; + struct queue_pages *qp = walk->private; + unsigned long flags; + + if (unlikely(is_pmd_migration_entry(*pmd))) { + ret = -EIO; + goto unlock; + } + page = pmd_page(*pmd); + if (is_huge_zero_page(page)) { + spin_unlock(ptl); + __split_huge_pmd(walk->vma, pmd, addr, false, NULL); + ret = 2; + goto out; + } + if (!queue_pages_required(page, qp)) + goto unlock; + + flags = qp->flags; + /* go to thp migration */ + if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { + if (!vma_migratable(walk->vma) || + migrate_page_add(page, qp->pagelist, flags)) { + ret = 1; + goto unlock; + } + } else + ret = -EIO; +unlock: + spin_unlock(ptl); +out: + return ret; +} + +/* + * Scan through pages checking if pages follow certain conditions, + * and move them to the pagelist if they do. + * + * queue_pages_pte_range() has three possible return values: + * 0 - pages are placed on the right node or queued successfully. + * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were + * specified. + * -EIO - only MPOL_MF_STRICT was specified and an existing page was already + * on a node that does not follow the policy. + */ +static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, + unsigned long end, struct mm_walk *walk) +{ + struct vm_area_struct *vma = walk->vma; + struct page *page; + struct queue_pages *qp = walk->private; + unsigned long flags = qp->flags; + int ret; + bool has_unmovable = false; + pte_t *pte, *mapped_pte; + spinlock_t *ptl; + + ptl = pmd_trans_huge_lock(pmd, vma); + if (ptl) { + ret = queue_pages_pmd(pmd, ptl, addr, end, walk); + if (ret != 2) + return ret; + } + /* THP was split, fall through to pte walk */ + + if (pmd_trans_unstable(pmd)) + return 0; + + mapped_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); + for (; addr != end; pte++, addr += PAGE_SIZE) { + if (!pte_present(*pte)) + continue; + page = vm_normal_page(vma, addr, *pte); + if (!page) + continue; + /* + * vm_normal_page() filters out zero pages, but there might + * still be PageReserved pages to skip, perhaps in a VDSO. + */ + if (PageReserved(page)) + continue; + if (!queue_pages_required(page, qp)) + continue; + if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { + /* MPOL_MF_STRICT must be specified if we get here */ + if (!vma_migratable(vma)) { + has_unmovable = true; + break; + } + + /* + * Do not abort immediately since there may be + * temporary off LRU pages in the range. Still + * need migrate other LRU pages. + */ + if (migrate_page_add(page, qp->pagelist, flags)) + has_unmovable = true; + } else + break; + } + pte_unmap_unlock(mapped_pte, ptl); + cond_resched(); + + if (has_unmovable) + return 1; + + return addr != end ? -EIO : 0; +} + +static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask, + unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + int ret = 0; +#ifdef CONFIG_HUGETLB_PAGE + struct queue_pages *qp = walk->private; + unsigned long flags = (qp->flags & MPOL_MF_VALID); + struct page *page; + spinlock_t *ptl; + pte_t entry; + + ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte); + entry = huge_ptep_get(pte); + if (!pte_present(entry)) + goto unlock; + page = pte_page(entry); + if (!queue_pages_required(page, qp)) + goto unlock; + + if (flags == MPOL_MF_STRICT) { + /* + * STRICT alone means only detecting misplaced page and no + * need to further check other vma. + */ + ret = -EIO; + goto unlock; + } + + if (!vma_migratable(walk->vma)) { + /* + * Must be STRICT with MOVE*, otherwise .test_walk() have + * stopped walking current vma. + * Detecting misplaced page but allow migrating pages which + * have been queued. + */ + ret = 1; + goto unlock; + } + + /* With MPOL_MF_MOVE, we migrate only unshared hugepage. */ + if (flags & (MPOL_MF_MOVE_ALL) || + (flags & MPOL_MF_MOVE && page_mapcount(page) == 1 && + !hugetlb_pmd_shared(pte))) { + if (isolate_hugetlb(page, qp->pagelist) && + (flags & MPOL_MF_STRICT)) + /* + * Failed to isolate page but allow migrating pages + * which have been queued. + */ + ret = 1; + } +unlock: + spin_unlock(ptl); +#else + BUG(); +#endif + return ret; +} + +#ifdef CONFIG_NUMA_BALANCING +/* + * This is used to mark a range of virtual addresses to be inaccessible. + * These are later cleared by a NUMA hinting fault. Depending on these + * faults, pages may be migrated for better NUMA placement. + * + * This is assuming that NUMA faults are handled using PROT_NONE. If + * an architecture makes a different choice, it will need further + * changes to the core. + */ +unsigned long change_prot_numa(struct vm_area_struct *vma, + unsigned long addr, unsigned long end) +{ + int nr_updated; + + nr_updated = change_protection(vma, addr, end, PAGE_NONE, MM_CP_PROT_NUMA); + if (nr_updated) + count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated); + + return nr_updated; +} +#else +static unsigned long change_prot_numa(struct vm_area_struct *vma, + unsigned long addr, unsigned long end) +{ + return 0; +} +#endif /* CONFIG_NUMA_BALANCING */ + +static int queue_pages_test_walk(unsigned long start, unsigned long end, + struct mm_walk *walk) +{ + struct vm_area_struct *vma = walk->vma; + struct queue_pages *qp = walk->private; + unsigned long endvma = vma->vm_end; + unsigned long flags = qp->flags; + + /* range check first */ + VM_BUG_ON_VMA((vma->vm_start > start) || (vma->vm_end < end), vma); + + if (!qp->first) { + qp->first = vma; + if (!(flags & MPOL_MF_DISCONTIG_OK) && + (qp->start < vma->vm_start)) + /* hole at head side of range */ + return -EFAULT; + } + if (!(flags & MPOL_MF_DISCONTIG_OK) && + ((vma->vm_end < qp->end) && + (!vma->vm_next || vma->vm_end < vma->vm_next->vm_start))) + /* hole at middle or tail of range */ + return -EFAULT; + + /* + * Need check MPOL_MF_STRICT to return -EIO if possible + * regardless of vma_migratable + */ + if (!vma_migratable(vma) && + !(flags & MPOL_MF_STRICT)) + return 1; + + if (endvma > end) + endvma = end; + + if (flags & MPOL_MF_LAZY) { + /* Similar to task_numa_work, skip inaccessible VMAs */ + if (!is_vm_hugetlb_page(vma) && vma_is_accessible(vma) && + !(vma->vm_flags & VM_MIXEDMAP)) + change_prot_numa(vma, start, endvma); + return 1; + } + + /* queue pages from current vma */ + if (flags & MPOL_MF_VALID) + return 0; + return 1; +} + +static const struct mm_walk_ops queue_pages_walk_ops = { + .hugetlb_entry = queue_pages_hugetlb, + .pmd_entry = queue_pages_pte_range, + .test_walk = queue_pages_test_walk, +}; + +/* + * Walk through page tables and collect pages to be migrated. + * + * If pages found in a given range are on a set of nodes (determined by + * @nodes and @flags,) it's isolated and queued to the pagelist which is + * passed via @private. + * + * queue_pages_range() has three possible return values: + * 1 - there is unmovable page, but MPOL_MF_MOVE* & MPOL_MF_STRICT were + * specified. + * 0 - queue pages successfully or no misplaced page. + * errno - i.e. misplaced pages with MPOL_MF_STRICT specified (-EIO) or + * memory range specified by nodemask and maxnode points outside + * your accessible address space (-EFAULT) + */ +static int +queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, + nodemask_t *nodes, unsigned long flags, + struct list_head *pagelist) +{ + int err; + struct queue_pages qp = { + .pagelist = pagelist, + .flags = flags, + .nmask = nodes, + .start = start, + .end = end, + .first = NULL, + }; + + err = walk_page_range(mm, start, end, &queue_pages_walk_ops, &qp); + + if (!qp.first) + /* whole range in hole */ + err = -EFAULT; + + return err; +} + +/* + * Apply policy to a single VMA + * This must be called with the mmap_lock held for writing. + */ +static int vma_replace_policy(struct vm_area_struct *vma, + struct mempolicy *pol) +{ + int err; + struct mempolicy *old; + struct mempolicy *new; + + pr_debug("vma %lx-%lx/%lx vm_ops %p vm_file %p set_policy %p\n", + vma->vm_start, vma->vm_end, vma->vm_pgoff, + vma->vm_ops, vma->vm_file, + vma->vm_ops ? vma->vm_ops->set_policy : NULL); + + new = mpol_dup(pol); + if (IS_ERR(new)) + return PTR_ERR(new); + + if (vma->vm_ops && vma->vm_ops->set_policy) { + err = vma->vm_ops->set_policy(vma, new); + if (err) + goto err_out; + } + + old = vma->vm_policy; + vma->vm_policy = new; /* protected by mmap_lock */ + mpol_put(old); + + return 0; + err_out: + mpol_put(new); + return err; +} + +/* Step 2: apply policy to a range and do splits. */ +static int mbind_range(struct mm_struct *mm, unsigned long start, + unsigned long end, struct mempolicy *new_pol) +{ + struct vm_area_struct *prev; + struct vm_area_struct *vma; + int err = 0; + pgoff_t pgoff; + unsigned long vmstart; + unsigned long vmend; + + vma = find_vma(mm, start); + VM_BUG_ON(!vma); + + prev = vma->vm_prev; + if (start > vma->vm_start) + prev = vma; + + for (; vma && vma->vm_start < end; prev = vma, vma = vma->vm_next) { + vmstart = max(start, vma->vm_start); + vmend = min(end, vma->vm_end); + + if (mpol_equal(vma_policy(vma), new_pol)) + continue; + + pgoff = vma->vm_pgoff + + ((vmstart - vma->vm_start) >> PAGE_SHIFT); + prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags, + vma->anon_vma, vma->vm_file, pgoff, + new_pol, vma->vm_userfaultfd_ctx); + if (prev) { + vma = prev; + goto replace; + } + if (vma->vm_start != vmstart) { + err = split_vma(vma->vm_mm, vma, vmstart, 1); + if (err) + goto out; + } + if (vma->vm_end != vmend) { + err = split_vma(vma->vm_mm, vma, vmend, 0); + if (err) + goto out; + } + replace: + err = vma_replace_policy(vma, new_pol); + if (err) + goto out; + } + + out: + return err; +} + +/* Set the process memory policy */ +static long do_set_mempolicy(unsigned short mode, unsigned short flags, + nodemask_t *nodes) +{ + struct mempolicy *new, *old; + NODEMASK_SCRATCH(scratch); + int ret; + + if (!scratch) + return -ENOMEM; + + new = mpol_new(mode, flags, nodes); + if (IS_ERR(new)) { + ret = PTR_ERR(new); + goto out; + } + + ret = mpol_set_nodemask(new, nodes, scratch); + if (ret) { + mpol_put(new); + goto out; + } + task_lock(current); + old = current->mempolicy; + current->mempolicy = new; + if (new && new->mode == MPOL_INTERLEAVE) + current->il_prev = MAX_NUMNODES-1; + task_unlock(current); + mpol_put(old); + ret = 0; +out: + NODEMASK_SCRATCH_FREE(scratch); + return ret; +} + +/* + * Return nodemask for policy for get_mempolicy() query + * + * Called with task's alloc_lock held + */ +static void get_policy_nodemask(struct mempolicy *p, nodemask_t *nodes) +{ + nodes_clear(*nodes); + if (p == &default_policy) + return; + + switch (p->mode) { + case MPOL_BIND: + case MPOL_INTERLEAVE: + *nodes = p->v.nodes; + break; + case MPOL_PREFERRED: + if (!(p->flags & MPOL_F_LOCAL)) + node_set(p->v.preferred_node, *nodes); + /* else return empty node mask for local allocation */ + break; + default: + BUG(); + } +} + +static int lookup_node(struct mm_struct *mm, unsigned long addr) +{ + struct page *p = NULL; + int err; + + int locked = 1; + err = get_user_pages_locked(addr & PAGE_MASK, 1, 0, &p, &locked); + if (err > 0) { + err = page_to_nid(p); + put_page(p); + } + if (locked) + mmap_read_unlock(mm); + return err; +} + +/* Retrieve NUMA policy */ +static long do_get_mempolicy(int *policy, nodemask_t *nmask, + unsigned long addr, unsigned long flags) +{ + int err; + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma = NULL; + struct mempolicy *pol = current->mempolicy, *pol_refcount = NULL; + + if (flags & + ~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR|MPOL_F_MEMS_ALLOWED)) + return -EINVAL; + + if (flags & MPOL_F_MEMS_ALLOWED) { + if (flags & (MPOL_F_NODE|MPOL_F_ADDR)) + return -EINVAL; + *policy = 0; /* just so it's initialized */ + task_lock(current); + *nmask = cpuset_current_mems_allowed; + task_unlock(current); + return 0; + } + + if (flags & MPOL_F_ADDR) { + /* + * Do NOT fall back to task policy if the + * vma/shared policy at addr is NULL. We + * want to return MPOL_DEFAULT in this case. + */ + mmap_read_lock(mm); + vma = find_vma_intersection(mm, addr, addr+1); + if (!vma) { + mmap_read_unlock(mm); + return -EFAULT; + } + if (vma->vm_ops && vma->vm_ops->get_policy) + pol = vma->vm_ops->get_policy(vma, addr); + else + pol = vma->vm_policy; + } else if (addr) + return -EINVAL; + + if (!pol) + pol = &default_policy; /* indicates default behavior */ + + if (flags & MPOL_F_NODE) { + if (flags & MPOL_F_ADDR) { + /* + * Take a refcount on the mpol, lookup_node() + * wil drop the mmap_lock, so after calling + * lookup_node() only "pol" remains valid, "vma" + * is stale. + */ + pol_refcount = pol; + vma = NULL; + mpol_get(pol); + err = lookup_node(mm, addr); + if (err < 0) + goto out; + *policy = err; + } else if (pol == current->mempolicy && + pol->mode == MPOL_INTERLEAVE) { + *policy = next_node_in(current->il_prev, pol->v.nodes); + } else { + err = -EINVAL; + goto out; + } + } else { + *policy = pol == &default_policy ? MPOL_DEFAULT : + pol->mode; + /* + * Internal mempolicy flags must be masked off before exposing + * the policy to userspace. + */ + *policy |= (pol->flags & MPOL_MODE_FLAGS); + } + + err = 0; + if (nmask) { + if (mpol_store_user_nodemask(pol)) { + *nmask = pol->w.user_nodemask; + } else { + task_lock(current); + get_policy_nodemask(pol, nmask); + task_unlock(current); + } + } + + out: + mpol_cond_put(pol); + if (vma) + mmap_read_unlock(mm); + if (pol_refcount) + mpol_put(pol_refcount); + return err; +} + +#ifdef CONFIG_MIGRATION +/* + * page migration, thp tail pages can be passed. + */ +static int migrate_page_add(struct page *page, struct list_head *pagelist, + unsigned long flags) +{ + struct page *head = compound_head(page); + /* + * Avoid migrating a page that is shared with others. + */ + if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(head) == 1) { + if (!isolate_lru_page(head)) { + list_add_tail(&head->lru, pagelist); + mod_node_page_state(page_pgdat(head), + NR_ISOLATED_ANON + page_is_file_lru(head), + thp_nr_pages(head)); + } else if (flags & MPOL_MF_STRICT) { + /* + * Non-movable page may reach here. And, there may be + * temporary off LRU pages or non-LRU movable pages. + * Treat them as unmovable pages since they can't be + * isolated, so they can't be moved at the moment. It + * should return -EIO for this case too. + */ + return -EIO; + } + } + + return 0; +} + +/* + * Migrate pages from one node to a target node. + * Returns error or the number of pages not migrated. + */ +static int migrate_to_node(struct mm_struct *mm, int source, int dest, + int flags) +{ + nodemask_t nmask; + LIST_HEAD(pagelist); + int err = 0; + struct migration_target_control mtc = { + .nid = dest, + .gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, + }; + + nodes_clear(nmask); + node_set(source, nmask); + + /* + * This does not "check" the range but isolates all pages that + * need migration. Between passing in the full user address + * space range and MPOL_MF_DISCONTIG_OK, this call can not fail. + */ + VM_BUG_ON(!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))); + queue_pages_range(mm, mm->mmap->vm_start, mm->task_size, &nmask, + flags | MPOL_MF_DISCONTIG_OK, &pagelist); + + if (!list_empty(&pagelist)) { + err = migrate_pages(&pagelist, alloc_migration_target, NULL, + (unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL); + if (err) + putback_movable_pages(&pagelist); + } + + return err; +} + +/* + * Move pages between the two nodesets so as to preserve the physical + * layout as much as possible. + * + * Returns the number of page that could not be moved. + */ +int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, + const nodemask_t *to, int flags) +{ + int busy = 0; + int err; + nodemask_t tmp; + + err = migrate_prep(); + if (err) + return err; + + mmap_read_lock(mm); + + /* + * Find a 'source' bit set in 'tmp' whose corresponding 'dest' + * bit in 'to' is not also set in 'tmp'. Clear the found 'source' + * bit in 'tmp', and return that pair for migration. + * The pair of nodemasks 'to' and 'from' define the map. + * + * If no pair of bits is found that way, fallback to picking some + * pair of 'source' and 'dest' bits that are not the same. If the + * 'source' and 'dest' bits are the same, this represents a node + * that will be migrating to itself, so no pages need move. + * + * If no bits are left in 'tmp', or if all remaining bits left + * in 'tmp' correspond to the same bit in 'to', return false + * (nothing left to migrate). + * + * This lets us pick a pair of nodes to migrate between, such that + * if possible the dest node is not already occupied by some other + * source node, minimizing the risk of overloading the memory on a + * node that would happen if we migrated incoming memory to a node + * before migrating outgoing memory source that same node. + * + * A single scan of tmp is sufficient. As we go, we remember the + * most recent pair that moved (s != d). If we find a pair + * that not only moved, but what's better, moved to an empty slot + * (d is not set in tmp), then we break out then, with that pair. + * Otherwise when we finish scanning from_tmp, we at least have the + * most recent pair that moved. If we get all the way through + * the scan of tmp without finding any node that moved, much less + * moved to an empty node, then there is nothing left worth migrating. + */ + + tmp = *from; + while (!nodes_empty(tmp)) { + int s,d; + int source = NUMA_NO_NODE; + int dest = 0; + + for_each_node_mask(s, tmp) { + + /* + * do_migrate_pages() tries to maintain the relative + * node relationship of the pages established between + * threads and memory areas. + * + * However if the number of source nodes is not equal to + * the number of destination nodes we can not preserve + * this node relative relationship. In that case, skip + * copying memory from a node that is in the destination + * mask. + * + * Example: [2,3,4] -> [3,4,5] moves everything. + * [0-7] - > [3,4,5] moves only 0,1,2,6,7. + */ + + if ((nodes_weight(*from) != nodes_weight(*to)) && + (node_isset(s, *to))) + continue; + + d = node_remap(s, *from, *to); + if (s == d) + continue; + + source = s; /* Node moved. Memorize */ + dest = d; + + /* dest not in remaining from nodes? */ + if (!node_isset(dest, tmp)) + break; + } + if (source == NUMA_NO_NODE) + break; + + node_clear(source, tmp); + err = migrate_to_node(mm, source, dest, flags); + if (err > 0) + busy += err; + if (err < 0) + break; + } + mmap_read_unlock(mm); + if (err < 0) + return err; + return busy; + +} + +/* + * Allocate a new page for page migration based on vma policy. + * Start by assuming the page is mapped by the same vma as contains @start. + * Search forward from there, if not. N.B., this assumes that the + * list of pages handed to migrate_pages()--which is how we get here-- + * is in virtual address order. + */ +static struct page *new_page(struct page *page, unsigned long start) +{ + struct vm_area_struct *vma; + unsigned long address; + + vma = find_vma(current->mm, start); + while (vma) { + address = page_address_in_vma(page, vma); + if (address != -EFAULT) + break; + vma = vma->vm_next; + } + + if (PageHuge(page)) { + return alloc_huge_page_vma(page_hstate(compound_head(page)), + vma, address); + } else if (PageTransHuge(page)) { + struct page *thp; + + thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address, + HPAGE_PMD_ORDER); + if (!thp) + return NULL; + prep_transhuge_page(thp); + return thp; + } + /* + * if !vma, alloc_page_vma() will use task or system default policy + */ + return alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL, + vma, address); +} +#else + +static int migrate_page_add(struct page *page, struct list_head *pagelist, + unsigned long flags) +{ + return -EIO; +} + +int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, + const nodemask_t *to, int flags) +{ + return -ENOSYS; +} + +static struct page *new_page(struct page *page, unsigned long start) +{ + return NULL; +} +#endif + +static long do_mbind(unsigned long start, unsigned long len, + unsigned short mode, unsigned short mode_flags, + nodemask_t *nmask, unsigned long flags) +{ + struct mm_struct *mm = current->mm; + struct mempolicy *new; + unsigned long end; + int err; + int ret; + LIST_HEAD(pagelist); + + if (flags & ~(unsigned long)MPOL_MF_VALID) + return -EINVAL; + if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE)) + return -EPERM; + + if (start & ~PAGE_MASK) + return -EINVAL; + + if (mode == MPOL_DEFAULT) + flags &= ~MPOL_MF_STRICT; + + len = (len + PAGE_SIZE - 1) & PAGE_MASK; + end = start + len; + + if (end < start) + return -EINVAL; + if (end == start) + return 0; + + new = mpol_new(mode, mode_flags, nmask); + if (IS_ERR(new)) + return PTR_ERR(new); + + if (flags & MPOL_MF_LAZY) + new->flags |= MPOL_F_MOF; + + /* + * If we are using the default policy then operation + * on discontinuous address spaces is okay after all + */ + if (!new) + flags |= MPOL_MF_DISCONTIG_OK; + + pr_debug("mbind %lx-%lx mode:%d flags:%d nodes:%lx\n", + start, start + len, mode, mode_flags, + nmask ? nodes_addr(*nmask)[0] : NUMA_NO_NODE); + + if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { + + err = migrate_prep(); + if (err) + goto mpol_out; + } + { + NODEMASK_SCRATCH(scratch); + if (scratch) { + mmap_write_lock(mm); + err = mpol_set_nodemask(new, nmask, scratch); + if (err) + mmap_write_unlock(mm); + } else + err = -ENOMEM; + NODEMASK_SCRATCH_FREE(scratch); + } + if (err) + goto mpol_out; + + ret = queue_pages_range(mm, start, end, nmask, + flags | MPOL_MF_INVERT, &pagelist); + + if (ret < 0) { + err = ret; + goto up_out; + } + + err = mbind_range(mm, start, end, new); + + if (!err) { + int nr_failed = 0; + + if (!list_empty(&pagelist)) { + WARN_ON_ONCE(flags & MPOL_MF_LAZY); + nr_failed = migrate_pages(&pagelist, new_page, NULL, + start, MIGRATE_SYNC, MR_MEMPOLICY_MBIND); + if (nr_failed) + putback_movable_pages(&pagelist); + } + + if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT))) + err = -EIO; + } else { +up_out: + if (!list_empty(&pagelist)) + putback_movable_pages(&pagelist); + } + + mmap_write_unlock(mm); +mpol_out: + mpol_put(new); + return err; +} + +/* + * User space interface with variable sized bitmaps for nodelists. + */ + +/* Copy a node mask from user space. */ +static int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask, + unsigned long maxnode) +{ + unsigned long k; + unsigned long t; + unsigned long nlongs; + unsigned long endmask; + + --maxnode; + nodes_clear(*nodes); + if (maxnode == 0 || !nmask) + return 0; + if (maxnode > PAGE_SIZE*BITS_PER_BYTE) + return -EINVAL; + + nlongs = BITS_TO_LONGS(maxnode); + if ((maxnode % BITS_PER_LONG) == 0) + endmask = ~0UL; + else + endmask = (1UL << (maxnode % BITS_PER_LONG)) - 1; + + /* + * When the user specified more nodes than supported just check + * if the non supported part is all zero. + * + * If maxnode have more longs than MAX_NUMNODES, check + * the bits in that area first. And then go through to + * check the rest bits which equal or bigger than MAX_NUMNODES. + * Otherwise, just check bits [MAX_NUMNODES, maxnode). + */ + if (nlongs > BITS_TO_LONGS(MAX_NUMNODES)) { + for (k = BITS_TO_LONGS(MAX_NUMNODES); k < nlongs; k++) { + if (get_user(t, nmask + k)) + return -EFAULT; + if (k == nlongs - 1) { + if (t & endmask) + return -EINVAL; + } else if (t) + return -EINVAL; + } + nlongs = BITS_TO_LONGS(MAX_NUMNODES); + endmask = ~0UL; + } + + if (maxnode > MAX_NUMNODES && MAX_NUMNODES % BITS_PER_LONG != 0) { + unsigned long valid_mask = endmask; + + valid_mask &= ~((1UL << (MAX_NUMNODES % BITS_PER_LONG)) - 1); + if (get_user(t, nmask + nlongs - 1)) + return -EFAULT; + if (t & valid_mask) + return -EINVAL; + } + + if (copy_from_user(nodes_addr(*nodes), nmask, nlongs*sizeof(unsigned long))) + return -EFAULT; + nodes_addr(*nodes)[nlongs-1] &= endmask; + return 0; +} + +/* Copy a kernel node mask to user space */ +static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode, + nodemask_t *nodes) +{ + unsigned long copy = ALIGN(maxnode-1, 64) / 8; + unsigned int nbytes = BITS_TO_LONGS(nr_node_ids) * sizeof(long); + + if (copy > nbytes) { + if (copy > PAGE_SIZE) + return -EINVAL; + if (clear_user((char __user *)mask + nbytes, copy - nbytes)) + return -EFAULT; + copy = nbytes; + } + return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0; +} + +static long kernel_mbind(unsigned long start, unsigned long len, + unsigned long mode, const unsigned long __user *nmask, + unsigned long maxnode, unsigned int flags) +{ + nodemask_t nodes; + int err; + unsigned short mode_flags; + + start = untagged_addr(start); + mode_flags = mode & MPOL_MODE_FLAGS; + mode &= ~MPOL_MODE_FLAGS; + if (mode >= MPOL_MAX) + return -EINVAL; + if ((mode_flags & MPOL_F_STATIC_NODES) && + (mode_flags & MPOL_F_RELATIVE_NODES)) + return -EINVAL; + err = get_nodes(&nodes, nmask, maxnode); + if (err) + return err; + return do_mbind(start, len, mode, mode_flags, &nodes, flags); +} + +SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, + unsigned long, mode, const unsigned long __user *, nmask, + unsigned long, maxnode, unsigned int, flags) +{ + return kernel_mbind(start, len, mode, nmask, maxnode, flags); +} + +/* Set the process memory policy */ +static long kernel_set_mempolicy(int mode, const unsigned long __user *nmask, + unsigned long maxnode) +{ + int err; + nodemask_t nodes; + unsigned short flags; + + flags = mode & MPOL_MODE_FLAGS; + mode &= ~MPOL_MODE_FLAGS; + if ((unsigned int)mode >= MPOL_MAX) + return -EINVAL; + if ((flags & MPOL_F_STATIC_NODES) && (flags & MPOL_F_RELATIVE_NODES)) + return -EINVAL; + err = get_nodes(&nodes, nmask, maxnode); + if (err) + return err; + return do_set_mempolicy(mode, flags, &nodes); +} + +SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask, + unsigned long, maxnode) +{ + return kernel_set_mempolicy(mode, nmask, maxnode); +} + +static int kernel_migrate_pages(pid_t pid, unsigned long maxnode, + const unsigned long __user *old_nodes, + const unsigned long __user *new_nodes) +{ + struct mm_struct *mm = NULL; + struct task_struct *task; + nodemask_t task_nodes; + int err; + nodemask_t *old; + nodemask_t *new; + NODEMASK_SCRATCH(scratch); + + if (!scratch) + return -ENOMEM; + + old = &scratch->mask1; + new = &scratch->mask2; + + err = get_nodes(old, old_nodes, maxnode); + if (err) + goto out; + + err = get_nodes(new, new_nodes, maxnode); + if (err) + goto out; + + /* Find the mm_struct */ + rcu_read_lock(); + task = pid ? find_task_by_vpid(pid) : current; + if (!task) { + rcu_read_unlock(); + err = -ESRCH; + goto out; + } + get_task_struct(task); + + err = -EINVAL; + + /* + * Check if this process has the right to modify the specified process. + * Use the regular "ptrace_may_access()" checks. + */ + if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) { + rcu_read_unlock(); + err = -EPERM; + goto out_put; + } + rcu_read_unlock(); + + task_nodes = cpuset_mems_allowed(task); + /* Is the user allowed to access the target nodes? */ + if (!nodes_subset(*new, task_nodes) && !capable(CAP_SYS_NICE)) { + err = -EPERM; + goto out_put; + } + + task_nodes = cpuset_mems_allowed(current); + nodes_and(*new, *new, task_nodes); + if (nodes_empty(*new)) + goto out_put; + + err = security_task_movememory(task); + if (err) + goto out_put; + + mm = get_task_mm(task); + put_task_struct(task); + + if (!mm) { + err = -EINVAL; + goto out; + } + + err = do_migrate_pages(mm, old, new, + capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE); + + mmput(mm); +out: + NODEMASK_SCRATCH_FREE(scratch); + + return err; + +out_put: + put_task_struct(task); + goto out; + +} + +SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode, + const unsigned long __user *, old_nodes, + const unsigned long __user *, new_nodes) +{ + return kernel_migrate_pages(pid, maxnode, old_nodes, new_nodes); +} + + +/* Retrieve NUMA policy */ +static int kernel_get_mempolicy(int __user *policy, + unsigned long __user *nmask, + unsigned long maxnode, + unsigned long addr, + unsigned long flags) +{ + int err; + int pval; + nodemask_t nodes; + + if (nmask != NULL && maxnode < nr_node_ids) + return -EINVAL; + + addr = untagged_addr(addr); + + err = do_get_mempolicy(&pval, &nodes, addr, flags); + + if (err) + return err; + + if (policy && put_user(pval, policy)) + return -EFAULT; + + if (nmask) + err = copy_nodes_to_user(nmask, maxnode, &nodes); + + return err; +} + +SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, + unsigned long __user *, nmask, unsigned long, maxnode, + unsigned long, addr, unsigned long, flags) +{ + return kernel_get_mempolicy(policy, nmask, maxnode, addr, flags); +} + +#ifdef CONFIG_COMPAT + +COMPAT_SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, + compat_ulong_t __user *, nmask, + compat_ulong_t, maxnode, + compat_ulong_t, addr, compat_ulong_t, flags) +{ + long err; + unsigned long __user *nm = NULL; + unsigned long nr_bits, alloc_size; + DECLARE_BITMAP(bm, MAX_NUMNODES); + + nr_bits = min_t(unsigned long, maxnode-1, nr_node_ids); + alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8; + + if (nmask) + nm = compat_alloc_user_space(alloc_size); + + err = kernel_get_mempolicy(policy, nm, nr_bits+1, addr, flags); + + if (!err && nmask) { + unsigned long copy_size; + copy_size = min_t(unsigned long, sizeof(bm), alloc_size); + err = copy_from_user(bm, nm, copy_size); + /* ensure entire bitmap is zeroed */ + err |= clear_user(nmask, ALIGN(maxnode-1, 8) / 8); + err |= compat_put_bitmap(nmask, bm, nr_bits); + } + + return err; +} + +COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask, + compat_ulong_t, maxnode) +{ + unsigned long __user *nm = NULL; + unsigned long nr_bits, alloc_size; + DECLARE_BITMAP(bm, MAX_NUMNODES); + + nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES); + alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8; + + if (nmask) { + if (compat_get_bitmap(bm, nmask, nr_bits)) + return -EFAULT; + nm = compat_alloc_user_space(alloc_size); + if (copy_to_user(nm, bm, alloc_size)) + return -EFAULT; + } + + return kernel_set_mempolicy(mode, nm, nr_bits+1); +} + +COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len, + compat_ulong_t, mode, compat_ulong_t __user *, nmask, + compat_ulong_t, maxnode, compat_ulong_t, flags) +{ + unsigned long __user *nm = NULL; + unsigned long nr_bits, alloc_size; + nodemask_t bm; + + nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES); + alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8; + + if (nmask) { + if (compat_get_bitmap(nodes_addr(bm), nmask, nr_bits)) + return -EFAULT; + nm = compat_alloc_user_space(alloc_size); + if (copy_to_user(nm, nodes_addr(bm), alloc_size)) + return -EFAULT; + } + + return kernel_mbind(start, len, mode, nm, nr_bits+1, flags); +} + +COMPAT_SYSCALL_DEFINE4(migrate_pages, compat_pid_t, pid, + compat_ulong_t, maxnode, + const compat_ulong_t __user *, old_nodes, + const compat_ulong_t __user *, new_nodes) +{ + unsigned long __user *old = NULL; + unsigned long __user *new = NULL; + nodemask_t tmp_mask; + unsigned long nr_bits; + unsigned long size; + + nr_bits = min_t(unsigned long, maxnode - 1, MAX_NUMNODES); + size = ALIGN(nr_bits, BITS_PER_LONG) / 8; + if (old_nodes) { + if (compat_get_bitmap(nodes_addr(tmp_mask), old_nodes, nr_bits)) + return -EFAULT; + old = compat_alloc_user_space(new_nodes ? size * 2 : size); + if (new_nodes) + new = old + size / sizeof(unsigned long); + if (copy_to_user(old, nodes_addr(tmp_mask), size)) + return -EFAULT; + } + if (new_nodes) { + if (compat_get_bitmap(nodes_addr(tmp_mask), new_nodes, nr_bits)) + return -EFAULT; + if (new == NULL) + new = compat_alloc_user_space(size); + if (copy_to_user(new, nodes_addr(tmp_mask), size)) + return -EFAULT; + } + return kernel_migrate_pages(pid, nr_bits + 1, old, new); +} + +#endif /* CONFIG_COMPAT */ + +bool vma_migratable(struct vm_area_struct *vma) +{ + if (vma->vm_flags & (VM_IO | VM_PFNMAP)) + return false; + + /* + * DAX device mappings require predictable access latency, so avoid + * incurring periodic faults. + */ + if (vma_is_dax(vma)) + return false; + + if (is_vm_hugetlb_page(vma) && + !hugepage_migration_supported(hstate_vma(vma))) + return false; + + /* + * Migration allocates pages in the highest zone. If we cannot + * do so then migration (at least from node to node) is not + * possible. + */ + if (vma->vm_file && + gfp_zone(mapping_gfp_mask(vma->vm_file->f_mapping)) + < policy_zone) + return false; + return true; +} + +struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, + unsigned long addr) +{ + struct mempolicy *pol = NULL; + + if (vma) { + if (vma->vm_ops && vma->vm_ops->get_policy) { + pol = vma->vm_ops->get_policy(vma, addr); + } else if (vma->vm_policy) { + pol = vma->vm_policy; + + /* + * shmem_alloc_page() passes MPOL_F_SHARED policy with + * a pseudo vma whose vma->vm_ops=NULL. Take a reference + * count on these policies which will be dropped by + * mpol_cond_put() later + */ + if (mpol_needs_cond_ref(pol)) + mpol_get(pol); + } + } + + return pol; +} + +/* + * get_vma_policy(@vma, @addr) + * @vma: virtual memory area whose policy is sought + * @addr: address in @vma for shared policy lookup + * + * Returns effective policy for a VMA at specified address. + * Falls back to current->mempolicy or system default policy, as necessary. + * Shared policies [those marked as MPOL_F_SHARED] require an extra reference + * count--added by the get_policy() vm_op, as appropriate--to protect against + * freeing by another task. It is the caller's responsibility to free the + * extra reference for shared policies. + */ +static struct mempolicy *get_vma_policy(struct vm_area_struct *vma, + unsigned long addr) +{ + struct mempolicy *pol = __get_vma_policy(vma, addr); + + if (!pol) + pol = get_task_policy(current); + + return pol; +} + +bool vma_policy_mof(struct vm_area_struct *vma) +{ + struct mempolicy *pol; + + if (vma->vm_ops && vma->vm_ops->get_policy) { + bool ret = false; + + pol = vma->vm_ops->get_policy(vma, vma->vm_start); + if (pol && (pol->flags & MPOL_F_MOF)) + ret = true; + mpol_cond_put(pol); + + return ret; + } + + pol = vma->vm_policy; + if (!pol) + pol = get_task_policy(current); + + return pol->flags & MPOL_F_MOF; +} + +static int apply_policy_zone(struct mempolicy *policy, enum zone_type zone) +{ + enum zone_type dynamic_policy_zone = policy_zone; + + BUG_ON(dynamic_policy_zone == ZONE_MOVABLE); + + /* + * if policy->v.nodes has movable memory only, + * we apply policy when gfp_zone(gfp) = ZONE_MOVABLE only. + * + * policy->v.nodes is intersect with node_states[N_MEMORY]. + * so if the following test faile, it implies + * policy->v.nodes has movable memory only. + */ + if (!nodes_intersects(policy->v.nodes, node_states[N_HIGH_MEMORY])) + dynamic_policy_zone = ZONE_MOVABLE; + + return zone >= dynamic_policy_zone; +} + +/* + * Return a nodemask representing a mempolicy for filtering nodes for + * page allocation + */ +nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy) +{ + /* Lower zones don't get a nodemask applied for MPOL_BIND */ + if (unlikely(policy->mode == MPOL_BIND) && + apply_policy_zone(policy, gfp_zone(gfp)) && + cpuset_nodemask_valid_mems_allowed(&policy->v.nodes)) + return &policy->v.nodes; + + return NULL; +} + +/* Return the node id preferred by the given mempolicy, or the given id */ +static int policy_node(gfp_t gfp, struct mempolicy *policy, int nd) +{ + if (policy->mode == MPOL_PREFERRED && !(policy->flags & MPOL_F_LOCAL)) + nd = policy->v.preferred_node; + else { + /* + * __GFP_THISNODE shouldn't even be used with the bind policy + * because we might easily break the expectation to stay on the + * requested node and not break the policy. + */ + WARN_ON_ONCE(policy->mode == MPOL_BIND && (gfp & __GFP_THISNODE)); + } + + return nd; +} + +/* Do dynamic interleaving for a process */ +static unsigned interleave_nodes(struct mempolicy *policy) +{ + unsigned next; + struct task_struct *me = current; + + next = next_node_in(me->il_prev, policy->v.nodes); + if (next < MAX_NUMNODES) + me->il_prev = next; + return next; +} + +/* + * Depending on the memory policy provide a node from which to allocate the + * next slab entry. + */ +unsigned int mempolicy_slab_node(void) +{ + struct mempolicy *policy; + int node = numa_mem_id(); + + if (in_interrupt()) + return node; + + policy = current->mempolicy; + if (!policy || policy->flags & MPOL_F_LOCAL) + return node; + + switch (policy->mode) { + case MPOL_PREFERRED: + /* + * handled MPOL_F_LOCAL above + */ + return policy->v.preferred_node; + + case MPOL_INTERLEAVE: + return interleave_nodes(policy); + + case MPOL_BIND: { + struct zoneref *z; + + /* + * Follow bind policy behavior and start allocation at the + * first node. + */ + struct zonelist *zonelist; + enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL); + zonelist = &NODE_DATA(node)->node_zonelists[ZONELIST_FALLBACK]; + z = first_zones_zonelist(zonelist, highest_zoneidx, + &policy->v.nodes); + return z->zone ? zone_to_nid(z->zone) : node; + } + + default: + BUG(); + } +} + +/* + * Do static interleaving for a VMA with known offset @n. Returns the n'th + * node in pol->v.nodes (starting from n=0), wrapping around if n exceeds the + * number of present nodes. + */ +static unsigned offset_il_node(struct mempolicy *pol, unsigned long n) +{ + unsigned nnodes = nodes_weight(pol->v.nodes); + unsigned target; + int i; + int nid; + + if (!nnodes) + return numa_node_id(); + target = (unsigned int)n % nnodes; + nid = first_node(pol->v.nodes); + for (i = 0; i < target; i++) + nid = next_node(nid, pol->v.nodes); + return nid; +} + +/* Determine a node number for interleave */ +static inline unsigned interleave_nid(struct mempolicy *pol, + struct vm_area_struct *vma, unsigned long addr, int shift) +{ + if (vma) { + unsigned long off; + + /* + * for small pages, there is no difference between + * shift and PAGE_SHIFT, so the bit-shift is safe. + * for huge pages, since vm_pgoff is in units of small + * pages, we need to shift off the always 0 bits to get + * a useful offset. + */ + BUG_ON(shift < PAGE_SHIFT); + off = vma->vm_pgoff >> (shift - PAGE_SHIFT); + off += (addr - vma->vm_start) >> shift; + return offset_il_node(pol, off); + } else + return interleave_nodes(pol); +} + +#ifdef CONFIG_HUGETLBFS +/* + * huge_node(@vma, @addr, @gfp_flags, @mpol) + * @vma: virtual memory area whose policy is sought + * @addr: address in @vma for shared policy lookup and interleave policy + * @gfp_flags: for requested zone + * @mpol: pointer to mempolicy pointer for reference counted mempolicy + * @nodemask: pointer to nodemask pointer for MPOL_BIND nodemask + * + * Returns a nid suitable for a huge page allocation and a pointer + * to the struct mempolicy for conditional unref after allocation. + * If the effective policy is 'BIND, returns a pointer to the mempolicy's + * @nodemask for filtering the zonelist. + * + * Must be protected by read_mems_allowed_begin() + */ +int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, + struct mempolicy **mpol, nodemask_t **nodemask) +{ + int nid; + + *mpol = get_vma_policy(vma, addr); + *nodemask = NULL; /* assume !MPOL_BIND */ + + if (unlikely((*mpol)->mode == MPOL_INTERLEAVE)) { + nid = interleave_nid(*mpol, vma, addr, + huge_page_shift(hstate_vma(vma))); + } else { + nid = policy_node(gfp_flags, *mpol, numa_node_id()); + if ((*mpol)->mode == MPOL_BIND) + *nodemask = &(*mpol)->v.nodes; + } + return nid; +} + +/* + * init_nodemask_of_mempolicy + * + * If the current task's mempolicy is "default" [NULL], return 'false' + * to indicate default policy. Otherwise, extract the policy nodemask + * for 'bind' or 'interleave' policy into the argument nodemask, or + * initialize the argument nodemask to contain the single node for + * 'preferred' or 'local' policy and return 'true' to indicate presence + * of non-default mempolicy. + * + * We don't bother with reference counting the mempolicy [mpol_get/put] + * because the current task is examining it's own mempolicy and a task's + * mempolicy is only ever changed by the task itself. + * + * N.B., it is the caller's responsibility to free a returned nodemask. + */ +bool init_nodemask_of_mempolicy(nodemask_t *mask) +{ + struct mempolicy *mempolicy; + int nid; + + if (!(mask && current->mempolicy)) + return false; + + task_lock(current); + mempolicy = current->mempolicy; + switch (mempolicy->mode) { + case MPOL_PREFERRED: + if (mempolicy->flags & MPOL_F_LOCAL) + nid = numa_node_id(); + else + nid = mempolicy->v.preferred_node; + init_nodemask_of_node(mask, nid); + break; + + case MPOL_BIND: + case MPOL_INTERLEAVE: + *mask = mempolicy->v.nodes; + break; + + default: + BUG(); + } + task_unlock(current); + + return true; +} +#endif + +/* + * mempolicy_nodemask_intersects + * + * If tsk's mempolicy is "default" [NULL], return 'true' to indicate default + * policy. Otherwise, check for intersection between mask and the policy + * nodemask for 'bind' or 'interleave' policy. For 'perferred' or 'local' + * policy, always return true since it may allocate elsewhere on fallback. + * + * Takes task_lock(tsk) to prevent freeing of its mempolicy. + */ +bool mempolicy_nodemask_intersects(struct task_struct *tsk, + const nodemask_t *mask) +{ + struct mempolicy *mempolicy; + bool ret = true; + + if (!mask) + return ret; + task_lock(tsk); + mempolicy = tsk->mempolicy; + if (!mempolicy) + goto out; + + switch (mempolicy->mode) { + case MPOL_PREFERRED: + /* + * MPOL_PREFERRED and MPOL_F_LOCAL are only preferred nodes to + * allocate from, they may fallback to other nodes when oom. + * Thus, it's possible for tsk to have allocated memory from + * nodes in mask. + */ + break; + case MPOL_BIND: + case MPOL_INTERLEAVE: + ret = nodes_intersects(mempolicy->v.nodes, *mask); + break; + default: + BUG(); + } +out: + task_unlock(tsk); + return ret; +} + +/* Allocate a page in interleaved policy. + Own path because it needs to do special accounting. */ +static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, + unsigned nid) +{ + struct page *page; + + page = __alloc_pages(gfp, order, nid); + /* skip NUMA_INTERLEAVE_HIT counter update if numa stats is disabled */ + if (!static_branch_likely(&vm_numa_stat_key)) + return page; + if (page && page_to_nid(page) == nid) { + preempt_disable(); + __inc_numa_state(page_zone(page), NUMA_INTERLEAVE_HIT); + preempt_enable(); + } + return page; +} + +/** + * alloc_pages_vma - Allocate a page for a VMA. + * + * @gfp: + * %GFP_USER user allocation. + * %GFP_KERNEL kernel allocations, + * %GFP_HIGHMEM highmem/user allocations, + * %GFP_FS allocation should not call back into a file system. + * %GFP_ATOMIC don't sleep. + * + * @order:Order of the GFP allocation. + * @vma: Pointer to VMA or NULL if not available. + * @addr: Virtual Address of the allocation. Must be inside the VMA. + * @node: Which node to prefer for allocation (modulo policy). + * @hugepage: for hugepages try only the preferred node if possible + * + * This function allocates a page from the kernel page pool and applies + * a NUMA policy associated with the VMA or the current process. + * When VMA is not NULL caller must read-lock the mmap_lock of the + * mm_struct of the VMA to prevent it from going away. Should be used for + * all allocations for pages that will be mapped into user space. Returns + * NULL when no page can be allocated. + */ +struct page * +alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, + unsigned long addr, int node, bool hugepage) +{ + struct mempolicy *pol; + struct page *page; + int preferred_nid; + nodemask_t *nmask; + + pol = get_vma_policy(vma, addr); + + if (pol->mode == MPOL_INTERLEAVE) { + unsigned nid; + + nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order); + mpol_cond_put(pol); + page = alloc_page_interleave(gfp, order, nid); + goto out; + } + + if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage)) { + int hpage_node = node; + + /* + * For hugepage allocation and non-interleave policy which + * allows the current node (or other explicitly preferred + * node) we only try to allocate from the current/preferred + * node and don't fall back to other nodes, as the cost of + * remote accesses would likely offset THP benefits. + * + * If the policy is interleave, or does not allow the current + * node in its nodemask, we allocate the standard way. + */ + if (pol->mode == MPOL_PREFERRED && !(pol->flags & MPOL_F_LOCAL)) + hpage_node = pol->v.preferred_node; + + nmask = policy_nodemask(gfp, pol); + if (!nmask || node_isset(hpage_node, *nmask)) { + mpol_cond_put(pol); + /* + * First, try to allocate THP only on local node, but + * don't reclaim unnecessarily, just compact. + */ + page = __alloc_pages_node(hpage_node, + gfp | __GFP_THISNODE | __GFP_NORETRY, order); + + /* + * If hugepage allocations are configured to always + * synchronous compact or the vma has been madvised + * to prefer hugepage backing, retry allowing remote + * memory with both reclaim and compact as well. + */ + if (!page && (gfp & __GFP_DIRECT_RECLAIM)) + page = __alloc_pages_nodemask(gfp, order, + hpage_node, nmask); + + goto out; + } + } + + nmask = policy_nodemask(gfp, pol); + preferred_nid = policy_node(gfp, pol, node); + page = __alloc_pages_nodemask(gfp, order, preferred_nid, nmask); + mpol_cond_put(pol); +out: + return page; +} +EXPORT_SYMBOL(alloc_pages_vma); + +/** + * alloc_pages_current - Allocate pages. + * + * @gfp: + * %GFP_USER user allocation, + * %GFP_KERNEL kernel allocation, + * %GFP_HIGHMEM highmem allocation, + * %GFP_FS don't call back into a file system. + * %GFP_ATOMIC don't sleep. + * @order: Power of two of allocation size in pages. 0 is a single page. + * + * Allocate a page from the kernel page pool. When not in + * interrupt context and apply the current process NUMA policy. + * Returns NULL when no page can be allocated. + */ +struct page *alloc_pages_current(gfp_t gfp, unsigned order) +{ + struct mempolicy *pol = &default_policy; + struct page *page; + + if (!in_interrupt() && !(gfp & __GFP_THISNODE)) + pol = get_task_policy(current); + + /* + * No reference counting needed for current->mempolicy + * nor system default_policy + */ + if (pol->mode == MPOL_INTERLEAVE) + page = alloc_page_interleave(gfp, order, interleave_nodes(pol)); + else + page = __alloc_pages_nodemask(gfp, order, + policy_node(gfp, pol, numa_node_id()), + policy_nodemask(gfp, pol)); + + return page; +} +EXPORT_SYMBOL(alloc_pages_current); + +int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) +{ + struct mempolicy *pol = mpol_dup(vma_policy(src)); + + if (IS_ERR(pol)) + return PTR_ERR(pol); + dst->vm_policy = pol; + return 0; +} + +/* + * If mpol_dup() sees current->cpuset == cpuset_being_rebound, then it + * rebinds the mempolicy its copying by calling mpol_rebind_policy() + * with the mems_allowed returned by cpuset_mems_allowed(). This + * keeps mempolicies cpuset relative after its cpuset moves. See + * further kernel/cpuset.c update_nodemask(). + * + * current's mempolicy may be rebinded by the other task(the task that changes + * cpuset's mems), so we needn't do rebind work for current task. + */ + +/* Slow path of a mempolicy duplicate */ +struct mempolicy *__mpol_dup(struct mempolicy *old) +{ + struct mempolicy *new = kmem_cache_alloc(policy_cache, GFP_KERNEL); + + if (!new) + return ERR_PTR(-ENOMEM); + + /* task's mempolicy is protected by alloc_lock */ + if (old == current->mempolicy) { + task_lock(current); + *new = *old; + task_unlock(current); + } else + *new = *old; + + if (current_cpuset_is_being_rebound()) { + nodemask_t mems = cpuset_mems_allowed(current); + mpol_rebind_policy(new, &mems); + } + atomic_set(&new->refcnt, 1); + return new; +} + +/* Slow path of a mempolicy comparison */ +bool __mpol_equal(struct mempolicy *a, struct mempolicy *b) +{ + if (!a || !b) + return false; + if (a->mode != b->mode) + return false; + if (a->flags != b->flags) + return false; + if (mpol_store_user_nodemask(a)) + if (!nodes_equal(a->w.user_nodemask, b->w.user_nodemask)) + return false; + + switch (a->mode) { + case MPOL_BIND: + case MPOL_INTERLEAVE: + return !!nodes_equal(a->v.nodes, b->v.nodes); + case MPOL_PREFERRED: + /* a's ->flags is the same as b's */ + if (a->flags & MPOL_F_LOCAL) + return true; + return a->v.preferred_node == b->v.preferred_node; + default: + BUG(); + return false; + } +} + +/* + * Shared memory backing store policy support. + * + * Remember policies even when nobody has shared memory mapped. + * The policies are kept in Red-Black tree linked from the inode. + * They are protected by the sp->lock rwlock, which should be held + * for any accesses to the tree. + */ + +/* + * lookup first element intersecting start-end. Caller holds sp->lock for + * reading or for writing + */ +static struct sp_node * +sp_lookup(struct shared_policy *sp, unsigned long start, unsigned long end) +{ + struct rb_node *n = sp->root.rb_node; + + while (n) { + struct sp_node *p = rb_entry(n, struct sp_node, nd); + + if (start >= p->end) + n = n->rb_right; + else if (end <= p->start) + n = n->rb_left; + else + break; + } + if (!n) + return NULL; + for (;;) { + struct sp_node *w = NULL; + struct rb_node *prev = rb_prev(n); + if (!prev) + break; + w = rb_entry(prev, struct sp_node, nd); + if (w->end <= start) + break; + n = prev; + } + return rb_entry(n, struct sp_node, nd); +} + +/* + * Insert a new shared policy into the list. Caller holds sp->lock for + * writing. + */ +static void sp_insert(struct shared_policy *sp, struct sp_node *new) +{ + struct rb_node **p = &sp->root.rb_node; + struct rb_node *parent = NULL; + struct sp_node *nd; + + while (*p) { + parent = *p; + nd = rb_entry(parent, struct sp_node, nd); + if (new->start < nd->start) + p = &(*p)->rb_left; + else if (new->end > nd->end) + p = &(*p)->rb_right; + else + BUG(); + } + rb_link_node(&new->nd, parent, p); + rb_insert_color(&new->nd, &sp->root); + pr_debug("inserting %lx-%lx: %d\n", new->start, new->end, + new->policy ? new->policy->mode : 0); +} + +/* Find shared policy intersecting idx */ +struct mempolicy * +mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx) +{ + struct mempolicy *pol = NULL; + struct sp_node *sn; + + if (!sp->root.rb_node) + return NULL; + read_lock(&sp->lock); + sn = sp_lookup(sp, idx, idx+1); + if (sn) { + mpol_get(sn->policy); + pol = sn->policy; + } + read_unlock(&sp->lock); + return pol; +} + +static void sp_free(struct sp_node *n) +{ + mpol_put(n->policy); + kmem_cache_free(sn_cache, n); +} + +/** + * mpol_misplaced - check whether current page node is valid in policy + * + * @page: page to be checked + * @vma: vm area where page mapped + * @addr: virtual address where page mapped + * + * Lookup current policy node id for vma,addr and "compare to" page's + * node id. + * + * Returns: + * -1 - not misplaced, page is in the right node + * node - node id where the page should be + * + * Policy determination "mimics" alloc_page_vma(). + * Called from fault path where we know the vma and faulting address. + */ +int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long addr) +{ + struct mempolicy *pol; + struct zoneref *z; + int curnid = page_to_nid(page); + unsigned long pgoff; + int thiscpu = raw_smp_processor_id(); + int thisnid = cpu_to_node(thiscpu); + int polnid = NUMA_NO_NODE; + int ret = -1; + + pol = get_vma_policy(vma, addr); + if (!(pol->flags & MPOL_F_MOF)) + goto out; + + switch (pol->mode) { + case MPOL_INTERLEAVE: + pgoff = vma->vm_pgoff; + pgoff += (addr - vma->vm_start) >> PAGE_SHIFT; + polnid = offset_il_node(pol, pgoff); + break; + + case MPOL_PREFERRED: + if (pol->flags & MPOL_F_LOCAL) + polnid = numa_node_id(); + else + polnid = pol->v.preferred_node; + break; + + case MPOL_BIND: + + /* + * allows binding to multiple nodes. + * use current page if in policy nodemask, + * else select nearest allowed node, if any. + * If no allowed nodes, use current [!misplaced]. + */ + if (node_isset(curnid, pol->v.nodes)) + goto out; + z = first_zones_zonelist( + node_zonelist(numa_node_id(), GFP_HIGHUSER), + gfp_zone(GFP_HIGHUSER), + &pol->v.nodes); + polnid = zone_to_nid(z->zone); + break; + + default: + BUG(); + } + + /* Migrate the page towards the node whose CPU is referencing it */ + if (pol->flags & MPOL_F_MORON) { + polnid = thisnid; + + if (!should_numa_migrate_memory(current, page, curnid, thiscpu)) + goto out; + } + + if (curnid != polnid) + ret = polnid; +out: + mpol_cond_put(pol); + + return ret; +} + +/* + * Drop the (possibly final) reference to task->mempolicy. It needs to be + * dropped after task->mempolicy is set to NULL so that any allocation done as + * part of its kmem_cache_free(), such as by KASAN, doesn't reference a freed + * policy. + */ +void mpol_put_task_policy(struct task_struct *task) +{ + struct mempolicy *pol; + + task_lock(task); + pol = task->mempolicy; + task->mempolicy = NULL; + task_unlock(task); + mpol_put(pol); +} + +static void sp_delete(struct shared_policy *sp, struct sp_node *n) +{ + pr_debug("deleting %lx-l%lx\n", n->start, n->end); + rb_erase(&n->nd, &sp->root); + sp_free(n); +} + +static void sp_node_init(struct sp_node *node, unsigned long start, + unsigned long end, struct mempolicy *pol) +{ + node->start = start; + node->end = end; + node->policy = pol; +} + +static struct sp_node *sp_alloc(unsigned long start, unsigned long end, + struct mempolicy *pol) +{ + struct sp_node *n; + struct mempolicy *newpol; + + n = kmem_cache_alloc(sn_cache, GFP_KERNEL); + if (!n) + return NULL; + + newpol = mpol_dup(pol); + if (IS_ERR(newpol)) { + kmem_cache_free(sn_cache, n); + return NULL; + } + newpol->flags |= MPOL_F_SHARED; + sp_node_init(n, start, end, newpol); + + return n; +} + +/* Replace a policy range. */ +static int shared_policy_replace(struct shared_policy *sp, unsigned long start, + unsigned long end, struct sp_node *new) +{ + struct sp_node *n; + struct sp_node *n_new = NULL; + struct mempolicy *mpol_new = NULL; + int ret = 0; + +restart: + write_lock(&sp->lock); + n = sp_lookup(sp, start, end); + /* Take care of old policies in the same range. */ + while (n && n->start < end) { + struct rb_node *next = rb_next(&n->nd); + if (n->start >= start) { + if (n->end <= end) + sp_delete(sp, n); + else + n->start = end; + } else { + /* Old policy spanning whole new range. */ + if (n->end > end) { + if (!n_new) + goto alloc_new; + + *mpol_new = *n->policy; + atomic_set(&mpol_new->refcnt, 1); + sp_node_init(n_new, end, n->end, mpol_new); + n->end = start; + sp_insert(sp, n_new); + n_new = NULL; + mpol_new = NULL; + break; + } else + n->end = start; + } + if (!next) + break; + n = rb_entry(next, struct sp_node, nd); + } + if (new) + sp_insert(sp, new); + write_unlock(&sp->lock); + ret = 0; + +err_out: + if (mpol_new) + mpol_put(mpol_new); + if (n_new) + kmem_cache_free(sn_cache, n_new); + + return ret; + +alloc_new: + write_unlock(&sp->lock); + ret = -ENOMEM; + n_new = kmem_cache_alloc(sn_cache, GFP_KERNEL); + if (!n_new) + goto err_out; + mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL); + if (!mpol_new) + goto err_out; + atomic_set(&mpol_new->refcnt, 1); + goto restart; +} + +/** + * mpol_shared_policy_init - initialize shared policy for inode + * @sp: pointer to inode shared policy + * @mpol: struct mempolicy to install + * + * Install non-NULL @mpol in inode's shared policy rb-tree. + * On entry, the current task has a reference on a non-NULL @mpol. + * This must be released on exit. + * This is called at get_inode() calls and we can use GFP_KERNEL. + */ +void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) +{ + int ret; + + sp->root = RB_ROOT; /* empty tree == default mempolicy */ + rwlock_init(&sp->lock); + + if (mpol) { + struct vm_area_struct pvma; + struct mempolicy *new; + NODEMASK_SCRATCH(scratch); + + if (!scratch) + goto put_mpol; + /* contextualize the tmpfs mount point mempolicy */ + new = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask); + if (IS_ERR(new)) + goto free_scratch; /* no valid nodemask intersection */ + + task_lock(current); + ret = mpol_set_nodemask(new, &mpol->w.user_nodemask, scratch); + task_unlock(current); + if (ret) + goto put_new; + + /* Create pseudo-vma that contains just the policy */ + vma_init(&pvma, NULL); + pvma.vm_end = TASK_SIZE; /* policy covers entire file */ + mpol_set_shared_policy(sp, &pvma, new); /* adds ref */ + +put_new: + mpol_put(new); /* drop initial ref */ +free_scratch: + NODEMASK_SCRATCH_FREE(scratch); +put_mpol: + mpol_put(mpol); /* drop our incoming ref on sb mpol */ + } +} + +int mpol_set_shared_policy(struct shared_policy *info, + struct vm_area_struct *vma, struct mempolicy *npol) +{ + int err; + struct sp_node *new = NULL; + unsigned long sz = vma_pages(vma); + + pr_debug("set_shared_policy %lx sz %lu %d %d %lx\n", + vma->vm_pgoff, + sz, npol ? npol->mode : -1, + npol ? npol->flags : -1, + npol ? nodes_addr(npol->v.nodes)[0] : NUMA_NO_NODE); + + if (npol) { + new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, npol); + if (!new) + return -ENOMEM; + } + err = shared_policy_replace(info, vma->vm_pgoff, vma->vm_pgoff+sz, new); + if (err && new) + sp_free(new); + return err; +} + +/* Free a backing policy store on inode delete. */ +void mpol_free_shared_policy(struct shared_policy *p) +{ + struct sp_node *n; + struct rb_node *next; + + if (!p->root.rb_node) + return; + write_lock(&p->lock); + next = rb_first(&p->root); + while (next) { + n = rb_entry(next, struct sp_node, nd); + next = rb_next(&n->nd); + sp_delete(p, n); + } + write_unlock(&p->lock); +} + +#ifdef CONFIG_NUMA_BALANCING +static int __initdata numabalancing_override; + +static void __init check_numabalancing_enable(void) +{ + bool numabalancing_default = false; + + if (IS_ENABLED(CONFIG_NUMA_BALANCING_DEFAULT_ENABLED)) + numabalancing_default = true; + + /* Parsed by setup_numabalancing. override == 1 enables, -1 disables */ + if (numabalancing_override) + set_numabalancing_state(numabalancing_override == 1); + + if (num_online_nodes() > 1 && !numabalancing_override) { + pr_info("%s automatic NUMA balancing. Configure with numa_balancing= or the kernel.numa_balancing sysctl\n", + numabalancing_default ? "Enabling" : "Disabling"); + set_numabalancing_state(numabalancing_default); + } +} + +static int __init setup_numabalancing(char *str) +{ + int ret = 0; + if (!str) + goto out; + + if (!strcmp(str, "enable")) { + numabalancing_override = 1; + ret = 1; + } else if (!strcmp(str, "disable")) { + numabalancing_override = -1; + ret = 1; + } +out: + if (!ret) + pr_warn("Unable to parse numa_balancing=\n"); + + return ret; +} +__setup("numa_balancing=", setup_numabalancing); +#else +static inline void __init check_numabalancing_enable(void) +{ +} +#endif /* CONFIG_NUMA_BALANCING */ + +/* assumes fs == KERNEL_DS */ +void __init numa_policy_init(void) +{ + nodemask_t interleave_nodes; + unsigned long largest = 0; + int nid, prefer = 0; + + policy_cache = kmem_cache_create("numa_policy", + sizeof(struct mempolicy), + 0, SLAB_PANIC, NULL); + + sn_cache = kmem_cache_create("shared_policy_node", + sizeof(struct sp_node), + 0, SLAB_PANIC, NULL); + + for_each_node(nid) { + preferred_node_policy[nid] = (struct mempolicy) { + .refcnt = ATOMIC_INIT(1), + .mode = MPOL_PREFERRED, + .flags = MPOL_F_MOF | MPOL_F_MORON, + .v = { .preferred_node = nid, }, + }; + } + + /* + * Set interleaving policy for system init. Interleaving is only + * enabled across suitably sized nodes (default is >= 16MB), or + * fall back to the largest node if they're all smaller. + */ + nodes_clear(interleave_nodes); + for_each_node_state(nid, N_MEMORY) { + unsigned long total_pages = node_present_pages(nid); + + /* Preserve the largest node */ + if (largest < total_pages) { + largest = total_pages; + prefer = nid; + } + + /* Interleave this node? */ + if ((total_pages << PAGE_SHIFT) >= (16 << 20)) + node_set(nid, interleave_nodes); + } + + /* All too small, use the largest */ + if (unlikely(nodes_empty(interleave_nodes))) + node_set(prefer, interleave_nodes); + + if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes)) + pr_err("%s: interleaving failed\n", __func__); + + check_numabalancing_enable(); +} + +/* Reset policy of current process to default */ +void numa_default_policy(void) +{ + do_set_mempolicy(MPOL_DEFAULT, 0, NULL); +} + +/* + * Parse and format mempolicy from/to strings + */ + +/* + * "local" is implemented internally by MPOL_PREFERRED with MPOL_F_LOCAL flag. + */ +static const char * const policy_modes[] = +{ + [MPOL_DEFAULT] = "default", + [MPOL_PREFERRED] = "prefer", + [MPOL_BIND] = "bind", + [MPOL_INTERLEAVE] = "interleave", + [MPOL_LOCAL] = "local", +}; + + +#ifdef CONFIG_TMPFS +/** + * mpol_parse_str - parse string to mempolicy, for tmpfs mpol mount option. + * @str: string containing mempolicy to parse + * @mpol: pointer to struct mempolicy pointer, returned on success. + * + * Format of input: + * [=][:] + * + * On success, returns 0, else 1 + */ +int mpol_parse_str(char *str, struct mempolicy **mpol) +{ + struct mempolicy *new = NULL; + unsigned short mode_flags; + nodemask_t nodes; + char *nodelist = strchr(str, ':'); + char *flags = strchr(str, '='); + int err = 1, mode; + + if (flags) + *flags++ = '\0'; /* terminate mode string */ + + if (nodelist) { + /* NUL-terminate mode or flags string */ + *nodelist++ = '\0'; + if (nodelist_parse(nodelist, nodes)) + goto out; + if (!nodes_subset(nodes, node_states[N_MEMORY])) + goto out; + } else + nodes_clear(nodes); + + mode = match_string(policy_modes, MPOL_MAX, str); + if (mode < 0) + goto out; + + switch (mode) { + case MPOL_PREFERRED: + /* + * Insist on a nodelist of one node only, although later + * we use first_node(nodes) to grab a single node, so here + * nodelist (or nodes) cannot be empty. + */ + if (nodelist) { + char *rest = nodelist; + while (isdigit(*rest)) + rest++; + if (*rest) + goto out; + if (nodes_empty(nodes)) + goto out; + } + break; + case MPOL_INTERLEAVE: + /* + * Default to online nodes with memory if no nodelist + */ + if (!nodelist) + nodes = node_states[N_MEMORY]; + break; + case MPOL_LOCAL: + /* + * Don't allow a nodelist; mpol_new() checks flags + */ + if (nodelist) + goto out; + mode = MPOL_PREFERRED; + break; + case MPOL_DEFAULT: + /* + * Insist on a empty nodelist + */ + if (!nodelist) + err = 0; + goto out; + case MPOL_BIND: + /* + * Insist on a nodelist + */ + if (!nodelist) + goto out; + } + + mode_flags = 0; + if (flags) { + /* + * Currently, we only support two mutually exclusive + * mode flags. + */ + if (!strcmp(flags, "static")) + mode_flags |= MPOL_F_STATIC_NODES; + else if (!strcmp(flags, "relative")) + mode_flags |= MPOL_F_RELATIVE_NODES; + else + goto out; + } + + new = mpol_new(mode, mode_flags, &nodes); + if (IS_ERR(new)) + goto out; + + /* + * Save nodes for mpol_to_str() to show the tmpfs mount options + * for /proc/mounts, /proc/pid/mounts and /proc/pid/mountinfo. + */ + if (mode != MPOL_PREFERRED) + new->v.nodes = nodes; + else if (nodelist) + new->v.preferred_node = first_node(nodes); + else + new->flags |= MPOL_F_LOCAL; + + /* + * Save nodes for contextualization: this will be used to "clone" + * the mempolicy in a specific context [cpuset] at a later time. + */ + new->w.user_nodemask = nodes; + + err = 0; + +out: + /* Restore string for error message */ + if (nodelist) + *--nodelist = ':'; + if (flags) + *--flags = '='; + if (!err) + *mpol = new; + return err; +} +#endif /* CONFIG_TMPFS */ + +/** + * mpol_to_str - format a mempolicy structure for printing + * @buffer: to contain formatted mempolicy string + * @maxlen: length of @buffer + * @pol: pointer to mempolicy to be formatted + * + * Convert @pol into a string. If @buffer is too short, truncate the string. + * Recommend a @maxlen of at least 32 for the longest mode, "interleave", the + * longest flag, "relative", and to display at least a few node ids. + */ +void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) +{ + char *p = buffer; + nodemask_t nodes = NODE_MASK_NONE; + unsigned short mode = MPOL_DEFAULT; + unsigned short flags = 0; + + if (pol && pol != &default_policy && !(pol->flags & MPOL_F_MORON)) { + mode = pol->mode; + flags = pol->flags; + } + + switch (mode) { + case MPOL_DEFAULT: + break; + case MPOL_PREFERRED: + if (flags & MPOL_F_LOCAL) + mode = MPOL_LOCAL; + else + node_set(pol->v.preferred_node, nodes); + break; + case MPOL_BIND: + case MPOL_INTERLEAVE: + nodes = pol->v.nodes; + break; + default: + WARN_ON_ONCE(1); + snprintf(p, maxlen, "unknown"); + return; + } + + p += snprintf(p, maxlen, "%s", policy_modes[mode]); + + if (flags & MPOL_MODE_FLAGS) { + p += snprintf(p, buffer + maxlen - p, "="); + + /* + * Currently, the only defined flags are mutually exclusive + */ + if (flags & MPOL_F_STATIC_NODES) + p += snprintf(p, buffer + maxlen - p, "static"); + else if (flags & MPOL_F_RELATIVE_NODES) + p += snprintf(p, buffer + maxlen - p, "relative"); + } + + if (!nodes_empty(nodes)) + p += scnprintf(p, buffer + maxlen - p, ":%*pbl", + nodemask_pr_args(&nodes)); +} diff --git a/mm/mempool.c b/mm/mempool.c new file mode 100644 index 000000000..f473cddda --- /dev/null +++ b/mm/mempool.c @@ -0,0 +1,555 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/mm/mempool.c + * + * memory buffer pool support. Such pools are mostly used + * for guaranteed, deadlock-free memory allocations during + * extreme VM load. + * + * started by Ingo Molnar, Copyright (C) 2001 + * debugging by David Rientjes, Copyright (C) 2015 + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "slab.h" + +#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_SLUB_DEBUG_ON) +static void poison_error(mempool_t *pool, void *element, size_t size, + size_t byte) +{ + const int nr = pool->curr_nr; + const int start = max_t(int, byte - (BITS_PER_LONG / 8), 0); + const int end = min_t(int, byte + (BITS_PER_LONG / 8), size); + int i; + + pr_err("BUG: mempool element poison mismatch\n"); + pr_err("Mempool %p size %zu\n", pool, size); + pr_err(" nr=%d @ %p: %s0x", nr, element, start > 0 ? "... " : ""); + for (i = start; i < end; i++) + pr_cont("%x ", *(u8 *)(element + i)); + pr_cont("%s\n", end < size ? "..." : ""); + dump_stack(); +} + +static void __check_element(mempool_t *pool, void *element, size_t size) +{ + u8 *obj = element; + size_t i; + + for (i = 0; i < size; i++) { + u8 exp = (i < size - 1) ? POISON_FREE : POISON_END; + + if (obj[i] != exp) { + poison_error(pool, element, size, i); + return; + } + } + memset(obj, POISON_INUSE, size); +} + +static void check_element(mempool_t *pool, void *element) +{ + /* Mempools backed by slab allocator */ + if (pool->free == mempool_free_slab || pool->free == mempool_kfree) { + __check_element(pool, element, ksize(element)); + } else if (pool->free == mempool_free_pages) { + /* Mempools backed by page allocator */ + int order = (int)(long)pool->pool_data; + void *addr = kmap_atomic((struct page *)element); + + __check_element(pool, addr, 1UL << (PAGE_SHIFT + order)); + kunmap_atomic(addr); + } +} + +static void __poison_element(void *element, size_t size) +{ + u8 *obj = element; + + memset(obj, POISON_FREE, size - 1); + obj[size - 1] = POISON_END; +} + +static void poison_element(mempool_t *pool, void *element) +{ + /* Mempools backed by slab allocator */ + if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc) { + __poison_element(element, ksize(element)); + } else if (pool->alloc == mempool_alloc_pages) { + /* Mempools backed by page allocator */ + int order = (int)(long)pool->pool_data; + void *addr = kmap_atomic((struct page *)element); + + __poison_element(addr, 1UL << (PAGE_SHIFT + order)); + kunmap_atomic(addr); + } +} +#else /* CONFIG_DEBUG_SLAB || CONFIG_SLUB_DEBUG_ON */ +static inline void check_element(mempool_t *pool, void *element) +{ +} +static inline void poison_element(mempool_t *pool, void *element) +{ +} +#endif /* CONFIG_DEBUG_SLAB || CONFIG_SLUB_DEBUG_ON */ + +static __always_inline void kasan_poison_element(mempool_t *pool, void *element) +{ + if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc) + kasan_poison_kfree(element, _RET_IP_); + else if (pool->alloc == mempool_alloc_pages) + kasan_free_pages(element, (unsigned long)pool->pool_data); +} + +static void kasan_unpoison_element(mempool_t *pool, void *element) +{ + if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc) + kasan_unpoison_slab(element); + else if (pool->alloc == mempool_alloc_pages) + kasan_alloc_pages(element, (unsigned long)pool->pool_data); +} + +static __always_inline void add_element(mempool_t *pool, void *element) +{ + BUG_ON(pool->curr_nr >= pool->min_nr); + poison_element(pool, element); + kasan_poison_element(pool, element); + pool->elements[pool->curr_nr++] = element; +} + +static void *remove_element(mempool_t *pool) +{ + void *element = pool->elements[--pool->curr_nr]; + + BUG_ON(pool->curr_nr < 0); + kasan_unpoison_element(pool, element); + check_element(pool, element); + return element; +} + +/** + * mempool_exit - exit a mempool initialized with mempool_init() + * @pool: pointer to the memory pool which was initialized with + * mempool_init(). + * + * Free all reserved elements in @pool and @pool itself. This function + * only sleeps if the free_fn() function sleeps. + * + * May be called on a zeroed but uninitialized mempool (i.e. allocated with + * kzalloc()). + */ +void mempool_exit(mempool_t *pool) +{ + while (pool->curr_nr) { + void *element = remove_element(pool); + pool->free(element, pool->pool_data); + } + kfree(pool->elements); + pool->elements = NULL; +} +EXPORT_SYMBOL(mempool_exit); + +/** + * mempool_destroy - deallocate a memory pool + * @pool: pointer to the memory pool which was allocated via + * mempool_create(). + * + * Free all reserved elements in @pool and @pool itself. This function + * only sleeps if the free_fn() function sleeps. + */ +void mempool_destroy(mempool_t *pool) +{ + if (unlikely(!pool)) + return; + + mempool_exit(pool); + kfree(pool); +} +EXPORT_SYMBOL(mempool_destroy); + +int mempool_init_node(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn, + mempool_free_t *free_fn, void *pool_data, + gfp_t gfp_mask, int node_id) +{ + spin_lock_init(&pool->lock); + pool->min_nr = min_nr; + pool->pool_data = pool_data; + pool->alloc = alloc_fn; + pool->free = free_fn; + init_waitqueue_head(&pool->wait); + + pool->elements = kmalloc_array_node(min_nr, sizeof(void *), + gfp_mask, node_id); + if (!pool->elements) + return -ENOMEM; + + /* + * First pre-allocate the guaranteed number of buffers. + */ + while (pool->curr_nr < pool->min_nr) { + void *element; + + element = pool->alloc(gfp_mask, pool->pool_data); + if (unlikely(!element)) { + mempool_exit(pool); + return -ENOMEM; + } + add_element(pool, element); + } + + return 0; +} +EXPORT_SYMBOL(mempool_init_node); + +/** + * mempool_init - initialize a memory pool + * @pool: pointer to the memory pool that should be initialized + * @min_nr: the minimum number of elements guaranteed to be + * allocated for this pool. + * @alloc_fn: user-defined element-allocation function. + * @free_fn: user-defined element-freeing function. + * @pool_data: optional private data available to the user-defined functions. + * + * Like mempool_create(), but initializes the pool in (i.e. embedded in another + * structure). + * + * Return: %0 on success, negative error code otherwise. + */ +int mempool_init(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn, + mempool_free_t *free_fn, void *pool_data) +{ + return mempool_init_node(pool, min_nr, alloc_fn, free_fn, + pool_data, GFP_KERNEL, NUMA_NO_NODE); + +} +EXPORT_SYMBOL(mempool_init); + +/** + * mempool_create - create a memory pool + * @min_nr: the minimum number of elements guaranteed to be + * allocated for this pool. + * @alloc_fn: user-defined element-allocation function. + * @free_fn: user-defined element-freeing function. + * @pool_data: optional private data available to the user-defined functions. + * + * this function creates and allocates a guaranteed size, preallocated + * memory pool. The pool can be used from the mempool_alloc() and mempool_free() + * functions. This function might sleep. Both the alloc_fn() and the free_fn() + * functions might sleep - as long as the mempool_alloc() function is not called + * from IRQ contexts. + * + * Return: pointer to the created memory pool object or %NULL on error. + */ +mempool_t *mempool_create(int min_nr, mempool_alloc_t *alloc_fn, + mempool_free_t *free_fn, void *pool_data) +{ + return mempool_create_node(min_nr,alloc_fn,free_fn, pool_data, + GFP_KERNEL, NUMA_NO_NODE); +} +EXPORT_SYMBOL(mempool_create); + +mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn, + mempool_free_t *free_fn, void *pool_data, + gfp_t gfp_mask, int node_id) +{ + mempool_t *pool; + + pool = kzalloc_node(sizeof(*pool), gfp_mask, node_id); + if (!pool) + return NULL; + + if (mempool_init_node(pool, min_nr, alloc_fn, free_fn, pool_data, + gfp_mask, node_id)) { + kfree(pool); + return NULL; + } + + return pool; +} +EXPORT_SYMBOL(mempool_create_node); + +/** + * mempool_resize - resize an existing memory pool + * @pool: pointer to the memory pool which was allocated via + * mempool_create(). + * @new_min_nr: the new minimum number of elements guaranteed to be + * allocated for this pool. + * + * This function shrinks/grows the pool. In the case of growing, + * it cannot be guaranteed that the pool will be grown to the new + * size immediately, but new mempool_free() calls will refill it. + * This function may sleep. + * + * Note, the caller must guarantee that no mempool_destroy is called + * while this function is running. mempool_alloc() & mempool_free() + * might be called (eg. from IRQ contexts) while this function executes. + * + * Return: %0 on success, negative error code otherwise. + */ +int mempool_resize(mempool_t *pool, int new_min_nr) +{ + void *element; + void **new_elements; + unsigned long flags; + + BUG_ON(new_min_nr <= 0); + might_sleep(); + + spin_lock_irqsave(&pool->lock, flags); + if (new_min_nr <= pool->min_nr) { + while (new_min_nr < pool->curr_nr) { + element = remove_element(pool); + spin_unlock_irqrestore(&pool->lock, flags); + pool->free(element, pool->pool_data); + spin_lock_irqsave(&pool->lock, flags); + } + pool->min_nr = new_min_nr; + goto out_unlock; + } + spin_unlock_irqrestore(&pool->lock, flags); + + /* Grow the pool */ + new_elements = kmalloc_array(new_min_nr, sizeof(*new_elements), + GFP_KERNEL); + if (!new_elements) + return -ENOMEM; + + spin_lock_irqsave(&pool->lock, flags); + if (unlikely(new_min_nr <= pool->min_nr)) { + /* Raced, other resize will do our work */ + spin_unlock_irqrestore(&pool->lock, flags); + kfree(new_elements); + goto out; + } + memcpy(new_elements, pool->elements, + pool->curr_nr * sizeof(*new_elements)); + kfree(pool->elements); + pool->elements = new_elements; + pool->min_nr = new_min_nr; + + while (pool->curr_nr < pool->min_nr) { + spin_unlock_irqrestore(&pool->lock, flags); + element = pool->alloc(GFP_KERNEL, pool->pool_data); + if (!element) + goto out; + spin_lock_irqsave(&pool->lock, flags); + if (pool->curr_nr < pool->min_nr) { + add_element(pool, element); + } else { + spin_unlock_irqrestore(&pool->lock, flags); + pool->free(element, pool->pool_data); /* Raced */ + goto out; + } + } +out_unlock: + spin_unlock_irqrestore(&pool->lock, flags); +out: + return 0; +} +EXPORT_SYMBOL(mempool_resize); + +/** + * mempool_alloc - allocate an element from a specific memory pool + * @pool: pointer to the memory pool which was allocated via + * mempool_create(). + * @gfp_mask: the usual allocation bitmask. + * + * this function only sleeps if the alloc_fn() function sleeps or + * returns NULL. Note that due to preallocation, this function + * *never* fails when called from process contexts. (it might + * fail if called from an IRQ context.) + * Note: using __GFP_ZERO is not supported. + * + * Return: pointer to the allocated element or %NULL on error. + */ +void *mempool_alloc(mempool_t *pool, gfp_t gfp_mask) +{ + void *element; + unsigned long flags; + wait_queue_entry_t wait; + gfp_t gfp_temp; + + VM_WARN_ON_ONCE(gfp_mask & __GFP_ZERO); + might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM); + + gfp_mask |= __GFP_NOMEMALLOC; /* don't allocate emergency reserves */ + gfp_mask |= __GFP_NORETRY; /* don't loop in __alloc_pages */ + gfp_mask |= __GFP_NOWARN; /* failures are OK */ + + gfp_temp = gfp_mask & ~(__GFP_DIRECT_RECLAIM|__GFP_IO); + +repeat_alloc: + + element = pool->alloc(gfp_temp, pool->pool_data); + if (likely(element != NULL)) + return element; + + spin_lock_irqsave(&pool->lock, flags); + if (likely(pool->curr_nr)) { + element = remove_element(pool); + spin_unlock_irqrestore(&pool->lock, flags); + /* paired with rmb in mempool_free(), read comment there */ + smp_wmb(); + /* + * Update the allocation stack trace as this is more useful + * for debugging. + */ + kmemleak_update_trace(element); + return element; + } + + /* + * We use gfp mask w/o direct reclaim or IO for the first round. If + * alloc failed with that and @pool was empty, retry immediately. + */ + if (gfp_temp != gfp_mask) { + spin_unlock_irqrestore(&pool->lock, flags); + gfp_temp = gfp_mask; + goto repeat_alloc; + } + + /* We must not sleep if !__GFP_DIRECT_RECLAIM */ + if (!(gfp_mask & __GFP_DIRECT_RECLAIM)) { + spin_unlock_irqrestore(&pool->lock, flags); + return NULL; + } + + /* Let's wait for someone else to return an element to @pool */ + init_wait(&wait); + prepare_to_wait(&pool->wait, &wait, TASK_UNINTERRUPTIBLE); + + spin_unlock_irqrestore(&pool->lock, flags); + + /* + * FIXME: this should be io_schedule(). The timeout is there as a + * workaround for some DM problems in 2.6.18. + */ + io_schedule_timeout(5*HZ); + + finish_wait(&pool->wait, &wait); + goto repeat_alloc; +} +EXPORT_SYMBOL(mempool_alloc); + +/** + * mempool_free - return an element to the pool. + * @element: pool element pointer. + * @pool: pointer to the memory pool which was allocated via + * mempool_create(). + * + * this function only sleeps if the free_fn() function sleeps. + */ +void mempool_free(void *element, mempool_t *pool) +{ + unsigned long flags; + + if (unlikely(element == NULL)) + return; + + /* + * Paired with the wmb in mempool_alloc(). The preceding read is + * for @element and the following @pool->curr_nr. This ensures + * that the visible value of @pool->curr_nr is from after the + * allocation of @element. This is necessary for fringe cases + * where @element was passed to this task without going through + * barriers. + * + * For example, assume @p is %NULL at the beginning and one task + * performs "p = mempool_alloc(...);" while another task is doing + * "while (!p) cpu_relax(); mempool_free(p, ...);". This function + * may end up using curr_nr value which is from before allocation + * of @p without the following rmb. + */ + smp_rmb(); + + /* + * For correctness, we need a test which is guaranteed to trigger + * if curr_nr + #allocated == min_nr. Testing curr_nr < min_nr + * without locking achieves that and refilling as soon as possible + * is desirable. + * + * Because curr_nr visible here is always a value after the + * allocation of @element, any task which decremented curr_nr below + * min_nr is guaranteed to see curr_nr < min_nr unless curr_nr gets + * incremented to min_nr afterwards. If curr_nr gets incremented + * to min_nr after the allocation of @element, the elements + * allocated after that are subject to the same guarantee. + * + * Waiters happen iff curr_nr is 0 and the above guarantee also + * ensures that there will be frees which return elements to the + * pool waking up the waiters. + */ + if (unlikely(READ_ONCE(pool->curr_nr) < pool->min_nr)) { + spin_lock_irqsave(&pool->lock, flags); + if (likely(pool->curr_nr < pool->min_nr)) { + add_element(pool, element); + spin_unlock_irqrestore(&pool->lock, flags); + wake_up(&pool->wait); + return; + } + spin_unlock_irqrestore(&pool->lock, flags); + } + pool->free(element, pool->pool_data); +} +EXPORT_SYMBOL(mempool_free); + +/* + * A commonly used alloc and free fn. + */ +void *mempool_alloc_slab(gfp_t gfp_mask, void *pool_data) +{ + struct kmem_cache *mem = pool_data; + VM_BUG_ON(mem->ctor); + return kmem_cache_alloc(mem, gfp_mask); +} +EXPORT_SYMBOL(mempool_alloc_slab); + +void mempool_free_slab(void *element, void *pool_data) +{ + struct kmem_cache *mem = pool_data; + kmem_cache_free(mem, element); +} +EXPORT_SYMBOL(mempool_free_slab); + +/* + * A commonly used alloc and free fn that kmalloc/kfrees the amount of memory + * specified by pool_data + */ +void *mempool_kmalloc(gfp_t gfp_mask, void *pool_data) +{ + size_t size = (size_t)pool_data; + return kmalloc(size, gfp_mask); +} +EXPORT_SYMBOL(mempool_kmalloc); + +void mempool_kfree(void *element, void *pool_data) +{ + kfree(element); +} +EXPORT_SYMBOL(mempool_kfree); + +/* + * A simple mempool-backed page allocator that allocates pages + * of the order specified by pool_data. + */ +void *mempool_alloc_pages(gfp_t gfp_mask, void *pool_data) +{ + int order = (int)(long)pool_data; + return alloc_pages(gfp_mask, order); +} +EXPORT_SYMBOL(mempool_alloc_pages); + +void mempool_free_pages(void *element, void *pool_data) +{ + int order = (int)(long)pool_data; + __free_pages(element, order); +} +EXPORT_SYMBOL(mempool_free_pages); diff --git a/mm/memremap.c b/mm/memremap.c new file mode 100644 index 000000000..299aad0d2 --- /dev/null +++ b/mm/memremap.c @@ -0,0 +1,532 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2015 Intel Corporation. All rights reserved. */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static DEFINE_XARRAY(pgmap_array); + +/* + * The memremap() and memremap_pages() interfaces are alternately used + * to map persistent memory namespaces. These interfaces place different + * constraints on the alignment and size of the mapping (namespace). + * memremap() can map individual PAGE_SIZE pages. memremap_pages() can + * only map subsections (2MB), and at least one architecture (PowerPC) + * the minimum mapping granularity of memremap_pages() is 16MB. + * + * The role of memremap_compat_align() is to communicate the minimum + * arch supported alignment of a namespace such that it can freely + * switch modes without violating the arch constraint. Namely, do not + * allow a namespace to be PAGE_SIZE aligned since that namespace may be + * reconfigured into a mode that requires SUBSECTION_SIZE alignment. + */ +#ifndef CONFIG_ARCH_HAS_MEMREMAP_COMPAT_ALIGN +unsigned long memremap_compat_align(void) +{ + return SUBSECTION_SIZE; +} +EXPORT_SYMBOL_GPL(memremap_compat_align); +#endif + +#ifdef CONFIG_DEV_PAGEMAP_OPS +DEFINE_STATIC_KEY_FALSE(devmap_managed_key); +EXPORT_SYMBOL(devmap_managed_key); + +static void devmap_managed_enable_put(struct dev_pagemap *pgmap) +{ + if (pgmap->type == MEMORY_DEVICE_PRIVATE || + pgmap->type == MEMORY_DEVICE_FS_DAX) + static_branch_dec(&devmap_managed_key); +} + +static void devmap_managed_enable_get(struct dev_pagemap *pgmap) +{ + if (pgmap->type == MEMORY_DEVICE_PRIVATE || + pgmap->type == MEMORY_DEVICE_FS_DAX) + static_branch_inc(&devmap_managed_key); +} +#else +static void devmap_managed_enable_get(struct dev_pagemap *pgmap) +{ +} +static void devmap_managed_enable_put(struct dev_pagemap *pgmap) +{ +} +#endif /* CONFIG_DEV_PAGEMAP_OPS */ + +static void pgmap_array_delete(struct range *range) +{ + xa_store_range(&pgmap_array, PHYS_PFN(range->start), PHYS_PFN(range->end), + NULL, GFP_KERNEL); + synchronize_rcu(); +} + +static unsigned long pfn_first(struct dev_pagemap *pgmap, int range_id) +{ + struct range *range = &pgmap->ranges[range_id]; + unsigned long pfn = PHYS_PFN(range->start); + + if (range_id) + return pfn; + return pfn + vmem_altmap_offset(pgmap_altmap(pgmap)); +} + +bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn) +{ + int i; + + for (i = 0; i < pgmap->nr_range; i++) { + struct range *range = &pgmap->ranges[i]; + + if (pfn >= PHYS_PFN(range->start) && + pfn <= PHYS_PFN(range->end)) + return pfn >= pfn_first(pgmap, i); + } + + return false; +} + +static unsigned long pfn_end(struct dev_pagemap *pgmap, int range_id) +{ + const struct range *range = &pgmap->ranges[range_id]; + + return (range->start + range_len(range)) >> PAGE_SHIFT; +} + +static unsigned long pfn_next(unsigned long pfn) +{ + if (pfn % 1024 == 0) + cond_resched(); + return pfn + 1; +} + +#define for_each_device_pfn(pfn, map, i) \ + for (pfn = pfn_first(map, i); pfn < pfn_end(map, i); pfn = pfn_next(pfn)) + +static void dev_pagemap_kill(struct dev_pagemap *pgmap) +{ + if (pgmap->ops && pgmap->ops->kill) + pgmap->ops->kill(pgmap); + else + percpu_ref_kill(pgmap->ref); +} + +static void dev_pagemap_cleanup(struct dev_pagemap *pgmap) +{ + if (pgmap->ops && pgmap->ops->cleanup) { + pgmap->ops->cleanup(pgmap); + } else { + wait_for_completion(&pgmap->done); + percpu_ref_exit(pgmap->ref); + } + /* + * Undo the pgmap ref assignment for the internal case as the + * caller may re-enable the same pgmap. + */ + if (pgmap->ref == &pgmap->internal_ref) + pgmap->ref = NULL; +} + +static void pageunmap_range(struct dev_pagemap *pgmap, int range_id) +{ + struct range *range = &pgmap->ranges[range_id]; + struct page *first_page; + int nid; + + /* make sure to access a memmap that was actually initialized */ + first_page = pfn_to_page(pfn_first(pgmap, range_id)); + + /* pages are dead and unused, undo the arch mapping */ + nid = page_to_nid(first_page); + + mem_hotplug_begin(); + remove_pfn_range_from_zone(page_zone(first_page), PHYS_PFN(range->start), + PHYS_PFN(range_len(range))); + if (pgmap->type == MEMORY_DEVICE_PRIVATE) { + __remove_pages(PHYS_PFN(range->start), + PHYS_PFN(range_len(range)), NULL); + } else { + arch_remove_memory(nid, range->start, range_len(range), + pgmap_altmap(pgmap)); + kasan_remove_zero_shadow(__va(range->start), range_len(range)); + } + mem_hotplug_done(); + + untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range)); + pgmap_array_delete(range); +} + +void memunmap_pages(struct dev_pagemap *pgmap) +{ + unsigned long pfn; + int i; + + dev_pagemap_kill(pgmap); + for (i = 0; i < pgmap->nr_range; i++) + for_each_device_pfn(pfn, pgmap, i) + put_page(pfn_to_page(pfn)); + dev_pagemap_cleanup(pgmap); + + for (i = 0; i < pgmap->nr_range; i++) + pageunmap_range(pgmap, i); + + WARN_ONCE(pgmap->altmap.alloc, "failed to free all reserved pages\n"); + devmap_managed_enable_put(pgmap); +} +EXPORT_SYMBOL_GPL(memunmap_pages); + +static void devm_memremap_pages_release(void *data) +{ + memunmap_pages(data); +} + +static void dev_pagemap_percpu_release(struct percpu_ref *ref) +{ + struct dev_pagemap *pgmap = + container_of(ref, struct dev_pagemap, internal_ref); + + complete(&pgmap->done); +} + +static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params, + int range_id, int nid) +{ + struct range *range = &pgmap->ranges[range_id]; + struct dev_pagemap *conflict_pgmap; + int error, is_ram; + + if (WARN_ONCE(pgmap_altmap(pgmap) && range_id > 0, + "altmap not supported for multiple ranges\n")) + return -EINVAL; + + conflict_pgmap = get_dev_pagemap(PHYS_PFN(range->start), NULL); + if (conflict_pgmap) { + WARN(1, "Conflicting mapping in same section\n"); + put_dev_pagemap(conflict_pgmap); + return -ENOMEM; + } + + conflict_pgmap = get_dev_pagemap(PHYS_PFN(range->end), NULL); + if (conflict_pgmap) { + WARN(1, "Conflicting mapping in same section\n"); + put_dev_pagemap(conflict_pgmap); + return -ENOMEM; + } + + is_ram = region_intersects(range->start, range_len(range), + IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE); + + if (is_ram != REGION_DISJOINT) { + WARN_ONCE(1, "attempted on %s region %#llx-%#llx\n", + is_ram == REGION_MIXED ? "mixed" : "ram", + range->start, range->end); + return -ENXIO; + } + + error = xa_err(xa_store_range(&pgmap_array, PHYS_PFN(range->start), + PHYS_PFN(range->end), pgmap, GFP_KERNEL)); + if (error) + return error; + + if (nid < 0) + nid = numa_mem_id(); + + error = track_pfn_remap(NULL, ¶ms->pgprot, PHYS_PFN(range->start), 0, + range_len(range)); + if (error) + goto err_pfn_remap; + + mem_hotplug_begin(); + + /* + * For device private memory we call add_pages() as we only need to + * allocate and initialize struct page for the device memory. More- + * over the device memory is un-accessible thus we do not want to + * create a linear mapping for the memory like arch_add_memory() + * would do. + * + * For all other device memory types, which are accessible by + * the CPU, we do want the linear mapping and thus use + * arch_add_memory(). + */ + if (pgmap->type == MEMORY_DEVICE_PRIVATE) { + error = add_pages(nid, PHYS_PFN(range->start), + PHYS_PFN(range_len(range)), params); + } else { + error = kasan_add_zero_shadow(__va(range->start), range_len(range)); + if (error) { + mem_hotplug_done(); + goto err_kasan; + } + + error = arch_add_memory(nid, range->start, range_len(range), + params); + } + + if (!error) { + struct zone *zone; + + zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE]; + move_pfn_range_to_zone(zone, PHYS_PFN(range->start), + PHYS_PFN(range_len(range)), params->altmap, + MIGRATE_MOVABLE); + } + + mem_hotplug_done(); + if (error) + goto err_add_memory; + + /* + * Initialization of the pages has been deferred until now in order + * to allow us to do the work while not holding the hotplug lock. + */ + memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE], + PHYS_PFN(range->start), + PHYS_PFN(range_len(range)), pgmap); + percpu_ref_get_many(pgmap->ref, pfn_end(pgmap, range_id) + - pfn_first(pgmap, range_id)); + return 0; + +err_add_memory: + kasan_remove_zero_shadow(__va(range->start), range_len(range)); +err_kasan: + untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range)); +err_pfn_remap: + pgmap_array_delete(range); + return error; +} + + +/* + * Not device managed version of dev_memremap_pages, undone by + * memunmap_pages(). Please use dev_memremap_pages if you have a struct + * device available. + */ +void *memremap_pages(struct dev_pagemap *pgmap, int nid) +{ + struct mhp_params params = { + .altmap = pgmap_altmap(pgmap), + .pgprot = PAGE_KERNEL, + }; + const int nr_range = pgmap->nr_range; + int error, i; + + if (WARN_ONCE(!nr_range, "nr_range must be specified\n")) + return ERR_PTR(-EINVAL); + + switch (pgmap->type) { + case MEMORY_DEVICE_PRIVATE: + if (!IS_ENABLED(CONFIG_DEVICE_PRIVATE)) { + WARN(1, "Device private memory not supported\n"); + return ERR_PTR(-EINVAL); + } + if (!pgmap->ops || !pgmap->ops->migrate_to_ram) { + WARN(1, "Missing migrate_to_ram method\n"); + return ERR_PTR(-EINVAL); + } + if (!pgmap->ops->page_free) { + WARN(1, "Missing page_free method\n"); + return ERR_PTR(-EINVAL); + } + if (!pgmap->owner) { + WARN(1, "Missing owner\n"); + return ERR_PTR(-EINVAL); + } + break; + case MEMORY_DEVICE_FS_DAX: + if (!IS_ENABLED(CONFIG_ZONE_DEVICE) || + IS_ENABLED(CONFIG_FS_DAX_LIMITED)) { + WARN(1, "File system DAX not supported\n"); + return ERR_PTR(-EINVAL); + } + params.pgprot = pgprot_decrypted(params.pgprot); + break; + case MEMORY_DEVICE_GENERIC: + break; + case MEMORY_DEVICE_PCI_P2PDMA: + params.pgprot = pgprot_noncached(params.pgprot); + break; + default: + WARN(1, "Invalid pgmap type %d\n", pgmap->type); + break; + } + + if (!pgmap->ref) { + if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup)) + return ERR_PTR(-EINVAL); + + init_completion(&pgmap->done); + error = percpu_ref_init(&pgmap->internal_ref, + dev_pagemap_percpu_release, 0, GFP_KERNEL); + if (error) + return ERR_PTR(error); + pgmap->ref = &pgmap->internal_ref; + } else { + if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) { + WARN(1, "Missing reference count teardown definition\n"); + return ERR_PTR(-EINVAL); + } + } + + devmap_managed_enable_get(pgmap); + + /* + * Clear the pgmap nr_range as it will be incremented for each + * successfully processed range. This communicates how many + * regions to unwind in the abort case. + */ + pgmap->nr_range = 0; + error = 0; + for (i = 0; i < nr_range; i++) { + error = pagemap_range(pgmap, ¶ms, i, nid); + if (error) + break; + pgmap->nr_range++; + } + + if (i < nr_range) { + memunmap_pages(pgmap); + pgmap->nr_range = nr_range; + return ERR_PTR(error); + } + + return __va(pgmap->ranges[0].start); +} +EXPORT_SYMBOL_GPL(memremap_pages); + +/** + * devm_memremap_pages - remap and provide memmap backing for the given resource + * @dev: hosting device for @res + * @pgmap: pointer to a struct dev_pagemap + * + * Notes: + * 1/ At a minimum the res and type members of @pgmap must be initialized + * by the caller before passing it to this function + * + * 2/ The altmap field may optionally be initialized, in which case + * PGMAP_ALTMAP_VALID must be set in pgmap->flags. + * + * 3/ The ref field may optionally be provided, in which pgmap->ref must be + * 'live' on entry and will be killed and reaped at + * devm_memremap_pages_release() time, or if this routine fails. + * + * 4/ range is expected to be a host memory range that could feasibly be + * treated as a "System RAM" range, i.e. not a device mmio range, but + * this is not enforced. + */ +void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) +{ + int error; + void *ret; + + ret = memremap_pages(pgmap, dev_to_node(dev)); + if (IS_ERR(ret)) + return ret; + + error = devm_add_action_or_reset(dev, devm_memremap_pages_release, + pgmap); + if (error) + return ERR_PTR(error); + return ret; +} +EXPORT_SYMBOL_GPL(devm_memremap_pages); + +void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap) +{ + devm_release_action(dev, devm_memremap_pages_release, pgmap); +} +EXPORT_SYMBOL_GPL(devm_memunmap_pages); + +unsigned long vmem_altmap_offset(struct vmem_altmap *altmap) +{ + /* number of pfns from base where pfn_to_page() is valid */ + if (altmap) + return altmap->reserve + altmap->free; + return 0; +} + +void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns) +{ + altmap->alloc -= nr_pfns; +} + +/** + * get_dev_pagemap() - take a new live reference on the dev_pagemap for @pfn + * @pfn: page frame number to lookup page_map + * @pgmap: optional known pgmap that already has a reference + * + * If @pgmap is non-NULL and covers @pfn it will be returned as-is. If @pgmap + * is non-NULL but does not cover @pfn the reference to it will be released. + */ +struct dev_pagemap *get_dev_pagemap(unsigned long pfn, + struct dev_pagemap *pgmap) +{ + resource_size_t phys = PFN_PHYS(pfn); + + /* + * In the cached case we're already holding a live reference. + */ + if (pgmap) { + if (phys >= pgmap->range.start && phys <= pgmap->range.end) + return pgmap; + put_dev_pagemap(pgmap); + } + + /* fall back to slow path lookup */ + rcu_read_lock(); + pgmap = xa_load(&pgmap_array, PHYS_PFN(phys)); + if (pgmap && !percpu_ref_tryget_live(pgmap->ref)) + pgmap = NULL; + rcu_read_unlock(); + + return pgmap; +} +EXPORT_SYMBOL_GPL(get_dev_pagemap); + +#ifdef CONFIG_DEV_PAGEMAP_OPS +void free_devmap_managed_page(struct page *page) +{ + /* notify page idle for dax */ + if (!is_device_private_page(page)) { + wake_up_var(&page->_refcount); + return; + } + + __ClearPageWaiters(page); + + mem_cgroup_uncharge(page); + + /* + * When a device_private page is freed, the page->mapping field + * may still contain a (stale) mapping value. For example, the + * lower bits of page->mapping may still identify the page as an + * anonymous page. Ultimately, this entire field is just stale + * and wrong, and it will cause errors if not cleared. One + * example is: + * + * migrate_vma_pages() + * migrate_vma_insert_page() + * page_add_new_anon_rmap() + * __page_set_anon_rmap() + * ...checks page->mapping, via PageAnon(page) call, + * and incorrectly concludes that the page is an + * anonymous page. Therefore, it incorrectly, + * silently fails to set up the new anon rmap. + * + * For other types of ZONE_DEVICE pages, migration is either + * handled differently or not done at all, so there is no need + * to clear page->mapping. + */ + page->mapping = NULL; + page->pgmap->ops->page_free(page); +} +#endif /* CONFIG_DEV_PAGEMAP_OPS */ diff --git a/mm/memtest.c b/mm/memtest.c new file mode 100644 index 000000000..f53ace709 --- /dev/null +++ b/mm/memtest.c @@ -0,0 +1,113 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include + +static u64 patterns[] __initdata = { + /* The first entry has to be 0 to leave memtest with zeroed memory */ + 0, + 0xffffffffffffffffULL, + 0x5555555555555555ULL, + 0xaaaaaaaaaaaaaaaaULL, + 0x1111111111111111ULL, + 0x2222222222222222ULL, + 0x4444444444444444ULL, + 0x8888888888888888ULL, + 0x3333333333333333ULL, + 0x6666666666666666ULL, + 0x9999999999999999ULL, + 0xccccccccccccccccULL, + 0x7777777777777777ULL, + 0xbbbbbbbbbbbbbbbbULL, + 0xddddddddddddddddULL, + 0xeeeeeeeeeeeeeeeeULL, + 0x7a6c7258554e494cULL, /* yeah ;-) */ +}; + +static void __init reserve_bad_mem(u64 pattern, phys_addr_t start_bad, phys_addr_t end_bad) +{ + pr_info(" %016llx bad mem addr %pa - %pa reserved\n", + cpu_to_be64(pattern), &start_bad, &end_bad); + memblock_reserve(start_bad, end_bad - start_bad); +} + +static void __init memtest(u64 pattern, phys_addr_t start_phys, phys_addr_t size) +{ + u64 *p, *start, *end; + phys_addr_t start_bad, last_bad; + phys_addr_t start_phys_aligned; + const size_t incr = sizeof(pattern); + + start_phys_aligned = ALIGN(start_phys, incr); + start = __va(start_phys_aligned); + end = start + (size - (start_phys_aligned - start_phys)) / incr; + start_bad = 0; + last_bad = 0; + + for (p = start; p < end; p++) + *p = pattern; + + for (p = start; p < end; p++, start_phys_aligned += incr) { + if (*p == pattern) + continue; + if (start_phys_aligned == last_bad + incr) { + last_bad += incr; + continue; + } + if (start_bad) + reserve_bad_mem(pattern, start_bad, last_bad + incr); + start_bad = last_bad = start_phys_aligned; + } + if (start_bad) + reserve_bad_mem(pattern, start_bad, last_bad + incr); +} + +static void __init do_one_pass(u64 pattern, phys_addr_t start, phys_addr_t end) +{ + u64 i; + phys_addr_t this_start, this_end; + + for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &this_start, + &this_end, NULL) { + this_start = clamp(this_start, start, end); + this_end = clamp(this_end, start, end); + if (this_start < this_end) { + pr_info(" %pa - %pa pattern %016llx\n", + &this_start, &this_end, cpu_to_be64(pattern)); + memtest(pattern, this_start, this_end - this_start); + } + } +} + +/* default is disabled */ +static unsigned int memtest_pattern __initdata; + +static int __init parse_memtest(char *arg) +{ + int ret = 0; + + if (arg) + ret = kstrtouint(arg, 0, &memtest_pattern); + else + memtest_pattern = ARRAY_SIZE(patterns); + + return ret; +} + +early_param("memtest", parse_memtest); + +void __init early_memtest(phys_addr_t start, phys_addr_t end) +{ + unsigned int i; + unsigned int idx = 0; + + if (!memtest_pattern) + return; + + pr_info("early_memtest: # of tests: %u\n", memtest_pattern); + for (i = memtest_pattern-1; i < UINT_MAX; --i) { + idx = i % ARRAY_SIZE(patterns); + do_one_pass(patterns[idx], start, end); + } +} diff --git a/mm/migrate.c b/mm/migrate.c new file mode 100644 index 000000000..fcb7eb6a6 --- /dev/null +++ b/mm/migrate.c @@ -0,0 +1,3122 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Memory Migration functionality - linux/mm/migrate.c + * + * Copyright (C) 2006 Silicon Graphics, Inc., Christoph Lameter + * + * Page migration was first developed in the context of the memory hotplug + * project. The main authors of the migration code are: + * + * IWAMOTO Toshihiro + * Hirokazu Takahashi + * Dave Hansen + * Christoph Lameter + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#define CREATE_TRACE_POINTS +#include + +#include "internal.h" + +/* + * migrate_prep() needs to be called before we start compiling a list of pages + * to be migrated using isolate_lru_page(). If scheduling work on other CPUs is + * undesirable, use migrate_prep_local() + */ +int migrate_prep(void) +{ + /* + * Clear the LRU lists so pages can be isolated. + * Note that pages may be moved off the LRU after we have + * drained them. Those pages will fail to migrate like other + * pages that may be busy. + */ + lru_add_drain_all(); + + return 0; +} + +/* Do the necessary work of migrate_prep but not if it involves other CPUs */ +int migrate_prep_local(void) +{ + lru_add_drain(); + + return 0; +} + +int isolate_movable_page(struct page *page, isolate_mode_t mode) +{ + struct address_space *mapping; + + /* + * Avoid burning cycles with pages that are yet under __free_pages(), + * or just got freed under us. + * + * In case we 'win' a race for a movable page being freed under us and + * raise its refcount preventing __free_pages() from doing its job + * the put_page() at the end of this block will take care of + * release this page, thus avoiding a nasty leakage. + */ + if (unlikely(!get_page_unless_zero(page))) + goto out; + + /* + * Check PageMovable before holding a PG_lock because page's owner + * assumes anybody doesn't touch PG_lock of newly allocated page + * so unconditionally grabbing the lock ruins page's owner side. + */ + if (unlikely(!__PageMovable(page))) + goto out_putpage; + /* + * As movable pages are not isolated from LRU lists, concurrent + * compaction threads can race against page migration functions + * as well as race against the releasing a page. + * + * In order to avoid having an already isolated movable page + * being (wrongly) re-isolated while it is under migration, + * or to avoid attempting to isolate pages being released, + * lets be sure we have the page lock + * before proceeding with the movable page isolation steps. + */ + if (unlikely(!trylock_page(page))) + goto out_putpage; + + if (!PageMovable(page) || PageIsolated(page)) + goto out_no_isolated; + + mapping = page_mapping(page); + VM_BUG_ON_PAGE(!mapping, page); + + if (!mapping->a_ops->isolate_page(page, mode)) + goto out_no_isolated; + + /* Driver shouldn't use PG_isolated bit of page->flags */ + WARN_ON_ONCE(PageIsolated(page)); + __SetPageIsolated(page); + unlock_page(page); + + return 0; + +out_no_isolated: + unlock_page(page); +out_putpage: + put_page(page); +out: + return -EBUSY; +} + +/* It should be called on page which is PG_movable */ +void putback_movable_page(struct page *page) +{ + struct address_space *mapping; + + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(!PageMovable(page), page); + VM_BUG_ON_PAGE(!PageIsolated(page), page); + + mapping = page_mapping(page); + mapping->a_ops->putback_page(page); + __ClearPageIsolated(page); +} + +/* + * Put previously isolated pages back onto the appropriate lists + * from where they were once taken off for compaction/migration. + * + * This function shall be used whenever the isolated pageset has been + * built from lru, balloon, hugetlbfs page. See isolate_migratepages_range() + * and isolate_hugetlb(). + */ +void putback_movable_pages(struct list_head *l) +{ + struct page *page; + struct page *page2; + + list_for_each_entry_safe(page, page2, l, lru) { + if (unlikely(PageHuge(page))) { + putback_active_hugepage(page); + continue; + } + list_del(&page->lru); + /* + * We isolated non-lru movable page so here we can use + * __PageMovable because LRU page's mapping cannot have + * PAGE_MAPPING_MOVABLE. + */ + if (unlikely(__PageMovable(page))) { + VM_BUG_ON_PAGE(!PageIsolated(page), page); + lock_page(page); + if (PageMovable(page)) + putback_movable_page(page); + else + __ClearPageIsolated(page); + unlock_page(page); + put_page(page); + } else { + mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + + page_is_file_lru(page), -thp_nr_pages(page)); + putback_lru_page(page); + } + } +} + +/* + * Restore a potential migration pte to a working pte entry + */ +static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma, + unsigned long addr, void *old) +{ + struct page_vma_mapped_walk pvmw = { + .page = old, + .vma = vma, + .address = addr, + .flags = PVMW_SYNC | PVMW_MIGRATION, + }; + struct page *new; + pte_t pte; + swp_entry_t entry; + + VM_BUG_ON_PAGE(PageTail(page), page); + while (page_vma_mapped_walk(&pvmw)) { + if (PageKsm(page)) + new = page; + else + new = page - pvmw.page->index + + linear_page_index(vma, pvmw.address); + +#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION + /* PMD-mapped THP migration entry */ + if (!pvmw.pte) { + VM_BUG_ON_PAGE(PageHuge(page) || !PageTransCompound(page), page); + remove_migration_pmd(&pvmw, new); + continue; + } +#endif + + get_page(new); + pte = pte_mkold(mk_pte(new, READ_ONCE(vma->vm_page_prot))); + if (pte_swp_soft_dirty(*pvmw.pte)) + pte = pte_mksoft_dirty(pte); + + /* + * Recheck VMA as permissions can change since migration started + */ + entry = pte_to_swp_entry(*pvmw.pte); + if (is_write_migration_entry(entry)) + pte = maybe_mkwrite(pte, vma); + else if (pte_swp_uffd_wp(*pvmw.pte)) + pte = pte_mkuffd_wp(pte); + + if (unlikely(is_device_private_page(new))) { + entry = make_device_private_entry(new, pte_write(pte)); + pte = swp_entry_to_pte(entry); + if (pte_swp_soft_dirty(*pvmw.pte)) + pte = pte_swp_mksoft_dirty(pte); + if (pte_swp_uffd_wp(*pvmw.pte)) + pte = pte_swp_mkuffd_wp(pte); + } + +#ifdef CONFIG_HUGETLB_PAGE + if (PageHuge(new)) { + pte = pte_mkhuge(pte); + pte = arch_make_huge_pte(pte, vma, new, 0); + set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte); + if (PageAnon(new)) + hugepage_add_anon_rmap(new, vma, pvmw.address); + else + page_dup_rmap(new, true); + } else +#endif + { + set_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte); + + if (PageAnon(new)) + page_add_anon_rmap(new, vma, pvmw.address, false); + else + page_add_file_rmap(new, false); + } + if (vma->vm_flags & VM_LOCKED && !PageTransCompound(new)) + mlock_vma_page(new); + + if (PageTransHuge(page) && PageMlocked(page)) + clear_page_mlock(page); + + /* No need to invalidate - it was non-present before */ + update_mmu_cache(vma, pvmw.address, pvmw.pte); + } + + return true; +} + +/* + * Get rid of all migration entries and replace them by + * references to the indicated page. + */ +void remove_migration_ptes(struct page *old, struct page *new, bool locked) +{ + struct rmap_walk_control rwc = { + .rmap_one = remove_migration_pte, + .arg = old, + }; + + if (locked) + rmap_walk_locked(new, &rwc); + else + rmap_walk(new, &rwc); +} + +/* + * Something used the pte of a page under migration. We need to + * get to the page and wait until migration is finished. + * When we return from this function the fault will be retried. + */ +void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, + spinlock_t *ptl) +{ + pte_t pte; + swp_entry_t entry; + struct page *page; + + spin_lock(ptl); + pte = *ptep; + if (!is_swap_pte(pte)) + goto out; + + entry = pte_to_swp_entry(pte); + if (!is_migration_entry(entry)) + goto out; + + page = migration_entry_to_page(entry); + page = compound_head(page); + + /* + * Once page cache replacement of page migration started, page_count + * is zero; but we must not call put_and_wait_on_page_locked() without + * a ref. Use get_page_unless_zero(), and just fault again if it fails. + */ + if (!get_page_unless_zero(page)) + goto out; + pte_unmap_unlock(ptep, ptl); + put_and_wait_on_page_locked(page); + return; +out: + pte_unmap_unlock(ptep, ptl); +} + +void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, + unsigned long address) +{ + spinlock_t *ptl = pte_lockptr(mm, pmd); + pte_t *ptep = pte_offset_map(pmd, address); + __migration_entry_wait(mm, ptep, ptl); +} + +void migration_entry_wait_huge(struct vm_area_struct *vma, + struct mm_struct *mm, pte_t *pte) +{ + spinlock_t *ptl = huge_pte_lockptr(hstate_vma(vma), mm, pte); + __migration_entry_wait(mm, pte, ptl); +} + +#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION +void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd) +{ + spinlock_t *ptl; + struct page *page; + + ptl = pmd_lock(mm, pmd); + if (!is_pmd_migration_entry(*pmd)) + goto unlock; + page = migration_entry_to_page(pmd_to_swp_entry(*pmd)); + if (!get_page_unless_zero(page)) + goto unlock; + spin_unlock(ptl); + put_and_wait_on_page_locked(page); + return; +unlock: + spin_unlock(ptl); +} +#endif + +static int expected_page_refs(struct address_space *mapping, struct page *page) +{ + int expected_count = 1; + + /* + * Device private pages have an extra refcount as they are + * ZONE_DEVICE pages. + */ + expected_count += is_device_private_page(page); + if (mapping) + expected_count += thp_nr_pages(page) + page_has_private(page); + + return expected_count; +} + +/* + * Replace the page in the mapping. + * + * The number of remaining references must be: + * 1 for anonymous pages without a mapping + * 2 for pages with a mapping + * 3 for pages with a mapping and PagePrivate/PagePrivate2 set. + */ +int migrate_page_move_mapping(struct address_space *mapping, + struct page *newpage, struct page *page, int extra_count) +{ + XA_STATE(xas, &mapping->i_pages, page_index(page)); + struct zone *oldzone, *newzone; + int dirty; + int expected_count = expected_page_refs(mapping, page) + extra_count; + int nr = thp_nr_pages(page); + + if (!mapping) { + /* Anonymous page without mapping */ + if (page_count(page) != expected_count) + return -EAGAIN; + + /* No turning back from here */ + newpage->index = page->index; + newpage->mapping = page->mapping; + if (PageSwapBacked(page)) + __SetPageSwapBacked(newpage); + + return MIGRATEPAGE_SUCCESS; + } + + oldzone = page_zone(page); + newzone = page_zone(newpage); + + xas_lock_irq(&xas); + if (page_count(page) != expected_count || xas_load(&xas) != page) { + xas_unlock_irq(&xas); + return -EAGAIN; + } + + if (!page_ref_freeze(page, expected_count)) { + xas_unlock_irq(&xas); + return -EAGAIN; + } + + /* + * Now we know that no one else is looking at the page: + * no turning back from here. + */ + newpage->index = page->index; + newpage->mapping = page->mapping; + page_ref_add(newpage, nr); /* add cache reference */ + if (PageSwapBacked(page)) { + __SetPageSwapBacked(newpage); + if (PageSwapCache(page)) { + SetPageSwapCache(newpage); + set_page_private(newpage, page_private(page)); + } + } else { + VM_BUG_ON_PAGE(PageSwapCache(page), page); + } + + /* Move dirty while page refs frozen and newpage not yet exposed */ + dirty = PageDirty(page); + if (dirty) { + ClearPageDirty(page); + SetPageDirty(newpage); + } + + xas_store(&xas, newpage); + if (PageTransHuge(page)) { + int i; + + for (i = 1; i < nr; i++) { + xas_next(&xas); + xas_store(&xas, newpage); + } + } + + /* + * Drop cache reference from old page by unfreezing + * to one less reference. + * We know this isn't the last reference. + */ + page_ref_unfreeze(page, expected_count - nr); + + xas_unlock(&xas); + /* Leave irq disabled to prevent preemption while updating stats */ + + /* + * If moved to a different zone then also account + * the page for that zone. Other VM counters will be + * taken care of when we establish references to the + * new page and drop references to the old page. + * + * Note that anonymous pages are accounted for + * via NR_FILE_PAGES and NR_ANON_MAPPED if they + * are mapped to swap space. + */ + if (newzone != oldzone) { + struct lruvec *old_lruvec, *new_lruvec; + struct mem_cgroup *memcg; + + memcg = page_memcg(page); + old_lruvec = mem_cgroup_lruvec(memcg, oldzone->zone_pgdat); + new_lruvec = mem_cgroup_lruvec(memcg, newzone->zone_pgdat); + + __mod_lruvec_state(old_lruvec, NR_FILE_PAGES, -nr); + __mod_lruvec_state(new_lruvec, NR_FILE_PAGES, nr); + if (PageSwapBacked(page) && !PageSwapCache(page)) { + __mod_lruvec_state(old_lruvec, NR_SHMEM, -nr); + __mod_lruvec_state(new_lruvec, NR_SHMEM, nr); + } + if (dirty && mapping_can_writeback(mapping)) { + __mod_lruvec_state(old_lruvec, NR_FILE_DIRTY, -nr); + __mod_zone_page_state(oldzone, NR_ZONE_WRITE_PENDING, -nr); + __mod_lruvec_state(new_lruvec, NR_FILE_DIRTY, nr); + __mod_zone_page_state(newzone, NR_ZONE_WRITE_PENDING, nr); + } + } + local_irq_enable(); + + return MIGRATEPAGE_SUCCESS; +} +EXPORT_SYMBOL(migrate_page_move_mapping); + +/* + * The expected number of remaining references is the same as that + * of migrate_page_move_mapping(). + */ +int migrate_huge_page_move_mapping(struct address_space *mapping, + struct page *newpage, struct page *page) +{ + XA_STATE(xas, &mapping->i_pages, page_index(page)); + int expected_count; + + xas_lock_irq(&xas); + expected_count = 2 + page_has_private(page); + if (page_count(page) != expected_count || xas_load(&xas) != page) { + xas_unlock_irq(&xas); + return -EAGAIN; + } + + if (!page_ref_freeze(page, expected_count)) { + xas_unlock_irq(&xas); + return -EAGAIN; + } + + newpage->index = page->index; + newpage->mapping = page->mapping; + + get_page(newpage); + + xas_store(&xas, newpage); + + page_ref_unfreeze(page, expected_count - 1); + + xas_unlock_irq(&xas); + + return MIGRATEPAGE_SUCCESS; +} + +/* + * Gigantic pages are so large that we do not guarantee that page++ pointer + * arithmetic will work across the entire page. We need something more + * specialized. + */ +static void __copy_gigantic_page(struct page *dst, struct page *src, + int nr_pages) +{ + int i; + struct page *dst_base = dst; + struct page *src_base = src; + + for (i = 0; i < nr_pages; ) { + cond_resched(); + copy_highpage(dst, src); + + i++; + dst = mem_map_next(dst, dst_base, i); + src = mem_map_next(src, src_base, i); + } +} + +static void copy_huge_page(struct page *dst, struct page *src) +{ + int i; + int nr_pages; + + if (PageHuge(src)) { + /* hugetlbfs page */ + struct hstate *h = page_hstate(src); + nr_pages = pages_per_huge_page(h); + + if (unlikely(nr_pages > MAX_ORDER_NR_PAGES)) { + __copy_gigantic_page(dst, src, nr_pages); + return; + } + } else { + /* thp page */ + BUG_ON(!PageTransHuge(src)); + nr_pages = thp_nr_pages(src); + } + + for (i = 0; i < nr_pages; i++) { + cond_resched(); + copy_highpage(dst + i, src + i); + } +} + +/* + * Copy the page to its new location + */ +void migrate_page_states(struct page *newpage, struct page *page) +{ + int cpupid; + + if (PageError(page)) + SetPageError(newpage); + if (PageReferenced(page)) + SetPageReferenced(newpage); + if (PageUptodate(page)) + SetPageUptodate(newpage); + if (TestClearPageActive(page)) { + VM_BUG_ON_PAGE(PageUnevictable(page), page); + SetPageActive(newpage); + } else if (TestClearPageUnevictable(page)) + SetPageUnevictable(newpage); + if (PageWorkingset(page)) + SetPageWorkingset(newpage); + if (PageChecked(page)) + SetPageChecked(newpage); + if (PageMappedToDisk(page)) + SetPageMappedToDisk(newpage); + + /* Move dirty on pages not done by migrate_page_move_mapping() */ + if (PageDirty(page)) + SetPageDirty(newpage); + + if (page_is_young(page)) + set_page_young(newpage); + if (page_is_idle(page)) + set_page_idle(newpage); + + /* + * Copy NUMA information to the new page, to prevent over-eager + * future migrations of this same page. + */ + cpupid = page_cpupid_xchg_last(page, -1); + page_cpupid_xchg_last(newpage, cpupid); + + ksm_migrate_page(newpage, page); + /* + * Please do not reorder this without considering how mm/ksm.c's + * get_ksm_page() depends upon ksm_migrate_page() and PageSwapCache(). + */ + if (PageSwapCache(page)) + ClearPageSwapCache(page); + ClearPagePrivate(page); + set_page_private(page, 0); + + /* + * If any waiters have accumulated on the new page then + * wake them up. + */ + if (PageWriteback(newpage)) + end_page_writeback(newpage); + + /* + * PG_readahead shares the same bit with PG_reclaim. The above + * end_page_writeback() may clear PG_readahead mistakenly, so set the + * bit after that. + */ + if (PageReadahead(page)) + SetPageReadahead(newpage); + + copy_page_owner(page, newpage); + + if (!PageHuge(page)) + mem_cgroup_migrate(page, newpage); +} +EXPORT_SYMBOL(migrate_page_states); + +void migrate_page_copy(struct page *newpage, struct page *page) +{ + if (PageHuge(page) || PageTransHuge(page)) + copy_huge_page(newpage, page); + else + copy_highpage(newpage, page); + + migrate_page_states(newpage, page); +} +EXPORT_SYMBOL(migrate_page_copy); + +/************************************************************ + * Migration functions + ***********************************************************/ + +/* + * Common logic to directly migrate a single LRU page suitable for + * pages that do not use PagePrivate/PagePrivate2. + * + * Pages are locked upon entry and exit. + */ +int migrate_page(struct address_space *mapping, + struct page *newpage, struct page *page, + enum migrate_mode mode) +{ + int rc; + + BUG_ON(PageWriteback(page)); /* Writeback must be complete */ + + rc = migrate_page_move_mapping(mapping, newpage, page, 0); + + if (rc != MIGRATEPAGE_SUCCESS) + return rc; + + if (mode != MIGRATE_SYNC_NO_COPY) + migrate_page_copy(newpage, page); + else + migrate_page_states(newpage, page); + return MIGRATEPAGE_SUCCESS; +} +EXPORT_SYMBOL(migrate_page); + +#ifdef CONFIG_BLOCK +/* Returns true if all buffers are successfully locked */ +static bool buffer_migrate_lock_buffers(struct buffer_head *head, + enum migrate_mode mode) +{ + struct buffer_head *bh = head; + + /* Simple case, sync compaction */ + if (mode != MIGRATE_ASYNC) { + do { + lock_buffer(bh); + bh = bh->b_this_page; + + } while (bh != head); + + return true; + } + + /* async case, we cannot block on lock_buffer so use trylock_buffer */ + do { + if (!trylock_buffer(bh)) { + /* + * We failed to lock the buffer and cannot stall in + * async migration. Release the taken locks + */ + struct buffer_head *failed_bh = bh; + bh = head; + while (bh != failed_bh) { + unlock_buffer(bh); + bh = bh->b_this_page; + } + return false; + } + + bh = bh->b_this_page; + } while (bh != head); + return true; +} + +static int __buffer_migrate_page(struct address_space *mapping, + struct page *newpage, struct page *page, enum migrate_mode mode, + bool check_refs) +{ + struct buffer_head *bh, *head; + int rc; + int expected_count; + + if (!page_has_buffers(page)) + return migrate_page(mapping, newpage, page, mode); + + /* Check whether page does not have extra refs before we do more work */ + expected_count = expected_page_refs(mapping, page); + if (page_count(page) != expected_count) + return -EAGAIN; + + head = page_buffers(page); + if (!buffer_migrate_lock_buffers(head, mode)) + return -EAGAIN; + + if (check_refs) { + bool busy; + bool invalidated = false; + +recheck_buffers: + busy = false; + spin_lock(&mapping->private_lock); + bh = head; + do { + if (atomic_read(&bh->b_count)) { + busy = true; + break; + } + bh = bh->b_this_page; + } while (bh != head); + if (busy) { + if (invalidated) { + rc = -EAGAIN; + goto unlock_buffers; + } + spin_unlock(&mapping->private_lock); + invalidate_bh_lrus(); + invalidated = true; + goto recheck_buffers; + } + } + + rc = migrate_page_move_mapping(mapping, newpage, page, 0); + if (rc != MIGRATEPAGE_SUCCESS) + goto unlock_buffers; + + attach_page_private(newpage, detach_page_private(page)); + + bh = head; + do { + set_bh_page(bh, newpage, bh_offset(bh)); + bh = bh->b_this_page; + + } while (bh != head); + + if (mode != MIGRATE_SYNC_NO_COPY) + migrate_page_copy(newpage, page); + else + migrate_page_states(newpage, page); + + rc = MIGRATEPAGE_SUCCESS; +unlock_buffers: + if (check_refs) + spin_unlock(&mapping->private_lock); + bh = head; + do { + unlock_buffer(bh); + bh = bh->b_this_page; + + } while (bh != head); + + return rc; +} + +/* + * Migration function for pages with buffers. This function can only be used + * if the underlying filesystem guarantees that no other references to "page" + * exist. For example attached buffer heads are accessed only under page lock. + */ +int buffer_migrate_page(struct address_space *mapping, + struct page *newpage, struct page *page, enum migrate_mode mode) +{ + return __buffer_migrate_page(mapping, newpage, page, mode, false); +} +EXPORT_SYMBOL(buffer_migrate_page); + +/* + * Same as above except that this variant is more careful and checks that there + * are also no buffer head references. This function is the right one for + * mappings where buffer heads are directly looked up and referenced (such as + * block device mappings). + */ +int buffer_migrate_page_norefs(struct address_space *mapping, + struct page *newpage, struct page *page, enum migrate_mode mode) +{ + return __buffer_migrate_page(mapping, newpage, page, mode, true); +} +#endif + +/* + * Writeback a page to clean the dirty state + */ +static int writeout(struct address_space *mapping, struct page *page) +{ + struct writeback_control wbc = { + .sync_mode = WB_SYNC_NONE, + .nr_to_write = 1, + .range_start = 0, + .range_end = LLONG_MAX, + .for_reclaim = 1 + }; + int rc; + + if (!mapping->a_ops->writepage) + /* No write method for the address space */ + return -EINVAL; + + if (!clear_page_dirty_for_io(page)) + /* Someone else already triggered a write */ + return -EAGAIN; + + /* + * A dirty page may imply that the underlying filesystem has + * the page on some queue. So the page must be clean for + * migration. Writeout may mean we loose the lock and the + * page state is no longer what we checked for earlier. + * At this point we know that the migration attempt cannot + * be successful. + */ + remove_migration_ptes(page, page, false); + + rc = mapping->a_ops->writepage(page, &wbc); + + if (rc != AOP_WRITEPAGE_ACTIVATE) + /* unlocked. Relock */ + lock_page(page); + + return (rc < 0) ? -EIO : -EAGAIN; +} + +/* + * Default handling if a filesystem does not provide a migration function. + */ +static int fallback_migrate_page(struct address_space *mapping, + struct page *newpage, struct page *page, enum migrate_mode mode) +{ + if (PageDirty(page)) { + /* Only writeback pages in full synchronous migration */ + switch (mode) { + case MIGRATE_SYNC: + case MIGRATE_SYNC_NO_COPY: + break; + default: + return -EBUSY; + } + return writeout(mapping, page); + } + + /* + * Buffers may be managed in a filesystem specific way. + * We must have no buffers or drop them. + */ + if (page_has_private(page) && + !try_to_release_page(page, GFP_KERNEL)) + return mode == MIGRATE_SYNC ? -EAGAIN : -EBUSY; + + return migrate_page(mapping, newpage, page, mode); +} + +/* + * Move a page to a newly allocated page + * The page is locked and all ptes have been successfully removed. + * + * The new page will have replaced the old page if this function + * is successful. + * + * Return value: + * < 0 - error code + * MIGRATEPAGE_SUCCESS - success + */ +static int move_to_new_page(struct page *newpage, struct page *page, + enum migrate_mode mode) +{ + struct address_space *mapping; + int rc = -EAGAIN; + bool is_lru = !__PageMovable(page); + + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(!PageLocked(newpage), newpage); + + mapping = page_mapping(page); + + if (likely(is_lru)) { + if (!mapping) + rc = migrate_page(mapping, newpage, page, mode); + else if (mapping->a_ops->migratepage) + /* + * Most pages have a mapping and most filesystems + * provide a migratepage callback. Anonymous pages + * are part of swap space which also has its own + * migratepage callback. This is the most common path + * for page migration. + */ + rc = mapping->a_ops->migratepage(mapping, newpage, + page, mode); + else + rc = fallback_migrate_page(mapping, newpage, + page, mode); + } else { + /* + * In case of non-lru page, it could be released after + * isolation step. In that case, we shouldn't try migration. + */ + VM_BUG_ON_PAGE(!PageIsolated(page), page); + if (!PageMovable(page)) { + rc = MIGRATEPAGE_SUCCESS; + __ClearPageIsolated(page); + goto out; + } + + rc = mapping->a_ops->migratepage(mapping, newpage, + page, mode); + WARN_ON_ONCE(rc == MIGRATEPAGE_SUCCESS && + !PageIsolated(page)); + } + + /* + * When successful, old pagecache page->mapping must be cleared before + * page is freed; but stats require that PageAnon be left as PageAnon. + */ + if (rc == MIGRATEPAGE_SUCCESS) { + if (__PageMovable(page)) { + VM_BUG_ON_PAGE(!PageIsolated(page), page); + + /* + * We clear PG_movable under page_lock so any compactor + * cannot try to migrate this page. + */ + __ClearPageIsolated(page); + } + + /* + * Anonymous and movable page->mapping will be cleared by + * free_pages_prepare so don't reset it here for keeping + * the type to work PageAnon, for example. + */ + if (!PageMappingFlags(page)) + page->mapping = NULL; + + if (likely(!is_zone_device_page(newpage))) { + int i, nr = compound_nr(newpage); + + for (i = 0; i < nr; i++) + flush_dcache_page(newpage + i); + } + } +out: + return rc; +} + +static int __unmap_and_move(struct page *page, struct page *newpage, + int force, enum migrate_mode mode) +{ + int rc = -EAGAIN; + int page_was_mapped = 0; + struct anon_vma *anon_vma = NULL; + bool is_lru = !__PageMovable(page); + + if (!trylock_page(page)) { + if (!force || mode == MIGRATE_ASYNC) + goto out; + + /* + * It's not safe for direct compaction to call lock_page. + * For example, during page readahead pages are added locked + * to the LRU. Later, when the IO completes the pages are + * marked uptodate and unlocked. However, the queueing + * could be merging multiple pages for one bio (e.g. + * mpage_readahead). If an allocation happens for the + * second or third page, the process can end up locking + * the same page twice and deadlocking. Rather than + * trying to be clever about what pages can be locked, + * avoid the use of lock_page for direct compaction + * altogether. + */ + if (current->flags & PF_MEMALLOC) + goto out; + + lock_page(page); + } + + if (PageWriteback(page)) { + /* + * Only in the case of a full synchronous migration is it + * necessary to wait for PageWriteback. In the async case, + * the retry loop is too short and in the sync-light case, + * the overhead of stalling is too much + */ + switch (mode) { + case MIGRATE_SYNC: + case MIGRATE_SYNC_NO_COPY: + break; + default: + rc = -EBUSY; + goto out_unlock; + } + if (!force) + goto out_unlock; + wait_on_page_writeback(page); + } + + /* + * By try_to_unmap(), page->mapcount goes down to 0 here. In this case, + * we cannot notice that anon_vma is freed while we migrates a page. + * This get_anon_vma() delays freeing anon_vma pointer until the end + * of migration. File cache pages are no problem because of page_lock() + * File Caches may use write_page() or lock_page() in migration, then, + * just care Anon page here. + * + * Only page_get_anon_vma() understands the subtleties of + * getting a hold on an anon_vma from outside one of its mms. + * But if we cannot get anon_vma, then we won't need it anyway, + * because that implies that the anon page is no longer mapped + * (and cannot be remapped so long as we hold the page lock). + */ + if (PageAnon(page) && !PageKsm(page)) + anon_vma = page_get_anon_vma(page); + + /* + * Block others from accessing the new page when we get around to + * establishing additional references. We are usually the only one + * holding a reference to newpage at this point. We used to have a BUG + * here if trylock_page(newpage) fails, but would like to allow for + * cases where there might be a race with the previous use of newpage. + * This is much like races on refcount of oldpage: just don't BUG(). + */ + if (unlikely(!trylock_page(newpage))) + goto out_unlock; + + if (unlikely(!is_lru)) { + rc = move_to_new_page(newpage, page, mode); + goto out_unlock_both; + } + + /* + * Corner case handling: + * 1. When a new swap-cache page is read into, it is added to the LRU + * and treated as swapcache but it has no rmap yet. + * Calling try_to_unmap() against a page->mapping==NULL page will + * trigger a BUG. So handle it here. + * 2. An orphaned page (see truncate_complete_page) might have + * fs-private metadata. The page can be picked up due to memory + * offlining. Everywhere else except page reclaim, the page is + * invisible to the vm, so the page can not be migrated. So try to + * free the metadata, so the page can be freed. + */ + if (!page->mapping) { + VM_BUG_ON_PAGE(PageAnon(page), page); + if (page_has_private(page)) { + try_to_free_buffers(page); + goto out_unlock_both; + } + } else if (page_mapped(page)) { + /* Establish migration ptes */ + VM_BUG_ON_PAGE(PageAnon(page) && !PageKsm(page) && !anon_vma, + page); + try_to_unmap(page, TTU_MIGRATION|TTU_IGNORE_MLOCK); + page_was_mapped = 1; + } + + if (!page_mapped(page)) + rc = move_to_new_page(newpage, page, mode); + + if (page_was_mapped) + remove_migration_ptes(page, + rc == MIGRATEPAGE_SUCCESS ? newpage : page, false); + +out_unlock_both: + unlock_page(newpage); +out_unlock: + /* Drop an anon_vma reference if we took one */ + if (anon_vma) + put_anon_vma(anon_vma); + unlock_page(page); +out: + /* + * If migration is successful, decrease refcount of the newpage + * which will not free the page because new page owner increased + * refcounter. As well, if it is LRU page, add the page to LRU + * list in here. Use the old state of the isolated source page to + * determine if we migrated a LRU page. newpage was already unlocked + * and possibly modified by its owner - don't rely on the page + * state. + */ + if (rc == MIGRATEPAGE_SUCCESS) { + if (unlikely(!is_lru)) + put_page(newpage); + else + putback_lru_page(newpage); + } + + return rc; +} + +/* + * Obtain the lock on page, remove all ptes and migrate the page + * to the newly allocated page in newpage. + */ +static int unmap_and_move(new_page_t get_new_page, + free_page_t put_new_page, + unsigned long private, struct page *page, + int force, enum migrate_mode mode, + enum migrate_reason reason) +{ + int rc = MIGRATEPAGE_SUCCESS; + struct page *newpage = NULL; + + if (!thp_migration_supported() && PageTransHuge(page)) + return -ENOMEM; + + if (page_count(page) == 1) { + /* page was freed from under us. So we are done. */ + ClearPageActive(page); + ClearPageUnevictable(page); + if (unlikely(__PageMovable(page))) { + lock_page(page); + if (!PageMovable(page)) + __ClearPageIsolated(page); + unlock_page(page); + } + goto out; + } + + newpage = get_new_page(page, private); + if (!newpage) + return -ENOMEM; + + rc = __unmap_and_move(page, newpage, force, mode); + if (rc == MIGRATEPAGE_SUCCESS) + set_page_owner_migrate_reason(newpage, reason); + +out: + if (rc != -EAGAIN) { + /* + * A page that has been migrated has all references + * removed and will be freed. A page that has not been + * migrated will have kept its references and be restored. + */ + list_del(&page->lru); + + /* + * Compaction can migrate also non-LRU pages which are + * not accounted to NR_ISOLATED_*. They can be recognized + * as __PageMovable + */ + if (likely(!__PageMovable(page))) + mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + + page_is_file_lru(page), -thp_nr_pages(page)); + } + + /* + * If migration is successful, releases reference grabbed during + * isolation. Otherwise, restore the page to right list unless + * we want to retry. + */ + if (rc == MIGRATEPAGE_SUCCESS) { + if (reason != MR_MEMORY_FAILURE) + /* + * We release the page in page_handle_poison. + */ + put_page(page); + } else { + if (rc != -EAGAIN) { + if (likely(!__PageMovable(page))) { + putback_lru_page(page); + goto put_new; + } + + lock_page(page); + if (PageMovable(page)) + putback_movable_page(page); + else + __ClearPageIsolated(page); + unlock_page(page); + put_page(page); + } +put_new: + if (put_new_page) + put_new_page(newpage, private); + else + put_page(newpage); + } + + return rc; +} + +/* + * Counterpart of unmap_and_move_page() for hugepage migration. + * + * This function doesn't wait the completion of hugepage I/O + * because there is no race between I/O and migration for hugepage. + * Note that currently hugepage I/O occurs only in direct I/O + * where no lock is held and PG_writeback is irrelevant, + * and writeback status of all subpages are counted in the reference + * count of the head page (i.e. if all subpages of a 2MB hugepage are + * under direct I/O, the reference of the head page is 512 and a bit more.) + * This means that when we try to migrate hugepage whose subpages are + * doing direct I/O, some references remain after try_to_unmap() and + * hugepage migration fails without data corruption. + * + * There is also no race when direct I/O is issued on the page under migration, + * because then pte is replaced with migration swap entry and direct I/O code + * will wait in the page fault for migration to complete. + */ +static int unmap_and_move_huge_page(new_page_t get_new_page, + free_page_t put_new_page, unsigned long private, + struct page *hpage, int force, + enum migrate_mode mode, int reason) +{ + int rc = -EAGAIN; + int page_was_mapped = 0; + struct page *new_hpage; + struct anon_vma *anon_vma = NULL; + struct address_space *mapping = NULL; + + /* + * Migratability of hugepages depends on architectures and their size. + * This check is necessary because some callers of hugepage migration + * like soft offline and memory hotremove don't walk through page + * tables or check whether the hugepage is pmd-based or not before + * kicking migration. + */ + if (!hugepage_migration_supported(page_hstate(hpage))) { + putback_active_hugepage(hpage); + return -ENOSYS; + } + + new_hpage = get_new_page(hpage, private); + if (!new_hpage) + return -ENOMEM; + + if (!trylock_page(hpage)) { + if (!force) + goto out; + switch (mode) { + case MIGRATE_SYNC: + case MIGRATE_SYNC_NO_COPY: + break; + default: + goto out; + } + lock_page(hpage); + } + + /* + * Check for pages which are in the process of being freed. Without + * page_mapping() set, hugetlbfs specific move page routine will not + * be called and we could leak usage counts for subpools. + */ + if (page_private(hpage) && !page_mapping(hpage)) { + rc = -EBUSY; + goto out_unlock; + } + + if (PageAnon(hpage)) + anon_vma = page_get_anon_vma(hpage); + + if (unlikely(!trylock_page(new_hpage))) + goto put_anon; + + if (page_mapped(hpage)) { + bool mapping_locked = false; + enum ttu_flags ttu = TTU_MIGRATION|TTU_IGNORE_MLOCK; + + if (!PageAnon(hpage)) { + /* + * In shared mappings, try_to_unmap could potentially + * call huge_pmd_unshare. Because of this, take + * semaphore in write mode here and set TTU_RMAP_LOCKED + * to let lower levels know we have taken the lock. + */ + mapping = hugetlb_page_mapping_lock_write(hpage); + if (unlikely(!mapping)) + goto unlock_put_anon; + + mapping_locked = true; + ttu |= TTU_RMAP_LOCKED; + } + + try_to_unmap(hpage, ttu); + page_was_mapped = 1; + + if (mapping_locked) + i_mmap_unlock_write(mapping); + } + + if (!page_mapped(hpage)) + rc = move_to_new_page(new_hpage, hpage, mode); + + if (page_was_mapped) + remove_migration_ptes(hpage, + rc == MIGRATEPAGE_SUCCESS ? new_hpage : hpage, false); + +unlock_put_anon: + unlock_page(new_hpage); + +put_anon: + if (anon_vma) + put_anon_vma(anon_vma); + + if (rc == MIGRATEPAGE_SUCCESS) { + move_hugetlb_state(hpage, new_hpage, reason); + put_new_page = NULL; + } + +out_unlock: + unlock_page(hpage); +out: + if (rc != -EAGAIN) + putback_active_hugepage(hpage); + + /* + * If migration was not successful and there's a freeing callback, use + * it. Otherwise, put_page() will drop the reference grabbed during + * isolation. + */ + if (put_new_page) + put_new_page(new_hpage, private); + else + putback_active_hugepage(new_hpage); + + return rc; +} + +/* + * migrate_pages - migrate the pages specified in a list, to the free pages + * supplied as the target for the page migration + * + * @from: The list of pages to be migrated. + * @get_new_page: The function used to allocate free pages to be used + * as the target of the page migration. + * @put_new_page: The function used to free target pages if migration + * fails, or NULL if no special handling is necessary. + * @private: Private data to be passed on to get_new_page() + * @mode: The migration mode that specifies the constraints for + * page migration, if any. + * @reason: The reason for page migration. + * + * The function returns after 10 attempts or if no pages are movable any more + * because the list has become empty or no retryable pages exist any more. + * The caller should call putback_movable_pages() to return pages to the LRU + * or free list only if ret != 0. + * + * Returns the number of pages that were not migrated, or an error code. + */ +int migrate_pages(struct list_head *from, new_page_t get_new_page, + free_page_t put_new_page, unsigned long private, + enum migrate_mode mode, int reason) +{ + int retry = 1; + int thp_retry = 1; + int nr_failed = 0; + int nr_succeeded = 0; + int nr_thp_succeeded = 0; + int nr_thp_failed = 0; + int nr_thp_split = 0; + int pass = 0; + bool is_thp = false; + struct page *page; + struct page *page2; + int swapwrite = current->flags & PF_SWAPWRITE; + int rc, nr_subpages; + + if (!swapwrite) + current->flags |= PF_SWAPWRITE; + + for (pass = 0; pass < 10 && (retry || thp_retry); pass++) { + retry = 0; + thp_retry = 0; + + list_for_each_entry_safe(page, page2, from, lru) { +retry: + /* + * THP statistics is based on the source huge page. + * Capture required information that might get lost + * during migration. + */ + is_thp = PageTransHuge(page) && !PageHuge(page); + nr_subpages = thp_nr_pages(page); + cond_resched(); + + if (PageHuge(page)) + rc = unmap_and_move_huge_page(get_new_page, + put_new_page, private, page, + pass > 2, mode, reason); + else + rc = unmap_and_move(get_new_page, put_new_page, + private, page, pass > 2, mode, + reason); + + switch(rc) { + case -ENOMEM: + /* + * THP migration might be unsupported or the + * allocation could've failed so we should + * retry on the same page with the THP split + * to base pages. + * + * Head page is retried immediately and tail + * pages are added to the tail of the list so + * we encounter them after the rest of the list + * is processed. + */ + if (is_thp) { + lock_page(page); + rc = split_huge_page_to_list(page, from); + unlock_page(page); + if (!rc) { + list_safe_reset_next(page, page2, lru); + nr_thp_split++; + goto retry; + } + + nr_thp_failed++; + nr_failed += nr_subpages; + goto out; + } + nr_failed++; + goto out; + case -EAGAIN: + if (is_thp) { + thp_retry++; + break; + } + retry++; + break; + case MIGRATEPAGE_SUCCESS: + if (is_thp) { + nr_thp_succeeded++; + nr_succeeded += nr_subpages; + break; + } + nr_succeeded++; + break; + default: + /* + * Permanent failure (-EBUSY, -ENOSYS, etc.): + * unlike -EAGAIN case, the failed page is + * removed from migration page list and not + * retried in the next outer loop. + */ + if (is_thp) { + nr_thp_failed++; + nr_failed += nr_subpages; + break; + } + nr_failed++; + break; + } + } + } + nr_failed += retry + thp_retry; + nr_thp_failed += thp_retry; + rc = nr_failed; +out: + count_vm_events(PGMIGRATE_SUCCESS, nr_succeeded); + count_vm_events(PGMIGRATE_FAIL, nr_failed); + count_vm_events(THP_MIGRATION_SUCCESS, nr_thp_succeeded); + count_vm_events(THP_MIGRATION_FAIL, nr_thp_failed); + count_vm_events(THP_MIGRATION_SPLIT, nr_thp_split); + trace_mm_migrate_pages(nr_succeeded, nr_failed, nr_thp_succeeded, + nr_thp_failed, nr_thp_split, mode, reason); + + if (!swapwrite) + current->flags &= ~PF_SWAPWRITE; + + return rc; +} + +struct page *alloc_migration_target(struct page *page, unsigned long private) +{ + struct migration_target_control *mtc; + gfp_t gfp_mask; + unsigned int order = 0; + struct page *new_page = NULL; + int nid; + int zidx; + + mtc = (struct migration_target_control *)private; + gfp_mask = mtc->gfp_mask; + nid = mtc->nid; + if (nid == NUMA_NO_NODE) + nid = page_to_nid(page); + + if (PageHuge(page)) { + struct hstate *h = page_hstate(compound_head(page)); + + gfp_mask = htlb_modify_alloc_mask(h, gfp_mask); + return alloc_huge_page_nodemask(h, nid, mtc->nmask, gfp_mask); + } + + if (PageTransHuge(page)) { + /* + * clear __GFP_RECLAIM to make the migration callback + * consistent with regular THP allocations. + */ + gfp_mask &= ~__GFP_RECLAIM; + gfp_mask |= GFP_TRANSHUGE; + order = HPAGE_PMD_ORDER; + } + zidx = zone_idx(page_zone(page)); + if (is_highmem_idx(zidx) || zidx == ZONE_MOVABLE) + gfp_mask |= __GFP_HIGHMEM; + + new_page = __alloc_pages_nodemask(gfp_mask, order, nid, mtc->nmask); + + if (new_page && PageTransHuge(new_page)) + prep_transhuge_page(new_page); + + return new_page; +} + +#ifdef CONFIG_NUMA + +static int store_status(int __user *status, int start, int value, int nr) +{ + while (nr-- > 0) { + if (put_user(value, status + start)) + return -EFAULT; + start++; + } + + return 0; +} + +static int do_move_pages_to_node(struct mm_struct *mm, + struct list_head *pagelist, int node) +{ + int err; + struct migration_target_control mtc = { + .nid = node, + .gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, + }; + + err = migrate_pages(pagelist, alloc_migration_target, NULL, + (unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL); + if (err) + putback_movable_pages(pagelist); + return err; +} + +/* + * Resolves the given address to a struct page, isolates it from the LRU and + * puts it to the given pagelist. + * Returns: + * errno - if the page cannot be found/isolated + * 0 - when it doesn't have to be migrated because it is already on the + * target node + * 1 - when it has been queued + */ +static int add_page_for_migration(struct mm_struct *mm, unsigned long addr, + int node, struct list_head *pagelist, bool migrate_all) +{ + struct vm_area_struct *vma; + struct page *page; + unsigned int follflags; + int err; + + mmap_read_lock(mm); + err = -EFAULT; + vma = find_vma(mm, addr); + if (!vma || addr < vma->vm_start || !vma_migratable(vma)) + goto out; + + /* FOLL_DUMP to ignore special (like zero) pages */ + follflags = FOLL_GET | FOLL_DUMP; + page = follow_page(vma, addr, follflags); + + err = PTR_ERR(page); + if (IS_ERR(page)) + goto out; + + err = -ENOENT; + if (!page) + goto out; + + err = 0; + if (page_to_nid(page) == node) + goto out_putpage; + + err = -EACCES; + if (page_mapcount(page) > 1 && !migrate_all) + goto out_putpage; + + if (PageHuge(page)) { + if (PageHead(page)) { + err = isolate_hugetlb(page, pagelist); + if (!err) + err = 1; + } + } else { + struct page *head; + + head = compound_head(page); + err = isolate_lru_page(head); + if (err) + goto out_putpage; + + err = 1; + list_add_tail(&head->lru, pagelist); + mod_node_page_state(page_pgdat(head), + NR_ISOLATED_ANON + page_is_file_lru(head), + thp_nr_pages(head)); + } +out_putpage: + /* + * Either remove the duplicate refcount from + * isolate_lru_page() or drop the page ref if it was + * not isolated. + */ + put_page(page); +out: + mmap_read_unlock(mm); + return err; +} + +static int move_pages_and_store_status(struct mm_struct *mm, int node, + struct list_head *pagelist, int __user *status, + int start, int i, unsigned long nr_pages) +{ + int err; + + if (list_empty(pagelist)) + return 0; + + err = do_move_pages_to_node(mm, pagelist, node); + if (err) { + /* + * Positive err means the number of failed + * pages to migrate. Since we are going to + * abort and return the number of non-migrated + * pages, so need to incude the rest of the + * nr_pages that have not been attempted as + * well. + */ + if (err > 0) + err += nr_pages - i - 1; + return err; + } + return store_status(status, start, node, i - start); +} + +/* + * Migrate an array of page address onto an array of nodes and fill + * the corresponding array of status. + */ +static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes, + unsigned long nr_pages, + const void __user * __user *pages, + const int __user *nodes, + int __user *status, int flags) +{ + int current_node = NUMA_NO_NODE; + LIST_HEAD(pagelist); + int start, i; + int err = 0, err1; + + migrate_prep(); + + for (i = start = 0; i < nr_pages; i++) { + const void __user *p; + unsigned long addr; + int node; + + err = -EFAULT; + if (get_user(p, pages + i)) + goto out_flush; + if (get_user(node, nodes + i)) + goto out_flush; + addr = (unsigned long)untagged_addr(p); + + err = -ENODEV; + if (node < 0 || node >= MAX_NUMNODES) + goto out_flush; + if (!node_state(node, N_MEMORY)) + goto out_flush; + + err = -EACCES; + if (!node_isset(node, task_nodes)) + goto out_flush; + + if (current_node == NUMA_NO_NODE) { + current_node = node; + start = i; + } else if (node != current_node) { + err = move_pages_and_store_status(mm, current_node, + &pagelist, status, start, i, nr_pages); + if (err) + goto out; + start = i; + current_node = node; + } + + /* + * Errors in the page lookup or isolation are not fatal and we simply + * report them via status + */ + err = add_page_for_migration(mm, addr, current_node, + &pagelist, flags & MPOL_MF_MOVE_ALL); + + if (err > 0) { + /* The page is successfully queued for migration */ + continue; + } + + /* + * If the page is already on the target node (!err), store the + * node, otherwise, store the err. + */ + err = store_status(status, i, err ? : current_node, 1); + if (err) + goto out_flush; + + err = move_pages_and_store_status(mm, current_node, &pagelist, + status, start, i, nr_pages); + if (err) + goto out; + current_node = NUMA_NO_NODE; + } +out_flush: + /* Make sure we do not overwrite the existing error */ + err1 = move_pages_and_store_status(mm, current_node, &pagelist, + status, start, i, nr_pages); + if (err >= 0) + err = err1; +out: + return err; +} + +/* + * Determine the nodes of an array of pages and store it in an array of status. + */ +static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages, + const void __user **pages, int *status) +{ + unsigned long i; + + mmap_read_lock(mm); + + for (i = 0; i < nr_pages; i++) { + unsigned long addr = (unsigned long)(*pages); + struct vm_area_struct *vma; + struct page *page; + int err = -EFAULT; + + vma = find_vma(mm, addr); + if (!vma || addr < vma->vm_start) + goto set_status; + + /* FOLL_DUMP to ignore special (like zero) pages */ + page = follow_page(vma, addr, FOLL_DUMP); + + err = PTR_ERR(page); + if (IS_ERR(page)) + goto set_status; + + err = page ? page_to_nid(page) : -ENOENT; +set_status: + *status = err; + + pages++; + status++; + } + + mmap_read_unlock(mm); +} + +/* + * Determine the nodes of a user array of pages and store it in + * a user array of status. + */ +static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages, + const void __user * __user *pages, + int __user *status) +{ +#define DO_PAGES_STAT_CHUNK_NR 16 + const void __user *chunk_pages[DO_PAGES_STAT_CHUNK_NR]; + int chunk_status[DO_PAGES_STAT_CHUNK_NR]; + + while (nr_pages) { + unsigned long chunk_nr; + + chunk_nr = nr_pages; + if (chunk_nr > DO_PAGES_STAT_CHUNK_NR) + chunk_nr = DO_PAGES_STAT_CHUNK_NR; + + if (copy_from_user(chunk_pages, pages, chunk_nr * sizeof(*chunk_pages))) + break; + + do_pages_stat_array(mm, chunk_nr, chunk_pages, chunk_status); + + if (copy_to_user(status, chunk_status, chunk_nr * sizeof(*status))) + break; + + pages += chunk_nr; + status += chunk_nr; + nr_pages -= chunk_nr; + } + return nr_pages ? -EFAULT : 0; +} + +static struct mm_struct *find_mm_struct(pid_t pid, nodemask_t *mem_nodes) +{ + struct task_struct *task; + struct mm_struct *mm; + + /* + * There is no need to check if current process has the right to modify + * the specified process when they are same. + */ + if (!pid) { + mmget(current->mm); + *mem_nodes = cpuset_mems_allowed(current); + return current->mm; + } + + /* Find the mm_struct */ + rcu_read_lock(); + task = find_task_by_vpid(pid); + if (!task) { + rcu_read_unlock(); + return ERR_PTR(-ESRCH); + } + get_task_struct(task); + + /* + * Check if this process has the right to modify the specified + * process. Use the regular "ptrace_may_access()" checks. + */ + if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) { + rcu_read_unlock(); + mm = ERR_PTR(-EPERM); + goto out; + } + rcu_read_unlock(); + + mm = ERR_PTR(security_task_movememory(task)); + if (IS_ERR(mm)) + goto out; + *mem_nodes = cpuset_mems_allowed(task); + mm = get_task_mm(task); +out: + put_task_struct(task); + if (!mm) + mm = ERR_PTR(-EINVAL); + return mm; +} + +/* + * Move a list of pages in the address space of the currently executing + * process. + */ +static int kernel_move_pages(pid_t pid, unsigned long nr_pages, + const void __user * __user *pages, + const int __user *nodes, + int __user *status, int flags) +{ + struct mm_struct *mm; + int err; + nodemask_t task_nodes; + + /* Check flags */ + if (flags & ~(MPOL_MF_MOVE|MPOL_MF_MOVE_ALL)) + return -EINVAL; + + if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE)) + return -EPERM; + + mm = find_mm_struct(pid, &task_nodes); + if (IS_ERR(mm)) + return PTR_ERR(mm); + + if (nodes) + err = do_pages_move(mm, task_nodes, nr_pages, pages, + nodes, status, flags); + else + err = do_pages_stat(mm, nr_pages, pages, status); + + mmput(mm); + return err; +} + +SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages, + const void __user * __user *, pages, + const int __user *, nodes, + int __user *, status, int, flags) +{ + return kernel_move_pages(pid, nr_pages, pages, nodes, status, flags); +} + +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE6(move_pages, pid_t, pid, compat_ulong_t, nr_pages, + compat_uptr_t __user *, pages32, + const int __user *, nodes, + int __user *, status, + int, flags) +{ + const void __user * __user *pages; + int i; + + pages = compat_alloc_user_space(nr_pages * sizeof(void *)); + for (i = 0; i < nr_pages; i++) { + compat_uptr_t p; + + if (get_user(p, pages32 + i) || + put_user(compat_ptr(p), pages + i)) + return -EFAULT; + } + return kernel_move_pages(pid, nr_pages, pages, nodes, status, flags); +} +#endif /* CONFIG_COMPAT */ + +#ifdef CONFIG_NUMA_BALANCING +/* + * Returns true if this is a safe migration target node for misplaced NUMA + * pages. Currently it only checks the watermarks which crude + */ +static bool migrate_balanced_pgdat(struct pglist_data *pgdat, + unsigned long nr_migrate_pages) +{ + int z; + + for (z = pgdat->nr_zones - 1; z >= 0; z--) { + struct zone *zone = pgdat->node_zones + z; + + if (!populated_zone(zone)) + continue; + + /* Avoid waking kswapd by allocating pages_to_migrate pages. */ + if (!zone_watermark_ok(zone, 0, + high_wmark_pages(zone) + + nr_migrate_pages, + ZONE_MOVABLE, 0)) + continue; + return true; + } + return false; +} + +static struct page *alloc_misplaced_dst_page(struct page *page, + unsigned long data) +{ + int nid = (int) data; + struct page *newpage; + + newpage = __alloc_pages_node(nid, + (GFP_HIGHUSER_MOVABLE | + __GFP_THISNODE | __GFP_NOMEMALLOC | + __GFP_NORETRY | __GFP_NOWARN) & + ~__GFP_RECLAIM, 0); + + return newpage; +} + +static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) +{ + int page_lru; + + VM_BUG_ON_PAGE(compound_order(page) && !PageTransHuge(page), page); + + /* Avoid migrating to a node that is nearly full */ + if (!migrate_balanced_pgdat(pgdat, compound_nr(page))) + return 0; + + if (isolate_lru_page(page)) + return 0; + + /* + * migrate_misplaced_transhuge_page() skips page migration's usual + * check on page_count(), so we must do it here, now that the page + * has been isolated: a GUP pin, or any other pin, prevents migration. + * The expected page count is 3: 1 for page's mapcount and 1 for the + * caller's pin and 1 for the reference taken by isolate_lru_page(). + */ + if (PageTransHuge(page) && page_count(page) != 3) { + putback_lru_page(page); + return 0; + } + + page_lru = page_is_file_lru(page); + mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_lru, + thp_nr_pages(page)); + + /* + * Isolating the page has taken another reference, so the + * caller's reference can be safely dropped without the page + * disappearing underneath us during migration. + */ + put_page(page); + return 1; +} + +bool pmd_trans_migrating(pmd_t pmd) +{ + struct page *page = pmd_page(pmd); + return PageLocked(page); +} + +/* + * Attempt to migrate a misplaced page to the specified destination + * node. Caller is expected to have an elevated reference count on + * the page that will be dropped by this function before returning. + */ +int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, + int node) +{ + pg_data_t *pgdat = NODE_DATA(node); + int isolated; + int nr_remaining; + LIST_HEAD(migratepages); + + /* + * Don't migrate file pages that are mapped in multiple processes + * with execute permissions as they are probably shared libraries. + */ + if (page_mapcount(page) != 1 && page_is_file_lru(page) && + (vma->vm_flags & VM_EXEC)) + goto out; + + /* + * Also do not migrate dirty pages as not all filesystems can move + * dirty pages in MIGRATE_ASYNC mode which is a waste of cycles. + */ + if (page_is_file_lru(page) && PageDirty(page)) + goto out; + + isolated = numamigrate_isolate_page(pgdat, page); + if (!isolated) + goto out; + + list_add(&page->lru, &migratepages); + nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page, + NULL, node, MIGRATE_ASYNC, + MR_NUMA_MISPLACED); + if (nr_remaining) { + if (!list_empty(&migratepages)) { + list_del(&page->lru); + dec_node_page_state(page, NR_ISOLATED_ANON + + page_is_file_lru(page)); + putback_lru_page(page); + } + isolated = 0; + } else + count_vm_numa_event(NUMA_PAGE_MIGRATE); + BUG_ON(!list_empty(&migratepages)); + return isolated; + +out: + put_page(page); + return 0; +} +#endif /* CONFIG_NUMA_BALANCING */ + +#if defined(CONFIG_NUMA_BALANCING) && defined(CONFIG_TRANSPARENT_HUGEPAGE) +/* + * Migrates a THP to a given target node. page must be locked and is unlocked + * before returning. + */ +int migrate_misplaced_transhuge_page(struct mm_struct *mm, + struct vm_area_struct *vma, + pmd_t *pmd, pmd_t entry, + unsigned long address, + struct page *page, int node) +{ + spinlock_t *ptl; + pg_data_t *pgdat = NODE_DATA(node); + int isolated = 0; + struct page *new_page = NULL; + int page_lru = page_is_file_lru(page); + unsigned long start = address & HPAGE_PMD_MASK; + + new_page = alloc_pages_node(node, + (GFP_TRANSHUGE_LIGHT | __GFP_THISNODE), + HPAGE_PMD_ORDER); + if (!new_page) + goto out_fail; + prep_transhuge_page(new_page); + + isolated = numamigrate_isolate_page(pgdat, page); + if (!isolated) { + put_page(new_page); + goto out_fail; + } + + /* Prepare a page as a migration target */ + __SetPageLocked(new_page); + if (PageSwapBacked(page)) + __SetPageSwapBacked(new_page); + + /* anon mapping, we can simply copy page->mapping to the new page: */ + new_page->mapping = page->mapping; + new_page->index = page->index; + /* flush the cache before copying using the kernel virtual address */ + flush_cache_range(vma, start, start + HPAGE_PMD_SIZE); + migrate_page_copy(new_page, page); + WARN_ON(PageLRU(new_page)); + + /* Recheck the target PMD */ + ptl = pmd_lock(mm, pmd); + if (unlikely(!pmd_same(*pmd, entry) || !page_ref_freeze(page, 2))) { + spin_unlock(ptl); + + /* Reverse changes made by migrate_page_copy() */ + if (TestClearPageActive(new_page)) + SetPageActive(page); + if (TestClearPageUnevictable(new_page)) + SetPageUnevictable(page); + + unlock_page(new_page); + put_page(new_page); /* Free it */ + + /* Retake the callers reference and putback on LRU */ + get_page(page); + putback_lru_page(page); + mod_node_page_state(page_pgdat(page), + NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR); + + goto out_unlock; + } + + entry = mk_huge_pmd(new_page, vma->vm_page_prot); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); + + /* + * Overwrite the old entry under pagetable lock and establish + * the new PTE. Any parallel GUP will either observe the old + * page blocking on the page lock, block on the page table + * lock or observe the new page. The SetPageUptodate on the + * new page and page_add_new_anon_rmap guarantee the copy is + * visible before the pagetable update. + */ + page_add_anon_rmap(new_page, vma, start, true); + /* + * At this point the pmd is numa/protnone (i.e. non present) and the TLB + * has already been flushed globally. So no TLB can be currently + * caching this non present pmd mapping. There's no need to clear the + * pmd before doing set_pmd_at(), nor to flush the TLB after + * set_pmd_at(). Clearing the pmd here would introduce a race + * condition against MADV_DONTNEED, because MADV_DONTNEED only holds the + * mmap_lock for reading. If the pmd is set to NULL at any given time, + * MADV_DONTNEED won't wait on the pmd lock and it'll skip clearing this + * pmd. + */ + set_pmd_at(mm, start, pmd, entry); + update_mmu_cache_pmd(vma, address, &entry); + + page_ref_unfreeze(page, 2); + mlock_migrate_page(new_page, page); + page_remove_rmap(page, true); + set_page_owner_migrate_reason(new_page, MR_NUMA_MISPLACED); + + spin_unlock(ptl); + + /* Take an "isolate" reference and put new page on the LRU. */ + get_page(new_page); + putback_lru_page(new_page); + + unlock_page(new_page); + unlock_page(page); + put_page(page); /* Drop the rmap reference */ + put_page(page); /* Drop the LRU isolation reference */ + + count_vm_events(PGMIGRATE_SUCCESS, HPAGE_PMD_NR); + count_vm_numa_events(NUMA_PAGE_MIGRATE, HPAGE_PMD_NR); + + mod_node_page_state(page_pgdat(page), + NR_ISOLATED_ANON + page_lru, + -HPAGE_PMD_NR); + return isolated; + +out_fail: + count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR); + ptl = pmd_lock(mm, pmd); + if (pmd_same(*pmd, entry)) { + entry = pmd_modify(entry, vma->vm_page_prot); + set_pmd_at(mm, start, pmd, entry); + update_mmu_cache_pmd(vma, address, &entry); + } + spin_unlock(ptl); + +out_unlock: + unlock_page(page); + put_page(page); + return 0; +} +#endif /* CONFIG_NUMA_BALANCING */ + +#endif /* CONFIG_NUMA */ + +#ifdef CONFIG_DEVICE_PRIVATE +static int migrate_vma_collect_hole(unsigned long start, + unsigned long end, + __always_unused int depth, + struct mm_walk *walk) +{ + struct migrate_vma *migrate = walk->private; + unsigned long addr; + + /* Only allow populating anonymous memory. */ + if (!vma_is_anonymous(walk->vma)) { + for (addr = start; addr < end; addr += PAGE_SIZE) { + migrate->src[migrate->npages] = 0; + migrate->dst[migrate->npages] = 0; + migrate->npages++; + } + return 0; + } + + for (addr = start; addr < end; addr += PAGE_SIZE) { + migrate->src[migrate->npages] = MIGRATE_PFN_MIGRATE; + migrate->dst[migrate->npages] = 0; + migrate->npages++; + migrate->cpages++; + } + + return 0; +} + +static int migrate_vma_collect_skip(unsigned long start, + unsigned long end, + struct mm_walk *walk) +{ + struct migrate_vma *migrate = walk->private; + unsigned long addr; + + for (addr = start; addr < end; addr += PAGE_SIZE) { + migrate->dst[migrate->npages] = 0; + migrate->src[migrate->npages++] = 0; + } + + return 0; +} + +static int migrate_vma_collect_pmd(pmd_t *pmdp, + unsigned long start, + unsigned long end, + struct mm_walk *walk) +{ + struct migrate_vma *migrate = walk->private; + struct vm_area_struct *vma = walk->vma; + struct mm_struct *mm = vma->vm_mm; + unsigned long addr = start, unmapped = 0; + spinlock_t *ptl; + pte_t *ptep; + +again: + if (pmd_none(*pmdp)) + return migrate_vma_collect_hole(start, end, -1, walk); + + if (pmd_trans_huge(*pmdp)) { + struct page *page; + + ptl = pmd_lock(mm, pmdp); + if (unlikely(!pmd_trans_huge(*pmdp))) { + spin_unlock(ptl); + goto again; + } + + page = pmd_page(*pmdp); + if (is_huge_zero_page(page)) { + spin_unlock(ptl); + split_huge_pmd(vma, pmdp, addr); + if (pmd_trans_unstable(pmdp)) + return migrate_vma_collect_skip(start, end, + walk); + } else { + int ret; + + get_page(page); + spin_unlock(ptl); + if (unlikely(!trylock_page(page))) + return migrate_vma_collect_skip(start, end, + walk); + ret = split_huge_page(page); + unlock_page(page); + put_page(page); + if (ret) + return migrate_vma_collect_skip(start, end, + walk); + if (pmd_none(*pmdp)) + return migrate_vma_collect_hole(start, end, -1, + walk); + } + } + + if (unlikely(pmd_bad(*pmdp))) + return migrate_vma_collect_skip(start, end, walk); + + ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl); + arch_enter_lazy_mmu_mode(); + + for (; addr < end; addr += PAGE_SIZE, ptep++) { + unsigned long mpfn = 0, pfn; + struct page *page; + swp_entry_t entry; + pte_t pte; + + pte = *ptep; + + if (pte_none(pte)) { + if (vma_is_anonymous(vma)) { + mpfn = MIGRATE_PFN_MIGRATE; + migrate->cpages++; + } + goto next; + } + + if (!pte_present(pte)) { + /* + * Only care about unaddressable device page special + * page table entry. Other special swap entries are not + * migratable, and we ignore regular swapped page. + */ + entry = pte_to_swp_entry(pte); + if (!is_device_private_entry(entry)) + goto next; + + page = device_private_entry_to_page(entry); + if (!(migrate->flags & + MIGRATE_VMA_SELECT_DEVICE_PRIVATE) || + page->pgmap->owner != migrate->pgmap_owner) + goto next; + + mpfn = migrate_pfn(page_to_pfn(page)) | + MIGRATE_PFN_MIGRATE; + if (is_write_device_private_entry(entry)) + mpfn |= MIGRATE_PFN_WRITE; + } else { + if (!(migrate->flags & MIGRATE_VMA_SELECT_SYSTEM)) + goto next; + pfn = pte_pfn(pte); + if (is_zero_pfn(pfn)) { + mpfn = MIGRATE_PFN_MIGRATE; + migrate->cpages++; + goto next; + } + page = vm_normal_page(migrate->vma, addr, pte); + mpfn = migrate_pfn(pfn) | MIGRATE_PFN_MIGRATE; + mpfn |= pte_write(pte) ? MIGRATE_PFN_WRITE : 0; + } + + /* FIXME support THP */ + if (!page || !page->mapping || PageTransCompound(page)) { + mpfn = 0; + goto next; + } + + /* + * By getting a reference on the page we pin it and that blocks + * any kind of migration. Side effect is that it "freezes" the + * pte. + * + * We drop this reference after isolating the page from the lru + * for non device page (device page are not on the lru and thus + * can't be dropped from it). + */ + get_page(page); + migrate->cpages++; + + /* + * Optimize for the common case where page is only mapped once + * in one process. If we can lock the page, then we can safely + * set up a special migration page table entry now. + */ + if (trylock_page(page)) { + pte_t swp_pte; + + mpfn |= MIGRATE_PFN_LOCKED; + ptep_get_and_clear(mm, addr, ptep); + + /* Setup special migration page table entry */ + entry = make_migration_entry(page, mpfn & + MIGRATE_PFN_WRITE); + swp_pte = swp_entry_to_pte(entry); + if (pte_present(pte)) { + if (pte_soft_dirty(pte)) + swp_pte = pte_swp_mksoft_dirty(swp_pte); + if (pte_uffd_wp(pte)) + swp_pte = pte_swp_mkuffd_wp(swp_pte); + } else { + if (pte_swp_soft_dirty(pte)) + swp_pte = pte_swp_mksoft_dirty(swp_pte); + if (pte_swp_uffd_wp(pte)) + swp_pte = pte_swp_mkuffd_wp(swp_pte); + } + set_pte_at(mm, addr, ptep, swp_pte); + + /* + * This is like regular unmap: we remove the rmap and + * drop page refcount. Page won't be freed, as we took + * a reference just above. + */ + page_remove_rmap(page, false); + put_page(page); + + if (pte_present(pte)) + unmapped++; + } + +next: + migrate->dst[migrate->npages] = 0; + migrate->src[migrate->npages++] = mpfn; + } + + /* Only flush the TLB if we actually modified any entries */ + if (unmapped) + flush_tlb_range(walk->vma, start, end); + + arch_leave_lazy_mmu_mode(); + pte_unmap_unlock(ptep - 1, ptl); + + return 0; +} + +static const struct mm_walk_ops migrate_vma_walk_ops = { + .pmd_entry = migrate_vma_collect_pmd, + .pte_hole = migrate_vma_collect_hole, +}; + +/* + * migrate_vma_collect() - collect pages over a range of virtual addresses + * @migrate: migrate struct containing all migration information + * + * This will walk the CPU page table. For each virtual address backed by a + * valid page, it updates the src array and takes a reference on the page, in + * order to pin the page until we lock it and unmap it. + */ +static void migrate_vma_collect(struct migrate_vma *migrate) +{ + struct mmu_notifier_range range; + + /* + * Note that the pgmap_owner is passed to the mmu notifier callback so + * that the registered device driver can skip invalidating device + * private page mappings that won't be migrated. + */ + mmu_notifier_range_init_migrate(&range, 0, migrate->vma, + migrate->vma->vm_mm, migrate->start, migrate->end, + migrate->pgmap_owner); + mmu_notifier_invalidate_range_start(&range); + + walk_page_range(migrate->vma->vm_mm, migrate->start, migrate->end, + &migrate_vma_walk_ops, migrate); + + mmu_notifier_invalidate_range_end(&range); + migrate->end = migrate->start + (migrate->npages << PAGE_SHIFT); +} + +/* + * migrate_vma_check_page() - check if page is pinned or not + * @page: struct page to check + * + * Pinned pages cannot be migrated. This is the same test as in + * migrate_page_move_mapping(), except that here we allow migration of a + * ZONE_DEVICE page. + */ +static bool migrate_vma_check_page(struct page *page) +{ + /* + * One extra ref because caller holds an extra reference, either from + * isolate_lru_page() for a regular page, or migrate_vma_collect() for + * a device page. + */ + int extra = 1; + + /* + * FIXME support THP (transparent huge page), it is bit more complex to + * check them than regular pages, because they can be mapped with a pmd + * or with a pte (split pte mapping). + */ + if (PageCompound(page)) + return false; + + /* Page from ZONE_DEVICE have one extra reference */ + if (is_zone_device_page(page)) { + /* + * Private page can never be pin as they have no valid pte and + * GUP will fail for those. Yet if there is a pending migration + * a thread might try to wait on the pte migration entry and + * will bump the page reference count. Sadly there is no way to + * differentiate a regular pin from migration wait. Hence to + * avoid 2 racing thread trying to migrate back to CPU to enter + * infinite loop (one stoping migration because the other is + * waiting on pte migration entry). We always return true here. + * + * FIXME proper solution is to rework migration_entry_wait() so + * it does not need to take a reference on page. + */ + return is_device_private_page(page); + } + + /* For file back page */ + if (page_mapping(page)) + extra += 1 + page_has_private(page); + + if ((page_count(page) - extra) > page_mapcount(page)) + return false; + + return true; +} + +/* + * migrate_vma_prepare() - lock pages and isolate them from the lru + * @migrate: migrate struct containing all migration information + * + * This locks pages that have been collected by migrate_vma_collect(). Once each + * page is locked it is isolated from the lru (for non-device pages). Finally, + * the ref taken by migrate_vma_collect() is dropped, as locked pages cannot be + * migrated by concurrent kernel threads. + */ +static void migrate_vma_prepare(struct migrate_vma *migrate) +{ + const unsigned long npages = migrate->npages; + const unsigned long start = migrate->start; + unsigned long addr, i, restore = 0; + bool allow_drain = true; + + lru_add_drain(); + + for (i = 0; (i < npages) && migrate->cpages; i++) { + struct page *page = migrate_pfn_to_page(migrate->src[i]); + bool remap = true; + + if (!page) + continue; + + if (!(migrate->src[i] & MIGRATE_PFN_LOCKED)) { + /* + * Because we are migrating several pages there can be + * a deadlock between 2 concurrent migration where each + * are waiting on each other page lock. + * + * Make migrate_vma() a best effort thing and backoff + * for any page we can not lock right away. + */ + if (!trylock_page(page)) { + migrate->src[i] = 0; + migrate->cpages--; + put_page(page); + continue; + } + remap = false; + migrate->src[i] |= MIGRATE_PFN_LOCKED; + } + + /* ZONE_DEVICE pages are not on LRU */ + if (!is_zone_device_page(page)) { + if (!PageLRU(page) && allow_drain) { + /* Drain CPU's pagevec */ + lru_add_drain_all(); + allow_drain = false; + } + + if (isolate_lru_page(page)) { + if (remap) { + migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; + migrate->cpages--; + restore++; + } else { + migrate->src[i] = 0; + unlock_page(page); + migrate->cpages--; + put_page(page); + } + continue; + } + + /* Drop the reference we took in collect */ + put_page(page); + } + + if (!migrate_vma_check_page(page)) { + if (remap) { + migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; + migrate->cpages--; + restore++; + + if (!is_zone_device_page(page)) { + get_page(page); + putback_lru_page(page); + } + } else { + migrate->src[i] = 0; + unlock_page(page); + migrate->cpages--; + + if (!is_zone_device_page(page)) + putback_lru_page(page); + else + put_page(page); + } + } + } + + for (i = 0, addr = start; i < npages && restore; i++, addr += PAGE_SIZE) { + struct page *page = migrate_pfn_to_page(migrate->src[i]); + + if (!page || (migrate->src[i] & MIGRATE_PFN_MIGRATE)) + continue; + + remove_migration_pte(page, migrate->vma, addr, page); + + migrate->src[i] = 0; + unlock_page(page); + put_page(page); + restore--; + } +} + +/* + * migrate_vma_unmap() - replace page mapping with special migration pte entry + * @migrate: migrate struct containing all migration information + * + * Replace page mapping (CPU page table pte) with a special migration pte entry + * and check again if it has been pinned. Pinned pages are restored because we + * cannot migrate them. + * + * This is the last step before we call the device driver callback to allocate + * destination memory and copy contents of original page over to new page. + */ +static void migrate_vma_unmap(struct migrate_vma *migrate) +{ + int flags = TTU_MIGRATION | TTU_IGNORE_MLOCK; + const unsigned long npages = migrate->npages; + const unsigned long start = migrate->start; + unsigned long addr, i, restore = 0; + + for (i = 0; i < npages; i++) { + struct page *page = migrate_pfn_to_page(migrate->src[i]); + + if (!page || !(migrate->src[i] & MIGRATE_PFN_MIGRATE)) + continue; + + if (page_mapped(page)) { + try_to_unmap(page, flags); + if (page_mapped(page)) + goto restore; + } + + if (migrate_vma_check_page(page)) + continue; + +restore: + migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; + migrate->cpages--; + restore++; + } + + for (addr = start, i = 0; i < npages && restore; addr += PAGE_SIZE, i++) { + struct page *page = migrate_pfn_to_page(migrate->src[i]); + + if (!page || (migrate->src[i] & MIGRATE_PFN_MIGRATE)) + continue; + + remove_migration_ptes(page, page, false); + + migrate->src[i] = 0; + unlock_page(page); + restore--; + + if (is_zone_device_page(page)) + put_page(page); + else + putback_lru_page(page); + } +} + +/** + * migrate_vma_setup() - prepare to migrate a range of memory + * @args: contains the vma, start, and pfns arrays for the migration + * + * Returns: negative errno on failures, 0 when 0 or more pages were migrated + * without an error. + * + * Prepare to migrate a range of memory virtual address range by collecting all + * the pages backing each virtual address in the range, saving them inside the + * src array. Then lock those pages and unmap them. Once the pages are locked + * and unmapped, check whether each page is pinned or not. Pages that aren't + * pinned have the MIGRATE_PFN_MIGRATE flag set (by this function) in the + * corresponding src array entry. Then restores any pages that are pinned, by + * remapping and unlocking those pages. + * + * The caller should then allocate destination memory and copy source memory to + * it for all those entries (ie with MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE + * flag set). Once these are allocated and copied, the caller must update each + * corresponding entry in the dst array with the pfn value of the destination + * page and with the MIGRATE_PFN_VALID and MIGRATE_PFN_LOCKED flags set + * (destination pages must have their struct pages locked, via lock_page()). + * + * Note that the caller does not have to migrate all the pages that are marked + * with MIGRATE_PFN_MIGRATE flag in src array unless this is a migration from + * device memory to system memory. If the caller cannot migrate a device page + * back to system memory, then it must return VM_FAULT_SIGBUS, which has severe + * consequences for the userspace process, so it must be avoided if at all + * possible. + * + * For empty entries inside CPU page table (pte_none() or pmd_none() is true) we + * do set MIGRATE_PFN_MIGRATE flag inside the corresponding source array thus + * allowing the caller to allocate device memory for those unback virtual + * address. For this the caller simply has to allocate device memory and + * properly set the destination entry like for regular migration. Note that + * this can still fails and thus inside the device driver must check if the + * migration was successful for those entries after calling migrate_vma_pages() + * just like for regular migration. + * + * After that, the callers must call migrate_vma_pages() to go over each entry + * in the src array that has the MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE flag + * set. If the corresponding entry in dst array has MIGRATE_PFN_VALID flag set, + * then migrate_vma_pages() to migrate struct page information from the source + * struct page to the destination struct page. If it fails to migrate the + * struct page information, then it clears the MIGRATE_PFN_MIGRATE flag in the + * src array. + * + * At this point all successfully migrated pages have an entry in the src + * array with MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE flag set and the dst + * array entry with MIGRATE_PFN_VALID flag set. + * + * Once migrate_vma_pages() returns the caller may inspect which pages were + * successfully migrated, and which were not. Successfully migrated pages will + * have the MIGRATE_PFN_MIGRATE flag set for their src array entry. + * + * It is safe to update device page table after migrate_vma_pages() because + * both destination and source page are still locked, and the mmap_lock is held + * in read mode (hence no one can unmap the range being migrated). + * + * Once the caller is done cleaning up things and updating its page table (if it + * chose to do so, this is not an obligation) it finally calls + * migrate_vma_finalize() to update the CPU page table to point to new pages + * for successfully migrated pages or otherwise restore the CPU page table to + * point to the original source pages. + */ +int migrate_vma_setup(struct migrate_vma *args) +{ + long nr_pages = (args->end - args->start) >> PAGE_SHIFT; + + args->start &= PAGE_MASK; + args->end &= PAGE_MASK; + if (!args->vma || is_vm_hugetlb_page(args->vma) || + (args->vma->vm_flags & VM_SPECIAL) || vma_is_dax(args->vma)) + return -EINVAL; + if (nr_pages <= 0) + return -EINVAL; + if (args->start < args->vma->vm_start || + args->start >= args->vma->vm_end) + return -EINVAL; + if (args->end <= args->vma->vm_start || args->end > args->vma->vm_end) + return -EINVAL; + if (!args->src || !args->dst) + return -EINVAL; + + memset(args->src, 0, sizeof(*args->src) * nr_pages); + args->cpages = 0; + args->npages = 0; + + migrate_vma_collect(args); + + if (args->cpages) + migrate_vma_prepare(args); + if (args->cpages) + migrate_vma_unmap(args); + + /* + * At this point pages are locked and unmapped, and thus they have + * stable content and can safely be copied to destination memory that + * is allocated by the drivers. + */ + return 0; + +} +EXPORT_SYMBOL(migrate_vma_setup); + +/* + * This code closely matches the code in: + * __handle_mm_fault() + * handle_pte_fault() + * do_anonymous_page() + * to map in an anonymous zero page but the struct page will be a ZONE_DEVICE + * private page. + */ +static void migrate_vma_insert_page(struct migrate_vma *migrate, + unsigned long addr, + struct page *page, + unsigned long *src, + unsigned long *dst) +{ + struct vm_area_struct *vma = migrate->vma; + struct mm_struct *mm = vma->vm_mm; + bool flush = false; + spinlock_t *ptl; + pte_t entry; + pgd_t *pgdp; + p4d_t *p4dp; + pud_t *pudp; + pmd_t *pmdp; + pte_t *ptep; + + /* Only allow populating anonymous memory */ + if (!vma_is_anonymous(vma)) + goto abort; + + pgdp = pgd_offset(mm, addr); + p4dp = p4d_alloc(mm, pgdp, addr); + if (!p4dp) + goto abort; + pudp = pud_alloc(mm, p4dp, addr); + if (!pudp) + goto abort; + pmdp = pmd_alloc(mm, pudp, addr); + if (!pmdp) + goto abort; + + if (pmd_trans_huge(*pmdp) || pmd_devmap(*pmdp)) + goto abort; + + /* + * Use pte_alloc() instead of pte_alloc_map(). We can't run + * pte_offset_map() on pmds where a huge pmd might be created + * from a different thread. + * + * pte_alloc_map() is safe to use under mmap_write_lock(mm) or when + * parallel threads are excluded by other means. + * + * Here we only have mmap_read_lock(mm). + */ + if (pte_alloc(mm, pmdp)) + goto abort; + + /* See the comment in pte_alloc_one_map() */ + if (unlikely(pmd_trans_unstable(pmdp))) + goto abort; + + if (unlikely(anon_vma_prepare(vma))) + goto abort; + if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL)) + goto abort; + + /* + * The memory barrier inside __SetPageUptodate makes sure that + * preceding stores to the page contents become visible before + * the set_pte_at() write. + */ + __SetPageUptodate(page); + + if (is_zone_device_page(page)) { + if (is_device_private_page(page)) { + swp_entry_t swp_entry; + + swp_entry = make_device_private_entry(page, vma->vm_flags & VM_WRITE); + entry = swp_entry_to_pte(swp_entry); + } else { + /* + * For now we only support migrating to un-addressable + * device memory. + */ + pr_warn_once("Unsupported ZONE_DEVICE page type.\n"); + goto abort; + } + } else { + entry = mk_pte(page, vma->vm_page_prot); + if (vma->vm_flags & VM_WRITE) + entry = pte_mkwrite(pte_mkdirty(entry)); + } + + ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl); + + if (check_stable_address_space(mm)) + goto unlock_abort; + + if (pte_present(*ptep)) { + unsigned long pfn = pte_pfn(*ptep); + + if (!is_zero_pfn(pfn)) + goto unlock_abort; + flush = true; + } else if (!pte_none(*ptep)) + goto unlock_abort; + + /* + * Check for userfaultfd but do not deliver the fault. Instead, + * just back off. + */ + if (userfaultfd_missing(vma)) + goto unlock_abort; + + inc_mm_counter(mm, MM_ANONPAGES); + page_add_new_anon_rmap(page, vma, addr, false); + if (!is_zone_device_page(page)) + lru_cache_add_inactive_or_unevictable(page, vma); + get_page(page); + + if (flush) { + flush_cache_page(vma, addr, pte_pfn(*ptep)); + ptep_clear_flush_notify(vma, addr, ptep); + set_pte_at_notify(mm, addr, ptep, entry); + update_mmu_cache(vma, addr, ptep); + } else { + /* No need to invalidate - it was non-present before */ + set_pte_at(mm, addr, ptep, entry); + update_mmu_cache(vma, addr, ptep); + } + + pte_unmap_unlock(ptep, ptl); + *src = MIGRATE_PFN_MIGRATE; + return; + +unlock_abort: + pte_unmap_unlock(ptep, ptl); +abort: + *src &= ~MIGRATE_PFN_MIGRATE; +} + +/** + * migrate_vma_pages() - migrate meta-data from src page to dst page + * @migrate: migrate struct containing all migration information + * + * This migrates struct page meta-data from source struct page to destination + * struct page. This effectively finishes the migration from source page to the + * destination page. + */ +void migrate_vma_pages(struct migrate_vma *migrate) +{ + const unsigned long npages = migrate->npages; + const unsigned long start = migrate->start; + struct mmu_notifier_range range; + unsigned long addr, i; + bool notified = false; + + for (i = 0, addr = start; i < npages; addr += PAGE_SIZE, i++) { + struct page *newpage = migrate_pfn_to_page(migrate->dst[i]); + struct page *page = migrate_pfn_to_page(migrate->src[i]); + struct address_space *mapping; + int r; + + if (!newpage) { + migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; + continue; + } + + if (!page) { + if (!(migrate->src[i] & MIGRATE_PFN_MIGRATE)) + continue; + if (!notified) { + notified = true; + + mmu_notifier_range_init(&range, + MMU_NOTIFY_CLEAR, 0, + NULL, + migrate->vma->vm_mm, + addr, migrate->end); + mmu_notifier_invalidate_range_start(&range); + } + migrate_vma_insert_page(migrate, addr, newpage, + &migrate->src[i], + &migrate->dst[i]); + continue; + } + + mapping = page_mapping(page); + + if (is_zone_device_page(newpage)) { + if (is_device_private_page(newpage)) { + /* + * For now only support private anonymous when + * migrating to un-addressable device memory. + */ + if (mapping) { + migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; + continue; + } + } else { + /* + * Other types of ZONE_DEVICE page are not + * supported. + */ + migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; + continue; + } + } + + r = migrate_page(mapping, newpage, page, MIGRATE_SYNC_NO_COPY); + if (r != MIGRATEPAGE_SUCCESS) + migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; + } + + /* + * No need to double call mmu_notifier->invalidate_range() callback as + * the above ptep_clear_flush_notify() inside migrate_vma_insert_page() + * did already call it. + */ + if (notified) + mmu_notifier_invalidate_range_only_end(&range); +} +EXPORT_SYMBOL(migrate_vma_pages); + +/** + * migrate_vma_finalize() - restore CPU page table entry + * @migrate: migrate struct containing all migration information + * + * This replaces the special migration pte entry with either a mapping to the + * new page if migration was successful for that page, or to the original page + * otherwise. + * + * This also unlocks the pages and puts them back on the lru, or drops the extra + * refcount, for device pages. + */ +void migrate_vma_finalize(struct migrate_vma *migrate) +{ + const unsigned long npages = migrate->npages; + unsigned long i; + + for (i = 0; i < npages; i++) { + struct page *newpage = migrate_pfn_to_page(migrate->dst[i]); + struct page *page = migrate_pfn_to_page(migrate->src[i]); + + if (!page) { + if (newpage) { + unlock_page(newpage); + put_page(newpage); + } + continue; + } + + if (!(migrate->src[i] & MIGRATE_PFN_MIGRATE) || !newpage) { + if (newpage) { + unlock_page(newpage); + put_page(newpage); + } + newpage = page; + } + + remove_migration_ptes(page, newpage, false); + unlock_page(page); + + if (is_zone_device_page(page)) + put_page(page); + else + putback_lru_page(page); + + if (newpage != page) { + unlock_page(newpage); + if (is_zone_device_page(newpage)) + put_page(newpage); + else + putback_lru_page(newpage); + } + } +} +EXPORT_SYMBOL(migrate_vma_finalize); +#endif /* CONFIG_DEVICE_PRIVATE */ diff --git a/mm/mincore.c b/mm/mincore.c new file mode 100644 index 000000000..02db1a834 --- /dev/null +++ b/mm/mincore.c @@ -0,0 +1,280 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/mm/mincore.c + * + * Copyright (C) 1994-2006 Linus Torvalds + */ + +/* + * The mincore() system call. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +static int mincore_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr, + unsigned long end, struct mm_walk *walk) +{ +#ifdef CONFIG_HUGETLB_PAGE + unsigned char present; + unsigned char *vec = walk->private; + + /* + * Hugepages under user process are always in RAM and never + * swapped out, but theoretically it needs to be checked. + */ + present = pte && !huge_pte_none(huge_ptep_get(pte)); + for (; addr != end; vec++, addr += PAGE_SIZE) + *vec = present; + walk->private = vec; +#else + BUG(); +#endif + return 0; +} + +/* + * Later we can get more picky about what "in core" means precisely. + * For now, simply check to see if the page is in the page cache, + * and is up to date; i.e. that no page-in operation would be required + * at this time if an application were to map and access this page. + */ +static unsigned char mincore_page(struct address_space *mapping, pgoff_t index) +{ + unsigned char present = 0; + struct page *page; + + /* + * When tmpfs swaps out a page from a file, any process mapping that + * file will not get a swp_entry_t in its pte, but rather it is like + * any other file mapping (ie. marked !present and faulted in with + * tmpfs's .fault). So swapped out tmpfs mappings are tested here. + */ + page = find_get_incore_page(mapping, index); + if (page) { + present = PageUptodate(page); + put_page(page); + } + + return present; +} + +static int __mincore_unmapped_range(unsigned long addr, unsigned long end, + struct vm_area_struct *vma, unsigned char *vec) +{ + unsigned long nr = (end - addr) >> PAGE_SHIFT; + int i; + + if (vma->vm_file) { + pgoff_t pgoff; + + pgoff = linear_page_index(vma, addr); + for (i = 0; i < nr; i++, pgoff++) + vec[i] = mincore_page(vma->vm_file->f_mapping, pgoff); + } else { + for (i = 0; i < nr; i++) + vec[i] = 0; + } + return nr; +} + +static int mincore_unmapped_range(unsigned long addr, unsigned long end, + __always_unused int depth, + struct mm_walk *walk) +{ + walk->private += __mincore_unmapped_range(addr, end, + walk->vma, walk->private); + return 0; +} + +static int mincore_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + spinlock_t *ptl; + struct vm_area_struct *vma = walk->vma; + pte_t *ptep; + unsigned char *vec = walk->private; + int nr = (end - addr) >> PAGE_SHIFT; + + ptl = pmd_trans_huge_lock(pmd, vma); + if (ptl) { + memset(vec, 1, nr); + spin_unlock(ptl); + goto out; + } + + if (pmd_trans_unstable(pmd)) { + __mincore_unmapped_range(addr, end, vma, vec); + goto out; + } + + ptep = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); + for (; addr != end; ptep++, addr += PAGE_SIZE) { + pte_t pte = *ptep; + + if (pte_none(pte)) + __mincore_unmapped_range(addr, addr + PAGE_SIZE, + vma, vec); + else if (pte_present(pte)) + *vec = 1; + else { /* pte is a swap entry */ + swp_entry_t entry = pte_to_swp_entry(pte); + + if (non_swap_entry(entry)) { + /* + * migration or hwpoison entries are always + * uptodate + */ + *vec = 1; + } else { +#ifdef CONFIG_SWAP + *vec = mincore_page(swap_address_space(entry), + swp_offset(entry)); +#else + WARN_ON(1); + *vec = 1; +#endif + } + } + vec++; + } + pte_unmap_unlock(ptep - 1, ptl); +out: + walk->private += nr; + cond_resched(); + return 0; +} + +static inline bool can_do_mincore(struct vm_area_struct *vma) +{ + if (vma_is_anonymous(vma)) + return true; + if (!vma->vm_file) + return false; + /* + * Reveal pagecache information only for non-anonymous mappings that + * correspond to the files the calling process could (if tried) open + * for writing; otherwise we'd be including shared non-exclusive + * mappings, which opens a side channel. + */ + return inode_owner_or_capable(file_inode(vma->vm_file)) || + inode_permission(file_inode(vma->vm_file), MAY_WRITE) == 0; +} + +static const struct mm_walk_ops mincore_walk_ops = { + .pmd_entry = mincore_pte_range, + .pte_hole = mincore_unmapped_range, + .hugetlb_entry = mincore_hugetlb, +}; + +/* + * Do a chunk of "sys_mincore()". We've already checked + * all the arguments, we hold the mmap semaphore: we should + * just return the amount of info we're asked for. + */ +static long do_mincore(unsigned long addr, unsigned long pages, unsigned char *vec) +{ + struct vm_area_struct *vma; + unsigned long end; + int err; + + vma = find_vma(current->mm, addr); + if (!vma || addr < vma->vm_start) + return -ENOMEM; + end = min(vma->vm_end, addr + (pages << PAGE_SHIFT)); + if (!can_do_mincore(vma)) { + unsigned long pages = DIV_ROUND_UP(end - addr, PAGE_SIZE); + memset(vec, 1, pages); + return pages; + } + err = walk_page_range(vma->vm_mm, addr, end, &mincore_walk_ops, vec); + if (err < 0) + return err; + return (end - addr) >> PAGE_SHIFT; +} + +/* + * The mincore(2) system call. + * + * mincore() returns the memory residency status of the pages in the + * current process's address space specified by [addr, addr + len). + * The status is returned in a vector of bytes. The least significant + * bit of each byte is 1 if the referenced page is in memory, otherwise + * it is zero. + * + * Because the status of a page can change after mincore() checks it + * but before it returns to the application, the returned vector may + * contain stale information. Only locked pages are guaranteed to + * remain in memory. + * + * return values: + * zero - success + * -EFAULT - vec points to an illegal address + * -EINVAL - addr is not a multiple of PAGE_SIZE + * -ENOMEM - Addresses in the range [addr, addr + len] are + * invalid for the address space of this process, or + * specify one or more pages which are not currently + * mapped + * -EAGAIN - A kernel resource was temporarily unavailable. + */ +SYSCALL_DEFINE3(mincore, unsigned long, start, size_t, len, + unsigned char __user *, vec) +{ + long retval; + unsigned long pages; + unsigned char *tmp; + + start = untagged_addr(start); + + /* Check the start address: needs to be page-aligned.. */ + if (start & ~PAGE_MASK) + return -EINVAL; + + /* ..and we need to be passed a valid user-space range */ + if (!access_ok((void __user *) start, len)) + return -ENOMEM; + + /* This also avoids any overflows on PAGE_ALIGN */ + pages = len >> PAGE_SHIFT; + pages += (offset_in_page(len)) != 0; + + if (!access_ok(vec, pages)) + return -EFAULT; + + tmp = (void *) __get_free_page(GFP_USER); + if (!tmp) + return -EAGAIN; + + retval = 0; + while (pages) { + /* + * Do at most PAGE_SIZE entries per iteration, due to + * the temporary buffer size. + */ + mmap_read_lock(current->mm); + retval = do_mincore(start, min(pages, PAGE_SIZE), tmp); + mmap_read_unlock(current->mm); + + if (retval <= 0) + break; + if (copy_to_user(vec, tmp, retval)) { + retval = -EFAULT; + break; + } + pages -= retval; + vec += retval; + start += retval << PAGE_SHIFT; + retval = 0; + } + free_page((unsigned long) tmp); + return retval; +} diff --git a/mm/mlock.c b/mm/mlock.c new file mode 100644 index 000000000..884b1216d --- /dev/null +++ b/mm/mlock.c @@ -0,0 +1,878 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/mm/mlock.c + * + * (C) Copyright 1995 Linus Torvalds + * (C) Copyright 2002 Christoph Hellwig + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "internal.h" + +bool can_do_mlock(void) +{ + if (rlimit(RLIMIT_MEMLOCK) != 0) + return true; + if (capable(CAP_IPC_LOCK)) + return true; + return false; +} +EXPORT_SYMBOL(can_do_mlock); + +/* + * Mlocked pages are marked with PageMlocked() flag for efficient testing + * in vmscan and, possibly, the fault path; and to support semi-accurate + * statistics. + * + * An mlocked page [PageMlocked(page)] is unevictable. As such, it will + * be placed on the LRU "unevictable" list, rather than the [in]active lists. + * The unevictable list is an LRU sibling list to the [in]active lists. + * PageUnevictable is set to indicate the unevictable state. + * + * When lazy mlocking via vmscan, it is important to ensure that the + * vma's VM_LOCKED status is not concurrently being modified, otherwise we + * may have mlocked a page that is being munlocked. So lazy mlock must take + * the mmap_lock for read, and verify that the vma really is locked + * (see mm/rmap.c). + */ + +/* + * LRU accounting for clear_page_mlock() + */ +void clear_page_mlock(struct page *page) +{ + int nr_pages; + + if (!TestClearPageMlocked(page)) + return; + + nr_pages = thp_nr_pages(page); + mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages); + count_vm_events(UNEVICTABLE_PGCLEARED, nr_pages); + /* + * The previous TestClearPageMlocked() corresponds to the smp_mb() + * in __pagevec_lru_add_fn(). + * + * See __pagevec_lru_add_fn for more explanation. + */ + if (!isolate_lru_page(page)) { + putback_lru_page(page); + } else { + /* + * We lost the race. the page already moved to evictable list. + */ + if (PageUnevictable(page)) + count_vm_events(UNEVICTABLE_PGSTRANDED, nr_pages); + } +} + +/* + * Mark page as mlocked if not already. + * If page on LRU, isolate and putback to move to unevictable list. + */ +void mlock_vma_page(struct page *page) +{ + /* Serialize with page migration */ + BUG_ON(!PageLocked(page)); + + VM_BUG_ON_PAGE(PageTail(page), page); + VM_BUG_ON_PAGE(PageCompound(page) && PageDoubleMap(page), page); + + if (!TestSetPageMlocked(page)) { + int nr_pages = thp_nr_pages(page); + + mod_zone_page_state(page_zone(page), NR_MLOCK, nr_pages); + count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages); + if (!isolate_lru_page(page)) + putback_lru_page(page); + } +} + +/* + * Isolate a page from LRU with optional get_page() pin. + * Assumes lru_lock already held and page already pinned. + */ +static bool __munlock_isolate_lru_page(struct page *page, bool getpage) +{ + if (PageLRU(page)) { + struct lruvec *lruvec; + + lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page)); + if (getpage) + get_page(page); + ClearPageLRU(page); + del_page_from_lru_list(page, lruvec, page_lru(page)); + return true; + } + + return false; +} + +/* + * Finish munlock after successful page isolation + * + * Page must be locked. This is a wrapper for try_to_munlock() + * and putback_lru_page() with munlock accounting. + */ +static void __munlock_isolated_page(struct page *page) +{ + /* + * Optimization: if the page was mapped just once, that's our mapping + * and we don't need to check all the other vmas. + */ + if (page_mapcount(page) > 1) + try_to_munlock(page); + + /* Did try_to_unlock() succeed or punt? */ + if (!PageMlocked(page)) + count_vm_events(UNEVICTABLE_PGMUNLOCKED, thp_nr_pages(page)); + + putback_lru_page(page); +} + +/* + * Accounting for page isolation fail during munlock + * + * Performs accounting when page isolation fails in munlock. There is nothing + * else to do because it means some other task has already removed the page + * from the LRU. putback_lru_page() will take care of removing the page from + * the unevictable list, if necessary. vmscan [page_referenced()] will move + * the page back to the unevictable list if some other vma has it mlocked. + */ +static void __munlock_isolation_failed(struct page *page) +{ + int nr_pages = thp_nr_pages(page); + + if (PageUnevictable(page)) + __count_vm_events(UNEVICTABLE_PGSTRANDED, nr_pages); + else + __count_vm_events(UNEVICTABLE_PGMUNLOCKED, nr_pages); +} + +/** + * munlock_vma_page - munlock a vma page + * @page: page to be unlocked, either a normal page or THP page head + * + * returns the size of the page as a page mask (0 for normal page, + * HPAGE_PMD_NR - 1 for THP head page) + * + * called from munlock()/munmap() path with page supposedly on the LRU. + * When we munlock a page, because the vma where we found the page is being + * munlock()ed or munmap()ed, we want to check whether other vmas hold the + * page locked so that we can leave it on the unevictable lru list and not + * bother vmscan with it. However, to walk the page's rmap list in + * try_to_munlock() we must isolate the page from the LRU. If some other + * task has removed the page from the LRU, we won't be able to do that. + * So we clear the PageMlocked as we might not get another chance. If we + * can't isolate the page, we leave it for putback_lru_page() and vmscan + * [page_referenced()/try_to_unmap()] to deal with. + */ +unsigned int munlock_vma_page(struct page *page) +{ + int nr_pages; + pg_data_t *pgdat = page_pgdat(page); + + /* For try_to_munlock() and to serialize with page migration */ + BUG_ON(!PageLocked(page)); + + VM_BUG_ON_PAGE(PageTail(page), page); + + /* + * Serialize with any parallel __split_huge_page_refcount() which + * might otherwise copy PageMlocked to part of the tail pages before + * we clear it in the head page. It also stabilizes thp_nr_pages(). + */ + spin_lock_irq(&pgdat->lru_lock); + + if (!TestClearPageMlocked(page)) { + /* Potentially, PTE-mapped THP: do not skip the rest PTEs */ + nr_pages = 1; + goto unlock_out; + } + + nr_pages = thp_nr_pages(page); + __mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages); + + if (__munlock_isolate_lru_page(page, true)) { + spin_unlock_irq(&pgdat->lru_lock); + __munlock_isolated_page(page); + goto out; + } + __munlock_isolation_failed(page); + +unlock_out: + spin_unlock_irq(&pgdat->lru_lock); + +out: + return nr_pages - 1; +} + +/* + * convert get_user_pages() return value to posix mlock() error + */ +static int __mlock_posix_error_return(long retval) +{ + if (retval == -EFAULT) + retval = -ENOMEM; + else if (retval == -ENOMEM) + retval = -EAGAIN; + return retval; +} + +/* + * Prepare page for fast batched LRU putback via putback_lru_evictable_pagevec() + * + * The fast path is available only for evictable pages with single mapping. + * Then we can bypass the per-cpu pvec and get better performance. + * when mapcount > 1 we need try_to_munlock() which can fail. + * when !page_evictable(), we need the full redo logic of putback_lru_page to + * avoid leaving evictable page in unevictable list. + * + * In case of success, @page is added to @pvec and @pgrescued is incremented + * in case that the page was previously unevictable. @page is also unlocked. + */ +static bool __putback_lru_fast_prepare(struct page *page, struct pagevec *pvec, + int *pgrescued) +{ + VM_BUG_ON_PAGE(PageLRU(page), page); + VM_BUG_ON_PAGE(!PageLocked(page), page); + + if (page_mapcount(page) <= 1 && page_evictable(page)) { + pagevec_add(pvec, page); + if (TestClearPageUnevictable(page)) + (*pgrescued)++; + unlock_page(page); + return true; + } + + return false; +} + +/* + * Putback multiple evictable pages to the LRU + * + * Batched putback of evictable pages that bypasses the per-cpu pvec. Some of + * the pages might have meanwhile become unevictable but that is OK. + */ +static void __putback_lru_fast(struct pagevec *pvec, int pgrescued) +{ + count_vm_events(UNEVICTABLE_PGMUNLOCKED, pagevec_count(pvec)); + /* + *__pagevec_lru_add() calls release_pages() so we don't call + * put_page() explicitly + */ + __pagevec_lru_add(pvec); + count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued); +} + +/* + * Munlock a batch of pages from the same zone + * + * The work is split to two main phases. First phase clears the Mlocked flag + * and attempts to isolate the pages, all under a single zone lru lock. + * The second phase finishes the munlock only for pages where isolation + * succeeded. + * + * Note that the pagevec may be modified during the process. + */ +static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone) +{ + int i; + int nr = pagevec_count(pvec); + int delta_munlocked = -nr; + struct pagevec pvec_putback; + int pgrescued = 0; + + pagevec_init(&pvec_putback); + + /* Phase 1: page isolation */ + spin_lock_irq(&zone->zone_pgdat->lru_lock); + for (i = 0; i < nr; i++) { + struct page *page = pvec->pages[i]; + + if (TestClearPageMlocked(page)) { + /* + * We already have pin from follow_page_mask() + * so we can spare the get_page() here. + */ + if (__munlock_isolate_lru_page(page, false)) + continue; + else + __munlock_isolation_failed(page); + } else { + delta_munlocked++; + } + + /* + * We won't be munlocking this page in the next phase + * but we still need to release the follow_page_mask() + * pin. We cannot do it under lru_lock however. If it's + * the last pin, __page_cache_release() would deadlock. + */ + pagevec_add(&pvec_putback, pvec->pages[i]); + pvec->pages[i] = NULL; + } + __mod_zone_page_state(zone, NR_MLOCK, delta_munlocked); + spin_unlock_irq(&zone->zone_pgdat->lru_lock); + + /* Now we can release pins of pages that we are not munlocking */ + pagevec_release(&pvec_putback); + + /* Phase 2: page munlock */ + for (i = 0; i < nr; i++) { + struct page *page = pvec->pages[i]; + + if (page) { + lock_page(page); + if (!__putback_lru_fast_prepare(page, &pvec_putback, + &pgrescued)) { + /* + * Slow path. We don't want to lose the last + * pin before unlock_page() + */ + get_page(page); /* for putback_lru_page() */ + __munlock_isolated_page(page); + unlock_page(page); + put_page(page); /* from follow_page_mask() */ + } + } + } + + /* + * Phase 3: page putback for pages that qualified for the fast path + * This will also call put_page() to return pin from follow_page_mask() + */ + if (pagevec_count(&pvec_putback)) + __putback_lru_fast(&pvec_putback, pgrescued); +} + +/* + * Fill up pagevec for __munlock_pagevec using pte walk + * + * The function expects that the struct page corresponding to @start address is + * a non-TPH page already pinned and in the @pvec, and that it belongs to @zone. + * + * The rest of @pvec is filled by subsequent pages within the same pmd and same + * zone, as long as the pte's are present and vm_normal_page() succeeds. These + * pages also get pinned. + * + * Returns the address of the next page that should be scanned. This equals + * @start + PAGE_SIZE when no page could be added by the pte walk. + */ +static unsigned long __munlock_pagevec_fill(struct pagevec *pvec, + struct vm_area_struct *vma, struct zone *zone, + unsigned long start, unsigned long end) +{ + pte_t *pte; + spinlock_t *ptl; + + /* + * Initialize pte walk starting at the already pinned page where we + * are sure that there is a pte, as it was pinned under the same + * mmap_lock write op. + */ + pte = get_locked_pte(vma->vm_mm, start, &ptl); + /* Make sure we do not cross the page table boundary */ + end = pgd_addr_end(start, end); + end = p4d_addr_end(start, end); + end = pud_addr_end(start, end); + end = pmd_addr_end(start, end); + + /* The page next to the pinned page is the first we will try to get */ + start += PAGE_SIZE; + while (start < end) { + struct page *page = NULL; + pte++; + if (pte_present(*pte)) + page = vm_normal_page(vma, start, *pte); + /* + * Break if page could not be obtained or the page's node+zone does not + * match + */ + if (!page || page_zone(page) != zone) + break; + + /* + * Do not use pagevec for PTE-mapped THP, + * munlock_vma_pages_range() will handle them. + */ + if (PageTransCompound(page)) + break; + + get_page(page); + /* + * Increase the address that will be returned *before* the + * eventual break due to pvec becoming full by adding the page + */ + start += PAGE_SIZE; + if (pagevec_add(pvec, page) == 0) + break; + } + pte_unmap_unlock(pte, ptl); + return start; +} + +/* + * munlock_vma_pages_range() - munlock all pages in the vma range.' + * @vma - vma containing range to be munlock()ed. + * @start - start address in @vma of the range + * @end - end of range in @vma. + * + * For mremap(), munmap() and exit(). + * + * Called with @vma VM_LOCKED. + * + * Returns with VM_LOCKED cleared. Callers must be prepared to + * deal with this. + * + * We don't save and restore VM_LOCKED here because pages are + * still on lru. In unmap path, pages might be scanned by reclaim + * and re-mlocked by try_to_{munlock|unmap} before we unmap and + * free them. This will result in freeing mlocked pages. + */ +void munlock_vma_pages_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + vma->vm_flags &= VM_LOCKED_CLEAR_MASK; + + while (start < end) { + struct page *page; + unsigned int page_mask = 0; + unsigned long page_increm; + struct pagevec pvec; + struct zone *zone; + + pagevec_init(&pvec); + /* + * Although FOLL_DUMP is intended for get_dump_page(), + * it just so happens that its special treatment of the + * ZERO_PAGE (returning an error instead of doing get_page) + * suits munlock very well (and if somehow an abnormal page + * has sneaked into the range, we won't oops here: great). + */ + page = follow_page(vma, start, FOLL_GET | FOLL_DUMP); + + if (page && !IS_ERR(page)) { + if (PageTransTail(page)) { + VM_BUG_ON_PAGE(PageMlocked(page), page); + put_page(page); /* follow_page_mask() */ + } else if (PageTransHuge(page)) { + lock_page(page); + /* + * Any THP page found by follow_page_mask() may + * have gotten split before reaching + * munlock_vma_page(), so we need to compute + * the page_mask here instead. + */ + page_mask = munlock_vma_page(page); + unlock_page(page); + put_page(page); /* follow_page_mask() */ + } else { + /* + * Non-huge pages are handled in batches via + * pagevec. The pin from follow_page_mask() + * prevents them from collapsing by THP. + */ + pagevec_add(&pvec, page); + zone = page_zone(page); + + /* + * Try to fill the rest of pagevec using fast + * pte walk. This will also update start to + * the next page to process. Then munlock the + * pagevec. + */ + start = __munlock_pagevec_fill(&pvec, vma, + zone, start, end); + __munlock_pagevec(&pvec, zone); + goto next; + } + } + page_increm = 1 + page_mask; + start += page_increm * PAGE_SIZE; +next: + cond_resched(); + } +} + +/* + * mlock_fixup - handle mlock[all]/munlock[all] requests. + * + * Filters out "special" vmas -- VM_LOCKED never gets set for these, and + * munlock is a no-op. However, for some special vmas, we go ahead and + * populate the ptes. + * + * For vmas that pass the filters, merge/split as appropriate. + */ +static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev, + unsigned long start, unsigned long end, vm_flags_t newflags) +{ + struct mm_struct *mm = vma->vm_mm; + pgoff_t pgoff; + int nr_pages; + int ret = 0; + int lock = !!(newflags & VM_LOCKED); + vm_flags_t old_flags = vma->vm_flags; + + if (newflags == vma->vm_flags || (vma->vm_flags & VM_SPECIAL) || + is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm) || + vma_is_dax(vma)) + /* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */ + goto out; + + pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); + *prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma, + vma->vm_file, pgoff, vma_policy(vma), + vma->vm_userfaultfd_ctx); + if (*prev) { + vma = *prev; + goto success; + } + + if (start != vma->vm_start) { + ret = split_vma(mm, vma, start, 1); + if (ret) + goto out; + } + + if (end != vma->vm_end) { + ret = split_vma(mm, vma, end, 0); + if (ret) + goto out; + } + +success: + /* + * Keep track of amount of locked VM. + */ + nr_pages = (end - start) >> PAGE_SHIFT; + if (!lock) + nr_pages = -nr_pages; + else if (old_flags & VM_LOCKED) + nr_pages = 0; + mm->locked_vm += nr_pages; + + /* + * vm_flags is protected by the mmap_lock held in write mode. + * It's okay if try_to_unmap_one unmaps a page just after we + * set VM_LOCKED, populate_vma_page_range will bring it back. + */ + + if (lock) + vma->vm_flags = newflags; + else + munlock_vma_pages_range(vma, start, end); + +out: + *prev = vma; + return ret; +} + +static int apply_vma_lock_flags(unsigned long start, size_t len, + vm_flags_t flags) +{ + unsigned long nstart, end, tmp; + struct vm_area_struct * vma, * prev; + int error; + + VM_BUG_ON(offset_in_page(start)); + VM_BUG_ON(len != PAGE_ALIGN(len)); + end = start + len; + if (end < start) + return -EINVAL; + if (end == start) + return 0; + vma = find_vma(current->mm, start); + if (!vma || vma->vm_start > start) + return -ENOMEM; + + prev = vma->vm_prev; + if (start > vma->vm_start) + prev = vma; + + for (nstart = start ; ; ) { + vm_flags_t newflags = vma->vm_flags & VM_LOCKED_CLEAR_MASK; + + newflags |= flags; + + /* Here we know that vma->vm_start <= nstart < vma->vm_end. */ + tmp = vma->vm_end; + if (tmp > end) + tmp = end; + error = mlock_fixup(vma, &prev, nstart, tmp, newflags); + if (error) + break; + nstart = tmp; + if (nstart < prev->vm_end) + nstart = prev->vm_end; + if (nstart >= end) + break; + + vma = prev->vm_next; + if (!vma || vma->vm_start != nstart) { + error = -ENOMEM; + break; + } + } + return error; +} + +/* + * Go through vma areas and sum size of mlocked + * vma pages, as return value. + * Note deferred memory locking case(mlock2(,,MLOCK_ONFAULT) + * is also counted. + * Return value: previously mlocked page counts + */ +static unsigned long count_mm_mlocked_page_nr(struct mm_struct *mm, + unsigned long start, size_t len) +{ + struct vm_area_struct *vma; + unsigned long count = 0; + + if (mm == NULL) + mm = current->mm; + + vma = find_vma(mm, start); + if (vma == NULL) + vma = mm->mmap; + + for (; vma ; vma = vma->vm_next) { + if (start >= vma->vm_end) + continue; + if (start + len <= vma->vm_start) + break; + if (vma->vm_flags & VM_LOCKED) { + if (start > vma->vm_start) + count -= (start - vma->vm_start); + if (start + len < vma->vm_end) { + count += start + len - vma->vm_start; + break; + } + count += vma->vm_end - vma->vm_start; + } + } + + return count >> PAGE_SHIFT; +} + +static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t flags) +{ + unsigned long locked; + unsigned long lock_limit; + int error = -ENOMEM; + + start = untagged_addr(start); + + if (!can_do_mlock()) + return -EPERM; + + len = PAGE_ALIGN(len + (offset_in_page(start))); + start &= PAGE_MASK; + + lock_limit = rlimit(RLIMIT_MEMLOCK); + lock_limit >>= PAGE_SHIFT; + locked = len >> PAGE_SHIFT; + + if (mmap_write_lock_killable(current->mm)) + return -EINTR; + + locked += current->mm->locked_vm; + if ((locked > lock_limit) && (!capable(CAP_IPC_LOCK))) { + /* + * It is possible that the regions requested intersect with + * previously mlocked areas, that part area in "mm->locked_vm" + * should not be counted to new mlock increment count. So check + * and adjust locked count if necessary. + */ + locked -= count_mm_mlocked_page_nr(current->mm, + start, len); + } + + /* check against resource limits */ + if ((locked <= lock_limit) || capable(CAP_IPC_LOCK)) + error = apply_vma_lock_flags(start, len, flags); + + mmap_write_unlock(current->mm); + if (error) + return error; + + error = __mm_populate(start, len, 0); + if (error) + return __mlock_posix_error_return(error); + return 0; +} + +SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len) +{ + return do_mlock(start, len, VM_LOCKED); +} + +SYSCALL_DEFINE3(mlock2, unsigned long, start, size_t, len, int, flags) +{ + vm_flags_t vm_flags = VM_LOCKED; + + if (flags & ~MLOCK_ONFAULT) + return -EINVAL; + + if (flags & MLOCK_ONFAULT) + vm_flags |= VM_LOCKONFAULT; + + return do_mlock(start, len, vm_flags); +} + +SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len) +{ + int ret; + + start = untagged_addr(start); + + len = PAGE_ALIGN(len + (offset_in_page(start))); + start &= PAGE_MASK; + + if (mmap_write_lock_killable(current->mm)) + return -EINTR; + ret = apply_vma_lock_flags(start, len, 0); + mmap_write_unlock(current->mm); + + return ret; +} + +/* + * Take the MCL_* flags passed into mlockall (or 0 if called from munlockall) + * and translate into the appropriate modifications to mm->def_flags and/or the + * flags for all current VMAs. + * + * There are a couple of subtleties with this. If mlockall() is called multiple + * times with different flags, the values do not necessarily stack. If mlockall + * is called once including the MCL_FUTURE flag and then a second time without + * it, VM_LOCKED and VM_LOCKONFAULT will be cleared from mm->def_flags. + */ +static int apply_mlockall_flags(int flags) +{ + struct vm_area_struct * vma, * prev = NULL; + vm_flags_t to_add = 0; + + current->mm->def_flags &= VM_LOCKED_CLEAR_MASK; + if (flags & MCL_FUTURE) { + current->mm->def_flags |= VM_LOCKED; + + if (flags & MCL_ONFAULT) + current->mm->def_flags |= VM_LOCKONFAULT; + + if (!(flags & MCL_CURRENT)) + goto out; + } + + if (flags & MCL_CURRENT) { + to_add |= VM_LOCKED; + if (flags & MCL_ONFAULT) + to_add |= VM_LOCKONFAULT; + } + + for (vma = current->mm->mmap; vma ; vma = prev->vm_next) { + vm_flags_t newflags; + + newflags = vma->vm_flags & VM_LOCKED_CLEAR_MASK; + newflags |= to_add; + + /* Ignore errors */ + mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags); + cond_resched(); + } +out: + return 0; +} + +SYSCALL_DEFINE1(mlockall, int, flags) +{ + unsigned long lock_limit; + int ret; + + if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT)) || + flags == MCL_ONFAULT) + return -EINVAL; + + if (!can_do_mlock()) + return -EPERM; + + lock_limit = rlimit(RLIMIT_MEMLOCK); + lock_limit >>= PAGE_SHIFT; + + if (mmap_write_lock_killable(current->mm)) + return -EINTR; + + ret = -ENOMEM; + if (!(flags & MCL_CURRENT) || (current->mm->total_vm <= lock_limit) || + capable(CAP_IPC_LOCK)) + ret = apply_mlockall_flags(flags); + mmap_write_unlock(current->mm); + if (!ret && (flags & MCL_CURRENT)) + mm_populate(0, TASK_SIZE); + + return ret; +} + +SYSCALL_DEFINE0(munlockall) +{ + int ret; + + if (mmap_write_lock_killable(current->mm)) + return -EINTR; + ret = apply_mlockall_flags(0); + mmap_write_unlock(current->mm); + return ret; +} + +/* + * Objects with different lifetime than processes (SHM_LOCK and SHM_HUGETLB + * shm segments) get accounted against the user_struct instead. + */ +static DEFINE_SPINLOCK(shmlock_user_lock); + +int user_shm_lock(size_t size, struct user_struct *user) +{ + unsigned long lock_limit, locked; + int allowed = 0; + + locked = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; + lock_limit = rlimit(RLIMIT_MEMLOCK); + if (lock_limit == RLIM_INFINITY) + allowed = 1; + lock_limit >>= PAGE_SHIFT; + spin_lock(&shmlock_user_lock); + if (!allowed && + locked + user->locked_shm > lock_limit && !capable(CAP_IPC_LOCK)) + goto out; + get_uid(user); + user->locked_shm += locked; + allowed = 1; +out: + spin_unlock(&shmlock_user_lock); + return allowed; +} + +void user_shm_unlock(size_t size, struct user_struct *user) +{ + spin_lock(&shmlock_user_lock); + user->locked_shm -= (size + PAGE_SIZE - 1) >> PAGE_SHIFT; + spin_unlock(&shmlock_user_lock); + free_uid(user); +} diff --git a/mm/mm_init.c b/mm/mm_init.c new file mode 100644 index 000000000..b06a30fbe --- /dev/null +++ b/mm/mm_init.c @@ -0,0 +1,207 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * mm_init.c - Memory initialisation verification and debugging + * + * Copyright 2008 IBM Corporation, 2008 + * Author Mel Gorman + * + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include "internal.h" + +#ifdef CONFIG_DEBUG_MEMORY_INIT +int __meminitdata mminit_loglevel; + +#ifndef SECTIONS_SHIFT +#define SECTIONS_SHIFT 0 +#endif + +/* The zonelists are simply reported, validation is manual. */ +void __init mminit_verify_zonelist(void) +{ + int nid; + + if (mminit_loglevel < MMINIT_VERIFY) + return; + + for_each_online_node(nid) { + pg_data_t *pgdat = NODE_DATA(nid); + struct zone *zone; + struct zoneref *z; + struct zonelist *zonelist; + int i, listid, zoneid; + + BUILD_BUG_ON(MAX_ZONELISTS > 2); + for (i = 0; i < MAX_ZONELISTS * MAX_NR_ZONES; i++) { + + /* Identify the zone and nodelist */ + zoneid = i % MAX_NR_ZONES; + listid = i / MAX_NR_ZONES; + zonelist = &pgdat->node_zonelists[listid]; + zone = &pgdat->node_zones[zoneid]; + if (!populated_zone(zone)) + continue; + + /* Print information about the zonelist */ + printk(KERN_DEBUG "mminit::zonelist %s %d:%s = ", + listid > 0 ? "thisnode" : "general", nid, + zone->name); + + /* Iterate the zonelist */ + for_each_zone_zonelist(zone, z, zonelist, zoneid) + pr_cont("%d:%s ", zone_to_nid(zone), zone->name); + pr_cont("\n"); + } + } +} + +void __init mminit_verify_pageflags_layout(void) +{ + int shift, width; + unsigned long or_mask, add_mask; + + shift = 8 * sizeof(unsigned long); + width = shift - SECTIONS_WIDTH - NODES_WIDTH - ZONES_WIDTH + - LAST_CPUPID_SHIFT - KASAN_TAG_WIDTH; + mminit_dprintk(MMINIT_TRACE, "pageflags_layout_widths", + "Section %d Node %d Zone %d Lastcpupid %d Kasantag %d Flags %d\n", + SECTIONS_WIDTH, + NODES_WIDTH, + ZONES_WIDTH, + LAST_CPUPID_WIDTH, + KASAN_TAG_WIDTH, + NR_PAGEFLAGS); + mminit_dprintk(MMINIT_TRACE, "pageflags_layout_shifts", + "Section %d Node %d Zone %d Lastcpupid %d Kasantag %d\n", + SECTIONS_SHIFT, + NODES_SHIFT, + ZONES_SHIFT, + LAST_CPUPID_SHIFT, + KASAN_TAG_WIDTH); + mminit_dprintk(MMINIT_TRACE, "pageflags_layout_pgshifts", + "Section %lu Node %lu Zone %lu Lastcpupid %lu Kasantag %lu\n", + (unsigned long)SECTIONS_PGSHIFT, + (unsigned long)NODES_PGSHIFT, + (unsigned long)ZONES_PGSHIFT, + (unsigned long)LAST_CPUPID_PGSHIFT, + (unsigned long)KASAN_TAG_PGSHIFT); + mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodezoneid", + "Node/Zone ID: %lu -> %lu\n", + (unsigned long)(ZONEID_PGOFF + ZONEID_SHIFT), + (unsigned long)ZONEID_PGOFF); + mminit_dprintk(MMINIT_TRACE, "pageflags_layout_usage", + "location: %d -> %d layout %d -> %d unused %d -> %d page-flags\n", + shift, width, width, NR_PAGEFLAGS, NR_PAGEFLAGS, 0); +#ifdef NODE_NOT_IN_PAGE_FLAGS + mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags", + "Node not in page flags"); +#endif +#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS + mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags", + "Last cpupid not in page flags"); +#endif + + if (SECTIONS_WIDTH) { + shift -= SECTIONS_WIDTH; + BUG_ON(shift != SECTIONS_PGSHIFT); + } + if (NODES_WIDTH) { + shift -= NODES_WIDTH; + BUG_ON(shift != NODES_PGSHIFT); + } + if (ZONES_WIDTH) { + shift -= ZONES_WIDTH; + BUG_ON(shift != ZONES_PGSHIFT); + } + + /* Check for bitmask overlaps */ + or_mask = (ZONES_MASK << ZONES_PGSHIFT) | + (NODES_MASK << NODES_PGSHIFT) | + (SECTIONS_MASK << SECTIONS_PGSHIFT); + add_mask = (ZONES_MASK << ZONES_PGSHIFT) + + (NODES_MASK << NODES_PGSHIFT) + + (SECTIONS_MASK << SECTIONS_PGSHIFT); + BUG_ON(or_mask != add_mask); +} + +static __init int set_mminit_loglevel(char *str) +{ + get_option(&str, &mminit_loglevel); + return 0; +} +early_param("mminit_loglevel", set_mminit_loglevel); +#endif /* CONFIG_DEBUG_MEMORY_INIT */ + +struct kobject *mm_kobj; +EXPORT_SYMBOL_GPL(mm_kobj); + +#ifdef CONFIG_SMP +s32 vm_committed_as_batch = 32; + +void mm_compute_batch(int overcommit_policy) +{ + u64 memsized_batch; + s32 nr = num_present_cpus(); + s32 batch = max_t(s32, nr*2, 32); + unsigned long ram_pages = totalram_pages(); + + /* + * For policy OVERCOMMIT_NEVER, set batch size to 0.4% of + * (total memory/#cpus), and lift it to 25% for other policies + * to easy the possible lock contention for percpu_counter + * vm_committed_as, while the max limit is INT_MAX + */ + if (overcommit_policy == OVERCOMMIT_NEVER) + memsized_batch = min_t(u64, ram_pages/nr/256, INT_MAX); + else + memsized_batch = min_t(u64, ram_pages/nr/4, INT_MAX); + + vm_committed_as_batch = max_t(s32, memsized_batch, batch); +} + +static int __meminit mm_compute_batch_notifier(struct notifier_block *self, + unsigned long action, void *arg) +{ + switch (action) { + case MEM_ONLINE: + case MEM_OFFLINE: + mm_compute_batch(sysctl_overcommit_memory); + default: + break; + } + return NOTIFY_OK; +} + +static struct notifier_block compute_batch_nb __meminitdata = { + .notifier_call = mm_compute_batch_notifier, + .priority = IPC_CALLBACK_PRI, /* use lowest priority */ +}; + +static int __init mm_compute_batch_init(void) +{ + mm_compute_batch(sysctl_overcommit_memory); + register_hotmemory_notifier(&compute_batch_nb); + + return 0; +} + +__initcall(mm_compute_batch_init); + +#endif + +static int __init mm_sysfs_init(void) +{ + mm_kobj = kobject_create_and_add("mm", kernel_kobj); + if (!mm_kobj) + return -ENOMEM; + + return 0; +} +postcore_initcall(mm_sysfs_init); diff --git a/mm/mmap.c b/mm/mmap.c new file mode 100644 index 000000000..33ebda838 --- /dev/null +++ b/mm/mmap.c @@ -0,0 +1,3854 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * mm/mmap.c + * + * Written by obz. + * + * Address space accounting code + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +#define CREATE_TRACE_POINTS +#include + +#include "internal.h" + +#ifndef arch_mmap_check +#define arch_mmap_check(addr, len, flags) (0) +#endif + +#ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS +const int mmap_rnd_bits_min = CONFIG_ARCH_MMAP_RND_BITS_MIN; +const int mmap_rnd_bits_max = CONFIG_ARCH_MMAP_RND_BITS_MAX; +int mmap_rnd_bits __read_mostly = CONFIG_ARCH_MMAP_RND_BITS; +#endif +#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS +const int mmap_rnd_compat_bits_min = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MIN; +const int mmap_rnd_compat_bits_max = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX; +int mmap_rnd_compat_bits __read_mostly = CONFIG_ARCH_MMAP_RND_COMPAT_BITS; +#endif + +static bool ignore_rlimit_data; +core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644); + +static void unmap_region(struct mm_struct *mm, + struct vm_area_struct *vma, struct vm_area_struct *prev, + unsigned long start, unsigned long end); + +/* description of effects of mapping type and prot in current implementation. + * this is due to the limited x86 page protection hardware. The expected + * behavior is in parens: + * + * map_type prot + * PROT_NONE PROT_READ PROT_WRITE PROT_EXEC + * MAP_SHARED r: (no) no r: (yes) yes r: (no) yes r: (no) yes + * w: (no) no w: (no) no w: (yes) yes w: (no) no + * x: (no) no x: (no) yes x: (no) yes x: (yes) yes + * + * MAP_PRIVATE r: (no) no r: (yes) yes r: (no) yes r: (no) yes + * w: (no) no w: (no) no w: (copy) copy w: (no) no + * x: (no) no x: (no) yes x: (no) yes x: (yes) yes + */ +pgprot_t protection_map[16] __ro_after_init = { + __P000, __P001, __P010, __P011, __P100, __P101, __P110, __P111, + __S000, __S001, __S010, __S011, __S100, __S101, __S110, __S111 +}; + +#ifndef CONFIG_ARCH_HAS_FILTER_PGPROT +static inline pgprot_t arch_filter_pgprot(pgprot_t prot) +{ + return prot; +} +#endif + +pgprot_t vm_get_page_prot(unsigned long vm_flags) +{ + pgprot_t ret = __pgprot(pgprot_val(protection_map[vm_flags & + (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]) | + pgprot_val(arch_vm_get_page_prot(vm_flags))); + + return arch_filter_pgprot(ret); +} +EXPORT_SYMBOL(vm_get_page_prot); + +static pgprot_t vm_pgprot_modify(pgprot_t oldprot, unsigned long vm_flags) +{ + return pgprot_modify(oldprot, vm_get_page_prot(vm_flags)); +} + +/* Update vma->vm_page_prot to reflect vma->vm_flags. */ +void vma_set_page_prot(struct vm_area_struct *vma) +{ + unsigned long vm_flags = vma->vm_flags; + pgprot_t vm_page_prot; + + vm_page_prot = vm_pgprot_modify(vma->vm_page_prot, vm_flags); + if (vma_wants_writenotify(vma, vm_page_prot)) { + vm_flags &= ~VM_SHARED; + vm_page_prot = vm_pgprot_modify(vm_page_prot, vm_flags); + } + /* remove_protection_ptes reads vma->vm_page_prot without mmap_lock */ + WRITE_ONCE(vma->vm_page_prot, vm_page_prot); +} + +/* + * Requires inode->i_mapping->i_mmap_rwsem + */ +static void __remove_shared_vm_struct(struct vm_area_struct *vma, + struct file *file, struct address_space *mapping) +{ + if (vma->vm_flags & VM_DENYWRITE) + allow_write_access(file); + if (vma->vm_flags & VM_SHARED) + mapping_unmap_writable(mapping); + + flush_dcache_mmap_lock(mapping); + vma_interval_tree_remove(vma, &mapping->i_mmap); + flush_dcache_mmap_unlock(mapping); +} + +/* + * Unlink a file-based vm structure from its interval tree, to hide + * vma from rmap and vmtruncate before freeing its page tables. + */ +void unlink_file_vma(struct vm_area_struct *vma) +{ + struct file *file = vma->vm_file; + + if (file) { + struct address_space *mapping = file->f_mapping; + i_mmap_lock_write(mapping); + __remove_shared_vm_struct(vma, file, mapping); + i_mmap_unlock_write(mapping); + } +} + +/* + * Close a vm structure and free it, returning the next. + */ +static struct vm_area_struct *remove_vma(struct vm_area_struct *vma) +{ + struct vm_area_struct *next = vma->vm_next; + + might_sleep(); + if (vma->vm_ops && vma->vm_ops->close) + vma->vm_ops->close(vma); + if (vma->vm_file) + fput(vma->vm_file); + mpol_put(vma_policy(vma)); + vm_area_free(vma); + return next; +} + +static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long flags, + struct list_head *uf); +SYSCALL_DEFINE1(brk, unsigned long, brk) +{ + unsigned long retval; + unsigned long newbrk, oldbrk, origbrk; + struct mm_struct *mm = current->mm; + struct vm_area_struct *next; + unsigned long min_brk; + bool populate; + bool downgraded = false; + LIST_HEAD(uf); + + if (mmap_write_lock_killable(mm)) + return -EINTR; + + origbrk = mm->brk; + +#ifdef CONFIG_COMPAT_BRK + /* + * CONFIG_COMPAT_BRK can still be overridden by setting + * randomize_va_space to 2, which will still cause mm->start_brk + * to be arbitrarily shifted + */ + if (current->brk_randomized) + min_brk = mm->start_brk; + else + min_brk = mm->end_data; +#else + min_brk = mm->start_brk; +#endif + if (brk < min_brk) + goto out; + + /* + * Check against rlimit here. If this check is done later after the test + * of oldbrk with newbrk then it can escape the test and let the data + * segment grow beyond its set limit the in case where the limit is + * not page aligned -Ram Gupta + */ + if (check_data_rlimit(rlimit(RLIMIT_DATA), brk, mm->start_brk, + mm->end_data, mm->start_data)) + goto out; + + newbrk = PAGE_ALIGN(brk); + oldbrk = PAGE_ALIGN(mm->brk); + if (oldbrk == newbrk) { + mm->brk = brk; + goto success; + } + + /* + * Always allow shrinking brk. + * __do_munmap() may downgrade mmap_lock to read. + */ + if (brk <= mm->brk) { + int ret; + + /* + * mm->brk must to be protected by write mmap_lock so update it + * before downgrading mmap_lock. When __do_munmap() fails, + * mm->brk will be restored from origbrk. + */ + mm->brk = brk; + ret = __do_munmap(mm, newbrk, oldbrk-newbrk, &uf, true); + if (ret < 0) { + mm->brk = origbrk; + goto out; + } else if (ret == 1) { + downgraded = true; + } + goto success; + } + + /* Check against existing mmap mappings. */ + next = find_vma(mm, oldbrk); + if (next && newbrk + PAGE_SIZE > vm_start_gap(next)) + goto out; + + /* Ok, looks good - let it rip. */ + if (do_brk_flags(oldbrk, newbrk-oldbrk, 0, &uf) < 0) + goto out; + mm->brk = brk; + +success: + populate = newbrk > oldbrk && (mm->def_flags & VM_LOCKED) != 0; + if (downgraded) + mmap_read_unlock(mm); + else + mmap_write_unlock(mm); + userfaultfd_unmap_complete(mm, &uf); + if (populate) + mm_populate(oldbrk, newbrk - oldbrk); + return brk; + +out: + retval = origbrk; + mmap_write_unlock(mm); + return retval; +} + +static inline unsigned long vma_compute_gap(struct vm_area_struct *vma) +{ + unsigned long gap, prev_end; + + /* + * Note: in the rare case of a VM_GROWSDOWN above a VM_GROWSUP, we + * allow two stack_guard_gaps between them here, and when choosing + * an unmapped area; whereas when expanding we only require one. + * That's a little inconsistent, but keeps the code here simpler. + */ + gap = vm_start_gap(vma); + if (vma->vm_prev) { + prev_end = vm_end_gap(vma->vm_prev); + if (gap > prev_end) + gap -= prev_end; + else + gap = 0; + } + return gap; +} + +#ifdef CONFIG_DEBUG_VM_RB +static unsigned long vma_compute_subtree_gap(struct vm_area_struct *vma) +{ + unsigned long max = vma_compute_gap(vma), subtree_gap; + if (vma->vm_rb.rb_left) { + subtree_gap = rb_entry(vma->vm_rb.rb_left, + struct vm_area_struct, vm_rb)->rb_subtree_gap; + if (subtree_gap > max) + max = subtree_gap; + } + if (vma->vm_rb.rb_right) { + subtree_gap = rb_entry(vma->vm_rb.rb_right, + struct vm_area_struct, vm_rb)->rb_subtree_gap; + if (subtree_gap > max) + max = subtree_gap; + } + return max; +} + +static int browse_rb(struct mm_struct *mm) +{ + struct rb_root *root = &mm->mm_rb; + int i = 0, j, bug = 0; + struct rb_node *nd, *pn = NULL; + unsigned long prev = 0, pend = 0; + + for (nd = rb_first(root); nd; nd = rb_next(nd)) { + struct vm_area_struct *vma; + vma = rb_entry(nd, struct vm_area_struct, vm_rb); + if (vma->vm_start < prev) { + pr_emerg("vm_start %lx < prev %lx\n", + vma->vm_start, prev); + bug = 1; + } + if (vma->vm_start < pend) { + pr_emerg("vm_start %lx < pend %lx\n", + vma->vm_start, pend); + bug = 1; + } + if (vma->vm_start > vma->vm_end) { + pr_emerg("vm_start %lx > vm_end %lx\n", + vma->vm_start, vma->vm_end); + bug = 1; + } + spin_lock(&mm->page_table_lock); + if (vma->rb_subtree_gap != vma_compute_subtree_gap(vma)) { + pr_emerg("free gap %lx, correct %lx\n", + vma->rb_subtree_gap, + vma_compute_subtree_gap(vma)); + bug = 1; + } + spin_unlock(&mm->page_table_lock); + i++; + pn = nd; + prev = vma->vm_start; + pend = vma->vm_end; + } + j = 0; + for (nd = pn; nd; nd = rb_prev(nd)) + j++; + if (i != j) { + pr_emerg("backwards %d, forwards %d\n", j, i); + bug = 1; + } + return bug ? -1 : i; +} + +static void validate_mm_rb(struct rb_root *root, struct vm_area_struct *ignore) +{ + struct rb_node *nd; + + for (nd = rb_first(root); nd; nd = rb_next(nd)) { + struct vm_area_struct *vma; + vma = rb_entry(nd, struct vm_area_struct, vm_rb); + VM_BUG_ON_VMA(vma != ignore && + vma->rb_subtree_gap != vma_compute_subtree_gap(vma), + vma); + } +} + +static void validate_mm(struct mm_struct *mm) +{ + int bug = 0; + int i = 0; + unsigned long highest_address = 0; + struct vm_area_struct *vma = mm->mmap; + + while (vma) { + struct anon_vma *anon_vma = vma->anon_vma; + struct anon_vma_chain *avc; + + if (anon_vma) { + anon_vma_lock_read(anon_vma); + list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) + anon_vma_interval_tree_verify(avc); + anon_vma_unlock_read(anon_vma); + } + + highest_address = vm_end_gap(vma); + vma = vma->vm_next; + i++; + } + if (i != mm->map_count) { + pr_emerg("map_count %d vm_next %d\n", mm->map_count, i); + bug = 1; + } + if (highest_address != mm->highest_vm_end) { + pr_emerg("mm->highest_vm_end %lx, found %lx\n", + mm->highest_vm_end, highest_address); + bug = 1; + } + i = browse_rb(mm); + if (i != mm->map_count) { + if (i != -1) + pr_emerg("map_count %d rb %d\n", mm->map_count, i); + bug = 1; + } + VM_BUG_ON_MM(bug, mm); +} +#else +#define validate_mm_rb(root, ignore) do { } while (0) +#define validate_mm(mm) do { } while (0) +#endif + +RB_DECLARE_CALLBACKS_MAX(static, vma_gap_callbacks, + struct vm_area_struct, vm_rb, + unsigned long, rb_subtree_gap, vma_compute_gap) + +/* + * Update augmented rbtree rb_subtree_gap values after vma->vm_start or + * vma->vm_prev->vm_end values changed, without modifying the vma's position + * in the rbtree. + */ +static void vma_gap_update(struct vm_area_struct *vma) +{ + /* + * As it turns out, RB_DECLARE_CALLBACKS_MAX() already created + * a callback function that does exactly what we want. + */ + vma_gap_callbacks_propagate(&vma->vm_rb, NULL); +} + +static inline void vma_rb_insert(struct vm_area_struct *vma, + struct rb_root *root) +{ + /* All rb_subtree_gap values must be consistent prior to insertion */ + validate_mm_rb(root, NULL); + + rb_insert_augmented(&vma->vm_rb, root, &vma_gap_callbacks); +} + +static void __vma_rb_erase(struct vm_area_struct *vma, struct rb_root *root) +{ + /* + * Note rb_erase_augmented is a fairly large inline function, + * so make sure we instantiate it only once with our desired + * augmented rbtree callbacks. + */ + rb_erase_augmented(&vma->vm_rb, root, &vma_gap_callbacks); +} + +static __always_inline void vma_rb_erase_ignore(struct vm_area_struct *vma, + struct rb_root *root, + struct vm_area_struct *ignore) +{ + /* + * All rb_subtree_gap values must be consistent prior to erase, + * with the possible exception of + * + * a. the "next" vma being erased if next->vm_start was reduced in + * __vma_adjust() -> __vma_unlink() + * b. the vma being erased in detach_vmas_to_be_unmapped() -> + * vma_rb_erase() + */ + validate_mm_rb(root, ignore); + + __vma_rb_erase(vma, root); +} + +static __always_inline void vma_rb_erase(struct vm_area_struct *vma, + struct rb_root *root) +{ + vma_rb_erase_ignore(vma, root, vma); +} + +/* + * vma has some anon_vma assigned, and is already inserted on that + * anon_vma's interval trees. + * + * Before updating the vma's vm_start / vm_end / vm_pgoff fields, the + * vma must be removed from the anon_vma's interval trees using + * anon_vma_interval_tree_pre_update_vma(). + * + * After the update, the vma will be reinserted using + * anon_vma_interval_tree_post_update_vma(). + * + * The entire update must be protected by exclusive mmap_lock and by + * the root anon_vma's mutex. + */ +static inline void +anon_vma_interval_tree_pre_update_vma(struct vm_area_struct *vma) +{ + struct anon_vma_chain *avc; + + list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) + anon_vma_interval_tree_remove(avc, &avc->anon_vma->rb_root); +} + +static inline void +anon_vma_interval_tree_post_update_vma(struct vm_area_struct *vma) +{ + struct anon_vma_chain *avc; + + list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) + anon_vma_interval_tree_insert(avc, &avc->anon_vma->rb_root); +} + +static int find_vma_links(struct mm_struct *mm, unsigned long addr, + unsigned long end, struct vm_area_struct **pprev, + struct rb_node ***rb_link, struct rb_node **rb_parent) +{ + struct rb_node **__rb_link, *__rb_parent, *rb_prev; + + __rb_link = &mm->mm_rb.rb_node; + rb_prev = __rb_parent = NULL; + + while (*__rb_link) { + struct vm_area_struct *vma_tmp; + + __rb_parent = *__rb_link; + vma_tmp = rb_entry(__rb_parent, struct vm_area_struct, vm_rb); + + if (vma_tmp->vm_end > addr) { + /* Fail if an existing vma overlaps the area */ + if (vma_tmp->vm_start < end) + return -ENOMEM; + __rb_link = &__rb_parent->rb_left; + } else { + rb_prev = __rb_parent; + __rb_link = &__rb_parent->rb_right; + } + } + + *pprev = NULL; + if (rb_prev) + *pprev = rb_entry(rb_prev, struct vm_area_struct, vm_rb); + *rb_link = __rb_link; + *rb_parent = __rb_parent; + return 0; +} + +/* + * vma_next() - Get the next VMA. + * @mm: The mm_struct. + * @vma: The current vma. + * + * If @vma is NULL, return the first vma in the mm. + * + * Returns: The next VMA after @vma. + */ +static inline struct vm_area_struct *vma_next(struct mm_struct *mm, + struct vm_area_struct *vma) +{ + if (!vma) + return mm->mmap; + + return vma->vm_next; +} + +/* + * munmap_vma_range() - munmap VMAs that overlap a range. + * @mm: The mm struct + * @start: The start of the range. + * @len: The length of the range. + * @pprev: pointer to the pointer that will be set to previous vm_area_struct + * @rb_link: the rb_node + * @rb_parent: the parent rb_node + * + * Find all the vm_area_struct that overlap from @start to + * @end and munmap them. Set @pprev to the previous vm_area_struct. + * + * Returns: -ENOMEM on munmap failure or 0 on success. + */ +static inline int +munmap_vma_range(struct mm_struct *mm, unsigned long start, unsigned long len, + struct vm_area_struct **pprev, struct rb_node ***link, + struct rb_node **parent, struct list_head *uf) +{ + + while (find_vma_links(mm, start, start + len, pprev, link, parent)) + if (do_munmap(mm, start, len, uf)) + return -ENOMEM; + + return 0; +} +static unsigned long count_vma_pages_range(struct mm_struct *mm, + unsigned long addr, unsigned long end) +{ + unsigned long nr_pages = 0; + struct vm_area_struct *vma; + + /* Find first overlaping mapping */ + vma = find_vma_intersection(mm, addr, end); + if (!vma) + return 0; + + nr_pages = (min(end, vma->vm_end) - + max(addr, vma->vm_start)) >> PAGE_SHIFT; + + /* Iterate over the rest of the overlaps */ + for (vma = vma->vm_next; vma; vma = vma->vm_next) { + unsigned long overlap_len; + + if (vma->vm_start > end) + break; + + overlap_len = min(end, vma->vm_end) - vma->vm_start; + nr_pages += overlap_len >> PAGE_SHIFT; + } + + return nr_pages; +} + +void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma, + struct rb_node **rb_link, struct rb_node *rb_parent) +{ + /* Update tracking information for the gap following the new vma. */ + if (vma->vm_next) + vma_gap_update(vma->vm_next); + else + mm->highest_vm_end = vm_end_gap(vma); + + /* + * vma->vm_prev wasn't known when we followed the rbtree to find the + * correct insertion point for that vma. As a result, we could not + * update the vma vm_rb parents rb_subtree_gap values on the way down. + * So, we first insert the vma with a zero rb_subtree_gap value + * (to be consistent with what we did on the way down), and then + * immediately update the gap to the correct value. Finally we + * rebalance the rbtree after all augmented values have been set. + */ + rb_link_node(&vma->vm_rb, rb_parent, rb_link); + vma->rb_subtree_gap = 0; + vma_gap_update(vma); + vma_rb_insert(vma, &mm->mm_rb); +} + +static void __vma_link_file(struct vm_area_struct *vma) +{ + struct file *file; + + file = vma->vm_file; + if (file) { + struct address_space *mapping = file->f_mapping; + + if (vma->vm_flags & VM_DENYWRITE) + put_write_access(file_inode(file)); + if (vma->vm_flags & VM_SHARED) + mapping_allow_writable(mapping); + + flush_dcache_mmap_lock(mapping); + vma_interval_tree_insert(vma, &mapping->i_mmap); + flush_dcache_mmap_unlock(mapping); + } +} + +static void +__vma_link(struct mm_struct *mm, struct vm_area_struct *vma, + struct vm_area_struct *prev, struct rb_node **rb_link, + struct rb_node *rb_parent) +{ + __vma_link_list(mm, vma, prev); + __vma_link_rb(mm, vma, rb_link, rb_parent); +} + +static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma, + struct vm_area_struct *prev, struct rb_node **rb_link, + struct rb_node *rb_parent) +{ + struct address_space *mapping = NULL; + + if (vma->vm_file) { + mapping = vma->vm_file->f_mapping; + i_mmap_lock_write(mapping); + } + + __vma_link(mm, vma, prev, rb_link, rb_parent); + __vma_link_file(vma); + + if (mapping) + i_mmap_unlock_write(mapping); + + mm->map_count++; + validate_mm(mm); +} + +/* + * Helper for vma_adjust() in the split_vma insert case: insert a vma into the + * mm's list and rbtree. It has already been inserted into the interval tree. + */ +static void __insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma) +{ + struct vm_area_struct *prev; + struct rb_node **rb_link, *rb_parent; + + if (find_vma_links(mm, vma->vm_start, vma->vm_end, + &prev, &rb_link, &rb_parent)) + BUG(); + __vma_link(mm, vma, prev, rb_link, rb_parent); + mm->map_count++; +} + +static __always_inline void __vma_unlink(struct mm_struct *mm, + struct vm_area_struct *vma, + struct vm_area_struct *ignore) +{ + vma_rb_erase_ignore(vma, &mm->mm_rb, ignore); + __vma_unlink_list(mm, vma); + /* Kill the cache */ + vmacache_invalidate(mm); +} + +/* + * We cannot adjust vm_start, vm_end, vm_pgoff fields of a vma that + * is already present in an i_mmap tree without adjusting the tree. + * The following helper function should be used when such adjustments + * are necessary. The "insert" vma (if any) is to be inserted + * before we drop the necessary locks. + */ +int __vma_adjust(struct vm_area_struct *vma, unsigned long start, + unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert, + struct vm_area_struct *expand) +{ + struct mm_struct *mm = vma->vm_mm; + struct vm_area_struct *next = vma->vm_next, *orig_vma = vma; + struct address_space *mapping = NULL; + struct rb_root_cached *root = NULL; + struct anon_vma *anon_vma = NULL; + struct file *file = vma->vm_file; + bool start_changed = false, end_changed = false; + long adjust_next = 0; + int remove_next = 0; + + if (next && !insert) { + struct vm_area_struct *exporter = NULL, *importer = NULL; + + if (end >= next->vm_end) { + /* + * vma expands, overlapping all the next, and + * perhaps the one after too (mprotect case 6). + * The only other cases that gets here are + * case 1, case 7 and case 8. + */ + if (next == expand) { + /* + * The only case where we don't expand "vma" + * and we expand "next" instead is case 8. + */ + VM_WARN_ON(end != next->vm_end); + /* + * remove_next == 3 means we're + * removing "vma" and that to do so we + * swapped "vma" and "next". + */ + remove_next = 3; + VM_WARN_ON(file != next->vm_file); + swap(vma, next); + } else { + VM_WARN_ON(expand != vma); + /* + * case 1, 6, 7, remove_next == 2 is case 6, + * remove_next == 1 is case 1 or 7. + */ + remove_next = 1 + (end > next->vm_end); + VM_WARN_ON(remove_next == 2 && + end != next->vm_next->vm_end); + /* trim end to next, for case 6 first pass */ + end = next->vm_end; + } + + exporter = next; + importer = vma; + + /* + * If next doesn't have anon_vma, import from vma after + * next, if the vma overlaps with it. + */ + if (remove_next == 2 && !next->anon_vma) + exporter = next->vm_next; + + } else if (end > next->vm_start) { + /* + * vma expands, overlapping part of the next: + * mprotect case 5 shifting the boundary up. + */ + adjust_next = (end - next->vm_start); + exporter = next; + importer = vma; + VM_WARN_ON(expand != importer); + } else if (end < vma->vm_end) { + /* + * vma shrinks, and !insert tells it's not + * split_vma inserting another: so it must be + * mprotect case 4 shifting the boundary down. + */ + adjust_next = -(vma->vm_end - end); + exporter = vma; + importer = next; + VM_WARN_ON(expand != importer); + } + + /* + * Easily overlooked: when mprotect shifts the boundary, + * make sure the expanding vma has anon_vma set if the + * shrinking vma had, to cover any anon pages imported. + */ + if (exporter && exporter->anon_vma && !importer->anon_vma) { + int error; + + importer->anon_vma = exporter->anon_vma; + error = anon_vma_clone(importer, exporter); + if (error) + return error; + } + } +again: + vma_adjust_trans_huge(orig_vma, start, end, adjust_next); + + if (file) { + mapping = file->f_mapping; + root = &mapping->i_mmap; + uprobe_munmap(vma, vma->vm_start, vma->vm_end); + + if (adjust_next) + uprobe_munmap(next, next->vm_start, next->vm_end); + + i_mmap_lock_write(mapping); + if (insert) { + /* + * Put into interval tree now, so instantiated pages + * are visible to arm/parisc __flush_dcache_page + * throughout; but we cannot insert into address + * space until vma start or end is updated. + */ + __vma_link_file(insert); + } + } + + anon_vma = vma->anon_vma; + if (!anon_vma && adjust_next) + anon_vma = next->anon_vma; + if (anon_vma) { + VM_WARN_ON(adjust_next && next->anon_vma && + anon_vma != next->anon_vma); + anon_vma_lock_write(anon_vma); + anon_vma_interval_tree_pre_update_vma(vma); + if (adjust_next) + anon_vma_interval_tree_pre_update_vma(next); + } + + if (file) { + flush_dcache_mmap_lock(mapping); + vma_interval_tree_remove(vma, root); + if (adjust_next) + vma_interval_tree_remove(next, root); + } + + if (start != vma->vm_start) { + vma->vm_start = start; + start_changed = true; + } + if (end != vma->vm_end) { + vma->vm_end = end; + end_changed = true; + } + vma->vm_pgoff = pgoff; + if (adjust_next) { + next->vm_start += adjust_next; + next->vm_pgoff += adjust_next >> PAGE_SHIFT; + } + + if (file) { + if (adjust_next) + vma_interval_tree_insert(next, root); + vma_interval_tree_insert(vma, root); + flush_dcache_mmap_unlock(mapping); + } + + if (remove_next) { + /* + * vma_merge has merged next into vma, and needs + * us to remove next before dropping the locks. + */ + if (remove_next != 3) + __vma_unlink(mm, next, next); + else + /* + * vma is not before next if they've been + * swapped. + * + * pre-swap() next->vm_start was reduced so + * tell validate_mm_rb to ignore pre-swap() + * "next" (which is stored in post-swap() + * "vma"). + */ + __vma_unlink(mm, next, vma); + if (file) + __remove_shared_vm_struct(next, file, mapping); + } else if (insert) { + /* + * split_vma has split insert from vma, and needs + * us to insert it before dropping the locks + * (it may either follow vma or precede it). + */ + __insert_vm_struct(mm, insert); + } else { + if (start_changed) + vma_gap_update(vma); + if (end_changed) { + if (!next) + mm->highest_vm_end = vm_end_gap(vma); + else if (!adjust_next) + vma_gap_update(next); + } + } + + if (anon_vma) { + anon_vma_interval_tree_post_update_vma(vma); + if (adjust_next) + anon_vma_interval_tree_post_update_vma(next); + anon_vma_unlock_write(anon_vma); + } + + if (file) { + i_mmap_unlock_write(mapping); + uprobe_mmap(vma); + + if (adjust_next) + uprobe_mmap(next); + } + + if (remove_next) { + if (file) { + uprobe_munmap(next, next->vm_start, next->vm_end); + fput(file); + } + if (next->anon_vma) + anon_vma_merge(vma, next); + mm->map_count--; + mpol_put(vma_policy(next)); + vm_area_free(next); + /* + * In mprotect's case 6 (see comments on vma_merge), + * we must remove another next too. It would clutter + * up the code too much to do both in one go. + */ + if (remove_next != 3) { + /* + * If "next" was removed and vma->vm_end was + * expanded (up) over it, in turn + * "next->vm_prev->vm_end" changed and the + * "vma->vm_next" gap must be updated. + */ + next = vma->vm_next; + } else { + /* + * For the scope of the comment "next" and + * "vma" considered pre-swap(): if "vma" was + * removed, next->vm_start was expanded (down) + * over it and the "next" gap must be updated. + * Because of the swap() the post-swap() "vma" + * actually points to pre-swap() "next" + * (post-swap() "next" as opposed is now a + * dangling pointer). + */ + next = vma; + } + if (remove_next == 2) { + remove_next = 1; + end = next->vm_end; + goto again; + } + else if (next) + vma_gap_update(next); + else { + /* + * If remove_next == 2 we obviously can't + * reach this path. + * + * If remove_next == 3 we can't reach this + * path because pre-swap() next is always not + * NULL. pre-swap() "next" is not being + * removed and its next->vm_end is not altered + * (and furthermore "end" already matches + * next->vm_end in remove_next == 3). + * + * We reach this only in the remove_next == 1 + * case if the "next" vma that was removed was + * the highest vma of the mm. However in such + * case next->vm_end == "end" and the extended + * "vma" has vma->vm_end == next->vm_end so + * mm->highest_vm_end doesn't need any update + * in remove_next == 1 case. + */ + VM_WARN_ON(mm->highest_vm_end != vm_end_gap(vma)); + } + } + if (insert && file) + uprobe_mmap(insert); + + validate_mm(mm); + + return 0; +} + +/* + * If the vma has a ->close operation then the driver probably needs to release + * per-vma resources, so we don't attempt to merge those. + */ +static inline int is_mergeable_vma(struct vm_area_struct *vma, + struct file *file, unsigned long vm_flags, + struct vm_userfaultfd_ctx vm_userfaultfd_ctx) +{ + /* + * VM_SOFTDIRTY should not prevent from VMA merging, if we + * match the flags but dirty bit -- the caller should mark + * merged VMA as dirty. If dirty bit won't be excluded from + * comparison, we increase pressure on the memory system forcing + * the kernel to generate new VMAs when old one could be + * extended instead. + */ + if ((vma->vm_flags ^ vm_flags) & ~VM_SOFTDIRTY) + return 0; + if (vma->vm_file != file) + return 0; + if (vma->vm_ops && vma->vm_ops->close) + return 0; + if (!is_mergeable_vm_userfaultfd_ctx(vma, vm_userfaultfd_ctx)) + return 0; + return 1; +} + +static inline int is_mergeable_anon_vma(struct anon_vma *anon_vma1, + struct anon_vma *anon_vma2, + struct vm_area_struct *vma) +{ + /* + * The list_is_singular() test is to avoid merging VMA cloned from + * parents. This can improve scalability caused by anon_vma lock. + */ + if ((!anon_vma1 || !anon_vma2) && (!vma || + list_is_singular(&vma->anon_vma_chain))) + return 1; + return anon_vma1 == anon_vma2; +} + +/* + * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff) + * in front of (at a lower virtual address and file offset than) the vma. + * + * We cannot merge two vmas if they have differently assigned (non-NULL) + * anon_vmas, nor if same anon_vma is assigned but offsets incompatible. + * + * We don't check here for the merged mmap wrapping around the end of pagecache + * indices (16TB on ia32) because do_mmap() does not permit mmap's which + * wrap, nor mmaps which cover the final page at index -1UL. + */ +static int +can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags, + struct anon_vma *anon_vma, struct file *file, + pgoff_t vm_pgoff, + struct vm_userfaultfd_ctx vm_userfaultfd_ctx) +{ + if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx) && + is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { + if (vma->vm_pgoff == vm_pgoff) + return 1; + } + return 0; +} + +/* + * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff) + * beyond (at a higher virtual address and file offset than) the vma. + * + * We cannot merge two vmas if they have differently assigned (non-NULL) + * anon_vmas, nor if same anon_vma is assigned but offsets incompatible. + */ +static int +can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, + struct anon_vma *anon_vma, struct file *file, + pgoff_t vm_pgoff, + struct vm_userfaultfd_ctx vm_userfaultfd_ctx) +{ + if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx) && + is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { + pgoff_t vm_pglen; + vm_pglen = vma_pages(vma); + if (vma->vm_pgoff + vm_pglen == vm_pgoff) + return 1; + } + return 0; +} + +/* + * Given a mapping request (addr,end,vm_flags,file,pgoff), figure out + * whether that can be merged with its predecessor or its successor. + * Or both (it neatly fills a hole). + * + * In most cases - when called for mmap, brk or mremap - [addr,end) is + * certain not to be mapped by the time vma_merge is called; but when + * called for mprotect, it is certain to be already mapped (either at + * an offset within prev, or at the start of next), and the flags of + * this area are about to be changed to vm_flags - and the no-change + * case has already been eliminated. + * + * The following mprotect cases have to be considered, where AAAA is + * the area passed down from mprotect_fixup, never extending beyond one + * vma, PPPPPP is the prev vma specified, and NNNNNN the next vma after: + * + * AAAA AAAA AAAA + * PPPPPPNNNNNN PPPPPPNNNNNN PPPPPPNNNNNN + * cannot merge might become might become + * PPNNNNNNNNNN PPPPPPPPPPNN + * mmap, brk or case 4 below case 5 below + * mremap move: + * AAAA AAAA + * PPPP NNNN PPPPNNNNXXXX + * might become might become + * PPPPPPPPPPPP 1 or PPPPPPPPPPPP 6 or + * PPPPPPPPNNNN 2 or PPPPPPPPXXXX 7 or + * PPPPNNNNNNNN 3 PPPPXXXXXXXX 8 + * + * It is important for case 8 that the vma NNNN overlapping the + * region AAAA is never going to extended over XXXX. Instead XXXX must + * be extended in region AAAA and NNNN must be removed. This way in + * all cases where vma_merge succeeds, the moment vma_adjust drops the + * rmap_locks, the properties of the merged vma will be already + * correct for the whole merged range. Some of those properties like + * vm_page_prot/vm_flags may be accessed by rmap_walks and they must + * be correct for the whole merged range immediately after the + * rmap_locks are released. Otherwise if XXXX would be removed and + * NNNN would be extended over the XXXX range, remove_migration_ptes + * or other rmap walkers (if working on addresses beyond the "end" + * parameter) may establish ptes with the wrong permissions of NNNN + * instead of the right permissions of XXXX. + */ +struct vm_area_struct *vma_merge(struct mm_struct *mm, + struct vm_area_struct *prev, unsigned long addr, + unsigned long end, unsigned long vm_flags, + struct anon_vma *anon_vma, struct file *file, + pgoff_t pgoff, struct mempolicy *policy, + struct vm_userfaultfd_ctx vm_userfaultfd_ctx) +{ + pgoff_t pglen = (end - addr) >> PAGE_SHIFT; + struct vm_area_struct *area, *next; + int err; + + /* + * We later require that vma->vm_flags == vm_flags, + * so this tests vma->vm_flags & VM_SPECIAL, too. + */ + if (vm_flags & VM_SPECIAL) + return NULL; + + next = vma_next(mm, prev); + area = next; + if (area && area->vm_end == end) /* cases 6, 7, 8 */ + next = next->vm_next; + + /* verify some invariant that must be enforced by the caller */ + VM_WARN_ON(prev && addr <= prev->vm_start); + VM_WARN_ON(area && end > area->vm_end); + VM_WARN_ON(addr >= end); + + /* + * Can it merge with the predecessor? + */ + if (prev && prev->vm_end == addr && + mpol_equal(vma_policy(prev), policy) && + can_vma_merge_after(prev, vm_flags, + anon_vma, file, pgoff, + vm_userfaultfd_ctx)) { + /* + * OK, it can. Can we now merge in the successor as well? + */ + if (next && end == next->vm_start && + mpol_equal(policy, vma_policy(next)) && + can_vma_merge_before(next, vm_flags, + anon_vma, file, + pgoff+pglen, + vm_userfaultfd_ctx) && + is_mergeable_anon_vma(prev->anon_vma, + next->anon_vma, NULL)) { + /* cases 1, 6 */ + err = __vma_adjust(prev, prev->vm_start, + next->vm_end, prev->vm_pgoff, NULL, + prev); + } else /* cases 2, 5, 7 */ + err = __vma_adjust(prev, prev->vm_start, + end, prev->vm_pgoff, NULL, prev); + if (err) + return NULL; + khugepaged_enter_vma_merge(prev, vm_flags); + return prev; + } + + /* + * Can this new request be merged in front of next? + */ + if (next && end == next->vm_start && + mpol_equal(policy, vma_policy(next)) && + can_vma_merge_before(next, vm_flags, + anon_vma, file, pgoff+pglen, + vm_userfaultfd_ctx)) { + if (prev && addr < prev->vm_end) /* case 4 */ + err = __vma_adjust(prev, prev->vm_start, + addr, prev->vm_pgoff, NULL, next); + else { /* cases 3, 8 */ + err = __vma_adjust(area, addr, next->vm_end, + next->vm_pgoff - pglen, NULL, next); + /* + * In case 3 area is already equal to next and + * this is a noop, but in case 8 "area" has + * been removed and next was expanded over it. + */ + area = next; + } + if (err) + return NULL; + khugepaged_enter_vma_merge(area, vm_flags); + return area; + } + + return NULL; +} + +/* + * Rough compatibility check to quickly see if it's even worth looking + * at sharing an anon_vma. + * + * They need to have the same vm_file, and the flags can only differ + * in things that mprotect may change. + * + * NOTE! The fact that we share an anon_vma doesn't _have_ to mean that + * we can merge the two vma's. For example, we refuse to merge a vma if + * there is a vm_ops->close() function, because that indicates that the + * driver is doing some kind of reference counting. But that doesn't + * really matter for the anon_vma sharing case. + */ +static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct *b) +{ + return a->vm_end == b->vm_start && + mpol_equal(vma_policy(a), vma_policy(b)) && + a->vm_file == b->vm_file && + !((a->vm_flags ^ b->vm_flags) & ~(VM_ACCESS_FLAGS | VM_SOFTDIRTY)) && + b->vm_pgoff == a->vm_pgoff + ((b->vm_start - a->vm_start) >> PAGE_SHIFT); +} + +/* + * Do some basic sanity checking to see if we can re-use the anon_vma + * from 'old'. The 'a'/'b' vma's are in VM order - one of them will be + * the same as 'old', the other will be the new one that is trying + * to share the anon_vma. + * + * NOTE! This runs with mm_sem held for reading, so it is possible that + * the anon_vma of 'old' is concurrently in the process of being set up + * by another page fault trying to merge _that_. But that's ok: if it + * is being set up, that automatically means that it will be a singleton + * acceptable for merging, so we can do all of this optimistically. But + * we do that READ_ONCE() to make sure that we never re-load the pointer. + * + * IOW: that the "list_is_singular()" test on the anon_vma_chain only + * matters for the 'stable anon_vma' case (ie the thing we want to avoid + * is to return an anon_vma that is "complex" due to having gone through + * a fork). + * + * We also make sure that the two vma's are compatible (adjacent, + * and with the same memory policies). That's all stable, even with just + * a read lock on the mm_sem. + */ +static struct anon_vma *reusable_anon_vma(struct vm_area_struct *old, struct vm_area_struct *a, struct vm_area_struct *b) +{ + if (anon_vma_compatible(a, b)) { + struct anon_vma *anon_vma = READ_ONCE(old->anon_vma); + + if (anon_vma && list_is_singular(&old->anon_vma_chain)) + return anon_vma; + } + return NULL; +} + +/* + * find_mergeable_anon_vma is used by anon_vma_prepare, to check + * neighbouring vmas for a suitable anon_vma, before it goes off + * to allocate a new anon_vma. It checks because a repetitive + * sequence of mprotects and faults may otherwise lead to distinct + * anon_vmas being allocated, preventing vma merge in subsequent + * mprotect. + */ +struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma) +{ + struct anon_vma *anon_vma = NULL; + + /* Try next first. */ + if (vma->vm_next) { + anon_vma = reusable_anon_vma(vma->vm_next, vma, vma->vm_next); + if (anon_vma) + return anon_vma; + } + + /* Try prev next. */ + if (vma->vm_prev) + anon_vma = reusable_anon_vma(vma->vm_prev, vma->vm_prev, vma); + + /* + * We might reach here with anon_vma == NULL if we can't find + * any reusable anon_vma. + * There's no absolute need to look only at touching neighbours: + * we could search further afield for "compatible" anon_vmas. + * But it would probably just be a waste of time searching, + * or lead to too many vmas hanging off the same anon_vma. + * We're trying to allow mprotect remerging later on, + * not trying to minimize memory used for anon_vmas. + */ + return anon_vma; +} + +/* + * If a hint addr is less than mmap_min_addr change hint to be as + * low as possible but still greater than mmap_min_addr + */ +static inline unsigned long round_hint_to_min(unsigned long hint) +{ + hint &= PAGE_MASK; + if (((void *)hint != NULL) && + (hint < mmap_min_addr)) + return PAGE_ALIGN(mmap_min_addr); + return hint; +} + +static inline int mlock_future_check(struct mm_struct *mm, + unsigned long flags, + unsigned long len) +{ + unsigned long locked, lock_limit; + + /* mlock MCL_FUTURE? */ + if (flags & VM_LOCKED) { + locked = len >> PAGE_SHIFT; + locked += mm->locked_vm; + lock_limit = rlimit(RLIMIT_MEMLOCK); + lock_limit >>= PAGE_SHIFT; + if (locked > lock_limit && !capable(CAP_IPC_LOCK)) + return -EAGAIN; + } + return 0; +} + +static inline u64 file_mmap_size_max(struct file *file, struct inode *inode) +{ + if (S_ISREG(inode->i_mode)) + return MAX_LFS_FILESIZE; + + if (S_ISBLK(inode->i_mode)) + return MAX_LFS_FILESIZE; + + if (S_ISSOCK(inode->i_mode)) + return MAX_LFS_FILESIZE; + + /* Special "we do even unsigned file positions" case */ + if (file->f_mode & FMODE_UNSIGNED_OFFSET) + return 0; + + /* Yes, random drivers might want more. But I'm tired of buggy drivers */ + return ULONG_MAX; +} + +static inline bool file_mmap_ok(struct file *file, struct inode *inode, + unsigned long pgoff, unsigned long len) +{ + u64 maxsize = file_mmap_size_max(file, inode); + + if (maxsize && len > maxsize) + return false; + maxsize -= len; + if (pgoff > maxsize >> PAGE_SHIFT) + return false; + return true; +} + +/* + * The caller must write-lock current->mm->mmap_lock. + */ +unsigned long do_mmap(struct file *file, unsigned long addr, + unsigned long len, unsigned long prot, + unsigned long flags, unsigned long pgoff, + unsigned long *populate, struct list_head *uf) +{ + struct mm_struct *mm = current->mm; + vm_flags_t vm_flags; + int pkey = 0; + + *populate = 0; + + if (!len) + return -EINVAL; + + /* + * Does the application expect PROT_READ to imply PROT_EXEC? + * + * (the exception is when the underlying filesystem is noexec + * mounted, in which case we dont add PROT_EXEC.) + */ + if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC)) + if (!(file && path_noexec(&file->f_path))) + prot |= PROT_EXEC; + + /* force arch specific MAP_FIXED handling in get_unmapped_area */ + if (flags & MAP_FIXED_NOREPLACE) + flags |= MAP_FIXED; + + if (!(flags & MAP_FIXED)) + addr = round_hint_to_min(addr); + + /* Careful about overflows.. */ + len = PAGE_ALIGN(len); + if (!len) + return -ENOMEM; + + /* offset overflow? */ + if ((pgoff + (len >> PAGE_SHIFT)) < pgoff) + return -EOVERFLOW; + + /* Too many mappings? */ + if (mm->map_count > sysctl_max_map_count) + return -ENOMEM; + + /* Obtain the address to map to. we verify (or select) it and ensure + * that it represents a valid section of the address space. + */ + addr = get_unmapped_area(file, addr, len, pgoff, flags); + if (IS_ERR_VALUE(addr)) + return addr; + + if (flags & MAP_FIXED_NOREPLACE) { + struct vm_area_struct *vma = find_vma(mm, addr); + + if (vma && vma->vm_start < addr + len) + return -EEXIST; + } + + if (prot == PROT_EXEC) { + pkey = execute_only_pkey(mm); + if (pkey < 0) + pkey = 0; + } + + /* Do simple checking here so the lower-level routines won't have + * to. we assume access permissions have been handled by the open + * of the memory object, so we don't do any here. + */ + vm_flags = calc_vm_prot_bits(prot, pkey) | calc_vm_flag_bits(flags) | + mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC; + + if (flags & MAP_LOCKED) + if (!can_do_mlock()) + return -EPERM; + + if (mlock_future_check(mm, vm_flags, len)) + return -EAGAIN; + + if (file) { + struct inode *inode = file_inode(file); + unsigned long flags_mask; + + if (!file_mmap_ok(file, inode, pgoff, len)) + return -EOVERFLOW; + + flags_mask = LEGACY_MAP_MASK | file->f_op->mmap_supported_flags; + + switch (flags & MAP_TYPE) { + case MAP_SHARED: + /* + * Force use of MAP_SHARED_VALIDATE with non-legacy + * flags. E.g. MAP_SYNC is dangerous to use with + * MAP_SHARED as you don't know which consistency model + * you will get. We silently ignore unsupported flags + * with MAP_SHARED to preserve backward compatibility. + */ + flags &= LEGACY_MAP_MASK; + fallthrough; + case MAP_SHARED_VALIDATE: + if (flags & ~flags_mask) + return -EOPNOTSUPP; + if (prot & PROT_WRITE) { + if (!(file->f_mode & FMODE_WRITE)) + return -EACCES; + if (IS_SWAPFILE(file->f_mapping->host)) + return -ETXTBSY; + } + + /* + * Make sure we don't allow writing to an append-only + * file.. + */ + if (IS_APPEND(inode) && (file->f_mode & FMODE_WRITE)) + return -EACCES; + + /* + * Make sure there are no mandatory locks on the file. + */ + if (locks_verify_locked(file)) + return -EAGAIN; + + vm_flags |= VM_SHARED | VM_MAYSHARE; + if (!(file->f_mode & FMODE_WRITE)) + vm_flags &= ~(VM_MAYWRITE | VM_SHARED); + fallthrough; + case MAP_PRIVATE: + if (!(file->f_mode & FMODE_READ)) + return -EACCES; + if (path_noexec(&file->f_path)) { + if (vm_flags & VM_EXEC) + return -EPERM; + vm_flags &= ~VM_MAYEXEC; + } + + if (!file->f_op->mmap) + return -ENODEV; + if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP)) + return -EINVAL; + break; + + default: + return -EINVAL; + } + } else { + switch (flags & MAP_TYPE) { + case MAP_SHARED: + if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP)) + return -EINVAL; + /* + * Ignore pgoff. + */ + pgoff = 0; + vm_flags |= VM_SHARED | VM_MAYSHARE; + break; + case MAP_PRIVATE: + /* + * Set pgoff according to addr for anon_vma. + */ + pgoff = addr >> PAGE_SHIFT; + break; + default: + return -EINVAL; + } + } + + /* + * Set 'VM_NORESERVE' if we should not account for the + * memory use of this mapping. + */ + if (flags & MAP_NORESERVE) { + /* We honor MAP_NORESERVE if allowed to overcommit */ + if (sysctl_overcommit_memory != OVERCOMMIT_NEVER) + vm_flags |= VM_NORESERVE; + + /* hugetlb applies strict overcommit unless MAP_NORESERVE */ + if (file && is_file_hugepages(file)) + vm_flags |= VM_NORESERVE; + } + + addr = mmap_region(file, addr, len, vm_flags, pgoff, uf); + if (!IS_ERR_VALUE(addr) && + ((vm_flags & VM_LOCKED) || + (flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE)) + *populate = len; + return addr; +} + +unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, + unsigned long prot, unsigned long flags, + unsigned long fd, unsigned long pgoff) +{ + struct file *file = NULL; + unsigned long retval; + + if (!(flags & MAP_ANONYMOUS)) { + audit_mmap_fd(fd, flags); + file = fget(fd); + if (!file) + return -EBADF; + if (is_file_hugepages(file)) { + len = ALIGN(len, huge_page_size(hstate_file(file))); + } else if (unlikely(flags & MAP_HUGETLB)) { + retval = -EINVAL; + goto out_fput; + } + } else if (flags & MAP_HUGETLB) { + struct user_struct *user = NULL; + struct hstate *hs; + + hs = hstate_sizelog((flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK); + if (!hs) + return -EINVAL; + + len = ALIGN(len, huge_page_size(hs)); + /* + * VM_NORESERVE is used because the reservations will be + * taken when vm_ops->mmap() is called + * A dummy user value is used because we are not locking + * memory so no accounting is necessary + */ + file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, + VM_NORESERVE, + &user, HUGETLB_ANONHUGE_INODE, + (flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK); + if (IS_ERR(file)) + return PTR_ERR(file); + } + + flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE); + + retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff); +out_fput: + if (file) + fput(file); + return retval; +} + +SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len, + unsigned long, prot, unsigned long, flags, + unsigned long, fd, unsigned long, pgoff) +{ + return ksys_mmap_pgoff(addr, len, prot, flags, fd, pgoff); +} + +#ifdef __ARCH_WANT_SYS_OLD_MMAP +struct mmap_arg_struct { + unsigned long addr; + unsigned long len; + unsigned long prot; + unsigned long flags; + unsigned long fd; + unsigned long offset; +}; + +SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg) +{ + struct mmap_arg_struct a; + + if (copy_from_user(&a, arg, sizeof(a))) + return -EFAULT; + if (offset_in_page(a.offset)) + return -EINVAL; + + return ksys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, + a.offset >> PAGE_SHIFT); +} +#endif /* __ARCH_WANT_SYS_OLD_MMAP */ + +/* + * Some shared mappings will want the pages marked read-only + * to track write events. If so, we'll downgrade vm_page_prot + * to the private version (using protection_map[] without the + * VM_SHARED bit). + */ +int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot) +{ + vm_flags_t vm_flags = vma->vm_flags; + const struct vm_operations_struct *vm_ops = vma->vm_ops; + + /* If it was private or non-writable, the write bit is already clear */ + if ((vm_flags & (VM_WRITE|VM_SHARED)) != ((VM_WRITE|VM_SHARED))) + return 0; + + /* The backer wishes to know when pages are first written to? */ + if (vm_ops && (vm_ops->page_mkwrite || vm_ops->pfn_mkwrite)) + return 1; + + /* The open routine did something to the protections that pgprot_modify + * won't preserve? */ + if (pgprot_val(vm_page_prot) != + pgprot_val(vm_pgprot_modify(vm_page_prot, vm_flags))) + return 0; + + /* + * Do we need to track softdirty? hugetlb does not support softdirty + * tracking yet. + */ + if (IS_ENABLED(CONFIG_MEM_SOFT_DIRTY) && !(vm_flags & VM_SOFTDIRTY) && + !is_vm_hugetlb_page(vma)) + return 1; + + /* Specialty mapping? */ + if (vm_flags & VM_PFNMAP) + return 0; + + /* Can the mapping track the dirty pages? */ + return vma->vm_file && vma->vm_file->f_mapping && + mapping_can_writeback(vma->vm_file->f_mapping); +} + +/* + * We account for memory if it's a private writeable mapping, + * not hugepages and VM_NORESERVE wasn't set. + */ +static inline int accountable_mapping(struct file *file, vm_flags_t vm_flags) +{ + /* + * hugetlb has its own accounting separate from the core VM + * VM_HUGETLB may not be set yet so we cannot check for that flag. + */ + if (file && is_file_hugepages(file)) + return 0; + + return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE; +} + +unsigned long mmap_region(struct file *file, unsigned long addr, + unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, + struct list_head *uf) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma, *prev, *merge; + int error; + struct rb_node **rb_link, *rb_parent; + unsigned long charged = 0; + + /* Check against address space limit. */ + if (!may_expand_vm(mm, vm_flags, len >> PAGE_SHIFT)) { + unsigned long nr_pages; + + /* + * MAP_FIXED may remove pages of mappings that intersects with + * requested mapping. Account for the pages it would unmap. + */ + nr_pages = count_vma_pages_range(mm, addr, addr + len); + + if (!may_expand_vm(mm, vm_flags, + (len >> PAGE_SHIFT) - nr_pages)) + return -ENOMEM; + } + + /* Clear old maps, set up prev, rb_link, rb_parent, and uf */ + if (munmap_vma_range(mm, addr, len, &prev, &rb_link, &rb_parent, uf)) + return -ENOMEM; + /* + * Private writable mapping: check memory availability + */ + if (accountable_mapping(file, vm_flags)) { + charged = len >> PAGE_SHIFT; + if (security_vm_enough_memory_mm(mm, charged)) + return -ENOMEM; + vm_flags |= VM_ACCOUNT; + } + + /* + * Can we just expand an old mapping? + */ + vma = vma_merge(mm, prev, addr, addr + len, vm_flags, + NULL, file, pgoff, NULL, NULL_VM_UFFD_CTX); + if (vma) + goto out; + + /* + * Determine the object being mapped and call the appropriate + * specific mapper. the address has already been validated, but + * not unmapped, but the maps are removed from the list. + */ + vma = vm_area_alloc(mm); + if (!vma) { + error = -ENOMEM; + goto unacct_error; + } + + vma->vm_start = addr; + vma->vm_end = addr + len; + vma->vm_flags = vm_flags; + vma->vm_page_prot = vm_get_page_prot(vm_flags); + vma->vm_pgoff = pgoff; + + if (file) { + if (vm_flags & VM_DENYWRITE) { + error = deny_write_access(file); + if (error) + goto free_vma; + } + if (vm_flags & VM_SHARED) { + error = mapping_map_writable(file->f_mapping); + if (error) + goto allow_write_and_free_vma; + } + + /* ->mmap() can change vma->vm_file, but must guarantee that + * vma_link() below can deny write-access if VM_DENYWRITE is set + * and map writably if VM_SHARED is set. This usually means the + * new file must not have been exposed to user-space, yet. + */ + vma->vm_file = get_file(file); + error = call_mmap(file, vma); + if (error) + goto unmap_and_free_vma; + + /* Can addr have changed?? + * + * Answer: Yes, several device drivers can do it in their + * f_op->mmap method. -DaveM + * Bug: If addr is changed, prev, rb_link, rb_parent should + * be updated for vma_link() + */ + WARN_ON_ONCE(addr != vma->vm_start); + + addr = vma->vm_start; + + /* If vm_flags changed after call_mmap(), we should try merge vma again + * as we may succeed this time. + */ + if (unlikely(vm_flags != vma->vm_flags && prev)) { + merge = vma_merge(mm, prev, vma->vm_start, vma->vm_end, vma->vm_flags, + NULL, vma->vm_file, vma->vm_pgoff, NULL, NULL_VM_UFFD_CTX); + if (merge) { + /* ->mmap() can change vma->vm_file and fput the original file. So + * fput the vma->vm_file here or we would add an extra fput for file + * and cause general protection fault ultimately. + */ + fput(vma->vm_file); + vm_area_free(vma); + vma = merge; + /* Update vm_flags to pick up the change. */ + vm_flags = vma->vm_flags; + goto unmap_writable; + } + } + + vm_flags = vma->vm_flags; + } else if (vm_flags & VM_SHARED) { + error = shmem_zero_setup(vma); + if (error) + goto free_vma; + } else { + vma_set_anonymous(vma); + } + + /* Allow architectures to sanity-check the vm_flags */ + if (!arch_validate_flags(vma->vm_flags)) { + error = -EINVAL; + if (file) + goto close_and_free_vma; + else + goto free_vma; + } + + vma_link(mm, vma, prev, rb_link, rb_parent); + /* Once vma denies write, undo our temporary denial count */ + if (file) { +unmap_writable: + if (vm_flags & VM_SHARED) + mapping_unmap_writable(file->f_mapping); + if (vm_flags & VM_DENYWRITE) + allow_write_access(file); + } + file = vma->vm_file; +out: + perf_event_mmap(vma); + + vm_stat_account(mm, vm_flags, len >> PAGE_SHIFT); + if (vm_flags & VM_LOCKED) { + if ((vm_flags & VM_SPECIAL) || vma_is_dax(vma) || + is_vm_hugetlb_page(vma) || + vma == get_gate_vma(current->mm)) + vma->vm_flags &= VM_LOCKED_CLEAR_MASK; + else + mm->locked_vm += (len >> PAGE_SHIFT); + } + + if (file) + uprobe_mmap(vma); + + /* + * New (or expanded) vma always get soft dirty status. + * Otherwise user-space soft-dirty page tracker won't + * be able to distinguish situation when vma area unmapped, + * then new mapped in-place (which must be aimed as + * a completely new data area). + */ + vma->vm_flags |= VM_SOFTDIRTY; + + vma_set_page_prot(vma); + + return addr; + +close_and_free_vma: + if (vma->vm_ops && vma->vm_ops->close) + vma->vm_ops->close(vma); +unmap_and_free_vma: + vma->vm_file = NULL; + fput(file); + + /* Undo any partial mapping done by a device driver. */ + unmap_region(mm, vma, prev, vma->vm_start, vma->vm_end); + if (vm_flags & VM_SHARED) + mapping_unmap_writable(file->f_mapping); +allow_write_and_free_vma: + if (vm_flags & VM_DENYWRITE) + allow_write_access(file); +free_vma: + vm_area_free(vma); +unacct_error: + if (charged) + vm_unacct_memory(charged); + return error; +} + +static unsigned long unmapped_area(struct vm_unmapped_area_info *info) +{ + /* + * We implement the search by looking for an rbtree node that + * immediately follows a suitable gap. That is, + * - gap_start = vma->vm_prev->vm_end <= info->high_limit - length; + * - gap_end = vma->vm_start >= info->low_limit + length; + * - gap_end - gap_start >= length + */ + + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + unsigned long length, low_limit, high_limit, gap_start, gap_end; + + /* Adjust search length to account for worst case alignment overhead */ + length = info->length + info->align_mask; + if (length < info->length) + return -ENOMEM; + + /* Adjust search limits by the desired length */ + if (info->high_limit < length) + return -ENOMEM; + high_limit = info->high_limit - length; + + if (info->low_limit > high_limit) + return -ENOMEM; + low_limit = info->low_limit + length; + + /* Check if rbtree root looks promising */ + if (RB_EMPTY_ROOT(&mm->mm_rb)) + goto check_highest; + vma = rb_entry(mm->mm_rb.rb_node, struct vm_area_struct, vm_rb); + if (vma->rb_subtree_gap < length) + goto check_highest; + + while (true) { + /* Visit left subtree if it looks promising */ + gap_end = vm_start_gap(vma); + if (gap_end >= low_limit && vma->vm_rb.rb_left) { + struct vm_area_struct *left = + rb_entry(vma->vm_rb.rb_left, + struct vm_area_struct, vm_rb); + if (left->rb_subtree_gap >= length) { + vma = left; + continue; + } + } + + gap_start = vma->vm_prev ? vm_end_gap(vma->vm_prev) : 0; +check_current: + /* Check if current node has a suitable gap */ + if (gap_start > high_limit) + return -ENOMEM; + if (gap_end >= low_limit && + gap_end > gap_start && gap_end - gap_start >= length) + goto found; + + /* Visit right subtree if it looks promising */ + if (vma->vm_rb.rb_right) { + struct vm_area_struct *right = + rb_entry(vma->vm_rb.rb_right, + struct vm_area_struct, vm_rb); + if (right->rb_subtree_gap >= length) { + vma = right; + continue; + } + } + + /* Go back up the rbtree to find next candidate node */ + while (true) { + struct rb_node *prev = &vma->vm_rb; + if (!rb_parent(prev)) + goto check_highest; + vma = rb_entry(rb_parent(prev), + struct vm_area_struct, vm_rb); + if (prev == vma->vm_rb.rb_left) { + gap_start = vm_end_gap(vma->vm_prev); + gap_end = vm_start_gap(vma); + goto check_current; + } + } + } + +check_highest: + /* Check highest gap, which does not precede any rbtree node */ + gap_start = mm->highest_vm_end; + gap_end = ULONG_MAX; /* Only for VM_BUG_ON below */ + if (gap_start > high_limit) + return -ENOMEM; + +found: + /* We found a suitable gap. Clip it with the original low_limit. */ + if (gap_start < info->low_limit) + gap_start = info->low_limit; + + /* Adjust gap address to the desired alignment */ + gap_start += (info->align_offset - gap_start) & info->align_mask; + + VM_BUG_ON(gap_start + info->length > info->high_limit); + VM_BUG_ON(gap_start + info->length > gap_end); + return gap_start; +} + +static unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + unsigned long length, low_limit, high_limit, gap_start, gap_end; + + /* Adjust search length to account for worst case alignment overhead */ + length = info->length + info->align_mask; + if (length < info->length) + return -ENOMEM; + + /* + * Adjust search limits by the desired length. + * See implementation comment at top of unmapped_area(). + */ + gap_end = info->high_limit; + if (gap_end < length) + return -ENOMEM; + high_limit = gap_end - length; + + if (info->low_limit > high_limit) + return -ENOMEM; + low_limit = info->low_limit + length; + + /* Check highest gap, which does not precede any rbtree node */ + gap_start = mm->highest_vm_end; + if (gap_start <= high_limit) + goto found_highest; + + /* Check if rbtree root looks promising */ + if (RB_EMPTY_ROOT(&mm->mm_rb)) + return -ENOMEM; + vma = rb_entry(mm->mm_rb.rb_node, struct vm_area_struct, vm_rb); + if (vma->rb_subtree_gap < length) + return -ENOMEM; + + while (true) { + /* Visit right subtree if it looks promising */ + gap_start = vma->vm_prev ? vm_end_gap(vma->vm_prev) : 0; + if (gap_start <= high_limit && vma->vm_rb.rb_right) { + struct vm_area_struct *right = + rb_entry(vma->vm_rb.rb_right, + struct vm_area_struct, vm_rb); + if (right->rb_subtree_gap >= length) { + vma = right; + continue; + } + } + +check_current: + /* Check if current node has a suitable gap */ + gap_end = vm_start_gap(vma); + if (gap_end < low_limit) + return -ENOMEM; + if (gap_start <= high_limit && + gap_end > gap_start && gap_end - gap_start >= length) + goto found; + + /* Visit left subtree if it looks promising */ + if (vma->vm_rb.rb_left) { + struct vm_area_struct *left = + rb_entry(vma->vm_rb.rb_left, + struct vm_area_struct, vm_rb); + if (left->rb_subtree_gap >= length) { + vma = left; + continue; + } + } + + /* Go back up the rbtree to find next candidate node */ + while (true) { + struct rb_node *prev = &vma->vm_rb; + if (!rb_parent(prev)) + return -ENOMEM; + vma = rb_entry(rb_parent(prev), + struct vm_area_struct, vm_rb); + if (prev == vma->vm_rb.rb_right) { + gap_start = vma->vm_prev ? + vm_end_gap(vma->vm_prev) : 0; + goto check_current; + } + } + } + +found: + /* We found a suitable gap. Clip it with the original high_limit. */ + if (gap_end > info->high_limit) + gap_end = info->high_limit; + +found_highest: + /* Compute highest gap address at the desired alignment */ + gap_end -= info->length; + gap_end -= (gap_end - info->align_offset) & info->align_mask; + + VM_BUG_ON(gap_end < info->low_limit); + VM_BUG_ON(gap_end < gap_start); + return gap_end; +} + +/* + * Search for an unmapped address range. + * + * We are looking for a range that: + * - does not intersect with any VMA; + * - is contained within the [low_limit, high_limit) interval; + * - is at least the desired size. + * - satisfies (begin_addr & align_mask) == (align_offset & align_mask) + */ +unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info) +{ + unsigned long addr; + + if (info->flags & VM_UNMAPPED_AREA_TOPDOWN) + addr = unmapped_area_topdown(info); + else + addr = unmapped_area(info); + + trace_vm_unmapped_area(addr, info); + return addr; +} + +/* Get an address range which is currently unmapped. + * For shmat() with addr=0. + * + * Ugly calling convention alert: + * Return value with the low bits set means error value, + * ie + * if (ret & ~PAGE_MASK) + * error = ret; + * + * This function "knows" that -ENOMEM has the bits set. + */ +#ifndef HAVE_ARCH_UNMAPPED_AREA +unsigned long +arch_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma, *prev; + struct vm_unmapped_area_info info; + const unsigned long mmap_end = arch_get_mmap_end(addr); + + if (len > mmap_end - mmap_min_addr) + return -ENOMEM; + + if (flags & MAP_FIXED) + return addr; + + if (addr) { + addr = PAGE_ALIGN(addr); + vma = find_vma_prev(mm, addr, &prev); + if (mmap_end - len >= addr && addr >= mmap_min_addr && + (!vma || addr + len <= vm_start_gap(vma)) && + (!prev || addr >= vm_end_gap(prev))) + return addr; + } + + info.flags = 0; + info.length = len; + info.low_limit = mm->mmap_base; + info.high_limit = mmap_end; + info.align_mask = 0; + info.align_offset = 0; + return vm_unmapped_area(&info); +} +#endif + +/* + * This mmap-allocator allocates new areas top-down from below the + * stack's low limit (the base): + */ +#ifndef HAVE_ARCH_UNMAPPED_AREA_TOPDOWN +unsigned long +arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags) +{ + struct vm_area_struct *vma, *prev; + struct mm_struct *mm = current->mm; + struct vm_unmapped_area_info info; + const unsigned long mmap_end = arch_get_mmap_end(addr); + + /* requested length too big for entire address space */ + if (len > mmap_end - mmap_min_addr) + return -ENOMEM; + + if (flags & MAP_FIXED) + return addr; + + /* requesting a specific address */ + if (addr) { + addr = PAGE_ALIGN(addr); + vma = find_vma_prev(mm, addr, &prev); + if (mmap_end - len >= addr && addr >= mmap_min_addr && + (!vma || addr + len <= vm_start_gap(vma)) && + (!prev || addr >= vm_end_gap(prev))) + return addr; + } + + info.flags = VM_UNMAPPED_AREA_TOPDOWN; + info.length = len; + info.low_limit = max(PAGE_SIZE, mmap_min_addr); + info.high_limit = arch_get_mmap_base(addr, mm->mmap_base); + info.align_mask = 0; + info.align_offset = 0; + addr = vm_unmapped_area(&info); + + /* + * A failed mmap() very likely causes application failure, + * so fall back to the bottom-up function here. This scenario + * can happen with large stack limits and large mmap() + * allocations. + */ + if (offset_in_page(addr)) { + VM_BUG_ON(addr != -ENOMEM); + info.flags = 0; + info.low_limit = TASK_UNMAPPED_BASE; + info.high_limit = mmap_end; + addr = vm_unmapped_area(&info); + } + + return addr; +} +#endif + +unsigned long +get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags) +{ + unsigned long (*get_area)(struct file *, unsigned long, + unsigned long, unsigned long, unsigned long); + + unsigned long error = arch_mmap_check(addr, len, flags); + if (error) + return error; + + /* Careful about overflows.. */ + if (len > TASK_SIZE) + return -ENOMEM; + + get_area = current->mm->get_unmapped_area; + if (file) { + if (file->f_op->get_unmapped_area) + get_area = file->f_op->get_unmapped_area; + } else if (flags & MAP_SHARED) { + /* + * mmap_region() will call shmem_zero_setup() to create a file, + * so use shmem's get_unmapped_area in case it can be huge. + * do_mmap() will clear pgoff, so match alignment. + */ + pgoff = 0; + get_area = shmem_get_unmapped_area; + } + + addr = get_area(file, addr, len, pgoff, flags); + if (IS_ERR_VALUE(addr)) + return addr; + + if (addr > TASK_SIZE - len) + return -ENOMEM; + if (offset_in_page(addr)) + return -EINVAL; + + error = security_mmap_addr(addr); + return error ? error : addr; +} + +EXPORT_SYMBOL(get_unmapped_area); + +/* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ +struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) +{ + struct rb_node *rb_node; + struct vm_area_struct *vma; + + /* Check the cache first. */ + vma = vmacache_find(mm, addr); + if (likely(vma)) + return vma; + + rb_node = mm->mm_rb.rb_node; + + while (rb_node) { + struct vm_area_struct *tmp; + + tmp = rb_entry(rb_node, struct vm_area_struct, vm_rb); + + if (tmp->vm_end > addr) { + vma = tmp; + if (tmp->vm_start <= addr) + break; + rb_node = rb_node->rb_left; + } else + rb_node = rb_node->rb_right; + } + + if (vma) + vmacache_update(addr, vma); + return vma; +} + +EXPORT_SYMBOL(find_vma); + +/* + * Same as find_vma, but also return a pointer to the previous VMA in *pprev. + */ +struct vm_area_struct * +find_vma_prev(struct mm_struct *mm, unsigned long addr, + struct vm_area_struct **pprev) +{ + struct vm_area_struct *vma; + + vma = find_vma(mm, addr); + if (vma) { + *pprev = vma->vm_prev; + } else { + struct rb_node *rb_node = rb_last(&mm->mm_rb); + + *pprev = rb_node ? rb_entry(rb_node, struct vm_area_struct, vm_rb) : NULL; + } + return vma; +} + +/* + * Verify that the stack growth is acceptable and + * update accounting. This is shared with both the + * grow-up and grow-down cases. + */ +static int acct_stack_growth(struct vm_area_struct *vma, + unsigned long size, unsigned long grow) +{ + struct mm_struct *mm = vma->vm_mm; + unsigned long new_start; + + /* address space limit tests */ + if (!may_expand_vm(mm, vma->vm_flags, grow)) + return -ENOMEM; + + /* Stack limit test */ + if (size > rlimit(RLIMIT_STACK)) + return -ENOMEM; + + /* mlock limit tests */ + if (vma->vm_flags & VM_LOCKED) { + unsigned long locked; + unsigned long limit; + locked = mm->locked_vm + grow; + limit = rlimit(RLIMIT_MEMLOCK); + limit >>= PAGE_SHIFT; + if (locked > limit && !capable(CAP_IPC_LOCK)) + return -ENOMEM; + } + + /* Check to ensure the stack will not grow into a hugetlb-only region */ + new_start = (vma->vm_flags & VM_GROWSUP) ? vma->vm_start : + vma->vm_end - size; + if (is_hugepage_only_range(vma->vm_mm, new_start, size)) + return -EFAULT; + + /* + * Overcommit.. This must be the final test, as it will + * update security statistics. + */ + if (security_vm_enough_memory_mm(mm, grow)) + return -ENOMEM; + + return 0; +} + +#if defined(CONFIG_STACK_GROWSUP) || defined(CONFIG_IA64) +/* + * PA-RISC uses this for its stack; IA64 for its Register Backing Store. + * vma is the last one with address > vma->vm_end. Have to extend vma. + */ +int expand_upwards(struct vm_area_struct *vma, unsigned long address) +{ + struct mm_struct *mm = vma->vm_mm; + struct vm_area_struct *next; + unsigned long gap_addr; + int error = 0; + + if (!(vma->vm_flags & VM_GROWSUP)) + return -EFAULT; + + /* Guard against exceeding limits of the address space. */ + address &= PAGE_MASK; + if (address >= (TASK_SIZE & PAGE_MASK)) + return -ENOMEM; + address += PAGE_SIZE; + + /* Enforce stack_guard_gap */ + gap_addr = address + stack_guard_gap; + + /* Guard against overflow */ + if (gap_addr < address || gap_addr > TASK_SIZE) + gap_addr = TASK_SIZE; + + next = vma->vm_next; + if (next && next->vm_start < gap_addr && vma_is_accessible(next)) { + if (!(next->vm_flags & VM_GROWSUP)) + return -ENOMEM; + /* Check that both stack segments have the same anon_vma? */ + } + + /* We must make sure the anon_vma is allocated. */ + if (unlikely(anon_vma_prepare(vma))) + return -ENOMEM; + + /* + * vma->vm_start/vm_end cannot change under us because the caller + * is required to hold the mmap_lock in read mode. We need the + * anon_vma lock to serialize against concurrent expand_stacks. + */ + anon_vma_lock_write(vma->anon_vma); + + /* Somebody else might have raced and expanded it already */ + if (address > vma->vm_end) { + unsigned long size, grow; + + size = address - vma->vm_start; + grow = (address - vma->vm_end) >> PAGE_SHIFT; + + error = -ENOMEM; + if (vma->vm_pgoff + (size >> PAGE_SHIFT) >= vma->vm_pgoff) { + error = acct_stack_growth(vma, size, grow); + if (!error) { + /* + * vma_gap_update() doesn't support concurrent + * updates, but we only hold a shared mmap_lock + * lock here, so we need to protect against + * concurrent vma expansions. + * anon_vma_lock_write() doesn't help here, as + * we don't guarantee that all growable vmas + * in a mm share the same root anon vma. + * So, we reuse mm->page_table_lock to guard + * against concurrent vma expansions. + */ + spin_lock(&mm->page_table_lock); + if (vma->vm_flags & VM_LOCKED) + mm->locked_vm += grow; + vm_stat_account(mm, vma->vm_flags, grow); + anon_vma_interval_tree_pre_update_vma(vma); + vma->vm_end = address; + anon_vma_interval_tree_post_update_vma(vma); + if (vma->vm_next) + vma_gap_update(vma->vm_next); + else + mm->highest_vm_end = vm_end_gap(vma); + spin_unlock(&mm->page_table_lock); + + perf_event_mmap(vma); + } + } + } + anon_vma_unlock_write(vma->anon_vma); + khugepaged_enter_vma_merge(vma, vma->vm_flags); + validate_mm(mm); + return error; +} +#endif /* CONFIG_STACK_GROWSUP || CONFIG_IA64 */ + +/* + * vma is the first one with address < vma->vm_start. Have to extend vma. + */ +int expand_downwards(struct vm_area_struct *vma, + unsigned long address) +{ + struct mm_struct *mm = vma->vm_mm; + struct vm_area_struct *prev; + int error = 0; + + address &= PAGE_MASK; + if (address < mmap_min_addr) + return -EPERM; + + /* Enforce stack_guard_gap */ + prev = vma->vm_prev; + /* Check that both stack segments have the same anon_vma? */ + if (prev && !(prev->vm_flags & VM_GROWSDOWN) && + vma_is_accessible(prev)) { + if (address - prev->vm_end < stack_guard_gap) + return -ENOMEM; + } + + /* We must make sure the anon_vma is allocated. */ + if (unlikely(anon_vma_prepare(vma))) + return -ENOMEM; + + /* + * vma->vm_start/vm_end cannot change under us because the caller + * is required to hold the mmap_lock in read mode. We need the + * anon_vma lock to serialize against concurrent expand_stacks. + */ + anon_vma_lock_write(vma->anon_vma); + + /* Somebody else might have raced and expanded it already */ + if (address < vma->vm_start) { + unsigned long size, grow; + + size = vma->vm_end - address; + grow = (vma->vm_start - address) >> PAGE_SHIFT; + + error = -ENOMEM; + if (grow <= vma->vm_pgoff) { + error = acct_stack_growth(vma, size, grow); + if (!error) { + /* + * vma_gap_update() doesn't support concurrent + * updates, but we only hold a shared mmap_lock + * lock here, so we need to protect against + * concurrent vma expansions. + * anon_vma_lock_write() doesn't help here, as + * we don't guarantee that all growable vmas + * in a mm share the same root anon vma. + * So, we reuse mm->page_table_lock to guard + * against concurrent vma expansions. + */ + spin_lock(&mm->page_table_lock); + if (vma->vm_flags & VM_LOCKED) + mm->locked_vm += grow; + vm_stat_account(mm, vma->vm_flags, grow); + anon_vma_interval_tree_pre_update_vma(vma); + vma->vm_start = address; + vma->vm_pgoff -= grow; + anon_vma_interval_tree_post_update_vma(vma); + vma_gap_update(vma); + spin_unlock(&mm->page_table_lock); + + perf_event_mmap(vma); + } + } + } + anon_vma_unlock_write(vma->anon_vma); + khugepaged_enter_vma_merge(vma, vma->vm_flags); + validate_mm(mm); + return error; +} + +/* enforced gap between the expanding stack and other mappings. */ +unsigned long stack_guard_gap = 256UL<comm, current->pid); + + if (prot) + return ret; + start = start & PAGE_MASK; + size = size & PAGE_MASK; + + if (start + size <= start) + return ret; + + /* Does pgoff wrap? */ + if (pgoff + (size >> PAGE_SHIFT) < pgoff) + return ret; + + if (mmap_write_lock_killable(mm)) + return -EINTR; + + vma = find_vma(mm, start); + + if (!vma || !(vma->vm_flags & VM_SHARED)) + goto out; + + if (start < vma->vm_start) + goto out; + + if (start + size > vma->vm_end) { + struct vm_area_struct *next; + + for (next = vma->vm_next; next; next = next->vm_next) { + /* hole between vmas ? */ + if (next->vm_start != next->vm_prev->vm_end) + goto out; + + if (next->vm_file != vma->vm_file) + goto out; + + if (next->vm_flags != vma->vm_flags) + goto out; + + if (start + size <= next->vm_end) + break; + } + + if (!next) + goto out; + } + + prot |= vma->vm_flags & VM_READ ? PROT_READ : 0; + prot |= vma->vm_flags & VM_WRITE ? PROT_WRITE : 0; + prot |= vma->vm_flags & VM_EXEC ? PROT_EXEC : 0; + + flags &= MAP_NONBLOCK; + flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE; + if (vma->vm_flags & VM_LOCKED) { + struct vm_area_struct *tmp; + flags |= MAP_LOCKED; + + /* drop PG_Mlocked flag for over-mapped range */ + for (tmp = vma; tmp->vm_start >= start + size; + tmp = tmp->vm_next) { + /* + * Split pmd and munlock page on the border + * of the range. + */ + vma_adjust_trans_huge(tmp, start, start + size, 0); + + munlock_vma_pages_range(tmp, + max(tmp->vm_start, start), + min(tmp->vm_end, start + size)); + } + } + + file = get_file(vma->vm_file); + ret = do_mmap(vma->vm_file, start, size, + prot, flags, pgoff, &populate, NULL); + fput(file); +out: + mmap_write_unlock(mm); + if (populate) + mm_populate(ret, populate); + if (!IS_ERR_VALUE(ret)) + ret = 0; + return ret; +} + +/* + * this is really a simplified "do_mmap". it only handles + * anonymous maps. eventually we may be able to do some + * brk-specific accounting here. + */ +static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long flags, struct list_head *uf) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma, *prev; + struct rb_node **rb_link, *rb_parent; + pgoff_t pgoff = addr >> PAGE_SHIFT; + int error; + unsigned long mapped_addr; + + /* Until we need other flags, refuse anything except VM_EXEC. */ + if ((flags & (~VM_EXEC)) != 0) + return -EINVAL; + flags |= VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags; + + mapped_addr = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED); + if (IS_ERR_VALUE(mapped_addr)) + return mapped_addr; + + error = mlock_future_check(mm, mm->def_flags, len); + if (error) + return error; + + /* Clear old maps, set up prev, rb_link, rb_parent, and uf */ + if (munmap_vma_range(mm, addr, len, &prev, &rb_link, &rb_parent, uf)) + return -ENOMEM; + + /* Check against address space limits *after* clearing old maps... */ + if (!may_expand_vm(mm, flags, len >> PAGE_SHIFT)) + return -ENOMEM; + + if (mm->map_count > sysctl_max_map_count) + return -ENOMEM; + + if (security_vm_enough_memory_mm(mm, len >> PAGE_SHIFT)) + return -ENOMEM; + + /* Can we just expand an old private anonymous mapping? */ + vma = vma_merge(mm, prev, addr, addr + len, flags, + NULL, NULL, pgoff, NULL, NULL_VM_UFFD_CTX); + if (vma) + goto out; + + /* + * create a vma struct for an anonymous mapping + */ + vma = vm_area_alloc(mm); + if (!vma) { + vm_unacct_memory(len >> PAGE_SHIFT); + return -ENOMEM; + } + + vma_set_anonymous(vma); + vma->vm_start = addr; + vma->vm_end = addr + len; + vma->vm_pgoff = pgoff; + vma->vm_flags = flags; + vma->vm_page_prot = vm_get_page_prot(flags); + vma_link(mm, vma, prev, rb_link, rb_parent); +out: + perf_event_mmap(vma); + mm->total_vm += len >> PAGE_SHIFT; + mm->data_vm += len >> PAGE_SHIFT; + if (flags & VM_LOCKED) + mm->locked_vm += (len >> PAGE_SHIFT); + vma->vm_flags |= VM_SOFTDIRTY; + return 0; +} + +int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags) +{ + struct mm_struct *mm = current->mm; + unsigned long len; + int ret; + bool populate; + LIST_HEAD(uf); + + len = PAGE_ALIGN(request); + if (len < request) + return -ENOMEM; + if (!len) + return 0; + + if (mmap_write_lock_killable(mm)) + return -EINTR; + + ret = do_brk_flags(addr, len, flags, &uf); + populate = ((mm->def_flags & VM_LOCKED) != 0); + mmap_write_unlock(mm); + userfaultfd_unmap_complete(mm, &uf); + if (populate && !ret) + mm_populate(addr, len); + return ret; +} +EXPORT_SYMBOL(vm_brk_flags); + +int vm_brk(unsigned long addr, unsigned long len) +{ + return vm_brk_flags(addr, len, 0); +} +EXPORT_SYMBOL(vm_brk); + +/* Release all mmaps. */ +void exit_mmap(struct mm_struct *mm) +{ + struct mmu_gather tlb; + struct vm_area_struct *vma; + unsigned long nr_accounted = 0; + + /* mm's last user has gone, and its about to be pulled down */ + mmu_notifier_release(mm); + + if (unlikely(mm_is_oom_victim(mm))) { + /* + * Manually reap the mm to free as much memory as possible. + * Then, as the oom reaper does, set MMF_OOM_SKIP to disregard + * this mm from further consideration. Taking mm->mmap_lock for + * write after setting MMF_OOM_SKIP will guarantee that the oom + * reaper will not run on this mm again after mmap_lock is + * dropped. + * + * Nothing can be holding mm->mmap_lock here and the above call + * to mmu_notifier_release(mm) ensures mmu notifier callbacks in + * __oom_reap_task_mm() will not block. + * + * This needs to be done before calling munlock_vma_pages_all(), + * which clears VM_LOCKED, otherwise the oom reaper cannot + * reliably test it. + */ + (void)__oom_reap_task_mm(mm); + + set_bit(MMF_OOM_SKIP, &mm->flags); + mmap_write_lock(mm); + mmap_write_unlock(mm); + } + + if (mm->locked_vm) { + vma = mm->mmap; + while (vma) { + if (vma->vm_flags & VM_LOCKED) + munlock_vma_pages_all(vma); + vma = vma->vm_next; + } + } + + arch_exit_mmap(mm); + + vma = mm->mmap; + if (!vma) /* Can happen if dup_mmap() received an OOM */ + return; + + lru_add_drain(); + flush_cache_mm(mm); + tlb_gather_mmu(&tlb, mm, 0, -1); + /* update_hiwater_rss(mm) here? but nobody should be looking */ + /* Use -1 here to ensure all VMAs in the mm are unmapped */ + unmap_vmas(&tlb, vma, 0, -1); + free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING); + tlb_finish_mmu(&tlb, 0, -1); + + /* + * Walk the list again, actually closing and freeing it, + * with preemption enabled, without holding any MM locks. + */ + while (vma) { + if (vma->vm_flags & VM_ACCOUNT) + nr_accounted += vma_pages(vma); + vma = remove_vma(vma); + cond_resched(); + } + vm_unacct_memory(nr_accounted); +} + +/* Insert vm structure into process list sorted by address + * and into the inode's i_mmap tree. If vm_file is non-NULL + * then i_mmap_rwsem is taken here. + */ +int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma) +{ + struct vm_area_struct *prev; + struct rb_node **rb_link, *rb_parent; + + if (find_vma_links(mm, vma->vm_start, vma->vm_end, + &prev, &rb_link, &rb_parent)) + return -ENOMEM; + if ((vma->vm_flags & VM_ACCOUNT) && + security_vm_enough_memory_mm(mm, vma_pages(vma))) + return -ENOMEM; + + /* + * The vm_pgoff of a purely anonymous vma should be irrelevant + * until its first write fault, when page's anon_vma and index + * are set. But now set the vm_pgoff it will almost certainly + * end up with (unless mremap moves it elsewhere before that + * first wfault), so /proc/pid/maps tells a consistent story. + * + * By setting it to reflect the virtual start address of the + * vma, merges and splits can happen in a seamless way, just + * using the existing file pgoff checks and manipulations. + * Similarly in do_mmap and in do_brk_flags. + */ + if (vma_is_anonymous(vma)) { + BUG_ON(vma->anon_vma); + vma->vm_pgoff = vma->vm_start >> PAGE_SHIFT; + } + + vma_link(mm, vma, prev, rb_link, rb_parent); + return 0; +} + +/* + * Copy the vma structure to a new location in the same mm, + * prior to moving page table entries, to effect an mremap move. + */ +struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, + unsigned long addr, unsigned long len, pgoff_t pgoff, + bool *need_rmap_locks) +{ + struct vm_area_struct *vma = *vmap; + unsigned long vma_start = vma->vm_start; + struct mm_struct *mm = vma->vm_mm; + struct vm_area_struct *new_vma, *prev; + struct rb_node **rb_link, *rb_parent; + bool faulted_in_anon_vma = true; + + /* + * If anonymous vma has not yet been faulted, update new pgoff + * to match new location, to increase its chance of merging. + */ + if (unlikely(vma_is_anonymous(vma) && !vma->anon_vma)) { + pgoff = addr >> PAGE_SHIFT; + faulted_in_anon_vma = false; + } + + if (find_vma_links(mm, addr, addr + len, &prev, &rb_link, &rb_parent)) + return NULL; /* should never get here */ + new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags, + vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), + vma->vm_userfaultfd_ctx); + if (new_vma) { + /* + * Source vma may have been merged into new_vma + */ + if (unlikely(vma_start >= new_vma->vm_start && + vma_start < new_vma->vm_end)) { + /* + * The only way we can get a vma_merge with + * self during an mremap is if the vma hasn't + * been faulted in yet and we were allowed to + * reset the dst vma->vm_pgoff to the + * destination address of the mremap to allow + * the merge to happen. mremap must change the + * vm_pgoff linearity between src and dst vmas + * (in turn preventing a vma_merge) to be + * safe. It is only safe to keep the vm_pgoff + * linear if there are no pages mapped yet. + */ + VM_BUG_ON_VMA(faulted_in_anon_vma, new_vma); + *vmap = vma = new_vma; + } + *need_rmap_locks = (new_vma->vm_pgoff <= vma->vm_pgoff); + } else { + new_vma = vm_area_dup(vma); + if (!new_vma) + goto out; + new_vma->vm_start = addr; + new_vma->vm_end = addr + len; + new_vma->vm_pgoff = pgoff; + if (vma_dup_policy(vma, new_vma)) + goto out_free_vma; + if (anon_vma_clone(new_vma, vma)) + goto out_free_mempol; + if (new_vma->vm_file) + get_file(new_vma->vm_file); + if (new_vma->vm_ops && new_vma->vm_ops->open) + new_vma->vm_ops->open(new_vma); + vma_link(mm, new_vma, prev, rb_link, rb_parent); + *need_rmap_locks = false; + } + return new_vma; + +out_free_mempol: + mpol_put(vma_policy(new_vma)); +out_free_vma: + vm_area_free(new_vma); +out: + return NULL; +} + +/* + * Return true if the calling process may expand its vm space by the passed + * number of pages + */ +bool may_expand_vm(struct mm_struct *mm, vm_flags_t flags, unsigned long npages) +{ + if (mm->total_vm + npages > rlimit(RLIMIT_AS) >> PAGE_SHIFT) + return false; + + if (is_data_mapping(flags) && + mm->data_vm + npages > rlimit(RLIMIT_DATA) >> PAGE_SHIFT) { + /* Workaround for Valgrind */ + if (rlimit(RLIMIT_DATA) == 0 && + mm->data_vm + npages <= rlimit_max(RLIMIT_DATA) >> PAGE_SHIFT) + return true; + + pr_warn_once("%s (%d): VmData %lu exceed data ulimit %lu. Update limits%s.\n", + current->comm, current->pid, + (mm->data_vm + npages) << PAGE_SHIFT, + rlimit(RLIMIT_DATA), + ignore_rlimit_data ? "" : " or use boot option ignore_rlimit_data"); + + if (!ignore_rlimit_data) + return false; + } + + return true; +} + +void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, long npages) +{ + mm->total_vm += npages; + + if (is_exec_mapping(flags)) + mm->exec_vm += npages; + else if (is_stack_mapping(flags)) + mm->stack_vm += npages; + else if (is_data_mapping(flags)) + mm->data_vm += npages; +} + +static vm_fault_t special_mapping_fault(struct vm_fault *vmf); + +/* + * Having a close hook prevents vma merging regardless of flags. + */ +static void special_mapping_close(struct vm_area_struct *vma) +{ +} + +static const char *special_mapping_name(struct vm_area_struct *vma) +{ + return ((struct vm_special_mapping *)vma->vm_private_data)->name; +} + +static int special_mapping_mremap(struct vm_area_struct *new_vma) +{ + struct vm_special_mapping *sm = new_vma->vm_private_data; + + if (WARN_ON_ONCE(current->mm != new_vma->vm_mm)) + return -EFAULT; + + if (sm->mremap) + return sm->mremap(sm, new_vma); + + return 0; +} + +static const struct vm_operations_struct special_mapping_vmops = { + .close = special_mapping_close, + .fault = special_mapping_fault, + .mremap = special_mapping_mremap, + .name = special_mapping_name, + /* vDSO code relies that VVAR can't be accessed remotely */ + .access = NULL, +}; + +static const struct vm_operations_struct legacy_special_mapping_vmops = { + .close = special_mapping_close, + .fault = special_mapping_fault, +}; + +static vm_fault_t special_mapping_fault(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + pgoff_t pgoff; + struct page **pages; + + if (vma->vm_ops == &legacy_special_mapping_vmops) { + pages = vma->vm_private_data; + } else { + struct vm_special_mapping *sm = vma->vm_private_data; + + if (sm->fault) + return sm->fault(sm, vmf->vma, vmf); + + pages = sm->pages; + } + + for (pgoff = vmf->pgoff; pgoff && *pages; ++pages) + pgoff--; + + if (*pages) { + struct page *page = *pages; + get_page(page); + vmf->page = page; + return 0; + } + + return VM_FAULT_SIGBUS; +} + +static struct vm_area_struct *__install_special_mapping( + struct mm_struct *mm, + unsigned long addr, unsigned long len, + unsigned long vm_flags, void *priv, + const struct vm_operations_struct *ops) +{ + int ret; + struct vm_area_struct *vma; + + vma = vm_area_alloc(mm); + if (unlikely(vma == NULL)) + return ERR_PTR(-ENOMEM); + + vma->vm_start = addr; + vma->vm_end = addr + len; + + vma->vm_flags = vm_flags | mm->def_flags | VM_DONTEXPAND | VM_SOFTDIRTY; + vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); + + vma->vm_ops = ops; + vma->vm_private_data = priv; + + ret = insert_vm_struct(mm, vma); + if (ret) + goto out; + + vm_stat_account(mm, vma->vm_flags, len >> PAGE_SHIFT); + + perf_event_mmap(vma); + + return vma; + +out: + vm_area_free(vma); + return ERR_PTR(ret); +} + +bool vma_is_special_mapping(const struct vm_area_struct *vma, + const struct vm_special_mapping *sm) +{ + return vma->vm_private_data == sm && + (vma->vm_ops == &special_mapping_vmops || + vma->vm_ops == &legacy_special_mapping_vmops); +} + +/* + * Called with mm->mmap_lock held for writing. + * Insert a new vma covering the given region, with the given flags. + * Its pages are supplied by the given array of struct page *. + * The array can be shorter than len >> PAGE_SHIFT if it's null-terminated. + * The region past the last page supplied will always produce SIGBUS. + * The array pointer and the pages it points to are assumed to stay alive + * for as long as this mapping might exist. + */ +struct vm_area_struct *_install_special_mapping( + struct mm_struct *mm, + unsigned long addr, unsigned long len, + unsigned long vm_flags, const struct vm_special_mapping *spec) +{ + return __install_special_mapping(mm, addr, len, vm_flags, (void *)spec, + &special_mapping_vmops); +} + +int install_special_mapping(struct mm_struct *mm, + unsigned long addr, unsigned long len, + unsigned long vm_flags, struct page **pages) +{ + struct vm_area_struct *vma = __install_special_mapping( + mm, addr, len, vm_flags, (void *)pages, + &legacy_special_mapping_vmops); + + return PTR_ERR_OR_ZERO(vma); +} + +static DEFINE_MUTEX(mm_all_locks_mutex); + +static void vm_lock_anon_vma(struct mm_struct *mm, struct anon_vma *anon_vma) +{ + if (!test_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) { + /* + * The LSB of head.next can't change from under us + * because we hold the mm_all_locks_mutex. + */ + down_write_nest_lock(&anon_vma->root->rwsem, &mm->mmap_lock); + /* + * We can safely modify head.next after taking the + * anon_vma->root->rwsem. If some other vma in this mm shares + * the same anon_vma we won't take it again. + * + * No need of atomic instructions here, head.next + * can't change from under us thanks to the + * anon_vma->root->rwsem. + */ + if (__test_and_set_bit(0, (unsigned long *) + &anon_vma->root->rb_root.rb_root.rb_node)) + BUG(); + } +} + +static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping) +{ + if (!test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) { + /* + * AS_MM_ALL_LOCKS can't change from under us because + * we hold the mm_all_locks_mutex. + * + * Operations on ->flags have to be atomic because + * even if AS_MM_ALL_LOCKS is stable thanks to the + * mm_all_locks_mutex, there may be other cpus + * changing other bitflags in parallel to us. + */ + if (test_and_set_bit(AS_MM_ALL_LOCKS, &mapping->flags)) + BUG(); + down_write_nest_lock(&mapping->i_mmap_rwsem, &mm->mmap_lock); + } +} + +/* + * This operation locks against the VM for all pte/vma/mm related + * operations that could ever happen on a certain mm. This includes + * vmtruncate, try_to_unmap, and all page faults. + * + * The caller must take the mmap_lock in write mode before calling + * mm_take_all_locks(). The caller isn't allowed to release the + * mmap_lock until mm_drop_all_locks() returns. + * + * mmap_lock in write mode is required in order to block all operations + * that could modify pagetables and free pages without need of + * altering the vma layout. It's also needed in write mode to avoid new + * anon_vmas to be associated with existing vmas. + * + * A single task can't take more than one mm_take_all_locks() in a row + * or it would deadlock. + * + * The LSB in anon_vma->rb_root.rb_node and the AS_MM_ALL_LOCKS bitflag in + * mapping->flags avoid to take the same lock twice, if more than one + * vma in this mm is backed by the same anon_vma or address_space. + * + * We take locks in following order, accordingly to comment at beginning + * of mm/rmap.c: + * - all hugetlbfs_i_mmap_rwsem_key locks (aka mapping->i_mmap_rwsem for + * hugetlb mapping); + * - all i_mmap_rwsem locks; + * - all anon_vma->rwseml + * + * We can take all locks within these types randomly because the VM code + * doesn't nest them and we protected from parallel mm_take_all_locks() by + * mm_all_locks_mutex. + * + * mm_take_all_locks() and mm_drop_all_locks are expensive operations + * that may have to take thousand of locks. + * + * mm_take_all_locks() can fail if it's interrupted by signals. + */ +int mm_take_all_locks(struct mm_struct *mm) +{ + struct vm_area_struct *vma; + struct anon_vma_chain *avc; + + BUG_ON(mmap_read_trylock(mm)); + + mutex_lock(&mm_all_locks_mutex); + + for (vma = mm->mmap; vma; vma = vma->vm_next) { + if (signal_pending(current)) + goto out_unlock; + if (vma->vm_file && vma->vm_file->f_mapping && + is_vm_hugetlb_page(vma)) + vm_lock_mapping(mm, vma->vm_file->f_mapping); + } + + for (vma = mm->mmap; vma; vma = vma->vm_next) { + if (signal_pending(current)) + goto out_unlock; + if (vma->vm_file && vma->vm_file->f_mapping && + !is_vm_hugetlb_page(vma)) + vm_lock_mapping(mm, vma->vm_file->f_mapping); + } + + for (vma = mm->mmap; vma; vma = vma->vm_next) { + if (signal_pending(current)) + goto out_unlock; + if (vma->anon_vma) + list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) + vm_lock_anon_vma(mm, avc->anon_vma); + } + + return 0; + +out_unlock: + mm_drop_all_locks(mm); + return -EINTR; +} + +static void vm_unlock_anon_vma(struct anon_vma *anon_vma) +{ + if (test_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) { + /* + * The LSB of head.next can't change to 0 from under + * us because we hold the mm_all_locks_mutex. + * + * We must however clear the bitflag before unlocking + * the vma so the users using the anon_vma->rb_root will + * never see our bitflag. + * + * No need of atomic instructions here, head.next + * can't change from under us until we release the + * anon_vma->root->rwsem. + */ + if (!__test_and_clear_bit(0, (unsigned long *) + &anon_vma->root->rb_root.rb_root.rb_node)) + BUG(); + anon_vma_unlock_write(anon_vma); + } +} + +static void vm_unlock_mapping(struct address_space *mapping) +{ + if (test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) { + /* + * AS_MM_ALL_LOCKS can't change to 0 from under us + * because we hold the mm_all_locks_mutex. + */ + i_mmap_unlock_write(mapping); + if (!test_and_clear_bit(AS_MM_ALL_LOCKS, + &mapping->flags)) + BUG(); + } +} + +/* + * The mmap_lock cannot be released by the caller until + * mm_drop_all_locks() returns. + */ +void mm_drop_all_locks(struct mm_struct *mm) +{ + struct vm_area_struct *vma; + struct anon_vma_chain *avc; + + BUG_ON(mmap_read_trylock(mm)); + BUG_ON(!mutex_is_locked(&mm_all_locks_mutex)); + + for (vma = mm->mmap; vma; vma = vma->vm_next) { + if (vma->anon_vma) + list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) + vm_unlock_anon_vma(avc->anon_vma); + if (vma->vm_file && vma->vm_file->f_mapping) + vm_unlock_mapping(vma->vm_file->f_mapping); + } + + mutex_unlock(&mm_all_locks_mutex); +} + +/* + * initialise the percpu counter for VM + */ +void __init mmap_init(void) +{ + int ret; + + ret = percpu_counter_init(&vm_committed_as, 0, GFP_KERNEL); + VM_BUG_ON(ret); +} + +/* + * Initialise sysctl_user_reserve_kbytes. + * + * This is intended to prevent a user from starting a single memory hogging + * process, such that they cannot recover (kill the hog) in OVERCOMMIT_NEVER + * mode. + * + * The default value is min(3% of free memory, 128MB) + * 128MB is enough to recover with sshd/login, bash, and top/kill. + */ +static int init_user_reserve(void) +{ + unsigned long free_kbytes; + + free_kbytes = global_zone_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); + + sysctl_user_reserve_kbytes = min(free_kbytes / 32, 1UL << 17); + return 0; +} +subsys_initcall(init_user_reserve); + +/* + * Initialise sysctl_admin_reserve_kbytes. + * + * The purpose of sysctl_admin_reserve_kbytes is to allow the sys admin + * to log in and kill a memory hogging process. + * + * Systems with more than 256MB will reserve 8MB, enough to recover + * with sshd, bash, and top in OVERCOMMIT_GUESS. Smaller systems will + * only reserve 3% of free pages by default. + */ +static int init_admin_reserve(void) +{ + unsigned long free_kbytes; + + free_kbytes = global_zone_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); + + sysctl_admin_reserve_kbytes = min(free_kbytes / 32, 1UL << 13); + return 0; +} +subsys_initcall(init_admin_reserve); + +/* + * Reinititalise user and admin reserves if memory is added or removed. + * + * The default user reserve max is 128MB, and the default max for the + * admin reserve is 8MB. These are usually, but not always, enough to + * enable recovery from a memory hogging process using login/sshd, a shell, + * and tools like top. It may make sense to increase or even disable the + * reserve depending on the existence of swap or variations in the recovery + * tools. So, the admin may have changed them. + * + * If memory is added and the reserves have been eliminated or increased above + * the default max, then we'll trust the admin. + * + * If memory is removed and there isn't enough free memory, then we + * need to reset the reserves. + * + * Otherwise keep the reserve set by the admin. + */ +static int reserve_mem_notifier(struct notifier_block *nb, + unsigned long action, void *data) +{ + unsigned long tmp, free_kbytes; + + switch (action) { + case MEM_ONLINE: + /* Default max is 128MB. Leave alone if modified by operator. */ + tmp = sysctl_user_reserve_kbytes; + if (0 < tmp && tmp < (1UL << 17)) + init_user_reserve(); + + /* Default max is 8MB. Leave alone if modified by operator. */ + tmp = sysctl_admin_reserve_kbytes; + if (0 < tmp && tmp < (1UL << 13)) + init_admin_reserve(); + + break; + case MEM_OFFLINE: + free_kbytes = global_zone_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); + + if (sysctl_user_reserve_kbytes > free_kbytes) { + init_user_reserve(); + pr_info("vm.user_reserve_kbytes reset to %lu\n", + sysctl_user_reserve_kbytes); + } + + if (sysctl_admin_reserve_kbytes > free_kbytes) { + init_admin_reserve(); + pr_info("vm.admin_reserve_kbytes reset to %lu\n", + sysctl_admin_reserve_kbytes); + } + break; + default: + break; + } + return NOTIFY_OK; +} + +static struct notifier_block reserve_mem_nb = { + .notifier_call = reserve_mem_notifier, +}; + +static int __meminit init_reserve_notifier(void) +{ + if (register_hotmemory_notifier(&reserve_mem_nb)) + pr_err("Failed registering memory add/remove notifier for admin reserve\n"); + + return 0; +} +subsys_initcall(init_reserve_notifier); diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c new file mode 100644 index 000000000..205fdbb57 --- /dev/null +++ b/mm/mmu_gather.c @@ -0,0 +1,332 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#ifndef CONFIG_MMU_GATHER_NO_GATHER + +static bool tlb_next_batch(struct mmu_gather *tlb) +{ + struct mmu_gather_batch *batch; + + batch = tlb->active; + if (batch->next) { + tlb->active = batch->next; + return true; + } + + if (tlb->batch_count == MAX_GATHER_BATCH_COUNT) + return false; + + batch = (void *)__get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0); + if (!batch) + return false; + + tlb->batch_count++; + batch->next = NULL; + batch->nr = 0; + batch->max = MAX_GATHER_BATCH; + + tlb->active->next = batch; + tlb->active = batch; + + return true; +} + +static void tlb_batch_pages_flush(struct mmu_gather *tlb) +{ + struct mmu_gather_batch *batch; + + for (batch = &tlb->local; batch && batch->nr; batch = batch->next) { + free_pages_and_swap_cache(batch->pages, batch->nr); + batch->nr = 0; + } + tlb->active = &tlb->local; +} + +static void tlb_batch_list_free(struct mmu_gather *tlb) +{ + struct mmu_gather_batch *batch, *next; + + for (batch = tlb->local.next; batch; batch = next) { + next = batch->next; + free_pages((unsigned long)batch, 0); + } + tlb->local.next = NULL; +} + +bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size) +{ + struct mmu_gather_batch *batch; + + VM_BUG_ON(!tlb->end); + +#ifdef CONFIG_MMU_GATHER_PAGE_SIZE + VM_WARN_ON(tlb->page_size != page_size); +#endif + + batch = tlb->active; + /* + * Add the page and check if we are full. If so + * force a flush. + */ + batch->pages[batch->nr++] = page; + if (batch->nr == batch->max) { + if (!tlb_next_batch(tlb)) + return true; + batch = tlb->active; + } + VM_BUG_ON_PAGE(batch->nr > batch->max, page); + + return false; +} + +#endif /* MMU_GATHER_NO_GATHER */ + +#ifdef CONFIG_MMU_GATHER_TABLE_FREE + +static void __tlb_remove_table_free(struct mmu_table_batch *batch) +{ + int i; + + for (i = 0; i < batch->nr; i++) + __tlb_remove_table(batch->tables[i]); + + free_page((unsigned long)batch); +} + +#ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE + +/* + * Semi RCU freeing of the page directories. + * + * This is needed by some architectures to implement software pagetable walkers. + * + * gup_fast() and other software pagetable walkers do a lockless page-table + * walk and therefore needs some synchronization with the freeing of the page + * directories. The chosen means to accomplish that is by disabling IRQs over + * the walk. + * + * Architectures that use IPIs to flush TLBs will then automagically DTRT, + * since we unlink the page, flush TLBs, free the page. Since the disabling of + * IRQs delays the completion of the TLB flush we can never observe an already + * freed page. + * + * Architectures that do not have this (PPC) need to delay the freeing by some + * other means, this is that means. + * + * What we do is batch the freed directory pages (tables) and RCU free them. + * We use the sched RCU variant, as that guarantees that IRQ/preempt disabling + * holds off grace periods. + * + * However, in order to batch these pages we need to allocate storage, this + * allocation is deep inside the MM code and can thus easily fail on memory + * pressure. To guarantee progress we fall back to single table freeing, see + * the implementation of tlb_remove_table_one(). + * + */ + +static void tlb_remove_table_smp_sync(void *arg) +{ + /* Simply deliver the interrupt */ +} + +void tlb_remove_table_sync_one(void) +{ + /* + * This isn't an RCU grace period and hence the page-tables cannot be + * assumed to be actually RCU-freed. + * + * It is however sufficient for software page-table walkers that rely on + * IRQ disabling. + */ + smp_call_function(tlb_remove_table_smp_sync, NULL, 1); +} + +static void tlb_remove_table_rcu(struct rcu_head *head) +{ + __tlb_remove_table_free(container_of(head, struct mmu_table_batch, rcu)); +} + +static void tlb_remove_table_free(struct mmu_table_batch *batch) +{ + call_rcu(&batch->rcu, tlb_remove_table_rcu); +} + +#else /* !CONFIG_MMU_GATHER_RCU_TABLE_FREE */ + +static void tlb_remove_table_free(struct mmu_table_batch *batch) +{ + __tlb_remove_table_free(batch); +} + +#endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */ + +/* + * If we want tlb_remove_table() to imply TLB invalidates. + */ +static inline void tlb_table_invalidate(struct mmu_gather *tlb) +{ + if (tlb_needs_table_invalidate()) { + /* + * Invalidate page-table caches used by hardware walkers. Then + * we still need to RCU-sched wait while freeing the pages + * because software walkers can still be in-flight. + */ + tlb_flush_mmu_tlbonly(tlb); + } +} + +static void tlb_remove_table_one(void *table) +{ + tlb_remove_table_sync_one(); + __tlb_remove_table(table); +} + +static void tlb_table_flush(struct mmu_gather *tlb) +{ + struct mmu_table_batch **batch = &tlb->batch; + + if (*batch) { + tlb_table_invalidate(tlb); + tlb_remove_table_free(*batch); + *batch = NULL; + } +} + +void tlb_remove_table(struct mmu_gather *tlb, void *table) +{ + struct mmu_table_batch **batch = &tlb->batch; + + if (*batch == NULL) { + *batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN); + if (*batch == NULL) { + tlb_table_invalidate(tlb); + tlb_remove_table_one(table); + return; + } + (*batch)->nr = 0; + } + + (*batch)->tables[(*batch)->nr++] = table; + if ((*batch)->nr == MAX_TABLE_BATCH) + tlb_table_flush(tlb); +} + +static inline void tlb_table_init(struct mmu_gather *tlb) +{ + tlb->batch = NULL; +} + +#else /* !CONFIG_MMU_GATHER_TABLE_FREE */ + +static inline void tlb_table_flush(struct mmu_gather *tlb) { } +static inline void tlb_table_init(struct mmu_gather *tlb) { } + +#endif /* CONFIG_MMU_GATHER_TABLE_FREE */ + +static void tlb_flush_mmu_free(struct mmu_gather *tlb) +{ + tlb_table_flush(tlb); +#ifndef CONFIG_MMU_GATHER_NO_GATHER + tlb_batch_pages_flush(tlb); +#endif +} + +void tlb_flush_mmu(struct mmu_gather *tlb) +{ + tlb_flush_mmu_tlbonly(tlb); + tlb_flush_mmu_free(tlb); +} + +/** + * tlb_gather_mmu - initialize an mmu_gather structure for page-table tear-down + * @tlb: the mmu_gather structure to initialize + * @mm: the mm_struct of the target address space + * @start: start of the region that will be removed from the page-table + * @end: end of the region that will be removed from the page-table + * + * Called to initialize an (on-stack) mmu_gather structure for page-table + * tear-down from @mm. The @start and @end are set to 0 and -1 + * respectively when @mm is without users and we're going to destroy + * the full address space (exit/execve). + */ +void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, + unsigned long start, unsigned long end) +{ + tlb->mm = mm; + + /* Is it from 0 to ~0? */ + tlb->fullmm = !(start | (end+1)); + +#ifndef CONFIG_MMU_GATHER_NO_GATHER + tlb->need_flush_all = 0; + tlb->local.next = NULL; + tlb->local.nr = 0; + tlb->local.max = ARRAY_SIZE(tlb->__pages); + tlb->active = &tlb->local; + tlb->batch_count = 0; +#endif + + tlb_table_init(tlb); +#ifdef CONFIG_MMU_GATHER_PAGE_SIZE + tlb->page_size = 0; +#endif + + __tlb_reset_range(tlb); + inc_tlb_flush_pending(tlb->mm); +} + +/** + * tlb_finish_mmu - finish an mmu_gather structure + * @tlb: the mmu_gather structure to finish + * @start: start of the region that will be removed from the page-table + * @end: end of the region that will be removed from the page-table + * + * Called at the end of the shootdown operation to free up any resources that + * were required. + */ +void tlb_finish_mmu(struct mmu_gather *tlb, + unsigned long start, unsigned long end) +{ + /* + * If there are parallel threads are doing PTE changes on same range + * under non-exclusive lock (e.g., mmap_lock read-side) but defer TLB + * flush by batching, one thread may end up seeing inconsistent PTEs + * and result in having stale TLB entries. So flush TLB forcefully + * if we detect parallel PTE batching threads. + * + * However, some syscalls, e.g. munmap(), may free page tables, this + * needs force flush everything in the given range. Otherwise this + * may result in having stale TLB entries for some architectures, + * e.g. aarch64, that could specify flush what level TLB. + */ + if (mm_tlb_flush_nested(tlb->mm)) { + /* + * The aarch64 yields better performance with fullmm by + * avoiding multiple CPUs spamming TLBI messages at the + * same time. + * + * On x86 non-fullmm doesn't yield significant difference + * against fullmm. + */ + tlb->fullmm = 1; + __tlb_reset_range(tlb); + tlb->freed_tables = 1; + } + + tlb_flush_mmu(tlb); + +#ifndef CONFIG_MMU_GATHER_NO_GATHER + tlb_batch_list_free(tlb); +#endif + dec_tlb_flush_pending(tlb->mm); +} diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c new file mode 100644 index 000000000..9165ca619 --- /dev/null +++ b/mm/mmu_notifier.c @@ -0,0 +1,1139 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/mm/mmu_notifier.c + * + * Copyright (C) 2008 Qumranet, Inc. + * Copyright (C) 2008 SGI + * Christoph Lameter + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* global SRCU for all MMs */ +DEFINE_STATIC_SRCU(srcu); + +#ifdef CONFIG_LOCKDEP +struct lockdep_map __mmu_notifier_invalidate_range_start_map = { + .name = "mmu_notifier_invalidate_range_start" +}; +#endif + +/* + * The mmu_notifier_subscriptions structure is allocated and installed in + * mm->notifier_subscriptions inside the mm_take_all_locks() protected + * critical section and it's released only when mm_count reaches zero + * in mmdrop(). + */ +struct mmu_notifier_subscriptions { + /* all mmu notifiers registered in this mm are queued in this list */ + struct hlist_head list; + bool has_itree; + /* to serialize the list modifications and hlist_unhashed */ + spinlock_t lock; + unsigned long invalidate_seq; + unsigned long active_invalidate_ranges; + struct rb_root_cached itree; + wait_queue_head_t wq; + struct hlist_head deferred_list; +}; + +/* + * This is a collision-retry read-side/write-side 'lock', a lot like a + * seqcount, however this allows multiple write-sides to hold it at + * once. Conceptually the write side is protecting the values of the PTEs in + * this mm, such that PTES cannot be read into SPTEs (shadow PTEs) while any + * writer exists. + * + * Note that the core mm creates nested invalidate_range_start()/end() regions + * within the same thread, and runs invalidate_range_start()/end() in parallel + * on multiple CPUs. This is designed to not reduce concurrency or block + * progress on the mm side. + * + * As a secondary function, holding the full write side also serves to prevent + * writers for the itree, this is an optimization to avoid extra locking + * during invalidate_range_start/end notifiers. + * + * The write side has two states, fully excluded: + * - mm->active_invalidate_ranges != 0 + * - subscriptions->invalidate_seq & 1 == True (odd) + * - some range on the mm_struct is being invalidated + * - the itree is not allowed to change + * + * And partially excluded: + * - mm->active_invalidate_ranges != 0 + * - subscriptions->invalidate_seq & 1 == False (even) + * - some range on the mm_struct is being invalidated + * - the itree is allowed to change + * + * Operations on notifier_subscriptions->invalidate_seq (under spinlock): + * seq |= 1 # Begin writing + * seq++ # Release the writing state + * seq & 1 # True if a writer exists + * + * The later state avoids some expensive work on inv_end in the common case of + * no mmu_interval_notifier monitoring the VA. + */ +static bool +mn_itree_is_invalidating(struct mmu_notifier_subscriptions *subscriptions) +{ + lockdep_assert_held(&subscriptions->lock); + return subscriptions->invalidate_seq & 1; +} + +static struct mmu_interval_notifier * +mn_itree_inv_start_range(struct mmu_notifier_subscriptions *subscriptions, + const struct mmu_notifier_range *range, + unsigned long *seq) +{ + struct interval_tree_node *node; + struct mmu_interval_notifier *res = NULL; + + spin_lock(&subscriptions->lock); + subscriptions->active_invalidate_ranges++; + node = interval_tree_iter_first(&subscriptions->itree, range->start, + range->end - 1); + if (node) { + subscriptions->invalidate_seq |= 1; + res = container_of(node, struct mmu_interval_notifier, + interval_tree); + } + + *seq = subscriptions->invalidate_seq; + spin_unlock(&subscriptions->lock); + return res; +} + +static struct mmu_interval_notifier * +mn_itree_inv_next(struct mmu_interval_notifier *interval_sub, + const struct mmu_notifier_range *range) +{ + struct interval_tree_node *node; + + node = interval_tree_iter_next(&interval_sub->interval_tree, + range->start, range->end - 1); + if (!node) + return NULL; + return container_of(node, struct mmu_interval_notifier, interval_tree); +} + +static void mn_itree_inv_end(struct mmu_notifier_subscriptions *subscriptions) +{ + struct mmu_interval_notifier *interval_sub; + struct hlist_node *next; + + spin_lock(&subscriptions->lock); + if (--subscriptions->active_invalidate_ranges || + !mn_itree_is_invalidating(subscriptions)) { + spin_unlock(&subscriptions->lock); + return; + } + + /* Make invalidate_seq even */ + subscriptions->invalidate_seq++; + + /* + * The inv_end incorporates a deferred mechanism like rtnl_unlock(). + * Adds and removes are queued until the final inv_end happens then + * they are progressed. This arrangement for tree updates is used to + * avoid using a blocking lock during invalidate_range_start. + */ + hlist_for_each_entry_safe(interval_sub, next, + &subscriptions->deferred_list, + deferred_item) { + if (RB_EMPTY_NODE(&interval_sub->interval_tree.rb)) + interval_tree_insert(&interval_sub->interval_tree, + &subscriptions->itree); + else + interval_tree_remove(&interval_sub->interval_tree, + &subscriptions->itree); + hlist_del(&interval_sub->deferred_item); + } + spin_unlock(&subscriptions->lock); + + wake_up_all(&subscriptions->wq); +} + +/** + * mmu_interval_read_begin - Begin a read side critical section against a VA + * range + * @interval_sub: The interval subscription + * + * mmu_iterval_read_begin()/mmu_iterval_read_retry() implement a + * collision-retry scheme similar to seqcount for the VA range under + * subscription. If the mm invokes invalidation during the critical section + * then mmu_interval_read_retry() will return true. + * + * This is useful to obtain shadow PTEs where teardown or setup of the SPTEs + * require a blocking context. The critical region formed by this can sleep, + * and the required 'user_lock' can also be a sleeping lock. + * + * The caller is required to provide a 'user_lock' to serialize both teardown + * and setup. + * + * The return value should be passed to mmu_interval_read_retry(). + */ +unsigned long +mmu_interval_read_begin(struct mmu_interval_notifier *interval_sub) +{ + struct mmu_notifier_subscriptions *subscriptions = + interval_sub->mm->notifier_subscriptions; + unsigned long seq; + bool is_invalidating; + + /* + * If the subscription has a different seq value under the user_lock + * than we started with then it has collided. + * + * If the subscription currently has the same seq value as the + * subscriptions seq, then it is currently between + * invalidate_start/end and is colliding. + * + * The locking looks broadly like this: + * mn_tree_invalidate_start(): mmu_interval_read_begin(): + * spin_lock + * seq = READ_ONCE(interval_sub->invalidate_seq); + * seq == subs->invalidate_seq + * spin_unlock + * spin_lock + * seq = ++subscriptions->invalidate_seq + * spin_unlock + * op->invalidate_range(): + * user_lock + * mmu_interval_set_seq() + * interval_sub->invalidate_seq = seq + * user_unlock + * + * [Required: mmu_interval_read_retry() == true] + * + * mn_itree_inv_end(): + * spin_lock + * seq = ++subscriptions->invalidate_seq + * spin_unlock + * + * user_lock + * mmu_interval_read_retry(): + * interval_sub->invalidate_seq != seq + * user_unlock + * + * Barriers are not needed here as any races here are closed by an + * eventual mmu_interval_read_retry(), which provides a barrier via the + * user_lock. + */ + spin_lock(&subscriptions->lock); + /* Pairs with the WRITE_ONCE in mmu_interval_set_seq() */ + seq = READ_ONCE(interval_sub->invalidate_seq); + is_invalidating = seq == subscriptions->invalidate_seq; + spin_unlock(&subscriptions->lock); + + /* + * interval_sub->invalidate_seq must always be set to an odd value via + * mmu_interval_set_seq() using the provided cur_seq from + * mn_itree_inv_start_range(). This ensures that if seq does wrap we + * will always clear the below sleep in some reasonable time as + * subscriptions->invalidate_seq is even in the idle state. + */ + lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); + lock_map_release(&__mmu_notifier_invalidate_range_start_map); + if (is_invalidating) + wait_event(subscriptions->wq, + READ_ONCE(subscriptions->invalidate_seq) != seq); + + /* + * Notice that mmu_interval_read_retry() can already be true at this + * point, avoiding loops here allows the caller to provide a global + * time bound. + */ + + return seq; +} +EXPORT_SYMBOL_GPL(mmu_interval_read_begin); + +static void mn_itree_release(struct mmu_notifier_subscriptions *subscriptions, + struct mm_struct *mm) +{ + struct mmu_notifier_range range = { + .flags = MMU_NOTIFIER_RANGE_BLOCKABLE, + .event = MMU_NOTIFY_RELEASE, + .mm = mm, + .start = 0, + .end = ULONG_MAX, + }; + struct mmu_interval_notifier *interval_sub; + unsigned long cur_seq; + bool ret; + + for (interval_sub = + mn_itree_inv_start_range(subscriptions, &range, &cur_seq); + interval_sub; + interval_sub = mn_itree_inv_next(interval_sub, &range)) { + ret = interval_sub->ops->invalidate(interval_sub, &range, + cur_seq); + WARN_ON(!ret); + } + + mn_itree_inv_end(subscriptions); +} + +/* + * This function can't run concurrently against mmu_notifier_register + * because mm->mm_users > 0 during mmu_notifier_register and exit_mmap + * runs with mm_users == 0. Other tasks may still invoke mmu notifiers + * in parallel despite there being no task using this mm any more, + * through the vmas outside of the exit_mmap context, such as with + * vmtruncate. This serializes against mmu_notifier_unregister with + * the notifier_subscriptions->lock in addition to SRCU and it serializes + * against the other mmu notifiers with SRCU. struct mmu_notifier_subscriptions + * can't go away from under us as exit_mmap holds an mm_count pin + * itself. + */ +static void mn_hlist_release(struct mmu_notifier_subscriptions *subscriptions, + struct mm_struct *mm) +{ + struct mmu_notifier *subscription; + int id; + + /* + * SRCU here will block mmu_notifier_unregister until + * ->release returns. + */ + id = srcu_read_lock(&srcu); + hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist, + srcu_read_lock_held(&srcu)) + /* + * If ->release runs before mmu_notifier_unregister it must be + * handled, as it's the only way for the driver to flush all + * existing sptes and stop the driver from establishing any more + * sptes before all the pages in the mm are freed. + */ + if (subscription->ops->release) + subscription->ops->release(subscription, mm); + + spin_lock(&subscriptions->lock); + while (unlikely(!hlist_empty(&subscriptions->list))) { + subscription = hlist_entry(subscriptions->list.first, + struct mmu_notifier, hlist); + /* + * We arrived before mmu_notifier_unregister so + * mmu_notifier_unregister will do nothing other than to wait + * for ->release to finish and for mmu_notifier_unregister to + * return. + */ + hlist_del_init_rcu(&subscription->hlist); + } + spin_unlock(&subscriptions->lock); + srcu_read_unlock(&srcu, id); + + /* + * synchronize_srcu here prevents mmu_notifier_release from returning to + * exit_mmap (which would proceed with freeing all pages in the mm) + * until the ->release method returns, if it was invoked by + * mmu_notifier_unregister. + * + * The notifier_subscriptions can't go away from under us because + * one mm_count is held by exit_mmap. + */ + synchronize_srcu(&srcu); +} + +void __mmu_notifier_release(struct mm_struct *mm) +{ + struct mmu_notifier_subscriptions *subscriptions = + mm->notifier_subscriptions; + + if (subscriptions->has_itree) + mn_itree_release(subscriptions, mm); + + if (!hlist_empty(&subscriptions->list)) + mn_hlist_release(subscriptions, mm); +} + +/* + * If no young bitflag is supported by the hardware, ->clear_flush_young can + * unmap the address and return 1 or 0 depending if the mapping previously + * existed or not. + */ +int __mmu_notifier_clear_flush_young(struct mm_struct *mm, + unsigned long start, + unsigned long end) +{ + struct mmu_notifier *subscription; + int young = 0, id; + + id = srcu_read_lock(&srcu); + hlist_for_each_entry_rcu(subscription, + &mm->notifier_subscriptions->list, hlist, + srcu_read_lock_held(&srcu)) { + if (subscription->ops->clear_flush_young) + young |= subscription->ops->clear_flush_young( + subscription, mm, start, end); + } + srcu_read_unlock(&srcu, id); + + return young; +} + +int __mmu_notifier_clear_young(struct mm_struct *mm, + unsigned long start, + unsigned long end) +{ + struct mmu_notifier *subscription; + int young = 0, id; + + id = srcu_read_lock(&srcu); + hlist_for_each_entry_rcu(subscription, + &mm->notifier_subscriptions->list, hlist, + srcu_read_lock_held(&srcu)) { + if (subscription->ops->clear_young) + young |= subscription->ops->clear_young(subscription, + mm, start, end); + } + srcu_read_unlock(&srcu, id); + + return young; +} + +int __mmu_notifier_test_young(struct mm_struct *mm, + unsigned long address) +{ + struct mmu_notifier *subscription; + int young = 0, id; + + id = srcu_read_lock(&srcu); + hlist_for_each_entry_rcu(subscription, + &mm->notifier_subscriptions->list, hlist, + srcu_read_lock_held(&srcu)) { + if (subscription->ops->test_young) { + young = subscription->ops->test_young(subscription, mm, + address); + if (young) + break; + } + } + srcu_read_unlock(&srcu, id); + + return young; +} + +void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address, + pte_t pte) +{ + struct mmu_notifier *subscription; + int id; + + id = srcu_read_lock(&srcu); + hlist_for_each_entry_rcu(subscription, + &mm->notifier_subscriptions->list, hlist, + srcu_read_lock_held(&srcu)) { + if (subscription->ops->change_pte) + subscription->ops->change_pte(subscription, mm, address, + pte); + } + srcu_read_unlock(&srcu, id); +} + +static int mn_itree_invalidate(struct mmu_notifier_subscriptions *subscriptions, + const struct mmu_notifier_range *range) +{ + struct mmu_interval_notifier *interval_sub; + unsigned long cur_seq; + + for (interval_sub = + mn_itree_inv_start_range(subscriptions, range, &cur_seq); + interval_sub; + interval_sub = mn_itree_inv_next(interval_sub, range)) { + bool ret; + + ret = interval_sub->ops->invalidate(interval_sub, range, + cur_seq); + if (!ret) { + if (WARN_ON(mmu_notifier_range_blockable(range))) + continue; + goto out_would_block; + } + } + return 0; + +out_would_block: + /* + * On -EAGAIN the non-blocking caller is not allowed to call + * invalidate_range_end() + */ + mn_itree_inv_end(subscriptions); + return -EAGAIN; +} + +static int mn_hlist_invalidate_range_start( + struct mmu_notifier_subscriptions *subscriptions, + struct mmu_notifier_range *range) +{ + struct mmu_notifier *subscription; + int ret = 0; + int id; + + id = srcu_read_lock(&srcu); + hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist, + srcu_read_lock_held(&srcu)) { + const struct mmu_notifier_ops *ops = subscription->ops; + + if (ops->invalidate_range_start) { + int _ret; + + if (!mmu_notifier_range_blockable(range)) + non_block_start(); + _ret = ops->invalidate_range_start(subscription, range); + if (!mmu_notifier_range_blockable(range)) + non_block_end(); + if (_ret) { + pr_info("%pS callback failed with %d in %sblockable context.\n", + ops->invalidate_range_start, _ret, + !mmu_notifier_range_blockable(range) ? + "non-" : + ""); + WARN_ON(mmu_notifier_range_blockable(range) || + _ret != -EAGAIN); + /* + * We call all the notifiers on any EAGAIN, + * there is no way for a notifier to know if + * its start method failed, thus a start that + * does EAGAIN can't also do end. + */ + WARN_ON(ops->invalidate_range_end); + ret = _ret; + } + } + } + + if (ret) { + /* + * Must be non-blocking to get here. If there are multiple + * notifiers and one or more failed start, any that succeeded + * start are expecting their end to be called. Do so now. + */ + hlist_for_each_entry_rcu(subscription, &subscriptions->list, + hlist, srcu_read_lock_held(&srcu)) { + if (!subscription->ops->invalidate_range_end) + continue; + + subscription->ops->invalidate_range_end(subscription, + range); + } + } + srcu_read_unlock(&srcu, id); + + return ret; +} + +int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) +{ + struct mmu_notifier_subscriptions *subscriptions = + range->mm->notifier_subscriptions; + int ret; + + if (subscriptions->has_itree) { + ret = mn_itree_invalidate(subscriptions, range); + if (ret) + return ret; + } + if (!hlist_empty(&subscriptions->list)) + return mn_hlist_invalidate_range_start(subscriptions, range); + return 0; +} + +static void +mn_hlist_invalidate_end(struct mmu_notifier_subscriptions *subscriptions, + struct mmu_notifier_range *range, bool only_end) +{ + struct mmu_notifier *subscription; + int id; + + id = srcu_read_lock(&srcu); + hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist, + srcu_read_lock_held(&srcu)) { + /* + * Call invalidate_range here too to avoid the need for the + * subsystem of having to register an invalidate_range_end + * call-back when there is invalidate_range already. Usually a + * subsystem registers either invalidate_range_start()/end() or + * invalidate_range(), so this will be no additional overhead + * (besides the pointer check). + * + * We skip call to invalidate_range() if we know it is safe ie + * call site use mmu_notifier_invalidate_range_only_end() which + * is safe to do when we know that a call to invalidate_range() + * already happen under page table lock. + */ + if (!only_end && subscription->ops->invalidate_range) + subscription->ops->invalidate_range(subscription, + range->mm, + range->start, + range->end); + if (subscription->ops->invalidate_range_end) { + if (!mmu_notifier_range_blockable(range)) + non_block_start(); + subscription->ops->invalidate_range_end(subscription, + range); + if (!mmu_notifier_range_blockable(range)) + non_block_end(); + } + } + srcu_read_unlock(&srcu, id); +} + +void __mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range, + bool only_end) +{ + struct mmu_notifier_subscriptions *subscriptions = + range->mm->notifier_subscriptions; + + lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); + if (subscriptions->has_itree) + mn_itree_inv_end(subscriptions); + + if (!hlist_empty(&subscriptions->list)) + mn_hlist_invalidate_end(subscriptions, range, only_end); + lock_map_release(&__mmu_notifier_invalidate_range_start_map); +} + +void __mmu_notifier_invalidate_range(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ + struct mmu_notifier *subscription; + int id; + + id = srcu_read_lock(&srcu); + hlist_for_each_entry_rcu(subscription, + &mm->notifier_subscriptions->list, hlist, + srcu_read_lock_held(&srcu)) { + if (subscription->ops->invalidate_range) + subscription->ops->invalidate_range(subscription, mm, + start, end); + } + srcu_read_unlock(&srcu, id); +} + +/* + * Same as mmu_notifier_register but here the caller must hold the mmap_lock in + * write mode. A NULL mn signals the notifier is being registered for itree + * mode. + */ +int __mmu_notifier_register(struct mmu_notifier *subscription, + struct mm_struct *mm) +{ + struct mmu_notifier_subscriptions *subscriptions = NULL; + int ret; + + mmap_assert_write_locked(mm); + BUG_ON(atomic_read(&mm->mm_users) <= 0); + + if (IS_ENABLED(CONFIG_LOCKDEP)) { + fs_reclaim_acquire(GFP_KERNEL); + lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); + lock_map_release(&__mmu_notifier_invalidate_range_start_map); + fs_reclaim_release(GFP_KERNEL); + } + + if (!mm->notifier_subscriptions) { + /* + * kmalloc cannot be called under mm_take_all_locks(), but we + * know that mm->notifier_subscriptions can't change while we + * hold the write side of the mmap_lock. + */ + subscriptions = kzalloc( + sizeof(struct mmu_notifier_subscriptions), GFP_KERNEL); + if (!subscriptions) + return -ENOMEM; + + INIT_HLIST_HEAD(&subscriptions->list); + spin_lock_init(&subscriptions->lock); + subscriptions->invalidate_seq = 2; + subscriptions->itree = RB_ROOT_CACHED; + init_waitqueue_head(&subscriptions->wq); + INIT_HLIST_HEAD(&subscriptions->deferred_list); + } + + ret = mm_take_all_locks(mm); + if (unlikely(ret)) + goto out_clean; + + /* + * Serialize the update against mmu_notifier_unregister. A + * side note: mmu_notifier_release can't run concurrently with + * us because we hold the mm_users pin (either implicitly as + * current->mm or explicitly with get_task_mm() or similar). + * We can't race against any other mmu notifier method either + * thanks to mm_take_all_locks(). + * + * release semantics on the initialization of the + * mmu_notifier_subscriptions's contents are provided for unlocked + * readers. acquire can only be used while holding the mmgrab or + * mmget, and is safe because once created the + * mmu_notifier_subscriptions is not freed until the mm is destroyed. + * As above, users holding the mmap_lock or one of the + * mm_take_all_locks() do not need to use acquire semantics. + */ + if (subscriptions) + smp_store_release(&mm->notifier_subscriptions, subscriptions); + + if (subscription) { + /* Pairs with the mmdrop in mmu_notifier_unregister_* */ + mmgrab(mm); + subscription->mm = mm; + subscription->users = 1; + + spin_lock(&mm->notifier_subscriptions->lock); + hlist_add_head_rcu(&subscription->hlist, + &mm->notifier_subscriptions->list); + spin_unlock(&mm->notifier_subscriptions->lock); + } else + mm->notifier_subscriptions->has_itree = true; + + mm_drop_all_locks(mm); + BUG_ON(atomic_read(&mm->mm_users) <= 0); + return 0; + +out_clean: + kfree(subscriptions); + return ret; +} +EXPORT_SYMBOL_GPL(__mmu_notifier_register); + +/** + * mmu_notifier_register - Register a notifier on a mm + * @subscription: The notifier to attach + * @mm: The mm to attach the notifier to + * + * Must not hold mmap_lock nor any other VM related lock when calling + * this registration function. Must also ensure mm_users can't go down + * to zero while this runs to avoid races with mmu_notifier_release, + * so mm has to be current->mm or the mm should be pinned safely such + * as with get_task_mm(). If the mm is not current->mm, the mm_users + * pin should be released by calling mmput after mmu_notifier_register + * returns. + * + * mmu_notifier_unregister() or mmu_notifier_put() must be always called to + * unregister the notifier. + * + * While the caller has a mmu_notifier get the subscription->mm pointer will remain + * valid, and can be converted to an active mm pointer via mmget_not_zero(). + */ +int mmu_notifier_register(struct mmu_notifier *subscription, + struct mm_struct *mm) +{ + int ret; + + mmap_write_lock(mm); + ret = __mmu_notifier_register(subscription, mm); + mmap_write_unlock(mm); + return ret; +} +EXPORT_SYMBOL_GPL(mmu_notifier_register); + +static struct mmu_notifier * +find_get_mmu_notifier(struct mm_struct *mm, const struct mmu_notifier_ops *ops) +{ + struct mmu_notifier *subscription; + + spin_lock(&mm->notifier_subscriptions->lock); + hlist_for_each_entry_rcu(subscription, + &mm->notifier_subscriptions->list, hlist, + lockdep_is_held(&mm->notifier_subscriptions->lock)) { + if (subscription->ops != ops) + continue; + + if (likely(subscription->users != UINT_MAX)) + subscription->users++; + else + subscription = ERR_PTR(-EOVERFLOW); + spin_unlock(&mm->notifier_subscriptions->lock); + return subscription; + } + spin_unlock(&mm->notifier_subscriptions->lock); + return NULL; +} + +/** + * mmu_notifier_get_locked - Return the single struct mmu_notifier for + * the mm & ops + * @ops: The operations struct being subscribe with + * @mm : The mm to attach notifiers too + * + * This function either allocates a new mmu_notifier via + * ops->alloc_notifier(), or returns an already existing notifier on the + * list. The value of the ops pointer is used to determine when two notifiers + * are the same. + * + * Each call to mmu_notifier_get() must be paired with a call to + * mmu_notifier_put(). The caller must hold the write side of mm->mmap_lock. + * + * While the caller has a mmu_notifier get the mm pointer will remain valid, + * and can be converted to an active mm pointer via mmget_not_zero(). + */ +struct mmu_notifier *mmu_notifier_get_locked(const struct mmu_notifier_ops *ops, + struct mm_struct *mm) +{ + struct mmu_notifier *subscription; + int ret; + + mmap_assert_write_locked(mm); + + if (mm->notifier_subscriptions) { + subscription = find_get_mmu_notifier(mm, ops); + if (subscription) + return subscription; + } + + subscription = ops->alloc_notifier(mm); + if (IS_ERR(subscription)) + return subscription; + subscription->ops = ops; + ret = __mmu_notifier_register(subscription, mm); + if (ret) + goto out_free; + return subscription; +out_free: + subscription->ops->free_notifier(subscription); + return ERR_PTR(ret); +} +EXPORT_SYMBOL_GPL(mmu_notifier_get_locked); + +/* this is called after the last mmu_notifier_unregister() returned */ +void __mmu_notifier_subscriptions_destroy(struct mm_struct *mm) +{ + BUG_ON(!hlist_empty(&mm->notifier_subscriptions->list)); + kfree(mm->notifier_subscriptions); + mm->notifier_subscriptions = LIST_POISON1; /* debug */ +} + +/* + * This releases the mm_count pin automatically and frees the mm + * structure if it was the last user of it. It serializes against + * running mmu notifiers with SRCU and against mmu_notifier_unregister + * with the unregister lock + SRCU. All sptes must be dropped before + * calling mmu_notifier_unregister. ->release or any other notifier + * method may be invoked concurrently with mmu_notifier_unregister, + * and only after mmu_notifier_unregister returned we're guaranteed + * that ->release or any other method can't run anymore. + */ +void mmu_notifier_unregister(struct mmu_notifier *subscription, + struct mm_struct *mm) +{ + BUG_ON(atomic_read(&mm->mm_count) <= 0); + + if (!hlist_unhashed(&subscription->hlist)) { + /* + * SRCU here will force exit_mmap to wait for ->release to + * finish before freeing the pages. + */ + int id; + + id = srcu_read_lock(&srcu); + /* + * exit_mmap will block in mmu_notifier_release to guarantee + * that ->release is called before freeing the pages. + */ + if (subscription->ops->release) + subscription->ops->release(subscription, mm); + srcu_read_unlock(&srcu, id); + + spin_lock(&mm->notifier_subscriptions->lock); + /* + * Can not use list_del_rcu() since __mmu_notifier_release + * can delete it before we hold the lock. + */ + hlist_del_init_rcu(&subscription->hlist); + spin_unlock(&mm->notifier_subscriptions->lock); + } + + /* + * Wait for any running method to finish, of course including + * ->release if it was run by mmu_notifier_release instead of us. + */ + synchronize_srcu(&srcu); + + BUG_ON(atomic_read(&mm->mm_count) <= 0); + + mmdrop(mm); +} +EXPORT_SYMBOL_GPL(mmu_notifier_unregister); + +static void mmu_notifier_free_rcu(struct rcu_head *rcu) +{ + struct mmu_notifier *subscription = + container_of(rcu, struct mmu_notifier, rcu); + struct mm_struct *mm = subscription->mm; + + subscription->ops->free_notifier(subscription); + /* Pairs with the get in __mmu_notifier_register() */ + mmdrop(mm); +} + +/** + * mmu_notifier_put - Release the reference on the notifier + * @subscription: The notifier to act on + * + * This function must be paired with each mmu_notifier_get(), it releases the + * reference obtained by the get. If this is the last reference then process + * to free the notifier will be run asynchronously. + * + * Unlike mmu_notifier_unregister() the get/put flow only calls ops->release + * when the mm_struct is destroyed. Instead free_notifier is always called to + * release any resources held by the user. + * + * As ops->release is not guaranteed to be called, the user must ensure that + * all sptes are dropped, and no new sptes can be established before + * mmu_notifier_put() is called. + * + * This function can be called from the ops->release callback, however the + * caller must still ensure it is called pairwise with mmu_notifier_get(). + * + * Modules calling this function must call mmu_notifier_synchronize() in + * their __exit functions to ensure the async work is completed. + */ +void mmu_notifier_put(struct mmu_notifier *subscription) +{ + struct mm_struct *mm = subscription->mm; + + spin_lock(&mm->notifier_subscriptions->lock); + if (WARN_ON(!subscription->users) || --subscription->users) + goto out_unlock; + hlist_del_init_rcu(&subscription->hlist); + spin_unlock(&mm->notifier_subscriptions->lock); + + call_srcu(&srcu, &subscription->rcu, mmu_notifier_free_rcu); + return; + +out_unlock: + spin_unlock(&mm->notifier_subscriptions->lock); +} +EXPORT_SYMBOL_GPL(mmu_notifier_put); + +static int __mmu_interval_notifier_insert( + struct mmu_interval_notifier *interval_sub, struct mm_struct *mm, + struct mmu_notifier_subscriptions *subscriptions, unsigned long start, + unsigned long length, const struct mmu_interval_notifier_ops *ops) +{ + interval_sub->mm = mm; + interval_sub->ops = ops; + RB_CLEAR_NODE(&interval_sub->interval_tree.rb); + interval_sub->interval_tree.start = start; + /* + * Note that the representation of the intervals in the interval tree + * considers the ending point as contained in the interval. + */ + if (length == 0 || + check_add_overflow(start, length - 1, + &interval_sub->interval_tree.last)) + return -EOVERFLOW; + + /* Must call with a mmget() held */ + if (WARN_ON(atomic_read(&mm->mm_users) <= 0)) + return -EINVAL; + + /* pairs with mmdrop in mmu_interval_notifier_remove() */ + mmgrab(mm); + + /* + * If some invalidate_range_start/end region is going on in parallel + * we don't know what VA ranges are affected, so we must assume this + * new range is included. + * + * If the itree is invalidating then we are not allowed to change + * it. Retrying until invalidation is done is tricky due to the + * possibility for live lock, instead defer the add to + * mn_itree_inv_end() so this algorithm is deterministic. + * + * In all cases the value for the interval_sub->invalidate_seq should be + * odd, see mmu_interval_read_begin() + */ + spin_lock(&subscriptions->lock); + if (subscriptions->active_invalidate_ranges) { + if (mn_itree_is_invalidating(subscriptions)) + hlist_add_head(&interval_sub->deferred_item, + &subscriptions->deferred_list); + else { + subscriptions->invalidate_seq |= 1; + interval_tree_insert(&interval_sub->interval_tree, + &subscriptions->itree); + } + interval_sub->invalidate_seq = subscriptions->invalidate_seq; + } else { + WARN_ON(mn_itree_is_invalidating(subscriptions)); + /* + * The starting seq for a subscription not under invalidation + * should be odd, not equal to the current invalidate_seq and + * invalidate_seq should not 'wrap' to the new seq any time + * soon. + */ + interval_sub->invalidate_seq = + subscriptions->invalidate_seq - 1; + interval_tree_insert(&interval_sub->interval_tree, + &subscriptions->itree); + } + spin_unlock(&subscriptions->lock); + return 0; +} + +/** + * mmu_interval_notifier_insert - Insert an interval notifier + * @interval_sub: Interval subscription to register + * @start: Starting virtual address to monitor + * @length: Length of the range to monitor + * @mm: mm_struct to attach to + * @ops: Interval notifier operations to be called on matching events + * + * This function subscribes the interval notifier for notifications from the + * mm. Upon return the ops related to mmu_interval_notifier will be called + * whenever an event that intersects with the given range occurs. + * + * Upon return the range_notifier may not be present in the interval tree yet. + * The caller must use the normal interval notifier read flow via + * mmu_interval_read_begin() to establish SPTEs for this range. + */ +int mmu_interval_notifier_insert(struct mmu_interval_notifier *interval_sub, + struct mm_struct *mm, unsigned long start, + unsigned long length, + const struct mmu_interval_notifier_ops *ops) +{ + struct mmu_notifier_subscriptions *subscriptions; + int ret; + + might_lock(&mm->mmap_lock); + + subscriptions = smp_load_acquire(&mm->notifier_subscriptions); + if (!subscriptions || !subscriptions->has_itree) { + ret = mmu_notifier_register(NULL, mm); + if (ret) + return ret; + subscriptions = mm->notifier_subscriptions; + } + return __mmu_interval_notifier_insert(interval_sub, mm, subscriptions, + start, length, ops); +} +EXPORT_SYMBOL_GPL(mmu_interval_notifier_insert); + +int mmu_interval_notifier_insert_locked( + struct mmu_interval_notifier *interval_sub, struct mm_struct *mm, + unsigned long start, unsigned long length, + const struct mmu_interval_notifier_ops *ops) +{ + struct mmu_notifier_subscriptions *subscriptions = + mm->notifier_subscriptions; + int ret; + + mmap_assert_write_locked(mm); + + if (!subscriptions || !subscriptions->has_itree) { + ret = __mmu_notifier_register(NULL, mm); + if (ret) + return ret; + subscriptions = mm->notifier_subscriptions; + } + return __mmu_interval_notifier_insert(interval_sub, mm, subscriptions, + start, length, ops); +} +EXPORT_SYMBOL_GPL(mmu_interval_notifier_insert_locked); + +static bool +mmu_interval_seq_released(struct mmu_notifier_subscriptions *subscriptions, + unsigned long seq) +{ + bool ret; + + spin_lock(&subscriptions->lock); + ret = subscriptions->invalidate_seq != seq; + spin_unlock(&subscriptions->lock); + return ret; +} + +/** + * mmu_interval_notifier_remove - Remove a interval notifier + * @interval_sub: Interval subscription to unregister + * + * This function must be paired with mmu_interval_notifier_insert(). It cannot + * be called from any ops callback. + * + * Once this returns ops callbacks are no longer running on other CPUs and + * will not be called in future. + */ +void mmu_interval_notifier_remove(struct mmu_interval_notifier *interval_sub) +{ + struct mm_struct *mm = interval_sub->mm; + struct mmu_notifier_subscriptions *subscriptions = + mm->notifier_subscriptions; + unsigned long seq = 0; + + might_sleep(); + + spin_lock(&subscriptions->lock); + if (mn_itree_is_invalidating(subscriptions)) { + /* + * remove is being called after insert put this on the + * deferred list, but before the deferred list was processed. + */ + if (RB_EMPTY_NODE(&interval_sub->interval_tree.rb)) { + hlist_del(&interval_sub->deferred_item); + } else { + hlist_add_head(&interval_sub->deferred_item, + &subscriptions->deferred_list); + seq = subscriptions->invalidate_seq; + } + } else { + WARN_ON(RB_EMPTY_NODE(&interval_sub->interval_tree.rb)); + interval_tree_remove(&interval_sub->interval_tree, + &subscriptions->itree); + } + spin_unlock(&subscriptions->lock); + + /* + * The possible sleep on progress in the invalidation requires the + * caller not hold any locks held by invalidation callbacks. + */ + lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); + lock_map_release(&__mmu_notifier_invalidate_range_start_map); + if (seq) + wait_event(subscriptions->wq, + mmu_interval_seq_released(subscriptions, seq)); + + /* pairs with mmgrab in mmu_interval_notifier_insert() */ + mmdrop(mm); +} +EXPORT_SYMBOL_GPL(mmu_interval_notifier_remove); + +/** + * mmu_notifier_synchronize - Ensure all mmu_notifiers are freed + * + * This function ensures that all outstanding async SRU work from + * mmu_notifier_put() is completed. After it returns any mmu_notifier_ops + * associated with an unused mmu_notifier will no longer be called. + * + * Before using the caller must ensure that all of its mmu_notifiers have been + * fully released via mmu_notifier_put(). + * + * Modules using the mmu_notifier_put() API should call this in their __exit + * function to avoid module unloading races. + */ +void mmu_notifier_synchronize(void) +{ + synchronize_srcu(&srcu); +} +EXPORT_SYMBOL_GPL(mmu_notifier_synchronize); + +bool +mmu_notifier_range_update_to_read_only(const struct mmu_notifier_range *range) +{ + if (!range->vma || range->event != MMU_NOTIFY_PROTECTION_VMA) + return false; + /* Return true if the vma still have the read flag set. */ + return range->vma->vm_flags & VM_READ; +} +EXPORT_SYMBOL_GPL(mmu_notifier_range_update_to_read_only); diff --git a/mm/mmzone.c b/mm/mmzone.c new file mode 100644 index 000000000..f337831af --- /dev/null +++ b/mm/mmzone.c @@ -0,0 +1,101 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/mm/mmzone.c + * + * management codes for pgdats, zones and page flags + */ + + +#include +#include +#include + +struct pglist_data *first_online_pgdat(void) +{ + return NODE_DATA(first_online_node); +} + +struct pglist_data *next_online_pgdat(struct pglist_data *pgdat) +{ + int nid = next_online_node(pgdat->node_id); + + if (nid == MAX_NUMNODES) + return NULL; + return NODE_DATA(nid); +} + +/* + * next_zone - helper magic for for_each_zone() + */ +struct zone *next_zone(struct zone *zone) +{ + pg_data_t *pgdat = zone->zone_pgdat; + + if (zone < pgdat->node_zones + MAX_NR_ZONES - 1) + zone++; + else { + pgdat = next_online_pgdat(pgdat); + if (pgdat) + zone = pgdat->node_zones; + else + zone = NULL; + } + return zone; +} + +static inline int zref_in_nodemask(struct zoneref *zref, nodemask_t *nodes) +{ +#ifdef CONFIG_NUMA + return node_isset(zonelist_node_idx(zref), *nodes); +#else + return 1; +#endif /* CONFIG_NUMA */ +} + +/* Returns the next zone at or below highest_zoneidx in a zonelist */ +struct zoneref *__next_zones_zonelist(struct zoneref *z, + enum zone_type highest_zoneidx, + nodemask_t *nodes) +{ + /* + * Find the next suitable zone to use for the allocation. + * Only filter based on nodemask if it's set + */ + if (unlikely(nodes == NULL)) + while (zonelist_zone_idx(z) > highest_zoneidx) + z++; + else + while (zonelist_zone_idx(z) > highest_zoneidx || + (z->zone && !zref_in_nodemask(z, nodes))) + z++; + + return z; +} + +void lruvec_init(struct lruvec *lruvec) +{ + enum lru_list lru; + + memset(lruvec, 0, sizeof(struct lruvec)); + + for_each_lru(lru) + INIT_LIST_HEAD(&lruvec->lists[lru]); +} + +#if defined(CONFIG_NUMA_BALANCING) && !defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) +int page_cpupid_xchg_last(struct page *page, int cpupid) +{ + unsigned long old_flags, flags; + int last_cpupid; + + do { + old_flags = flags = page->flags; + last_cpupid = page_cpupid_last(page); + + flags &= ~(LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT); + flags |= (cpupid & LAST_CPUPID_MASK) << LAST_CPUPID_PGSHIFT; + } while (unlikely(cmpxchg(&page->flags, old_flags, flags) != old_flags)); + + return last_cpupid; +} +#endif diff --git a/mm/mprotect.c b/mm/mprotect.c new file mode 100644 index 000000000..7ea0aee0c --- /dev/null +++ b/mm/mprotect.c @@ -0,0 +1,700 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * mm/mprotect.c + * + * (C) Copyright 1994 Linus Torvalds + * (C) Copyright 2002 Christoph Hellwig + * + * Address space accounting code + * (C) Copyright 2002 Red Hat Inc, All Rights Reserved + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "internal.h" + +static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, + unsigned long addr, unsigned long end, pgprot_t newprot, + unsigned long cp_flags) +{ + pte_t *pte, oldpte; + spinlock_t *ptl; + unsigned long pages = 0; + int target_node = NUMA_NO_NODE; + bool dirty_accountable = cp_flags & MM_CP_DIRTY_ACCT; + bool prot_numa = cp_flags & MM_CP_PROT_NUMA; + bool uffd_wp = cp_flags & MM_CP_UFFD_WP; + bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE; + + /* + * Can be called with only the mmap_lock for reading by + * prot_numa so we must check the pmd isn't constantly + * changing from under us from pmd_none to pmd_trans_huge + * and/or the other way around. + */ + if (pmd_trans_unstable(pmd)) + return 0; + + /* + * The pmd points to a regular pte so the pmd can't change + * from under us even if the mmap_lock is only hold for + * reading. + */ + pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); + + /* Get target node for single threaded private VMAs */ + if (prot_numa && !(vma->vm_flags & VM_SHARED) && + atomic_read(&vma->vm_mm->mm_users) == 1) + target_node = numa_node_id(); + + flush_tlb_batched_pending(vma->vm_mm); + arch_enter_lazy_mmu_mode(); + do { + oldpte = *pte; + if (pte_present(oldpte)) { + pte_t ptent; + bool preserve_write = prot_numa && pte_write(oldpte); + + /* + * Avoid trapping faults against the zero or KSM + * pages. See similar comment in change_huge_pmd. + */ + if (prot_numa) { + struct page *page; + + /* Avoid TLB flush if possible */ + if (pte_protnone(oldpte)) + continue; + + page = vm_normal_page(vma, addr, oldpte); + if (!page || PageKsm(page)) + continue; + + /* Also skip shared copy-on-write pages */ + if (is_cow_mapping(vma->vm_flags) && + page_count(page) != 1) + continue; + + /* + * While migration can move some dirty pages, + * it cannot move them all from MIGRATE_ASYNC + * context. + */ + if (page_is_file_lru(page) && PageDirty(page)) + continue; + + /* + * Don't mess with PTEs if page is already on the node + * a single-threaded process is running on. + */ + if (target_node == page_to_nid(page)) + continue; + } + + oldpte = ptep_modify_prot_start(vma, addr, pte); + ptent = pte_modify(oldpte, newprot); + if (preserve_write) + ptent = pte_mk_savedwrite(ptent); + + if (uffd_wp) { + ptent = pte_wrprotect(ptent); + ptent = pte_mkuffd_wp(ptent); + } else if (uffd_wp_resolve) { + /* + * Leave the write bit to be handled + * by PF interrupt handler, then + * things like COW could be properly + * handled. + */ + ptent = pte_clear_uffd_wp(ptent); + } + + /* Avoid taking write faults for known dirty pages */ + if (dirty_accountable && pte_dirty(ptent) && + (pte_soft_dirty(ptent) || + !(vma->vm_flags & VM_SOFTDIRTY))) { + ptent = pte_mkwrite(ptent); + } + ptep_modify_prot_commit(vma, addr, pte, oldpte, ptent); + pages++; + } else if (is_swap_pte(oldpte)) { + swp_entry_t entry = pte_to_swp_entry(oldpte); + pte_t newpte; + + if (is_write_migration_entry(entry)) { + /* + * A protection check is difficult so + * just be safe and disable write + */ + make_migration_entry_read(&entry); + newpte = swp_entry_to_pte(entry); + if (pte_swp_soft_dirty(oldpte)) + newpte = pte_swp_mksoft_dirty(newpte); + if (pte_swp_uffd_wp(oldpte)) + newpte = pte_swp_mkuffd_wp(newpte); + } else if (is_write_device_private_entry(entry)) { + /* + * We do not preserve soft-dirtiness. See + * copy_one_pte() for explanation. + */ + make_device_private_entry_read(&entry); + newpte = swp_entry_to_pte(entry); + if (pte_swp_uffd_wp(oldpte)) + newpte = pte_swp_mkuffd_wp(newpte); + } else { + newpte = oldpte; + } + + if (uffd_wp) + newpte = pte_swp_mkuffd_wp(newpte); + else if (uffd_wp_resolve) + newpte = pte_swp_clear_uffd_wp(newpte); + + if (!pte_same(oldpte, newpte)) { + set_pte_at(vma->vm_mm, addr, pte, newpte); + pages++; + } + } + } while (pte++, addr += PAGE_SIZE, addr != end); + arch_leave_lazy_mmu_mode(); + pte_unmap_unlock(pte - 1, ptl); + + return pages; +} + +/* + * Used when setting automatic NUMA hinting protection where it is + * critical that a numa hinting PMD is not confused with a bad PMD. + */ +static inline int pmd_none_or_clear_bad_unless_trans_huge(pmd_t *pmd) +{ + pmd_t pmdval = pmd_read_atomic(pmd); + + /* See pmd_none_or_trans_huge_or_clear_bad for info on barrier */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + barrier(); +#endif + + if (pmd_none(pmdval)) + return 1; + if (pmd_trans_huge(pmdval)) + return 0; + if (unlikely(pmd_bad(pmdval))) { + pmd_clear_bad(pmd); + return 1; + } + + return 0; +} + +static inline unsigned long change_pmd_range(struct vm_area_struct *vma, + pud_t *pud, unsigned long addr, unsigned long end, + pgprot_t newprot, unsigned long cp_flags) +{ + pmd_t *pmd; + unsigned long next; + unsigned long pages = 0; + unsigned long nr_huge_updates = 0; + struct mmu_notifier_range range; + + range.start = 0; + + pmd = pmd_offset(pud, addr); + do { + unsigned long this_pages; + + next = pmd_addr_end(addr, end); + + /* + * Automatic NUMA balancing walks the tables with mmap_lock + * held for read. It's possible a parallel update to occur + * between pmd_trans_huge() and a pmd_none_or_clear_bad() + * check leading to a false positive and clearing. + * Hence, it's necessary to atomically read the PMD value + * for all the checks. + */ + if (!is_swap_pmd(*pmd) && !pmd_devmap(*pmd) && + pmd_none_or_clear_bad_unless_trans_huge(pmd)) + goto next; + + /* invoke the mmu notifier if the pmd is populated */ + if (!range.start) { + mmu_notifier_range_init(&range, + MMU_NOTIFY_PROTECTION_VMA, 0, + vma, vma->vm_mm, addr, end); + mmu_notifier_invalidate_range_start(&range); + } + + if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) { + if (next - addr != HPAGE_PMD_SIZE) { + __split_huge_pmd(vma, pmd, addr, false, NULL); + } else { + int nr_ptes = change_huge_pmd(vma, pmd, addr, + newprot, cp_flags); + + if (nr_ptes) { + if (nr_ptes == HPAGE_PMD_NR) { + pages += HPAGE_PMD_NR; + nr_huge_updates++; + } + + /* huge pmd was handled */ + goto next; + } + } + /* fall through, the trans huge pmd just split */ + } + this_pages = change_pte_range(vma, pmd, addr, next, newprot, + cp_flags); + pages += this_pages; +next: + cond_resched(); + } while (pmd++, addr = next, addr != end); + + if (range.start) + mmu_notifier_invalidate_range_end(&range); + + if (nr_huge_updates) + count_vm_numa_events(NUMA_HUGE_PTE_UPDATES, nr_huge_updates); + return pages; +} + +static inline unsigned long change_pud_range(struct vm_area_struct *vma, + p4d_t *p4d, unsigned long addr, unsigned long end, + pgprot_t newprot, unsigned long cp_flags) +{ + pud_t *pud; + unsigned long next; + unsigned long pages = 0; + + pud = pud_offset(p4d, addr); + do { + next = pud_addr_end(addr, end); + if (pud_none_or_clear_bad(pud)) + continue; + pages += change_pmd_range(vma, pud, addr, next, newprot, + cp_flags); + } while (pud++, addr = next, addr != end); + + return pages; +} + +static inline unsigned long change_p4d_range(struct vm_area_struct *vma, + pgd_t *pgd, unsigned long addr, unsigned long end, + pgprot_t newprot, unsigned long cp_flags) +{ + p4d_t *p4d; + unsigned long next; + unsigned long pages = 0; + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(p4d)) + continue; + pages += change_pud_range(vma, p4d, addr, next, newprot, + cp_flags); + } while (p4d++, addr = next, addr != end); + + return pages; +} + +static unsigned long change_protection_range(struct vm_area_struct *vma, + unsigned long addr, unsigned long end, pgprot_t newprot, + unsigned long cp_flags) +{ + struct mm_struct *mm = vma->vm_mm; + pgd_t *pgd; + unsigned long next; + unsigned long start = addr; + unsigned long pages = 0; + + BUG_ON(addr >= end); + pgd = pgd_offset(mm, addr); + flush_cache_range(vma, addr, end); + inc_tlb_flush_pending(mm); + do { + next = pgd_addr_end(addr, end); + if (pgd_none_or_clear_bad(pgd)) + continue; + pages += change_p4d_range(vma, pgd, addr, next, newprot, + cp_flags); + } while (pgd++, addr = next, addr != end); + + /* Only flush the TLB if we actually modified any entries: */ + if (pages) + flush_tlb_range(vma, start, end); + dec_tlb_flush_pending(mm); + + return pages; +} + +unsigned long change_protection(struct vm_area_struct *vma, unsigned long start, + unsigned long end, pgprot_t newprot, + unsigned long cp_flags) +{ + unsigned long pages; + + BUG_ON((cp_flags & MM_CP_UFFD_WP_ALL) == MM_CP_UFFD_WP_ALL); + + if (is_vm_hugetlb_page(vma)) + pages = hugetlb_change_protection(vma, start, end, newprot); + else + pages = change_protection_range(vma, start, end, newprot, + cp_flags); + + return pages; +} + +static int prot_none_pte_entry(pte_t *pte, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + return pfn_modify_allowed(pte_pfn(*pte), *(pgprot_t *)(walk->private)) ? + 0 : -EACCES; +} + +static int prot_none_hugetlb_entry(pte_t *pte, unsigned long hmask, + unsigned long addr, unsigned long next, + struct mm_walk *walk) +{ + return pfn_modify_allowed(pte_pfn(*pte), *(pgprot_t *)(walk->private)) ? + 0 : -EACCES; +} + +static int prot_none_test(unsigned long addr, unsigned long next, + struct mm_walk *walk) +{ + return 0; +} + +static const struct mm_walk_ops prot_none_walk_ops = { + .pte_entry = prot_none_pte_entry, + .hugetlb_entry = prot_none_hugetlb_entry, + .test_walk = prot_none_test, +}; + +int +mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, + unsigned long start, unsigned long end, unsigned long newflags) +{ + struct mm_struct *mm = vma->vm_mm; + unsigned long oldflags = vma->vm_flags; + long nrpages = (end - start) >> PAGE_SHIFT; + unsigned long charged = 0; + pgoff_t pgoff; + int error; + int dirty_accountable = 0; + + if (newflags == oldflags) { + *pprev = vma; + return 0; + } + + /* + * Do PROT_NONE PFN permission checks here when we can still + * bail out without undoing a lot of state. This is a rather + * uncommon case, so doesn't need to be very optimized. + */ + if (arch_has_pfn_modify_check() && + (vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) && + (newflags & VM_ACCESS_FLAGS) == 0) { + pgprot_t new_pgprot = vm_get_page_prot(newflags); + + error = walk_page_range(current->mm, start, end, + &prot_none_walk_ops, &new_pgprot); + if (error) + return error; + } + + /* + * If we make a private mapping writable we increase our commit; + * but (without finer accounting) cannot reduce our commit if we + * make it unwritable again. hugetlb mapping were accounted for + * even if read-only so there is no need to account for them here + */ + if (newflags & VM_WRITE) { + /* Check space limits when area turns into data. */ + if (!may_expand_vm(mm, newflags, nrpages) && + may_expand_vm(mm, oldflags, nrpages)) + return -ENOMEM; + if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_HUGETLB| + VM_SHARED|VM_NORESERVE))) { + charged = nrpages; + if (security_vm_enough_memory_mm(mm, charged)) + return -ENOMEM; + newflags |= VM_ACCOUNT; + } + } + + /* + * First try to merge with previous and/or next vma. + */ + pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); + *pprev = vma_merge(mm, *pprev, start, end, newflags, + vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), + vma->vm_userfaultfd_ctx); + if (*pprev) { + vma = *pprev; + VM_WARN_ON((vma->vm_flags ^ newflags) & ~VM_SOFTDIRTY); + goto success; + } + + *pprev = vma; + + if (start != vma->vm_start) { + error = split_vma(mm, vma, start, 1); + if (error) + goto fail; + } + + if (end != vma->vm_end) { + error = split_vma(mm, vma, end, 0); + if (error) + goto fail; + } + +success: + /* + * vm_flags and vm_page_prot are protected by the mmap_lock + * held in write mode. + */ + vma->vm_flags = newflags; + dirty_accountable = vma_wants_writenotify(vma, vma->vm_page_prot); + vma_set_page_prot(vma); + + change_protection(vma, start, end, vma->vm_page_prot, + dirty_accountable ? MM_CP_DIRTY_ACCT : 0); + + /* + * Private VM_LOCKED VMA becoming writable: trigger COW to avoid major + * fault on access. + */ + if ((oldflags & (VM_WRITE | VM_SHARED | VM_LOCKED)) == VM_LOCKED && + (newflags & VM_WRITE)) { + populate_vma_page_range(vma, start, end, NULL); + } + + vm_stat_account(mm, oldflags, -nrpages); + vm_stat_account(mm, newflags, nrpages); + perf_event_mmap(vma); + return 0; + +fail: + vm_unacct_memory(charged); + return error; +} + +/* + * pkey==-1 when doing a legacy mprotect() + */ +static int do_mprotect_pkey(unsigned long start, size_t len, + unsigned long prot, int pkey) +{ + unsigned long nstart, end, tmp, reqprot; + struct vm_area_struct *vma, *prev; + int error = -EINVAL; + const int grows = prot & (PROT_GROWSDOWN|PROT_GROWSUP); + const bool rier = (current->personality & READ_IMPLIES_EXEC) && + (prot & PROT_READ); + + start = untagged_addr(start); + + prot &= ~(PROT_GROWSDOWN|PROT_GROWSUP); + if (grows == (PROT_GROWSDOWN|PROT_GROWSUP)) /* can't be both */ + return -EINVAL; + + if (start & ~PAGE_MASK) + return -EINVAL; + if (!len) + return 0; + len = PAGE_ALIGN(len); + end = start + len; + if (end <= start) + return -ENOMEM; + if (!arch_validate_prot(prot, start)) + return -EINVAL; + + reqprot = prot; + + if (mmap_write_lock_killable(current->mm)) + return -EINTR; + + /* + * If userspace did not allocate the pkey, do not let + * them use it here. + */ + error = -EINVAL; + if ((pkey != -1) && !mm_pkey_is_allocated(current->mm, pkey)) + goto out; + + vma = find_vma(current->mm, start); + error = -ENOMEM; + if (!vma) + goto out; + prev = vma->vm_prev; + if (unlikely(grows & PROT_GROWSDOWN)) { + if (vma->vm_start >= end) + goto out; + start = vma->vm_start; + error = -EINVAL; + if (!(vma->vm_flags & VM_GROWSDOWN)) + goto out; + } else { + if (vma->vm_start > start) + goto out; + if (unlikely(grows & PROT_GROWSUP)) { + end = vma->vm_end; + error = -EINVAL; + if (!(vma->vm_flags & VM_GROWSUP)) + goto out; + } + } + if (start > vma->vm_start) + prev = vma; + + for (nstart = start ; ; ) { + unsigned long mask_off_old_flags; + unsigned long newflags; + int new_vma_pkey; + + /* Here we know that vma->vm_start <= nstart < vma->vm_end. */ + + /* Does the application expect PROT_READ to imply PROT_EXEC */ + if (rier && (vma->vm_flags & VM_MAYEXEC)) + prot |= PROT_EXEC; + + /* + * Each mprotect() call explicitly passes r/w/x permissions. + * If a permission is not passed to mprotect(), it must be + * cleared from the VMA. + */ + mask_off_old_flags = VM_READ | VM_WRITE | VM_EXEC | + VM_FLAGS_CLEAR; + + new_vma_pkey = arch_override_mprotect_pkey(vma, prot, pkey); + newflags = calc_vm_prot_bits(prot, new_vma_pkey); + newflags |= (vma->vm_flags & ~mask_off_old_flags); + + /* newflags >> 4 shift VM_MAY% in place of VM_% */ + if ((newflags & ~(newflags >> 4)) & VM_ACCESS_FLAGS) { + error = -EACCES; + goto out; + } + + /* Allow architectures to sanity-check the new flags */ + if (!arch_validate_flags(newflags)) { + error = -EINVAL; + goto out; + } + + error = security_file_mprotect(vma, reqprot, prot); + if (error) + goto out; + + tmp = vma->vm_end; + if (tmp > end) + tmp = end; + error = mprotect_fixup(vma, &prev, nstart, tmp, newflags); + if (error) + goto out; + nstart = tmp; + + if (nstart < prev->vm_end) + nstart = prev->vm_end; + if (nstart >= end) + goto out; + + vma = prev->vm_next; + if (!vma || vma->vm_start != nstart) { + error = -ENOMEM; + goto out; + } + prot = reqprot; + } +out: + mmap_write_unlock(current->mm); + return error; +} + +SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len, + unsigned long, prot) +{ + return do_mprotect_pkey(start, len, prot, -1); +} + +#ifdef CONFIG_ARCH_HAS_PKEYS + +SYSCALL_DEFINE4(pkey_mprotect, unsigned long, start, size_t, len, + unsigned long, prot, int, pkey) +{ + return do_mprotect_pkey(start, len, prot, pkey); +} + +SYSCALL_DEFINE2(pkey_alloc, unsigned long, flags, unsigned long, init_val) +{ + int pkey; + int ret; + + /* No flags supported yet. */ + if (flags) + return -EINVAL; + /* check for unsupported init values */ + if (init_val & ~PKEY_ACCESS_MASK) + return -EINVAL; + + mmap_write_lock(current->mm); + pkey = mm_pkey_alloc(current->mm); + + ret = -ENOSPC; + if (pkey == -1) + goto out; + + ret = arch_set_user_pkey_access(current, pkey, init_val); + if (ret) { + mm_pkey_free(current->mm, pkey); + goto out; + } + ret = pkey; +out: + mmap_write_unlock(current->mm); + return ret; +} + +SYSCALL_DEFINE1(pkey_free, int, pkey) +{ + int ret; + + mmap_write_lock(current->mm); + ret = mm_pkey_free(current->mm, pkey); + mmap_write_unlock(current->mm); + + /* + * We could provie warnings or errors if any VMA still + * has the pkey set here. + */ + return ret; +} + +#endif /* CONFIG_ARCH_HAS_PKEYS */ diff --git a/mm/mremap.c b/mm/mremap.c new file mode 100644 index 000000000..3334c4022 --- /dev/null +++ b/mm/mremap.c @@ -0,0 +1,815 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * mm/mremap.c + * + * (C) Copyright 1996 Linus Torvalds + * + * Address space accounting code + * (C) Copyright 2002 Red Hat Inc, All Rights Reserved + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include "internal.h" + +static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr) +{ + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + pgd = pgd_offset(mm, addr); + if (pgd_none_or_clear_bad(pgd)) + return NULL; + + p4d = p4d_offset(pgd, addr); + if (p4d_none_or_clear_bad(p4d)) + return NULL; + + pud = pud_offset(p4d, addr); + if (pud_none_or_clear_bad(pud)) + return NULL; + + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) + return NULL; + + return pmd; +} + +static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr) +{ + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + pgd = pgd_offset(mm, addr); + p4d = p4d_alloc(mm, pgd, addr); + if (!p4d) + return NULL; + pud = pud_alloc(mm, p4d, addr); + if (!pud) + return NULL; + + pmd = pmd_alloc(mm, pud, addr); + if (!pmd) + return NULL; + + VM_BUG_ON(pmd_trans_huge(*pmd)); + + return pmd; +} + +static void take_rmap_locks(struct vm_area_struct *vma) +{ + if (vma->vm_file) + i_mmap_lock_write(vma->vm_file->f_mapping); + if (vma->anon_vma) + anon_vma_lock_write(vma->anon_vma); +} + +static void drop_rmap_locks(struct vm_area_struct *vma) +{ + if (vma->anon_vma) + anon_vma_unlock_write(vma->anon_vma); + if (vma->vm_file) + i_mmap_unlock_write(vma->vm_file->f_mapping); +} + +static pte_t move_soft_dirty_pte(pte_t pte) +{ + /* + * Set soft dirty bit so we can notice + * in userspace the ptes were moved. + */ +#ifdef CONFIG_MEM_SOFT_DIRTY + if (pte_present(pte)) + pte = pte_mksoft_dirty(pte); + else if (is_swap_pte(pte)) + pte = pte_swp_mksoft_dirty(pte); +#endif + return pte; +} + +static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, + unsigned long old_addr, unsigned long old_end, + struct vm_area_struct *new_vma, pmd_t *new_pmd, + unsigned long new_addr, bool need_rmap_locks) +{ + struct mm_struct *mm = vma->vm_mm; + pte_t *old_pte, *new_pte, pte; + spinlock_t *old_ptl, *new_ptl; + bool force_flush = false; + unsigned long len = old_end - old_addr; + + /* + * When need_rmap_locks is true, we take the i_mmap_rwsem and anon_vma + * locks to ensure that rmap will always observe either the old or the + * new ptes. This is the easiest way to avoid races with + * truncate_pagecache(), page migration, etc... + * + * When need_rmap_locks is false, we use other ways to avoid + * such races: + * + * - During exec() shift_arg_pages(), we use a specially tagged vma + * which rmap call sites look for using vma_is_temporary_stack(). + * + * - During mremap(), new_vma is often known to be placed after vma + * in rmap traversal order. This ensures rmap will always observe + * either the old pte, or the new pte, or both (the page table locks + * serialize access to individual ptes, but only rmap traversal + * order guarantees that we won't miss both the old and new ptes). + */ + if (need_rmap_locks) + take_rmap_locks(vma); + + /* + * We don't have to worry about the ordering of src and dst + * pte locks because exclusive mmap_lock prevents deadlock. + */ + old_pte = pte_offset_map_lock(mm, old_pmd, old_addr, &old_ptl); + new_pte = pte_offset_map(new_pmd, new_addr); + new_ptl = pte_lockptr(mm, new_pmd); + if (new_ptl != old_ptl) + spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); + flush_tlb_batched_pending(vma->vm_mm); + arch_enter_lazy_mmu_mode(); + + for (; old_addr < old_end; old_pte++, old_addr += PAGE_SIZE, + new_pte++, new_addr += PAGE_SIZE) { + if (pte_none(*old_pte)) + continue; + + pte = ptep_get_and_clear(mm, old_addr, old_pte); + /* + * If we are remapping a valid PTE, make sure + * to flush TLB before we drop the PTL for the + * PTE. + * + * NOTE! Both old and new PTL matter: the old one + * for racing with page_mkclean(), the new one to + * make sure the physical page stays valid until + * the TLB entry for the old mapping has been + * flushed. + */ + if (pte_present(pte)) + force_flush = true; + pte = move_pte(pte, new_vma->vm_page_prot, old_addr, new_addr); + pte = move_soft_dirty_pte(pte); + set_pte_at(mm, new_addr, new_pte, pte); + } + + arch_leave_lazy_mmu_mode(); + if (force_flush) + flush_tlb_range(vma, old_end - len, old_end); + if (new_ptl != old_ptl) + spin_unlock(new_ptl); + pte_unmap(new_pte - 1); + pte_unmap_unlock(old_pte - 1, old_ptl); + if (need_rmap_locks) + drop_rmap_locks(vma); +} + +#ifdef CONFIG_HAVE_MOVE_PMD +static bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr, + unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd) +{ + spinlock_t *old_ptl, *new_ptl; + struct mm_struct *mm = vma->vm_mm; + pmd_t pmd; + + /* + * The destination pmd shouldn't be established, free_pgtables() + * should have released it. + * + * However, there's a case during execve() where we use mremap + * to move the initial stack, and in that case the target area + * may overlap the source area (always moving down). + * + * If everything is PMD-aligned, that works fine, as moving + * each pmd down will clear the source pmd. But if we first + * have a few 4kB-only pages that get moved down, and then + * hit the "now the rest is PMD-aligned, let's do everything + * one pmd at a time", we will still have the old (now empty + * of any 4kB pages, but still there) PMD in the page table + * tree. + * + * Warn on it once - because we really should try to figure + * out how to do this better - but then say "I won't move + * this pmd". + * + * One alternative might be to just unmap the target pmd at + * this point, and verify that it really is empty. We'll see. + */ + if (WARN_ON_ONCE(!pmd_none(*new_pmd))) + return false; + + /* + * We don't have to worry about the ordering of src and dst + * ptlocks because exclusive mmap_lock prevents deadlock. + */ + old_ptl = pmd_lock(vma->vm_mm, old_pmd); + new_ptl = pmd_lockptr(mm, new_pmd); + if (new_ptl != old_ptl) + spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); + + /* Clear the pmd */ + pmd = *old_pmd; + pmd_clear(old_pmd); + + VM_BUG_ON(!pmd_none(*new_pmd)); + + /* Set the new pmd */ + set_pmd_at(mm, new_addr, new_pmd, pmd); + flush_tlb_range(vma, old_addr, old_addr + PMD_SIZE); + if (new_ptl != old_ptl) + spin_unlock(new_ptl); + spin_unlock(old_ptl); + + return true; +} +#endif + +unsigned long move_page_tables(struct vm_area_struct *vma, + unsigned long old_addr, struct vm_area_struct *new_vma, + unsigned long new_addr, unsigned long len, + bool need_rmap_locks) +{ + unsigned long extent, next, old_end; + struct mmu_notifier_range range; + pmd_t *old_pmd, *new_pmd; + + if (!len) + return 0; + + old_end = old_addr + len; + flush_cache_range(vma, old_addr, old_end); + + mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm, + old_addr, old_end); + mmu_notifier_invalidate_range_start(&range); + + for (; old_addr < old_end; old_addr += extent, new_addr += extent) { + cond_resched(); + next = (old_addr + PMD_SIZE) & PMD_MASK; + /* even if next overflowed, extent below will be ok */ + extent = next - old_addr; + if (extent > old_end - old_addr) + extent = old_end - old_addr; + next = (new_addr + PMD_SIZE) & PMD_MASK; + if (extent > next - new_addr) + extent = next - new_addr; + old_pmd = get_old_pmd(vma->vm_mm, old_addr); + if (!old_pmd) + continue; + new_pmd = alloc_new_pmd(vma->vm_mm, vma, new_addr); + if (!new_pmd) + break; + if (is_swap_pmd(*old_pmd) || pmd_trans_huge(*old_pmd) || pmd_devmap(*old_pmd)) { + if (extent == HPAGE_PMD_SIZE) { + bool moved; + /* See comment in move_ptes() */ + if (need_rmap_locks) + take_rmap_locks(vma); + moved = move_huge_pmd(vma, old_addr, new_addr, + old_pmd, new_pmd); + if (need_rmap_locks) + drop_rmap_locks(vma); + if (moved) + continue; + } + split_huge_pmd(vma, old_pmd, old_addr); + if (pmd_trans_unstable(old_pmd)) + continue; + } else if (extent == PMD_SIZE) { +#ifdef CONFIG_HAVE_MOVE_PMD + /* + * If the extent is PMD-sized, try to speed the move by + * moving at the PMD level if possible. + */ + bool moved; + + take_rmap_locks(vma); + moved = move_normal_pmd(vma, old_addr, new_addr, + old_pmd, new_pmd); + drop_rmap_locks(vma); + if (moved) + continue; +#endif + } + + if (pte_alloc(new_vma->vm_mm, new_pmd)) + break; + move_ptes(vma, old_pmd, old_addr, old_addr + extent, new_vma, + new_pmd, new_addr, need_rmap_locks); + } + + mmu_notifier_invalidate_range_end(&range); + + return len + old_addr - old_end; /* how much done */ +} + +static unsigned long move_vma(struct vm_area_struct *vma, + unsigned long old_addr, unsigned long old_len, + unsigned long new_len, unsigned long new_addr, + bool *locked, unsigned long flags, + struct vm_userfaultfd_ctx *uf, struct list_head *uf_unmap) +{ + struct mm_struct *mm = vma->vm_mm; + struct vm_area_struct *new_vma; + unsigned long vm_flags = vma->vm_flags; + unsigned long new_pgoff; + unsigned long moved_len; + unsigned long excess = 0; + unsigned long hiwater_vm; + int split = 0; + int err; + bool need_rmap_locks; + + /* + * We'd prefer to avoid failure later on in do_munmap: + * which may split one vma into three before unmapping. + */ + if (mm->map_count >= sysctl_max_map_count - 3) + return -ENOMEM; + + /* + * Advise KSM to break any KSM pages in the area to be moved: + * it would be confusing if they were to turn up at the new + * location, where they happen to coincide with different KSM + * pages recently unmapped. But leave vma->vm_flags as it was, + * so KSM can come around to merge on vma and new_vma afterwards. + */ + err = ksm_madvise(vma, old_addr, old_addr + old_len, + MADV_UNMERGEABLE, &vm_flags); + if (err) + return err; + + new_pgoff = vma->vm_pgoff + ((old_addr - vma->vm_start) >> PAGE_SHIFT); + new_vma = copy_vma(&vma, new_addr, new_len, new_pgoff, + &need_rmap_locks); + if (!new_vma) + return -ENOMEM; + + moved_len = move_page_tables(vma, old_addr, new_vma, new_addr, old_len, + need_rmap_locks); + if (moved_len < old_len) { + err = -ENOMEM; + } else if (vma->vm_ops && vma->vm_ops->mremap) { + err = vma->vm_ops->mremap(new_vma); + } + + if (unlikely(err)) { + /* + * On error, move entries back from new area to old, + * which will succeed since page tables still there, + * and then proceed to unmap new area instead of old. + */ + move_page_tables(new_vma, new_addr, vma, old_addr, moved_len, + true); + vma = new_vma; + old_len = new_len; + old_addr = new_addr; + new_addr = err; + } else { + mremap_userfaultfd_prep(new_vma, uf); + arch_remap(mm, old_addr, old_addr + old_len, + new_addr, new_addr + new_len); + } + + /* Conceal VM_ACCOUNT so old reservation is not undone */ + if (vm_flags & VM_ACCOUNT) { + vma->vm_flags &= ~VM_ACCOUNT; + excess = vma->vm_end - vma->vm_start - old_len; + if (old_addr > vma->vm_start && + old_addr + old_len < vma->vm_end) + split = 1; + } + + /* + * If we failed to move page tables we still do total_vm increment + * since do_munmap() will decrement it by old_len == new_len. + * + * Since total_vm is about to be raised artificially high for a + * moment, we need to restore high watermark afterwards: if stats + * are taken meanwhile, total_vm and hiwater_vm appear too high. + * If this were a serious issue, we'd add a flag to do_munmap(). + */ + hiwater_vm = mm->hiwater_vm; + vm_stat_account(mm, vma->vm_flags, new_len >> PAGE_SHIFT); + + /* Tell pfnmap has moved from this vma */ + if (unlikely(vma->vm_flags & VM_PFNMAP)) + untrack_pfn_moved(vma); + + if (unlikely(!err && (flags & MREMAP_DONTUNMAP))) { + if (vm_flags & VM_ACCOUNT) { + /* Always put back VM_ACCOUNT since we won't unmap */ + vma->vm_flags |= VM_ACCOUNT; + + vm_acct_memory(new_len >> PAGE_SHIFT); + } + + /* + * VMAs can actually be merged back together in copy_vma + * calling merge_vma. This can happen with anonymous vmas + * which have not yet been faulted, so if we were to consider + * this VMA split we'll end up adding VM_ACCOUNT on the + * next VMA, which is completely unrelated if this VMA + * was re-merged. + */ + if (split && new_vma == vma) + split = 0; + + /* We always clear VM_LOCKED[ONFAULT] on the old vma */ + vma->vm_flags &= VM_LOCKED_CLEAR_MASK; + + /* Because we won't unmap we don't need to touch locked_vm */ + goto out; + } + + if (do_munmap(mm, old_addr, old_len, uf_unmap) < 0) { + /* OOM: unable to split vma, just get accounts right */ + vm_unacct_memory(excess >> PAGE_SHIFT); + excess = 0; + } + + if (vm_flags & VM_LOCKED) { + mm->locked_vm += new_len >> PAGE_SHIFT; + *locked = true; + } +out: + mm->hiwater_vm = hiwater_vm; + + /* Restore VM_ACCOUNT if one or two pieces of vma left */ + if (excess) { + vma->vm_flags |= VM_ACCOUNT; + if (split) + vma->vm_next->vm_flags |= VM_ACCOUNT; + } + + return new_addr; +} + +static struct vm_area_struct *vma_to_resize(unsigned long addr, + unsigned long old_len, unsigned long new_len, unsigned long flags, + unsigned long *p) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma = find_vma(mm, addr); + unsigned long pgoff; + + if (!vma || vma->vm_start > addr) + return ERR_PTR(-EFAULT); + + /* + * !old_len is a special case where an attempt is made to 'duplicate' + * a mapping. This makes no sense for private mappings as it will + * instead create a fresh/new mapping unrelated to the original. This + * is contrary to the basic idea of mremap which creates new mappings + * based on the original. There are no known use cases for this + * behavior. As a result, fail such attempts. + */ + if (!old_len && !(vma->vm_flags & (VM_SHARED | VM_MAYSHARE))) { + pr_warn_once("%s (%d): attempted to duplicate a private mapping with mremap. This is not supported.\n", current->comm, current->pid); + return ERR_PTR(-EINVAL); + } + + if (flags & MREMAP_DONTUNMAP && (!vma_is_anonymous(vma) || + vma->vm_flags & VM_SHARED)) + return ERR_PTR(-EINVAL); + + if (is_vm_hugetlb_page(vma)) + return ERR_PTR(-EINVAL); + + /* We can't remap across vm area boundaries */ + if (old_len > vma->vm_end - addr) + return ERR_PTR(-EFAULT); + + if (new_len == old_len) + return vma; + + /* Need to be careful about a growing mapping */ + pgoff = (addr - vma->vm_start) >> PAGE_SHIFT; + pgoff += vma->vm_pgoff; + if (pgoff + (new_len >> PAGE_SHIFT) < pgoff) + return ERR_PTR(-EINVAL); + + if (vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP)) + return ERR_PTR(-EFAULT); + + if (vma->vm_flags & VM_LOCKED) { + unsigned long locked, lock_limit; + locked = mm->locked_vm << PAGE_SHIFT; + lock_limit = rlimit(RLIMIT_MEMLOCK); + locked += new_len - old_len; + if (locked > lock_limit && !capable(CAP_IPC_LOCK)) + return ERR_PTR(-EAGAIN); + } + + if (!may_expand_vm(mm, vma->vm_flags, + (new_len - old_len) >> PAGE_SHIFT)) + return ERR_PTR(-ENOMEM); + + if (vma->vm_flags & VM_ACCOUNT) { + unsigned long charged = (new_len - old_len) >> PAGE_SHIFT; + if (security_vm_enough_memory_mm(mm, charged)) + return ERR_PTR(-ENOMEM); + *p = charged; + } + + return vma; +} + +static unsigned long mremap_to(unsigned long addr, unsigned long old_len, + unsigned long new_addr, unsigned long new_len, bool *locked, + unsigned long flags, struct vm_userfaultfd_ctx *uf, + struct list_head *uf_unmap_early, + struct list_head *uf_unmap) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + unsigned long ret = -EINVAL; + unsigned long charged = 0; + unsigned long map_flags = 0; + + if (offset_in_page(new_addr)) + goto out; + + if (new_len > TASK_SIZE || new_addr > TASK_SIZE - new_len) + goto out; + + /* Ensure the old/new locations do not overlap */ + if (addr + old_len > new_addr && new_addr + new_len > addr) + goto out; + + /* + * move_vma() need us to stay 4 maps below the threshold, otherwise + * it will bail out at the very beginning. + * That is a problem if we have already unmaped the regions here + * (new_addr, and old_addr), because userspace will not know the + * state of the vma's after it gets -ENOMEM. + * So, to avoid such scenario we can pre-compute if the whole + * operation has high chances to success map-wise. + * Worst-scenario case is when both vma's (new_addr and old_addr) get + * split in 3 before unmaping it. + * That means 2 more maps (1 for each) to the ones we already hold. + * Check whether current map count plus 2 still leads us to 4 maps below + * the threshold, otherwise return -ENOMEM here to be more safe. + */ + if ((mm->map_count + 2) >= sysctl_max_map_count - 3) + return -ENOMEM; + + if (flags & MREMAP_FIXED) { + ret = do_munmap(mm, new_addr, new_len, uf_unmap_early); + if (ret) + goto out; + } + + if (old_len >= new_len) { + ret = do_munmap(mm, addr+new_len, old_len - new_len, uf_unmap); + if (ret && old_len != new_len) + goto out; + old_len = new_len; + } + + vma = vma_to_resize(addr, old_len, new_len, flags, &charged); + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + goto out; + } + + /* MREMAP_DONTUNMAP expands by old_len since old_len == new_len */ + if (flags & MREMAP_DONTUNMAP && + !may_expand_vm(mm, vma->vm_flags, old_len >> PAGE_SHIFT)) { + ret = -ENOMEM; + goto out; + } + + if (flags & MREMAP_FIXED) + map_flags |= MAP_FIXED; + + if (vma->vm_flags & VM_MAYSHARE) + map_flags |= MAP_SHARED; + + ret = get_unmapped_area(vma->vm_file, new_addr, new_len, vma->vm_pgoff + + ((addr - vma->vm_start) >> PAGE_SHIFT), + map_flags); + if (IS_ERR_VALUE(ret)) + goto out1; + + /* We got a new mapping */ + if (!(flags & MREMAP_FIXED)) + new_addr = ret; + + ret = move_vma(vma, addr, old_len, new_len, new_addr, locked, flags, uf, + uf_unmap); + + if (!(offset_in_page(ret))) + goto out; + +out1: + vm_unacct_memory(charged); + +out: + return ret; +} + +static int vma_expandable(struct vm_area_struct *vma, unsigned long delta) +{ + unsigned long end = vma->vm_end + delta; + if (end < vma->vm_end) /* overflow */ + return 0; + if (vma->vm_next && vma->vm_next->vm_start < end) /* intersection */ + return 0; + if (get_unmapped_area(NULL, vma->vm_start, end - vma->vm_start, + 0, MAP_FIXED) & ~PAGE_MASK) + return 0; + return 1; +} + +/* + * Expand (or shrink) an existing mapping, potentially moving it at the + * same time (controlled by the MREMAP_MAYMOVE flag and available VM space) + * + * MREMAP_FIXED option added 5-Dec-1999 by Benjamin LaHaise + * This option implies MREMAP_MAYMOVE. + */ +SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, + unsigned long, new_len, unsigned long, flags, + unsigned long, new_addr) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + unsigned long ret = -EINVAL; + unsigned long charged = 0; + bool locked = false; + bool downgraded = false; + struct vm_userfaultfd_ctx uf = NULL_VM_UFFD_CTX; + LIST_HEAD(uf_unmap_early); + LIST_HEAD(uf_unmap); + + /* + * There is a deliberate asymmetry here: we strip the pointer tag + * from the old address but leave the new address alone. This is + * for consistency with mmap(), where we prevent the creation of + * aliasing mappings in userspace by leaving the tag bits of the + * mapping address intact. A non-zero tag will cause the subsequent + * range checks to reject the address as invalid. + * + * See Documentation/arm64/tagged-address-abi.rst for more information. + */ + addr = untagged_addr(addr); + + if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE | MREMAP_DONTUNMAP)) + return ret; + + if (flags & MREMAP_FIXED && !(flags & MREMAP_MAYMOVE)) + return ret; + + /* + * MREMAP_DONTUNMAP is always a move and it does not allow resizing + * in the process. + */ + if (flags & MREMAP_DONTUNMAP && + (!(flags & MREMAP_MAYMOVE) || old_len != new_len)) + return ret; + + + if (offset_in_page(addr)) + return ret; + + old_len = PAGE_ALIGN(old_len); + new_len = PAGE_ALIGN(new_len); + + /* + * We allow a zero old-len as a special case + * for DOS-emu "duplicate shm area" thing. But + * a zero new-len is nonsensical. + */ + if (!new_len) + return ret; + + if (mmap_write_lock_killable(current->mm)) + return -EINTR; + + if (flags & (MREMAP_FIXED | MREMAP_DONTUNMAP)) { + ret = mremap_to(addr, old_len, new_addr, new_len, + &locked, flags, &uf, &uf_unmap_early, + &uf_unmap); + goto out; + } + + /* + * Always allow a shrinking remap: that just unmaps + * the unnecessary pages.. + * __do_munmap does all the needed commit accounting, and + * downgrades mmap_lock to read if so directed. + */ + if (old_len >= new_len) { + int retval; + + retval = __do_munmap(mm, addr+new_len, old_len - new_len, + &uf_unmap, true); + if (retval < 0 && old_len != new_len) { + ret = retval; + goto out; + /* Returning 1 indicates mmap_lock is downgraded to read. */ + } else if (retval == 1) + downgraded = true; + ret = addr; + goto out; + } + + /* + * Ok, we need to grow.. + */ + vma = vma_to_resize(addr, old_len, new_len, flags, &charged); + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + goto out; + } + + /* old_len exactly to the end of the area.. + */ + if (old_len == vma->vm_end - addr) { + /* can we just expand the current mapping? */ + if (vma_expandable(vma, new_len - old_len)) { + int pages = (new_len - old_len) >> PAGE_SHIFT; + + if (vma_adjust(vma, vma->vm_start, addr + new_len, + vma->vm_pgoff, NULL)) { + ret = -ENOMEM; + goto out; + } + + vm_stat_account(mm, vma->vm_flags, pages); + if (vma->vm_flags & VM_LOCKED) { + mm->locked_vm += pages; + locked = true; + new_addr = addr; + } + ret = addr; + goto out; + } + } + + /* + * We weren't able to just expand or shrink the area, + * we need to create a new one and move it.. + */ + ret = -ENOMEM; + if (flags & MREMAP_MAYMOVE) { + unsigned long map_flags = 0; + if (vma->vm_flags & VM_MAYSHARE) + map_flags |= MAP_SHARED; + + new_addr = get_unmapped_area(vma->vm_file, 0, new_len, + vma->vm_pgoff + + ((addr - vma->vm_start) >> PAGE_SHIFT), + map_flags); + if (IS_ERR_VALUE(new_addr)) { + ret = new_addr; + goto out; + } + + ret = move_vma(vma, addr, old_len, new_len, new_addr, + &locked, flags, &uf, &uf_unmap); + } +out: + if (offset_in_page(ret)) { + vm_unacct_memory(charged); + locked = false; + } + if (downgraded) + mmap_read_unlock(current->mm); + else + mmap_write_unlock(current->mm); + if (locked && new_len > old_len) + mm_populate(new_addr + old_len, new_len - old_len); + userfaultfd_unmap_complete(mm, &uf_unmap_early); + mremap_userfaultfd_complete(&uf, addr, ret, old_len); + userfaultfd_unmap_complete(mm, &uf_unmap); + return ret; +} diff --git a/mm/msync.c b/mm/msync.c new file mode 100644 index 000000000..69c6d2029 --- /dev/null +++ b/mm/msync.c @@ -0,0 +1,110 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/mm/msync.c + * + * Copyright (C) 1994-1999 Linus Torvalds + */ + +/* + * The msync() system call. + */ +#include +#include +#include +#include +#include +#include + +/* + * MS_SYNC syncs the entire file - including mappings. + * + * MS_ASYNC does not start I/O (it used to, up to 2.5.67). + * Nor does it marks the relevant pages dirty (it used to up to 2.6.17). + * Now it doesn't do anything, since dirty pages are properly tracked. + * + * The application may now run fsync() to + * write out the dirty pages and wait on the writeout and check the result. + * Or the application may run fadvise(FADV_DONTNEED) against the fd to start + * async writeout immediately. + * So by _not_ starting I/O in MS_ASYNC we provide complete flexibility to + * applications. + */ +SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags) +{ + unsigned long end; + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + int unmapped_error = 0; + int error = -EINVAL; + + start = untagged_addr(start); + + if (flags & ~(MS_ASYNC | MS_INVALIDATE | MS_SYNC)) + goto out; + if (offset_in_page(start)) + goto out; + if ((flags & MS_ASYNC) && (flags & MS_SYNC)) + goto out; + error = -ENOMEM; + len = (len + ~PAGE_MASK) & PAGE_MASK; + end = start + len; + if (end < start) + goto out; + error = 0; + if (end == start) + goto out; + /* + * If the interval [start,end) covers some unmapped address ranges, + * just ignore them, but return -ENOMEM at the end. + */ + mmap_read_lock(mm); + vma = find_vma(mm, start); + for (;;) { + struct file *file; + loff_t fstart, fend; + + /* Still start < end. */ + error = -ENOMEM; + if (!vma) + goto out_unlock; + /* Here start < vma->vm_end. */ + if (start < vma->vm_start) { + start = vma->vm_start; + if (start >= end) + goto out_unlock; + unmapped_error = -ENOMEM; + } + /* Here vma->vm_start <= start < vma->vm_end. */ + if ((flags & MS_INVALIDATE) && + (vma->vm_flags & VM_LOCKED)) { + error = -EBUSY; + goto out_unlock; + } + file = vma->vm_file; + fstart = (start - vma->vm_start) + + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); + fend = fstart + (min(end, vma->vm_end) - start) - 1; + start = vma->vm_end; + if ((flags & MS_SYNC) && file && + (vma->vm_flags & VM_SHARED)) { + get_file(file); + mmap_read_unlock(mm); + error = vfs_fsync_range(file, fstart, fend, 1); + fput(file); + if (error || start >= end) + goto out; + mmap_read_lock(mm); + vma = find_vma(mm, start); + } else { + if (start >= end) { + error = 0; + goto out_unlock; + } + vma = vma->vm_next; + } + } +out_unlock: + mmap_read_unlock(mm); +out: + return error ? : unmapped_error; +} diff --git a/mm/nommu.c b/mm/nommu.c new file mode 100644 index 000000000..0faf39b32 --- /dev/null +++ b/mm/nommu.c @@ -0,0 +1,1853 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/mm/nommu.c + * + * Replacement code for mm functions to support CPU's that don't + * have any form of memory management unit (thus no virtual memory). + * + * See Documentation/admin-guide/mm/nommu-mmap.rst + * + * Copyright (c) 2004-2008 David Howells + * Copyright (c) 2000-2003 David McCullough + * Copyright (c) 2000-2001 D Jeff Dionne + * Copyright (c) 2002 Greg Ungerer + * Copyright (c) 2007-2010 Paul Mundt + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include "internal.h" + +void *high_memory; +EXPORT_SYMBOL(high_memory); +struct page *mem_map; +unsigned long max_mapnr; +EXPORT_SYMBOL(max_mapnr); +unsigned long highest_memmap_pfn; +int sysctl_nr_trim_pages = CONFIG_NOMMU_INITIAL_TRIM_EXCESS; +int heap_stack_gap = 0; + +atomic_long_t mmap_pages_allocated; + +EXPORT_SYMBOL(mem_map); + +/* list of mapped, potentially shareable regions */ +static struct kmem_cache *vm_region_jar; +struct rb_root nommu_region_tree = RB_ROOT; +DECLARE_RWSEM(nommu_region_sem); + +const struct vm_operations_struct generic_file_vm_ops = { +}; + +/* + * Return the total memory allocated for this pointer, not + * just what the caller asked for. + * + * Doesn't have to be accurate, i.e. may have races. + */ +unsigned int kobjsize(const void *objp) +{ + struct page *page; + + /* + * If the object we have should not have ksize performed on it, + * return size of 0 + */ + if (!objp || !virt_addr_valid(objp)) + return 0; + + page = virt_to_head_page(objp); + + /* + * If the allocator sets PageSlab, we know the pointer came from + * kmalloc(). + */ + if (PageSlab(page)) + return ksize(objp); + + /* + * If it's not a compound page, see if we have a matching VMA + * region. This test is intentionally done in reverse order, + * so if there's no VMA, we still fall through and hand back + * PAGE_SIZE for 0-order pages. + */ + if (!PageCompound(page)) { + struct vm_area_struct *vma; + + vma = find_vma(current->mm, (unsigned long)objp); + if (vma) + return vma->vm_end - vma->vm_start; + } + + /* + * The ksize() function is only guaranteed to work for pointers + * returned by kmalloc(). So handle arbitrary pointers here. + */ + return page_size(page); +} + +/** + * follow_pfn - look up PFN at a user virtual address + * @vma: memory mapping + * @address: user virtual address + * @pfn: location to store found PFN + * + * Only IO mappings and raw PFN mappings are allowed. + * + * Returns zero and the pfn at @pfn on success, -ve otherwise. + */ +int follow_pfn(struct vm_area_struct *vma, unsigned long address, + unsigned long *pfn) +{ + if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) + return -EINVAL; + + *pfn = address >> PAGE_SHIFT; + return 0; +} +EXPORT_SYMBOL(follow_pfn); + +LIST_HEAD(vmap_area_list); + +void vfree(const void *addr) +{ + kfree(addr); +} +EXPORT_SYMBOL(vfree); + +void *__vmalloc(unsigned long size, gfp_t gfp_mask) +{ + /* + * You can't specify __GFP_HIGHMEM with kmalloc() since kmalloc() + * returns only a logical address. + */ + return kmalloc(size, (gfp_mask | __GFP_COMP) & ~__GFP_HIGHMEM); +} +EXPORT_SYMBOL(__vmalloc); + +void *__vmalloc_node_range(unsigned long size, unsigned long align, + unsigned long start, unsigned long end, gfp_t gfp_mask, + pgprot_t prot, unsigned long vm_flags, int node, + const void *caller) +{ + return __vmalloc(size, gfp_mask); +} + +void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, + int node, const void *caller) +{ + return __vmalloc(size, gfp_mask); +} + +static void *__vmalloc_user_flags(unsigned long size, gfp_t flags) +{ + void *ret; + + ret = __vmalloc(size, flags); + if (ret) { + struct vm_area_struct *vma; + + mmap_write_lock(current->mm); + vma = find_vma(current->mm, (unsigned long)ret); + if (vma) + vma->vm_flags |= VM_USERMAP; + mmap_write_unlock(current->mm); + } + + return ret; +} + +void *vmalloc_user(unsigned long size) +{ + return __vmalloc_user_flags(size, GFP_KERNEL | __GFP_ZERO); +} +EXPORT_SYMBOL(vmalloc_user); + +struct page *vmalloc_to_page(const void *addr) +{ + return virt_to_page(addr); +} +EXPORT_SYMBOL(vmalloc_to_page); + +unsigned long vmalloc_to_pfn(const void *addr) +{ + return page_to_pfn(virt_to_page(addr)); +} +EXPORT_SYMBOL(vmalloc_to_pfn); + +long vread(char *buf, char *addr, unsigned long count) +{ + /* Don't allow overflow */ + if ((unsigned long) buf + count < count) + count = -(unsigned long) buf; + + memcpy(buf, addr, count); + return count; +} + +long vwrite(char *buf, char *addr, unsigned long count) +{ + /* Don't allow overflow */ + if ((unsigned long) addr + count < count) + count = -(unsigned long) addr; + + memcpy(addr, buf, count); + return count; +} + +/* + * vmalloc - allocate virtually contiguous memory + * + * @size: allocation size + * + * Allocate enough pages to cover @size from the page level + * allocator and map them into contiguous kernel virtual space. + * + * For tight control over page level allocator and protection flags + * use __vmalloc() instead. + */ +void *vmalloc(unsigned long size) +{ + return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM); +} +EXPORT_SYMBOL(vmalloc); + +/* + * vzalloc - allocate virtually contiguous memory with zero fill + * + * @size: allocation size + * + * Allocate enough pages to cover @size from the page level + * allocator and map them into contiguous kernel virtual space. + * The memory allocated is set to zero. + * + * For tight control over page level allocator and protection flags + * use __vmalloc() instead. + */ +void *vzalloc(unsigned long size) +{ + return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO); +} +EXPORT_SYMBOL(vzalloc); + +/** + * vmalloc_node - allocate memory on a specific node + * @size: allocation size + * @node: numa node + * + * Allocate enough pages to cover @size from the page level + * allocator and map them into contiguous kernel virtual space. + * + * For tight control over page level allocator and protection flags + * use __vmalloc() instead. + */ +void *vmalloc_node(unsigned long size, int node) +{ + return vmalloc(size); +} +EXPORT_SYMBOL(vmalloc_node); + +/** + * vzalloc_node - allocate memory on a specific node with zero fill + * @size: allocation size + * @node: numa node + * + * Allocate enough pages to cover @size from the page level + * allocator and map them into contiguous kernel virtual space. + * The memory allocated is set to zero. + * + * For tight control over page level allocator and protection flags + * use __vmalloc() instead. + */ +void *vzalloc_node(unsigned long size, int node) +{ + return vzalloc(size); +} +EXPORT_SYMBOL(vzalloc_node); + +/** + * vmalloc_32 - allocate virtually contiguous memory (32bit addressable) + * @size: allocation size + * + * Allocate enough 32bit PA addressable pages to cover @size from the + * page level allocator and map them into contiguous kernel virtual space. + */ +void *vmalloc_32(unsigned long size) +{ + return __vmalloc(size, GFP_KERNEL); +} +EXPORT_SYMBOL(vmalloc_32); + +/** + * vmalloc_32_user - allocate zeroed virtually contiguous 32bit memory + * @size: allocation size + * + * The resulting memory area is 32bit addressable and zeroed so it can be + * mapped to userspace without leaking data. + * + * VM_USERMAP is set on the corresponding VMA so that subsequent calls to + * remap_vmalloc_range() are permissible. + */ +void *vmalloc_32_user(unsigned long size) +{ + /* + * We'll have to sort out the ZONE_DMA bits for 64-bit, + * but for now this can simply use vmalloc_user() directly. + */ + return vmalloc_user(size); +} +EXPORT_SYMBOL(vmalloc_32_user); + +void *vmap(struct page **pages, unsigned int count, unsigned long flags, pgprot_t prot) +{ + BUG(); + return NULL; +} +EXPORT_SYMBOL(vmap); + +void vunmap(const void *addr) +{ + BUG(); +} +EXPORT_SYMBOL(vunmap); + +void *vm_map_ram(struct page **pages, unsigned int count, int node) +{ + BUG(); + return NULL; +} +EXPORT_SYMBOL(vm_map_ram); + +void vm_unmap_ram(const void *mem, unsigned int count) +{ + BUG(); +} +EXPORT_SYMBOL(vm_unmap_ram); + +void vm_unmap_aliases(void) +{ +} +EXPORT_SYMBOL_GPL(vm_unmap_aliases); + +void free_vm_area(struct vm_struct *area) +{ + BUG(); +} +EXPORT_SYMBOL_GPL(free_vm_area); + +int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, + struct page *page) +{ + return -EINVAL; +} +EXPORT_SYMBOL(vm_insert_page); + +int vm_map_pages(struct vm_area_struct *vma, struct page **pages, + unsigned long num) +{ + return -EINVAL; +} +EXPORT_SYMBOL(vm_map_pages); + +int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages, + unsigned long num) +{ + return -EINVAL; +} +EXPORT_SYMBOL(vm_map_pages_zero); + +/* + * sys_brk() for the most part doesn't need the global kernel + * lock, except when an application is doing something nasty + * like trying to un-brk an area that has already been mapped + * to a regular file. in this case, the unmapping will need + * to invoke file system routines that need the global lock. + */ +SYSCALL_DEFINE1(brk, unsigned long, brk) +{ + struct mm_struct *mm = current->mm; + + if (brk < mm->start_brk || brk > mm->context.end_brk) + return mm->brk; + + if (mm->brk == brk) + return mm->brk; + + /* + * Always allow shrinking brk + */ + if (brk <= mm->brk) { + mm->brk = brk; + return brk; + } + + /* + * Ok, looks good - let it rip. + */ + flush_icache_user_range(mm->brk, brk); + return mm->brk = brk; +} + +/* + * initialise the percpu counter for VM and region record slabs + */ +void __init mmap_init(void) +{ + int ret; + + ret = percpu_counter_init(&vm_committed_as, 0, GFP_KERNEL); + VM_BUG_ON(ret); + vm_region_jar = KMEM_CACHE(vm_region, SLAB_PANIC|SLAB_ACCOUNT); +} + +/* + * validate the region tree + * - the caller must hold the region lock + */ +#ifdef CONFIG_DEBUG_NOMMU_REGIONS +static noinline void validate_nommu_regions(void) +{ + struct vm_region *region, *last; + struct rb_node *p, *lastp; + + lastp = rb_first(&nommu_region_tree); + if (!lastp) + return; + + last = rb_entry(lastp, struct vm_region, vm_rb); + BUG_ON(last->vm_end <= last->vm_start); + BUG_ON(last->vm_top < last->vm_end); + + while ((p = rb_next(lastp))) { + region = rb_entry(p, struct vm_region, vm_rb); + last = rb_entry(lastp, struct vm_region, vm_rb); + + BUG_ON(region->vm_end <= region->vm_start); + BUG_ON(region->vm_top < region->vm_end); + BUG_ON(region->vm_start < last->vm_top); + + lastp = p; + } +} +#else +static void validate_nommu_regions(void) +{ +} +#endif + +/* + * add a region into the global tree + */ +static void add_nommu_region(struct vm_region *region) +{ + struct vm_region *pregion; + struct rb_node **p, *parent; + + validate_nommu_regions(); + + parent = NULL; + p = &nommu_region_tree.rb_node; + while (*p) { + parent = *p; + pregion = rb_entry(parent, struct vm_region, vm_rb); + if (region->vm_start < pregion->vm_start) + p = &(*p)->rb_left; + else if (region->vm_start > pregion->vm_start) + p = &(*p)->rb_right; + else if (pregion == region) + return; + else + BUG(); + } + + rb_link_node(®ion->vm_rb, parent, p); + rb_insert_color(®ion->vm_rb, &nommu_region_tree); + + validate_nommu_regions(); +} + +/* + * delete a region from the global tree + */ +static void delete_nommu_region(struct vm_region *region) +{ + BUG_ON(!nommu_region_tree.rb_node); + + validate_nommu_regions(); + rb_erase(®ion->vm_rb, &nommu_region_tree); + validate_nommu_regions(); +} + +/* + * free a contiguous series of pages + */ +static void free_page_series(unsigned long from, unsigned long to) +{ + for (; from < to; from += PAGE_SIZE) { + struct page *page = virt_to_page(from); + + atomic_long_dec(&mmap_pages_allocated); + put_page(page); + } +} + +/* + * release a reference to a region + * - the caller must hold the region semaphore for writing, which this releases + * - the region may not have been added to the tree yet, in which case vm_top + * will equal vm_start + */ +static void __put_nommu_region(struct vm_region *region) + __releases(nommu_region_sem) +{ + BUG_ON(!nommu_region_tree.rb_node); + + if (--region->vm_usage == 0) { + if (region->vm_top > region->vm_start) + delete_nommu_region(region); + up_write(&nommu_region_sem); + + if (region->vm_file) + fput(region->vm_file); + + /* IO memory and memory shared directly out of the pagecache + * from ramfs/tmpfs mustn't be released here */ + if (region->vm_flags & VM_MAPPED_COPY) + free_page_series(region->vm_start, region->vm_top); + kmem_cache_free(vm_region_jar, region); + } else { + up_write(&nommu_region_sem); + } +} + +/* + * release a reference to a region + */ +static void put_nommu_region(struct vm_region *region) +{ + down_write(&nommu_region_sem); + __put_nommu_region(region); +} + +/* + * add a VMA into a process's mm_struct in the appropriate place in the list + * and tree and add to the address space's page tree also if not an anonymous + * page + * - should be called with mm->mmap_lock held writelocked + */ +static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma) +{ + struct vm_area_struct *pvma, *prev; + struct address_space *mapping; + struct rb_node **p, *parent, *rb_prev; + + BUG_ON(!vma->vm_region); + + mm->map_count++; + vma->vm_mm = mm; + + /* add the VMA to the mapping */ + if (vma->vm_file) { + mapping = vma->vm_file->f_mapping; + + i_mmap_lock_write(mapping); + flush_dcache_mmap_lock(mapping); + vma_interval_tree_insert(vma, &mapping->i_mmap); + flush_dcache_mmap_unlock(mapping); + i_mmap_unlock_write(mapping); + } + + /* add the VMA to the tree */ + parent = rb_prev = NULL; + p = &mm->mm_rb.rb_node; + while (*p) { + parent = *p; + pvma = rb_entry(parent, struct vm_area_struct, vm_rb); + + /* sort by: start addr, end addr, VMA struct addr in that order + * (the latter is necessary as we may get identical VMAs) */ + if (vma->vm_start < pvma->vm_start) + p = &(*p)->rb_left; + else if (vma->vm_start > pvma->vm_start) { + rb_prev = parent; + p = &(*p)->rb_right; + } else if (vma->vm_end < pvma->vm_end) + p = &(*p)->rb_left; + else if (vma->vm_end > pvma->vm_end) { + rb_prev = parent; + p = &(*p)->rb_right; + } else if (vma < pvma) + p = &(*p)->rb_left; + else if (vma > pvma) { + rb_prev = parent; + p = &(*p)->rb_right; + } else + BUG(); + } + + rb_link_node(&vma->vm_rb, parent, p); + rb_insert_color(&vma->vm_rb, &mm->mm_rb); + + /* add VMA to the VMA list also */ + prev = NULL; + if (rb_prev) + prev = rb_entry(rb_prev, struct vm_area_struct, vm_rb); + + __vma_link_list(mm, vma, prev); +} + +/* + * delete a VMA from its owning mm_struct and address space + */ +static void delete_vma_from_mm(struct vm_area_struct *vma) +{ + int i; + struct address_space *mapping; + struct mm_struct *mm = vma->vm_mm; + struct task_struct *curr = current; + + mm->map_count--; + for (i = 0; i < VMACACHE_SIZE; i++) { + /* if the vma is cached, invalidate the entire cache */ + if (curr->vmacache.vmas[i] == vma) { + vmacache_invalidate(mm); + break; + } + } + + /* remove the VMA from the mapping */ + if (vma->vm_file) { + mapping = vma->vm_file->f_mapping; + + i_mmap_lock_write(mapping); + flush_dcache_mmap_lock(mapping); + vma_interval_tree_remove(vma, &mapping->i_mmap); + flush_dcache_mmap_unlock(mapping); + i_mmap_unlock_write(mapping); + } + + /* remove from the MM's tree and list */ + rb_erase(&vma->vm_rb, &mm->mm_rb); + + __vma_unlink_list(mm, vma); +} + +/* + * destroy a VMA record + */ +static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma) +{ + if (vma->vm_ops && vma->vm_ops->close) + vma->vm_ops->close(vma); + if (vma->vm_file) + fput(vma->vm_file); + put_nommu_region(vma->vm_region); + vm_area_free(vma); +} + +/* + * look up the first VMA in which addr resides, NULL if none + * - should be called with mm->mmap_lock at least held readlocked + */ +struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) +{ + struct vm_area_struct *vma; + + /* check the cache first */ + vma = vmacache_find(mm, addr); + if (likely(vma)) + return vma; + + /* trawl the list (there may be multiple mappings in which addr + * resides) */ + for (vma = mm->mmap; vma; vma = vma->vm_next) { + if (vma->vm_start > addr) + return NULL; + if (vma->vm_end > addr) { + vmacache_update(addr, vma); + return vma; + } + } + + return NULL; +} +EXPORT_SYMBOL(find_vma); + +/* + * find a VMA + * - we don't extend stack VMAs under NOMMU conditions + */ +struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr) +{ + return find_vma(mm, addr); +} + +/* + * expand a stack to a given address + * - not supported under NOMMU conditions + */ +int expand_stack(struct vm_area_struct *vma, unsigned long address) +{ + return -ENOMEM; +} + +/* + * look up the first VMA exactly that exactly matches addr + * - should be called with mm->mmap_lock at least held readlocked + */ +static struct vm_area_struct *find_vma_exact(struct mm_struct *mm, + unsigned long addr, + unsigned long len) +{ + struct vm_area_struct *vma; + unsigned long end = addr + len; + + /* check the cache first */ + vma = vmacache_find_exact(mm, addr, end); + if (vma) + return vma; + + /* trawl the list (there may be multiple mappings in which addr + * resides) */ + for (vma = mm->mmap; vma; vma = vma->vm_next) { + if (vma->vm_start < addr) + continue; + if (vma->vm_start > addr) + return NULL; + if (vma->vm_end == end) { + vmacache_update(addr, vma); + return vma; + } + } + + return NULL; +} + +/* + * determine whether a mapping should be permitted and, if so, what sort of + * mapping we're capable of supporting + */ +static int validate_mmap_request(struct file *file, + unsigned long addr, + unsigned long len, + unsigned long prot, + unsigned long flags, + unsigned long pgoff, + unsigned long *_capabilities) +{ + unsigned long capabilities, rlen; + int ret; + + /* do the simple checks first */ + if (flags & MAP_FIXED) + return -EINVAL; + + if ((flags & MAP_TYPE) != MAP_PRIVATE && + (flags & MAP_TYPE) != MAP_SHARED) + return -EINVAL; + + if (!len) + return -EINVAL; + + /* Careful about overflows.. */ + rlen = PAGE_ALIGN(len); + if (!rlen || rlen > TASK_SIZE) + return -ENOMEM; + + /* offset overflow? */ + if ((pgoff + (rlen >> PAGE_SHIFT)) < pgoff) + return -EOVERFLOW; + + if (file) { + /* files must support mmap */ + if (!file->f_op->mmap) + return -ENODEV; + + /* work out if what we've got could possibly be shared + * - we support chardevs that provide their own "memory" + * - we support files/blockdevs that are memory backed + */ + if (file->f_op->mmap_capabilities) { + capabilities = file->f_op->mmap_capabilities(file); + } else { + /* no explicit capabilities set, so assume some + * defaults */ + switch (file_inode(file)->i_mode & S_IFMT) { + case S_IFREG: + case S_IFBLK: + capabilities = NOMMU_MAP_COPY; + break; + + case S_IFCHR: + capabilities = + NOMMU_MAP_DIRECT | + NOMMU_MAP_READ | + NOMMU_MAP_WRITE; + break; + + default: + return -EINVAL; + } + } + + /* eliminate any capabilities that we can't support on this + * device */ + if (!file->f_op->get_unmapped_area) + capabilities &= ~NOMMU_MAP_DIRECT; + if (!(file->f_mode & FMODE_CAN_READ)) + capabilities &= ~NOMMU_MAP_COPY; + + /* The file shall have been opened with read permission. */ + if (!(file->f_mode & FMODE_READ)) + return -EACCES; + + if (flags & MAP_SHARED) { + /* do checks for writing, appending and locking */ + if ((prot & PROT_WRITE) && + !(file->f_mode & FMODE_WRITE)) + return -EACCES; + + if (IS_APPEND(file_inode(file)) && + (file->f_mode & FMODE_WRITE)) + return -EACCES; + + if (locks_verify_locked(file)) + return -EAGAIN; + + if (!(capabilities & NOMMU_MAP_DIRECT)) + return -ENODEV; + + /* we mustn't privatise shared mappings */ + capabilities &= ~NOMMU_MAP_COPY; + } else { + /* we're going to read the file into private memory we + * allocate */ + if (!(capabilities & NOMMU_MAP_COPY)) + return -ENODEV; + + /* we don't permit a private writable mapping to be + * shared with the backing device */ + if (prot & PROT_WRITE) + capabilities &= ~NOMMU_MAP_DIRECT; + } + + if (capabilities & NOMMU_MAP_DIRECT) { + if (((prot & PROT_READ) && !(capabilities & NOMMU_MAP_READ)) || + ((prot & PROT_WRITE) && !(capabilities & NOMMU_MAP_WRITE)) || + ((prot & PROT_EXEC) && !(capabilities & NOMMU_MAP_EXEC)) + ) { + capabilities &= ~NOMMU_MAP_DIRECT; + if (flags & MAP_SHARED) { + pr_warn("MAP_SHARED not completely supported on !MMU\n"); + return -EINVAL; + } + } + } + + /* handle executable mappings and implied executable + * mappings */ + if (path_noexec(&file->f_path)) { + if (prot & PROT_EXEC) + return -EPERM; + } else if ((prot & PROT_READ) && !(prot & PROT_EXEC)) { + /* handle implication of PROT_EXEC by PROT_READ */ + if (current->personality & READ_IMPLIES_EXEC) { + if (capabilities & NOMMU_MAP_EXEC) + prot |= PROT_EXEC; + } + } else if ((prot & PROT_READ) && + (prot & PROT_EXEC) && + !(capabilities & NOMMU_MAP_EXEC) + ) { + /* backing file is not executable, try to copy */ + capabilities &= ~NOMMU_MAP_DIRECT; + } + } else { + /* anonymous mappings are always memory backed and can be + * privately mapped + */ + capabilities = NOMMU_MAP_COPY; + + /* handle PROT_EXEC implication by PROT_READ */ + if ((prot & PROT_READ) && + (current->personality & READ_IMPLIES_EXEC)) + prot |= PROT_EXEC; + } + + /* allow the security API to have its say */ + ret = security_mmap_addr(addr); + if (ret < 0) + return ret; + + /* looks okay */ + *_capabilities = capabilities; + return 0; +} + +/* + * we've determined that we can make the mapping, now translate what we + * now know into VMA flags + */ +static unsigned long determine_vm_flags(struct file *file, + unsigned long prot, + unsigned long flags, + unsigned long capabilities) +{ + unsigned long vm_flags; + + vm_flags = calc_vm_prot_bits(prot, 0) | calc_vm_flag_bits(flags); + /* vm_flags |= mm->def_flags; */ + + if (!(capabilities & NOMMU_MAP_DIRECT)) { + /* attempt to share read-only copies of mapped file chunks */ + vm_flags |= VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC; + if (file && !(prot & PROT_WRITE)) + vm_flags |= VM_MAYSHARE; + } else { + /* overlay a shareable mapping on the backing device or inode + * if possible - used for chardevs, ramfs/tmpfs/shmfs and + * romfs/cramfs */ + vm_flags |= VM_MAYSHARE | (capabilities & NOMMU_VMFLAGS); + if (flags & MAP_SHARED) + vm_flags |= VM_SHARED; + } + + /* refuse to let anyone share private mappings with this process if + * it's being traced - otherwise breakpoints set in it may interfere + * with another untraced process + */ + if ((flags & MAP_PRIVATE) && current->ptrace) + vm_flags &= ~VM_MAYSHARE; + + return vm_flags; +} + +/* + * set up a shared mapping on a file (the driver or filesystem provides and + * pins the storage) + */ +static int do_mmap_shared_file(struct vm_area_struct *vma) +{ + int ret; + + ret = call_mmap(vma->vm_file, vma); + if (ret == 0) { + vma->vm_region->vm_top = vma->vm_region->vm_end; + return 0; + } + if (ret != -ENOSYS) + return ret; + + /* getting -ENOSYS indicates that direct mmap isn't possible (as + * opposed to tried but failed) so we can only give a suitable error as + * it's not possible to make a private copy if MAP_SHARED was given */ + return -ENODEV; +} + +/* + * set up a private mapping or an anonymous shared mapping + */ +static int do_mmap_private(struct vm_area_struct *vma, + struct vm_region *region, + unsigned long len, + unsigned long capabilities) +{ + unsigned long total, point; + void *base; + int ret, order; + + /* invoke the file's mapping function so that it can keep track of + * shared mappings on devices or memory + * - VM_MAYSHARE will be set if it may attempt to share + */ + if (capabilities & NOMMU_MAP_DIRECT) { + ret = call_mmap(vma->vm_file, vma); + if (ret == 0) { + /* shouldn't return success if we're not sharing */ + BUG_ON(!(vma->vm_flags & VM_MAYSHARE)); + vma->vm_region->vm_top = vma->vm_region->vm_end; + return 0; + } + if (ret != -ENOSYS) + return ret; + + /* getting an ENOSYS error indicates that direct mmap isn't + * possible (as opposed to tried but failed) so we'll try to + * make a private copy of the data and map that instead */ + } + + + /* allocate some memory to hold the mapping + * - note that this may not return a page-aligned address if the object + * we're allocating is smaller than a page + */ + order = get_order(len); + total = 1 << order; + point = len >> PAGE_SHIFT; + + /* we don't want to allocate a power-of-2 sized page set */ + if (sysctl_nr_trim_pages && total - point >= sysctl_nr_trim_pages) + total = point; + + base = alloc_pages_exact(total << PAGE_SHIFT, GFP_KERNEL); + if (!base) + goto enomem; + + atomic_long_add(total, &mmap_pages_allocated); + + region->vm_flags = vma->vm_flags |= VM_MAPPED_COPY; + region->vm_start = (unsigned long) base; + region->vm_end = region->vm_start + len; + region->vm_top = region->vm_start + (total << PAGE_SHIFT); + + vma->vm_start = region->vm_start; + vma->vm_end = region->vm_start + len; + + if (vma->vm_file) { + /* read the contents of a file into the copy */ + loff_t fpos; + + fpos = vma->vm_pgoff; + fpos <<= PAGE_SHIFT; + + ret = kernel_read(vma->vm_file, base, len, &fpos); + if (ret < 0) + goto error_free; + + /* clear the last little bit */ + if (ret < len) + memset(base + ret, 0, len - ret); + + } else { + vma_set_anonymous(vma); + } + + return 0; + +error_free: + free_page_series(region->vm_start, region->vm_top); + region->vm_start = vma->vm_start = 0; + region->vm_end = vma->vm_end = 0; + region->vm_top = 0; + return ret; + +enomem: + pr_err("Allocation of length %lu from process %d (%s) failed\n", + len, current->pid, current->comm); + show_free_areas(0, NULL); + return -ENOMEM; +} + +/* + * handle mapping creation for uClinux + */ +unsigned long do_mmap(struct file *file, + unsigned long addr, + unsigned long len, + unsigned long prot, + unsigned long flags, + unsigned long pgoff, + unsigned long *populate, + struct list_head *uf) +{ + struct vm_area_struct *vma; + struct vm_region *region; + struct rb_node *rb; + vm_flags_t vm_flags; + unsigned long capabilities, result; + int ret; + + *populate = 0; + + /* decide whether we should attempt the mapping, and if so what sort of + * mapping */ + ret = validate_mmap_request(file, addr, len, prot, flags, pgoff, + &capabilities); + if (ret < 0) + return ret; + + /* we ignore the address hint */ + addr = 0; + len = PAGE_ALIGN(len); + + /* we've determined that we can make the mapping, now translate what we + * now know into VMA flags */ + vm_flags = determine_vm_flags(file, prot, flags, capabilities); + + /* we're going to need to record the mapping */ + region = kmem_cache_zalloc(vm_region_jar, GFP_KERNEL); + if (!region) + goto error_getting_region; + + vma = vm_area_alloc(current->mm); + if (!vma) + goto error_getting_vma; + + region->vm_usage = 1; + region->vm_flags = vm_flags; + region->vm_pgoff = pgoff; + + vma->vm_flags = vm_flags; + vma->vm_pgoff = pgoff; + + if (file) { + region->vm_file = get_file(file); + vma->vm_file = get_file(file); + } + + down_write(&nommu_region_sem); + + /* if we want to share, we need to check for regions created by other + * mmap() calls that overlap with our proposed mapping + * - we can only share with a superset match on most regular files + * - shared mappings on character devices and memory backed files are + * permitted to overlap inexactly as far as we are concerned for in + * these cases, sharing is handled in the driver or filesystem rather + * than here + */ + if (vm_flags & VM_MAYSHARE) { + struct vm_region *pregion; + unsigned long pglen, rpglen, pgend, rpgend, start; + + pglen = (len + PAGE_SIZE - 1) >> PAGE_SHIFT; + pgend = pgoff + pglen; + + for (rb = rb_first(&nommu_region_tree); rb; rb = rb_next(rb)) { + pregion = rb_entry(rb, struct vm_region, vm_rb); + + if (!(pregion->vm_flags & VM_MAYSHARE)) + continue; + + /* search for overlapping mappings on the same file */ + if (file_inode(pregion->vm_file) != + file_inode(file)) + continue; + + if (pregion->vm_pgoff >= pgend) + continue; + + rpglen = pregion->vm_end - pregion->vm_start; + rpglen = (rpglen + PAGE_SIZE - 1) >> PAGE_SHIFT; + rpgend = pregion->vm_pgoff + rpglen; + if (pgoff >= rpgend) + continue; + + /* handle inexactly overlapping matches between + * mappings */ + if ((pregion->vm_pgoff != pgoff || rpglen != pglen) && + !(pgoff >= pregion->vm_pgoff && pgend <= rpgend)) { + /* new mapping is not a subset of the region */ + if (!(capabilities & NOMMU_MAP_DIRECT)) + goto sharing_violation; + continue; + } + + /* we've found a region we can share */ + pregion->vm_usage++; + vma->vm_region = pregion; + start = pregion->vm_start; + start += (pgoff - pregion->vm_pgoff) << PAGE_SHIFT; + vma->vm_start = start; + vma->vm_end = start + len; + + if (pregion->vm_flags & VM_MAPPED_COPY) + vma->vm_flags |= VM_MAPPED_COPY; + else { + ret = do_mmap_shared_file(vma); + if (ret < 0) { + vma->vm_region = NULL; + vma->vm_start = 0; + vma->vm_end = 0; + pregion->vm_usage--; + pregion = NULL; + goto error_just_free; + } + } + fput(region->vm_file); + kmem_cache_free(vm_region_jar, region); + region = pregion; + result = start; + goto share; + } + + /* obtain the address at which to make a shared mapping + * - this is the hook for quasi-memory character devices to + * tell us the location of a shared mapping + */ + if (capabilities & NOMMU_MAP_DIRECT) { + addr = file->f_op->get_unmapped_area(file, addr, len, + pgoff, flags); + if (IS_ERR_VALUE(addr)) { + ret = addr; + if (ret != -ENOSYS) + goto error_just_free; + + /* the driver refused to tell us where to site + * the mapping so we'll have to attempt to copy + * it */ + ret = -ENODEV; + if (!(capabilities & NOMMU_MAP_COPY)) + goto error_just_free; + + capabilities &= ~NOMMU_MAP_DIRECT; + } else { + vma->vm_start = region->vm_start = addr; + vma->vm_end = region->vm_end = addr + len; + } + } + } + + vma->vm_region = region; + + /* set up the mapping + * - the region is filled in if NOMMU_MAP_DIRECT is still set + */ + if (file && vma->vm_flags & VM_SHARED) + ret = do_mmap_shared_file(vma); + else + ret = do_mmap_private(vma, region, len, capabilities); + if (ret < 0) + goto error_just_free; + add_nommu_region(region); + + /* clear anonymous mappings that don't ask for uninitialized data */ + if (!vma->vm_file && + (!IS_ENABLED(CONFIG_MMAP_ALLOW_UNINITIALIZED) || + !(flags & MAP_UNINITIALIZED))) + memset((void *)region->vm_start, 0, + region->vm_end - region->vm_start); + + /* okay... we have a mapping; now we have to register it */ + result = vma->vm_start; + + current->mm->total_vm += len >> PAGE_SHIFT; + +share: + add_vma_to_mm(current->mm, vma); + + /* we flush the region from the icache only when the first executable + * mapping of it is made */ + if (vma->vm_flags & VM_EXEC && !region->vm_icache_flushed) { + flush_icache_user_range(region->vm_start, region->vm_end); + region->vm_icache_flushed = true; + } + + up_write(&nommu_region_sem); + + return result; + +error_just_free: + up_write(&nommu_region_sem); +error: + if (region->vm_file) + fput(region->vm_file); + kmem_cache_free(vm_region_jar, region); + if (vma->vm_file) + fput(vma->vm_file); + vm_area_free(vma); + return ret; + +sharing_violation: + up_write(&nommu_region_sem); + pr_warn("Attempt to share mismatched mappings\n"); + ret = -EINVAL; + goto error; + +error_getting_vma: + kmem_cache_free(vm_region_jar, region); + pr_warn("Allocation of vma for %lu byte allocation from process %d failed\n", + len, current->pid); + show_free_areas(0, NULL); + return -ENOMEM; + +error_getting_region: + pr_warn("Allocation of vm region for %lu byte allocation from process %d failed\n", + len, current->pid); + show_free_areas(0, NULL); + return -ENOMEM; +} + +unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, + unsigned long prot, unsigned long flags, + unsigned long fd, unsigned long pgoff) +{ + struct file *file = NULL; + unsigned long retval = -EBADF; + + audit_mmap_fd(fd, flags); + if (!(flags & MAP_ANONYMOUS)) { + file = fget(fd); + if (!file) + goto out; + } + + flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE); + + retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff); + + if (file) + fput(file); +out: + return retval; +} + +SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len, + unsigned long, prot, unsigned long, flags, + unsigned long, fd, unsigned long, pgoff) +{ + return ksys_mmap_pgoff(addr, len, prot, flags, fd, pgoff); +} + +#ifdef __ARCH_WANT_SYS_OLD_MMAP +struct mmap_arg_struct { + unsigned long addr; + unsigned long len; + unsigned long prot; + unsigned long flags; + unsigned long fd; + unsigned long offset; +}; + +SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg) +{ + struct mmap_arg_struct a; + + if (copy_from_user(&a, arg, sizeof(a))) + return -EFAULT; + if (offset_in_page(a.offset)) + return -EINVAL; + + return ksys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, + a.offset >> PAGE_SHIFT); +} +#endif /* __ARCH_WANT_SYS_OLD_MMAP */ + +/* + * split a vma into two pieces at address 'addr', a new vma is allocated either + * for the first part or the tail. + */ +int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, int new_below) +{ + struct vm_area_struct *new; + struct vm_region *region; + unsigned long npages; + + /* we're only permitted to split anonymous regions (these should have + * only a single usage on the region) */ + if (vma->vm_file) + return -ENOMEM; + + if (mm->map_count >= sysctl_max_map_count) + return -ENOMEM; + + region = kmem_cache_alloc(vm_region_jar, GFP_KERNEL); + if (!region) + return -ENOMEM; + + new = vm_area_dup(vma); + if (!new) { + kmem_cache_free(vm_region_jar, region); + return -ENOMEM; + } + + /* most fields are the same, copy all, and then fixup */ + *region = *vma->vm_region; + new->vm_region = region; + + npages = (addr - vma->vm_start) >> PAGE_SHIFT; + + if (new_below) { + region->vm_top = region->vm_end = new->vm_end = addr; + } else { + region->vm_start = new->vm_start = addr; + region->vm_pgoff = new->vm_pgoff += npages; + } + + if (new->vm_ops && new->vm_ops->open) + new->vm_ops->open(new); + + delete_vma_from_mm(vma); + down_write(&nommu_region_sem); + delete_nommu_region(vma->vm_region); + if (new_below) { + vma->vm_region->vm_start = vma->vm_start = addr; + vma->vm_region->vm_pgoff = vma->vm_pgoff += npages; + } else { + vma->vm_region->vm_end = vma->vm_end = addr; + vma->vm_region->vm_top = addr; + } + add_nommu_region(vma->vm_region); + add_nommu_region(new->vm_region); + up_write(&nommu_region_sem); + add_vma_to_mm(mm, vma); + add_vma_to_mm(mm, new); + return 0; +} + +/* + * shrink a VMA by removing the specified chunk from either the beginning or + * the end + */ +static int shrink_vma(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long from, unsigned long to) +{ + struct vm_region *region; + + /* adjust the VMA's pointers, which may reposition it in the MM's tree + * and list */ + delete_vma_from_mm(vma); + if (from > vma->vm_start) + vma->vm_end = from; + else + vma->vm_start = to; + add_vma_to_mm(mm, vma); + + /* cut the backing region down to size */ + region = vma->vm_region; + BUG_ON(region->vm_usage != 1); + + down_write(&nommu_region_sem); + delete_nommu_region(region); + if (from > region->vm_start) { + to = region->vm_top; + region->vm_top = region->vm_end = from; + } else { + region->vm_start = to; + } + add_nommu_region(region); + up_write(&nommu_region_sem); + + free_page_series(from, to); + return 0; +} + +/* + * release a mapping + * - under NOMMU conditions the chunk to be unmapped must be backed by a single + * VMA, though it need not cover the whole VMA + */ +int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf) +{ + struct vm_area_struct *vma; + unsigned long end; + int ret; + + len = PAGE_ALIGN(len); + if (len == 0) + return -EINVAL; + + end = start + len; + + /* find the first potentially overlapping VMA */ + vma = find_vma(mm, start); + if (!vma) { + static int limit; + if (limit < 5) { + pr_warn("munmap of memory not mmapped by process %d (%s): 0x%lx-0x%lx\n", + current->pid, current->comm, + start, start + len - 1); + limit++; + } + return -EINVAL; + } + + /* we're allowed to split an anonymous VMA but not a file-backed one */ + if (vma->vm_file) { + do { + if (start > vma->vm_start) + return -EINVAL; + if (end == vma->vm_end) + goto erase_whole_vma; + vma = vma->vm_next; + } while (vma); + return -EINVAL; + } else { + /* the chunk must be a subset of the VMA found */ + if (start == vma->vm_start && end == vma->vm_end) + goto erase_whole_vma; + if (start < vma->vm_start || end > vma->vm_end) + return -EINVAL; + if (offset_in_page(start)) + return -EINVAL; + if (end != vma->vm_end && offset_in_page(end)) + return -EINVAL; + if (start != vma->vm_start && end != vma->vm_end) { + ret = split_vma(mm, vma, start, 1); + if (ret < 0) + return ret; + } + return shrink_vma(mm, vma, start, end); + } + +erase_whole_vma: + delete_vma_from_mm(vma); + delete_vma(mm, vma); + return 0; +} +EXPORT_SYMBOL(do_munmap); + +int vm_munmap(unsigned long addr, size_t len) +{ + struct mm_struct *mm = current->mm; + int ret; + + mmap_write_lock(mm); + ret = do_munmap(mm, addr, len, NULL); + mmap_write_unlock(mm); + return ret; +} +EXPORT_SYMBOL(vm_munmap); + +SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len) +{ + return vm_munmap(addr, len); +} + +/* + * release all the mappings made in a process's VM space + */ +void exit_mmap(struct mm_struct *mm) +{ + struct vm_area_struct *vma; + + if (!mm) + return; + + mm->total_vm = 0; + + while ((vma = mm->mmap)) { + mm->mmap = vma->vm_next; + delete_vma_from_mm(vma); + delete_vma(mm, vma); + cond_resched(); + } +} + +int vm_brk(unsigned long addr, unsigned long len) +{ + return -ENOMEM; +} + +/* + * expand (or shrink) an existing mapping, potentially moving it at the same + * time (controlled by the MREMAP_MAYMOVE flag and available VM space) + * + * under NOMMU conditions, we only permit changing a mapping's size, and only + * as long as it stays within the region allocated by do_mmap_private() and the + * block is not shareable + * + * MREMAP_FIXED is not supported under NOMMU conditions + */ +static unsigned long do_mremap(unsigned long addr, + unsigned long old_len, unsigned long new_len, + unsigned long flags, unsigned long new_addr) +{ + struct vm_area_struct *vma; + + /* insanity checks first */ + old_len = PAGE_ALIGN(old_len); + new_len = PAGE_ALIGN(new_len); + if (old_len == 0 || new_len == 0) + return (unsigned long) -EINVAL; + + if (offset_in_page(addr)) + return -EINVAL; + + if (flags & MREMAP_FIXED && new_addr != addr) + return (unsigned long) -EINVAL; + + vma = find_vma_exact(current->mm, addr, old_len); + if (!vma) + return (unsigned long) -EINVAL; + + if (vma->vm_end != vma->vm_start + old_len) + return (unsigned long) -EFAULT; + + if (vma->vm_flags & VM_MAYSHARE) + return (unsigned long) -EPERM; + + if (new_len > vma->vm_region->vm_end - vma->vm_region->vm_start) + return (unsigned long) -ENOMEM; + + /* all checks complete - do it */ + vma->vm_end = vma->vm_start + new_len; + return vma->vm_start; +} + +SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, + unsigned long, new_len, unsigned long, flags, + unsigned long, new_addr) +{ + unsigned long ret; + + mmap_write_lock(current->mm); + ret = do_mremap(addr, old_len, new_len, flags, new_addr); + mmap_write_unlock(current->mm); + return ret; +} + +struct page *follow_page(struct vm_area_struct *vma, unsigned long address, + unsigned int foll_flags) +{ + return NULL; +} + +int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, unsigned long size, pgprot_t prot) +{ + if (addr != (pfn << PAGE_SHIFT)) + return -EINVAL; + + vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; + return 0; +} +EXPORT_SYMBOL(remap_pfn_range); + +int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len) +{ + unsigned long pfn = start >> PAGE_SHIFT; + unsigned long vm_len = vma->vm_end - vma->vm_start; + + pfn += vma->vm_pgoff; + return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot); +} +EXPORT_SYMBOL(vm_iomap_memory); + +int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, + unsigned long pgoff) +{ + unsigned int size = vma->vm_end - vma->vm_start; + + if (!(vma->vm_flags & VM_USERMAP)) + return -EINVAL; + + vma->vm_start = (unsigned long)(addr + (pgoff << PAGE_SHIFT)); + vma->vm_end = vma->vm_start + size; + + return 0; +} +EXPORT_SYMBOL(remap_vmalloc_range); + +unsigned long arch_get_unmapped_area(struct file *file, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags) +{ + return -ENOMEM; +} + +vm_fault_t filemap_fault(struct vm_fault *vmf) +{ + BUG(); + return 0; +} +EXPORT_SYMBOL(filemap_fault); + +void filemap_map_pages(struct vm_fault *vmf, + pgoff_t start_pgoff, pgoff_t end_pgoff) +{ + BUG(); +} +EXPORT_SYMBOL(filemap_map_pages); + +int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, + unsigned long addr, void *buf, int len, unsigned int gup_flags) +{ + struct vm_area_struct *vma; + int write = gup_flags & FOLL_WRITE; + + if (mmap_read_lock_killable(mm)) + return 0; + + /* the access must start within one of the target process's mappings */ + vma = find_vma(mm, addr); + if (vma) { + /* don't overrun this mapping */ + if (addr + len >= vma->vm_end) + len = vma->vm_end - addr; + + /* only read or write mappings where it is permitted */ + if (write && vma->vm_flags & VM_MAYWRITE) + copy_to_user_page(vma, NULL, addr, + (void *) addr, buf, len); + else if (!write && vma->vm_flags & VM_MAYREAD) + copy_from_user_page(vma, NULL, addr, + buf, (void *) addr, len); + else + len = 0; + } else { + len = 0; + } + + mmap_read_unlock(mm); + + return len; +} + +/** + * access_remote_vm - access another process' address space + * @mm: the mm_struct of the target address space + * @addr: start address to access + * @buf: source or destination buffer + * @len: number of bytes to transfer + * @gup_flags: flags modifying lookup behaviour + * + * The caller must hold a reference on @mm. + */ +int access_remote_vm(struct mm_struct *mm, unsigned long addr, + void *buf, int len, unsigned int gup_flags) +{ + return __access_remote_vm(NULL, mm, addr, buf, len, gup_flags); +} + +/* + * Access another process' address space. + * - source/target buffer must be kernel space + */ +int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, + unsigned int gup_flags) +{ + struct mm_struct *mm; + + if (addr + len < addr) + return 0; + + mm = get_task_mm(tsk); + if (!mm) + return 0; + + len = __access_remote_vm(tsk, mm, addr, buf, len, gup_flags); + + mmput(mm); + return len; +} +EXPORT_SYMBOL_GPL(access_process_vm); + +/** + * nommu_shrink_inode_mappings - Shrink the shared mappings on an inode + * @inode: The inode to check + * @size: The current filesize of the inode + * @newsize: The proposed filesize of the inode + * + * Check the shared mappings on an inode on behalf of a shrinking truncate to + * make sure that any outstanding VMAs aren't broken and then shrink the + * vm_regions that extend beyond so that do_mmap() doesn't + * automatically grant mappings that are too large. + */ +int nommu_shrink_inode_mappings(struct inode *inode, size_t size, + size_t newsize) +{ + struct vm_area_struct *vma; + struct vm_region *region; + pgoff_t low, high; + size_t r_size, r_top; + + low = newsize >> PAGE_SHIFT; + high = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; + + down_write(&nommu_region_sem); + i_mmap_lock_read(inode->i_mapping); + + /* search for VMAs that fall within the dead zone */ + vma_interval_tree_foreach(vma, &inode->i_mapping->i_mmap, low, high) { + /* found one - only interested if it's shared out of the page + * cache */ + if (vma->vm_flags & VM_SHARED) { + i_mmap_unlock_read(inode->i_mapping); + up_write(&nommu_region_sem); + return -ETXTBSY; /* not quite true, but near enough */ + } + } + + /* reduce any regions that overlap the dead zone - if in existence, + * these will be pointed to by VMAs that don't overlap the dead zone + * + * we don't check for any regions that start beyond the EOF as there + * shouldn't be any + */ + vma_interval_tree_foreach(vma, &inode->i_mapping->i_mmap, 0, ULONG_MAX) { + if (!(vma->vm_flags & VM_SHARED)) + continue; + + region = vma->vm_region; + r_size = region->vm_top - region->vm_start; + r_top = (region->vm_pgoff << PAGE_SHIFT) + r_size; + + if (r_top > newsize) { + region->vm_top -= r_top - newsize; + if (region->vm_end > region->vm_top) + region->vm_end = region->vm_top; + } + } + + i_mmap_unlock_read(inode->i_mapping); + up_write(&nommu_region_sem); + return 0; +} + +/* + * Initialise sysctl_user_reserve_kbytes. + * + * This is intended to prevent a user from starting a single memory hogging + * process, such that they cannot recover (kill the hog) in OVERCOMMIT_NEVER + * mode. + * + * The default value is min(3% of free memory, 128MB) + * 128MB is enough to recover with sshd/login, bash, and top/kill. + */ +static int __meminit init_user_reserve(void) +{ + unsigned long free_kbytes; + + free_kbytes = global_zone_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); + + sysctl_user_reserve_kbytes = min(free_kbytes / 32, 1UL << 17); + return 0; +} +subsys_initcall(init_user_reserve); + +/* + * Initialise sysctl_admin_reserve_kbytes. + * + * The purpose of sysctl_admin_reserve_kbytes is to allow the sys admin + * to log in and kill a memory hogging process. + * + * Systems with more than 256MB will reserve 8MB, enough to recover + * with sshd, bash, and top in OVERCOMMIT_GUESS. Smaller systems will + * only reserve 3% of free pages by default. + */ +static int __meminit init_admin_reserve(void) +{ + unsigned long free_kbytes; + + free_kbytes = global_zone_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); + + sysctl_admin_reserve_kbytes = min(free_kbytes / 32, 1UL << 13); + return 0; +} +subsys_initcall(init_admin_reserve); diff --git a/mm/oom_kill.c b/mm/oom_kill.c new file mode 100644 index 000000000..3d7c557fb --- /dev/null +++ b/mm/oom_kill.c @@ -0,0 +1,1165 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/mm/oom_kill.c + * + * Copyright (C) 1998,2000 Rik van Riel + * Thanks go out to Claus Fischer for some serious inspiration and + * for goading me into coding this file... + * Copyright (C) 2010 Google, Inc. + * Rewritten by David Rientjes + * + * The routines in this file are used to kill a process when + * we're seriously out of memory. This gets called from __alloc_pages() + * in mm/page_alloc.c when we really run out of memory. + * + * Since we won't call these routines often (on a well-configured + * machine) this file will double as a 'coding guide' and a signpost + * for newbie kernel hackers. It features several pointers to major + * kernel subsystems and hints as to where to find out what things do. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include "internal.h" +#include "slab.h" + +#define CREATE_TRACE_POINTS +#include + +int sysctl_panic_on_oom; +int sysctl_oom_kill_allocating_task; +int sysctl_oom_dump_tasks = 1; + +/* + * Serializes oom killer invocations (out_of_memory()) from all contexts to + * prevent from over eager oom killing (e.g. when the oom killer is invoked + * from different domains). + * + * oom_killer_disable() relies on this lock to stabilize oom_killer_disabled + * and mark_oom_victim + */ +DEFINE_MUTEX(oom_lock); +/* Serializes oom_score_adj and oom_score_adj_min updates */ +DEFINE_MUTEX(oom_adj_mutex); + +static inline bool is_memcg_oom(struct oom_control *oc) +{ + return oc->memcg != NULL; +} + +#ifdef CONFIG_NUMA +/** + * oom_cpuset_eligible() - check task eligiblity for kill + * @start: task struct of which task to consider + * @oc: pointer to struct oom_control + * + * Task eligibility is determined by whether or not a candidate task, @tsk, + * shares the same mempolicy nodes as current if it is bound by such a policy + * and whether or not it has the same set of allowed cpuset nodes. + * + * This function is assuming oom-killer context and 'current' has triggered + * the oom-killer. + */ +static bool oom_cpuset_eligible(struct task_struct *start, + struct oom_control *oc) +{ + struct task_struct *tsk; + bool ret = false; + const nodemask_t *mask = oc->nodemask; + + if (is_memcg_oom(oc)) + return true; + + rcu_read_lock(); + for_each_thread(start, tsk) { + if (mask) { + /* + * If this is a mempolicy constrained oom, tsk's + * cpuset is irrelevant. Only return true if its + * mempolicy intersects current, otherwise it may be + * needlessly killed. + */ + ret = mempolicy_nodemask_intersects(tsk, mask); + } else { + /* + * This is not a mempolicy constrained oom, so only + * check the mems of tsk's cpuset. + */ + ret = cpuset_mems_allowed_intersects(current, tsk); + } + if (ret) + break; + } + rcu_read_unlock(); + + return ret; +} +#else +static bool oom_cpuset_eligible(struct task_struct *tsk, struct oom_control *oc) +{ + return true; +} +#endif /* CONFIG_NUMA */ + +/* + * The process p may have detached its own ->mm while exiting or through + * kthread_use_mm(), but one or more of its subthreads may still have a valid + * pointer. Return p, or any of its subthreads with a valid ->mm, with + * task_lock() held. + */ +struct task_struct *find_lock_task_mm(struct task_struct *p) +{ + struct task_struct *t; + + rcu_read_lock(); + + for_each_thread(p, t) { + task_lock(t); + if (likely(t->mm)) + goto found; + task_unlock(t); + } + t = NULL; +found: + rcu_read_unlock(); + + return t; +} + +/* + * order == -1 means the oom kill is required by sysrq, otherwise only + * for display purposes. + */ +static inline bool is_sysrq_oom(struct oom_control *oc) +{ + return oc->order == -1; +} + +/* return true if the task is not adequate as candidate victim task. */ +static bool oom_unkillable_task(struct task_struct *p) +{ + if (is_global_init(p)) + return true; + if (p->flags & PF_KTHREAD) + return true; + return false; +} + +/* + * Print out unreclaimble slabs info when unreclaimable slabs amount is greater + * than all user memory (LRU pages) + */ +static bool is_dump_unreclaim_slabs(void) +{ + unsigned long nr_lru; + + nr_lru = global_node_page_state(NR_ACTIVE_ANON) + + global_node_page_state(NR_INACTIVE_ANON) + + global_node_page_state(NR_ACTIVE_FILE) + + global_node_page_state(NR_INACTIVE_FILE) + + global_node_page_state(NR_ISOLATED_ANON) + + global_node_page_state(NR_ISOLATED_FILE) + + global_node_page_state(NR_UNEVICTABLE); + + return (global_node_page_state_pages(NR_SLAB_UNRECLAIMABLE_B) > nr_lru); +} + +/** + * oom_badness - heuristic function to determine which candidate task to kill + * @p: task struct of which task we should calculate + * @totalpages: total present RAM allowed for page allocation + * + * The heuristic for determining which task to kill is made to be as simple and + * predictable as possible. The goal is to return the highest value for the + * task consuming the most memory to avoid subsequent oom failures. + */ +long oom_badness(struct task_struct *p, unsigned long totalpages) +{ + long points; + long adj; + + if (oom_unkillable_task(p)) + return LONG_MIN; + + p = find_lock_task_mm(p); + if (!p) + return LONG_MIN; + + /* + * Do not even consider tasks which are explicitly marked oom + * unkillable or have been already oom reaped or the are in + * the middle of vfork + */ + adj = (long)p->signal->oom_score_adj; + if (adj == OOM_SCORE_ADJ_MIN || + test_bit(MMF_OOM_SKIP, &p->mm->flags) || + in_vfork(p)) { + task_unlock(p); + return LONG_MIN; + } + + /* + * The baseline for the badness score is the proportion of RAM that each + * task's rss, pagetable and swap space use. + */ + points = get_mm_rss(p->mm) + get_mm_counter(p->mm, MM_SWAPENTS) + + mm_pgtables_bytes(p->mm) / PAGE_SIZE; + task_unlock(p); + + /* Normalize to oom_score_adj units */ + adj *= totalpages / 1000; + points += adj; + + return points; +} + +static const char * const oom_constraint_text[] = { + [CONSTRAINT_NONE] = "CONSTRAINT_NONE", + [CONSTRAINT_CPUSET] = "CONSTRAINT_CPUSET", + [CONSTRAINT_MEMORY_POLICY] = "CONSTRAINT_MEMORY_POLICY", + [CONSTRAINT_MEMCG] = "CONSTRAINT_MEMCG", +}; + +/* + * Determine the type of allocation constraint. + */ +static enum oom_constraint constrained_alloc(struct oom_control *oc) +{ + struct zone *zone; + struct zoneref *z; + enum zone_type highest_zoneidx = gfp_zone(oc->gfp_mask); + bool cpuset_limited = false; + int nid; + + if (is_memcg_oom(oc)) { + oc->totalpages = mem_cgroup_get_max(oc->memcg) ?: 1; + return CONSTRAINT_MEMCG; + } + + /* Default to all available memory */ + oc->totalpages = totalram_pages() + total_swap_pages; + + if (!IS_ENABLED(CONFIG_NUMA)) + return CONSTRAINT_NONE; + + if (!oc->zonelist) + return CONSTRAINT_NONE; + /* + * Reach here only when __GFP_NOFAIL is used. So, we should avoid + * to kill current.We have to random task kill in this case. + * Hopefully, CONSTRAINT_THISNODE...but no way to handle it, now. + */ + if (oc->gfp_mask & __GFP_THISNODE) + return CONSTRAINT_NONE; + + /* + * This is not a __GFP_THISNODE allocation, so a truncated nodemask in + * the page allocator means a mempolicy is in effect. Cpuset policy + * is enforced in get_page_from_freelist(). + */ + if (oc->nodemask && + !nodes_subset(node_states[N_MEMORY], *oc->nodemask)) { + oc->totalpages = total_swap_pages; + for_each_node_mask(nid, *oc->nodemask) + oc->totalpages += node_present_pages(nid); + return CONSTRAINT_MEMORY_POLICY; + } + + /* Check this allocation failure is caused by cpuset's wall function */ + for_each_zone_zonelist_nodemask(zone, z, oc->zonelist, + highest_zoneidx, oc->nodemask) + if (!cpuset_zone_allowed(zone, oc->gfp_mask)) + cpuset_limited = true; + + if (cpuset_limited) { + oc->totalpages = total_swap_pages; + for_each_node_mask(nid, cpuset_current_mems_allowed) + oc->totalpages += node_present_pages(nid); + return CONSTRAINT_CPUSET; + } + return CONSTRAINT_NONE; +} + +static int oom_evaluate_task(struct task_struct *task, void *arg) +{ + struct oom_control *oc = arg; + long points; + + if (oom_unkillable_task(task)) + goto next; + + /* p may not have freeable memory in nodemask */ + if (!is_memcg_oom(oc) && !oom_cpuset_eligible(task, oc)) + goto next; + + /* + * This task already has access to memory reserves and is being killed. + * Don't allow any other task to have access to the reserves unless + * the task has MMF_OOM_SKIP because chances that it would release + * any memory is quite low. + */ + if (!is_sysrq_oom(oc) && tsk_is_oom_victim(task)) { + if (test_bit(MMF_OOM_SKIP, &task->signal->oom_mm->flags)) + goto next; + goto abort; + } + + /* + * If task is allocating a lot of memory and has been marked to be + * killed first if it triggers an oom, then select it. + */ + if (oom_task_origin(task)) { + points = LONG_MAX; + goto select; + } + + points = oom_badness(task, oc->totalpages); + if (points == LONG_MIN || points < oc->chosen_points) + goto next; + +select: + if (oc->chosen) + put_task_struct(oc->chosen); + get_task_struct(task); + oc->chosen = task; + oc->chosen_points = points; +next: + return 0; +abort: + if (oc->chosen) + put_task_struct(oc->chosen); + oc->chosen = (void *)-1UL; + return 1; +} + +/* + * Simple selection loop. We choose the process with the highest number of + * 'points'. In case scan was aborted, oc->chosen is set to -1. + */ +static void select_bad_process(struct oom_control *oc) +{ + oc->chosen_points = LONG_MIN; + + if (is_memcg_oom(oc)) + mem_cgroup_scan_tasks(oc->memcg, oom_evaluate_task, oc); + else { + struct task_struct *p; + + rcu_read_lock(); + for_each_process(p) + if (oom_evaluate_task(p, oc)) + break; + rcu_read_unlock(); + } +} + +static int dump_task(struct task_struct *p, void *arg) +{ + struct oom_control *oc = arg; + struct task_struct *task; + + if (oom_unkillable_task(p)) + return 0; + + /* p may not have freeable memory in nodemask */ + if (!is_memcg_oom(oc) && !oom_cpuset_eligible(p, oc)) + return 0; + + task = find_lock_task_mm(p); + if (!task) { + /* + * This is a kthread or all of p's threads have already + * detached their mm's. There's no need to report + * them; they can't be oom killed anyway. + */ + return 0; + } + + pr_info("[%7d] %5d %5d %8lu %8lu %8ld %8lu %5hd %s\n", + task->pid, from_kuid(&init_user_ns, task_uid(task)), + task->tgid, task->mm->total_vm, get_mm_rss(task->mm), + mm_pgtables_bytes(task->mm), + get_mm_counter(task->mm, MM_SWAPENTS), + task->signal->oom_score_adj, task->comm); + task_unlock(task); + + return 0; +} + +/** + * dump_tasks - dump current memory state of all system tasks + * @oc: pointer to struct oom_control + * + * Dumps the current memory state of all eligible tasks. Tasks not in the same + * memcg, not in the same cpuset, or bound to a disjoint set of mempolicy nodes + * are not shown. + * State information includes task's pid, uid, tgid, vm size, rss, + * pgtables_bytes, swapents, oom_score_adj value, and name. + */ +static void dump_tasks(struct oom_control *oc) +{ + pr_info("Tasks state (memory values in pages):\n"); + pr_info("[ pid ] uid tgid total_vm rss pgtables_bytes swapents oom_score_adj name\n"); + + if (is_memcg_oom(oc)) + mem_cgroup_scan_tasks(oc->memcg, dump_task, oc); + else { + struct task_struct *p; + + rcu_read_lock(); + for_each_process(p) + dump_task(p, oc); + rcu_read_unlock(); + } +} + +static void dump_oom_summary(struct oom_control *oc, struct task_struct *victim) +{ + /* one line summary of the oom killer context. */ + pr_info("oom-kill:constraint=%s,nodemask=%*pbl", + oom_constraint_text[oc->constraint], + nodemask_pr_args(oc->nodemask)); + cpuset_print_current_mems_allowed(); + mem_cgroup_print_oom_context(oc->memcg, victim); + pr_cont(",task=%s,pid=%d,uid=%d\n", victim->comm, victim->pid, + from_kuid(&init_user_ns, task_uid(victim))); +} + +static void dump_header(struct oom_control *oc, struct task_struct *p) +{ + pr_warn("%s invoked oom-killer: gfp_mask=%#x(%pGg), order=%d, oom_score_adj=%hd\n", + current->comm, oc->gfp_mask, &oc->gfp_mask, oc->order, + current->signal->oom_score_adj); + if (!IS_ENABLED(CONFIG_COMPACTION) && oc->order) + pr_warn("COMPACTION is disabled!!!\n"); + + dump_stack(); + if (is_memcg_oom(oc)) + mem_cgroup_print_oom_meminfo(oc->memcg); + else { + show_mem(SHOW_MEM_FILTER_NODES, oc->nodemask); + if (is_dump_unreclaim_slabs()) + dump_unreclaimable_slab(); + } + if (sysctl_oom_dump_tasks) + dump_tasks(oc); + if (p) + dump_oom_summary(oc, p); +} + +/* + * Number of OOM victims in flight + */ +static atomic_t oom_victims = ATOMIC_INIT(0); +static DECLARE_WAIT_QUEUE_HEAD(oom_victims_wait); + +static bool oom_killer_disabled __read_mostly; + +#define K(x) ((x) << (PAGE_SHIFT-10)) + +/* + * task->mm can be NULL if the task is the exited group leader. So to + * determine whether the task is using a particular mm, we examine all the + * task's threads: if one of those is using this mm then this task was also + * using it. + */ +bool process_shares_mm(struct task_struct *p, struct mm_struct *mm) +{ + struct task_struct *t; + + for_each_thread(p, t) { + struct mm_struct *t_mm = READ_ONCE(t->mm); + if (t_mm) + return t_mm == mm; + } + return false; +} + +#ifdef CONFIG_MMU +/* + * OOM Reaper kernel thread which tries to reap the memory used by the OOM + * victim (if that is possible) to help the OOM killer to move on. + */ +static struct task_struct *oom_reaper_th; +static DECLARE_WAIT_QUEUE_HEAD(oom_reaper_wait); +static struct task_struct *oom_reaper_list; +static DEFINE_SPINLOCK(oom_reaper_lock); + +bool __oom_reap_task_mm(struct mm_struct *mm) +{ + struct vm_area_struct *vma; + bool ret = true; + + /* + * Tell all users of get_user/copy_from_user etc... that the content + * is no longer stable. No barriers really needed because unmapping + * should imply barriers already and the reader would hit a page fault + * if it stumbled over a reaped memory. + */ + set_bit(MMF_UNSTABLE, &mm->flags); + + for (vma = mm->mmap ; vma; vma = vma->vm_next) { + if (!can_madv_lru_vma(vma)) + continue; + + /* + * Only anonymous pages have a good chance to be dropped + * without additional steps which we cannot afford as we + * are OOM already. + * + * We do not even care about fs backed pages because all + * which are reclaimable have already been reclaimed and + * we do not want to block exit_mmap by keeping mm ref + * count elevated without a good reason. + */ + if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) { + struct mmu_notifier_range range; + struct mmu_gather tlb; + + mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, + vma, mm, vma->vm_start, + vma->vm_end); + tlb_gather_mmu(&tlb, mm, range.start, range.end); + if (mmu_notifier_invalidate_range_start_nonblock(&range)) { + tlb_finish_mmu(&tlb, range.start, range.end); + ret = false; + continue; + } + unmap_page_range(&tlb, vma, range.start, range.end, NULL); + mmu_notifier_invalidate_range_end(&range); + tlb_finish_mmu(&tlb, range.start, range.end); + } + } + + return ret; +} + +/* + * Reaps the address space of the give task. + * + * Returns true on success and false if none or part of the address space + * has been reclaimed and the caller should retry later. + */ +static bool oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm) +{ + bool ret = true; + + if (!mmap_read_trylock(mm)) { + trace_skip_task_reaping(tsk->pid); + return false; + } + + /* + * MMF_OOM_SKIP is set by exit_mmap when the OOM reaper can't + * work on the mm anymore. The check for MMF_OOM_SKIP must run + * under mmap_lock for reading because it serializes against the + * mmap_write_lock();mmap_write_unlock() cycle in exit_mmap(). + */ + if (test_bit(MMF_OOM_SKIP, &mm->flags)) { + trace_skip_task_reaping(tsk->pid); + goto out_unlock; + } + + trace_start_task_reaping(tsk->pid); + + /* failed to reap part of the address space. Try again later */ + ret = __oom_reap_task_mm(mm); + if (!ret) + goto out_finish; + + pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n", + task_pid_nr(tsk), tsk->comm, + K(get_mm_counter(mm, MM_ANONPAGES)), + K(get_mm_counter(mm, MM_FILEPAGES)), + K(get_mm_counter(mm, MM_SHMEMPAGES))); +out_finish: + trace_finish_task_reaping(tsk->pid); +out_unlock: + mmap_read_unlock(mm); + + return ret; +} + +#define MAX_OOM_REAP_RETRIES 10 +static void oom_reap_task(struct task_struct *tsk) +{ + int attempts = 0; + struct mm_struct *mm = tsk->signal->oom_mm; + + /* Retry the mmap_read_trylock(mm) a few times */ + while (attempts++ < MAX_OOM_REAP_RETRIES && !oom_reap_task_mm(tsk, mm)) + schedule_timeout_idle(HZ/10); + + if (attempts <= MAX_OOM_REAP_RETRIES || + test_bit(MMF_OOM_SKIP, &mm->flags)) + goto done; + + pr_info("oom_reaper: unable to reap pid:%d (%s)\n", + task_pid_nr(tsk), tsk->comm); + sched_show_task(tsk); + debug_show_all_locks(); + +done: + tsk->oom_reaper_list = NULL; + + /* + * Hide this mm from OOM killer because it has been either reaped or + * somebody can't call mmap_write_unlock(mm). + */ + set_bit(MMF_OOM_SKIP, &mm->flags); + + /* Drop a reference taken by queue_oom_reaper */ + put_task_struct(tsk); +} + +static int oom_reaper(void *unused) +{ + while (true) { + struct task_struct *tsk = NULL; + + wait_event_freezable(oom_reaper_wait, oom_reaper_list != NULL); + spin_lock_irq(&oom_reaper_lock); + if (oom_reaper_list != NULL) { + tsk = oom_reaper_list; + oom_reaper_list = tsk->oom_reaper_list; + } + spin_unlock_irq(&oom_reaper_lock); + + if (tsk) + oom_reap_task(tsk); + } + + return 0; +} + +static void wake_oom_reaper(struct timer_list *timer) +{ + struct task_struct *tsk = container_of(timer, struct task_struct, + oom_reaper_timer); + struct mm_struct *mm = tsk->signal->oom_mm; + unsigned long flags; + + /* The victim managed to terminate on its own - see exit_mmap */ + if (test_bit(MMF_OOM_SKIP, &mm->flags)) { + put_task_struct(tsk); + return; + } + + spin_lock_irqsave(&oom_reaper_lock, flags); + tsk->oom_reaper_list = oom_reaper_list; + oom_reaper_list = tsk; + spin_unlock_irqrestore(&oom_reaper_lock, flags); + trace_wake_reaper(tsk->pid); + wake_up(&oom_reaper_wait); +} + +/* + * Give the OOM victim time to exit naturally before invoking the oom_reaping. + * The timers timeout is arbitrary... the longer it is, the longer the worst + * case scenario for the OOM can take. If it is too small, the oom_reaper can + * get in the way and release resources needed by the process exit path. + * e.g. The futex robust list can sit in Anon|Private memory that gets reaped + * before the exit path is able to wake the futex waiters. + */ +#define OOM_REAPER_DELAY (2*HZ) +static void queue_oom_reaper(struct task_struct *tsk) +{ + /* mm is already queued? */ + if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags)) + return; + + get_task_struct(tsk); + timer_setup(&tsk->oom_reaper_timer, wake_oom_reaper, 0); + tsk->oom_reaper_timer.expires = jiffies + OOM_REAPER_DELAY; + add_timer(&tsk->oom_reaper_timer); +} + +static int __init oom_init(void) +{ + oom_reaper_th = kthread_run(oom_reaper, NULL, "oom_reaper"); + return 0; +} +subsys_initcall(oom_init) +#else +static inline void queue_oom_reaper(struct task_struct *tsk) +{ +} +#endif /* CONFIG_MMU */ + +/** + * mark_oom_victim - mark the given task as OOM victim + * @tsk: task to mark + * + * Has to be called with oom_lock held and never after + * oom has been disabled already. + * + * tsk->mm has to be non NULL and caller has to guarantee it is stable (either + * under task_lock or operate on the current). + */ +static void mark_oom_victim(struct task_struct *tsk) +{ + struct mm_struct *mm = tsk->mm; + + WARN_ON(oom_killer_disabled); + /* OOM killer might race with memcg OOM */ + if (test_and_set_tsk_thread_flag(tsk, TIF_MEMDIE)) + return; + + /* oom_mm is bound to the signal struct life time. */ + if (!cmpxchg(&tsk->signal->oom_mm, NULL, mm)) { + mmgrab(tsk->signal->oom_mm); + set_bit(MMF_OOM_VICTIM, &mm->flags); + } + + /* + * Make sure that the task is woken up from uninterruptible sleep + * if it is frozen because OOM killer wouldn't be able to free + * any memory and livelock. freezing_slow_path will tell the freezer + * that TIF_MEMDIE tasks should be ignored. + */ + __thaw_task(tsk); + atomic_inc(&oom_victims); + trace_mark_victim(tsk->pid); +} + +/** + * exit_oom_victim - note the exit of an OOM victim + */ +void exit_oom_victim(void) +{ + clear_thread_flag(TIF_MEMDIE); + + if (!atomic_dec_return(&oom_victims)) + wake_up_all(&oom_victims_wait); +} + +/** + * oom_killer_enable - enable OOM killer + */ +void oom_killer_enable(void) +{ + oom_killer_disabled = false; + pr_info("OOM killer enabled.\n"); +} + +/** + * oom_killer_disable - disable OOM killer + * @timeout: maximum timeout to wait for oom victims in jiffies + * + * Forces all page allocations to fail rather than trigger OOM killer. + * Will block and wait until all OOM victims are killed or the given + * timeout expires. + * + * The function cannot be called when there are runnable user tasks because + * the userspace would see unexpected allocation failures as a result. Any + * new usage of this function should be consulted with MM people. + * + * Returns true if successful and false if the OOM killer cannot be + * disabled. + */ +bool oom_killer_disable(signed long timeout) +{ + signed long ret; + + /* + * Make sure to not race with an ongoing OOM killer. Check that the + * current is not killed (possibly due to sharing the victim's memory). + */ + if (mutex_lock_killable(&oom_lock)) + return false; + oom_killer_disabled = true; + mutex_unlock(&oom_lock); + + ret = wait_event_interruptible_timeout(oom_victims_wait, + !atomic_read(&oom_victims), timeout); + if (ret <= 0) { + oom_killer_enable(); + return false; + } + pr_info("OOM killer disabled.\n"); + + return true; +} + +static inline bool __task_will_free_mem(struct task_struct *task) +{ + struct signal_struct *sig = task->signal; + + /* + * A coredumping process may sleep for an extended period in exit_mm(), + * so the oom killer cannot assume that the process will promptly exit + * and release memory. + */ + if (sig->flags & SIGNAL_GROUP_COREDUMP) + return false; + + if (sig->flags & SIGNAL_GROUP_EXIT) + return true; + + if (thread_group_empty(task) && (task->flags & PF_EXITING)) + return true; + + return false; +} + +/* + * Checks whether the given task is dying or exiting and likely to + * release its address space. This means that all threads and processes + * sharing the same mm have to be killed or exiting. + * Caller has to make sure that task->mm is stable (hold task_lock or + * it operates on the current). + */ +static bool task_will_free_mem(struct task_struct *task) +{ + struct mm_struct *mm = task->mm; + struct task_struct *p; + bool ret = true; + + /* + * Skip tasks without mm because it might have passed its exit_mm and + * exit_oom_victim. oom_reaper could have rescued that but do not rely + * on that for now. We can consider find_lock_task_mm in future. + */ + if (!mm) + return false; + + if (!__task_will_free_mem(task)) + return false; + + /* + * This task has already been drained by the oom reaper so there are + * only small chances it will free some more + */ + if (test_bit(MMF_OOM_SKIP, &mm->flags)) + return false; + + if (atomic_read(&mm->mm_users) <= 1) + return true; + + /* + * Make sure that all tasks which share the mm with the given tasks + * are dying as well to make sure that a) nobody pins its mm and + * b) the task is also reapable by the oom reaper. + */ + rcu_read_lock(); + for_each_process(p) { + if (!process_shares_mm(p, mm)) + continue; + if (same_thread_group(task, p)) + continue; + ret = __task_will_free_mem(p); + if (!ret) + break; + } + rcu_read_unlock(); + + return ret; +} + +static void __oom_kill_process(struct task_struct *victim, const char *message) +{ + struct task_struct *p; + struct mm_struct *mm; + bool can_oom_reap = true; + + p = find_lock_task_mm(victim); + if (!p) { + pr_info("%s: OOM victim %d (%s) is already exiting. Skip killing the task\n", + message, task_pid_nr(victim), victim->comm); + put_task_struct(victim); + return; + } else if (victim != p) { + get_task_struct(p); + put_task_struct(victim); + victim = p; + } + + /* Get a reference to safely compare mm after task_unlock(victim) */ + mm = victim->mm; + mmgrab(mm); + + /* Raise event before sending signal: task reaper must see this */ + count_vm_event(OOM_KILL); + memcg_memory_event_mm(mm, MEMCG_OOM_KILL); + + /* + * We should send SIGKILL before granting access to memory reserves + * in order to prevent the OOM victim from depleting the memory + * reserves from the user space under its control. + */ + do_send_sig_info(SIGKILL, SEND_SIG_PRIV, victim, PIDTYPE_TGID); + mark_oom_victim(victim); + pr_err("%s: Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB, UID:%u pgtables:%lukB oom_score_adj:%hd\n", + message, task_pid_nr(victim), victim->comm, K(mm->total_vm), + K(get_mm_counter(mm, MM_ANONPAGES)), + K(get_mm_counter(mm, MM_FILEPAGES)), + K(get_mm_counter(mm, MM_SHMEMPAGES)), + from_kuid(&init_user_ns, task_uid(victim)), + mm_pgtables_bytes(mm) >> 10, victim->signal->oom_score_adj); + task_unlock(victim); + + /* + * Kill all user processes sharing victim->mm in other thread groups, if + * any. They don't get access to memory reserves, though, to avoid + * depletion of all memory. This prevents mm->mmap_lock livelock when an + * oom killed thread cannot exit because it requires the semaphore and + * its contended by another thread trying to allocate memory itself. + * That thread will now get access to memory reserves since it has a + * pending fatal signal. + */ + rcu_read_lock(); + for_each_process(p) { + if (!process_shares_mm(p, mm)) + continue; + if (same_thread_group(p, victim)) + continue; + if (is_global_init(p)) { + can_oom_reap = false; + set_bit(MMF_OOM_SKIP, &mm->flags); + pr_info("oom killer %d (%s) has mm pinned by %d (%s)\n", + task_pid_nr(victim), victim->comm, + task_pid_nr(p), p->comm); + continue; + } + /* + * No kthead_use_mm() user needs to read from the userspace so + * we are ok to reap it. + */ + if (unlikely(p->flags & PF_KTHREAD)) + continue; + do_send_sig_info(SIGKILL, SEND_SIG_PRIV, p, PIDTYPE_TGID); + } + rcu_read_unlock(); + + if (can_oom_reap) + queue_oom_reaper(victim); + + mmdrop(mm); + put_task_struct(victim); +} +#undef K + +/* + * Kill provided task unless it's secured by setting + * oom_score_adj to OOM_SCORE_ADJ_MIN. + */ +static int oom_kill_memcg_member(struct task_struct *task, void *message) +{ + if (task->signal->oom_score_adj != OOM_SCORE_ADJ_MIN && + !is_global_init(task)) { + get_task_struct(task); + __oom_kill_process(task, message); + } + return 0; +} + +static void oom_kill_process(struct oom_control *oc, const char *message) +{ + struct task_struct *victim = oc->chosen; + struct mem_cgroup *oom_group; + static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); + + /* + * If the task is already exiting, don't alarm the sysadmin or kill + * its children or threads, just give it access to memory reserves + * so it can die quickly + */ + task_lock(victim); + if (task_will_free_mem(victim)) { + mark_oom_victim(victim); + queue_oom_reaper(victim); + task_unlock(victim); + put_task_struct(victim); + return; + } + task_unlock(victim); + + if (__ratelimit(&oom_rs)) + dump_header(oc, victim); + + /* + * Do we need to kill the entire memory cgroup? + * Or even one of the ancestor memory cgroups? + * Check this out before killing the victim task. + */ + oom_group = mem_cgroup_get_oom_group(victim, oc->memcg); + + __oom_kill_process(victim, message); + + /* + * If necessary, kill all tasks in the selected memory cgroup. + */ + if (oom_group) { + mem_cgroup_print_oom_group(oom_group); + mem_cgroup_scan_tasks(oom_group, oom_kill_memcg_member, + (void*)message); + mem_cgroup_put(oom_group); + } +} + +/* + * Determines whether the kernel must panic because of the panic_on_oom sysctl. + */ +static void check_panic_on_oom(struct oom_control *oc) +{ + if (likely(!sysctl_panic_on_oom)) + return; + if (sysctl_panic_on_oom != 2) { + /* + * panic_on_oom == 1 only affects CONSTRAINT_NONE, the kernel + * does not panic for cpuset, mempolicy, or memcg allocation + * failures. + */ + if (oc->constraint != CONSTRAINT_NONE) + return; + } + /* Do not panic for oom kills triggered by sysrq */ + if (is_sysrq_oom(oc)) + return; + dump_header(oc, NULL); + panic("Out of memory: %s panic_on_oom is enabled\n", + sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide"); +} + +static BLOCKING_NOTIFIER_HEAD(oom_notify_list); + +int register_oom_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&oom_notify_list, nb); +} +EXPORT_SYMBOL_GPL(register_oom_notifier); + +int unregister_oom_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&oom_notify_list, nb); +} +EXPORT_SYMBOL_GPL(unregister_oom_notifier); + +/** + * out_of_memory - kill the "best" process when we run out of memory + * @oc: pointer to struct oom_control + * + * If we run out of memory, we have the choice between either + * killing a random task (bad), letting the system crash (worse) + * OR try to be smart about which process to kill. Note that we + * don't have to be perfect here, we just have to be good. + */ +bool out_of_memory(struct oom_control *oc) +{ + unsigned long freed = 0; + + if (oom_killer_disabled) + return false; + + if (!is_memcg_oom(oc)) { + blocking_notifier_call_chain(&oom_notify_list, 0, &freed); + if (freed > 0) + /* Got some memory back in the last second. */ + return true; + } + + /* + * If current has a pending SIGKILL or is exiting, then automatically + * select it. The goal is to allow it to allocate so that it may + * quickly exit and free its memory. + */ + if (task_will_free_mem(current)) { + mark_oom_victim(current); + queue_oom_reaper(current); + return true; + } + + /* + * The OOM killer does not compensate for IO-less reclaim. + * pagefault_out_of_memory lost its gfp context so we have to + * make sure exclude 0 mask - all other users should have at least + * ___GFP_DIRECT_RECLAIM to get here. But mem_cgroup_oom() has to + * invoke the OOM killer even if it is a GFP_NOFS allocation. + */ + if (oc->gfp_mask && !(oc->gfp_mask & __GFP_FS) && !is_memcg_oom(oc)) + return true; + + /* + * Check if there were limitations on the allocation (only relevant for + * NUMA and memcg) that may require different handling. + */ + oc->constraint = constrained_alloc(oc); + if (oc->constraint != CONSTRAINT_MEMORY_POLICY) + oc->nodemask = NULL; + check_panic_on_oom(oc); + + if (!is_memcg_oom(oc) && sysctl_oom_kill_allocating_task && + current->mm && !oom_unkillable_task(current) && + oom_cpuset_eligible(current, oc) && + current->signal->oom_score_adj != OOM_SCORE_ADJ_MIN) { + get_task_struct(current); + oc->chosen = current; + oom_kill_process(oc, "Out of memory (oom_kill_allocating_task)"); + return true; + } + + select_bad_process(oc); + /* Found nothing?!?! */ + if (!oc->chosen) { + dump_header(oc, NULL); + pr_warn("Out of memory and no killable processes...\n"); + /* + * If we got here due to an actual allocation at the + * system level, we cannot survive this and will enter + * an endless loop in the allocator. Bail out now. + */ + if (!is_sysrq_oom(oc) && !is_memcg_oom(oc)) + panic("System is deadlocked on memory\n"); + } + if (oc->chosen && oc->chosen != (void *)-1UL) + oom_kill_process(oc, !is_memcg_oom(oc) ? "Out of memory" : + "Memory cgroup out of memory"); + return !!oc->chosen; +} + +/* + * The pagefault handler calls here because some allocation has failed. We have + * to take care of the memcg OOM here because this is the only safe context without + * any locks held but let the oom killer triggered from the allocation context care + * about the global OOM. + */ +void pagefault_out_of_memory(void) +{ + static DEFINE_RATELIMIT_STATE(pfoom_rs, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); + + if (mem_cgroup_oom_synchronize(true)) + return; + + if (fatal_signal_pending(current)) + return; + + if (__ratelimit(&pfoom_rs)) + pr_warn("Huh VM_FAULT_OOM leaked out to the #PF handler. Retrying PF\n"); +} diff --git a/mm/page-writeback.c b/mm/page-writeback.c new file mode 100644 index 000000000..eb34d204d --- /dev/null +++ b/mm/page-writeback.c @@ -0,0 +1,2850 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * mm/page-writeback.c + * + * Copyright (C) 2002, Linus Torvalds. + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra + * + * Contains functions related to writing back dirty pages at the + * address_space level. + * + * 10Apr2002 Andrew Morton + * Initial version + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include /* __set_page_dirty_buffers */ +#include +#include +#include +#include +#include +#include + +#include "internal.h" + +/* + * Sleep at most 200ms at a time in balance_dirty_pages(). + */ +#define MAX_PAUSE max(HZ/5, 1) + +/* + * Try to keep balance_dirty_pages() call intervals higher than this many pages + * by raising pause time to max_pause when falls below it. + */ +#define DIRTY_POLL_THRESH (128 >> (PAGE_SHIFT - 10)) + +/* + * Estimate write bandwidth at 200ms intervals. + */ +#define BANDWIDTH_INTERVAL max(HZ/5, 1) + +#define RATELIMIT_CALC_SHIFT 10 + +/* + * After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited + * will look to see if it needs to force writeback or throttling. + */ +static long ratelimit_pages = 32; + +/* The following parameters are exported via /proc/sys/vm */ + +/* + * Start background writeback (via writeback threads) at this percentage + */ +int dirty_background_ratio = 10; + +/* + * dirty_background_bytes starts at 0 (disabled) so that it is a function of + * dirty_background_ratio * the amount of dirtyable memory + */ +unsigned long dirty_background_bytes; + +/* + * free highmem will not be subtracted from the total free memory + * for calculating free ratios if vm_highmem_is_dirtyable is true + */ +int vm_highmem_is_dirtyable; + +/* + * The generator of dirty data starts writeback at this percentage + */ +int vm_dirty_ratio = 20; + +/* + * vm_dirty_bytes starts at 0 (disabled) so that it is a function of + * vm_dirty_ratio * the amount of dirtyable memory + */ +unsigned long vm_dirty_bytes; + +/* + * The interval between `kupdate'-style writebacks + */ +unsigned int dirty_writeback_interval = 5 * 100; /* centiseconds */ + +EXPORT_SYMBOL_GPL(dirty_writeback_interval); + +/* + * The longest time for which data is allowed to remain dirty + */ +unsigned int dirty_expire_interval = 30 * 100; /* centiseconds */ + +/* + * Flag that makes the machine dump writes/reads and block dirtyings. + */ +int block_dump; + +/* + * Flag that puts the machine in "laptop mode". Doubles as a timeout in jiffies: + * a full sync is triggered after this time elapses without any disk activity. + */ +int laptop_mode; + +EXPORT_SYMBOL(laptop_mode); + +/* End of sysctl-exported parameters */ + +struct wb_domain global_wb_domain; + +/* consolidated parameters for balance_dirty_pages() and its subroutines */ +struct dirty_throttle_control { +#ifdef CONFIG_CGROUP_WRITEBACK + struct wb_domain *dom; + struct dirty_throttle_control *gdtc; /* only set in memcg dtc's */ +#endif + struct bdi_writeback *wb; + struct fprop_local_percpu *wb_completions; + + unsigned long avail; /* dirtyable */ + unsigned long dirty; /* file_dirty + write + nfs */ + unsigned long thresh; /* dirty threshold */ + unsigned long bg_thresh; /* dirty background threshold */ + + unsigned long wb_dirty; /* per-wb counterparts */ + unsigned long wb_thresh; + unsigned long wb_bg_thresh; + + unsigned long pos_ratio; +}; + +/* + * Length of period for aging writeout fractions of bdis. This is an + * arbitrarily chosen number. The longer the period, the slower fractions will + * reflect changes in current writeout rate. + */ +#define VM_COMPLETIONS_PERIOD_LEN (3*HZ) + +#ifdef CONFIG_CGROUP_WRITEBACK + +#define GDTC_INIT(__wb) .wb = (__wb), \ + .dom = &global_wb_domain, \ + .wb_completions = &(__wb)->completions + +#define GDTC_INIT_NO_WB .dom = &global_wb_domain + +#define MDTC_INIT(__wb, __gdtc) .wb = (__wb), \ + .dom = mem_cgroup_wb_domain(__wb), \ + .wb_completions = &(__wb)->memcg_completions, \ + .gdtc = __gdtc + +static bool mdtc_valid(struct dirty_throttle_control *dtc) +{ + return dtc->dom; +} + +static struct wb_domain *dtc_dom(struct dirty_throttle_control *dtc) +{ + return dtc->dom; +} + +static struct dirty_throttle_control *mdtc_gdtc(struct dirty_throttle_control *mdtc) +{ + return mdtc->gdtc; +} + +static struct fprop_local_percpu *wb_memcg_completions(struct bdi_writeback *wb) +{ + return &wb->memcg_completions; +} + +static void wb_min_max_ratio(struct bdi_writeback *wb, + unsigned long *minp, unsigned long *maxp) +{ + unsigned long this_bw = wb->avg_write_bandwidth; + unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth); + unsigned long long min = wb->bdi->min_ratio; + unsigned long long max = wb->bdi->max_ratio; + + /* + * @wb may already be clean by the time control reaches here and + * the total may not include its bw. + */ + if (this_bw < tot_bw) { + if (min) { + min *= this_bw; + min = div64_ul(min, tot_bw); + } + if (max < 100) { + max *= this_bw; + max = div64_ul(max, tot_bw); + } + } + + *minp = min; + *maxp = max; +} + +#else /* CONFIG_CGROUP_WRITEBACK */ + +#define GDTC_INIT(__wb) .wb = (__wb), \ + .wb_completions = &(__wb)->completions +#define GDTC_INIT_NO_WB +#define MDTC_INIT(__wb, __gdtc) + +static bool mdtc_valid(struct dirty_throttle_control *dtc) +{ + return false; +} + +static struct wb_domain *dtc_dom(struct dirty_throttle_control *dtc) +{ + return &global_wb_domain; +} + +static struct dirty_throttle_control *mdtc_gdtc(struct dirty_throttle_control *mdtc) +{ + return NULL; +} + +static struct fprop_local_percpu *wb_memcg_completions(struct bdi_writeback *wb) +{ + return NULL; +} + +static void wb_min_max_ratio(struct bdi_writeback *wb, + unsigned long *minp, unsigned long *maxp) +{ + *minp = wb->bdi->min_ratio; + *maxp = wb->bdi->max_ratio; +} + +#endif /* CONFIG_CGROUP_WRITEBACK */ + +/* + * In a memory zone, there is a certain amount of pages we consider + * available for the page cache, which is essentially the number of + * free and reclaimable pages, minus some zone reserves to protect + * lowmem and the ability to uphold the zone's watermarks without + * requiring writeback. + * + * This number of dirtyable pages is the base value of which the + * user-configurable dirty ratio is the effective number of pages that + * are allowed to be actually dirtied. Per individual zone, or + * globally by using the sum of dirtyable pages over all zones. + * + * Because the user is allowed to specify the dirty limit globally as + * absolute number of bytes, calculating the per-zone dirty limit can + * require translating the configured limit into a percentage of + * global dirtyable memory first. + */ + +/** + * node_dirtyable_memory - number of dirtyable pages in a node + * @pgdat: the node + * + * Return: the node's number of pages potentially available for dirty + * page cache. This is the base value for the per-node dirty limits. + */ +static unsigned long node_dirtyable_memory(struct pglist_data *pgdat) +{ + unsigned long nr_pages = 0; + int z; + + for (z = 0; z < MAX_NR_ZONES; z++) { + struct zone *zone = pgdat->node_zones + z; + + if (!populated_zone(zone)) + continue; + + nr_pages += zone_page_state(zone, NR_FREE_PAGES); + } + + /* + * Pages reserved for the kernel should not be considered + * dirtyable, to prevent a situation where reclaim has to + * clean pages in order to balance the zones. + */ + nr_pages -= min(nr_pages, pgdat->totalreserve_pages); + + nr_pages += node_page_state(pgdat, NR_INACTIVE_FILE); + nr_pages += node_page_state(pgdat, NR_ACTIVE_FILE); + + return nr_pages; +} + +static unsigned long highmem_dirtyable_memory(unsigned long total) +{ +#ifdef CONFIG_HIGHMEM + int node; + unsigned long x = 0; + int i; + + for_each_node_state(node, N_HIGH_MEMORY) { + for (i = ZONE_NORMAL + 1; i < MAX_NR_ZONES; i++) { + struct zone *z; + unsigned long nr_pages; + + if (!is_highmem_idx(i)) + continue; + + z = &NODE_DATA(node)->node_zones[i]; + if (!populated_zone(z)) + continue; + + nr_pages = zone_page_state(z, NR_FREE_PAGES); + /* watch for underflows */ + nr_pages -= min(nr_pages, high_wmark_pages(z)); + nr_pages += zone_page_state(z, NR_ZONE_INACTIVE_FILE); + nr_pages += zone_page_state(z, NR_ZONE_ACTIVE_FILE); + x += nr_pages; + } + } + + /* + * Unreclaimable memory (kernel memory or anonymous memory + * without swap) can bring down the dirtyable pages below + * the zone's dirty balance reserve and the above calculation + * will underflow. However we still want to add in nodes + * which are below threshold (negative values) to get a more + * accurate calculation but make sure that the total never + * underflows. + */ + if ((long)x < 0) + x = 0; + + /* + * Make sure that the number of highmem pages is never larger + * than the number of the total dirtyable memory. This can only + * occur in very strange VM situations but we want to make sure + * that this does not occur. + */ + return min(x, total); +#else + return 0; +#endif +} + +/** + * global_dirtyable_memory - number of globally dirtyable pages + * + * Return: the global number of pages potentially available for dirty + * page cache. This is the base value for the global dirty limits. + */ +static unsigned long global_dirtyable_memory(void) +{ + unsigned long x; + + x = global_zone_page_state(NR_FREE_PAGES); + /* + * Pages reserved for the kernel should not be considered + * dirtyable, to prevent a situation where reclaim has to + * clean pages in order to balance the zones. + */ + x -= min(x, totalreserve_pages); + + x += global_node_page_state(NR_INACTIVE_FILE); + x += global_node_page_state(NR_ACTIVE_FILE); + + if (!vm_highmem_is_dirtyable) + x -= highmem_dirtyable_memory(x); + + return x + 1; /* Ensure that we never return 0 */ +} + +/** + * domain_dirty_limits - calculate thresh and bg_thresh for a wb_domain + * @dtc: dirty_throttle_control of interest + * + * Calculate @dtc->thresh and ->bg_thresh considering + * vm_dirty_{bytes|ratio} and dirty_background_{bytes|ratio}. The caller + * must ensure that @dtc->avail is set before calling this function. The + * dirty limits will be lifted by 1/4 for real-time tasks. + */ +static void domain_dirty_limits(struct dirty_throttle_control *dtc) +{ + const unsigned long available_memory = dtc->avail; + struct dirty_throttle_control *gdtc = mdtc_gdtc(dtc); + unsigned long bytes = vm_dirty_bytes; + unsigned long bg_bytes = dirty_background_bytes; + /* convert ratios to per-PAGE_SIZE for higher precision */ + unsigned long ratio = (vm_dirty_ratio * PAGE_SIZE) / 100; + unsigned long bg_ratio = (dirty_background_ratio * PAGE_SIZE) / 100; + unsigned long thresh; + unsigned long bg_thresh; + struct task_struct *tsk; + + /* gdtc is !NULL iff @dtc is for memcg domain */ + if (gdtc) { + unsigned long global_avail = gdtc->avail; + + /* + * The byte settings can't be applied directly to memcg + * domains. Convert them to ratios by scaling against + * globally available memory. As the ratios are in + * per-PAGE_SIZE, they can be obtained by dividing bytes by + * number of pages. + */ + if (bytes) + ratio = min(DIV_ROUND_UP(bytes, global_avail), + PAGE_SIZE); + if (bg_bytes) + bg_ratio = min(DIV_ROUND_UP(bg_bytes, global_avail), + PAGE_SIZE); + bytes = bg_bytes = 0; + } + + if (bytes) + thresh = DIV_ROUND_UP(bytes, PAGE_SIZE); + else + thresh = (ratio * available_memory) / PAGE_SIZE; + + if (bg_bytes) + bg_thresh = DIV_ROUND_UP(bg_bytes, PAGE_SIZE); + else + bg_thresh = (bg_ratio * available_memory) / PAGE_SIZE; + + if (bg_thresh >= thresh) + bg_thresh = thresh / 2; + tsk = current; + if (rt_task(tsk)) { + bg_thresh += bg_thresh / 4 + global_wb_domain.dirty_limit / 32; + thresh += thresh / 4 + global_wb_domain.dirty_limit / 32; + } + dtc->thresh = thresh; + dtc->bg_thresh = bg_thresh; + + /* we should eventually report the domain in the TP */ + if (!gdtc) + trace_global_dirty_state(bg_thresh, thresh); +} + +/** + * global_dirty_limits - background-writeback and dirty-throttling thresholds + * @pbackground: out parameter for bg_thresh + * @pdirty: out parameter for thresh + * + * Calculate bg_thresh and thresh for global_wb_domain. See + * domain_dirty_limits() for details. + */ +void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty) +{ + struct dirty_throttle_control gdtc = { GDTC_INIT_NO_WB }; + + gdtc.avail = global_dirtyable_memory(); + domain_dirty_limits(&gdtc); + + *pbackground = gdtc.bg_thresh; + *pdirty = gdtc.thresh; +} + +/** + * node_dirty_limit - maximum number of dirty pages allowed in a node + * @pgdat: the node + * + * Return: the maximum number of dirty pages allowed in a node, based + * on the node's dirtyable memory. + */ +static unsigned long node_dirty_limit(struct pglist_data *pgdat) +{ + unsigned long node_memory = node_dirtyable_memory(pgdat); + struct task_struct *tsk = current; + unsigned long dirty; + + if (vm_dirty_bytes) + dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) * + node_memory / global_dirtyable_memory(); + else + dirty = vm_dirty_ratio * node_memory / 100; + + if (rt_task(tsk)) + dirty += dirty / 4; + + return dirty; +} + +/** + * node_dirty_ok - tells whether a node is within its dirty limits + * @pgdat: the node to check + * + * Return: %true when the dirty pages in @pgdat are within the node's + * dirty limit, %false if the limit is exceeded. + */ +bool node_dirty_ok(struct pglist_data *pgdat) +{ + unsigned long limit = node_dirty_limit(pgdat); + unsigned long nr_pages = 0; + + nr_pages += node_page_state(pgdat, NR_FILE_DIRTY); + nr_pages += node_page_state(pgdat, NR_WRITEBACK); + + return nr_pages <= limit; +} + +int dirty_background_ratio_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + int ret; + + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (ret == 0 && write) + dirty_background_bytes = 0; + return ret; +} + +int dirty_background_bytes_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + int ret; + + ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); + if (ret == 0 && write) + dirty_background_ratio = 0; + return ret; +} + +int dirty_ratio_handler(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos) +{ + int old_ratio = vm_dirty_ratio; + int ret; + + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (ret == 0 && write && vm_dirty_ratio != old_ratio) { + writeback_set_ratelimit(); + vm_dirty_bytes = 0; + } + return ret; +} + +int dirty_bytes_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + unsigned long old_bytes = vm_dirty_bytes; + int ret; + + ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); + if (ret == 0 && write && vm_dirty_bytes != old_bytes) { + writeback_set_ratelimit(); + vm_dirty_ratio = 0; + } + return ret; +} + +static unsigned long wp_next_time(unsigned long cur_time) +{ + cur_time += VM_COMPLETIONS_PERIOD_LEN; + /* 0 has a special meaning... */ + if (!cur_time) + return 1; + return cur_time; +} + +static void wb_domain_writeout_inc(struct wb_domain *dom, + struct fprop_local_percpu *completions, + unsigned int max_prop_frac) +{ + __fprop_inc_percpu_max(&dom->completions, completions, + max_prop_frac); + /* First event after period switching was turned off? */ + if (unlikely(!dom->period_time)) { + /* + * We can race with other __bdi_writeout_inc calls here but + * it does not cause any harm since the resulting time when + * timer will fire and what is in writeout_period_time will be + * roughly the same. + */ + dom->period_time = wp_next_time(jiffies); + mod_timer(&dom->period_timer, dom->period_time); + } +} + +/* + * Increment @wb's writeout completion count and the global writeout + * completion count. Called from test_clear_page_writeback(). + */ +static inline void __wb_writeout_inc(struct bdi_writeback *wb) +{ + struct wb_domain *cgdom; + + inc_wb_stat(wb, WB_WRITTEN); + wb_domain_writeout_inc(&global_wb_domain, &wb->completions, + wb->bdi->max_prop_frac); + + cgdom = mem_cgroup_wb_domain(wb); + if (cgdom) + wb_domain_writeout_inc(cgdom, wb_memcg_completions(wb), + wb->bdi->max_prop_frac); +} + +void wb_writeout_inc(struct bdi_writeback *wb) +{ + unsigned long flags; + + local_irq_save(flags); + __wb_writeout_inc(wb); + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(wb_writeout_inc); + +/* + * On idle system, we can be called long after we scheduled because we use + * deferred timers so count with missed periods. + */ +static void writeout_period(struct timer_list *t) +{ + struct wb_domain *dom = from_timer(dom, t, period_timer); + int miss_periods = (jiffies - dom->period_time) / + VM_COMPLETIONS_PERIOD_LEN; + + if (fprop_new_period(&dom->completions, miss_periods + 1)) { + dom->period_time = wp_next_time(dom->period_time + + miss_periods * VM_COMPLETIONS_PERIOD_LEN); + mod_timer(&dom->period_timer, dom->period_time); + } else { + /* + * Aging has zeroed all fractions. Stop wasting CPU on period + * updates. + */ + dom->period_time = 0; + } +} + +int wb_domain_init(struct wb_domain *dom, gfp_t gfp) +{ + memset(dom, 0, sizeof(*dom)); + + spin_lock_init(&dom->lock); + + timer_setup(&dom->period_timer, writeout_period, TIMER_DEFERRABLE); + + dom->dirty_limit_tstamp = jiffies; + + return fprop_global_init(&dom->completions, gfp); +} + +#ifdef CONFIG_CGROUP_WRITEBACK +void wb_domain_exit(struct wb_domain *dom) +{ + del_timer_sync(&dom->period_timer); + fprop_global_destroy(&dom->completions); +} +#endif + +/* + * bdi_min_ratio keeps the sum of the minimum dirty shares of all + * registered backing devices, which, for obvious reasons, can not + * exceed 100%. + */ +static unsigned int bdi_min_ratio; + +int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) +{ + int ret = 0; + + spin_lock_bh(&bdi_lock); + if (min_ratio > bdi->max_ratio) { + ret = -EINVAL; + } else { + min_ratio -= bdi->min_ratio; + if (bdi_min_ratio + min_ratio < 100) { + bdi_min_ratio += min_ratio; + bdi->min_ratio += min_ratio; + } else { + ret = -EINVAL; + } + } + spin_unlock_bh(&bdi_lock); + + return ret; +} + +int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio) +{ + int ret = 0; + + if (max_ratio > 100) + return -EINVAL; + + spin_lock_bh(&bdi_lock); + if (bdi->min_ratio > max_ratio) { + ret = -EINVAL; + } else { + bdi->max_ratio = max_ratio; + bdi->max_prop_frac = (FPROP_FRAC_BASE * max_ratio) / 100; + } + spin_unlock_bh(&bdi_lock); + + return ret; +} +EXPORT_SYMBOL(bdi_set_max_ratio); + +static unsigned long dirty_freerun_ceiling(unsigned long thresh, + unsigned long bg_thresh) +{ + return (thresh + bg_thresh) / 2; +} + +static unsigned long hard_dirty_limit(struct wb_domain *dom, + unsigned long thresh) +{ + return max(thresh, dom->dirty_limit); +} + +/* + * Memory which can be further allocated to a memcg domain is capped by + * system-wide clean memory excluding the amount being used in the domain. + */ +static void mdtc_calc_avail(struct dirty_throttle_control *mdtc, + unsigned long filepages, unsigned long headroom) +{ + struct dirty_throttle_control *gdtc = mdtc_gdtc(mdtc); + unsigned long clean = filepages - min(filepages, mdtc->dirty); + unsigned long global_clean = gdtc->avail - min(gdtc->avail, gdtc->dirty); + unsigned long other_clean = global_clean - min(global_clean, clean); + + mdtc->avail = filepages + min(headroom, other_clean); +} + +/** + * __wb_calc_thresh - @wb's share of dirty throttling threshold + * @dtc: dirty_throttle_context of interest + * + * Note that balance_dirty_pages() will only seriously take it as a hard limit + * when sleeping max_pause per page is not enough to keep the dirty pages under + * control. For example, when the device is completely stalled due to some error + * conditions, or when there are 1000 dd tasks writing to a slow 10MB/s USB key. + * In the other normal situations, it acts more gently by throttling the tasks + * more (rather than completely block them) when the wb dirty pages go high. + * + * It allocates high/low dirty limits to fast/slow devices, in order to prevent + * - starving fast devices + * - piling up dirty pages (that will take long time to sync) on slow devices + * + * The wb's share of dirty limit will be adapting to its throughput and + * bounded by the bdi->min_ratio and/or bdi->max_ratio parameters, if set. + * + * Return: @wb's dirty limit in pages. The term "dirty" in the context of + * dirty balancing includes all PG_dirty and PG_writeback pages. + */ +static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc) +{ + struct wb_domain *dom = dtc_dom(dtc); + unsigned long thresh = dtc->thresh; + u64 wb_thresh; + unsigned long numerator, denominator; + unsigned long wb_min_ratio, wb_max_ratio; + + /* + * Calculate this BDI's share of the thresh ratio. + */ + fprop_fraction_percpu(&dom->completions, dtc->wb_completions, + &numerator, &denominator); + + wb_thresh = (thresh * (100 - bdi_min_ratio)) / 100; + wb_thresh *= numerator; + wb_thresh = div64_ul(wb_thresh, denominator); + + wb_min_max_ratio(dtc->wb, &wb_min_ratio, &wb_max_ratio); + + wb_thresh += (thresh * wb_min_ratio) / 100; + if (wb_thresh > (thresh * wb_max_ratio) / 100) + wb_thresh = thresh * wb_max_ratio / 100; + + return wb_thresh; +} + +unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh) +{ + struct dirty_throttle_control gdtc = { GDTC_INIT(wb), + .thresh = thresh }; + return __wb_calc_thresh(&gdtc); +} + +/* + * setpoint - dirty 3 + * f(dirty) := 1.0 + (----------------) + * limit - setpoint + * + * it's a 3rd order polynomial that subjects to + * + * (1) f(freerun) = 2.0 => rampup dirty_ratelimit reasonably fast + * (2) f(setpoint) = 1.0 => the balance point + * (3) f(limit) = 0 => the hard limit + * (4) df/dx <= 0 => negative feedback control + * (5) the closer to setpoint, the smaller |df/dx| (and the reverse) + * => fast response on large errors; small oscillation near setpoint + */ +static long long pos_ratio_polynom(unsigned long setpoint, + unsigned long dirty, + unsigned long limit) +{ + long long pos_ratio; + long x; + + x = div64_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT, + (limit - setpoint) | 1); + pos_ratio = x; + pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; + pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; + pos_ratio += 1 << RATELIMIT_CALC_SHIFT; + + return clamp(pos_ratio, 0LL, 2LL << RATELIMIT_CALC_SHIFT); +} + +/* + * Dirty position control. + * + * (o) global/bdi setpoints + * + * We want the dirty pages be balanced around the global/wb setpoints. + * When the number of dirty pages is higher/lower than the setpoint, the + * dirty position control ratio (and hence task dirty ratelimit) will be + * decreased/increased to bring the dirty pages back to the setpoint. + * + * pos_ratio = 1 << RATELIMIT_CALC_SHIFT + * + * if (dirty < setpoint) scale up pos_ratio + * if (dirty > setpoint) scale down pos_ratio + * + * if (wb_dirty < wb_setpoint) scale up pos_ratio + * if (wb_dirty > wb_setpoint) scale down pos_ratio + * + * task_ratelimit = dirty_ratelimit * pos_ratio >> RATELIMIT_CALC_SHIFT + * + * (o) global control line + * + * ^ pos_ratio + * | + * | |<===== global dirty control scope ======>| + * 2.0 .............* + * | .* + * | . * + * | . * + * | . * + * | . * + * | . * + * 1.0 ................................* + * | . . * + * | . . * + * | . . * + * | . . * + * | . . * + * 0 +------------.------------------.----------------------*-------------> + * freerun^ setpoint^ limit^ dirty pages + * + * (o) wb control line + * + * ^ pos_ratio + * | + * | * + * | * + * | * + * | * + * | * |<=========== span ============>| + * 1.0 .......................* + * | . * + * | . * + * | . * + * | . * + * | . * + * | . * + * | . * + * | . * + * | . * + * | . * + * | . * + * 1/4 ...............................................* * * * * * * * * * * * + * | . . + * | . . + * | . . + * 0 +----------------------.-------------------------------.-------------> + * wb_setpoint^ x_intercept^ + * + * The wb control line won't drop below pos_ratio=1/4, so that wb_dirty can + * be smoothly throttled down to normal if it starts high in situations like + * - start writing to a slow SD card and a fast disk at the same time. The SD + * card's wb_dirty may rush to many times higher than wb_setpoint. + * - the wb dirty thresh drops quickly due to change of JBOD workload + */ +static void wb_position_ratio(struct dirty_throttle_control *dtc) +{ + struct bdi_writeback *wb = dtc->wb; + unsigned long write_bw = wb->avg_write_bandwidth; + unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh); + unsigned long limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh); + unsigned long wb_thresh = dtc->wb_thresh; + unsigned long x_intercept; + unsigned long setpoint; /* dirty pages' target balance point */ + unsigned long wb_setpoint; + unsigned long span; + long long pos_ratio; /* for scaling up/down the rate limit */ + long x; + + dtc->pos_ratio = 0; + + if (unlikely(dtc->dirty >= limit)) + return; + + /* + * global setpoint + * + * See comment for pos_ratio_polynom(). + */ + setpoint = (freerun + limit) / 2; + pos_ratio = pos_ratio_polynom(setpoint, dtc->dirty, limit); + + /* + * The strictlimit feature is a tool preventing mistrusted filesystems + * from growing a large number of dirty pages before throttling. For + * such filesystems balance_dirty_pages always checks wb counters + * against wb limits. Even if global "nr_dirty" is under "freerun". + * This is especially important for fuse which sets bdi->max_ratio to + * 1% by default. Without strictlimit feature, fuse writeback may + * consume arbitrary amount of RAM because it is accounted in + * NR_WRITEBACK_TEMP which is not involved in calculating "nr_dirty". + * + * Here, in wb_position_ratio(), we calculate pos_ratio based on + * two values: wb_dirty and wb_thresh. Let's consider an example: + * total amount of RAM is 16GB, bdi->max_ratio is equal to 1%, global + * limits are set by default to 10% and 20% (background and throttle). + * Then wb_thresh is 1% of 20% of 16GB. This amounts to ~8K pages. + * wb_calc_thresh(wb, bg_thresh) is about ~4K pages. wb_setpoint is + * about ~6K pages (as the average of background and throttle wb + * limits). The 3rd order polynomial will provide positive feedback if + * wb_dirty is under wb_setpoint and vice versa. + * + * Note, that we cannot use global counters in these calculations + * because we want to throttle process writing to a strictlimit wb + * much earlier than global "freerun" is reached (~23MB vs. ~2.3GB + * in the example above). + */ + if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) { + long long wb_pos_ratio; + + if (dtc->wb_dirty < 8) { + dtc->pos_ratio = min_t(long long, pos_ratio * 2, + 2 << RATELIMIT_CALC_SHIFT); + return; + } + + if (dtc->wb_dirty >= wb_thresh) + return; + + wb_setpoint = dirty_freerun_ceiling(wb_thresh, + dtc->wb_bg_thresh); + + if (wb_setpoint == 0 || wb_setpoint == wb_thresh) + return; + + wb_pos_ratio = pos_ratio_polynom(wb_setpoint, dtc->wb_dirty, + wb_thresh); + + /* + * Typically, for strictlimit case, wb_setpoint << setpoint + * and pos_ratio >> wb_pos_ratio. In the other words global + * state ("dirty") is not limiting factor and we have to + * make decision based on wb counters. But there is an + * important case when global pos_ratio should get precedence: + * global limits are exceeded (e.g. due to activities on other + * wb's) while given strictlimit wb is below limit. + * + * "pos_ratio * wb_pos_ratio" would work for the case above, + * but it would look too non-natural for the case of all + * activity in the system coming from a single strictlimit wb + * with bdi->max_ratio == 100%. + * + * Note that min() below somewhat changes the dynamics of the + * control system. Normally, pos_ratio value can be well over 3 + * (when globally we are at freerun and wb is well below wb + * setpoint). Now the maximum pos_ratio in the same situation + * is 2. We might want to tweak this if we observe the control + * system is too slow to adapt. + */ + dtc->pos_ratio = min(pos_ratio, wb_pos_ratio); + return; + } + + /* + * We have computed basic pos_ratio above based on global situation. If + * the wb is over/under its share of dirty pages, we want to scale + * pos_ratio further down/up. That is done by the following mechanism. + */ + + /* + * wb setpoint + * + * f(wb_dirty) := 1.0 + k * (wb_dirty - wb_setpoint) + * + * x_intercept - wb_dirty + * := -------------------------- + * x_intercept - wb_setpoint + * + * The main wb control line is a linear function that subjects to + * + * (1) f(wb_setpoint) = 1.0 + * (2) k = - 1 / (8 * write_bw) (in single wb case) + * or equally: x_intercept = wb_setpoint + 8 * write_bw + * + * For single wb case, the dirty pages are observed to fluctuate + * regularly within range + * [wb_setpoint - write_bw/2, wb_setpoint + write_bw/2] + * for various filesystems, where (2) can yield in a reasonable 12.5% + * fluctuation range for pos_ratio. + * + * For JBOD case, wb_thresh (not wb_dirty!) could fluctuate up to its + * own size, so move the slope over accordingly and choose a slope that + * yields 100% pos_ratio fluctuation on suddenly doubled wb_thresh. + */ + if (unlikely(wb_thresh > dtc->thresh)) + wb_thresh = dtc->thresh; + /* + * It's very possible that wb_thresh is close to 0 not because the + * device is slow, but that it has remained inactive for long time. + * Honour such devices a reasonable good (hopefully IO efficient) + * threshold, so that the occasional writes won't be blocked and active + * writes can rampup the threshold quickly. + */ + wb_thresh = max(wb_thresh, (limit - dtc->dirty) / 8); + /* + * scale global setpoint to wb's: + * wb_setpoint = setpoint * wb_thresh / thresh + */ + x = div_u64((u64)wb_thresh << 16, dtc->thresh | 1); + wb_setpoint = setpoint * (u64)x >> 16; + /* + * Use span=(8*write_bw) in single wb case as indicated by + * (thresh - wb_thresh ~= 0) and transit to wb_thresh in JBOD case. + * + * wb_thresh thresh - wb_thresh + * span = --------- * (8 * write_bw) + ------------------ * wb_thresh + * thresh thresh + */ + span = (dtc->thresh - wb_thresh + 8 * write_bw) * (u64)x >> 16; + x_intercept = wb_setpoint + span; + + if (dtc->wb_dirty < x_intercept - span / 4) { + pos_ratio = div64_u64(pos_ratio * (x_intercept - dtc->wb_dirty), + (x_intercept - wb_setpoint) | 1); + } else + pos_ratio /= 4; + + /* + * wb reserve area, safeguard against dirty pool underrun and disk idle + * It may push the desired control point of global dirty pages higher + * than setpoint. + */ + x_intercept = wb_thresh / 2; + if (dtc->wb_dirty < x_intercept) { + if (dtc->wb_dirty > x_intercept / 8) + pos_ratio = div_u64(pos_ratio * x_intercept, + dtc->wb_dirty); + else + pos_ratio *= 8; + } + + dtc->pos_ratio = pos_ratio; +} + +static void wb_update_write_bandwidth(struct bdi_writeback *wb, + unsigned long elapsed, + unsigned long written) +{ + const unsigned long period = roundup_pow_of_two(3 * HZ); + unsigned long avg = wb->avg_write_bandwidth; + unsigned long old = wb->write_bandwidth; + u64 bw; + + /* + * bw = written * HZ / elapsed + * + * bw * elapsed + write_bandwidth * (period - elapsed) + * write_bandwidth = --------------------------------------------------- + * period + * + * @written may have decreased due to account_page_redirty(). + * Avoid underflowing @bw calculation. + */ + bw = written - min(written, wb->written_stamp); + bw *= HZ; + if (unlikely(elapsed > period)) { + bw = div64_ul(bw, elapsed); + avg = bw; + goto out; + } + bw += (u64)wb->write_bandwidth * (period - elapsed); + bw >>= ilog2(period); + + /* + * one more level of smoothing, for filtering out sudden spikes + */ + if (avg > old && old >= (unsigned long)bw) + avg -= (avg - old) >> 3; + + if (avg < old && old <= (unsigned long)bw) + avg += (old - avg) >> 3; + +out: + /* keep avg > 0 to guarantee that tot > 0 if there are dirty wbs */ + avg = max(avg, 1LU); + if (wb_has_dirty_io(wb)) { + long delta = avg - wb->avg_write_bandwidth; + WARN_ON_ONCE(atomic_long_add_return(delta, + &wb->bdi->tot_write_bandwidth) <= 0); + } + wb->write_bandwidth = bw; + wb->avg_write_bandwidth = avg; +} + +static void update_dirty_limit(struct dirty_throttle_control *dtc) +{ + struct wb_domain *dom = dtc_dom(dtc); + unsigned long thresh = dtc->thresh; + unsigned long limit = dom->dirty_limit; + + /* + * Follow up in one step. + */ + if (limit < thresh) { + limit = thresh; + goto update; + } + + /* + * Follow down slowly. Use the higher one as the target, because thresh + * may drop below dirty. This is exactly the reason to introduce + * dom->dirty_limit which is guaranteed to lie above the dirty pages. + */ + thresh = max(thresh, dtc->dirty); + if (limit > thresh) { + limit -= (limit - thresh) >> 5; + goto update; + } + return; +update: + dom->dirty_limit = limit; +} + +static void domain_update_bandwidth(struct dirty_throttle_control *dtc, + unsigned long now) +{ + struct wb_domain *dom = dtc_dom(dtc); + + /* + * check locklessly first to optimize away locking for the most time + */ + if (time_before(now, dom->dirty_limit_tstamp + BANDWIDTH_INTERVAL)) + return; + + spin_lock(&dom->lock); + if (time_after_eq(now, dom->dirty_limit_tstamp + BANDWIDTH_INTERVAL)) { + update_dirty_limit(dtc); + dom->dirty_limit_tstamp = now; + } + spin_unlock(&dom->lock); +} + +/* + * Maintain wb->dirty_ratelimit, the base dirty throttle rate. + * + * Normal wb tasks will be curbed at or below it in long term. + * Obviously it should be around (write_bw / N) when there are N dd tasks. + */ +static void wb_update_dirty_ratelimit(struct dirty_throttle_control *dtc, + unsigned long dirtied, + unsigned long elapsed) +{ + struct bdi_writeback *wb = dtc->wb; + unsigned long dirty = dtc->dirty; + unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh); + unsigned long limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh); + unsigned long setpoint = (freerun + limit) / 2; + unsigned long write_bw = wb->avg_write_bandwidth; + unsigned long dirty_ratelimit = wb->dirty_ratelimit; + unsigned long dirty_rate; + unsigned long task_ratelimit; + unsigned long balanced_dirty_ratelimit; + unsigned long step; + unsigned long x; + unsigned long shift; + + /* + * The dirty rate will match the writeout rate in long term, except + * when dirty pages are truncated by userspace or re-dirtied by FS. + */ + dirty_rate = (dirtied - wb->dirtied_stamp) * HZ / elapsed; + + /* + * task_ratelimit reflects each dd's dirty rate for the past 200ms. + */ + task_ratelimit = (u64)dirty_ratelimit * + dtc->pos_ratio >> RATELIMIT_CALC_SHIFT; + task_ratelimit++; /* it helps rampup dirty_ratelimit from tiny values */ + + /* + * A linear estimation of the "balanced" throttle rate. The theory is, + * if there are N dd tasks, each throttled at task_ratelimit, the wb's + * dirty_rate will be measured to be (N * task_ratelimit). So the below + * formula will yield the balanced rate limit (write_bw / N). + * + * Note that the expanded form is not a pure rate feedback: + * rate_(i+1) = rate_(i) * (write_bw / dirty_rate) (1) + * but also takes pos_ratio into account: + * rate_(i+1) = rate_(i) * (write_bw / dirty_rate) * pos_ratio (2) + * + * (1) is not realistic because pos_ratio also takes part in balancing + * the dirty rate. Consider the state + * pos_ratio = 0.5 (3) + * rate = 2 * (write_bw / N) (4) + * If (1) is used, it will stuck in that state! Because each dd will + * be throttled at + * task_ratelimit = pos_ratio * rate = (write_bw / N) (5) + * yielding + * dirty_rate = N * task_ratelimit = write_bw (6) + * put (6) into (1) we get + * rate_(i+1) = rate_(i) (7) + * + * So we end up using (2) to always keep + * rate_(i+1) ~= (write_bw / N) (8) + * regardless of the value of pos_ratio. As long as (8) is satisfied, + * pos_ratio is able to drive itself to 1.0, which is not only where + * the dirty count meet the setpoint, but also where the slope of + * pos_ratio is most flat and hence task_ratelimit is least fluctuated. + */ + balanced_dirty_ratelimit = div_u64((u64)task_ratelimit * write_bw, + dirty_rate | 1); + /* + * balanced_dirty_ratelimit ~= (write_bw / N) <= write_bw + */ + if (unlikely(balanced_dirty_ratelimit > write_bw)) + balanced_dirty_ratelimit = write_bw; + + /* + * We could safely do this and return immediately: + * + * wb->dirty_ratelimit = balanced_dirty_ratelimit; + * + * However to get a more stable dirty_ratelimit, the below elaborated + * code makes use of task_ratelimit to filter out singular points and + * limit the step size. + * + * The below code essentially only uses the relative value of + * + * task_ratelimit - dirty_ratelimit + * = (pos_ratio - 1) * dirty_ratelimit + * + * which reflects the direction and size of dirty position error. + */ + + /* + * dirty_ratelimit will follow balanced_dirty_ratelimit iff + * task_ratelimit is on the same side of dirty_ratelimit, too. + * For example, when + * - dirty_ratelimit > balanced_dirty_ratelimit + * - dirty_ratelimit > task_ratelimit (dirty pages are above setpoint) + * lowering dirty_ratelimit will help meet both the position and rate + * control targets. Otherwise, don't update dirty_ratelimit if it will + * only help meet the rate target. After all, what the users ultimately + * feel and care are stable dirty rate and small position error. + * + * |task_ratelimit - dirty_ratelimit| is used to limit the step size + * and filter out the singular points of balanced_dirty_ratelimit. Which + * keeps jumping around randomly and can even leap far away at times + * due to the small 200ms estimation period of dirty_rate (we want to + * keep that period small to reduce time lags). + */ + step = 0; + + /* + * For strictlimit case, calculations above were based on wb counters + * and limits (starting from pos_ratio = wb_position_ratio() and up to + * balanced_dirty_ratelimit = task_ratelimit * write_bw / dirty_rate). + * Hence, to calculate "step" properly, we have to use wb_dirty as + * "dirty" and wb_setpoint as "setpoint". + * + * We rampup dirty_ratelimit forcibly if wb_dirty is low because + * it's possible that wb_thresh is close to zero due to inactivity + * of backing device. + */ + if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) { + dirty = dtc->wb_dirty; + if (dtc->wb_dirty < 8) + setpoint = dtc->wb_dirty + 1; + else + setpoint = (dtc->wb_thresh + dtc->wb_bg_thresh) / 2; + } + + if (dirty < setpoint) { + x = min3(wb->balanced_dirty_ratelimit, + balanced_dirty_ratelimit, task_ratelimit); + if (dirty_ratelimit < x) + step = x - dirty_ratelimit; + } else { + x = max3(wb->balanced_dirty_ratelimit, + balanced_dirty_ratelimit, task_ratelimit); + if (dirty_ratelimit > x) + step = dirty_ratelimit - x; + } + + /* + * Don't pursue 100% rate matching. It's impossible since the balanced + * rate itself is constantly fluctuating. So decrease the track speed + * when it gets close to the target. Helps eliminate pointless tremors. + */ + shift = dirty_ratelimit / (2 * step + 1); + if (shift < BITS_PER_LONG) + step = DIV_ROUND_UP(step >> shift, 8); + else + step = 0; + + if (dirty_ratelimit < balanced_dirty_ratelimit) + dirty_ratelimit += step; + else + dirty_ratelimit -= step; + + wb->dirty_ratelimit = max(dirty_ratelimit, 1UL); + wb->balanced_dirty_ratelimit = balanced_dirty_ratelimit; + + trace_bdi_dirty_ratelimit(wb, dirty_rate, task_ratelimit); +} + +static void __wb_update_bandwidth(struct dirty_throttle_control *gdtc, + struct dirty_throttle_control *mdtc, + unsigned long start_time, + bool update_ratelimit) +{ + struct bdi_writeback *wb = gdtc->wb; + unsigned long now = jiffies; + unsigned long elapsed = now - wb->bw_time_stamp; + unsigned long dirtied; + unsigned long written; + + lockdep_assert_held(&wb->list_lock); + + /* + * rate-limit, only update once every 200ms. + */ + if (elapsed < BANDWIDTH_INTERVAL) + return; + + dirtied = percpu_counter_read(&wb->stat[WB_DIRTIED]); + written = percpu_counter_read(&wb->stat[WB_WRITTEN]); + + /* + * Skip quiet periods when disk bandwidth is under-utilized. + * (at least 1s idle time between two flusher runs) + */ + if (elapsed > HZ && time_before(wb->bw_time_stamp, start_time)) + goto snapshot; + + if (update_ratelimit) { + domain_update_bandwidth(gdtc, now); + wb_update_dirty_ratelimit(gdtc, dirtied, elapsed); + + /* + * @mdtc is always NULL if !CGROUP_WRITEBACK but the + * compiler has no way to figure that out. Help it. + */ + if (IS_ENABLED(CONFIG_CGROUP_WRITEBACK) && mdtc) { + domain_update_bandwidth(mdtc, now); + wb_update_dirty_ratelimit(mdtc, dirtied, elapsed); + } + } + wb_update_write_bandwidth(wb, elapsed, written); + +snapshot: + wb->dirtied_stamp = dirtied; + wb->written_stamp = written; + wb->bw_time_stamp = now; +} + +void wb_update_bandwidth(struct bdi_writeback *wb, unsigned long start_time) +{ + struct dirty_throttle_control gdtc = { GDTC_INIT(wb) }; + + __wb_update_bandwidth(&gdtc, NULL, start_time, false); +} + +/* + * After a task dirtied this many pages, balance_dirty_pages_ratelimited() + * will look to see if it needs to start dirty throttling. + * + * If dirty_poll_interval is too low, big NUMA machines will call the expensive + * global_zone_page_state() too often. So scale it near-sqrt to the safety margin + * (the number of pages we may dirty without exceeding the dirty limits). + */ +static unsigned long dirty_poll_interval(unsigned long dirty, + unsigned long thresh) +{ + if (thresh > dirty) + return 1UL << (ilog2(thresh - dirty) >> 1); + + return 1; +} + +static unsigned long wb_max_pause(struct bdi_writeback *wb, + unsigned long wb_dirty) +{ + unsigned long bw = wb->avg_write_bandwidth; + unsigned long t; + + /* + * Limit pause time for small memory systems. If sleeping for too long + * time, a small pool of dirty/writeback pages may go empty and disk go + * idle. + * + * 8 serves as the safety ratio. + */ + t = wb_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8)); + t++; + + return min_t(unsigned long, t, MAX_PAUSE); +} + +static long wb_min_pause(struct bdi_writeback *wb, + long max_pause, + unsigned long task_ratelimit, + unsigned long dirty_ratelimit, + int *nr_dirtied_pause) +{ + long hi = ilog2(wb->avg_write_bandwidth); + long lo = ilog2(wb->dirty_ratelimit); + long t; /* target pause */ + long pause; /* estimated next pause */ + int pages; /* target nr_dirtied_pause */ + + /* target for 10ms pause on 1-dd case */ + t = max(1, HZ / 100); + + /* + * Scale up pause time for concurrent dirtiers in order to reduce CPU + * overheads. + * + * (N * 10ms) on 2^N concurrent tasks. + */ + if (hi > lo) + t += (hi - lo) * (10 * HZ) / 1024; + + /* + * This is a bit convoluted. We try to base the next nr_dirtied_pause + * on the much more stable dirty_ratelimit. However the next pause time + * will be computed based on task_ratelimit and the two rate limits may + * depart considerably at some time. Especially if task_ratelimit goes + * below dirty_ratelimit/2 and the target pause is max_pause, the next + * pause time will be max_pause*2 _trimmed down_ to max_pause. As a + * result task_ratelimit won't be executed faithfully, which could + * eventually bring down dirty_ratelimit. + * + * We apply two rules to fix it up: + * 1) try to estimate the next pause time and if necessary, use a lower + * nr_dirtied_pause so as not to exceed max_pause. When this happens, + * nr_dirtied_pause will be "dancing" with task_ratelimit. + * 2) limit the target pause time to max_pause/2, so that the normal + * small fluctuations of task_ratelimit won't trigger rule (1) and + * nr_dirtied_pause will remain as stable as dirty_ratelimit. + */ + t = min(t, 1 + max_pause / 2); + pages = dirty_ratelimit * t / roundup_pow_of_two(HZ); + + /* + * Tiny nr_dirtied_pause is found to hurt I/O performance in the test + * case fio-mmap-randwrite-64k, which does 16*{sync read, async write}. + * When the 16 consecutive reads are often interrupted by some dirty + * throttling pause during the async writes, cfq will go into idles + * (deadline is fine). So push nr_dirtied_pause as high as possible + * until reaches DIRTY_POLL_THRESH=32 pages. + */ + if (pages < DIRTY_POLL_THRESH) { + t = max_pause; + pages = dirty_ratelimit * t / roundup_pow_of_two(HZ); + if (pages > DIRTY_POLL_THRESH) { + pages = DIRTY_POLL_THRESH; + t = HZ * DIRTY_POLL_THRESH / dirty_ratelimit; + } + } + + pause = HZ * pages / (task_ratelimit + 1); + if (pause > max_pause) { + t = max_pause; + pages = task_ratelimit * t / roundup_pow_of_two(HZ); + } + + *nr_dirtied_pause = pages; + /* + * The minimal pause time will normally be half the target pause time. + */ + return pages >= DIRTY_POLL_THRESH ? 1 + t / 2 : t; +} + +static inline void wb_dirty_limits(struct dirty_throttle_control *dtc) +{ + struct bdi_writeback *wb = dtc->wb; + unsigned long wb_reclaimable; + + /* + * wb_thresh is not treated as some limiting factor as + * dirty_thresh, due to reasons + * - in JBOD setup, wb_thresh can fluctuate a lot + * - in a system with HDD and USB key, the USB key may somehow + * go into state (wb_dirty >> wb_thresh) either because + * wb_dirty starts high, or because wb_thresh drops low. + * In this case we don't want to hard throttle the USB key + * dirtiers for 100 seconds until wb_dirty drops under + * wb_thresh. Instead the auxiliary wb control line in + * wb_position_ratio() will let the dirtier task progress + * at some rate <= (write_bw / 2) for bringing down wb_dirty. + */ + dtc->wb_thresh = __wb_calc_thresh(dtc); + dtc->wb_bg_thresh = dtc->thresh ? + div_u64((u64)dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0; + + /* + * In order to avoid the stacked BDI deadlock we need + * to ensure we accurately count the 'dirty' pages when + * the threshold is low. + * + * Otherwise it would be possible to get thresh+n pages + * reported dirty, even though there are thresh-m pages + * actually dirty; with m+n sitting in the percpu + * deltas. + */ + if (dtc->wb_thresh < 2 * wb_stat_error()) { + wb_reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE); + dtc->wb_dirty = wb_reclaimable + wb_stat_sum(wb, WB_WRITEBACK); + } else { + wb_reclaimable = wb_stat(wb, WB_RECLAIMABLE); + dtc->wb_dirty = wb_reclaimable + wb_stat(wb, WB_WRITEBACK); + } +} + +/* + * balance_dirty_pages() must be called by processes which are generating dirty + * data. It looks at the number of dirty pages in the machine and will force + * the caller to wait once crossing the (background_thresh + dirty_thresh) / 2. + * If we're over `background_thresh' then the writeback threads are woken to + * perform some writeout. + */ +static void balance_dirty_pages(struct bdi_writeback *wb, + unsigned long pages_dirtied) +{ + struct dirty_throttle_control gdtc_stor = { GDTC_INIT(wb) }; + struct dirty_throttle_control mdtc_stor = { MDTC_INIT(wb, &gdtc_stor) }; + struct dirty_throttle_control * const gdtc = &gdtc_stor; + struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ? + &mdtc_stor : NULL; + struct dirty_throttle_control *sdtc; + unsigned long nr_reclaimable; /* = file_dirty */ + long period; + long pause; + long max_pause; + long min_pause; + int nr_dirtied_pause; + bool dirty_exceeded = false; + unsigned long task_ratelimit; + unsigned long dirty_ratelimit; + struct backing_dev_info *bdi = wb->bdi; + bool strictlimit = bdi->capabilities & BDI_CAP_STRICTLIMIT; + unsigned long start_time = jiffies; + + for (;;) { + unsigned long now = jiffies; + unsigned long dirty, thresh, bg_thresh; + unsigned long m_dirty = 0; /* stop bogus uninit warnings */ + unsigned long m_thresh = 0; + unsigned long m_bg_thresh = 0; + + nr_reclaimable = global_node_page_state(NR_FILE_DIRTY); + gdtc->avail = global_dirtyable_memory(); + gdtc->dirty = nr_reclaimable + global_node_page_state(NR_WRITEBACK); + + domain_dirty_limits(gdtc); + + if (unlikely(strictlimit)) { + wb_dirty_limits(gdtc); + + dirty = gdtc->wb_dirty; + thresh = gdtc->wb_thresh; + bg_thresh = gdtc->wb_bg_thresh; + } else { + dirty = gdtc->dirty; + thresh = gdtc->thresh; + bg_thresh = gdtc->bg_thresh; + } + + if (mdtc) { + unsigned long filepages, headroom, writeback; + + /* + * If @wb belongs to !root memcg, repeat the same + * basic calculations for the memcg domain. + */ + mem_cgroup_wb_stats(wb, &filepages, &headroom, + &mdtc->dirty, &writeback); + mdtc->dirty += writeback; + mdtc_calc_avail(mdtc, filepages, headroom); + + domain_dirty_limits(mdtc); + + if (unlikely(strictlimit)) { + wb_dirty_limits(mdtc); + m_dirty = mdtc->wb_dirty; + m_thresh = mdtc->wb_thresh; + m_bg_thresh = mdtc->wb_bg_thresh; + } else { + m_dirty = mdtc->dirty; + m_thresh = mdtc->thresh; + m_bg_thresh = mdtc->bg_thresh; + } + } + + /* + * Throttle it only when the background writeback cannot + * catch-up. This avoids (excessively) small writeouts + * when the wb limits are ramping up in case of !strictlimit. + * + * In strictlimit case make decision based on the wb counters + * and limits. Small writeouts when the wb limits are ramping + * up are the price we consciously pay for strictlimit-ing. + * + * If memcg domain is in effect, @dirty should be under + * both global and memcg freerun ceilings. + */ + if (dirty <= dirty_freerun_ceiling(thresh, bg_thresh) && + (!mdtc || + m_dirty <= dirty_freerun_ceiling(m_thresh, m_bg_thresh))) { + unsigned long intv; + unsigned long m_intv; + +free_running: + intv = dirty_poll_interval(dirty, thresh); + m_intv = ULONG_MAX; + + current->dirty_paused_when = now; + current->nr_dirtied = 0; + if (mdtc) + m_intv = dirty_poll_interval(m_dirty, m_thresh); + current->nr_dirtied_pause = min(intv, m_intv); + break; + } + + if (unlikely(!writeback_in_progress(wb))) + wb_start_background_writeback(wb); + + mem_cgroup_flush_foreign(wb); + + /* + * Calculate global domain's pos_ratio and select the + * global dtc by default. + */ + if (!strictlimit) { + wb_dirty_limits(gdtc); + + if ((current->flags & PF_LOCAL_THROTTLE) && + gdtc->wb_dirty < + dirty_freerun_ceiling(gdtc->wb_thresh, + gdtc->wb_bg_thresh)) + /* + * LOCAL_THROTTLE tasks must not be throttled + * when below the per-wb freerun ceiling. + */ + goto free_running; + } + + dirty_exceeded = (gdtc->wb_dirty > gdtc->wb_thresh) && + ((gdtc->dirty > gdtc->thresh) || strictlimit); + + wb_position_ratio(gdtc); + sdtc = gdtc; + + if (mdtc) { + /* + * If memcg domain is in effect, calculate its + * pos_ratio. @wb should satisfy constraints from + * both global and memcg domains. Choose the one + * w/ lower pos_ratio. + */ + if (!strictlimit) { + wb_dirty_limits(mdtc); + + if ((current->flags & PF_LOCAL_THROTTLE) && + mdtc->wb_dirty < + dirty_freerun_ceiling(mdtc->wb_thresh, + mdtc->wb_bg_thresh)) + /* + * LOCAL_THROTTLE tasks must not be + * throttled when below the per-wb + * freerun ceiling. + */ + goto free_running; + } + dirty_exceeded |= (mdtc->wb_dirty > mdtc->wb_thresh) && + ((mdtc->dirty > mdtc->thresh) || strictlimit); + + wb_position_ratio(mdtc); + if (mdtc->pos_ratio < gdtc->pos_ratio) + sdtc = mdtc; + } + + if (dirty_exceeded && !wb->dirty_exceeded) + wb->dirty_exceeded = 1; + + if (time_is_before_jiffies(wb->bw_time_stamp + + BANDWIDTH_INTERVAL)) { + spin_lock(&wb->list_lock); + __wb_update_bandwidth(gdtc, mdtc, start_time, true); + spin_unlock(&wb->list_lock); + } + + /* throttle according to the chosen dtc */ + dirty_ratelimit = wb->dirty_ratelimit; + task_ratelimit = ((u64)dirty_ratelimit * sdtc->pos_ratio) >> + RATELIMIT_CALC_SHIFT; + max_pause = wb_max_pause(wb, sdtc->wb_dirty); + min_pause = wb_min_pause(wb, max_pause, + task_ratelimit, dirty_ratelimit, + &nr_dirtied_pause); + + if (unlikely(task_ratelimit == 0)) { + period = max_pause; + pause = max_pause; + goto pause; + } + period = HZ * pages_dirtied / task_ratelimit; + pause = period; + if (current->dirty_paused_when) + pause -= now - current->dirty_paused_when; + /* + * For less than 1s think time (ext3/4 may block the dirtier + * for up to 800ms from time to time on 1-HDD; so does xfs, + * however at much less frequency), try to compensate it in + * future periods by updating the virtual time; otherwise just + * do a reset, as it may be a light dirtier. + */ + if (pause < min_pause) { + trace_balance_dirty_pages(wb, + sdtc->thresh, + sdtc->bg_thresh, + sdtc->dirty, + sdtc->wb_thresh, + sdtc->wb_dirty, + dirty_ratelimit, + task_ratelimit, + pages_dirtied, + period, + min(pause, 0L), + start_time); + if (pause < -HZ) { + current->dirty_paused_when = now; + current->nr_dirtied = 0; + } else if (period) { + current->dirty_paused_when += period; + current->nr_dirtied = 0; + } else if (current->nr_dirtied_pause <= pages_dirtied) + current->nr_dirtied_pause += pages_dirtied; + break; + } + if (unlikely(pause > max_pause)) { + /* for occasional dropped task_ratelimit */ + now += min(pause - max_pause, max_pause); + pause = max_pause; + } + +pause: + trace_balance_dirty_pages(wb, + sdtc->thresh, + sdtc->bg_thresh, + sdtc->dirty, + sdtc->wb_thresh, + sdtc->wb_dirty, + dirty_ratelimit, + task_ratelimit, + pages_dirtied, + period, + pause, + start_time); + __set_current_state(TASK_KILLABLE); + wb->dirty_sleep = now; + io_schedule_timeout(pause); + + current->dirty_paused_when = now + pause; + current->nr_dirtied = 0; + current->nr_dirtied_pause = nr_dirtied_pause; + + /* + * This is typically equal to (dirty < thresh) and can also + * keep "1000+ dd on a slow USB stick" under control. + */ + if (task_ratelimit) + break; + + /* + * In the case of an unresponding NFS server and the NFS dirty + * pages exceeds dirty_thresh, give the other good wb's a pipe + * to go through, so that tasks on them still remain responsive. + * + * In theory 1 page is enough to keep the consumer-producer + * pipe going: the flusher cleans 1 page => the task dirties 1 + * more page. However wb_dirty has accounting errors. So use + * the larger and more IO friendly wb_stat_error. + */ + if (sdtc->wb_dirty <= wb_stat_error()) + break; + + if (fatal_signal_pending(current)) + break; + } + + if (!dirty_exceeded && wb->dirty_exceeded) + wb->dirty_exceeded = 0; + + if (writeback_in_progress(wb)) + return; + + /* + * In laptop mode, we wait until hitting the higher threshold before + * starting background writeout, and then write out all the way down + * to the lower threshold. So slow writers cause minimal disk activity. + * + * In normal mode, we start background writeout at the lower + * background_thresh, to keep the amount of dirty memory low. + */ + if (laptop_mode) + return; + + if (nr_reclaimable > gdtc->bg_thresh) + wb_start_background_writeback(wb); +} + +static DEFINE_PER_CPU(int, bdp_ratelimits); + +/* + * Normal tasks are throttled by + * loop { + * dirty tsk->nr_dirtied_pause pages; + * take a snap in balance_dirty_pages(); + * } + * However there is a worst case. If every task exit immediately when dirtied + * (tsk->nr_dirtied_pause - 1) pages, balance_dirty_pages() will never be + * called to throttle the page dirties. The solution is to save the not yet + * throttled page dirties in dirty_throttle_leaks on task exit and charge them + * randomly into the running tasks. This works well for the above worst case, + * as the new task will pick up and accumulate the old task's leaked dirty + * count and eventually get throttled. + */ +DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0; + +/** + * balance_dirty_pages_ratelimited - balance dirty memory state + * @mapping: address_space which was dirtied + * + * Processes which are dirtying memory should call in here once for each page + * which was newly dirtied. The function will periodically check the system's + * dirty state and will initiate writeback if needed. + * + * On really big machines, get_writeback_state is expensive, so try to avoid + * calling it too often (ratelimiting). But once we're over the dirty memory + * limit we decrease the ratelimiting by a lot, to prevent individual processes + * from overshooting the limit by (ratelimit_pages) each. + */ +void balance_dirty_pages_ratelimited(struct address_space *mapping) +{ + struct inode *inode = mapping->host; + struct backing_dev_info *bdi = inode_to_bdi(inode); + struct bdi_writeback *wb = NULL; + int ratelimit; + int *p; + + if (!(bdi->capabilities & BDI_CAP_WRITEBACK)) + return; + + if (inode_cgwb_enabled(inode)) + wb = wb_get_create_current(bdi, GFP_KERNEL); + if (!wb) + wb = &bdi->wb; + + ratelimit = current->nr_dirtied_pause; + if (wb->dirty_exceeded) + ratelimit = min(ratelimit, 32 >> (PAGE_SHIFT - 10)); + + preempt_disable(); + /* + * This prevents one CPU to accumulate too many dirtied pages without + * calling into balance_dirty_pages(), which can happen when there are + * 1000+ tasks, all of them start dirtying pages at exactly the same + * time, hence all honoured too large initial task->nr_dirtied_pause. + */ + p = this_cpu_ptr(&bdp_ratelimits); + if (unlikely(current->nr_dirtied >= ratelimit)) + *p = 0; + else if (unlikely(*p >= ratelimit_pages)) { + *p = 0; + ratelimit = 0; + } + /* + * Pick up the dirtied pages by the exited tasks. This avoids lots of + * short-lived tasks (eg. gcc invocations in a kernel build) escaping + * the dirty throttling and livelock other long-run dirtiers. + */ + p = this_cpu_ptr(&dirty_throttle_leaks); + if (*p > 0 && current->nr_dirtied < ratelimit) { + unsigned long nr_pages_dirtied; + nr_pages_dirtied = min(*p, ratelimit - current->nr_dirtied); + *p -= nr_pages_dirtied; + current->nr_dirtied += nr_pages_dirtied; + } + preempt_enable(); + + if (unlikely(current->nr_dirtied >= ratelimit)) + balance_dirty_pages(wb, current->nr_dirtied); + + wb_put(wb); +} +EXPORT_SYMBOL(balance_dirty_pages_ratelimited); + +/** + * wb_over_bg_thresh - does @wb need to be written back? + * @wb: bdi_writeback of interest + * + * Determines whether background writeback should keep writing @wb or it's + * clean enough. + * + * Return: %true if writeback should continue. + */ +bool wb_over_bg_thresh(struct bdi_writeback *wb) +{ + struct dirty_throttle_control gdtc_stor = { GDTC_INIT(wb) }; + struct dirty_throttle_control mdtc_stor = { MDTC_INIT(wb, &gdtc_stor) }; + struct dirty_throttle_control * const gdtc = &gdtc_stor; + struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ? + &mdtc_stor : NULL; + + /* + * Similar to balance_dirty_pages() but ignores pages being written + * as we're trying to decide whether to put more under writeback. + */ + gdtc->avail = global_dirtyable_memory(); + gdtc->dirty = global_node_page_state(NR_FILE_DIRTY); + domain_dirty_limits(gdtc); + + if (gdtc->dirty > gdtc->bg_thresh) + return true; + + if (wb_stat(wb, WB_RECLAIMABLE) > + wb_calc_thresh(gdtc->wb, gdtc->bg_thresh)) + return true; + + if (mdtc) { + unsigned long filepages, headroom, writeback; + + mem_cgroup_wb_stats(wb, &filepages, &headroom, &mdtc->dirty, + &writeback); + mdtc_calc_avail(mdtc, filepages, headroom); + domain_dirty_limits(mdtc); /* ditto, ignore writeback */ + + if (mdtc->dirty > mdtc->bg_thresh) + return true; + + if (wb_stat(wb, WB_RECLAIMABLE) > + wb_calc_thresh(mdtc->wb, mdtc->bg_thresh)) + return true; + } + + return false; +} + +/* + * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs + */ +int dirty_writeback_centisecs_handler(struct ctl_table *table, int write, + void *buffer, size_t *length, loff_t *ppos) +{ + unsigned int old_interval = dirty_writeback_interval; + int ret; + + ret = proc_dointvec(table, write, buffer, length, ppos); + + /* + * Writing 0 to dirty_writeback_interval will disable periodic writeback + * and a different non-zero value will wakeup the writeback threads. + * wb_wakeup_delayed() would be more appropriate, but it's a pain to + * iterate over all bdis and wbs. + * The reason we do this is to make the change take effect immediately. + */ + if (!ret && write && dirty_writeback_interval && + dirty_writeback_interval != old_interval) + wakeup_flusher_threads(WB_REASON_PERIODIC); + + return ret; +} + +#ifdef CONFIG_BLOCK +void laptop_mode_timer_fn(struct timer_list *t) +{ + struct backing_dev_info *backing_dev_info = + from_timer(backing_dev_info, t, laptop_mode_wb_timer); + + wakeup_flusher_threads_bdi(backing_dev_info, WB_REASON_LAPTOP_TIMER); +} + +/* + * We've spun up the disk and we're in laptop mode: schedule writeback + * of all dirty data a few seconds from now. If the flush is already scheduled + * then push it back - the user is still using the disk. + */ +void laptop_io_completion(struct backing_dev_info *info) +{ + mod_timer(&info->laptop_mode_wb_timer, jiffies + laptop_mode); +} + +/* + * We're in laptop mode and we've just synced. The sync's writes will have + * caused another writeback to be scheduled by laptop_io_completion. + * Nothing needs to be written back anymore, so we unschedule the writeback. + */ +void laptop_sync_completion(void) +{ + struct backing_dev_info *bdi; + + rcu_read_lock(); + + list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) + del_timer(&bdi->laptop_mode_wb_timer); + + rcu_read_unlock(); +} +#endif + +/* + * If ratelimit_pages is too high then we can get into dirty-data overload + * if a large number of processes all perform writes at the same time. + * If it is too low then SMP machines will call the (expensive) + * get_writeback_state too often. + * + * Here we set ratelimit_pages to a level which ensures that when all CPUs are + * dirtying in parallel, we cannot go more than 3% (1/32) over the dirty memory + * thresholds. + */ + +void writeback_set_ratelimit(void) +{ + struct wb_domain *dom = &global_wb_domain; + unsigned long background_thresh; + unsigned long dirty_thresh; + + global_dirty_limits(&background_thresh, &dirty_thresh); + dom->dirty_limit = dirty_thresh; + ratelimit_pages = dirty_thresh / (num_online_cpus() * 32); + if (ratelimit_pages < 16) + ratelimit_pages = 16; +} + +static int page_writeback_cpu_online(unsigned int cpu) +{ + writeback_set_ratelimit(); + return 0; +} + +/* + * Called early on to tune the page writeback dirty limits. + * + * We used to scale dirty pages according to how total memory + * related to pages that could be allocated for buffers. + * + * However, that was when we used "dirty_ratio" to scale with + * all memory, and we don't do that any more. "dirty_ratio" + * is now applied to total non-HIGHPAGE memory, and as such we can't + * get into the old insane situation any more where we had + * large amounts of dirty pages compared to a small amount of + * non-HIGHMEM memory. + * + * But we might still want to scale the dirty_ratio by how + * much memory the box has.. + */ +void __init page_writeback_init(void) +{ + BUG_ON(wb_domain_init(&global_wb_domain, GFP_KERNEL)); + + cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mm/writeback:online", + page_writeback_cpu_online, NULL); + cpuhp_setup_state(CPUHP_MM_WRITEBACK_DEAD, "mm/writeback:dead", NULL, + page_writeback_cpu_online); +} + +/** + * tag_pages_for_writeback - tag pages to be written by write_cache_pages + * @mapping: address space structure to write + * @start: starting page index + * @end: ending page index (inclusive) + * + * This function scans the page range from @start to @end (inclusive) and tags + * all pages that have DIRTY tag set with a special TOWRITE tag. The idea is + * that write_cache_pages (or whoever calls this function) will then use + * TOWRITE tag to identify pages eligible for writeback. This mechanism is + * used to avoid livelocking of writeback by a process steadily creating new + * dirty pages in the file (thus it is important for this function to be quick + * so that it can tag pages faster than a dirtying process can create them). + */ +void tag_pages_for_writeback(struct address_space *mapping, + pgoff_t start, pgoff_t end) +{ + XA_STATE(xas, &mapping->i_pages, start); + unsigned int tagged = 0; + void *page; + + xas_lock_irq(&xas); + xas_for_each_marked(&xas, page, end, PAGECACHE_TAG_DIRTY) { + xas_set_mark(&xas, PAGECACHE_TAG_TOWRITE); + if (++tagged % XA_CHECK_SCHED) + continue; + + xas_pause(&xas); + xas_unlock_irq(&xas); + cond_resched(); + xas_lock_irq(&xas); + } + xas_unlock_irq(&xas); +} +EXPORT_SYMBOL(tag_pages_for_writeback); + +/** + * write_cache_pages - walk the list of dirty pages of the given address space and write all of them. + * @mapping: address space structure to write + * @wbc: subtract the number of written pages from *@wbc->nr_to_write + * @writepage: function called for each page + * @data: data passed to writepage function + * + * If a page is already under I/O, write_cache_pages() skips it, even + * if it's dirty. This is desirable behaviour for memory-cleaning writeback, + * but it is INCORRECT for data-integrity system calls such as fsync(). fsync() + * and msync() need to guarantee that all the data which was dirty at the time + * the call was made get new I/O started against them. If wbc->sync_mode is + * WB_SYNC_ALL then we were called for data integrity and we must wait for + * existing IO to complete. + * + * To avoid livelocks (when other process dirties new pages), we first tag + * pages which should be written back with TOWRITE tag and only then start + * writing them. For data-integrity sync we have to be careful so that we do + * not miss some pages (e.g., because some other process has cleared TOWRITE + * tag we set). The rule we follow is that TOWRITE tag can be cleared only + * by the process clearing the DIRTY tag (and submitting the page for IO). + * + * To avoid deadlocks between range_cyclic writeback and callers that hold + * pages in PageWriteback to aggregate IO until write_cache_pages() returns, + * we do not loop back to the start of the file. Doing so causes a page + * lock/page writeback access order inversion - we should only ever lock + * multiple pages in ascending page->index order, and looping back to the start + * of the file violates that rule and causes deadlocks. + * + * Return: %0 on success, negative error code otherwise + */ +int write_cache_pages(struct address_space *mapping, + struct writeback_control *wbc, writepage_t writepage, + void *data) +{ + int ret = 0; + int done = 0; + int error; + struct pagevec pvec; + int nr_pages; + pgoff_t index; + pgoff_t end; /* Inclusive */ + pgoff_t done_index; + int range_whole = 0; + xa_mark_t tag; + + pagevec_init(&pvec); + if (wbc->range_cyclic) { + index = mapping->writeback_index; /* prev offset */ + end = -1; + } else { + index = wbc->range_start >> PAGE_SHIFT; + end = wbc->range_end >> PAGE_SHIFT; + if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) + range_whole = 1; + } + if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) { + tag_pages_for_writeback(mapping, index, end); + tag = PAGECACHE_TAG_TOWRITE; + } else { + tag = PAGECACHE_TAG_DIRTY; + } + done_index = index; + while (!done && (index <= end)) { + int i; + + nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end, + tag); + if (nr_pages == 0) + break; + + for (i = 0; i < nr_pages; i++) { + struct page *page = pvec.pages[i]; + + done_index = page->index; + + lock_page(page); + + /* + * Page truncated or invalidated. We can freely skip it + * then, even for data integrity operations: the page + * has disappeared concurrently, so there could be no + * real expectation of this data interity operation + * even if there is now a new, dirty page at the same + * pagecache address. + */ + if (unlikely(page->mapping != mapping)) { +continue_unlock: + unlock_page(page); + continue; + } + + if (!PageDirty(page)) { + /* someone wrote it for us */ + goto continue_unlock; + } + + if (PageWriteback(page)) { + if (wbc->sync_mode != WB_SYNC_NONE) + wait_on_page_writeback(page); + else + goto continue_unlock; + } + + BUG_ON(PageWriteback(page)); + if (!clear_page_dirty_for_io(page)) + goto continue_unlock; + + trace_wbc_writepage(wbc, inode_to_bdi(mapping->host)); + error = (*writepage)(page, wbc, data); + if (unlikely(error)) { + /* + * Handle errors according to the type of + * writeback. There's no need to continue for + * background writeback. Just push done_index + * past this page so media errors won't choke + * writeout for the entire file. For integrity + * writeback, we must process the entire dirty + * set regardless of errors because the fs may + * still have state to clear for each page. In + * that case we continue processing and return + * the first error. + */ + if (error == AOP_WRITEPAGE_ACTIVATE) { + unlock_page(page); + error = 0; + } else if (wbc->sync_mode != WB_SYNC_ALL) { + ret = error; + done_index = page->index + 1; + done = 1; + break; + } + if (!ret) + ret = error; + } + + /* + * We stop writing back only if we are not doing + * integrity sync. In case of integrity sync we have to + * keep going until we have written all the pages + * we tagged for writeback prior to entering this loop. + */ + if (--wbc->nr_to_write <= 0 && + wbc->sync_mode == WB_SYNC_NONE) { + done = 1; + break; + } + } + pagevec_release(&pvec); + cond_resched(); + } + + /* + * If we hit the last page and there is more work to be done: wrap + * back the index back to the start of the file for the next + * time we are called. + */ + if (wbc->range_cyclic && !done) + done_index = 0; + if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) + mapping->writeback_index = done_index; + + return ret; +} +EXPORT_SYMBOL(write_cache_pages); + +/* + * Function used by generic_writepages to call the real writepage + * function and set the mapping flags on error + */ +static int __writepage(struct page *page, struct writeback_control *wbc, + void *data) +{ + struct address_space *mapping = data; + int ret = mapping->a_ops->writepage(page, wbc); + mapping_set_error(mapping, ret); + return ret; +} + +/** + * generic_writepages - walk the list of dirty pages of the given address space and writepage() all of them. + * @mapping: address space structure to write + * @wbc: subtract the number of written pages from *@wbc->nr_to_write + * + * This is a library function, which implements the writepages() + * address_space_operation. + * + * Return: %0 on success, negative error code otherwise + */ +int generic_writepages(struct address_space *mapping, + struct writeback_control *wbc) +{ + struct blk_plug plug; + int ret; + + /* deal with chardevs and other special file */ + if (!mapping->a_ops->writepage) + return 0; + + blk_start_plug(&plug); + ret = write_cache_pages(mapping, wbc, __writepage, mapping); + blk_finish_plug(&plug); + return ret; +} + +EXPORT_SYMBOL(generic_writepages); + +int do_writepages(struct address_space *mapping, struct writeback_control *wbc) +{ + int ret; + + if (wbc->nr_to_write <= 0) + return 0; + while (1) { + if (mapping->a_ops->writepages) + ret = mapping->a_ops->writepages(mapping, wbc); + else + ret = generic_writepages(mapping, wbc); + if ((ret != -ENOMEM) || (wbc->sync_mode != WB_SYNC_ALL)) + break; + cond_resched(); + congestion_wait(BLK_RW_ASYNC, HZ/50); + } + return ret; +} + +/** + * write_one_page - write out a single page and wait on I/O + * @page: the page to write + * + * The page must be locked by the caller and will be unlocked upon return. + * + * Note that the mapping's AS_EIO/AS_ENOSPC flags will be cleared when this + * function returns. + * + * Return: %0 on success, negative error code otherwise + */ +int write_one_page(struct page *page) +{ + struct address_space *mapping = page->mapping; + int ret = 0; + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = 1, + }; + + BUG_ON(!PageLocked(page)); + + wait_on_page_writeback(page); + + if (clear_page_dirty_for_io(page)) { + get_page(page); + ret = mapping->a_ops->writepage(page, &wbc); + if (ret == 0) + wait_on_page_writeback(page); + put_page(page); + } else { + unlock_page(page); + } + + if (!ret) + ret = filemap_check_errors(mapping); + return ret; +} +EXPORT_SYMBOL(write_one_page); + +/* + * For address_spaces which do not use buffers nor write back. + */ +int __set_page_dirty_no_writeback(struct page *page) +{ + if (!PageDirty(page)) + return !TestSetPageDirty(page); + return 0; +} + +/* + * Helper function for set_page_dirty family. + * + * Caller must hold lock_page_memcg(). + * + * NOTE: This relies on being atomic wrt interrupts. + */ +void account_page_dirtied(struct page *page, struct address_space *mapping) +{ + struct inode *inode = mapping->host; + + trace_writeback_dirty_page(page, mapping); + + if (mapping_can_writeback(mapping)) { + struct bdi_writeback *wb; + + inode_attach_wb(inode, page); + wb = inode_to_wb(inode); + + __inc_lruvec_page_state(page, NR_FILE_DIRTY); + __inc_zone_page_state(page, NR_ZONE_WRITE_PENDING); + __inc_node_page_state(page, NR_DIRTIED); + inc_wb_stat(wb, WB_RECLAIMABLE); + inc_wb_stat(wb, WB_DIRTIED); + task_io_account_write(PAGE_SIZE); + current->nr_dirtied++; + this_cpu_inc(bdp_ratelimits); + + mem_cgroup_track_foreign_dirty(page, wb); + } +} + +/* + * Helper function for deaccounting dirty page without writeback. + * + * Caller must hold lock_page_memcg(). + */ +void account_page_cleaned(struct page *page, struct address_space *mapping, + struct bdi_writeback *wb) +{ + if (mapping_can_writeback(mapping)) { + dec_lruvec_page_state(page, NR_FILE_DIRTY); + dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); + dec_wb_stat(wb, WB_RECLAIMABLE); + task_io_account_cancelled_write(PAGE_SIZE); + } +} + +/* + * For address_spaces which do not use buffers. Just tag the page as dirty in + * the xarray. + * + * This is also used when a single buffer is being dirtied: we want to set the + * page dirty in that case, but not all the buffers. This is a "bottom-up" + * dirtying, whereas __set_page_dirty_buffers() is a "top-down" dirtying. + * + * The caller must ensure this doesn't race with truncation. Most will simply + * hold the page lock, but e.g. zap_pte_range() calls with the page mapped and + * the pte lock held, which also locks out truncation. + */ +int __set_page_dirty_nobuffers(struct page *page) +{ + lock_page_memcg(page); + if (!TestSetPageDirty(page)) { + struct address_space *mapping = page_mapping(page); + unsigned long flags; + + if (!mapping) { + unlock_page_memcg(page); + return 1; + } + + xa_lock_irqsave(&mapping->i_pages, flags); + BUG_ON(page_mapping(page) != mapping); + WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page)); + account_page_dirtied(page, mapping); + __xa_set_mark(&mapping->i_pages, page_index(page), + PAGECACHE_TAG_DIRTY); + xa_unlock_irqrestore(&mapping->i_pages, flags); + unlock_page_memcg(page); + + if (mapping->host) { + /* !PageAnon && !swapper_space */ + __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); + } + return 1; + } + unlock_page_memcg(page); + return 0; +} +EXPORT_SYMBOL(__set_page_dirty_nobuffers); + +/* + * Call this whenever redirtying a page, to de-account the dirty counters + * (NR_DIRTIED, WB_DIRTIED, tsk->nr_dirtied), so that they match the written + * counters (NR_WRITTEN, WB_WRITTEN) in long term. The mismatches will lead to + * systematic errors in balanced_dirty_ratelimit and the dirty pages position + * control. + */ +void account_page_redirty(struct page *page) +{ + struct address_space *mapping = page->mapping; + + if (mapping && mapping_can_writeback(mapping)) { + struct inode *inode = mapping->host; + struct bdi_writeback *wb; + struct wb_lock_cookie cookie = {}; + + wb = unlocked_inode_to_wb_begin(inode, &cookie); + current->nr_dirtied--; + dec_node_page_state(page, NR_DIRTIED); + dec_wb_stat(wb, WB_DIRTIED); + unlocked_inode_to_wb_end(inode, &cookie); + } +} +EXPORT_SYMBOL(account_page_redirty); + +/* + * When a writepage implementation decides that it doesn't want to write this + * page for some reason, it should redirty the locked page via + * redirty_page_for_writepage() and it should then unlock the page and return 0 + */ +int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page) +{ + int ret; + + wbc->pages_skipped++; + ret = __set_page_dirty_nobuffers(page); + account_page_redirty(page); + return ret; +} +EXPORT_SYMBOL(redirty_page_for_writepage); + +/* + * Dirty a page. + * + * For pages with a mapping this should be done under the page lock + * for the benefit of asynchronous memory errors who prefer a consistent + * dirty state. This rule can be broken in some special cases, + * but should be better not to. + * + * If the mapping doesn't provide a set_page_dirty a_op, then + * just fall through and assume that it wants buffer_heads. + */ +int set_page_dirty(struct page *page) +{ + struct address_space *mapping = page_mapping(page); + + page = compound_head(page); + if (likely(mapping)) { + int (*spd)(struct page *) = mapping->a_ops->set_page_dirty; + /* + * readahead/lru_deactivate_page could remain + * PG_readahead/PG_reclaim due to race with end_page_writeback + * About readahead, if the page is written, the flags would be + * reset. So no problem. + * About lru_deactivate_page, if the page is redirty, the flag + * will be reset. So no problem. but if the page is used by readahead + * it will confuse readahead and make it restart the size rampup + * process. But it's a trivial problem. + */ + if (PageReclaim(page)) + ClearPageReclaim(page); +#ifdef CONFIG_BLOCK + if (!spd) + spd = __set_page_dirty_buffers; +#endif + return (*spd)(page); + } + if (!PageDirty(page)) { + if (!TestSetPageDirty(page)) + return 1; + } + return 0; +} +EXPORT_SYMBOL(set_page_dirty); + +/* + * set_page_dirty() is racy if the caller has no reference against + * page->mapping->host, and if the page is unlocked. This is because another + * CPU could truncate the page off the mapping and then free the mapping. + * + * Usually, the page _is_ locked, or the caller is a user-space process which + * holds a reference on the inode by having an open file. + * + * In other cases, the page should be locked before running set_page_dirty(). + */ +int set_page_dirty_lock(struct page *page) +{ + int ret; + + lock_page(page); + ret = set_page_dirty(page); + unlock_page(page); + return ret; +} +EXPORT_SYMBOL(set_page_dirty_lock); + +/* + * This cancels just the dirty bit on the kernel page itself, it does NOT + * actually remove dirty bits on any mmap's that may be around. It also + * leaves the page tagged dirty, so any sync activity will still find it on + * the dirty lists, and in particular, clear_page_dirty_for_io() will still + * look at the dirty bits in the VM. + * + * Doing this should *normally* only ever be done when a page is truncated, + * and is not actually mapped anywhere at all. However, fs/buffer.c does + * this when it notices that somebody has cleaned out all the buffers on a + * page without actually doing it through the VM. Can you say "ext3 is + * horribly ugly"? Thought you could. + */ +void __cancel_dirty_page(struct page *page) +{ + struct address_space *mapping = page_mapping(page); + + if (mapping_can_writeback(mapping)) { + struct inode *inode = mapping->host; + struct bdi_writeback *wb; + struct wb_lock_cookie cookie = {}; + + lock_page_memcg(page); + wb = unlocked_inode_to_wb_begin(inode, &cookie); + + if (TestClearPageDirty(page)) + account_page_cleaned(page, mapping, wb); + + unlocked_inode_to_wb_end(inode, &cookie); + unlock_page_memcg(page); + } else { + ClearPageDirty(page); + } +} +EXPORT_SYMBOL(__cancel_dirty_page); + +/* + * Clear a page's dirty flag, while caring for dirty memory accounting. + * Returns true if the page was previously dirty. + * + * This is for preparing to put the page under writeout. We leave the page + * tagged as dirty in the xarray so that a concurrent write-for-sync + * can discover it via a PAGECACHE_TAG_DIRTY walk. The ->writepage + * implementation will run either set_page_writeback() or set_page_dirty(), + * at which stage we bring the page's dirty flag and xarray dirty tag + * back into sync. + * + * This incoherency between the page's dirty flag and xarray tag is + * unfortunate, but it only exists while the page is locked. + */ +int clear_page_dirty_for_io(struct page *page) +{ + struct address_space *mapping = page_mapping(page); + int ret = 0; + + VM_BUG_ON_PAGE(!PageLocked(page), page); + + if (mapping && mapping_can_writeback(mapping)) { + struct inode *inode = mapping->host; + struct bdi_writeback *wb; + struct wb_lock_cookie cookie = {}; + + /* + * Yes, Virginia, this is indeed insane. + * + * We use this sequence to make sure that + * (a) we account for dirty stats properly + * (b) we tell the low-level filesystem to + * mark the whole page dirty if it was + * dirty in a pagetable. Only to then + * (c) clean the page again and return 1 to + * cause the writeback. + * + * This way we avoid all nasty races with the + * dirty bit in multiple places and clearing + * them concurrently from different threads. + * + * Note! Normally the "set_page_dirty(page)" + * has no effect on the actual dirty bit - since + * that will already usually be set. But we + * need the side effects, and it can help us + * avoid races. + * + * We basically use the page "master dirty bit" + * as a serialization point for all the different + * threads doing their things. + */ + if (page_mkclean(page)) + set_page_dirty(page); + /* + * We carefully synchronise fault handlers against + * installing a dirty pte and marking the page dirty + * at this point. We do this by having them hold the + * page lock while dirtying the page, and pages are + * always locked coming in here, so we get the desired + * exclusion. + */ + wb = unlocked_inode_to_wb_begin(inode, &cookie); + if (TestClearPageDirty(page)) { + dec_lruvec_page_state(page, NR_FILE_DIRTY); + dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); + dec_wb_stat(wb, WB_RECLAIMABLE); + ret = 1; + } + unlocked_inode_to_wb_end(inode, &cookie); + return ret; + } + return TestClearPageDirty(page); +} +EXPORT_SYMBOL(clear_page_dirty_for_io); + +int test_clear_page_writeback(struct page *page) +{ + struct address_space *mapping = page_mapping(page); + struct mem_cgroup *memcg; + struct lruvec *lruvec; + int ret; + + memcg = lock_page_memcg(page); + lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page)); + if (mapping && mapping_use_writeback_tags(mapping)) { + struct inode *inode = mapping->host; + struct backing_dev_info *bdi = inode_to_bdi(inode); + unsigned long flags; + + xa_lock_irqsave(&mapping->i_pages, flags); + ret = TestClearPageWriteback(page); + if (ret) { + __xa_clear_mark(&mapping->i_pages, page_index(page), + PAGECACHE_TAG_WRITEBACK); + if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) { + struct bdi_writeback *wb = inode_to_wb(inode); + + dec_wb_stat(wb, WB_WRITEBACK); + __wb_writeout_inc(wb); + } + } + + if (mapping->host && !mapping_tagged(mapping, + PAGECACHE_TAG_WRITEBACK)) + sb_clear_inode_writeback(mapping->host); + + xa_unlock_irqrestore(&mapping->i_pages, flags); + } else { + ret = TestClearPageWriteback(page); + } + if (ret) { + dec_lruvec_state(lruvec, NR_WRITEBACK); + dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); + inc_node_page_state(page, NR_WRITTEN); + } + __unlock_page_memcg(memcg); + return ret; +} + +int __test_set_page_writeback(struct page *page, bool keep_write) +{ + struct address_space *mapping = page_mapping(page); + int ret, access_ret; + + lock_page_memcg(page); + if (mapping && mapping_use_writeback_tags(mapping)) { + XA_STATE(xas, &mapping->i_pages, page_index(page)); + struct inode *inode = mapping->host; + struct backing_dev_info *bdi = inode_to_bdi(inode); + unsigned long flags; + + xas_lock_irqsave(&xas, flags); + xas_load(&xas); + ret = TestSetPageWriteback(page); + if (!ret) { + bool on_wblist; + + on_wblist = mapping_tagged(mapping, + PAGECACHE_TAG_WRITEBACK); + + xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK); + if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) + inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK); + + /* + * We can come through here when swapping anonymous + * pages, so we don't necessarily have an inode to track + * for sync. + */ + if (mapping->host && !on_wblist) + sb_mark_inode_writeback(mapping->host); + } + if (!PageDirty(page)) + xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY); + if (!keep_write) + xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE); + xas_unlock_irqrestore(&xas, flags); + } else { + ret = TestSetPageWriteback(page); + } + if (!ret) { + inc_lruvec_page_state(page, NR_WRITEBACK); + inc_zone_page_state(page, NR_ZONE_WRITE_PENDING); + } + unlock_page_memcg(page); + access_ret = arch_make_page_accessible(page); + /* + * If writeback has been triggered on a page that cannot be made + * accessible, it is too late to recover here. + */ + VM_BUG_ON_PAGE(access_ret != 0, page); + + return ret; + +} +EXPORT_SYMBOL(__test_set_page_writeback); + +/* + * Wait for a page to complete writeback + */ +void wait_on_page_writeback(struct page *page) +{ + while (PageWriteback(page)) { + trace_wait_on_page_writeback(page, page_mapping(page)); + wait_on_page_bit(page, PG_writeback); + } +} +EXPORT_SYMBOL_GPL(wait_on_page_writeback); + +/** + * wait_for_stable_page() - wait for writeback to finish, if necessary. + * @page: The page to wait on. + * + * This function determines if the given page is related to a backing device + * that requires page contents to be held stable during writeback. If so, then + * it will wait for any pending writeback to complete. + */ +void wait_for_stable_page(struct page *page) +{ + page = thp_head(page); + if (page->mapping->host->i_sb->s_iflags & SB_I_STABLE_WRITES) + wait_on_page_writeback(page); +} +EXPORT_SYMBOL_GPL(wait_for_stable_page); diff --git a/mm/page_alloc.c b/mm/page_alloc.c new file mode 100644 index 000000000..124ab9324 --- /dev/null +++ b/mm/page_alloc.c @@ -0,0 +1,8997 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/mm/page_alloc.c + * + * Manages the free list, the system allocates free pages here. + * Note that kmalloc() lives in slab.c + * + * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds + * Swap reorganised 29.12.95, Stephen Tweedie + * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 + * Reshaped it to be a zoned allocator, Ingo Molnar, Red Hat, 1999 + * Discontiguous memory support, Kanoj Sarcar, SGI, Nov 1999 + * Zone balancing, Kanoj Sarcar, SGI, Jan 2000 + * Per cpu hot/cold page lists, bulk allocation, Martin J. Bligh, Sept 2002 + * (lots of bits borrowed from Ingo Molnar & Andrew Morton) + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include "internal.h" +#include "shuffle.h" +#include "page_reporting.h" + +/* Free Page Internal flags: for internal, non-pcp variants of free_pages(). */ +typedef int __bitwise fpi_t; + +/* No special request */ +#define FPI_NONE ((__force fpi_t)0) + +/* + * Skip free page reporting notification for the (possibly merged) page. + * This does not hinder free page reporting from grabbing the page, + * reporting it and marking it "reported" - it only skips notifying + * the free page reporting infrastructure about a newly freed page. For + * example, used when temporarily pulling a page from a freelist and + * putting it back unmodified. + */ +#define FPI_SKIP_REPORT_NOTIFY ((__force fpi_t)BIT(0)) + +/* + * Place the (possibly merged) page to the tail of the freelist. Will ignore + * page shuffling (relevant code - e.g., memory onlining - is expected to + * shuffle the whole zone). + * + * Note: No code should rely on this flag for correctness - it's purely + * to allow for optimizations when handing back either fresh pages + * (memory onlining) or untouched pages (page isolation, free page + * reporting). + */ +#define FPI_TO_TAIL ((__force fpi_t)BIT(1)) + +/* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */ +static DEFINE_MUTEX(pcp_batch_high_lock); +#define MIN_PERCPU_PAGELIST_FRACTION (8) + +#ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID +DEFINE_PER_CPU(int, numa_node); +EXPORT_PER_CPU_SYMBOL(numa_node); +#endif + +DEFINE_STATIC_KEY_TRUE(vm_numa_stat_key); + +#ifdef CONFIG_HAVE_MEMORYLESS_NODES +/* + * N.B., Do NOT reference the '_numa_mem_' per cpu variable directly. + * It will not be defined when CONFIG_HAVE_MEMORYLESS_NODES is not defined. + * Use the accessor functions set_numa_mem(), numa_mem_id() and cpu_to_mem() + * defined in . + */ +DEFINE_PER_CPU(int, _numa_mem_); /* Kernel "local memory" node */ +EXPORT_PER_CPU_SYMBOL(_numa_mem_); +#endif + +/* work_structs for global per-cpu drains */ +struct pcpu_drain { + struct zone *zone; + struct work_struct work; +}; +static DEFINE_MUTEX(pcpu_drain_mutex); +static DEFINE_PER_CPU(struct pcpu_drain, pcpu_drain); + +#ifdef CONFIG_GCC_PLUGIN_LATENT_ENTROPY +volatile unsigned long latent_entropy __latent_entropy; +EXPORT_SYMBOL(latent_entropy); +#endif + +/* + * Array of node states. + */ +nodemask_t node_states[NR_NODE_STATES] __read_mostly = { + [N_POSSIBLE] = NODE_MASK_ALL, + [N_ONLINE] = { { [0] = 1UL } }, +#ifndef CONFIG_NUMA + [N_NORMAL_MEMORY] = { { [0] = 1UL } }, +#ifdef CONFIG_HIGHMEM + [N_HIGH_MEMORY] = { { [0] = 1UL } }, +#endif + [N_MEMORY] = { { [0] = 1UL } }, + [N_CPU] = { { [0] = 1UL } }, +#endif /* NUMA */ +}; +EXPORT_SYMBOL(node_states); + +atomic_long_t _totalram_pages __read_mostly; +EXPORT_SYMBOL(_totalram_pages); +unsigned long totalreserve_pages __read_mostly; +unsigned long totalcma_pages __read_mostly; + +int percpu_pagelist_fraction; +gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK; +#ifdef CONFIG_INIT_ON_ALLOC_DEFAULT_ON +DEFINE_STATIC_KEY_TRUE(init_on_alloc); +#else +DEFINE_STATIC_KEY_FALSE(init_on_alloc); +#endif +EXPORT_SYMBOL(init_on_alloc); + +#ifdef CONFIG_INIT_ON_FREE_DEFAULT_ON +DEFINE_STATIC_KEY_TRUE(init_on_free); +#else +DEFINE_STATIC_KEY_FALSE(init_on_free); +#endif +EXPORT_SYMBOL(init_on_free); + +static int __init early_init_on_alloc(char *buf) +{ + int ret; + bool bool_result; + + ret = kstrtobool(buf, &bool_result); + if (ret) + return ret; + if (bool_result && page_poisoning_enabled()) + pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, will take precedence over init_on_alloc\n"); + if (bool_result) + static_branch_enable(&init_on_alloc); + else + static_branch_disable(&init_on_alloc); + return 0; +} +early_param("init_on_alloc", early_init_on_alloc); + +static int __init early_init_on_free(char *buf) +{ + int ret; + bool bool_result; + + ret = kstrtobool(buf, &bool_result); + if (ret) + return ret; + if (bool_result && page_poisoning_enabled()) + pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, will take precedence over init_on_free\n"); + if (bool_result) + static_branch_enable(&init_on_free); + else + static_branch_disable(&init_on_free); + return 0; +} +early_param("init_on_free", early_init_on_free); + +/* + * A cached value of the page's pageblock's migratetype, used when the page is + * put on a pcplist. Used to avoid the pageblock migratetype lookup when + * freeing from pcplists in most cases, at the cost of possibly becoming stale. + * Also the migratetype set in the page does not necessarily match the pcplist + * index, e.g. page might have MIGRATE_CMA set but be on a pcplist with any + * other index - this ensures that it will be put on the correct CMA freelist. + */ +static inline int get_pcppage_migratetype(struct page *page) +{ + return page->index; +} + +static inline void set_pcppage_migratetype(struct page *page, int migratetype) +{ + page->index = migratetype; +} + +#ifdef CONFIG_PM_SLEEP +/* + * The following functions are used by the suspend/hibernate code to temporarily + * change gfp_allowed_mask in order to avoid using I/O during memory allocations + * while devices are suspended. To avoid races with the suspend/hibernate code, + * they should always be called with system_transition_mutex held + * (gfp_allowed_mask also should only be modified with system_transition_mutex + * held, unless the suspend/hibernate code is guaranteed not to run in parallel + * with that modification). + */ + +static gfp_t saved_gfp_mask; + +void pm_restore_gfp_mask(void) +{ + WARN_ON(!mutex_is_locked(&system_transition_mutex)); + if (saved_gfp_mask) { + gfp_allowed_mask = saved_gfp_mask; + saved_gfp_mask = 0; + } +} + +void pm_restrict_gfp_mask(void) +{ + WARN_ON(!mutex_is_locked(&system_transition_mutex)); + WARN_ON(saved_gfp_mask); + saved_gfp_mask = gfp_allowed_mask; + gfp_allowed_mask &= ~(__GFP_IO | __GFP_FS); +} + +bool pm_suspended_storage(void) +{ + if ((gfp_allowed_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS)) + return false; + return true; +} +#endif /* CONFIG_PM_SLEEP */ + +#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE +unsigned int pageblock_order __read_mostly; +#endif + +static void __free_pages_ok(struct page *page, unsigned int order, + fpi_t fpi_flags); + +/* + * results with 256, 32 in the lowmem_reserve sysctl: + * 1G machine -> (16M dma, 800M-16M normal, 1G-800M high) + * 1G machine -> (16M dma, 784M normal, 224M high) + * NORMAL allocation will leave 784M/256 of ram reserved in the ZONE_DMA + * HIGHMEM allocation will leave 224M/32 of ram reserved in ZONE_NORMAL + * HIGHMEM allocation will leave (224M+784M)/256 of ram reserved in ZONE_DMA + * + * TBD: should special case ZONE_DMA32 machines here - in those we normally + * don't need any ZONE_NORMAL reservation + */ +int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES] = { +#ifdef CONFIG_ZONE_DMA + [ZONE_DMA] = 256, +#endif +#ifdef CONFIG_ZONE_DMA32 + [ZONE_DMA32] = 256, +#endif + [ZONE_NORMAL] = 32, +#ifdef CONFIG_HIGHMEM + [ZONE_HIGHMEM] = 0, +#endif + [ZONE_MOVABLE] = 0, +}; + +static char * const zone_names[MAX_NR_ZONES] = { +#ifdef CONFIG_ZONE_DMA + "DMA", +#endif +#ifdef CONFIG_ZONE_DMA32 + "DMA32", +#endif + "Normal", +#ifdef CONFIG_HIGHMEM + "HighMem", +#endif + "Movable", +#ifdef CONFIG_ZONE_DEVICE + "Device", +#endif +}; + +const char * const migratetype_names[MIGRATE_TYPES] = { + "Unmovable", + "Movable", + "Reclaimable", + "HighAtomic", +#ifdef CONFIG_CMA + "CMA", +#endif +#ifdef CONFIG_MEMORY_ISOLATION + "Isolate", +#endif +}; + +compound_page_dtor * const compound_page_dtors[NR_COMPOUND_DTORS] = { + [NULL_COMPOUND_DTOR] = NULL, + [COMPOUND_PAGE_DTOR] = free_compound_page, +#ifdef CONFIG_HUGETLB_PAGE + [HUGETLB_PAGE_DTOR] = free_huge_page, +#endif +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + [TRANSHUGE_PAGE_DTOR] = free_transhuge_page, +#endif +}; + +int min_free_kbytes = 1024; +int user_min_free_kbytes = -1; +#ifdef CONFIG_DISCONTIGMEM +/* + * DiscontigMem defines memory ranges as separate pg_data_t even if the ranges + * are not on separate NUMA nodes. Functionally this works but with + * watermark_boost_factor, it can reclaim prematurely as the ranges can be + * quite small. By default, do not boost watermarks on discontigmem as in + * many cases very high-order allocations like THP are likely to be + * unsupported and the premature reclaim offsets the advantage of long-term + * fragmentation avoidance. + */ +int watermark_boost_factor __read_mostly; +#else +int watermark_boost_factor __read_mostly = 15000; +#endif +int watermark_scale_factor = 10; + +static unsigned long nr_kernel_pages __initdata; +static unsigned long nr_all_pages __initdata; +static unsigned long dma_reserve __initdata; + +static unsigned long arch_zone_lowest_possible_pfn[MAX_NR_ZONES] __initdata; +static unsigned long arch_zone_highest_possible_pfn[MAX_NR_ZONES] __initdata; +static unsigned long required_kernelcore __initdata; +static unsigned long required_kernelcore_percent __initdata; +static unsigned long required_movablecore __initdata; +static unsigned long required_movablecore_percent __initdata; +static unsigned long zone_movable_pfn[MAX_NUMNODES] __initdata; +static bool mirrored_kernelcore __meminitdata; + +/* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */ +int movable_zone; +EXPORT_SYMBOL(movable_zone); + +#if MAX_NUMNODES > 1 +unsigned int nr_node_ids __read_mostly = MAX_NUMNODES; +unsigned int nr_online_nodes __read_mostly = 1; +EXPORT_SYMBOL(nr_node_ids); +EXPORT_SYMBOL(nr_online_nodes); +#endif + +int page_group_by_mobility_disabled __read_mostly; + +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT +/* + * During boot we initialize deferred pages on-demand, as needed, but once + * page_alloc_init_late() has finished, the deferred pages are all initialized, + * and we can permanently disable that path. + */ +static DEFINE_STATIC_KEY_TRUE(deferred_pages); + +/* + * Calling kasan_free_pages() only after deferred memory initialization + * has completed. Poisoning pages during deferred memory init will greatly + * lengthen the process and cause problem in large memory systems as the + * deferred pages initialization is done with interrupt disabled. + * + * Assuming that there will be no reference to those newly initialized + * pages before they are ever allocated, this should have no effect on + * KASAN memory tracking as the poison will be properly inserted at page + * allocation time. The only corner case is when pages are allocated by + * on-demand allocation and then freed again before the deferred pages + * initialization is done, but this is not likely to happen. + */ +static inline void kasan_free_nondeferred_pages(struct page *page, int order) +{ + if (!static_branch_unlikely(&deferred_pages)) + kasan_free_pages(page, order); +} + +/* Returns true if the struct page for the pfn is uninitialised */ +static inline bool __meminit early_page_uninitialised(unsigned long pfn) +{ + int nid = early_pfn_to_nid(pfn); + + if (node_online(nid) && pfn >= NODE_DATA(nid)->first_deferred_pfn) + return true; + + return false; +} + +/* + * Returns true when the remaining initialisation should be deferred until + * later in the boot cycle when it can be parallelised. + */ +static bool __meminit +defer_init(int nid, unsigned long pfn, unsigned long end_pfn) +{ + static unsigned long prev_end_pfn, nr_initialised; + + /* + * prev_end_pfn static that contains the end of previous zone + * No need to protect because called very early in boot before smp_init. + */ + if (prev_end_pfn != end_pfn) { + prev_end_pfn = end_pfn; + nr_initialised = 0; + } + + /* Always populate low zones for address-constrained allocations */ + if (end_pfn < pgdat_end_pfn(NODE_DATA(nid))) + return false; + + if (NODE_DATA(nid)->first_deferred_pfn != ULONG_MAX) + return true; + /* + * We start only with one section of pages, more pages are added as + * needed until the rest of deferred pages are initialized. + */ + nr_initialised++; + if ((nr_initialised > PAGES_PER_SECTION) && + (pfn & (PAGES_PER_SECTION - 1)) == 0) { + NODE_DATA(nid)->first_deferred_pfn = pfn; + return true; + } + return false; +} +#else +#define kasan_free_nondeferred_pages(p, o) kasan_free_pages(p, o) + +static inline bool early_page_uninitialised(unsigned long pfn) +{ + return false; +} + +static inline bool defer_init(int nid, unsigned long pfn, unsigned long end_pfn) +{ + return false; +} +#endif + +/* Return a pointer to the bitmap storing bits affecting a block of pages */ +static inline unsigned long *get_pageblock_bitmap(struct page *page, + unsigned long pfn) +{ +#ifdef CONFIG_SPARSEMEM + return section_to_usemap(__pfn_to_section(pfn)); +#else + return page_zone(page)->pageblock_flags; +#endif /* CONFIG_SPARSEMEM */ +} + +static inline int pfn_to_bitidx(struct page *page, unsigned long pfn) +{ +#ifdef CONFIG_SPARSEMEM + pfn &= (PAGES_PER_SECTION-1); +#else + pfn = pfn - round_down(page_zone(page)->zone_start_pfn, pageblock_nr_pages); +#endif /* CONFIG_SPARSEMEM */ + return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS; +} + +/** + * get_pfnblock_flags_mask - Return the requested group of flags for the pageblock_nr_pages block of pages + * @page: The page within the block of interest + * @pfn: The target page frame number + * @mask: mask of bits that the caller is interested in + * + * Return: pageblock_bits flags + */ +static __always_inline +unsigned long __get_pfnblock_flags_mask(struct page *page, + unsigned long pfn, + unsigned long mask) +{ + unsigned long *bitmap; + unsigned long bitidx, word_bitidx; + unsigned long word; + + bitmap = get_pageblock_bitmap(page, pfn); + bitidx = pfn_to_bitidx(page, pfn); + word_bitidx = bitidx / BITS_PER_LONG; + bitidx &= (BITS_PER_LONG-1); + + word = bitmap[word_bitidx]; + return (word >> bitidx) & mask; +} + +unsigned long get_pfnblock_flags_mask(struct page *page, unsigned long pfn, + unsigned long mask) +{ + return __get_pfnblock_flags_mask(page, pfn, mask); +} + +static __always_inline int get_pfnblock_migratetype(struct page *page, unsigned long pfn) +{ + return __get_pfnblock_flags_mask(page, pfn, MIGRATETYPE_MASK); +} + +/** + * set_pfnblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages + * @page: The page within the block of interest + * @flags: The flags to set + * @pfn: The target page frame number + * @mask: mask of bits that the caller is interested in + */ +void set_pfnblock_flags_mask(struct page *page, unsigned long flags, + unsigned long pfn, + unsigned long mask) +{ + unsigned long *bitmap; + unsigned long bitidx, word_bitidx; + unsigned long old_word, word; + + BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4); + BUILD_BUG_ON(MIGRATE_TYPES > (1 << PB_migratetype_bits)); + + bitmap = get_pageblock_bitmap(page, pfn); + bitidx = pfn_to_bitidx(page, pfn); + word_bitidx = bitidx / BITS_PER_LONG; + bitidx &= (BITS_PER_LONG-1); + + VM_BUG_ON_PAGE(!zone_spans_pfn(page_zone(page), pfn), page); + + mask <<= bitidx; + flags <<= bitidx; + + word = READ_ONCE(bitmap[word_bitidx]); + for (;;) { + old_word = cmpxchg(&bitmap[word_bitidx], word, (word & ~mask) | flags); + if (word == old_word) + break; + word = old_word; + } +} + +void set_pageblock_migratetype(struct page *page, int migratetype) +{ + if (unlikely(page_group_by_mobility_disabled && + migratetype < MIGRATE_PCPTYPES)) + migratetype = MIGRATE_UNMOVABLE; + + set_pfnblock_flags_mask(page, (unsigned long)migratetype, + page_to_pfn(page), MIGRATETYPE_MASK); +} + +#ifdef CONFIG_DEBUG_VM +static int page_outside_zone_boundaries(struct zone *zone, struct page *page) +{ + int ret = 0; + unsigned seq; + unsigned long pfn = page_to_pfn(page); + unsigned long sp, start_pfn; + + do { + seq = zone_span_seqbegin(zone); + start_pfn = zone->zone_start_pfn; + sp = zone->spanned_pages; + if (!zone_spans_pfn(zone, pfn)) + ret = 1; + } while (zone_span_seqretry(zone, seq)); + + if (ret) + pr_err("page 0x%lx outside node %d zone %s [ 0x%lx - 0x%lx ]\n", + pfn, zone_to_nid(zone), zone->name, + start_pfn, start_pfn + sp); + + return ret; +} + +static int page_is_consistent(struct zone *zone, struct page *page) +{ + if (!pfn_valid_within(page_to_pfn(page))) + return 0; + if (zone != page_zone(page)) + return 0; + + return 1; +} +/* + * Temporary debugging check for pages not lying within a given zone. + */ +static int __maybe_unused bad_range(struct zone *zone, struct page *page) +{ + if (page_outside_zone_boundaries(zone, page)) + return 1; + if (!page_is_consistent(zone, page)) + return 1; + + return 0; +} +#else +static inline int __maybe_unused bad_range(struct zone *zone, struct page *page) +{ + return 0; +} +#endif + +static void bad_page(struct page *page, const char *reason) +{ + static unsigned long resume; + static unsigned long nr_shown; + static unsigned long nr_unshown; + + /* + * Allow a burst of 60 reports, then keep quiet for that minute; + * or allow a steady drip of one report per second. + */ + if (nr_shown == 60) { + if (time_before(jiffies, resume)) { + nr_unshown++; + goto out; + } + if (nr_unshown) { + pr_alert( + "BUG: Bad page state: %lu messages suppressed\n", + nr_unshown); + nr_unshown = 0; + } + nr_shown = 0; + } + if (nr_shown++ == 0) + resume = jiffies + 60 * HZ; + + pr_alert("BUG: Bad page state in process %s pfn:%05lx\n", + current->comm, page_to_pfn(page)); + __dump_page(page, reason); + dump_page_owner(page); + + print_modules(); + dump_stack(); +out: + /* Leave bad fields for debug, except PageBuddy could make trouble */ + page_mapcount_reset(page); /* remove PageBuddy */ + add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); +} + +/* + * Higher-order pages are called "compound pages". They are structured thusly: + * + * The first PAGE_SIZE page is called the "head page" and have PG_head set. + * + * The remaining PAGE_SIZE pages are called "tail pages". PageTail() is encoded + * in bit 0 of page->compound_head. The rest of bits is pointer to head page. + * + * The first tail page's ->compound_dtor holds the offset in array of compound + * page destructors. See compound_page_dtors. + * + * The first tail page's ->compound_order holds the order of allocation. + * This usage means that zero-order pages may not be compound. + */ + +void free_compound_page(struct page *page) +{ + mem_cgroup_uncharge(page); + __free_pages_ok(page, compound_order(page), FPI_NONE); +} + +void prep_compound_page(struct page *page, unsigned int order) +{ + int i; + int nr_pages = 1 << order; + + __SetPageHead(page); + for (i = 1; i < nr_pages; i++) { + struct page *p = page + i; + set_page_count(p, 0); + p->mapping = TAIL_MAPPING; + set_compound_head(p, page); + } + + set_compound_page_dtor(page, COMPOUND_PAGE_DTOR); + set_compound_order(page, order); + atomic_set(compound_mapcount_ptr(page), -1); + if (hpage_pincount_available(page)) + atomic_set(compound_pincount_ptr(page), 0); +} + +#ifdef CONFIG_DEBUG_PAGEALLOC +unsigned int _debug_guardpage_minorder; + +bool _debug_pagealloc_enabled_early __read_mostly + = IS_ENABLED(CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT); +EXPORT_SYMBOL(_debug_pagealloc_enabled_early); +DEFINE_STATIC_KEY_FALSE(_debug_pagealloc_enabled); +EXPORT_SYMBOL(_debug_pagealloc_enabled); + +DEFINE_STATIC_KEY_FALSE(_debug_guardpage_enabled); + +static int __init early_debug_pagealloc(char *buf) +{ + return kstrtobool(buf, &_debug_pagealloc_enabled_early); +} +early_param("debug_pagealloc", early_debug_pagealloc); + +void init_debug_pagealloc(void) +{ + if (!debug_pagealloc_enabled()) + return; + + static_branch_enable(&_debug_pagealloc_enabled); + + if (!debug_guardpage_minorder()) + return; + + static_branch_enable(&_debug_guardpage_enabled); +} + +static int __init debug_guardpage_minorder_setup(char *buf) +{ + unsigned long res; + + if (kstrtoul(buf, 10, &res) < 0 || res > MAX_ORDER / 2) { + pr_err("Bad debug_guardpage_minorder value\n"); + return 0; + } + _debug_guardpage_minorder = res; + pr_info("Setting debug_guardpage_minorder to %lu\n", res); + return 0; +} +early_param("debug_guardpage_minorder", debug_guardpage_minorder_setup); + +static inline bool set_page_guard(struct zone *zone, struct page *page, + unsigned int order, int migratetype) +{ + if (!debug_guardpage_enabled()) + return false; + + if (order >= debug_guardpage_minorder()) + return false; + + __SetPageGuard(page); + INIT_LIST_HEAD(&page->lru); + set_page_private(page, order); + /* Guard pages are not available for any usage */ + __mod_zone_freepage_state(zone, -(1 << order), migratetype); + + return true; +} + +static inline void clear_page_guard(struct zone *zone, struct page *page, + unsigned int order, int migratetype) +{ + if (!debug_guardpage_enabled()) + return; + + __ClearPageGuard(page); + + set_page_private(page, 0); + if (!is_migrate_isolate(migratetype)) + __mod_zone_freepage_state(zone, (1 << order), migratetype); +} +#else +static inline bool set_page_guard(struct zone *zone, struct page *page, + unsigned int order, int migratetype) { return false; } +static inline void clear_page_guard(struct zone *zone, struct page *page, + unsigned int order, int migratetype) {} +#endif + +static inline void set_buddy_order(struct page *page, unsigned int order) +{ + set_page_private(page, order); + __SetPageBuddy(page); +} + +/* + * This function checks whether a page is free && is the buddy + * we can coalesce a page and its buddy if + * (a) the buddy is not in a hole (check before calling!) && + * (b) the buddy is in the buddy system && + * (c) a page and its buddy have the same order && + * (d) a page and its buddy are in the same zone. + * + * For recording whether a page is in the buddy system, we set PageBuddy. + * Setting, clearing, and testing PageBuddy is serialized by zone->lock. + * + * For recording page's order, we use page_private(page). + */ +static inline bool page_is_buddy(struct page *page, struct page *buddy, + unsigned int order) +{ + if (!page_is_guard(buddy) && !PageBuddy(buddy)) + return false; + + if (buddy_order(buddy) != order) + return false; + + /* + * zone check is done late to avoid uselessly calculating + * zone/node ids for pages that could never merge. + */ + if (page_zone_id(page) != page_zone_id(buddy)) + return false; + + VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); + + return true; +} + +#ifdef CONFIG_COMPACTION +static inline struct capture_control *task_capc(struct zone *zone) +{ + struct capture_control *capc = current->capture_control; + + return unlikely(capc) && + !(current->flags & PF_KTHREAD) && + !capc->page && + capc->cc->zone == zone ? capc : NULL; +} + +static inline bool +compaction_capture(struct capture_control *capc, struct page *page, + int order, int migratetype) +{ + if (!capc || order != capc->cc->order) + return false; + + /* Do not accidentally pollute CMA or isolated regions*/ + if (is_migrate_cma(migratetype) || + is_migrate_isolate(migratetype)) + return false; + + /* + * Do not let lower order allocations polluate a movable pageblock. + * This might let an unmovable request use a reclaimable pageblock + * and vice-versa but no more than normal fallback logic which can + * have trouble finding a high-order free page. + */ + if (order < pageblock_order && migratetype == MIGRATE_MOVABLE) + return false; + + capc->page = page; + return true; +} + +#else +static inline struct capture_control *task_capc(struct zone *zone) +{ + return NULL; +} + +static inline bool +compaction_capture(struct capture_control *capc, struct page *page, + int order, int migratetype) +{ + return false; +} +#endif /* CONFIG_COMPACTION */ + +/* Used for pages not on another list */ +static inline void add_to_free_list(struct page *page, struct zone *zone, + unsigned int order, int migratetype) +{ + struct free_area *area = &zone->free_area[order]; + + list_add(&page->lru, &area->free_list[migratetype]); + area->nr_free++; +} + +/* Used for pages not on another list */ +static inline void add_to_free_list_tail(struct page *page, struct zone *zone, + unsigned int order, int migratetype) +{ + struct free_area *area = &zone->free_area[order]; + + list_add_tail(&page->lru, &area->free_list[migratetype]); + area->nr_free++; +} + +/* + * Used for pages which are on another list. Move the pages to the tail + * of the list - so the moved pages won't immediately be considered for + * allocation again (e.g., optimization for memory onlining). + */ +static inline void move_to_free_list(struct page *page, struct zone *zone, + unsigned int order, int migratetype) +{ + struct free_area *area = &zone->free_area[order]; + + list_move_tail(&page->lru, &area->free_list[migratetype]); +} + +static inline void del_page_from_free_list(struct page *page, struct zone *zone, + unsigned int order) +{ + /* clear reported state and update reported page count */ + if (page_reported(page)) + __ClearPageReported(page); + + list_del(&page->lru); + __ClearPageBuddy(page); + set_page_private(page, 0); + zone->free_area[order].nr_free--; +} + +/* + * If this is not the largest possible page, check if the buddy + * of the next-highest order is free. If it is, it's possible + * that pages are being freed that will coalesce soon. In case, + * that is happening, add the free page to the tail of the list + * so it's less likely to be used soon and more likely to be merged + * as a higher order page + */ +static inline bool +buddy_merge_likely(unsigned long pfn, unsigned long buddy_pfn, + struct page *page, unsigned int order) +{ + struct page *higher_page, *higher_buddy; + unsigned long combined_pfn; + + if (order >= MAX_ORDER - 2) + return false; + + if (!pfn_valid_within(buddy_pfn)) + return false; + + combined_pfn = buddy_pfn & pfn; + higher_page = page + (combined_pfn - pfn); + buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1); + higher_buddy = higher_page + (buddy_pfn - combined_pfn); + + return pfn_valid_within(buddy_pfn) && + page_is_buddy(higher_page, higher_buddy, order + 1); +} + +/* + * Freeing function for a buddy system allocator. + * + * The concept of a buddy system is to maintain direct-mapped table + * (containing bit values) for memory blocks of various "orders". + * The bottom level table contains the map for the smallest allocatable + * units of memory (here, pages), and each level above it describes + * pairs of units from the levels below, hence, "buddies". + * At a high level, all that happens here is marking the table entry + * at the bottom level available, and propagating the changes upward + * as necessary, plus some accounting needed to play nicely with other + * parts of the VM system. + * At each level, we keep a list of pages, which are heads of continuous + * free pages of length of (1 << order) and marked with PageBuddy. + * Page's order is recorded in page_private(page) field. + * So when we are allocating or freeing one, we can derive the state of the + * other. That is, if we allocate a small block, and both were + * free, the remainder of the region must be split into blocks. + * If a block is freed, and its buddy is also free, then this + * triggers coalescing into a block of larger size. + * + * -- nyc + */ + +static inline void __free_one_page(struct page *page, + unsigned long pfn, + struct zone *zone, unsigned int order, + int migratetype, fpi_t fpi_flags) +{ + struct capture_control *capc = task_capc(zone); + unsigned long buddy_pfn; + unsigned long combined_pfn; + unsigned int max_order; + struct page *buddy; + bool to_tail; + + max_order = min_t(unsigned int, MAX_ORDER - 1, pageblock_order); + + VM_BUG_ON(!zone_is_initialized(zone)); + VM_BUG_ON_PAGE(page->flags & PAGE_FLAGS_CHECK_AT_PREP, page); + + VM_BUG_ON(migratetype == -1); + if (likely(!is_migrate_isolate(migratetype))) + __mod_zone_freepage_state(zone, 1 << order, migratetype); + + VM_BUG_ON_PAGE(pfn & ((1 << order) - 1), page); + VM_BUG_ON_PAGE(bad_range(zone, page), page); + +continue_merging: + while (order < max_order) { + if (compaction_capture(capc, page, order, migratetype)) { + __mod_zone_freepage_state(zone, -(1 << order), + migratetype); + return; + } + buddy_pfn = __find_buddy_pfn(pfn, order); + buddy = page + (buddy_pfn - pfn); + + if (!pfn_valid_within(buddy_pfn)) + goto done_merging; + if (!page_is_buddy(page, buddy, order)) + goto done_merging; + /* + * Our buddy is free or it is CONFIG_DEBUG_PAGEALLOC guard page, + * merge with it and move up one order. + */ + if (page_is_guard(buddy)) + clear_page_guard(zone, buddy, order, migratetype); + else + del_page_from_free_list(buddy, zone, order); + combined_pfn = buddy_pfn & pfn; + page = page + (combined_pfn - pfn); + pfn = combined_pfn; + order++; + } + if (order < MAX_ORDER - 1) { + /* If we are here, it means order is >= pageblock_order. + * We want to prevent merge between freepages on isolate + * pageblock and normal pageblock. Without this, pageblock + * isolation could cause incorrect freepage or CMA accounting. + * + * We don't want to hit this code for the more frequent + * low-order merging. + */ + if (unlikely(has_isolate_pageblock(zone))) { + int buddy_mt; + + buddy_pfn = __find_buddy_pfn(pfn, order); + buddy = page + (buddy_pfn - pfn); + buddy_mt = get_pageblock_migratetype(buddy); + + if (migratetype != buddy_mt + && (is_migrate_isolate(migratetype) || + is_migrate_isolate(buddy_mt))) + goto done_merging; + } + max_order = order + 1; + goto continue_merging; + } + +done_merging: + set_buddy_order(page, order); + + if (fpi_flags & FPI_TO_TAIL) + to_tail = true; + else if (is_shuffle_order(order)) + to_tail = shuffle_pick_tail(); + else + to_tail = buddy_merge_likely(pfn, buddy_pfn, page, order); + + if (to_tail) + add_to_free_list_tail(page, zone, order, migratetype); + else + add_to_free_list(page, zone, order, migratetype); + + /* Notify page reporting subsystem of freed page */ + if (!(fpi_flags & FPI_SKIP_REPORT_NOTIFY)) + page_reporting_notify_free(order); +} + +/* + * A bad page could be due to a number of fields. Instead of multiple branches, + * try and check multiple fields with one check. The caller must do a detailed + * check if necessary. + */ +static inline bool page_expected_state(struct page *page, + unsigned long check_flags) +{ + if (unlikely(atomic_read(&page->_mapcount) != -1)) + return false; + + if (unlikely((unsigned long)page->mapping | + page_ref_count(page) | +#ifdef CONFIG_MEMCG + (unsigned long)page->mem_cgroup | +#endif + (page->flags & check_flags))) + return false; + + return true; +} + +static const char *page_bad_reason(struct page *page, unsigned long flags) +{ + const char *bad_reason = NULL; + + if (unlikely(atomic_read(&page->_mapcount) != -1)) + bad_reason = "nonzero mapcount"; + if (unlikely(page->mapping != NULL)) + bad_reason = "non-NULL mapping"; + if (unlikely(page_ref_count(page) != 0)) + bad_reason = "nonzero _refcount"; + if (unlikely(page->flags & flags)) { + if (flags == PAGE_FLAGS_CHECK_AT_PREP) + bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag(s) set"; + else + bad_reason = "PAGE_FLAGS_CHECK_AT_FREE flag(s) set"; + } +#ifdef CONFIG_MEMCG + if (unlikely(page->mem_cgroup)) + bad_reason = "page still charged to cgroup"; +#endif + return bad_reason; +} + +static void check_free_page_bad(struct page *page) +{ + bad_page(page, + page_bad_reason(page, PAGE_FLAGS_CHECK_AT_FREE)); +} + +static inline int check_free_page(struct page *page) +{ + if (likely(page_expected_state(page, PAGE_FLAGS_CHECK_AT_FREE))) + return 0; + + /* Something has gone sideways, find it */ + check_free_page_bad(page); + return 1; +} + +static int free_tail_pages_check(struct page *head_page, struct page *page) +{ + int ret = 1; + + /* + * We rely page->lru.next never has bit 0 set, unless the page + * is PageTail(). Let's make sure that's true even for poisoned ->lru. + */ + BUILD_BUG_ON((unsigned long)LIST_POISON1 & 1); + + if (!IS_ENABLED(CONFIG_DEBUG_VM)) { + ret = 0; + goto out; + } + switch (page - head_page) { + case 1: + /* the first tail page: ->mapping may be compound_mapcount() */ + if (unlikely(compound_mapcount(page))) { + bad_page(page, "nonzero compound_mapcount"); + goto out; + } + break; + case 2: + /* + * the second tail page: ->mapping is + * deferred_list.next -- ignore value. + */ + break; + default: + if (page->mapping != TAIL_MAPPING) { + bad_page(page, "corrupted mapping in tail page"); + goto out; + } + break; + } + if (unlikely(!PageTail(page))) { + bad_page(page, "PageTail not set"); + goto out; + } + if (unlikely(compound_head(page) != head_page)) { + bad_page(page, "compound_head not consistent"); + goto out; + } + ret = 0; +out: + page->mapping = NULL; + clear_compound_head(page); + return ret; +} + +static void kernel_init_free_pages(struct page *page, int numpages) +{ + int i; + + /* s390's use of memset() could override KASAN redzones. */ + kasan_disable_current(); + for (i = 0; i < numpages; i++) + clear_highpage(page + i); + kasan_enable_current(); +} + +static __always_inline bool free_pages_prepare(struct page *page, + unsigned int order, bool check_free) +{ + int bad = 0; + + VM_BUG_ON_PAGE(PageTail(page), page); + + trace_mm_page_free(page, order); + + if (unlikely(PageHWPoison(page)) && !order) { + /* + * Do not let hwpoison pages hit pcplists/buddy + * Untie memcg state and reset page's owner + */ + if (memcg_kmem_enabled() && PageKmemcg(page)) + __memcg_kmem_uncharge_page(page, order); + reset_page_owner(page, order); + return false; + } + + /* + * Check tail pages before head page information is cleared to + * avoid checking PageCompound for order-0 pages. + */ + if (unlikely(order)) { + bool compound = PageCompound(page); + int i; + + VM_BUG_ON_PAGE(compound && compound_order(page) != order, page); + + if (compound) + ClearPageDoubleMap(page); + for (i = 1; i < (1 << order); i++) { + if (compound) + bad += free_tail_pages_check(page, page + i); + if (unlikely(check_free_page(page + i))) { + bad++; + continue; + } + (page + i)->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; + } + } + if (PageMappingFlags(page)) + page->mapping = NULL; + if (memcg_kmem_enabled() && PageKmemcg(page)) + __memcg_kmem_uncharge_page(page, order); + if (check_free) + bad += check_free_page(page); + if (bad) + return false; + + page_cpupid_reset_last(page); + page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; + reset_page_owner(page, order); + + if (!PageHighMem(page)) { + debug_check_no_locks_freed(page_address(page), + PAGE_SIZE << order); + debug_check_no_obj_freed(page_address(page), + PAGE_SIZE << order); + } + if (want_init_on_free()) + kernel_init_free_pages(page, 1 << order); + + kernel_poison_pages(page, 1 << order, 0); + /* + * arch_free_page() can make the page's contents inaccessible. s390 + * does this. So nothing which can access the page's contents should + * happen after this. + */ + arch_free_page(page, order); + + if (debug_pagealloc_enabled_static()) + kernel_map_pages(page, 1 << order, 0); + + kasan_free_nondeferred_pages(page, order); + + return true; +} + +#ifdef CONFIG_DEBUG_VM +/* + * With DEBUG_VM enabled, order-0 pages are checked immediately when being freed + * to pcp lists. With debug_pagealloc also enabled, they are also rechecked when + * moved from pcp lists to free lists. + */ +static bool free_pcp_prepare(struct page *page) +{ + return free_pages_prepare(page, 0, true); +} + +static bool bulkfree_pcp_prepare(struct page *page) +{ + if (debug_pagealloc_enabled_static()) + return check_free_page(page); + else + return false; +} +#else +/* + * With DEBUG_VM disabled, order-0 pages being freed are checked only when + * moving from pcp lists to free list in order to reduce overhead. With + * debug_pagealloc enabled, they are checked also immediately when being freed + * to the pcp lists. + */ +static bool free_pcp_prepare(struct page *page) +{ + if (debug_pagealloc_enabled_static()) + return free_pages_prepare(page, 0, true); + else + return free_pages_prepare(page, 0, false); +} + +static bool bulkfree_pcp_prepare(struct page *page) +{ + return check_free_page(page); +} +#endif /* CONFIG_DEBUG_VM */ + +static inline void prefetch_buddy(struct page *page) +{ + unsigned long pfn = page_to_pfn(page); + unsigned long buddy_pfn = __find_buddy_pfn(pfn, 0); + struct page *buddy = page + (buddy_pfn - pfn); + + prefetch(buddy); +} + +/* + * Frees a number of pages from the PCP lists + * Assumes all pages on list are in same zone, and of same order. + * count is the number of pages to free. + * + * If the zone was previously in an "all pages pinned" state then look to + * see if this freeing clears that state. + * + * And clear the zone's pages_scanned counter, to hold off the "all pages are + * pinned" detection logic. + */ +static void free_pcppages_bulk(struct zone *zone, int count, + struct per_cpu_pages *pcp) +{ + int migratetype = 0; + int batch_free = 0; + int prefetch_nr = 0; + bool isolated_pageblocks; + struct page *page, *tmp; + LIST_HEAD(head); + + /* + * Ensure proper count is passed which otherwise would stuck in the + * below while (list_empty(list)) loop. + */ + count = min(pcp->count, count); + while (count) { + struct list_head *list; + + /* + * Remove pages from lists in a round-robin fashion. A + * batch_free count is maintained that is incremented when an + * empty list is encountered. This is so more pages are freed + * off fuller lists instead of spinning excessively around empty + * lists + */ + do { + batch_free++; + if (++migratetype == MIGRATE_PCPTYPES) + migratetype = 0; + list = &pcp->lists[migratetype]; + } while (list_empty(list)); + + /* This is the only non-empty list. Free them all. */ + if (batch_free == MIGRATE_PCPTYPES) + batch_free = count; + + do { + page = list_last_entry(list, struct page, lru); + /* must delete to avoid corrupting pcp list */ + list_del(&page->lru); + pcp->count--; + + if (bulkfree_pcp_prepare(page)) + continue; + + list_add_tail(&page->lru, &head); + + /* + * We are going to put the page back to the global + * pool, prefetch its buddy to speed up later access + * under zone->lock. It is believed the overhead of + * an additional test and calculating buddy_pfn here + * can be offset by reduced memory latency later. To + * avoid excessive prefetching due to large count, only + * prefetch buddy for the first pcp->batch nr of pages. + */ + if (prefetch_nr++ < pcp->batch) + prefetch_buddy(page); + } while (--count && --batch_free && !list_empty(list)); + } + + spin_lock(&zone->lock); + isolated_pageblocks = has_isolate_pageblock(zone); + + /* + * Use safe version since after __free_one_page(), + * page->lru.next will not point to original list. + */ + list_for_each_entry_safe(page, tmp, &head, lru) { + int mt = get_pcppage_migratetype(page); + /* MIGRATE_ISOLATE page should not go to pcplists */ + VM_BUG_ON_PAGE(is_migrate_isolate(mt), page); + /* Pageblock could have been isolated meanwhile */ + if (unlikely(isolated_pageblocks)) + mt = get_pageblock_migratetype(page); + + __free_one_page(page, page_to_pfn(page), zone, 0, mt, FPI_NONE); + trace_mm_page_pcpu_drain(page, 0, mt); + } + spin_unlock(&zone->lock); +} + +static void free_one_page(struct zone *zone, + struct page *page, unsigned long pfn, + unsigned int order, + int migratetype, fpi_t fpi_flags) +{ + spin_lock(&zone->lock); + if (unlikely(has_isolate_pageblock(zone) || + is_migrate_isolate(migratetype))) { + migratetype = get_pfnblock_migratetype(page, pfn); + } + __free_one_page(page, pfn, zone, order, migratetype, fpi_flags); + spin_unlock(&zone->lock); +} + +static void __meminit __init_single_page(struct page *page, unsigned long pfn, + unsigned long zone, int nid) +{ + mm_zero_struct_page(page); + set_page_links(page, zone, nid, pfn); + init_page_count(page); + page_mapcount_reset(page); + page_cpupid_reset_last(page); + page_kasan_tag_reset(page); + + INIT_LIST_HEAD(&page->lru); +#ifdef WANT_PAGE_VIRTUAL + /* The shift won't overflow because ZONE_NORMAL is below 4G. */ + if (!is_highmem_idx(zone)) + set_page_address(page, __va(pfn << PAGE_SHIFT)); +#endif +} + +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT +static void __meminit init_reserved_page(unsigned long pfn) +{ + pg_data_t *pgdat; + int nid, zid; + + if (!early_page_uninitialised(pfn)) + return; + + nid = early_pfn_to_nid(pfn); + pgdat = NODE_DATA(nid); + + for (zid = 0; zid < MAX_NR_ZONES; zid++) { + struct zone *zone = &pgdat->node_zones[zid]; + + if (pfn >= zone->zone_start_pfn && pfn < zone_end_pfn(zone)) + break; + } + __init_single_page(pfn_to_page(pfn), pfn, zid, nid); +} +#else +static inline void init_reserved_page(unsigned long pfn) +{ +} +#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ + +/* + * Initialised pages do not have PageReserved set. This function is + * called for each range allocated by the bootmem allocator and + * marks the pages PageReserved. The remaining valid pages are later + * sent to the buddy page allocator. + */ +void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end) +{ + unsigned long start_pfn = PFN_DOWN(start); + unsigned long end_pfn = PFN_UP(end); + + for (; start_pfn < end_pfn; start_pfn++) { + if (pfn_valid(start_pfn)) { + struct page *page = pfn_to_page(start_pfn); + + init_reserved_page(start_pfn); + + /* Avoid false-positive PageTail() */ + INIT_LIST_HEAD(&page->lru); + + /* + * no need for atomic set_bit because the struct + * page is not visible yet so nobody should + * access it yet. + */ + __SetPageReserved(page); + } + } +} + +static void __free_pages_ok(struct page *page, unsigned int order, + fpi_t fpi_flags) +{ + unsigned long flags; + int migratetype; + unsigned long pfn = page_to_pfn(page); + + if (!free_pages_prepare(page, order, true)) + return; + + migratetype = get_pfnblock_migratetype(page, pfn); + local_irq_save(flags); + __count_vm_events(PGFREE, 1 << order); + free_one_page(page_zone(page), page, pfn, order, migratetype, + fpi_flags); + local_irq_restore(flags); +} + +void __free_pages_core(struct page *page, unsigned int order) +{ + unsigned int nr_pages = 1 << order; + struct page *p = page; + unsigned int loop; + + /* + * When initializing the memmap, __init_single_page() sets the refcount + * of all pages to 1 ("allocated"/"not free"). We have to set the + * refcount of all involved pages to 0. + */ + prefetchw(p); + for (loop = 0; loop < (nr_pages - 1); loop++, p++) { + prefetchw(p + 1); + __ClearPageReserved(p); + set_page_count(p, 0); + } + __ClearPageReserved(p); + set_page_count(p, 0); + + atomic_long_add(nr_pages, &page_zone(page)->managed_pages); + + /* + * Bypass PCP and place fresh pages right to the tail, primarily + * relevant for memory onlining. + */ + __free_pages_ok(page, order, FPI_TO_TAIL); +} + +#ifdef CONFIG_NEED_MULTIPLE_NODES + +static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata; + +#ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID + +/* + * Required by SPARSEMEM. Given a PFN, return what node the PFN is on. + */ +int __meminit __early_pfn_to_nid(unsigned long pfn, + struct mminit_pfnnid_cache *state) +{ + unsigned long start_pfn, end_pfn; + int nid; + + if (state->last_start <= pfn && pfn < state->last_end) + return state->last_nid; + + nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn); + if (nid != NUMA_NO_NODE) { + state->last_start = start_pfn; + state->last_end = end_pfn; + state->last_nid = nid; + } + + return nid; +} +#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */ + +int __meminit early_pfn_to_nid(unsigned long pfn) +{ + static DEFINE_SPINLOCK(early_pfn_lock); + int nid; + + spin_lock(&early_pfn_lock); + nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache); + if (nid < 0) + nid = first_online_node; + spin_unlock(&early_pfn_lock); + + return nid; +} +#endif /* CONFIG_NEED_MULTIPLE_NODES */ + +void __init memblock_free_pages(struct page *page, unsigned long pfn, + unsigned int order) +{ + if (early_page_uninitialised(pfn)) + return; + __free_pages_core(page, order); +} + +/* + * Check that the whole (or subset of) a pageblock given by the interval of + * [start_pfn, end_pfn) is valid and within the same zone, before scanning it + * with the migration of free compaction scanner. The scanners then need to + * use only pfn_valid_within() check for arches that allow holes within + * pageblocks. + * + * Return struct page pointer of start_pfn, or NULL if checks were not passed. + * + * It's possible on some configurations to have a setup like node0 node1 node0 + * i.e. it's possible that all pages within a zones range of pages do not + * belong to a single zone. We assume that a border between node0 and node1 + * can occur within a single pageblock, but not a node0 node1 node0 + * interleaving within a single pageblock. It is therefore sufficient to check + * the first and last page of a pageblock and avoid checking each individual + * page in a pageblock. + */ +struct page *__pageblock_pfn_to_page(unsigned long start_pfn, + unsigned long end_pfn, struct zone *zone) +{ + struct page *start_page; + struct page *end_page; + + /* end_pfn is one past the range we are checking */ + end_pfn--; + + if (!pfn_valid(start_pfn) || !pfn_valid(end_pfn)) + return NULL; + + start_page = pfn_to_online_page(start_pfn); + if (!start_page) + return NULL; + + if (page_zone(start_page) != zone) + return NULL; + + end_page = pfn_to_page(end_pfn); + + /* This gives a shorter code than deriving page_zone(end_page) */ + if (page_zone_id(start_page) != page_zone_id(end_page)) + return NULL; + + return start_page; +} + +void set_zone_contiguous(struct zone *zone) +{ + unsigned long block_start_pfn = zone->zone_start_pfn; + unsigned long block_end_pfn; + + block_end_pfn = ALIGN(block_start_pfn + 1, pageblock_nr_pages); + for (; block_start_pfn < zone_end_pfn(zone); + block_start_pfn = block_end_pfn, + block_end_pfn += pageblock_nr_pages) { + + block_end_pfn = min(block_end_pfn, zone_end_pfn(zone)); + + if (!__pageblock_pfn_to_page(block_start_pfn, + block_end_pfn, zone)) + return; + cond_resched(); + } + + /* We confirm that there is no hole */ + zone->contiguous = true; +} + +void clear_zone_contiguous(struct zone *zone) +{ + zone->contiguous = false; +} + +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT +static void __init deferred_free_range(unsigned long pfn, + unsigned long nr_pages) +{ + struct page *page; + unsigned long i; + + if (!nr_pages) + return; + + page = pfn_to_page(pfn); + + /* Free a large naturally-aligned chunk if possible */ + if (nr_pages == pageblock_nr_pages && + (pfn & (pageblock_nr_pages - 1)) == 0) { + set_pageblock_migratetype(page, MIGRATE_MOVABLE); + __free_pages_core(page, pageblock_order); + return; + } + + for (i = 0; i < nr_pages; i++, page++, pfn++) { + if ((pfn & (pageblock_nr_pages - 1)) == 0) + set_pageblock_migratetype(page, MIGRATE_MOVABLE); + __free_pages_core(page, 0); + } +} + +/* Completion tracking for deferred_init_memmap() threads */ +static atomic_t pgdat_init_n_undone __initdata; +static __initdata DECLARE_COMPLETION(pgdat_init_all_done_comp); + +static inline void __init pgdat_init_report_one_done(void) +{ + if (atomic_dec_and_test(&pgdat_init_n_undone)) + complete(&pgdat_init_all_done_comp); +} + +/* + * Returns true if page needs to be initialized or freed to buddy allocator. + * + * First we check if pfn is valid on architectures where it is possible to have + * holes within pageblock_nr_pages. On systems where it is not possible, this + * function is optimized out. + * + * Then, we check if a current large page is valid by only checking the validity + * of the head pfn. + */ +static inline bool __init deferred_pfn_valid(unsigned long pfn) +{ + if (!pfn_valid_within(pfn)) + return false; + if (!(pfn & (pageblock_nr_pages - 1)) && !pfn_valid(pfn)) + return false; + return true; +} + +/* + * Free pages to buddy allocator. Try to free aligned pages in + * pageblock_nr_pages sizes. + */ +static void __init deferred_free_pages(unsigned long pfn, + unsigned long end_pfn) +{ + unsigned long nr_pgmask = pageblock_nr_pages - 1; + unsigned long nr_free = 0; + + for (; pfn < end_pfn; pfn++) { + if (!deferred_pfn_valid(pfn)) { + deferred_free_range(pfn - nr_free, nr_free); + nr_free = 0; + } else if (!(pfn & nr_pgmask)) { + deferred_free_range(pfn - nr_free, nr_free); + nr_free = 1; + } else { + nr_free++; + } + } + /* Free the last block of pages to allocator */ + deferred_free_range(pfn - nr_free, nr_free); +} + +/* + * Initialize struct pages. We minimize pfn page lookups and scheduler checks + * by performing it only once every pageblock_nr_pages. + * Return number of pages initialized. + */ +static unsigned long __init deferred_init_pages(struct zone *zone, + unsigned long pfn, + unsigned long end_pfn) +{ + unsigned long nr_pgmask = pageblock_nr_pages - 1; + int nid = zone_to_nid(zone); + unsigned long nr_pages = 0; + int zid = zone_idx(zone); + struct page *page = NULL; + + for (; pfn < end_pfn; pfn++) { + if (!deferred_pfn_valid(pfn)) { + page = NULL; + continue; + } else if (!page || !(pfn & nr_pgmask)) { + page = pfn_to_page(pfn); + } else { + page++; + } + __init_single_page(page, pfn, zid, nid); + nr_pages++; + } + return (nr_pages); +} + +/* + * This function is meant to pre-load the iterator for the zone init. + * Specifically it walks through the ranges until we are caught up to the + * first_init_pfn value and exits there. If we never encounter the value we + * return false indicating there are no valid ranges left. + */ +static bool __init +deferred_init_mem_pfn_range_in_zone(u64 *i, struct zone *zone, + unsigned long *spfn, unsigned long *epfn, + unsigned long first_init_pfn) +{ + u64 j; + + /* + * Start out by walking through the ranges in this zone that have + * already been initialized. We don't need to do anything with them + * so we just need to flush them out of the system. + */ + for_each_free_mem_pfn_range_in_zone(j, zone, spfn, epfn) { + if (*epfn <= first_init_pfn) + continue; + if (*spfn < first_init_pfn) + *spfn = first_init_pfn; + *i = j; + return true; + } + + return false; +} + +/* + * Initialize and free pages. We do it in two loops: first we initialize + * struct page, then free to buddy allocator, because while we are + * freeing pages we can access pages that are ahead (computing buddy + * page in __free_one_page()). + * + * In order to try and keep some memory in the cache we have the loop + * broken along max page order boundaries. This way we will not cause + * any issues with the buddy page computation. + */ +static unsigned long __init +deferred_init_maxorder(u64 *i, struct zone *zone, unsigned long *start_pfn, + unsigned long *end_pfn) +{ + unsigned long mo_pfn = ALIGN(*start_pfn + 1, MAX_ORDER_NR_PAGES); + unsigned long spfn = *start_pfn, epfn = *end_pfn; + unsigned long nr_pages = 0; + u64 j = *i; + + /* First we loop through and initialize the page values */ + for_each_free_mem_pfn_range_in_zone_from(j, zone, start_pfn, end_pfn) { + unsigned long t; + + if (mo_pfn <= *start_pfn) + break; + + t = min(mo_pfn, *end_pfn); + nr_pages += deferred_init_pages(zone, *start_pfn, t); + + if (mo_pfn < *end_pfn) { + *start_pfn = mo_pfn; + break; + } + } + + /* Reset values and now loop through freeing pages as needed */ + swap(j, *i); + + for_each_free_mem_pfn_range_in_zone_from(j, zone, &spfn, &epfn) { + unsigned long t; + + if (mo_pfn <= spfn) + break; + + t = min(mo_pfn, epfn); + deferred_free_pages(spfn, t); + + if (mo_pfn <= epfn) + break; + } + + return nr_pages; +} + +static void __init +deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn, + void *arg) +{ + unsigned long spfn, epfn; + struct zone *zone = arg; + u64 i; + + deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, start_pfn); + + /* + * Initialize and free pages in MAX_ORDER sized increments so that we + * can avoid introducing any issues with the buddy allocator. + */ + while (spfn < end_pfn) { + deferred_init_maxorder(&i, zone, &spfn, &epfn); + cond_resched(); + } +} + +/* An arch may override for more concurrency. */ +__weak int __init +deferred_page_init_max_threads(const struct cpumask *node_cpumask) +{ + return 1; +} + +/* Initialise remaining memory on a node */ +static int __init deferred_init_memmap(void *data) +{ + pg_data_t *pgdat = data; + const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id); + unsigned long spfn = 0, epfn = 0; + unsigned long first_init_pfn, flags; + unsigned long start = jiffies; + struct zone *zone; + int zid, max_threads; + u64 i; + + /* Bind memory initialisation thread to a local node if possible */ + if (!cpumask_empty(cpumask)) + set_cpus_allowed_ptr(current, cpumask); + + pgdat_resize_lock(pgdat, &flags); + first_init_pfn = pgdat->first_deferred_pfn; + if (first_init_pfn == ULONG_MAX) { + pgdat_resize_unlock(pgdat, &flags); + pgdat_init_report_one_done(); + return 0; + } + + /* Sanity check boundaries */ + BUG_ON(pgdat->first_deferred_pfn < pgdat->node_start_pfn); + BUG_ON(pgdat->first_deferred_pfn > pgdat_end_pfn(pgdat)); + pgdat->first_deferred_pfn = ULONG_MAX; + + /* + * Once we unlock here, the zone cannot be grown anymore, thus if an + * interrupt thread must allocate this early in boot, zone must be + * pre-grown prior to start of deferred page initialization. + */ + pgdat_resize_unlock(pgdat, &flags); + + /* Only the highest zone is deferred so find it */ + for (zid = 0; zid < MAX_NR_ZONES; zid++) { + zone = pgdat->node_zones + zid; + if (first_init_pfn < zone_end_pfn(zone)) + break; + } + + /* If the zone is empty somebody else may have cleared out the zone */ + if (!deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, + first_init_pfn)) + goto zone_empty; + + max_threads = deferred_page_init_max_threads(cpumask); + + while (spfn < epfn) { + unsigned long epfn_align = ALIGN(epfn, PAGES_PER_SECTION); + struct padata_mt_job job = { + .thread_fn = deferred_init_memmap_chunk, + .fn_arg = zone, + .start = spfn, + .size = epfn_align - spfn, + .align = PAGES_PER_SECTION, + .min_chunk = PAGES_PER_SECTION, + .max_threads = max_threads, + }; + + padata_do_multithreaded(&job); + deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, + epfn_align); + } +zone_empty: + /* Sanity check that the next zone really is unpopulated */ + WARN_ON(++zid < MAX_NR_ZONES && populated_zone(++zone)); + + pr_info("node %d deferred pages initialised in %ums\n", + pgdat->node_id, jiffies_to_msecs(jiffies - start)); + + pgdat_init_report_one_done(); + return 0; +} + +/* + * If this zone has deferred pages, try to grow it by initializing enough + * deferred pages to satisfy the allocation specified by order, rounded up to + * the nearest PAGES_PER_SECTION boundary. So we're adding memory in increments + * of SECTION_SIZE bytes by initializing struct pages in increments of + * PAGES_PER_SECTION * sizeof(struct page) bytes. + * + * Return true when zone was grown, otherwise return false. We return true even + * when we grow less than requested, to let the caller decide if there are + * enough pages to satisfy the allocation. + * + * Note: We use noinline because this function is needed only during boot, and + * it is called from a __ref function _deferred_grow_zone. This way we are + * making sure that it is not inlined into permanent text section. + */ +static noinline bool __init +deferred_grow_zone(struct zone *zone, unsigned int order) +{ + unsigned long nr_pages_needed = ALIGN(1 << order, PAGES_PER_SECTION); + pg_data_t *pgdat = zone->zone_pgdat; + unsigned long first_deferred_pfn = pgdat->first_deferred_pfn; + unsigned long spfn, epfn, flags; + unsigned long nr_pages = 0; + u64 i; + + /* Only the last zone may have deferred pages */ + if (zone_end_pfn(zone) != pgdat_end_pfn(pgdat)) + return false; + + pgdat_resize_lock(pgdat, &flags); + + /* + * If someone grew this zone while we were waiting for spinlock, return + * true, as there might be enough pages already. + */ + if (first_deferred_pfn != pgdat->first_deferred_pfn) { + pgdat_resize_unlock(pgdat, &flags); + return true; + } + + /* If the zone is empty somebody else may have cleared out the zone */ + if (!deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, + first_deferred_pfn)) { + pgdat->first_deferred_pfn = ULONG_MAX; + pgdat_resize_unlock(pgdat, &flags); + /* Retry only once. */ + return first_deferred_pfn != ULONG_MAX; + } + + /* + * Initialize and free pages in MAX_ORDER sized increments so + * that we can avoid introducing any issues with the buddy + * allocator. + */ + while (spfn < epfn) { + /* update our first deferred PFN for this section */ + first_deferred_pfn = spfn; + + nr_pages += deferred_init_maxorder(&i, zone, &spfn, &epfn); + touch_nmi_watchdog(); + + /* We should only stop along section boundaries */ + if ((first_deferred_pfn ^ spfn) < PAGES_PER_SECTION) + continue; + + /* If our quota has been met we can stop here */ + if (nr_pages >= nr_pages_needed) + break; + } + + pgdat->first_deferred_pfn = spfn; + pgdat_resize_unlock(pgdat, &flags); + + return nr_pages > 0; +} + +/* + * deferred_grow_zone() is __init, but it is called from + * get_page_from_freelist() during early boot until deferred_pages permanently + * disables this call. This is why we have refdata wrapper to avoid warning, + * and to ensure that the function body gets unloaded. + */ +static bool __ref +_deferred_grow_zone(struct zone *zone, unsigned int order) +{ + return deferred_grow_zone(zone, order); +} + +#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ + +void __init page_alloc_init_late(void) +{ + struct zone *zone; + int nid; + +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT + + /* There will be num_node_state(N_MEMORY) threads */ + atomic_set(&pgdat_init_n_undone, num_node_state(N_MEMORY)); + for_each_node_state(nid, N_MEMORY) { + kthread_run(deferred_init_memmap, NODE_DATA(nid), "pgdatinit%d", nid); + } + + /* Block until all are initialised */ + wait_for_completion(&pgdat_init_all_done_comp); + + /* + * The number of managed pages has changed due to the initialisation + * so the pcpu batch and high limits needs to be updated or the limits + * will be artificially small. + */ + for_each_populated_zone(zone) + zone_pcp_update(zone); + + /* + * We initialized the rest of the deferred pages. Permanently disable + * on-demand struct page initialization. + */ + static_branch_disable(&deferred_pages); + + /* Reinit limits that are based on free pages after the kernel is up */ + files_maxfiles_init(); +#endif + + /* Discard memblock private memory */ + memblock_discard(); + + for_each_node_state(nid, N_MEMORY) + shuffle_free_memory(NODE_DATA(nid)); + + for_each_populated_zone(zone) + set_zone_contiguous(zone); +} + +#ifdef CONFIG_CMA +/* Free whole pageblock and set its migration type to MIGRATE_CMA. */ +void __init init_cma_reserved_pageblock(struct page *page) +{ + unsigned i = pageblock_nr_pages; + struct page *p = page; + + do { + __ClearPageReserved(p); + set_page_count(p, 0); + } while (++p, --i); + + set_pageblock_migratetype(page, MIGRATE_CMA); + + if (pageblock_order >= MAX_ORDER) { + i = pageblock_nr_pages; + p = page; + do { + set_page_refcounted(p); + __free_pages(p, MAX_ORDER - 1); + p += MAX_ORDER_NR_PAGES; + } while (i -= MAX_ORDER_NR_PAGES); + } else { + set_page_refcounted(page); + __free_pages(page, pageblock_order); + } + + adjust_managed_page_count(page, pageblock_nr_pages); +} +#endif + +/* + * The order of subdivision here is critical for the IO subsystem. + * Please do not alter this order without good reasons and regression + * testing. Specifically, as large blocks of memory are subdivided, + * the order in which smaller blocks are delivered depends on the order + * they're subdivided in this function. This is the primary factor + * influencing the order in which pages are delivered to the IO + * subsystem according to empirical testing, and this is also justified + * by considering the behavior of a buddy system containing a single + * large block of memory acted on by a series of small allocations. + * This behavior is a critical factor in sglist merging's success. + * + * -- nyc + */ +static inline void expand(struct zone *zone, struct page *page, + int low, int high, int migratetype) +{ + unsigned long size = 1 << high; + + while (high > low) { + high--; + size >>= 1; + VM_BUG_ON_PAGE(bad_range(zone, &page[size]), &page[size]); + + /* + * Mark as guard pages (or page), that will allow to + * merge back to allocator when buddy will be freed. + * Corresponding page table entries will not be touched, + * pages will stay not present in virtual address space + */ + if (set_page_guard(zone, &page[size], high, migratetype)) + continue; + + add_to_free_list(&page[size], zone, high, migratetype); + set_buddy_order(&page[size], high); + } +} + +static void check_new_page_bad(struct page *page) +{ + if (unlikely(page->flags & __PG_HWPOISON)) { + /* Don't complain about hwpoisoned pages */ + page_mapcount_reset(page); /* remove PageBuddy */ + return; + } + + bad_page(page, + page_bad_reason(page, PAGE_FLAGS_CHECK_AT_PREP)); +} + +/* + * This page is about to be returned from the page allocator + */ +static inline int check_new_page(struct page *page) +{ + if (likely(page_expected_state(page, + PAGE_FLAGS_CHECK_AT_PREP|__PG_HWPOISON))) + return 0; + + check_new_page_bad(page); + return 1; +} + +static inline bool free_pages_prezeroed(void) +{ + return (IS_ENABLED(CONFIG_PAGE_POISONING_ZERO) && + page_poisoning_enabled()) || want_init_on_free(); +} + +#ifdef CONFIG_DEBUG_VM +/* + * With DEBUG_VM enabled, order-0 pages are checked for expected state when + * being allocated from pcp lists. With debug_pagealloc also enabled, they are + * also checked when pcp lists are refilled from the free lists. + */ +static inline bool check_pcp_refill(struct page *page) +{ + if (debug_pagealloc_enabled_static()) + return check_new_page(page); + else + return false; +} + +static inline bool check_new_pcp(struct page *page) +{ + return check_new_page(page); +} +#else +/* + * With DEBUG_VM disabled, free order-0 pages are checked for expected state + * when pcp lists are being refilled from the free lists. With debug_pagealloc + * enabled, they are also checked when being allocated from the pcp lists. + */ +static inline bool check_pcp_refill(struct page *page) +{ + return check_new_page(page); +} +static inline bool check_new_pcp(struct page *page) +{ + if (debug_pagealloc_enabled_static()) + return check_new_page(page); + else + return false; +} +#endif /* CONFIG_DEBUG_VM */ + +static bool check_new_pages(struct page *page, unsigned int order) +{ + int i; + for (i = 0; i < (1 << order); i++) { + struct page *p = page + i; + + if (unlikely(check_new_page(p))) + return true; + } + + return false; +} + +inline void post_alloc_hook(struct page *page, unsigned int order, + gfp_t gfp_flags) +{ + set_page_private(page, 0); + set_page_refcounted(page); + + arch_alloc_page(page, order); + if (debug_pagealloc_enabled_static()) + kernel_map_pages(page, 1 << order, 1); + kasan_alloc_pages(page, order); + kernel_poison_pages(page, 1 << order, 1); + set_page_owner(page, order, gfp_flags); +} + +static void prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags, + unsigned int alloc_flags) +{ + post_alloc_hook(page, order, gfp_flags); + + if (!free_pages_prezeroed() && want_init_on_alloc(gfp_flags)) + kernel_init_free_pages(page, 1 << order); + + if (order && (gfp_flags & __GFP_COMP)) + prep_compound_page(page, order); + + /* + * page is set pfmemalloc when ALLOC_NO_WATERMARKS was necessary to + * allocate the page. The expectation is that the caller is taking + * steps that will free more memory. The caller should avoid the page + * being used for !PFMEMALLOC purposes. + */ + if (alloc_flags & ALLOC_NO_WATERMARKS) + set_page_pfmemalloc(page); + else + clear_page_pfmemalloc(page); +} + +/* + * Go through the free lists for the given migratetype and remove + * the smallest available page from the freelists + */ +static __always_inline +struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, + int migratetype) +{ + unsigned int current_order; + struct free_area *area; + struct page *page; + + /* Find a page of the appropriate size in the preferred list */ + for (current_order = order; current_order < MAX_ORDER; ++current_order) { + area = &(zone->free_area[current_order]); + page = get_page_from_free_area(area, migratetype); + if (!page) + continue; + del_page_from_free_list(page, zone, current_order); + expand(zone, page, order, current_order, migratetype); + set_pcppage_migratetype(page, migratetype); + return page; + } + + return NULL; +} + + +/* + * This array describes the order lists are fallen back to when + * the free lists for the desirable migrate type are depleted + */ +static int fallbacks[MIGRATE_TYPES][3] = { + [MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE, MIGRATE_TYPES }, + [MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_TYPES }, + [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_TYPES }, +#ifdef CONFIG_CMA + [MIGRATE_CMA] = { MIGRATE_TYPES }, /* Never used */ +#endif +#ifdef CONFIG_MEMORY_ISOLATION + [MIGRATE_ISOLATE] = { MIGRATE_TYPES }, /* Never used */ +#endif +}; + +#ifdef CONFIG_CMA +static __always_inline struct page *__rmqueue_cma_fallback(struct zone *zone, + unsigned int order) +{ + return __rmqueue_smallest(zone, order, MIGRATE_CMA); +} +#else +static inline struct page *__rmqueue_cma_fallback(struct zone *zone, + unsigned int order) { return NULL; } +#endif + +/* + * Move the free pages in a range to the freelist tail of the requested type. + * Note that start_page and end_pages are not aligned on a pageblock + * boundary. If alignment is required, use move_freepages_block() + */ +static int move_freepages(struct zone *zone, + struct page *start_page, struct page *end_page, + int migratetype, int *num_movable) +{ + struct page *page; + unsigned int order; + int pages_moved = 0; + + for (page = start_page; page <= end_page;) { + if (!pfn_valid_within(page_to_pfn(page))) { + page++; + continue; + } + + if (!PageBuddy(page)) { + /* + * We assume that pages that could be isolated for + * migration are movable. But we don't actually try + * isolating, as that would be expensive. + */ + if (num_movable && + (PageLRU(page) || __PageMovable(page))) + (*num_movable)++; + + page++; + continue; + } + + /* Make sure we are not inadvertently changing nodes */ + VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page); + VM_BUG_ON_PAGE(page_zone(page) != zone, page); + + order = buddy_order(page); + move_to_free_list(page, zone, order, migratetype); + page += 1 << order; + pages_moved += 1 << order; + } + + return pages_moved; +} + +int move_freepages_block(struct zone *zone, struct page *page, + int migratetype, int *num_movable) +{ + unsigned long start_pfn, end_pfn; + struct page *start_page, *end_page; + + if (num_movable) + *num_movable = 0; + + start_pfn = page_to_pfn(page); + start_pfn = start_pfn & ~(pageblock_nr_pages-1); + start_page = pfn_to_page(start_pfn); + end_page = start_page + pageblock_nr_pages - 1; + end_pfn = start_pfn + pageblock_nr_pages - 1; + + /* Do not cross zone boundaries */ + if (!zone_spans_pfn(zone, start_pfn)) + start_page = page; + if (!zone_spans_pfn(zone, end_pfn)) + return 0; + + return move_freepages(zone, start_page, end_page, migratetype, + num_movable); +} + +static void change_pageblock_range(struct page *pageblock_page, + int start_order, int migratetype) +{ + int nr_pageblocks = 1 << (start_order - pageblock_order); + + while (nr_pageblocks--) { + set_pageblock_migratetype(pageblock_page, migratetype); + pageblock_page += pageblock_nr_pages; + } +} + +/* + * When we are falling back to another migratetype during allocation, try to + * steal extra free pages from the same pageblocks to satisfy further + * allocations, instead of polluting multiple pageblocks. + * + * If we are stealing a relatively large buddy page, it is likely there will + * be more free pages in the pageblock, so try to steal them all. For + * reclaimable and unmovable allocations, we steal regardless of page size, + * as fragmentation caused by those allocations polluting movable pageblocks + * is worse than movable allocations stealing from unmovable and reclaimable + * pageblocks. + */ +static bool can_steal_fallback(unsigned int order, int start_mt) +{ + /* + * Leaving this order check is intended, although there is + * relaxed order check in next check. The reason is that + * we can actually steal whole pageblock if this condition met, + * but, below check doesn't guarantee it and that is just heuristic + * so could be changed anytime. + */ + if (order >= pageblock_order) + return true; + + if (order >= pageblock_order / 2 || + start_mt == MIGRATE_RECLAIMABLE || + start_mt == MIGRATE_UNMOVABLE || + page_group_by_mobility_disabled) + return true; + + return false; +} + +static inline bool boost_watermark(struct zone *zone) +{ + unsigned long max_boost; + + if (!watermark_boost_factor) + return false; + /* + * Don't bother in zones that are unlikely to produce results. + * On small machines, including kdump capture kernels running + * in a small area, boosting the watermark can cause an out of + * memory situation immediately. + */ + if ((pageblock_nr_pages * 4) > zone_managed_pages(zone)) + return false; + + max_boost = mult_frac(zone->_watermark[WMARK_HIGH], + watermark_boost_factor, 10000); + + /* + * high watermark may be uninitialised if fragmentation occurs + * very early in boot so do not boost. We do not fall + * through and boost by pageblock_nr_pages as failing + * allocations that early means that reclaim is not going + * to help and it may even be impossible to reclaim the + * boosted watermark resulting in a hang. + */ + if (!max_boost) + return false; + + max_boost = max(pageblock_nr_pages, max_boost); + + zone->watermark_boost = min(zone->watermark_boost + pageblock_nr_pages, + max_boost); + + return true; +} + +/* + * This function implements actual steal behaviour. If order is large enough, + * we can steal whole pageblock. If not, we first move freepages in this + * pageblock to our migratetype and determine how many already-allocated pages + * are there in the pageblock with a compatible migratetype. If at least half + * of pages are free or compatible, we can change migratetype of the pageblock + * itself, so pages freed in the future will be put on the correct free list. + */ +static void steal_suitable_fallback(struct zone *zone, struct page *page, + unsigned int alloc_flags, int start_type, bool whole_block) +{ + unsigned int current_order = buddy_order(page); + int free_pages, movable_pages, alike_pages; + int old_block_type; + + old_block_type = get_pageblock_migratetype(page); + + /* + * This can happen due to races and we want to prevent broken + * highatomic accounting. + */ + if (is_migrate_highatomic(old_block_type)) + goto single_page; + + /* Take ownership for orders >= pageblock_order */ + if (current_order >= pageblock_order) { + change_pageblock_range(page, current_order, start_type); + goto single_page; + } + + /* + * Boost watermarks to increase reclaim pressure to reduce the + * likelihood of future fallbacks. Wake kswapd now as the node + * may be balanced overall and kswapd will not wake naturally. + */ + if (boost_watermark(zone) && (alloc_flags & ALLOC_KSWAPD)) + set_bit(ZONE_BOOSTED_WATERMARK, &zone->flags); + + /* We are not allowed to try stealing from the whole block */ + if (!whole_block) + goto single_page; + + free_pages = move_freepages_block(zone, page, start_type, + &movable_pages); + /* + * Determine how many pages are compatible with our allocation. + * For movable allocation, it's the number of movable pages which + * we just obtained. For other types it's a bit more tricky. + */ + if (start_type == MIGRATE_MOVABLE) { + alike_pages = movable_pages; + } else { + /* + * If we are falling back a RECLAIMABLE or UNMOVABLE allocation + * to MOVABLE pageblock, consider all non-movable pages as + * compatible. If it's UNMOVABLE falling back to RECLAIMABLE or + * vice versa, be conservative since we can't distinguish the + * exact migratetype of non-movable pages. + */ + if (old_block_type == MIGRATE_MOVABLE) + alike_pages = pageblock_nr_pages + - (free_pages + movable_pages); + else + alike_pages = 0; + } + + /* moving whole block can fail due to zone boundary conditions */ + if (!free_pages) + goto single_page; + + /* + * If a sufficient number of pages in the block are either free or of + * comparable migratability as our allocation, claim the whole block. + */ + if (free_pages + alike_pages >= (1 << (pageblock_order-1)) || + page_group_by_mobility_disabled) + set_pageblock_migratetype(page, start_type); + + return; + +single_page: + move_to_free_list(page, zone, current_order, start_type); +} + +/* + * Check whether there is a suitable fallback freepage with requested order. + * If only_stealable is true, this function returns fallback_mt only if + * we can steal other freepages all together. This would help to reduce + * fragmentation due to mixed migratetype pages in one pageblock. + */ +int find_suitable_fallback(struct free_area *area, unsigned int order, + int migratetype, bool only_stealable, bool *can_steal) +{ + int i; + int fallback_mt; + + if (area->nr_free == 0) + return -1; + + *can_steal = false; + for (i = 0;; i++) { + fallback_mt = fallbacks[migratetype][i]; + if (fallback_mt == MIGRATE_TYPES) + break; + + if (free_area_empty(area, fallback_mt)) + continue; + + if (can_steal_fallback(order, migratetype)) + *can_steal = true; + + if (!only_stealable) + return fallback_mt; + + if (*can_steal) + return fallback_mt; + } + + return -1; +} + +/* + * Reserve a pageblock for exclusive use of high-order atomic allocations if + * there are no empty page blocks that contain a page with a suitable order + */ +static void reserve_highatomic_pageblock(struct page *page, struct zone *zone, + unsigned int alloc_order) +{ + int mt; + unsigned long max_managed, flags; + + /* + * Limit the number reserved to 1 pageblock or roughly 1% of a zone. + * Check is race-prone but harmless. + */ + max_managed = (zone_managed_pages(zone) / 100) + pageblock_nr_pages; + if (zone->nr_reserved_highatomic >= max_managed) + return; + + spin_lock_irqsave(&zone->lock, flags); + + /* Recheck the nr_reserved_highatomic limit under the lock */ + if (zone->nr_reserved_highatomic >= max_managed) + goto out_unlock; + + /* Yoink! */ + mt = get_pageblock_migratetype(page); + if (!is_migrate_highatomic(mt) && !is_migrate_isolate(mt) + && !is_migrate_cma(mt)) { + zone->nr_reserved_highatomic += pageblock_nr_pages; + set_pageblock_migratetype(page, MIGRATE_HIGHATOMIC); + move_freepages_block(zone, page, MIGRATE_HIGHATOMIC, NULL); + } + +out_unlock: + spin_unlock_irqrestore(&zone->lock, flags); +} + +/* + * Used when an allocation is about to fail under memory pressure. This + * potentially hurts the reliability of high-order allocations when under + * intense memory pressure but failed atomic allocations should be easier + * to recover from than an OOM. + * + * If @force is true, try to unreserve a pageblock even though highatomic + * pageblock is exhausted. + */ +static bool unreserve_highatomic_pageblock(const struct alloc_context *ac, + bool force) +{ + struct zonelist *zonelist = ac->zonelist; + unsigned long flags; + struct zoneref *z; + struct zone *zone; + struct page *page; + int order; + bool ret; + + for_each_zone_zonelist_nodemask(zone, z, zonelist, ac->highest_zoneidx, + ac->nodemask) { + /* + * Preserve at least one pageblock unless memory pressure + * is really high. + */ + if (!force && zone->nr_reserved_highatomic <= + pageblock_nr_pages) + continue; + + spin_lock_irqsave(&zone->lock, flags); + for (order = 0; order < MAX_ORDER; order++) { + struct free_area *area = &(zone->free_area[order]); + + page = get_page_from_free_area(area, MIGRATE_HIGHATOMIC); + if (!page) + continue; + + /* + * In page freeing path, migratetype change is racy so + * we can counter several free pages in a pageblock + * in this loop althoug we changed the pageblock type + * from highatomic to ac->migratetype. So we should + * adjust the count once. + */ + if (is_migrate_highatomic_page(page)) { + /* + * It should never happen but changes to + * locking could inadvertently allow a per-cpu + * drain to add pages to MIGRATE_HIGHATOMIC + * while unreserving so be safe and watch for + * underflows. + */ + zone->nr_reserved_highatomic -= min( + pageblock_nr_pages, + zone->nr_reserved_highatomic); + } + + /* + * Convert to ac->migratetype and avoid the normal + * pageblock stealing heuristics. Minimally, the caller + * is doing the work and needs the pages. More + * importantly, if the block was always converted to + * MIGRATE_UNMOVABLE or another type then the number + * of pageblocks that cannot be completely freed + * may increase. + */ + set_pageblock_migratetype(page, ac->migratetype); + ret = move_freepages_block(zone, page, ac->migratetype, + NULL); + if (ret) { + spin_unlock_irqrestore(&zone->lock, flags); + return ret; + } + } + spin_unlock_irqrestore(&zone->lock, flags); + } + + return false; +} + +/* + * Try finding a free buddy page on the fallback list and put it on the free + * list of requested migratetype, possibly along with other pages from the same + * block, depending on fragmentation avoidance heuristics. Returns true if + * fallback was found so that __rmqueue_smallest() can grab it. + * + * The use of signed ints for order and current_order is a deliberate + * deviation from the rest of this file, to make the for loop + * condition simpler. + */ +static __always_inline bool +__rmqueue_fallback(struct zone *zone, int order, int start_migratetype, + unsigned int alloc_flags) +{ + struct free_area *area; + int current_order; + int min_order = order; + struct page *page; + int fallback_mt; + bool can_steal; + + /* + * Do not steal pages from freelists belonging to other pageblocks + * i.e. orders < pageblock_order. If there are no local zones free, + * the zonelists will be reiterated without ALLOC_NOFRAGMENT. + */ + if (alloc_flags & ALLOC_NOFRAGMENT) + min_order = pageblock_order; + + /* + * Find the largest available free page in the other list. This roughly + * approximates finding the pageblock with the most free pages, which + * would be too costly to do exactly. + */ + for (current_order = MAX_ORDER - 1; current_order >= min_order; + --current_order) { + area = &(zone->free_area[current_order]); + fallback_mt = find_suitable_fallback(area, current_order, + start_migratetype, false, &can_steal); + if (fallback_mt == -1) + continue; + + /* + * We cannot steal all free pages from the pageblock and the + * requested migratetype is movable. In that case it's better to + * steal and split the smallest available page instead of the + * largest available page, because even if the next movable + * allocation falls back into a different pageblock than this + * one, it won't cause permanent fragmentation. + */ + if (!can_steal && start_migratetype == MIGRATE_MOVABLE + && current_order > order) + goto find_smallest; + + goto do_steal; + } + + return false; + +find_smallest: + for (current_order = order; current_order < MAX_ORDER; + current_order++) { + area = &(zone->free_area[current_order]); + fallback_mt = find_suitable_fallback(area, current_order, + start_migratetype, false, &can_steal); + if (fallback_mt != -1) + break; + } + + /* + * This should not happen - we already found a suitable fallback + * when looking for the largest page. + */ + VM_BUG_ON(current_order == MAX_ORDER); + +do_steal: + page = get_page_from_free_area(area, fallback_mt); + + steal_suitable_fallback(zone, page, alloc_flags, start_migratetype, + can_steal); + + trace_mm_page_alloc_extfrag(page, order, current_order, + start_migratetype, fallback_mt); + + return true; + +} + +/* + * Do the hard work of removing an element from the buddy allocator. + * Call me with the zone->lock already held. + */ +static __always_inline struct page * +__rmqueue(struct zone *zone, unsigned int order, int migratetype, + unsigned int alloc_flags) +{ + struct page *page; + + if (IS_ENABLED(CONFIG_CMA)) { + /* + * Balance movable allocations between regular and CMA areas by + * allocating from CMA when over half of the zone's free memory + * is in the CMA area. + */ + if (alloc_flags & ALLOC_CMA && + zone_page_state(zone, NR_FREE_CMA_PAGES) > + zone_page_state(zone, NR_FREE_PAGES) / 2) { + page = __rmqueue_cma_fallback(zone, order); + if (page) + goto out; + } + } +retry: + page = __rmqueue_smallest(zone, order, migratetype); + if (unlikely(!page)) { + if (alloc_flags & ALLOC_CMA) + page = __rmqueue_cma_fallback(zone, order); + + if (!page && __rmqueue_fallback(zone, order, migratetype, + alloc_flags)) + goto retry; + } +out: + if (page) + trace_mm_page_alloc_zone_locked(page, order, migratetype); + return page; +} + +/* + * Obtain a specified number of elements from the buddy allocator, all under + * a single hold of the lock, for efficiency. Add them to the supplied list. + * Returns the number of new pages which were placed at *list. + */ +static int rmqueue_bulk(struct zone *zone, unsigned int order, + unsigned long count, struct list_head *list, + int migratetype, unsigned int alloc_flags) +{ + int i, alloced = 0; + + spin_lock(&zone->lock); + for (i = 0; i < count; ++i) { + struct page *page = __rmqueue(zone, order, migratetype, + alloc_flags); + if (unlikely(page == NULL)) + break; + + if (unlikely(check_pcp_refill(page))) + continue; + + /* + * Split buddy pages returned by expand() are received here in + * physical page order. The page is added to the tail of + * caller's list. From the callers perspective, the linked list + * is ordered by page number under some conditions. This is + * useful for IO devices that can forward direction from the + * head, thus also in the physical page order. This is useful + * for IO devices that can merge IO requests if the physical + * pages are ordered properly. + */ + list_add_tail(&page->lru, list); + alloced++; + if (is_migrate_cma(get_pcppage_migratetype(page))) + __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, + -(1 << order)); + } + + /* + * i pages were removed from the buddy list even if some leak due + * to check_pcp_refill failing so adjust NR_FREE_PAGES based + * on i. Do not confuse with 'alloced' which is the number of + * pages added to the pcp list. + */ + __mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order)); + spin_unlock(&zone->lock); + return alloced; +} + +#ifdef CONFIG_NUMA +/* + * Called from the vmstat counter updater to drain pagesets of this + * currently executing processor on remote nodes after they have + * expired. + * + * Note that this function must be called with the thread pinned to + * a single processor. + */ +void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) +{ + unsigned long flags; + int to_drain, batch; + + local_irq_save(flags); + batch = READ_ONCE(pcp->batch); + to_drain = min(pcp->count, batch); + if (to_drain > 0) + free_pcppages_bulk(zone, to_drain, pcp); + local_irq_restore(flags); +} +#endif + +/* + * Drain pcplists of the indicated processor and zone. + * + * The processor must either be the current processor and the + * thread pinned to the current processor or a processor that + * is not online. + */ +static void drain_pages_zone(unsigned int cpu, struct zone *zone) +{ + unsigned long flags; + struct per_cpu_pageset *pset; + struct per_cpu_pages *pcp; + + local_irq_save(flags); + pset = per_cpu_ptr(zone->pageset, cpu); + + pcp = &pset->pcp; + if (pcp->count) + free_pcppages_bulk(zone, pcp->count, pcp); + local_irq_restore(flags); +} + +/* + * Drain pcplists of all zones on the indicated processor. + * + * The processor must either be the current processor and the + * thread pinned to the current processor or a processor that + * is not online. + */ +static void drain_pages(unsigned int cpu) +{ + struct zone *zone; + + for_each_populated_zone(zone) { + drain_pages_zone(cpu, zone); + } +} + +/* + * Spill all of this CPU's per-cpu pages back into the buddy allocator. + * + * The CPU has to be pinned. When zone parameter is non-NULL, spill just + * the single zone's pages. + */ +void drain_local_pages(struct zone *zone) +{ + int cpu = smp_processor_id(); + + if (zone) + drain_pages_zone(cpu, zone); + else + drain_pages(cpu); +} + +static void drain_local_pages_wq(struct work_struct *work) +{ + struct pcpu_drain *drain; + + drain = container_of(work, struct pcpu_drain, work); + + /* + * drain_all_pages doesn't use proper cpu hotplug protection so + * we can race with cpu offline when the WQ can move this from + * a cpu pinned worker to an unbound one. We can operate on a different + * cpu which is allright but we also have to make sure to not move to + * a different one. + */ + preempt_disable(); + drain_local_pages(drain->zone); + preempt_enable(); +} + +/* + * Spill all the per-cpu pages from all CPUs back into the buddy allocator. + * + * When zone parameter is non-NULL, spill just the single zone's pages. + * + * Note that this can be extremely slow as the draining happens in a workqueue. + */ +void drain_all_pages(struct zone *zone) +{ + int cpu; + + /* + * Allocate in the BSS so we wont require allocation in + * direct reclaim path for CONFIG_CPUMASK_OFFSTACK=y + */ + static cpumask_t cpus_with_pcps; + + /* + * Make sure nobody triggers this path before mm_percpu_wq is fully + * initialized. + */ + if (WARN_ON_ONCE(!mm_percpu_wq)) + return; + + /* + * Do not drain if one is already in progress unless it's specific to + * a zone. Such callers are primarily CMA and memory hotplug and need + * the drain to be complete when the call returns. + */ + if (unlikely(!mutex_trylock(&pcpu_drain_mutex))) { + if (!zone) + return; + mutex_lock(&pcpu_drain_mutex); + } + + /* + * We don't care about racing with CPU hotplug event + * as offline notification will cause the notified + * cpu to drain that CPU pcps and on_each_cpu_mask + * disables preemption as part of its processing + */ + for_each_online_cpu(cpu) { + struct per_cpu_pageset *pcp; + struct zone *z; + bool has_pcps = false; + + if (zone) { + pcp = per_cpu_ptr(zone->pageset, cpu); + if (pcp->pcp.count) + has_pcps = true; + } else { + for_each_populated_zone(z) { + pcp = per_cpu_ptr(z->pageset, cpu); + if (pcp->pcp.count) { + has_pcps = true; + break; + } + } + } + + if (has_pcps) + cpumask_set_cpu(cpu, &cpus_with_pcps); + else + cpumask_clear_cpu(cpu, &cpus_with_pcps); + } + + for_each_cpu(cpu, &cpus_with_pcps) { + struct pcpu_drain *drain = per_cpu_ptr(&pcpu_drain, cpu); + + drain->zone = zone; + INIT_WORK(&drain->work, drain_local_pages_wq); + queue_work_on(cpu, mm_percpu_wq, &drain->work); + } + for_each_cpu(cpu, &cpus_with_pcps) + flush_work(&per_cpu_ptr(&pcpu_drain, cpu)->work); + + mutex_unlock(&pcpu_drain_mutex); +} + +#ifdef CONFIG_HIBERNATION + +/* + * Touch the watchdog for every WD_PAGE_COUNT pages. + */ +#define WD_PAGE_COUNT (128*1024) + +void mark_free_pages(struct zone *zone) +{ + unsigned long pfn, max_zone_pfn, page_count = WD_PAGE_COUNT; + unsigned long flags; + unsigned int order, t; + struct page *page; + + if (zone_is_empty(zone)) + return; + + spin_lock_irqsave(&zone->lock, flags); + + max_zone_pfn = zone_end_pfn(zone); + for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) + if (pfn_valid(pfn)) { + page = pfn_to_page(pfn); + + if (!--page_count) { + touch_nmi_watchdog(); + page_count = WD_PAGE_COUNT; + } + + if (page_zone(page) != zone) + continue; + + if (!swsusp_page_is_forbidden(page)) + swsusp_unset_page_free(page); + } + + for_each_migratetype_order(order, t) { + list_for_each_entry(page, + &zone->free_area[order].free_list[t], lru) { + unsigned long i; + + pfn = page_to_pfn(page); + for (i = 0; i < (1UL << order); i++) { + if (!--page_count) { + touch_nmi_watchdog(); + page_count = WD_PAGE_COUNT; + } + swsusp_set_page_free(pfn_to_page(pfn + i)); + } + } + } + spin_unlock_irqrestore(&zone->lock, flags); +} +#endif /* CONFIG_PM */ + +static bool free_unref_page_prepare(struct page *page, unsigned long pfn) +{ + int migratetype; + + if (!free_pcp_prepare(page)) + return false; + + migratetype = get_pfnblock_migratetype(page, pfn); + set_pcppage_migratetype(page, migratetype); + return true; +} + +static void free_unref_page_commit(struct page *page, unsigned long pfn) +{ + struct zone *zone = page_zone(page); + struct per_cpu_pages *pcp; + int migratetype; + + migratetype = get_pcppage_migratetype(page); + __count_vm_event(PGFREE); + + /* + * We only track unmovable, reclaimable and movable on pcp lists. + * Free ISOLATE pages back to the allocator because they are being + * offlined but treat HIGHATOMIC as movable pages so we can get those + * areas back if necessary. Otherwise, we may have to free + * excessively into the page allocator + */ + if (migratetype >= MIGRATE_PCPTYPES) { + if (unlikely(is_migrate_isolate(migratetype))) { + free_one_page(zone, page, pfn, 0, migratetype, + FPI_NONE); + return; + } + migratetype = MIGRATE_MOVABLE; + } + + pcp = &this_cpu_ptr(zone->pageset)->pcp; + list_add(&page->lru, &pcp->lists[migratetype]); + pcp->count++; + if (pcp->count >= pcp->high) { + unsigned long batch = READ_ONCE(pcp->batch); + free_pcppages_bulk(zone, batch, pcp); + } +} + +/* + * Free a 0-order page + */ +void free_unref_page(struct page *page) +{ + unsigned long flags; + unsigned long pfn = page_to_pfn(page); + + if (!free_unref_page_prepare(page, pfn)) + return; + + local_irq_save(flags); + free_unref_page_commit(page, pfn); + local_irq_restore(flags); +} + +/* + * Free a list of 0-order pages + */ +void free_unref_page_list(struct list_head *list) +{ + struct page *page, *next; + unsigned long flags, pfn; + int batch_count = 0; + + /* Prepare pages for freeing */ + list_for_each_entry_safe(page, next, list, lru) { + pfn = page_to_pfn(page); + if (!free_unref_page_prepare(page, pfn)) + list_del(&page->lru); + set_page_private(page, pfn); + } + + local_irq_save(flags); + list_for_each_entry_safe(page, next, list, lru) { + unsigned long pfn = page_private(page); + + set_page_private(page, 0); + trace_mm_page_free_batched(page); + free_unref_page_commit(page, pfn); + + /* + * Guard against excessive IRQ disabled times when we get + * a large list of pages to free. + */ + if (++batch_count == SWAP_CLUSTER_MAX) { + local_irq_restore(flags); + batch_count = 0; + local_irq_save(flags); + } + } + local_irq_restore(flags); +} + +/* + * split_page takes a non-compound higher-order page, and splits it into + * n (1<_watermark[WMARK_MIN] + (1UL << order); + if (!zone_watermark_ok(zone, 0, watermark, 0, ALLOC_CMA)) + return 0; + + __mod_zone_freepage_state(zone, -(1UL << order), mt); + } + + /* Remove page from free list */ + + del_page_from_free_list(page, zone, order); + + /* + * Set the pageblock if the isolated page is at least half of a + * pageblock + */ + if (order >= pageblock_order - 1) { + struct page *endpage = page + (1 << order) - 1; + for (; page < endpage; page += pageblock_nr_pages) { + int mt = get_pageblock_migratetype(page); + if (!is_migrate_isolate(mt) && !is_migrate_cma(mt) + && !is_migrate_highatomic(mt)) + set_pageblock_migratetype(page, + MIGRATE_MOVABLE); + } + } + + + return 1UL << order; +} + +/** + * __putback_isolated_page - Return a now-isolated page back where we got it + * @page: Page that was isolated + * @order: Order of the isolated page + * @mt: The page's pageblock's migratetype + * + * This function is meant to return a page pulled from the free lists via + * __isolate_free_page back to the free lists they were pulled from. + */ +void __putback_isolated_page(struct page *page, unsigned int order, int mt) +{ + struct zone *zone = page_zone(page); + + /* zone lock should be held when this function is called */ + lockdep_assert_held(&zone->lock); + + /* Return isolated page to tail of freelist. */ + __free_one_page(page, page_to_pfn(page), zone, order, mt, + FPI_SKIP_REPORT_NOTIFY | FPI_TO_TAIL); +} + +/* + * Update NUMA hit/miss statistics + * + * Must be called with interrupts disabled. + */ +static inline void zone_statistics(struct zone *preferred_zone, struct zone *z) +{ +#ifdef CONFIG_NUMA + enum numa_stat_item local_stat = NUMA_LOCAL; + + /* skip numa counters update if numa stats is disabled */ + if (!static_branch_likely(&vm_numa_stat_key)) + return; + + if (zone_to_nid(z) != numa_node_id()) + local_stat = NUMA_OTHER; + + if (zone_to_nid(z) == zone_to_nid(preferred_zone)) + __inc_numa_state(z, NUMA_HIT); + else { + __inc_numa_state(z, NUMA_MISS); + __inc_numa_state(preferred_zone, NUMA_FOREIGN); + } + __inc_numa_state(z, local_stat); +#endif +} + +/* Remove page from the per-cpu list, caller must protect the list */ +static struct page *__rmqueue_pcplist(struct zone *zone, int migratetype, + unsigned int alloc_flags, + struct per_cpu_pages *pcp, + struct list_head *list) +{ + struct page *page; + + do { + if (list_empty(list)) { + pcp->count += rmqueue_bulk(zone, 0, + pcp->batch, list, + migratetype, alloc_flags); + if (unlikely(list_empty(list))) + return NULL; + } + + page = list_first_entry(list, struct page, lru); + list_del(&page->lru); + pcp->count--; + } while (check_new_pcp(page)); + + return page; +} + +/* Lock and remove page from the per-cpu list */ +static struct page *rmqueue_pcplist(struct zone *preferred_zone, + struct zone *zone, gfp_t gfp_flags, + int migratetype, unsigned int alloc_flags) +{ + struct per_cpu_pages *pcp; + struct list_head *list; + struct page *page; + unsigned long flags; + + local_irq_save(flags); + pcp = &this_cpu_ptr(zone->pageset)->pcp; + list = &pcp->lists[migratetype]; + page = __rmqueue_pcplist(zone, migratetype, alloc_flags, pcp, list); + if (page) { + __count_zid_vm_events(PGALLOC, page_zonenum(page), 1); + zone_statistics(preferred_zone, zone); + } + local_irq_restore(flags); + return page; +} + +/* + * Allocate a page from the given zone. Use pcplists for order-0 allocations. + */ +static inline +struct page *rmqueue(struct zone *preferred_zone, + struct zone *zone, unsigned int order, + gfp_t gfp_flags, unsigned int alloc_flags, + int migratetype) +{ + unsigned long flags; + struct page *page; + + if (likely(order == 0)) { + /* + * MIGRATE_MOVABLE pcplist could have the pages on CMA area and + * we need to skip it when CMA area isn't allowed. + */ + if (!IS_ENABLED(CONFIG_CMA) || alloc_flags & ALLOC_CMA || + migratetype != MIGRATE_MOVABLE) { + page = rmqueue_pcplist(preferred_zone, zone, gfp_flags, + migratetype, alloc_flags); + goto out; + } + } + + /* + * We most definitely don't want callers attempting to + * allocate greater than order-1 page units with __GFP_NOFAIL. + */ + WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1)); + spin_lock_irqsave(&zone->lock, flags); + + do { + page = NULL; + /* + * order-0 request can reach here when the pcplist is skipped + * due to non-CMA allocation context. HIGHATOMIC area is + * reserved for high-order atomic allocation, so order-0 + * request should skip it. + */ + if (order > 0 && alloc_flags & ALLOC_HARDER) { + page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC); + if (page) + trace_mm_page_alloc_zone_locked(page, order, migratetype); + } + if (!page) + page = __rmqueue(zone, order, migratetype, alloc_flags); + } while (page && check_new_pages(page, order)); + spin_unlock(&zone->lock); + if (!page) + goto failed; + __mod_zone_freepage_state(zone, -(1 << order), + get_pcppage_migratetype(page)); + + __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); + zone_statistics(preferred_zone, zone); + local_irq_restore(flags); + +out: + /* Separate test+clear to avoid unnecessary atomics */ + if (test_bit(ZONE_BOOSTED_WATERMARK, &zone->flags)) { + clear_bit(ZONE_BOOSTED_WATERMARK, &zone->flags); + wakeup_kswapd(zone, 0, 0, zone_idx(zone)); + } + + VM_BUG_ON_PAGE(page && bad_range(zone, page), page); + return page; + +failed: + local_irq_restore(flags); + return NULL; +} + +#ifdef CONFIG_FAIL_PAGE_ALLOC + +static struct { + struct fault_attr attr; + + bool ignore_gfp_highmem; + bool ignore_gfp_reclaim; + u32 min_order; +} fail_page_alloc = { + .attr = FAULT_ATTR_INITIALIZER, + .ignore_gfp_reclaim = true, + .ignore_gfp_highmem = true, + .min_order = 1, +}; + +static int __init setup_fail_page_alloc(char *str) +{ + return setup_fault_attr(&fail_page_alloc.attr, str); +} +__setup("fail_page_alloc=", setup_fail_page_alloc); + +static bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) +{ + if (order < fail_page_alloc.min_order) + return false; + if (gfp_mask & __GFP_NOFAIL) + return false; + if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM)) + return false; + if (fail_page_alloc.ignore_gfp_reclaim && + (gfp_mask & __GFP_DIRECT_RECLAIM)) + return false; + + return should_fail(&fail_page_alloc.attr, 1 << order); +} + +#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS + +static int __init fail_page_alloc_debugfs(void) +{ + umode_t mode = S_IFREG | 0600; + struct dentry *dir; + + dir = fault_create_debugfs_attr("fail_page_alloc", NULL, + &fail_page_alloc.attr); + + debugfs_create_bool("ignore-gfp-wait", mode, dir, + &fail_page_alloc.ignore_gfp_reclaim); + debugfs_create_bool("ignore-gfp-highmem", mode, dir, + &fail_page_alloc.ignore_gfp_highmem); + debugfs_create_u32("min-order", mode, dir, &fail_page_alloc.min_order); + + return 0; +} + +late_initcall(fail_page_alloc_debugfs); + +#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ + +#else /* CONFIG_FAIL_PAGE_ALLOC */ + +static inline bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) +{ + return false; +} + +#endif /* CONFIG_FAIL_PAGE_ALLOC */ + +noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) +{ + return __should_fail_alloc_page(gfp_mask, order); +} +ALLOW_ERROR_INJECTION(should_fail_alloc_page, TRUE); + +static inline long __zone_watermark_unusable_free(struct zone *z, + unsigned int order, unsigned int alloc_flags) +{ + const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM)); + long unusable_free = (1 << order) - 1; + + /* + * If the caller does not have rights to ALLOC_HARDER then subtract + * the high-atomic reserves. This will over-estimate the size of the + * atomic reserve but it avoids a search. + */ + if (likely(!alloc_harder)) + unusable_free += z->nr_reserved_highatomic; + +#ifdef CONFIG_CMA + /* If allocation can't use CMA areas don't use free CMA pages */ + if (!(alloc_flags & ALLOC_CMA)) + unusable_free += zone_page_state(z, NR_FREE_CMA_PAGES); +#endif + + return unusable_free; +} + +/* + * Return true if free base pages are above 'mark'. For high-order checks it + * will return true of the order-0 watermark is reached and there is at least + * one free page of a suitable size. Checking now avoids taking the zone lock + * to check in the allocation paths if no pages are free. + */ +bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, + int highest_zoneidx, unsigned int alloc_flags, + long free_pages) +{ + long min = mark; + int o; + const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM)); + + /* free_pages may go negative - that's OK */ + free_pages -= __zone_watermark_unusable_free(z, order, alloc_flags); + + if (alloc_flags & ALLOC_HIGH) + min -= min / 2; + + if (unlikely(alloc_harder)) { + /* + * OOM victims can try even harder than normal ALLOC_HARDER + * users on the grounds that it's definitely going to be in + * the exit path shortly and free memory. Any allocation it + * makes during the free path will be small and short-lived. + */ + if (alloc_flags & ALLOC_OOM) + min -= min / 2; + else + min -= min / 4; + } + + /* + * Check watermarks for an order-0 allocation request. If these + * are not met, then a high-order request also cannot go ahead + * even if a suitable page happened to be free. + */ + if (free_pages <= min + z->lowmem_reserve[highest_zoneidx]) + return false; + + /* If this is an order-0 request then the watermark is fine */ + if (!order) + return true; + + /* For a high-order request, check at least one suitable page is free */ + for (o = order; o < MAX_ORDER; o++) { + struct free_area *area = &z->free_area[o]; + int mt; + + if (!area->nr_free) + continue; + + for (mt = 0; mt < MIGRATE_PCPTYPES; mt++) { + if (!free_area_empty(area, mt)) + return true; + } + +#ifdef CONFIG_CMA + if ((alloc_flags & ALLOC_CMA) && + !free_area_empty(area, MIGRATE_CMA)) { + return true; + } +#endif + if (alloc_harder && !free_area_empty(area, MIGRATE_HIGHATOMIC)) + return true; + } + return false; +} + +bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, + int highest_zoneidx, unsigned int alloc_flags) +{ + return __zone_watermark_ok(z, order, mark, highest_zoneidx, alloc_flags, + zone_page_state(z, NR_FREE_PAGES)); +} + +static inline bool zone_watermark_fast(struct zone *z, unsigned int order, + unsigned long mark, int highest_zoneidx, + unsigned int alloc_flags, gfp_t gfp_mask) +{ + long free_pages; + + free_pages = zone_page_state(z, NR_FREE_PAGES); + + /* + * Fast check for order-0 only. If this fails then the reserves + * need to be calculated. + */ + if (!order) { + long usable_free; + long reserved; + + usable_free = free_pages; + reserved = __zone_watermark_unusable_free(z, 0, alloc_flags); + + /* reserved may over estimate high-atomic reserves. */ + usable_free -= min(usable_free, reserved); + if (usable_free > mark + z->lowmem_reserve[highest_zoneidx]) + return true; + } + + if (__zone_watermark_ok(z, order, mark, highest_zoneidx, alloc_flags, + free_pages)) + return true; + /* + * Ignore watermark boosting for GFP_ATOMIC order-0 allocations + * when checking the min watermark. The min watermark is the + * point where boosting is ignored so that kswapd is woken up + * when below the low watermark. + */ + if (unlikely(!order && (gfp_mask & __GFP_ATOMIC) && z->watermark_boost + && ((alloc_flags & ALLOC_WMARK_MASK) == WMARK_MIN))) { + mark = z->_watermark[WMARK_MIN]; + return __zone_watermark_ok(z, order, mark, highest_zoneidx, + alloc_flags, free_pages); + } + + return false; +} + +bool zone_watermark_ok_safe(struct zone *z, unsigned int order, + unsigned long mark, int highest_zoneidx) +{ + long free_pages = zone_page_state(z, NR_FREE_PAGES); + + if (z->percpu_drift_mark && free_pages < z->percpu_drift_mark) + free_pages = zone_page_state_snapshot(z, NR_FREE_PAGES); + + return __zone_watermark_ok(z, order, mark, highest_zoneidx, 0, + free_pages); +} + +#ifdef CONFIG_NUMA +static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) +{ + return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <= + node_reclaim_distance; +} +#else /* CONFIG_NUMA */ +static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) +{ + return true; +} +#endif /* CONFIG_NUMA */ + +/* + * The restriction on ZONE_DMA32 as being a suitable zone to use to avoid + * fragmentation is subtle. If the preferred zone was HIGHMEM then + * premature use of a lower zone may cause lowmem pressure problems that + * are worse than fragmentation. If the next zone is ZONE_DMA then it is + * probably too small. It only makes sense to spread allocations to avoid + * fragmentation between the Normal and DMA32 zones. + */ +static inline unsigned int +alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask) +{ + unsigned int alloc_flags; + + /* + * __GFP_KSWAPD_RECLAIM is assumed to be the same as ALLOC_KSWAPD + * to save a branch. + */ + alloc_flags = (__force int) (gfp_mask & __GFP_KSWAPD_RECLAIM); + +#ifdef CONFIG_ZONE_DMA32 + if (!zone) + return alloc_flags; + + if (zone_idx(zone) != ZONE_NORMAL) + return alloc_flags; + + /* + * If ZONE_DMA32 exists, assume it is the one after ZONE_NORMAL and + * the pointer is within zone->zone_pgdat->node_zones[]. Also assume + * on UMA that if Normal is populated then so is DMA32. + */ + BUILD_BUG_ON(ZONE_NORMAL - ZONE_DMA32 != 1); + if (nr_online_nodes > 1 && !populated_zone(--zone)) + return alloc_flags; + + alloc_flags |= ALLOC_NOFRAGMENT; +#endif /* CONFIG_ZONE_DMA32 */ + return alloc_flags; +} + +static inline unsigned int current_alloc_flags(gfp_t gfp_mask, + unsigned int alloc_flags) +{ +#ifdef CONFIG_CMA + unsigned int pflags = current->flags; + + if (!(pflags & PF_MEMALLOC_NOCMA) && + gfp_migratetype(gfp_mask) == MIGRATE_MOVABLE) + alloc_flags |= ALLOC_CMA; + +#endif + return alloc_flags; +} + +/* + * get_page_from_freelist goes through the zonelist trying to allocate + * a page. + */ +static struct page * +get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags, + const struct alloc_context *ac) +{ + struct zoneref *z; + struct zone *zone; + struct pglist_data *last_pgdat_dirty_limit = NULL; + bool no_fallback; + +retry: + /* + * Scan zonelist, looking for a zone with enough free. + * See also __cpuset_node_allowed() comment in kernel/cpuset.c. + */ + no_fallback = alloc_flags & ALLOC_NOFRAGMENT; + z = ac->preferred_zoneref; + for_next_zone_zonelist_nodemask(zone, z, ac->highest_zoneidx, + ac->nodemask) { + struct page *page; + unsigned long mark; + + if (cpusets_enabled() && + (alloc_flags & ALLOC_CPUSET) && + !__cpuset_zone_allowed(zone, gfp_mask)) + continue; + /* + * When allocating a page cache page for writing, we + * want to get it from a node that is within its dirty + * limit, such that no single node holds more than its + * proportional share of globally allowed dirty pages. + * The dirty limits take into account the node's + * lowmem reserves and high watermark so that kswapd + * should be able to balance it without having to + * write pages from its LRU list. + * + * XXX: For now, allow allocations to potentially + * exceed the per-node dirty limit in the slowpath + * (spread_dirty_pages unset) before going into reclaim, + * which is important when on a NUMA setup the allowed + * nodes are together not big enough to reach the + * global limit. The proper fix for these situations + * will require awareness of nodes in the + * dirty-throttling and the flusher threads. + */ + if (ac->spread_dirty_pages) { + if (last_pgdat_dirty_limit == zone->zone_pgdat) + continue; + + if (!node_dirty_ok(zone->zone_pgdat)) { + last_pgdat_dirty_limit = zone->zone_pgdat; + continue; + } + } + + if (no_fallback && nr_online_nodes > 1 && + zone != ac->preferred_zoneref->zone) { + int local_nid; + + /* + * If moving to a remote node, retry but allow + * fragmenting fallbacks. Locality is more important + * than fragmentation avoidance. + */ + local_nid = zone_to_nid(ac->preferred_zoneref->zone); + if (zone_to_nid(zone) != local_nid) { + alloc_flags &= ~ALLOC_NOFRAGMENT; + goto retry; + } + } + + mark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK); + if (!zone_watermark_fast(zone, order, mark, + ac->highest_zoneidx, alloc_flags, + gfp_mask)) { + int ret; + +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT + /* + * Watermark failed for this zone, but see if we can + * grow this zone if it contains deferred pages. + */ + if (static_branch_unlikely(&deferred_pages)) { + if (_deferred_grow_zone(zone, order)) + goto try_this_zone; + } +#endif + /* Checked here to keep the fast path fast */ + BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK); + if (alloc_flags & ALLOC_NO_WATERMARKS) + goto try_this_zone; + + if (node_reclaim_mode == 0 || + !zone_allows_reclaim(ac->preferred_zoneref->zone, zone)) + continue; + + ret = node_reclaim(zone->zone_pgdat, gfp_mask, order); + switch (ret) { + case NODE_RECLAIM_NOSCAN: + /* did not scan */ + continue; + case NODE_RECLAIM_FULL: + /* scanned but unreclaimable */ + continue; + default: + /* did we reclaim enough */ + if (zone_watermark_ok(zone, order, mark, + ac->highest_zoneidx, alloc_flags)) + goto try_this_zone; + + continue; + } + } + +try_this_zone: + page = rmqueue(ac->preferred_zoneref->zone, zone, order, + gfp_mask, alloc_flags, ac->migratetype); + if (page) { + prep_new_page(page, order, gfp_mask, alloc_flags); + + /* + * If this is a high-order atomic allocation then check + * if the pageblock should be reserved for the future + */ + if (unlikely(order && (alloc_flags & ALLOC_HARDER))) + reserve_highatomic_pageblock(page, zone, order); + + return page; + } else { +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT + /* Try again if zone has deferred pages */ + if (static_branch_unlikely(&deferred_pages)) { + if (_deferred_grow_zone(zone, order)) + goto try_this_zone; + } +#endif + } + } + + /* + * It's possible on a UMA machine to get through all zones that are + * fragmented. If avoiding fragmentation, reset and try again. + */ + if (no_fallback) { + alloc_flags &= ~ALLOC_NOFRAGMENT; + goto retry; + } + + return NULL; +} + +static void warn_alloc_show_mem(gfp_t gfp_mask, nodemask_t *nodemask) +{ + unsigned int filter = SHOW_MEM_FILTER_NODES; + + /* + * This documents exceptions given to allocations in certain + * contexts that are allowed to allocate outside current's set + * of allowed nodes. + */ + if (!(gfp_mask & __GFP_NOMEMALLOC)) + if (tsk_is_oom_victim(current) || + (current->flags & (PF_MEMALLOC | PF_EXITING))) + filter &= ~SHOW_MEM_FILTER_NODES; + if (in_interrupt() || !(gfp_mask & __GFP_DIRECT_RECLAIM)) + filter &= ~SHOW_MEM_FILTER_NODES; + + show_mem(filter, nodemask); +} + +void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...) +{ + struct va_format vaf; + va_list args; + static DEFINE_RATELIMIT_STATE(nopage_rs, 10*HZ, 1); + + if ((gfp_mask & __GFP_NOWARN) || + !__ratelimit(&nopage_rs) || + ((gfp_mask & __GFP_DMA) && !has_managed_dma())) + return; + + va_start(args, fmt); + vaf.fmt = fmt; + vaf.va = &args; + pr_warn("%s: %pV, mode:%#x(%pGg), nodemask=%*pbl", + current->comm, &vaf, gfp_mask, &gfp_mask, + nodemask_pr_args(nodemask)); + va_end(args); + + cpuset_print_current_mems_allowed(); + pr_cont("\n"); + dump_stack(); + warn_alloc_show_mem(gfp_mask, nodemask); +} + +static inline struct page * +__alloc_pages_cpuset_fallback(gfp_t gfp_mask, unsigned int order, + unsigned int alloc_flags, + const struct alloc_context *ac) +{ + struct page *page; + + page = get_page_from_freelist(gfp_mask, order, + alloc_flags|ALLOC_CPUSET, ac); + /* + * fallback to ignore cpuset restriction if our nodes + * are depleted + */ + if (!page) + page = get_page_from_freelist(gfp_mask, order, + alloc_flags, ac); + + return page; +} + +static inline struct page * +__alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, + const struct alloc_context *ac, unsigned long *did_some_progress) +{ + struct oom_control oc = { + .zonelist = ac->zonelist, + .nodemask = ac->nodemask, + .memcg = NULL, + .gfp_mask = gfp_mask, + .order = order, + }; + struct page *page; + + *did_some_progress = 0; + + /* + * Acquire the oom lock. If that fails, somebody else is + * making progress for us. + */ + if (!mutex_trylock(&oom_lock)) { + *did_some_progress = 1; + schedule_timeout_uninterruptible(1); + return NULL; + } + + /* + * Go through the zonelist yet one more time, keep very high watermark + * here, this is only to catch a parallel oom killing, we must fail if + * we're still under heavy pressure. But make sure that this reclaim + * attempt shall not depend on __GFP_DIRECT_RECLAIM && !__GFP_NORETRY + * allocation which will never fail due to oom_lock already held. + */ + page = get_page_from_freelist((gfp_mask | __GFP_HARDWALL) & + ~__GFP_DIRECT_RECLAIM, order, + ALLOC_WMARK_HIGH|ALLOC_CPUSET, ac); + if (page) + goto out; + + /* Coredumps can quickly deplete all memory reserves */ + if (current->flags & PF_DUMPCORE) + goto out; + /* The OOM killer will not help higher order allocs */ + if (order > PAGE_ALLOC_COSTLY_ORDER) + goto out; + /* + * We have already exhausted all our reclaim opportunities without any + * success so it is time to admit defeat. We will skip the OOM killer + * because it is very likely that the caller has a more reasonable + * fallback than shooting a random task. + * + * The OOM killer may not free memory on a specific node. + */ + if (gfp_mask & (__GFP_RETRY_MAYFAIL | __GFP_THISNODE)) + goto out; + /* The OOM killer does not needlessly kill tasks for lowmem */ + if (ac->highest_zoneidx < ZONE_NORMAL) + goto out; + if (pm_suspended_storage()) + goto out; + /* + * XXX: GFP_NOFS allocations should rather fail than rely on + * other request to make a forward progress. + * We are in an unfortunate situation where out_of_memory cannot + * do much for this context but let's try it to at least get + * access to memory reserved if the current task is killed (see + * out_of_memory). Once filesystems are ready to handle allocation + * failures more gracefully we should just bail out here. + */ + + /* Exhausted what can be done so it's blame time */ + if (out_of_memory(&oc) || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) { + *did_some_progress = 1; + + /* + * Help non-failing allocations by giving them access to memory + * reserves + */ + if (gfp_mask & __GFP_NOFAIL) + page = __alloc_pages_cpuset_fallback(gfp_mask, order, + ALLOC_NO_WATERMARKS, ac); + } +out: + mutex_unlock(&oom_lock); + return page; +} + +/* + * Maximum number of compaction retries wit a progress before OOM + * killer is consider as the only way to move forward. + */ +#define MAX_COMPACT_RETRIES 16 + +#ifdef CONFIG_COMPACTION +/* Try memory compaction for high-order allocations before reclaim */ +static struct page * +__alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, + unsigned int alloc_flags, const struct alloc_context *ac, + enum compact_priority prio, enum compact_result *compact_result) +{ + struct page *page = NULL; + unsigned long pflags; + unsigned int noreclaim_flag; + + if (!order) + return NULL; + + psi_memstall_enter(&pflags); + noreclaim_flag = memalloc_noreclaim_save(); + + *compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac, + prio, &page); + + memalloc_noreclaim_restore(noreclaim_flag); + psi_memstall_leave(&pflags); + + /* + * At least in one zone compaction wasn't deferred or skipped, so let's + * count a compaction stall + */ + count_vm_event(COMPACTSTALL); + + /* Prep a captured page if available */ + if (page) + prep_new_page(page, order, gfp_mask, alloc_flags); + + /* Try get a page from the freelist if available */ + if (!page) + page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac); + + if (page) { + struct zone *zone = page_zone(page); + + zone->compact_blockskip_flush = false; + compaction_defer_reset(zone, order, true); + count_vm_event(COMPACTSUCCESS); + return page; + } + + /* + * It's bad if compaction run occurs and fails. The most likely reason + * is that pages exist, but not enough to satisfy watermarks. + */ + count_vm_event(COMPACTFAIL); + + cond_resched(); + + return NULL; +} + +static inline bool +should_compact_retry(struct alloc_context *ac, int order, int alloc_flags, + enum compact_result compact_result, + enum compact_priority *compact_priority, + int *compaction_retries) +{ + int max_retries = MAX_COMPACT_RETRIES; + int min_priority; + bool ret = false; + int retries = *compaction_retries; + enum compact_priority priority = *compact_priority; + + if (!order) + return false; + + if (compaction_made_progress(compact_result)) + (*compaction_retries)++; + + /* + * compaction considers all the zone as desperately out of memory + * so it doesn't really make much sense to retry except when the + * failure could be caused by insufficient priority + */ + if (compaction_failed(compact_result)) + goto check_priority; + + /* + * compaction was skipped because there are not enough order-0 pages + * to work with, so we retry only if it looks like reclaim can help. + */ + if (compaction_needs_reclaim(compact_result)) { + ret = compaction_zonelist_suitable(ac, order, alloc_flags); + goto out; + } + + /* + * make sure the compaction wasn't deferred or didn't bail out early + * due to locks contention before we declare that we should give up. + * But the next retry should use a higher priority if allowed, so + * we don't just keep bailing out endlessly. + */ + if (compaction_withdrawn(compact_result)) { + goto check_priority; + } + + /* + * !costly requests are much more important than __GFP_RETRY_MAYFAIL + * costly ones because they are de facto nofail and invoke OOM + * killer to move on while costly can fail and users are ready + * to cope with that. 1/4 retries is rather arbitrary but we + * would need much more detailed feedback from compaction to + * make a better decision. + */ + if (order > PAGE_ALLOC_COSTLY_ORDER) + max_retries /= 4; + if (*compaction_retries <= max_retries) { + ret = true; + goto out; + } + + /* + * Make sure there are attempts at the highest priority if we exhausted + * all retries or failed at the lower priorities. + */ +check_priority: + min_priority = (order > PAGE_ALLOC_COSTLY_ORDER) ? + MIN_COMPACT_COSTLY_PRIORITY : MIN_COMPACT_PRIORITY; + + if (*compact_priority > min_priority) { + (*compact_priority)--; + *compaction_retries = 0; + ret = true; + } +out: + trace_compact_retry(order, priority, compact_result, retries, max_retries, ret); + return ret; +} +#else +static inline struct page * +__alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, + unsigned int alloc_flags, const struct alloc_context *ac, + enum compact_priority prio, enum compact_result *compact_result) +{ + *compact_result = COMPACT_SKIPPED; + return NULL; +} + +static inline bool +should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_flags, + enum compact_result compact_result, + enum compact_priority *compact_priority, + int *compaction_retries) +{ + struct zone *zone; + struct zoneref *z; + + if (!order || order > PAGE_ALLOC_COSTLY_ORDER) + return false; + + /* + * There are setups with compaction disabled which would prefer to loop + * inside the allocator rather than hit the oom killer prematurely. + * Let's give them a good hope and keep retrying while the order-0 + * watermarks are OK. + */ + for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, + ac->highest_zoneidx, ac->nodemask) { + if (zone_watermark_ok(zone, 0, min_wmark_pages(zone), + ac->highest_zoneidx, alloc_flags)) + return true; + } + return false; +} +#endif /* CONFIG_COMPACTION */ + +#ifdef CONFIG_LOCKDEP +static struct lockdep_map __fs_reclaim_map = + STATIC_LOCKDEP_MAP_INIT("fs_reclaim", &__fs_reclaim_map); + +static bool __need_fs_reclaim(gfp_t gfp_mask) +{ + gfp_mask = current_gfp_context(gfp_mask); + + /* no reclaim without waiting on it */ + if (!(gfp_mask & __GFP_DIRECT_RECLAIM)) + return false; + + /* this guy won't enter reclaim */ + if (current->flags & PF_MEMALLOC) + return false; + + /* We're only interested __GFP_FS allocations for now */ + if (!(gfp_mask & __GFP_FS)) + return false; + + if (gfp_mask & __GFP_NOLOCKDEP) + return false; + + return true; +} + +void __fs_reclaim_acquire(void) +{ + lock_map_acquire(&__fs_reclaim_map); +} + +void __fs_reclaim_release(void) +{ + lock_map_release(&__fs_reclaim_map); +} + +void fs_reclaim_acquire(gfp_t gfp_mask) +{ + if (__need_fs_reclaim(gfp_mask)) + __fs_reclaim_acquire(); +} +EXPORT_SYMBOL_GPL(fs_reclaim_acquire); + +void fs_reclaim_release(gfp_t gfp_mask) +{ + if (__need_fs_reclaim(gfp_mask)) + __fs_reclaim_release(); +} +EXPORT_SYMBOL_GPL(fs_reclaim_release); +#endif + +/* + * Zonelists may change due to hotplug during allocation. Detect when zonelists + * have been rebuilt so allocation retries. Reader side does not lock and + * retries the allocation if zonelist changes. Writer side is protected by the + * embedded spin_lock. + */ +static DEFINE_SEQLOCK(zonelist_update_seq); + +static unsigned int zonelist_iter_begin(void) +{ + if (IS_ENABLED(CONFIG_MEMORY_HOTREMOVE)) + return read_seqbegin(&zonelist_update_seq); + + return 0; +} + +static unsigned int check_retry_zonelist(unsigned int seq) +{ + if (IS_ENABLED(CONFIG_MEMORY_HOTREMOVE)) + return read_seqretry(&zonelist_update_seq, seq); + + return seq; +} + +/* Perform direct synchronous page reclaim */ +static unsigned long +__perform_reclaim(gfp_t gfp_mask, unsigned int order, + const struct alloc_context *ac) +{ + unsigned int noreclaim_flag; + unsigned long pflags, progress; + + cond_resched(); + + /* We now go into synchronous reclaim */ + cpuset_memory_pressure_bump(); + psi_memstall_enter(&pflags); + fs_reclaim_acquire(gfp_mask); + noreclaim_flag = memalloc_noreclaim_save(); + + progress = try_to_free_pages(ac->zonelist, order, gfp_mask, + ac->nodemask); + + memalloc_noreclaim_restore(noreclaim_flag); + fs_reclaim_release(gfp_mask); + psi_memstall_leave(&pflags); + + cond_resched(); + + return progress; +} + +/* The really slow allocator path where we enter direct reclaim */ +static inline struct page * +__alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, + unsigned int alloc_flags, const struct alloc_context *ac, + unsigned long *did_some_progress) +{ + struct page *page = NULL; + bool drained = false; + + *did_some_progress = __perform_reclaim(gfp_mask, order, ac); + if (unlikely(!(*did_some_progress))) + return NULL; + +retry: + page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac); + + /* + * If an allocation failed after direct reclaim, it could be because + * pages are pinned on the per-cpu lists or in high alloc reserves. + * Shrink them and try again + */ + if (!page && !drained) { + unreserve_highatomic_pageblock(ac, false); + drain_all_pages(NULL); + drained = true; + goto retry; + } + + return page; +} + +static void wake_all_kswapds(unsigned int order, gfp_t gfp_mask, + const struct alloc_context *ac) +{ + struct zoneref *z; + struct zone *zone; + pg_data_t *last_pgdat = NULL; + enum zone_type highest_zoneidx = ac->highest_zoneidx; + + for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, highest_zoneidx, + ac->nodemask) { + if (last_pgdat != zone->zone_pgdat) + wakeup_kswapd(zone, gfp_mask, order, highest_zoneidx); + last_pgdat = zone->zone_pgdat; + } +} + +static inline unsigned int +gfp_to_alloc_flags(gfp_t gfp_mask) +{ + unsigned int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET; + + /* + * __GFP_HIGH is assumed to be the same as ALLOC_HIGH + * and __GFP_KSWAPD_RECLAIM is assumed to be the same as ALLOC_KSWAPD + * to save two branches. + */ + BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH); + BUILD_BUG_ON(__GFP_KSWAPD_RECLAIM != (__force gfp_t) ALLOC_KSWAPD); + + /* + * The caller may dip into page reserves a bit more if the caller + * cannot run direct reclaim, or if the caller has realtime scheduling + * policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will + * set both ALLOC_HARDER (__GFP_ATOMIC) and ALLOC_HIGH (__GFP_HIGH). + */ + alloc_flags |= (__force int) + (gfp_mask & (__GFP_HIGH | __GFP_KSWAPD_RECLAIM)); + + if (gfp_mask & __GFP_ATOMIC) { + /* + * Not worth trying to allocate harder for __GFP_NOMEMALLOC even + * if it can't schedule. + */ + if (!(gfp_mask & __GFP_NOMEMALLOC)) + alloc_flags |= ALLOC_HARDER; + /* + * Ignore cpuset mems for GFP_ATOMIC rather than fail, see the + * comment for __cpuset_node_allowed(). + */ + alloc_flags &= ~ALLOC_CPUSET; + } else if (unlikely(rt_task(current)) && !in_interrupt()) + alloc_flags |= ALLOC_HARDER; + + alloc_flags = current_alloc_flags(gfp_mask, alloc_flags); + + return alloc_flags; +} + +static bool oom_reserves_allowed(struct task_struct *tsk) +{ + if (!tsk_is_oom_victim(tsk)) + return false; + + /* + * !MMU doesn't have oom reaper so give access to memory reserves + * only to the thread with TIF_MEMDIE set + */ + if (!IS_ENABLED(CONFIG_MMU) && !test_thread_flag(TIF_MEMDIE)) + return false; + + return true; +} + +/* + * Distinguish requests which really need access to full memory + * reserves from oom victims which can live with a portion of it + */ +static inline int __gfp_pfmemalloc_flags(gfp_t gfp_mask) +{ + if (unlikely(gfp_mask & __GFP_NOMEMALLOC)) + return 0; + if (gfp_mask & __GFP_MEMALLOC) + return ALLOC_NO_WATERMARKS; + if (in_serving_softirq() && (current->flags & PF_MEMALLOC)) + return ALLOC_NO_WATERMARKS; + if (!in_interrupt()) { + if (current->flags & PF_MEMALLOC) + return ALLOC_NO_WATERMARKS; + else if (oom_reserves_allowed(current)) + return ALLOC_OOM; + } + + return 0; +} + +bool gfp_pfmemalloc_allowed(gfp_t gfp_mask) +{ + return !!__gfp_pfmemalloc_flags(gfp_mask); +} + +/* + * Checks whether it makes sense to retry the reclaim to make a forward progress + * for the given allocation request. + * + * We give up when we either have tried MAX_RECLAIM_RETRIES in a row + * without success, or when we couldn't even meet the watermark if we + * reclaimed all remaining pages on the LRU lists. + * + * Returns true if a retry is viable or false to enter the oom path. + */ +static inline bool +should_reclaim_retry(gfp_t gfp_mask, unsigned order, + struct alloc_context *ac, int alloc_flags, + bool did_some_progress, int *no_progress_loops) +{ + struct zone *zone; + struct zoneref *z; + bool ret = false; + + /* + * Costly allocations might have made a progress but this doesn't mean + * their order will become available due to high fragmentation so + * always increment the no progress counter for them + */ + if (did_some_progress && order <= PAGE_ALLOC_COSTLY_ORDER) + *no_progress_loops = 0; + else + (*no_progress_loops)++; + + /* + * Make sure we converge to OOM if we cannot make any progress + * several times in the row. + */ + if (*no_progress_loops > MAX_RECLAIM_RETRIES) { + /* Before OOM, exhaust highatomic_reserve */ + return unreserve_highatomic_pageblock(ac, true); + } + + /* + * Keep reclaiming pages while there is a chance this will lead + * somewhere. If none of the target zones can satisfy our allocation + * request even if all reclaimable pages are considered then we are + * screwed and have to go OOM. + */ + for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, + ac->highest_zoneidx, ac->nodemask) { + unsigned long available; + unsigned long reclaimable; + unsigned long min_wmark = min_wmark_pages(zone); + bool wmark; + + available = reclaimable = zone_reclaimable_pages(zone); + available += zone_page_state_snapshot(zone, NR_FREE_PAGES); + + /* + * Would the allocation succeed if we reclaimed all + * reclaimable pages? + */ + wmark = __zone_watermark_ok(zone, order, min_wmark, + ac->highest_zoneidx, alloc_flags, available); + trace_reclaim_retry_zone(z, order, reclaimable, + available, min_wmark, *no_progress_loops, wmark); + if (wmark) { + /* + * If we didn't make any progress and have a lot of + * dirty + writeback pages then we should wait for + * an IO to complete to slow down the reclaim and + * prevent from pre mature OOM + */ + if (!did_some_progress) { + unsigned long write_pending; + + write_pending = zone_page_state_snapshot(zone, + NR_ZONE_WRITE_PENDING); + + if (2 * write_pending > reclaimable) { + congestion_wait(BLK_RW_ASYNC, HZ/10); + return true; + } + } + + ret = true; + goto out; + } + } + +out: + /* + * Memory allocation/reclaim might be called from a WQ context and the + * current implementation of the WQ concurrency control doesn't + * recognize that a particular WQ is congested if the worker thread is + * looping without ever sleeping. Therefore we have to do a short sleep + * here rather than calling cond_resched(). + */ + if (current->flags & PF_WQ_WORKER) + schedule_timeout_uninterruptible(1); + else + cond_resched(); + return ret; +} + +static inline bool +check_retry_cpuset(int cpuset_mems_cookie, struct alloc_context *ac) +{ + /* + * It's possible that cpuset's mems_allowed and the nodemask from + * mempolicy don't intersect. This should be normally dealt with by + * policy_nodemask(), but it's possible to race with cpuset update in + * such a way the check therein was true, and then it became false + * before we got our cpuset_mems_cookie here. + * This assumes that for all allocations, ac->nodemask can come only + * from MPOL_BIND mempolicy (whose documented semantics is to be ignored + * when it does not intersect with the cpuset restrictions) or the + * caller can deal with a violated nodemask. + */ + if (cpusets_enabled() && ac->nodemask && + !cpuset_nodemask_valid_mems_allowed(ac->nodemask)) { + ac->nodemask = NULL; + return true; + } + + /* + * When updating a task's mems_allowed or mempolicy nodemask, it is + * possible to race with parallel threads in such a way that our + * allocation can fail while the mask is being updated. If we are about + * to fail, check if the cpuset changed during allocation and if so, + * retry. + */ + if (read_mems_allowed_retry(cpuset_mems_cookie)) + return true; + + return false; +} + +static inline struct page * +__alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, + struct alloc_context *ac) +{ + bool can_direct_reclaim = gfp_mask & __GFP_DIRECT_RECLAIM; + const bool costly_order = order > PAGE_ALLOC_COSTLY_ORDER; + struct page *page = NULL; + unsigned int alloc_flags; + unsigned long did_some_progress; + enum compact_priority compact_priority; + enum compact_result compact_result; + int compaction_retries; + int no_progress_loops; + unsigned int cpuset_mems_cookie; + unsigned int zonelist_iter_cookie; + int reserve_flags; + + /* + * We also sanity check to catch abuse of atomic reserves being used by + * callers that are not in atomic context. + */ + if (WARN_ON_ONCE((gfp_mask & (__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)) == + (__GFP_ATOMIC|__GFP_DIRECT_RECLAIM))) + gfp_mask &= ~__GFP_ATOMIC; + +restart: + compaction_retries = 0; + no_progress_loops = 0; + compact_priority = DEF_COMPACT_PRIORITY; + cpuset_mems_cookie = read_mems_allowed_begin(); + zonelist_iter_cookie = zonelist_iter_begin(); + + /* + * The fast path uses conservative alloc_flags to succeed only until + * kswapd needs to be woken up, and to avoid the cost of setting up + * alloc_flags precisely. So we do that now. + */ + alloc_flags = gfp_to_alloc_flags(gfp_mask); + + /* + * We need to recalculate the starting point for the zonelist iterator + * because we might have used different nodemask in the fast path, or + * there was a cpuset modification and we are retrying - otherwise we + * could end up iterating over non-eligible zones endlessly. + */ + ac->preferred_zoneref = first_zones_zonelist(ac->zonelist, + ac->highest_zoneidx, ac->nodemask); + if (!ac->preferred_zoneref->zone) + goto nopage; + + if (alloc_flags & ALLOC_KSWAPD) + wake_all_kswapds(order, gfp_mask, ac); + + /* + * The adjusted alloc_flags might result in immediate success, so try + * that first + */ + page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac); + if (page) + goto got_pg; + + /* + * For costly allocations, try direct compaction first, as it's likely + * that we have enough base pages and don't need to reclaim. For non- + * movable high-order allocations, do that as well, as compaction will + * try prevent permanent fragmentation by migrating from blocks of the + * same migratetype. + * Don't try this for allocations that are allowed to ignore + * watermarks, as the ALLOC_NO_WATERMARKS attempt didn't yet happen. + */ + if (can_direct_reclaim && + (costly_order || + (order > 0 && ac->migratetype != MIGRATE_MOVABLE)) + && !gfp_pfmemalloc_allowed(gfp_mask)) { + page = __alloc_pages_direct_compact(gfp_mask, order, + alloc_flags, ac, + INIT_COMPACT_PRIORITY, + &compact_result); + if (page) + goto got_pg; + + /* + * Checks for costly allocations with __GFP_NORETRY, which + * includes some THP page fault allocations + */ + if (costly_order && (gfp_mask & __GFP_NORETRY)) { + /* + * If allocating entire pageblock(s) and compaction + * failed because all zones are below low watermarks + * or is prohibited because it recently failed at this + * order, fail immediately unless the allocator has + * requested compaction and reclaim retry. + * + * Reclaim is + * - potentially very expensive because zones are far + * below their low watermarks or this is part of very + * bursty high order allocations, + * - not guaranteed to help because isolate_freepages() + * may not iterate over freed pages as part of its + * linear scan, and + * - unlikely to make entire pageblocks free on its + * own. + */ + if (compact_result == COMPACT_SKIPPED || + compact_result == COMPACT_DEFERRED) + goto nopage; + + /* + * Looks like reclaim/compaction is worth trying, but + * sync compaction could be very expensive, so keep + * using async compaction. + */ + compact_priority = INIT_COMPACT_PRIORITY; + } + } + +retry: + /* Ensure kswapd doesn't accidentally go to sleep as long as we loop */ + if (alloc_flags & ALLOC_KSWAPD) + wake_all_kswapds(order, gfp_mask, ac); + + reserve_flags = __gfp_pfmemalloc_flags(gfp_mask); + if (reserve_flags) + alloc_flags = current_alloc_flags(gfp_mask, reserve_flags); + + /* + * Reset the nodemask and zonelist iterators if memory policies can be + * ignored. These allocations are high priority and system rather than + * user oriented. + */ + if (!(alloc_flags & ALLOC_CPUSET) || reserve_flags) { + ac->nodemask = NULL; + ac->preferred_zoneref = first_zones_zonelist(ac->zonelist, + ac->highest_zoneidx, ac->nodemask); + } + + /* Attempt with potentially adjusted zonelist and alloc_flags */ + page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac); + if (page) + goto got_pg; + + /* Caller is not willing to reclaim, we can't balance anything */ + if (!can_direct_reclaim) + goto nopage; + + /* Avoid recursion of direct reclaim */ + if (current->flags & PF_MEMALLOC) + goto nopage; + + /* Try direct reclaim and then allocating */ + page = __alloc_pages_direct_reclaim(gfp_mask, order, alloc_flags, ac, + &did_some_progress); + if (page) + goto got_pg; + + /* Try direct compaction and then allocating */ + page = __alloc_pages_direct_compact(gfp_mask, order, alloc_flags, ac, + compact_priority, &compact_result); + if (page) + goto got_pg; + + /* Do not loop if specifically requested */ + if (gfp_mask & __GFP_NORETRY) + goto nopage; + + /* + * Do not retry costly high order allocations unless they are + * __GFP_RETRY_MAYFAIL + */ + if (costly_order && !(gfp_mask & __GFP_RETRY_MAYFAIL)) + goto nopage; + + if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags, + did_some_progress > 0, &no_progress_loops)) + goto retry; + + /* + * It doesn't make any sense to retry for the compaction if the order-0 + * reclaim is not able to make any progress because the current + * implementation of the compaction depends on the sufficient amount + * of free memory (see __compaction_suitable) + */ + if (did_some_progress > 0 && + should_compact_retry(ac, order, alloc_flags, + compact_result, &compact_priority, + &compaction_retries)) + goto retry; + + + /* + * Deal with possible cpuset update races or zonelist updates to avoid + * a unnecessary OOM kill. + */ + if (check_retry_cpuset(cpuset_mems_cookie, ac) || + check_retry_zonelist(zonelist_iter_cookie)) + goto restart; + + /* Reclaim has failed us, start killing things */ + page = __alloc_pages_may_oom(gfp_mask, order, ac, &did_some_progress); + if (page) + goto got_pg; + + /* Avoid allocations with no watermarks from looping endlessly */ + if (tsk_is_oom_victim(current) && + (alloc_flags & ALLOC_OOM || + (gfp_mask & __GFP_NOMEMALLOC))) + goto nopage; + + /* Retry as long as the OOM killer is making progress */ + if (did_some_progress) { + no_progress_loops = 0; + goto retry; + } + +nopage: + /* + * Deal with possible cpuset update races or zonelist updates to avoid + * a unnecessary OOM kill. + */ + if (check_retry_cpuset(cpuset_mems_cookie, ac) || + check_retry_zonelist(zonelist_iter_cookie)) + goto restart; + + /* + * Make sure that __GFP_NOFAIL request doesn't leak out and make sure + * we always retry + */ + if (gfp_mask & __GFP_NOFAIL) { + /* + * All existing users of the __GFP_NOFAIL are blockable, so warn + * of any new users that actually require GFP_NOWAIT + */ + if (WARN_ON_ONCE(!can_direct_reclaim)) + goto fail; + + /* + * PF_MEMALLOC request from this context is rather bizarre + * because we cannot reclaim anything and only can loop waiting + * for somebody to do a work for us + */ + WARN_ON_ONCE(current->flags & PF_MEMALLOC); + + /* + * non failing costly orders are a hard requirement which we + * are not prepared for much so let's warn about these users + * so that we can identify them and convert them to something + * else. + */ + WARN_ON_ONCE(order > PAGE_ALLOC_COSTLY_ORDER); + + /* + * Help non-failing allocations by giving them access to memory + * reserves but do not use ALLOC_NO_WATERMARKS because this + * could deplete whole memory reserves which would just make + * the situation worse + */ + page = __alloc_pages_cpuset_fallback(gfp_mask, order, ALLOC_HARDER, ac); + if (page) + goto got_pg; + + cond_resched(); + goto retry; + } +fail: + warn_alloc(gfp_mask, ac->nodemask, + "page allocation failure: order:%u", order); +got_pg: + return page; +} + +static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order, + int preferred_nid, nodemask_t *nodemask, + struct alloc_context *ac, gfp_t *alloc_mask, + unsigned int *alloc_flags) +{ + ac->highest_zoneidx = gfp_zone(gfp_mask); + ac->zonelist = node_zonelist(preferred_nid, gfp_mask); + ac->nodemask = nodemask; + ac->migratetype = gfp_migratetype(gfp_mask); + + if (cpusets_enabled()) { + *alloc_mask |= __GFP_HARDWALL; + /* + * When we are in the interrupt context, it is irrelevant + * to the current task context. It means that any node ok. + */ + if (!in_interrupt() && !ac->nodemask) + ac->nodemask = &cpuset_current_mems_allowed; + else + *alloc_flags |= ALLOC_CPUSET; + } + + fs_reclaim_acquire(gfp_mask); + fs_reclaim_release(gfp_mask); + + might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM); + + if (should_fail_alloc_page(gfp_mask, order)) + return false; + + *alloc_flags = current_alloc_flags(gfp_mask, *alloc_flags); + + /* Dirty zone balancing only done in the fast path */ + ac->spread_dirty_pages = (gfp_mask & __GFP_WRITE); + + /* + * The preferred zone is used for statistics but crucially it is + * also used as the starting point for the zonelist iterator. It + * may get reset for allocations that ignore memory policies. + */ + ac->preferred_zoneref = first_zones_zonelist(ac->zonelist, + ac->highest_zoneidx, ac->nodemask); + + return true; +} + +/* + * This is the 'heart' of the zoned buddy allocator. + */ +struct page * +__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, int preferred_nid, + nodemask_t *nodemask) +{ + struct page *page; + unsigned int alloc_flags = ALLOC_WMARK_LOW; + gfp_t alloc_mask; /* The gfp_t that was actually used for allocation */ + struct alloc_context ac = { }; + + /* + * There are several places where we assume that the order value is sane + * so bail out early if the request is out of bound. + */ + if (unlikely(order >= MAX_ORDER)) { + WARN_ON_ONCE(!(gfp_mask & __GFP_NOWARN)); + return NULL; + } + + gfp_mask &= gfp_allowed_mask; + alloc_mask = gfp_mask; + if (!prepare_alloc_pages(gfp_mask, order, preferred_nid, nodemask, &ac, &alloc_mask, &alloc_flags)) + return NULL; + + /* + * Forbid the first pass from falling back to types that fragment + * memory until all local zones are considered. + */ + alloc_flags |= alloc_flags_nofragment(ac.preferred_zoneref->zone, gfp_mask); + + /* First allocation attempt */ + page = get_page_from_freelist(alloc_mask, order, alloc_flags, &ac); + if (likely(page)) + goto out; + + /* + * Apply scoped allocation constraints. This is mainly about GFP_NOFS + * resp. GFP_NOIO which has to be inherited for all allocation requests + * from a particular context which has been marked by + * memalloc_no{fs,io}_{save,restore}. + */ + alloc_mask = current_gfp_context(gfp_mask); + ac.spread_dirty_pages = false; + + /* + * Restore the original nodemask if it was potentially replaced with + * &cpuset_current_mems_allowed to optimize the fast-path attempt. + */ + ac.nodemask = nodemask; + + page = __alloc_pages_slowpath(alloc_mask, order, &ac); + +out: + if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page && + unlikely(__memcg_kmem_charge_page(page, gfp_mask, order) != 0)) { + __free_pages(page, order); + page = NULL; + } + + trace_mm_page_alloc(page, order, alloc_mask, ac.migratetype); + + return page; +} +EXPORT_SYMBOL(__alloc_pages_nodemask); + +/* + * Common helper functions. Never use with __GFP_HIGHMEM because the returned + * address cannot represent highmem pages. Use alloc_pages and then kmap if + * you need to access high mem. + */ +unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order) +{ + struct page *page; + + page = alloc_pages(gfp_mask & ~__GFP_HIGHMEM, order); + if (!page) + return 0; + return (unsigned long) page_address(page); +} +EXPORT_SYMBOL(__get_free_pages); + +unsigned long get_zeroed_page(gfp_t gfp_mask) +{ + return __get_free_pages(gfp_mask | __GFP_ZERO, 0); +} +EXPORT_SYMBOL(get_zeroed_page); + +static inline void free_the_page(struct page *page, unsigned int order) +{ + if (order == 0) /* Via pcp? */ + free_unref_page(page); + else + __free_pages_ok(page, order, FPI_NONE); +} + +void __free_pages(struct page *page, unsigned int order) +{ + /* get PageHead before we drop reference */ + int head = PageHead(page); + + if (put_page_testzero(page)) + free_the_page(page, order); + else if (!head) + while (order-- > 0) + free_the_page(page + (1 << order), order); +} +EXPORT_SYMBOL(__free_pages); + +void free_pages(unsigned long addr, unsigned int order) +{ + if (addr != 0) { + VM_BUG_ON(!virt_addr_valid((void *)addr)); + __free_pages(virt_to_page((void *)addr), order); + } +} + +EXPORT_SYMBOL(free_pages); + +/* + * Page Fragment: + * An arbitrary-length arbitrary-offset area of memory which resides + * within a 0 or higher order page. Multiple fragments within that page + * are individually refcounted, in the page's reference counter. + * + * The page_frag functions below provide a simple allocation framework for + * page fragments. This is used by the network stack and network device + * drivers to provide a backing region of memory for use as either an + * sk_buff->head, or to be used in the "frags" portion of skb_shared_info. + */ +static struct page *__page_frag_cache_refill(struct page_frag_cache *nc, + gfp_t gfp_mask) +{ + struct page *page = NULL; + gfp_t gfp = gfp_mask; + +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY | + __GFP_NOMEMALLOC; + page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, + PAGE_FRAG_CACHE_MAX_ORDER); + nc->size = page ? PAGE_FRAG_CACHE_MAX_SIZE : PAGE_SIZE; +#endif + if (unlikely(!page)) + page = alloc_pages_node(NUMA_NO_NODE, gfp, 0); + + nc->va = page ? page_address(page) : NULL; + + return page; +} + +void __page_frag_cache_drain(struct page *page, unsigned int count) +{ + VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); + + if (page_ref_sub_and_test(page, count)) + free_the_page(page, compound_order(page)); +} +EXPORT_SYMBOL(__page_frag_cache_drain); + +void *page_frag_alloc(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask) +{ + unsigned int size = PAGE_SIZE; + struct page *page; + int offset; + + if (unlikely(!nc->va)) { +refill: + page = __page_frag_cache_refill(nc, gfp_mask); + if (!page) + return NULL; + +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + /* if size can vary use size else just use PAGE_SIZE */ + size = nc->size; +#endif + /* Even if we own the page, we do not use atomic_set(). + * This would break get_page_unless_zero() users. + */ + page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE); + + /* reset page count bias and offset to start of new frag */ + nc->pfmemalloc = page_is_pfmemalloc(page); + nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; + nc->offset = size; + } + + offset = nc->offset - fragsz; + if (unlikely(offset < 0)) { + page = virt_to_page(nc->va); + + if (!page_ref_sub_and_test(page, nc->pagecnt_bias)) + goto refill; + + if (unlikely(nc->pfmemalloc)) { + free_the_page(page, compound_order(page)); + goto refill; + } + +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + /* if size can vary use size else just use PAGE_SIZE */ + size = nc->size; +#endif + /* OK, page count is 0, we can safely set it */ + set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1); + + /* reset page count bias and offset to start of new frag */ + nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; + offset = size - fragsz; + if (unlikely(offset < 0)) { + /* + * The caller is trying to allocate a fragment + * with fragsz > PAGE_SIZE but the cache isn't big + * enough to satisfy the request, this may + * happen in low memory conditions. + * We don't release the cache page because + * it could make memory pressure worse + * so we simply return NULL here. + */ + return NULL; + } + } + + nc->pagecnt_bias--; + nc->offset = offset; + + return nc->va + offset; +} +EXPORT_SYMBOL(page_frag_alloc); + +/* + * Frees a page fragment allocated out of either a compound or order 0 page. + */ +void page_frag_free(void *addr) +{ + struct page *page = virt_to_head_page(addr); + + if (unlikely(put_page_testzero(page))) + free_the_page(page, compound_order(page)); +} +EXPORT_SYMBOL(page_frag_free); + +static void *make_alloc_exact(unsigned long addr, unsigned int order, + size_t size) +{ + if (addr) { + unsigned long alloc_end = addr + (PAGE_SIZE << order); + unsigned long used = addr + PAGE_ALIGN(size); + + split_page(virt_to_page((void *)addr), order); + while (used < alloc_end) { + free_page(used); + used += PAGE_SIZE; + } + } + return (void *)addr; +} + +/** + * alloc_pages_exact - allocate an exact number physically-contiguous pages. + * @size: the number of bytes to allocate + * @gfp_mask: GFP flags for the allocation, must not contain __GFP_COMP + * + * This function is similar to alloc_pages(), except that it allocates the + * minimum number of pages to satisfy the request. alloc_pages() can only + * allocate memory in power-of-two pages. + * + * This function is also limited by MAX_ORDER. + * + * Memory allocated by this function must be released by free_pages_exact(). + * + * Return: pointer to the allocated area or %NULL in case of error. + */ +void *alloc_pages_exact(size_t size, gfp_t gfp_mask) +{ + unsigned int order = get_order(size); + unsigned long addr; + + if (WARN_ON_ONCE(gfp_mask & __GFP_COMP)) + gfp_mask &= ~__GFP_COMP; + + addr = __get_free_pages(gfp_mask, order); + return make_alloc_exact(addr, order, size); +} +EXPORT_SYMBOL(alloc_pages_exact); + +/** + * alloc_pages_exact_nid - allocate an exact number of physically-contiguous + * pages on a node. + * @nid: the preferred node ID where memory should be allocated + * @size: the number of bytes to allocate + * @gfp_mask: GFP flags for the allocation, must not contain __GFP_COMP + * + * Like alloc_pages_exact(), but try to allocate on node nid first before falling + * back. + * + * Return: pointer to the allocated area or %NULL in case of error. + */ +void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) +{ + unsigned int order = get_order(size); + struct page *p; + + if (WARN_ON_ONCE(gfp_mask & __GFP_COMP)) + gfp_mask &= ~__GFP_COMP; + + p = alloc_pages_node(nid, gfp_mask, order); + if (!p) + return NULL; + return make_alloc_exact((unsigned long)page_address(p), order, size); +} + +/** + * free_pages_exact - release memory allocated via alloc_pages_exact() + * @virt: the value returned by alloc_pages_exact. + * @size: size of allocation, same value as passed to alloc_pages_exact(). + * + * Release the memory allocated by a previous call to alloc_pages_exact. + */ +void free_pages_exact(void *virt, size_t size) +{ + unsigned long addr = (unsigned long)virt; + unsigned long end = addr + PAGE_ALIGN(size); + + while (addr < end) { + free_page(addr); + addr += PAGE_SIZE; + } +} +EXPORT_SYMBOL(free_pages_exact); + +/** + * nr_free_zone_pages - count number of pages beyond high watermark + * @offset: The zone index of the highest zone + * + * nr_free_zone_pages() counts the number of pages which are beyond the + * high watermark within all zones at or below a given zone index. For each + * zone, the number of pages is calculated as: + * + * nr_free_zone_pages = managed_pages - high_pages + * + * Return: number of pages beyond high watermark. + */ +static unsigned long nr_free_zone_pages(int offset) +{ + struct zoneref *z; + struct zone *zone; + + /* Just pick one node, since fallback list is circular */ + unsigned long sum = 0; + + struct zonelist *zonelist = node_zonelist(numa_node_id(), GFP_KERNEL); + + for_each_zone_zonelist(zone, z, zonelist, offset) { + unsigned long size = zone_managed_pages(zone); + unsigned long high = high_wmark_pages(zone); + if (size > high) + sum += size - high; + } + + return sum; +} + +/** + * nr_free_buffer_pages - count number of pages beyond high watermark + * + * nr_free_buffer_pages() counts the number of pages which are beyond the high + * watermark within ZONE_DMA and ZONE_NORMAL. + * + * Return: number of pages beyond high watermark within ZONE_DMA and + * ZONE_NORMAL. + */ +unsigned long nr_free_buffer_pages(void) +{ + return nr_free_zone_pages(gfp_zone(GFP_USER)); +} +EXPORT_SYMBOL_GPL(nr_free_buffer_pages); + +static inline void show_node(struct zone *zone) +{ + if (IS_ENABLED(CONFIG_NUMA)) + printk("Node %d ", zone_to_nid(zone)); +} + +long si_mem_available(void) +{ + long available; + unsigned long pagecache; + unsigned long wmark_low = 0; + unsigned long pages[NR_LRU_LISTS]; + unsigned long reclaimable; + struct zone *zone; + int lru; + + for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++) + pages[lru] = global_node_page_state(NR_LRU_BASE + lru); + + for_each_zone(zone) + wmark_low += low_wmark_pages(zone); + + /* + * Estimate the amount of memory available for userspace allocations, + * without causing swapping. + */ + available = global_zone_page_state(NR_FREE_PAGES) - totalreserve_pages; + + /* + * Not all the page cache can be freed, otherwise the system will + * start swapping. Assume at least half of the page cache, or the + * low watermark worth of cache, needs to stay. + */ + pagecache = pages[LRU_ACTIVE_FILE] + pages[LRU_INACTIVE_FILE]; + pagecache -= min(pagecache / 2, wmark_low); + available += pagecache; + + /* + * Part of the reclaimable slab and other kernel memory consists of + * items that are in use, and cannot be freed. Cap this estimate at the + * low watermark. + */ + reclaimable = global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B) + + global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE); + available += reclaimable - min(reclaimable / 2, wmark_low); + + if (available < 0) + available = 0; + return available; +} +EXPORT_SYMBOL_GPL(si_mem_available); + +void si_meminfo(struct sysinfo *val) +{ + val->totalram = totalram_pages(); + val->sharedram = global_node_page_state(NR_SHMEM); + val->freeram = global_zone_page_state(NR_FREE_PAGES); + val->bufferram = nr_blockdev_pages(); + val->totalhigh = totalhigh_pages(); + val->freehigh = nr_free_highpages(); + val->mem_unit = PAGE_SIZE; +} + +EXPORT_SYMBOL(si_meminfo); + +#ifdef CONFIG_NUMA +void si_meminfo_node(struct sysinfo *val, int nid) +{ + int zone_type; /* needs to be signed */ + unsigned long managed_pages = 0; + unsigned long managed_highpages = 0; + unsigned long free_highpages = 0; + pg_data_t *pgdat = NODE_DATA(nid); + + for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) + managed_pages += zone_managed_pages(&pgdat->node_zones[zone_type]); + val->totalram = managed_pages; + val->sharedram = node_page_state(pgdat, NR_SHMEM); + val->freeram = sum_zone_node_page_state(nid, NR_FREE_PAGES); +#ifdef CONFIG_HIGHMEM + for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) { + struct zone *zone = &pgdat->node_zones[zone_type]; + + if (is_highmem(zone)) { + managed_highpages += zone_managed_pages(zone); + free_highpages += zone_page_state(zone, NR_FREE_PAGES); + } + } + val->totalhigh = managed_highpages; + val->freehigh = free_highpages; +#else + val->totalhigh = managed_highpages; + val->freehigh = free_highpages; +#endif + val->mem_unit = PAGE_SIZE; +} +#endif + +/* + * Determine whether the node should be displayed or not, depending on whether + * SHOW_MEM_FILTER_NODES was passed to show_free_areas(). + */ +static bool show_mem_node_skip(unsigned int flags, int nid, nodemask_t *nodemask) +{ + if (!(flags & SHOW_MEM_FILTER_NODES)) + return false; + + /* + * no node mask - aka implicit memory numa policy. Do not bother with + * the synchronization - read_mems_allowed_begin - because we do not + * have to be precise here. + */ + if (!nodemask) + nodemask = &cpuset_current_mems_allowed; + + return !node_isset(nid, *nodemask); +} + +#define K(x) ((x) << (PAGE_SHIFT-10)) + +static void show_migration_types(unsigned char type) +{ + static const char types[MIGRATE_TYPES] = { + [MIGRATE_UNMOVABLE] = 'U', + [MIGRATE_MOVABLE] = 'M', + [MIGRATE_RECLAIMABLE] = 'E', + [MIGRATE_HIGHATOMIC] = 'H', +#ifdef CONFIG_CMA + [MIGRATE_CMA] = 'C', +#endif +#ifdef CONFIG_MEMORY_ISOLATION + [MIGRATE_ISOLATE] = 'I', +#endif + }; + char tmp[MIGRATE_TYPES + 1]; + char *p = tmp; + int i; + + for (i = 0; i < MIGRATE_TYPES; i++) { + if (type & (1 << i)) + *p++ = types[i]; + } + + *p = '\0'; + printk(KERN_CONT "(%s) ", tmp); +} + +/* + * Show free area list (used inside shift_scroll-lock stuff) + * We also calculate the percentage fragmentation. We do this by counting the + * memory on each free list with the exception of the first item on the list. + * + * Bits in @filter: + * SHOW_MEM_FILTER_NODES: suppress nodes that are not allowed by current's + * cpuset. + */ +void show_free_areas(unsigned int filter, nodemask_t *nodemask) +{ + unsigned long free_pcp = 0; + int cpu; + struct zone *zone; + pg_data_t *pgdat; + + for_each_populated_zone(zone) { + if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask)) + continue; + + for_each_online_cpu(cpu) + free_pcp += per_cpu_ptr(zone->pageset, cpu)->pcp.count; + } + + printk("active_anon:%lu inactive_anon:%lu isolated_anon:%lu\n" + " active_file:%lu inactive_file:%lu isolated_file:%lu\n" + " unevictable:%lu dirty:%lu writeback:%lu\n" + " slab_reclaimable:%lu slab_unreclaimable:%lu\n" + " mapped:%lu shmem:%lu pagetables:%lu bounce:%lu\n" + " free:%lu free_pcp:%lu free_cma:%lu\n", + global_node_page_state(NR_ACTIVE_ANON), + global_node_page_state(NR_INACTIVE_ANON), + global_node_page_state(NR_ISOLATED_ANON), + global_node_page_state(NR_ACTIVE_FILE), + global_node_page_state(NR_INACTIVE_FILE), + global_node_page_state(NR_ISOLATED_FILE), + global_node_page_state(NR_UNEVICTABLE), + global_node_page_state(NR_FILE_DIRTY), + global_node_page_state(NR_WRITEBACK), + global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B), + global_node_page_state_pages(NR_SLAB_UNRECLAIMABLE_B), + global_node_page_state(NR_FILE_MAPPED), + global_node_page_state(NR_SHMEM), + global_zone_page_state(NR_PAGETABLE), + global_zone_page_state(NR_BOUNCE), + global_zone_page_state(NR_FREE_PAGES), + free_pcp, + global_zone_page_state(NR_FREE_CMA_PAGES)); + + for_each_online_pgdat(pgdat) { + if (show_mem_node_skip(filter, pgdat->node_id, nodemask)) + continue; + + printk("Node %d" + " active_anon:%lukB" + " inactive_anon:%lukB" + " active_file:%lukB" + " inactive_file:%lukB" + " unevictable:%lukB" + " isolated(anon):%lukB" + " isolated(file):%lukB" + " mapped:%lukB" + " dirty:%lukB" + " writeback:%lukB" + " shmem:%lukB" +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + " shmem_thp: %lukB" + " shmem_pmdmapped: %lukB" + " anon_thp: %lukB" +#endif + " writeback_tmp:%lukB" + " kernel_stack:%lukB" +#ifdef CONFIG_SHADOW_CALL_STACK + " shadow_call_stack:%lukB" +#endif + " all_unreclaimable? %s" + "\n", + pgdat->node_id, + K(node_page_state(pgdat, NR_ACTIVE_ANON)), + K(node_page_state(pgdat, NR_INACTIVE_ANON)), + K(node_page_state(pgdat, NR_ACTIVE_FILE)), + K(node_page_state(pgdat, NR_INACTIVE_FILE)), + K(node_page_state(pgdat, NR_UNEVICTABLE)), + K(node_page_state(pgdat, NR_ISOLATED_ANON)), + K(node_page_state(pgdat, NR_ISOLATED_FILE)), + K(node_page_state(pgdat, NR_FILE_MAPPED)), + K(node_page_state(pgdat, NR_FILE_DIRTY)), + K(node_page_state(pgdat, NR_WRITEBACK)), + K(node_page_state(pgdat, NR_SHMEM)), +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + K(node_page_state(pgdat, NR_SHMEM_THPS) * HPAGE_PMD_NR), + K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED) + * HPAGE_PMD_NR), + K(node_page_state(pgdat, NR_ANON_THPS) * HPAGE_PMD_NR), +#endif + K(node_page_state(pgdat, NR_WRITEBACK_TEMP)), + node_page_state(pgdat, NR_KERNEL_STACK_KB), +#ifdef CONFIG_SHADOW_CALL_STACK + node_page_state(pgdat, NR_KERNEL_SCS_KB), +#endif + pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES ? + "yes" : "no"); + } + + for_each_populated_zone(zone) { + int i; + + if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask)) + continue; + + free_pcp = 0; + for_each_online_cpu(cpu) + free_pcp += per_cpu_ptr(zone->pageset, cpu)->pcp.count; + + show_node(zone); + printk(KERN_CONT + "%s" + " free:%lukB" + " min:%lukB" + " low:%lukB" + " high:%lukB" + " reserved_highatomic:%luKB" + " active_anon:%lukB" + " inactive_anon:%lukB" + " active_file:%lukB" + " inactive_file:%lukB" + " unevictable:%lukB" + " writepending:%lukB" + " present:%lukB" + " managed:%lukB" + " mlocked:%lukB" + " pagetables:%lukB" + " bounce:%lukB" + " free_pcp:%lukB" + " local_pcp:%ukB" + " free_cma:%lukB" + "\n", + zone->name, + K(zone_page_state(zone, NR_FREE_PAGES)), + K(min_wmark_pages(zone)), + K(low_wmark_pages(zone)), + K(high_wmark_pages(zone)), + K(zone->nr_reserved_highatomic), + K(zone_page_state(zone, NR_ZONE_ACTIVE_ANON)), + K(zone_page_state(zone, NR_ZONE_INACTIVE_ANON)), + K(zone_page_state(zone, NR_ZONE_ACTIVE_FILE)), + K(zone_page_state(zone, NR_ZONE_INACTIVE_FILE)), + K(zone_page_state(zone, NR_ZONE_UNEVICTABLE)), + K(zone_page_state(zone, NR_ZONE_WRITE_PENDING)), + K(zone->present_pages), + K(zone_managed_pages(zone)), + K(zone_page_state(zone, NR_MLOCK)), + K(zone_page_state(zone, NR_PAGETABLE)), + K(zone_page_state(zone, NR_BOUNCE)), + K(free_pcp), + K(this_cpu_read(zone->pageset->pcp.count)), + K(zone_page_state(zone, NR_FREE_CMA_PAGES))); + printk("lowmem_reserve[]:"); + for (i = 0; i < MAX_NR_ZONES; i++) + printk(KERN_CONT " %ld", zone->lowmem_reserve[i]); + printk(KERN_CONT "\n"); + } + + for_each_populated_zone(zone) { + unsigned int order; + unsigned long nr[MAX_ORDER], flags, total = 0; + unsigned char types[MAX_ORDER]; + + if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask)) + continue; + show_node(zone); + printk(KERN_CONT "%s: ", zone->name); + + spin_lock_irqsave(&zone->lock, flags); + for (order = 0; order < MAX_ORDER; order++) { + struct free_area *area = &zone->free_area[order]; + int type; + + nr[order] = area->nr_free; + total += nr[order] << order; + + types[order] = 0; + for (type = 0; type < MIGRATE_TYPES; type++) { + if (!free_area_empty(area, type)) + types[order] |= 1 << type; + } + } + spin_unlock_irqrestore(&zone->lock, flags); + for (order = 0; order < MAX_ORDER; order++) { + printk(KERN_CONT "%lu*%lukB ", + nr[order], K(1UL) << order); + if (nr[order]) + show_migration_types(types[order]); + } + printk(KERN_CONT "= %lukB\n", K(total)); + } + + hugetlb_show_meminfo(); + + printk("%ld total pagecache pages\n", global_node_page_state(NR_FILE_PAGES)); + + show_swap_cache_info(); +} + +static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref) +{ + zoneref->zone = zone; + zoneref->zone_idx = zone_idx(zone); +} + +/* + * Builds allocation fallback zone lists. + * + * Add all populated zones of a node to the zonelist. + */ +static int build_zonerefs_node(pg_data_t *pgdat, struct zoneref *zonerefs) +{ + struct zone *zone; + enum zone_type zone_type = MAX_NR_ZONES; + int nr_zones = 0; + + do { + zone_type--; + zone = pgdat->node_zones + zone_type; + if (populated_zone(zone)) { + zoneref_set_zone(zone, &zonerefs[nr_zones++]); + check_highest_zone(zone_type); + } + } while (zone_type); + + return nr_zones; +} + +#ifdef CONFIG_NUMA + +static int __parse_numa_zonelist_order(char *s) +{ + /* + * We used to support different zonlists modes but they turned + * out to be just not useful. Let's keep the warning in place + * if somebody still use the cmd line parameter so that we do + * not fail it silently + */ + if (!(*s == 'd' || *s == 'D' || *s == 'n' || *s == 'N')) { + pr_warn("Ignoring unsupported numa_zonelist_order value: %s\n", s); + return -EINVAL; + } + return 0; +} + +char numa_zonelist_order[] = "Node"; + +/* + * sysctl handler for numa_zonelist_order + */ +int numa_zonelist_order_handler(struct ctl_table *table, int write, + void *buffer, size_t *length, loff_t *ppos) +{ + if (write) + return __parse_numa_zonelist_order(buffer); + return proc_dostring(table, write, buffer, length, ppos); +} + + +#define MAX_NODE_LOAD (nr_online_nodes) +static int node_load[MAX_NUMNODES]; + +/** + * find_next_best_node - find the next node that should appear in a given node's fallback list + * @node: node whose fallback list we're appending + * @used_node_mask: nodemask_t of already used nodes + * + * We use a number of factors to determine which is the next node that should + * appear on a given node's fallback list. The node should not have appeared + * already in @node's fallback list, and it should be the next closest node + * according to the distance array (which contains arbitrary distance values + * from each node to each node in the system), and should also prefer nodes + * with no CPUs, since presumably they'll have very little allocation pressure + * on them otherwise. + * + * Return: node id of the found node or %NUMA_NO_NODE if no node is found. + */ +static int find_next_best_node(int node, nodemask_t *used_node_mask) +{ + int n, val; + int min_val = INT_MAX; + int best_node = NUMA_NO_NODE; + + /* Use the local node if we haven't already */ + if (!node_isset(node, *used_node_mask)) { + node_set(node, *used_node_mask); + return node; + } + + for_each_node_state(n, N_MEMORY) { + + /* Don't want a node to appear more than once */ + if (node_isset(n, *used_node_mask)) + continue; + + /* Use the distance array to find the distance */ + val = node_distance(node, n); + + /* Penalize nodes under us ("prefer the next node") */ + val += (n < node); + + /* Give preference to headless and unused nodes */ + if (!cpumask_empty(cpumask_of_node(n))) + val += PENALTY_FOR_NODE_WITH_CPUS; + + /* Slight preference for less loaded node */ + val *= (MAX_NODE_LOAD*MAX_NUMNODES); + val += node_load[n]; + + if (val < min_val) { + min_val = val; + best_node = n; + } + } + + if (best_node >= 0) + node_set(best_node, *used_node_mask); + + return best_node; +} + + +/* + * Build zonelists ordered by node and zones within node. + * This results in maximum locality--normal zone overflows into local + * DMA zone, if any--but risks exhausting DMA zone. + */ +static void build_zonelists_in_node_order(pg_data_t *pgdat, int *node_order, + unsigned nr_nodes) +{ + struct zoneref *zonerefs; + int i; + + zonerefs = pgdat->node_zonelists[ZONELIST_FALLBACK]._zonerefs; + + for (i = 0; i < nr_nodes; i++) { + int nr_zones; + + pg_data_t *node = NODE_DATA(node_order[i]); + + nr_zones = build_zonerefs_node(node, zonerefs); + zonerefs += nr_zones; + } + zonerefs->zone = NULL; + zonerefs->zone_idx = 0; +} + +/* + * Build gfp_thisnode zonelists + */ +static void build_thisnode_zonelists(pg_data_t *pgdat) +{ + struct zoneref *zonerefs; + int nr_zones; + + zonerefs = pgdat->node_zonelists[ZONELIST_NOFALLBACK]._zonerefs; + nr_zones = build_zonerefs_node(pgdat, zonerefs); + zonerefs += nr_zones; + zonerefs->zone = NULL; + zonerefs->zone_idx = 0; +} + +/* + * Build zonelists ordered by zone and nodes within zones. + * This results in conserving DMA zone[s] until all Normal memory is + * exhausted, but results in overflowing to remote node while memory + * may still exist in local DMA zone. + */ + +static void build_zonelists(pg_data_t *pgdat) +{ + static int node_order[MAX_NUMNODES]; + int node, load, nr_nodes = 0; + nodemask_t used_mask = NODE_MASK_NONE; + int local_node, prev_node; + + /* NUMA-aware ordering of nodes */ + local_node = pgdat->node_id; + load = nr_online_nodes; + prev_node = local_node; + + memset(node_order, 0, sizeof(node_order)); + while ((node = find_next_best_node(local_node, &used_mask)) >= 0) { + /* + * We don't want to pressure a particular node. + * So adding penalty to the first node in same + * distance group to make it round-robin. + */ + if (node_distance(local_node, node) != + node_distance(local_node, prev_node)) + node_load[node] = load; + + node_order[nr_nodes++] = node; + prev_node = node; + load--; + } + + build_zonelists_in_node_order(pgdat, node_order, nr_nodes); + build_thisnode_zonelists(pgdat); +} + +#ifdef CONFIG_HAVE_MEMORYLESS_NODES +/* + * Return node id of node used for "local" allocations. + * I.e., first node id of first zone in arg node's generic zonelist. + * Used for initializing percpu 'numa_mem', which is used primarily + * for kernel allocations, so use GFP_KERNEL flags to locate zonelist. + */ +int local_memory_node(int node) +{ + struct zoneref *z; + + z = first_zones_zonelist(node_zonelist(node, GFP_KERNEL), + gfp_zone(GFP_KERNEL), + NULL); + return zone_to_nid(z->zone); +} +#endif + +static void setup_min_unmapped_ratio(void); +static void setup_min_slab_ratio(void); +#else /* CONFIG_NUMA */ + +static void build_zonelists(pg_data_t *pgdat) +{ + int node, local_node; + struct zoneref *zonerefs; + int nr_zones; + + local_node = pgdat->node_id; + + zonerefs = pgdat->node_zonelists[ZONELIST_FALLBACK]._zonerefs; + nr_zones = build_zonerefs_node(pgdat, zonerefs); + zonerefs += nr_zones; + + /* + * Now we build the zonelist so that it contains the zones + * of all the other nodes. + * We don't want to pressure a particular node, so when + * building the zones for node N, we make sure that the + * zones coming right after the local ones are those from + * node N+1 (modulo N) + */ + for (node = local_node + 1; node < MAX_NUMNODES; node++) { + if (!node_online(node)) + continue; + nr_zones = build_zonerefs_node(NODE_DATA(node), zonerefs); + zonerefs += nr_zones; + } + for (node = 0; node < local_node; node++) { + if (!node_online(node)) + continue; + nr_zones = build_zonerefs_node(NODE_DATA(node), zonerefs); + zonerefs += nr_zones; + } + + zonerefs->zone = NULL; + zonerefs->zone_idx = 0; +} + +#endif /* CONFIG_NUMA */ + +/* + * Boot pageset table. One per cpu which is going to be used for all + * zones and all nodes. The parameters will be set in such a way + * that an item put on a list will immediately be handed over to + * the buddy list. This is safe since pageset manipulation is done + * with interrupts disabled. + * + * The boot_pagesets must be kept even after bootup is complete for + * unused processors and/or zones. They do play a role for bootstrapping + * hotplugged processors. + * + * zoneinfo_show() and maybe other functions do + * not check if the processor is online before following the pageset pointer. + * Other parts of the kernel may not check if the zone is available. + */ +static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch); +static DEFINE_PER_CPU(struct per_cpu_pageset, boot_pageset); +static DEFINE_PER_CPU(struct per_cpu_nodestat, boot_nodestats); + +static void __build_all_zonelists(void *data) +{ + int nid; + int __maybe_unused cpu; + pg_data_t *self = data; + unsigned long flags; + + /* + * Explicitly disable this CPU's interrupts before taking seqlock + * to prevent any IRQ handler from calling into the page allocator + * (e.g. GFP_ATOMIC) that could hit zonelist_iter_begin and livelock. + */ + local_irq_save(flags); + /* + * Explicitly disable this CPU's synchronous printk() before taking + * seqlock to prevent any printk() from trying to hold port->lock, for + * tty_insert_flip_string_and_push_buffer() on other CPU might be + * calling kmalloc(GFP_ATOMIC | __GFP_NOWARN) with port->lock held. + */ + printk_deferred_enter(); + write_seqlock(&zonelist_update_seq); + +#ifdef CONFIG_NUMA + memset(node_load, 0, sizeof(node_load)); +#endif + + /* + * This node is hotadded and no memory is yet present. So just + * building zonelists is fine - no need to touch other nodes. + */ + if (self && !node_online(self->node_id)) { + build_zonelists(self); + } else { + for_each_online_node(nid) { + pg_data_t *pgdat = NODE_DATA(nid); + + build_zonelists(pgdat); + } + +#ifdef CONFIG_HAVE_MEMORYLESS_NODES + /* + * We now know the "local memory node" for each node-- + * i.e., the node of the first zone in the generic zonelist. + * Set up numa_mem percpu variable for on-line cpus. During + * boot, only the boot cpu should be on-line; we'll init the + * secondary cpus' numa_mem as they come on-line. During + * node/memory hotplug, we'll fixup all on-line cpus. + */ + for_each_online_cpu(cpu) + set_cpu_numa_mem(cpu, local_memory_node(cpu_to_node(cpu))); +#endif + } + + write_sequnlock(&zonelist_update_seq); + printk_deferred_exit(); + local_irq_restore(flags); +} + +static noinline void __init +build_all_zonelists_init(void) +{ + int cpu; + + __build_all_zonelists(NULL); + + /* + * Initialize the boot_pagesets that are going to be used + * for bootstrapping processors. The real pagesets for + * each zone will be allocated later when the per cpu + * allocator is available. + * + * boot_pagesets are used also for bootstrapping offline + * cpus if the system is already booted because the pagesets + * are needed to initialize allocators on a specific cpu too. + * F.e. the percpu allocator needs the page allocator which + * needs the percpu allocator in order to allocate its pagesets + * (a chicken-egg dilemma). + */ + for_each_possible_cpu(cpu) + setup_pageset(&per_cpu(boot_pageset, cpu), 0); + + mminit_verify_zonelist(); + cpuset_init_current_mems_allowed(); +} + +/* + * unless system_state == SYSTEM_BOOTING. + * + * __ref due to call of __init annotated helper build_all_zonelists_init + * [protected by SYSTEM_BOOTING]. + */ +void __ref build_all_zonelists(pg_data_t *pgdat) +{ + unsigned long vm_total_pages; + + if (system_state == SYSTEM_BOOTING) { + build_all_zonelists_init(); + } else { + __build_all_zonelists(pgdat); + /* cpuset refresh routine should be here */ + } + /* Get the number of free pages beyond high watermark in all zones. */ + vm_total_pages = nr_free_zone_pages(gfp_zone(GFP_HIGHUSER_MOVABLE)); + /* + * Disable grouping by mobility if the number of pages in the + * system is too low to allow the mechanism to work. It would be + * more accurate, but expensive to check per-zone. This check is + * made on memory-hotadd so a system can start with mobility + * disabled and enable it later + */ + if (vm_total_pages < (pageblock_nr_pages * MIGRATE_TYPES)) + page_group_by_mobility_disabled = 1; + else + page_group_by_mobility_disabled = 0; + + pr_info("Built %u zonelists, mobility grouping %s. Total pages: %ld\n", + nr_online_nodes, + page_group_by_mobility_disabled ? "off" : "on", + vm_total_pages); +#ifdef CONFIG_NUMA + pr_info("Policy zone: %s\n", zone_names[policy_zone]); +#endif +} + +/* If zone is ZONE_MOVABLE but memory is mirrored, it is an overlapped init */ +static bool __meminit +overlap_memmap_init(unsigned long zone, unsigned long *pfn) +{ + static struct memblock_region *r; + + if (mirrored_kernelcore && zone == ZONE_MOVABLE) { + if (!r || *pfn >= memblock_region_memory_end_pfn(r)) { + for_each_mem_region(r) { + if (*pfn < memblock_region_memory_end_pfn(r)) + break; + } + } + if (*pfn >= memblock_region_memory_base_pfn(r) && + memblock_is_mirror(r)) { + *pfn = memblock_region_memory_end_pfn(r); + return true; + } + } + return false; +} + +/* + * Initially all pages are reserved - free ones are freed + * up by memblock_free_all() once the early boot process is + * done. Non-atomic initialization, single-pass. + * + * All aligned pageblocks are initialized to the specified migratetype + * (usually MIGRATE_MOVABLE). Besides setting the migratetype, no related + * zone stats (e.g., nr_isolate_pageblock) are touched. + */ +void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, + unsigned long start_pfn, unsigned long zone_end_pfn, + enum meminit_context context, + struct vmem_altmap *altmap, int migratetype) +{ + unsigned long pfn, end_pfn = start_pfn + size; + struct page *page; + + if (highest_memmap_pfn < end_pfn - 1) + highest_memmap_pfn = end_pfn - 1; + +#ifdef CONFIG_ZONE_DEVICE + /* + * Honor reservation requested by the driver for this ZONE_DEVICE + * memory. We limit the total number of pages to initialize to just + * those that might contain the memory mapping. We will defer the + * ZONE_DEVICE page initialization until after we have released + * the hotplug lock. + */ + if (zone == ZONE_DEVICE) { + if (!altmap) + return; + + if (start_pfn == altmap->base_pfn) + start_pfn += altmap->reserve; + end_pfn = altmap->base_pfn + vmem_altmap_offset(altmap); + } +#endif + + for (pfn = start_pfn; pfn < end_pfn; ) { + /* + * There can be holes in boot-time mem_map[]s handed to this + * function. They do not exist on hotplugged memory. + */ + if (context == MEMINIT_EARLY) { + if (overlap_memmap_init(zone, &pfn)) + continue; + if (defer_init(nid, pfn, zone_end_pfn)) + break; + } + + page = pfn_to_page(pfn); + __init_single_page(page, pfn, zone, nid); + if (context == MEMINIT_HOTPLUG) + __SetPageReserved(page); + + /* + * Usually, we want to mark the pageblock MIGRATE_MOVABLE, + * such that unmovable allocations won't be scattered all + * over the place during system boot. + */ + if (IS_ALIGNED(pfn, pageblock_nr_pages)) { + set_pageblock_migratetype(page, migratetype); + cond_resched(); + } + pfn++; + } +} + +#ifdef CONFIG_ZONE_DEVICE +void __ref memmap_init_zone_device(struct zone *zone, + unsigned long start_pfn, + unsigned long nr_pages, + struct dev_pagemap *pgmap) +{ + unsigned long pfn, end_pfn = start_pfn + nr_pages; + struct pglist_data *pgdat = zone->zone_pgdat; + struct vmem_altmap *altmap = pgmap_altmap(pgmap); + unsigned long zone_idx = zone_idx(zone); + unsigned long start = jiffies; + int nid = pgdat->node_id; + + if (WARN_ON_ONCE(!pgmap || zone_idx(zone) != ZONE_DEVICE)) + return; + + /* + * The call to memmap_init should have already taken care + * of the pages reserved for the memmap, so we can just jump to + * the end of that region and start processing the device pages. + */ + if (altmap) { + start_pfn = altmap->base_pfn + vmem_altmap_offset(altmap); + nr_pages = end_pfn - start_pfn; + } + + for (pfn = start_pfn; pfn < end_pfn; pfn++) { + struct page *page = pfn_to_page(pfn); + + __init_single_page(page, pfn, zone_idx, nid); + + /* + * Mark page reserved as it will need to wait for onlining + * phase for it to be fully associated with a zone. + * + * We can use the non-atomic __set_bit operation for setting + * the flag as we are still initializing the pages. + */ + __SetPageReserved(page); + + /* + * ZONE_DEVICE pages union ->lru with a ->pgmap back pointer + * and zone_device_data. It is a bug if a ZONE_DEVICE page is + * ever freed or placed on a driver-private list. + */ + page->pgmap = pgmap; + page->zone_device_data = NULL; + + /* + * Mark the block movable so that blocks are reserved for + * movable at startup. This will force kernel allocations + * to reserve their blocks rather than leaking throughout + * the address space during boot when many long-lived + * kernel allocations are made. + * + * Please note that MEMINIT_HOTPLUG path doesn't clear memmap + * because this is done early in section_activate() + */ + if (IS_ALIGNED(pfn, pageblock_nr_pages)) { + set_pageblock_migratetype(page, MIGRATE_MOVABLE); + cond_resched(); + } + } + + pr_info("%s initialised %lu pages in %ums\n", __func__, + nr_pages, jiffies_to_msecs(jiffies - start)); +} + +#endif +static void __meminit zone_init_free_lists(struct zone *zone) +{ + unsigned int order, t; + for_each_migratetype_order(order, t) { + INIT_LIST_HEAD(&zone->free_area[order].free_list[t]); + zone->free_area[order].nr_free = 0; + } +} + +#if !defined(CONFIG_FLAT_NODE_MEM_MAP) +/* + * Only struct pages that correspond to ranges defined by memblock.memory + * are zeroed and initialized by going through __init_single_page() during + * memmap_init_zone_range(). + * + * But, there could be struct pages that correspond to holes in + * memblock.memory. This can happen because of the following reasons: + * - physical memory bank size is not necessarily the exact multiple of the + * arbitrary section size + * - early reserved memory may not be listed in memblock.memory + * - memory layouts defined with memmap= kernel parameter may not align + * nicely with memmap sections + * + * Explicitly initialize those struct pages so that: + * - PG_Reserved is set + * - zone and node links point to zone and node that span the page if the + * hole is in the middle of a zone + * - zone and node links point to adjacent zone/node if the hole falls on + * the zone boundary; the pages in such holes will be prepended to the + * zone/node above the hole except for the trailing pages in the last + * section that will be appended to the zone/node below. + */ +static void __init init_unavailable_range(unsigned long spfn, + unsigned long epfn, + int zone, int node) +{ + unsigned long pfn; + u64 pgcnt = 0; + + for (pfn = spfn; pfn < epfn; pfn++) { + if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) { + pfn = ALIGN_DOWN(pfn, pageblock_nr_pages) + + pageblock_nr_pages - 1; + continue; + } + __init_single_page(pfn_to_page(pfn), pfn, zone, node); + __SetPageReserved(pfn_to_page(pfn)); + pgcnt++; + } + + if (pgcnt) + pr_info("On node %d, zone %s: %lld pages in unavailable ranges", + node, zone_names[zone], pgcnt); +} +#else +static inline void init_unavailable_range(unsigned long spfn, + unsigned long epfn, + int zone, int node) +{ +} +#endif + +static void __init memmap_init_zone_range(struct zone *zone, + unsigned long start_pfn, + unsigned long end_pfn, + unsigned long *hole_pfn) +{ + unsigned long zone_start_pfn = zone->zone_start_pfn; + unsigned long zone_end_pfn = zone_start_pfn + zone->spanned_pages; + int nid = zone_to_nid(zone), zone_id = zone_idx(zone); + + start_pfn = clamp(start_pfn, zone_start_pfn, zone_end_pfn); + end_pfn = clamp(end_pfn, zone_start_pfn, zone_end_pfn); + + if (start_pfn >= end_pfn) + return; + + memmap_init_zone(end_pfn - start_pfn, nid, zone_id, start_pfn, + zone_end_pfn, MEMINIT_EARLY, NULL, MIGRATE_MOVABLE); + + if (*hole_pfn < start_pfn) + init_unavailable_range(*hole_pfn, start_pfn, zone_id, nid); + + *hole_pfn = end_pfn; +} + +void __init __weak memmap_init(void) +{ + unsigned long start_pfn, end_pfn; + unsigned long hole_pfn = 0; + int i, j, zone_id, nid; + + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { + struct pglist_data *node = NODE_DATA(nid); + + for (j = 0; j < MAX_NR_ZONES; j++) { + struct zone *zone = node->node_zones + j; + + if (!populated_zone(zone)) + continue; + + memmap_init_zone_range(zone, start_pfn, end_pfn, + &hole_pfn); + zone_id = j; + } + } + +#ifdef CONFIG_SPARSEMEM + /* + * Initialize the memory map for hole in the range [memory_end, + * section_end]. + * Append the pages in this hole to the highest zone in the last + * node. + * The call to init_unavailable_range() is outside the ifdef to + * silence the compiler warining about zone_id set but not used; + * for FLATMEM it is a nop anyway + */ + end_pfn = round_up(end_pfn, PAGES_PER_SECTION); + if (hole_pfn < end_pfn) +#endif + init_unavailable_range(hole_pfn, end_pfn, zone_id, nid); +} + +/* A stub for backwards compatibility with custom implementatin on IA-64 */ +void __meminit __weak arch_memmap_init(unsigned long size, int nid, + unsigned long zone, + unsigned long range_start_pfn) +{ +} + +static int zone_batchsize(struct zone *zone) +{ +#ifdef CONFIG_MMU + int batch; + + /* + * The per-cpu-pages pools are set to around 1000th of the + * size of the zone. + */ + batch = zone_managed_pages(zone) / 1024; + /* But no more than a meg. */ + if (batch * PAGE_SIZE > 1024 * 1024) + batch = (1024 * 1024) / PAGE_SIZE; + batch /= 4; /* We effectively *= 4 below */ + if (batch < 1) + batch = 1; + + /* + * Clamp the batch to a 2^n - 1 value. Having a power + * of 2 value was found to be more likely to have + * suboptimal cache aliasing properties in some cases. + * + * For example if 2 tasks are alternately allocating + * batches of pages, one task can end up with a lot + * of pages of one half of the possible page colors + * and the other with pages of the other colors. + */ + batch = rounddown_pow_of_two(batch + batch/2) - 1; + + return batch; + +#else + /* The deferral and batching of frees should be suppressed under NOMMU + * conditions. + * + * The problem is that NOMMU needs to be able to allocate large chunks + * of contiguous memory as there's no hardware page translation to + * assemble apparent contiguous memory from discontiguous pages. + * + * Queueing large contiguous runs of pages for batching, however, + * causes the pages to actually be freed in smaller chunks. As there + * can be a significant delay between the individual batches being + * recycled, this leads to the once large chunks of space being + * fragmented and becoming unavailable for high-order allocations. + */ + return 0; +#endif +} + +/* + * pcp->high and pcp->batch values are related and dependent on one another: + * ->batch must never be higher then ->high. + * The following function updates them in a safe manner without read side + * locking. + * + * Any new users of pcp->batch and pcp->high should ensure they can cope with + * those fields changing asynchronously (acording to the above rule). + * + * mutex_is_locked(&pcp_batch_high_lock) required when calling this function + * outside of boot time (or some other assurance that no concurrent updaters + * exist). + */ +static void pageset_update(struct per_cpu_pages *pcp, unsigned long high, + unsigned long batch) +{ + /* start with a fail safe value for batch */ + pcp->batch = 1; + smp_wmb(); + + /* Update high, then batch, in order */ + pcp->high = high; + smp_wmb(); + + pcp->batch = batch; +} + +/* a companion to pageset_set_high() */ +static void pageset_set_batch(struct per_cpu_pageset *p, unsigned long batch) +{ + pageset_update(&p->pcp, 6 * batch, max(1UL, 1 * batch)); +} + +static void pageset_init(struct per_cpu_pageset *p) +{ + struct per_cpu_pages *pcp; + int migratetype; + + memset(p, 0, sizeof(*p)); + + pcp = &p->pcp; + for (migratetype = 0; migratetype < MIGRATE_PCPTYPES; migratetype++) + INIT_LIST_HEAD(&pcp->lists[migratetype]); +} + +static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch) +{ + pageset_init(p); + pageset_set_batch(p, batch); +} + +/* + * pageset_set_high() sets the high water mark for hot per_cpu_pagelist + * to the value high for the pageset p. + */ +static void pageset_set_high(struct per_cpu_pageset *p, + unsigned long high) +{ + unsigned long batch = max(1UL, high / 4); + if ((high / 4) > (PAGE_SHIFT * 8)) + batch = PAGE_SHIFT * 8; + + pageset_update(&p->pcp, high, batch); +} + +static void pageset_set_high_and_batch(struct zone *zone, + struct per_cpu_pageset *pcp) +{ + if (percpu_pagelist_fraction) + pageset_set_high(pcp, + (zone_managed_pages(zone) / + percpu_pagelist_fraction)); + else + pageset_set_batch(pcp, zone_batchsize(zone)); +} + +static void __meminit zone_pageset_init(struct zone *zone, int cpu) +{ + struct per_cpu_pageset *pcp = per_cpu_ptr(zone->pageset, cpu); + + pageset_init(pcp); + pageset_set_high_and_batch(zone, pcp); +} + +void __meminit setup_zone_pageset(struct zone *zone) +{ + int cpu; + zone->pageset = alloc_percpu(struct per_cpu_pageset); + for_each_possible_cpu(cpu) + zone_pageset_init(zone, cpu); +} + +/* + * Allocate per cpu pagesets and initialize them. + * Before this call only boot pagesets were available. + */ +void __init setup_per_cpu_pageset(void) +{ + struct pglist_data *pgdat; + struct zone *zone; + int __maybe_unused cpu; + + for_each_populated_zone(zone) + setup_zone_pageset(zone); + +#ifdef CONFIG_NUMA + /* + * Unpopulated zones continue using the boot pagesets. + * The numa stats for these pagesets need to be reset. + * Otherwise, they will end up skewing the stats of + * the nodes these zones are associated with. + */ + for_each_possible_cpu(cpu) { + struct per_cpu_pageset *pcp = &per_cpu(boot_pageset, cpu); + memset(pcp->vm_numa_stat_diff, 0, + sizeof(pcp->vm_numa_stat_diff)); + } +#endif + + for_each_online_pgdat(pgdat) + pgdat->per_cpu_nodestats = + alloc_percpu(struct per_cpu_nodestat); +} + +static __meminit void zone_pcp_init(struct zone *zone) +{ + /* + * per cpu subsystem is not up at this point. The following code + * relies on the ability of the linker to provide the + * offset of a (static) per cpu variable into the per cpu area. + */ + zone->pageset = &boot_pageset; + + if (populated_zone(zone)) + printk(KERN_DEBUG " %s zone: %lu pages, LIFO batch:%u\n", + zone->name, zone->present_pages, + zone_batchsize(zone)); +} + +void __meminit init_currently_empty_zone(struct zone *zone, + unsigned long zone_start_pfn, + unsigned long size) +{ + struct pglist_data *pgdat = zone->zone_pgdat; + int zone_idx = zone_idx(zone) + 1; + + if (zone_idx > pgdat->nr_zones) + pgdat->nr_zones = zone_idx; + + zone->zone_start_pfn = zone_start_pfn; + + mminit_dprintk(MMINIT_TRACE, "memmap_init", + "Initialising map node %d zone %lu pfns %lu -> %lu\n", + pgdat->node_id, + (unsigned long)zone_idx(zone), + zone_start_pfn, (zone_start_pfn + size)); + + zone_init_free_lists(zone); + zone->initialized = 1; +} + +/** + * get_pfn_range_for_nid - Return the start and end page frames for a node + * @nid: The nid to return the range for. If MAX_NUMNODES, the min and max PFN are returned. + * @start_pfn: Passed by reference. On return, it will have the node start_pfn. + * @end_pfn: Passed by reference. On return, it will have the node end_pfn. + * + * It returns the start and end page frame of a node based on information + * provided by memblock_set_node(). If called for a node + * with no available memory, a warning is printed and the start and end + * PFNs will be 0. + */ +void __init get_pfn_range_for_nid(unsigned int nid, + unsigned long *start_pfn, unsigned long *end_pfn) +{ + unsigned long this_start_pfn, this_end_pfn; + int i; + + *start_pfn = -1UL; + *end_pfn = 0; + + for_each_mem_pfn_range(i, nid, &this_start_pfn, &this_end_pfn, NULL) { + *start_pfn = min(*start_pfn, this_start_pfn); + *end_pfn = max(*end_pfn, this_end_pfn); + } + + if (*start_pfn == -1UL) + *start_pfn = 0; +} + +/* + * This finds a zone that can be used for ZONE_MOVABLE pages. The + * assumption is made that zones within a node are ordered in monotonic + * increasing memory addresses so that the "highest" populated zone is used + */ +static void __init find_usable_zone_for_movable(void) +{ + int zone_index; + for (zone_index = MAX_NR_ZONES - 1; zone_index >= 0; zone_index--) { + if (zone_index == ZONE_MOVABLE) + continue; + + if (arch_zone_highest_possible_pfn[zone_index] > + arch_zone_lowest_possible_pfn[zone_index]) + break; + } + + VM_BUG_ON(zone_index == -1); + movable_zone = zone_index; +} + +/* + * The zone ranges provided by the architecture do not include ZONE_MOVABLE + * because it is sized independent of architecture. Unlike the other zones, + * the starting point for ZONE_MOVABLE is not fixed. It may be different + * in each node depending on the size of each node and how evenly kernelcore + * is distributed. This helper function adjusts the zone ranges + * provided by the architecture for a given node by using the end of the + * highest usable zone for ZONE_MOVABLE. This preserves the assumption that + * zones within a node are in order of monotonic increases memory addresses + */ +static void __init adjust_zone_range_for_zone_movable(int nid, + unsigned long zone_type, + unsigned long node_start_pfn, + unsigned long node_end_pfn, + unsigned long *zone_start_pfn, + unsigned long *zone_end_pfn) +{ + /* Only adjust if ZONE_MOVABLE is on this node */ + if (zone_movable_pfn[nid]) { + /* Size ZONE_MOVABLE */ + if (zone_type == ZONE_MOVABLE) { + *zone_start_pfn = zone_movable_pfn[nid]; + *zone_end_pfn = min(node_end_pfn, + arch_zone_highest_possible_pfn[movable_zone]); + + /* Adjust for ZONE_MOVABLE starting within this range */ + } else if (!mirrored_kernelcore && + *zone_start_pfn < zone_movable_pfn[nid] && + *zone_end_pfn > zone_movable_pfn[nid]) { + *zone_end_pfn = zone_movable_pfn[nid]; + + /* Check if this whole range is within ZONE_MOVABLE */ + } else if (*zone_start_pfn >= zone_movable_pfn[nid]) + *zone_start_pfn = *zone_end_pfn; + } +} + +/* + * Return the number of pages a zone spans in a node, including holes + * present_pages = zone_spanned_pages_in_node() - zone_absent_pages_in_node() + */ +static unsigned long __init zone_spanned_pages_in_node(int nid, + unsigned long zone_type, + unsigned long node_start_pfn, + unsigned long node_end_pfn, + unsigned long *zone_start_pfn, + unsigned long *zone_end_pfn) +{ + unsigned long zone_low = arch_zone_lowest_possible_pfn[zone_type]; + unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type]; + /* When hotadd a new node from cpu_up(), the node should be empty */ + if (!node_start_pfn && !node_end_pfn) + return 0; + + /* Get the start and end of the zone */ + *zone_start_pfn = clamp(node_start_pfn, zone_low, zone_high); + *zone_end_pfn = clamp(node_end_pfn, zone_low, zone_high); + adjust_zone_range_for_zone_movable(nid, zone_type, + node_start_pfn, node_end_pfn, + zone_start_pfn, zone_end_pfn); + + /* Check that this node has pages within the zone's required range */ + if (*zone_end_pfn < node_start_pfn || *zone_start_pfn > node_end_pfn) + return 0; + + /* Move the zone boundaries inside the node if necessary */ + *zone_end_pfn = min(*zone_end_pfn, node_end_pfn); + *zone_start_pfn = max(*zone_start_pfn, node_start_pfn); + + /* Return the spanned pages */ + return *zone_end_pfn - *zone_start_pfn; +} + +/* + * Return the number of holes in a range on a node. If nid is MAX_NUMNODES, + * then all holes in the requested range will be accounted for. + */ +unsigned long __init __absent_pages_in_range(int nid, + unsigned long range_start_pfn, + unsigned long range_end_pfn) +{ + unsigned long nr_absent = range_end_pfn - range_start_pfn; + unsigned long start_pfn, end_pfn; + int i; + + for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) { + start_pfn = clamp(start_pfn, range_start_pfn, range_end_pfn); + end_pfn = clamp(end_pfn, range_start_pfn, range_end_pfn); + nr_absent -= end_pfn - start_pfn; + } + return nr_absent; +} + +/** + * absent_pages_in_range - Return number of page frames in holes within a range + * @start_pfn: The start PFN to start searching for holes + * @end_pfn: The end PFN to stop searching for holes + * + * Return: the number of pages frames in memory holes within a range. + */ +unsigned long __init absent_pages_in_range(unsigned long start_pfn, + unsigned long end_pfn) +{ + return __absent_pages_in_range(MAX_NUMNODES, start_pfn, end_pfn); +} + +/* Return the number of page frames in holes in a zone on a node */ +static unsigned long __init zone_absent_pages_in_node(int nid, + unsigned long zone_type, + unsigned long node_start_pfn, + unsigned long node_end_pfn) +{ + unsigned long zone_low = arch_zone_lowest_possible_pfn[zone_type]; + unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type]; + unsigned long zone_start_pfn, zone_end_pfn; + unsigned long nr_absent; + + /* When hotadd a new node from cpu_up(), the node should be empty */ + if (!node_start_pfn && !node_end_pfn) + return 0; + + zone_start_pfn = clamp(node_start_pfn, zone_low, zone_high); + zone_end_pfn = clamp(node_end_pfn, zone_low, zone_high); + + adjust_zone_range_for_zone_movable(nid, zone_type, + node_start_pfn, node_end_pfn, + &zone_start_pfn, &zone_end_pfn); + nr_absent = __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn); + + /* + * ZONE_MOVABLE handling. + * Treat pages to be ZONE_MOVABLE in ZONE_NORMAL as absent pages + * and vice versa. + */ + if (mirrored_kernelcore && zone_movable_pfn[nid]) { + unsigned long start_pfn, end_pfn; + struct memblock_region *r; + + for_each_mem_region(r) { + start_pfn = clamp(memblock_region_memory_base_pfn(r), + zone_start_pfn, zone_end_pfn); + end_pfn = clamp(memblock_region_memory_end_pfn(r), + zone_start_pfn, zone_end_pfn); + + if (zone_type == ZONE_MOVABLE && + memblock_is_mirror(r)) + nr_absent += end_pfn - start_pfn; + + if (zone_type == ZONE_NORMAL && + !memblock_is_mirror(r)) + nr_absent += end_pfn - start_pfn; + } + } + + return nr_absent; +} + +static void __init calculate_node_totalpages(struct pglist_data *pgdat, + unsigned long node_start_pfn, + unsigned long node_end_pfn) +{ + unsigned long realtotalpages = 0, totalpages = 0; + enum zone_type i; + + for (i = 0; i < MAX_NR_ZONES; i++) { + struct zone *zone = pgdat->node_zones + i; + unsigned long zone_start_pfn, zone_end_pfn; + unsigned long spanned, absent; + unsigned long size, real_size; + + spanned = zone_spanned_pages_in_node(pgdat->node_id, i, + node_start_pfn, + node_end_pfn, + &zone_start_pfn, + &zone_end_pfn); + absent = zone_absent_pages_in_node(pgdat->node_id, i, + node_start_pfn, + node_end_pfn); + + size = spanned; + real_size = size - absent; + + if (size) + zone->zone_start_pfn = zone_start_pfn; + else + zone->zone_start_pfn = 0; + zone->spanned_pages = size; + zone->present_pages = real_size; + + totalpages += size; + realtotalpages += real_size; + } + + pgdat->node_spanned_pages = totalpages; + pgdat->node_present_pages = realtotalpages; + printk(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id, + realtotalpages); +} + +#ifndef CONFIG_SPARSEMEM +/* + * Calculate the size of the zone->blockflags rounded to an unsigned long + * Start by making sure zonesize is a multiple of pageblock_order by rounding + * up. Then use 1 NR_PAGEBLOCK_BITS worth of bits per pageblock, finally + * round what is now in bits to nearest long in bits, then return it in + * bytes. + */ +static unsigned long __init usemap_size(unsigned long zone_start_pfn, unsigned long zonesize) +{ + unsigned long usemapsize; + + zonesize += zone_start_pfn & (pageblock_nr_pages-1); + usemapsize = roundup(zonesize, pageblock_nr_pages); + usemapsize = usemapsize >> pageblock_order; + usemapsize *= NR_PAGEBLOCK_BITS; + usemapsize = roundup(usemapsize, 8 * sizeof(unsigned long)); + + return usemapsize / 8; +} + +static void __ref setup_usemap(struct pglist_data *pgdat, + struct zone *zone, + unsigned long zone_start_pfn, + unsigned long zonesize) +{ + unsigned long usemapsize = usemap_size(zone_start_pfn, zonesize); + zone->pageblock_flags = NULL; + if (usemapsize) { + zone->pageblock_flags = + memblock_alloc_node(usemapsize, SMP_CACHE_BYTES, + pgdat->node_id); + if (!zone->pageblock_flags) + panic("Failed to allocate %ld bytes for zone %s pageblock flags on node %d\n", + usemapsize, zone->name, pgdat->node_id); + } +} +#else +static inline void setup_usemap(struct pglist_data *pgdat, struct zone *zone, + unsigned long zone_start_pfn, unsigned long zonesize) {} +#endif /* CONFIG_SPARSEMEM */ + +#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE + +/* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */ +void __init set_pageblock_order(void) +{ + unsigned int order; + + /* Check that pageblock_nr_pages has not already been setup */ + if (pageblock_order) + return; + + if (HPAGE_SHIFT > PAGE_SHIFT) + order = HUGETLB_PAGE_ORDER; + else + order = MAX_ORDER - 1; + + /* + * Assume the largest contiguous order of interest is a huge page. + * This value may be variable depending on boot parameters on IA64 and + * powerpc. + */ + pageblock_order = order; +} +#else /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */ + +/* + * When CONFIG_HUGETLB_PAGE_SIZE_VARIABLE is not set, set_pageblock_order() + * is unused as pageblock_order is set at compile-time. See + * include/linux/pageblock-flags.h for the values of pageblock_order based on + * the kernel config + */ +void __init set_pageblock_order(void) +{ +} + +#endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */ + +static unsigned long __init calc_memmap_size(unsigned long spanned_pages, + unsigned long present_pages) +{ + unsigned long pages = spanned_pages; + + /* + * Provide a more accurate estimation if there are holes within + * the zone and SPARSEMEM is in use. If there are holes within the + * zone, each populated memory region may cost us one or two extra + * memmap pages due to alignment because memmap pages for each + * populated regions may not be naturally aligned on page boundary. + * So the (present_pages >> 4) heuristic is a tradeoff for that. + */ + if (spanned_pages > present_pages + (present_pages >> 4) && + IS_ENABLED(CONFIG_SPARSEMEM)) + pages = present_pages; + + return PAGE_ALIGN(pages * sizeof(struct page)) >> PAGE_SHIFT; +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static void pgdat_init_split_queue(struct pglist_data *pgdat) +{ + struct deferred_split *ds_queue = &pgdat->deferred_split_queue; + + spin_lock_init(&ds_queue->split_queue_lock); + INIT_LIST_HEAD(&ds_queue->split_queue); + ds_queue->split_queue_len = 0; +} +#else +static void pgdat_init_split_queue(struct pglist_data *pgdat) {} +#endif + +#ifdef CONFIG_COMPACTION +static void pgdat_init_kcompactd(struct pglist_data *pgdat) +{ + init_waitqueue_head(&pgdat->kcompactd_wait); +} +#else +static void pgdat_init_kcompactd(struct pglist_data *pgdat) {} +#endif + +static void __meminit pgdat_init_internals(struct pglist_data *pgdat) +{ + pgdat_resize_init(pgdat); + + pgdat_init_split_queue(pgdat); + pgdat_init_kcompactd(pgdat); + + init_waitqueue_head(&pgdat->kswapd_wait); + init_waitqueue_head(&pgdat->pfmemalloc_wait); + + pgdat_page_ext_init(pgdat); + spin_lock_init(&pgdat->lru_lock); + lruvec_init(&pgdat->__lruvec); +} + +static void __meminit zone_init_internals(struct zone *zone, enum zone_type idx, int nid, + unsigned long remaining_pages) +{ + atomic_long_set(&zone->managed_pages, remaining_pages); + zone_set_nid(zone, nid); + zone->name = zone_names[idx]; + zone->zone_pgdat = NODE_DATA(nid); + spin_lock_init(&zone->lock); + zone_seqlock_init(zone); + zone_pcp_init(zone); +} + +/* + * Set up the zone data structures + * - init pgdat internals + * - init all zones belonging to this node + * + * NOTE: this function is only called during memory hotplug + */ +#ifdef CONFIG_MEMORY_HOTPLUG +void __ref free_area_init_core_hotplug(int nid) +{ + enum zone_type z; + pg_data_t *pgdat = NODE_DATA(nid); + + pgdat_init_internals(pgdat); + for (z = 0; z < MAX_NR_ZONES; z++) + zone_init_internals(&pgdat->node_zones[z], z, nid, 0); +} +#endif + +/* + * Set up the zone data structures: + * - mark all pages reserved + * - mark all memory queues empty + * - clear the memory bitmaps + * + * NOTE: pgdat should get zeroed by caller. + * NOTE: this function is only called during early init. + */ +static void __init free_area_init_core(struct pglist_data *pgdat) +{ + enum zone_type j; + int nid = pgdat->node_id; + + pgdat_init_internals(pgdat); + pgdat->per_cpu_nodestats = &boot_nodestats; + + for (j = 0; j < MAX_NR_ZONES; j++) { + struct zone *zone = pgdat->node_zones + j; + unsigned long size, freesize, memmap_pages; + unsigned long zone_start_pfn = zone->zone_start_pfn; + + size = zone->spanned_pages; + freesize = zone->present_pages; + + /* + * Adjust freesize so that it accounts for how much memory + * is used by this zone for memmap. This affects the watermark + * and per-cpu initialisations + */ + memmap_pages = calc_memmap_size(size, freesize); + if (!is_highmem_idx(j)) { + if (freesize >= memmap_pages) { + freesize -= memmap_pages; + if (memmap_pages) + printk(KERN_DEBUG + " %s zone: %lu pages used for memmap\n", + zone_names[j], memmap_pages); + } else + pr_warn(" %s zone: %lu pages exceeds freesize %lu\n", + zone_names[j], memmap_pages, freesize); + } + + /* Account for reserved pages */ + if (j == 0 && freesize > dma_reserve) { + freesize -= dma_reserve; + printk(KERN_DEBUG " %s zone: %lu pages reserved\n", + zone_names[0], dma_reserve); + } + + if (!is_highmem_idx(j)) + nr_kernel_pages += freesize; + /* Charge for highmem memmap if there are enough kernel pages */ + else if (nr_kernel_pages > memmap_pages * 2) + nr_kernel_pages -= memmap_pages; + nr_all_pages += freesize; + + /* + * Set an approximate value for lowmem here, it will be adjusted + * when the bootmem allocator frees pages into the buddy system. + * And all highmem pages will be managed by the buddy system. + */ + zone_init_internals(zone, j, nid, freesize); + + if (!size) + continue; + + set_pageblock_order(); + setup_usemap(pgdat, zone, zone_start_pfn, size); + init_currently_empty_zone(zone, zone_start_pfn, size); + arch_memmap_init(size, nid, j, zone_start_pfn); + } +} + +#ifdef CONFIG_FLAT_NODE_MEM_MAP +static void __ref alloc_node_mem_map(struct pglist_data *pgdat) +{ + unsigned long __maybe_unused start = 0; + unsigned long __maybe_unused offset = 0; + + /* Skip empty nodes */ + if (!pgdat->node_spanned_pages) + return; + + start = pgdat->node_start_pfn & ~(MAX_ORDER_NR_PAGES - 1); + offset = pgdat->node_start_pfn - start; + /* ia64 gets its own node_mem_map, before this, without bootmem */ + if (!pgdat->node_mem_map) { + unsigned long size, end; + struct page *map; + + /* + * The zone's endpoints aren't required to be MAX_ORDER + * aligned but the node_mem_map endpoints must be in order + * for the buddy allocator to function correctly. + */ + end = pgdat_end_pfn(pgdat); + end = ALIGN(end, MAX_ORDER_NR_PAGES); + size = (end - start) * sizeof(struct page); + map = memblock_alloc_node(size, SMP_CACHE_BYTES, + pgdat->node_id); + if (!map) + panic("Failed to allocate %ld bytes for node %d memory map\n", + size, pgdat->node_id); + pgdat->node_mem_map = map + offset; + } + pr_debug("%s: node %d, pgdat %08lx, node_mem_map %08lx\n", + __func__, pgdat->node_id, (unsigned long)pgdat, + (unsigned long)pgdat->node_mem_map); +#ifndef CONFIG_NEED_MULTIPLE_NODES + /* + * With no DISCONTIG, the global mem_map is just set as node 0's + */ + if (pgdat == NODE_DATA(0)) { + mem_map = NODE_DATA(0)->node_mem_map; + if (page_to_pfn(mem_map) != pgdat->node_start_pfn) + mem_map -= offset; + } +#endif +} +#else +static void __ref alloc_node_mem_map(struct pglist_data *pgdat) { } +#endif /* CONFIG_FLAT_NODE_MEM_MAP */ + +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT +static inline void pgdat_set_deferred_range(pg_data_t *pgdat) +{ + pgdat->first_deferred_pfn = ULONG_MAX; +} +#else +static inline void pgdat_set_deferred_range(pg_data_t *pgdat) {} +#endif + +static void __init free_area_init_node(int nid) +{ + pg_data_t *pgdat = NODE_DATA(nid); + unsigned long start_pfn = 0; + unsigned long end_pfn = 0; + + /* pg_data_t should be reset to zero when it's allocated */ + WARN_ON(pgdat->nr_zones || pgdat->kswapd_highest_zoneidx); + + get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); + + pgdat->node_id = nid; + pgdat->node_start_pfn = start_pfn; + pgdat->per_cpu_nodestats = NULL; + + pr_info("Initmem setup node %d [mem %#018Lx-%#018Lx]\n", nid, + (u64)start_pfn << PAGE_SHIFT, + end_pfn ? ((u64)end_pfn << PAGE_SHIFT) - 1 : 0); + calculate_node_totalpages(pgdat, start_pfn, end_pfn); + + alloc_node_mem_map(pgdat); + pgdat_set_deferred_range(pgdat); + + free_area_init_core(pgdat); +} + +void __init free_area_init_memoryless_node(int nid) +{ + free_area_init_node(nid); +} + +#if MAX_NUMNODES > 1 +/* + * Figure out the number of possible node ids. + */ +void __init setup_nr_node_ids(void) +{ + unsigned int highest; + + highest = find_last_bit(node_possible_map.bits, MAX_NUMNODES); + nr_node_ids = highest + 1; +} +#endif + +/** + * node_map_pfn_alignment - determine the maximum internode alignment + * + * This function should be called after node map is populated and sorted. + * It calculates the maximum power of two alignment which can distinguish + * all the nodes. + * + * For example, if all nodes are 1GiB and aligned to 1GiB, the return value + * would indicate 1GiB alignment with (1 << (30 - PAGE_SHIFT)). If the + * nodes are shifted by 256MiB, 256MiB. Note that if only the last node is + * shifted, 1GiB is enough and this function will indicate so. + * + * This is used to test whether pfn -> nid mapping of the chosen memory + * model has fine enough granularity to avoid incorrect mapping for the + * populated node map. + * + * Return: the determined alignment in pfn's. 0 if there is no alignment + * requirement (single node). + */ +unsigned long __init node_map_pfn_alignment(void) +{ + unsigned long accl_mask = 0, last_end = 0; + unsigned long start, end, mask; + int last_nid = NUMA_NO_NODE; + int i, nid; + + for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, &nid) { + if (!start || last_nid < 0 || last_nid == nid) { + last_nid = nid; + last_end = end; + continue; + } + + /* + * Start with a mask granular enough to pin-point to the + * start pfn and tick off bits one-by-one until it becomes + * too coarse to separate the current node from the last. + */ + mask = ~((1 << __ffs(start)) - 1); + while (mask && last_end <= (start & (mask << 1))) + mask <<= 1; + + /* accumulate all internode masks */ + accl_mask |= mask; + } + + /* convert mask to number of pages */ + return ~accl_mask + 1; +} + +/** + * find_min_pfn_with_active_regions - Find the minimum PFN registered + * + * Return: the minimum PFN based on information provided via + * memblock_set_node(). + */ +unsigned long __init find_min_pfn_with_active_regions(void) +{ + return PHYS_PFN(memblock_start_of_DRAM()); +} + +/* + * early_calculate_totalpages() + * Sum pages in active regions for movable zone. + * Populate N_MEMORY for calculating usable_nodes. + */ +static unsigned long __init early_calculate_totalpages(void) +{ + unsigned long totalpages = 0; + unsigned long start_pfn, end_pfn; + int i, nid; + + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { + unsigned long pages = end_pfn - start_pfn; + + totalpages += pages; + if (pages) + node_set_state(nid, N_MEMORY); + } + return totalpages; +} + +/* + * Find the PFN the Movable zone begins in each node. Kernel memory + * is spread evenly between nodes as long as the nodes have enough + * memory. When they don't, some nodes will have more kernelcore than + * others + */ +static void __init find_zone_movable_pfns_for_nodes(void) +{ + int i, nid; + unsigned long usable_startpfn; + unsigned long kernelcore_node, kernelcore_remaining; + /* save the state before borrow the nodemask */ + nodemask_t saved_node_state = node_states[N_MEMORY]; + unsigned long totalpages = early_calculate_totalpages(); + int usable_nodes = nodes_weight(node_states[N_MEMORY]); + struct memblock_region *r; + + /* Need to find movable_zone earlier when movable_node is specified. */ + find_usable_zone_for_movable(); + + /* + * If movable_node is specified, ignore kernelcore and movablecore + * options. + */ + if (movable_node_is_enabled()) { + for_each_mem_region(r) { + if (!memblock_is_hotpluggable(r)) + continue; + + nid = memblock_get_region_node(r); + + usable_startpfn = PFN_DOWN(r->base); + zone_movable_pfn[nid] = zone_movable_pfn[nid] ? + min(usable_startpfn, zone_movable_pfn[nid]) : + usable_startpfn; + } + + goto out2; + } + + /* + * If kernelcore=mirror is specified, ignore movablecore option + */ + if (mirrored_kernelcore) { + bool mem_below_4gb_not_mirrored = false; + + for_each_mem_region(r) { + if (memblock_is_mirror(r)) + continue; + + nid = memblock_get_region_node(r); + + usable_startpfn = memblock_region_memory_base_pfn(r); + + if (usable_startpfn < 0x100000) { + mem_below_4gb_not_mirrored = true; + continue; + } + + zone_movable_pfn[nid] = zone_movable_pfn[nid] ? + min(usable_startpfn, zone_movable_pfn[nid]) : + usable_startpfn; + } + + if (mem_below_4gb_not_mirrored) + pr_warn("This configuration results in unmirrored kernel memory.\n"); + + goto out2; + } + + /* + * If kernelcore=nn% or movablecore=nn% was specified, calculate the + * amount of necessary memory. + */ + if (required_kernelcore_percent) + required_kernelcore = (totalpages * 100 * required_kernelcore_percent) / + 10000UL; + if (required_movablecore_percent) + required_movablecore = (totalpages * 100 * required_movablecore_percent) / + 10000UL; + + /* + * If movablecore= was specified, calculate what size of + * kernelcore that corresponds so that memory usable for + * any allocation type is evenly spread. If both kernelcore + * and movablecore are specified, then the value of kernelcore + * will be used for required_kernelcore if it's greater than + * what movablecore would have allowed. + */ + if (required_movablecore) { + unsigned long corepages; + + /* + * Round-up so that ZONE_MOVABLE is at least as large as what + * was requested by the user + */ + required_movablecore = + roundup(required_movablecore, MAX_ORDER_NR_PAGES); + required_movablecore = min(totalpages, required_movablecore); + corepages = totalpages - required_movablecore; + + required_kernelcore = max(required_kernelcore, corepages); + } + + /* + * If kernelcore was not specified or kernelcore size is larger + * than totalpages, there is no ZONE_MOVABLE. + */ + if (!required_kernelcore || required_kernelcore >= totalpages) + goto out; + + /* usable_startpfn is the lowest possible pfn ZONE_MOVABLE can be at */ + usable_startpfn = arch_zone_lowest_possible_pfn[movable_zone]; + +restart: + /* Spread kernelcore memory as evenly as possible throughout nodes */ + kernelcore_node = required_kernelcore / usable_nodes; + for_each_node_state(nid, N_MEMORY) { + unsigned long start_pfn, end_pfn; + + /* + * Recalculate kernelcore_node if the division per node + * now exceeds what is necessary to satisfy the requested + * amount of memory for the kernel + */ + if (required_kernelcore < kernelcore_node) + kernelcore_node = required_kernelcore / usable_nodes; + + /* + * As the map is walked, we track how much memory is usable + * by the kernel using kernelcore_remaining. When it is + * 0, the rest of the node is usable by ZONE_MOVABLE + */ + kernelcore_remaining = kernelcore_node; + + /* Go through each range of PFNs within this node */ + for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) { + unsigned long size_pages; + + start_pfn = max(start_pfn, zone_movable_pfn[nid]); + if (start_pfn >= end_pfn) + continue; + + /* Account for what is only usable for kernelcore */ + if (start_pfn < usable_startpfn) { + unsigned long kernel_pages; + kernel_pages = min(end_pfn, usable_startpfn) + - start_pfn; + + kernelcore_remaining -= min(kernel_pages, + kernelcore_remaining); + required_kernelcore -= min(kernel_pages, + required_kernelcore); + + /* Continue if range is now fully accounted */ + if (end_pfn <= usable_startpfn) { + + /* + * Push zone_movable_pfn to the end so + * that if we have to rebalance + * kernelcore across nodes, we will + * not double account here + */ + zone_movable_pfn[nid] = end_pfn; + continue; + } + start_pfn = usable_startpfn; + } + + /* + * The usable PFN range for ZONE_MOVABLE is from + * start_pfn->end_pfn. Calculate size_pages as the + * number of pages used as kernelcore + */ + size_pages = end_pfn - start_pfn; + if (size_pages > kernelcore_remaining) + size_pages = kernelcore_remaining; + zone_movable_pfn[nid] = start_pfn + size_pages; + + /* + * Some kernelcore has been met, update counts and + * break if the kernelcore for this node has been + * satisfied + */ + required_kernelcore -= min(required_kernelcore, + size_pages); + kernelcore_remaining -= size_pages; + if (!kernelcore_remaining) + break; + } + } + + /* + * If there is still required_kernelcore, we do another pass with one + * less node in the count. This will push zone_movable_pfn[nid] further + * along on the nodes that still have memory until kernelcore is + * satisfied + */ + usable_nodes--; + if (usable_nodes && required_kernelcore > usable_nodes) + goto restart; + +out2: + /* Align start of ZONE_MOVABLE on all nids to MAX_ORDER_NR_PAGES */ + for (nid = 0; nid < MAX_NUMNODES; nid++) { + unsigned long start_pfn, end_pfn; + + zone_movable_pfn[nid] = + roundup(zone_movable_pfn[nid], MAX_ORDER_NR_PAGES); + + get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); + if (zone_movable_pfn[nid] >= end_pfn) + zone_movable_pfn[nid] = 0; + } + +out: + /* restore the node_state */ + node_states[N_MEMORY] = saved_node_state; +} + +/* Any regular or high memory on that node ? */ +static void check_for_memory(pg_data_t *pgdat, int nid) +{ + enum zone_type zone_type; + + for (zone_type = 0; zone_type <= ZONE_MOVABLE - 1; zone_type++) { + struct zone *zone = &pgdat->node_zones[zone_type]; + if (populated_zone(zone)) { + if (IS_ENABLED(CONFIG_HIGHMEM)) + node_set_state(nid, N_HIGH_MEMORY); + if (zone_type <= ZONE_NORMAL) + node_set_state(nid, N_NORMAL_MEMORY); + break; + } + } +} + +/* + * Some architecturs, e.g. ARC may have ZONE_HIGHMEM below ZONE_NORMAL. For + * such cases we allow max_zone_pfn sorted in the descending order + */ +bool __weak arch_has_descending_max_zone_pfns(void) +{ + return false; +} + +/** + * free_area_init - Initialise all pg_data_t and zone data + * @max_zone_pfn: an array of max PFNs for each zone + * + * This will call free_area_init_node() for each active node in the system. + * Using the page ranges provided by memblock_set_node(), the size of each + * zone in each node and their holes is calculated. If the maximum PFN + * between two adjacent zones match, it is assumed that the zone is empty. + * For example, if arch_max_dma_pfn == arch_max_dma32_pfn, it is assumed + * that arch_max_dma32_pfn has no pages. It is also assumed that a zone + * starts where the previous one ended. For example, ZONE_DMA32 starts + * at arch_max_dma_pfn. + */ +void __init free_area_init(unsigned long *max_zone_pfn) +{ + unsigned long start_pfn, end_pfn; + int i, nid, zone; + bool descending; + + /* Record where the zone boundaries are */ + memset(arch_zone_lowest_possible_pfn, 0, + sizeof(arch_zone_lowest_possible_pfn)); + memset(arch_zone_highest_possible_pfn, 0, + sizeof(arch_zone_highest_possible_pfn)); + + start_pfn = find_min_pfn_with_active_regions(); + descending = arch_has_descending_max_zone_pfns(); + + for (i = 0; i < MAX_NR_ZONES; i++) { + if (descending) + zone = MAX_NR_ZONES - i - 1; + else + zone = i; + + if (zone == ZONE_MOVABLE) + continue; + + end_pfn = max(max_zone_pfn[zone], start_pfn); + arch_zone_lowest_possible_pfn[zone] = start_pfn; + arch_zone_highest_possible_pfn[zone] = end_pfn; + + start_pfn = end_pfn; + } + + /* Find the PFNs that ZONE_MOVABLE begins at in each node */ + memset(zone_movable_pfn, 0, sizeof(zone_movable_pfn)); + find_zone_movable_pfns_for_nodes(); + + /* Print out the zone ranges */ + pr_info("Zone ranges:\n"); + for (i = 0; i < MAX_NR_ZONES; i++) { + if (i == ZONE_MOVABLE) + continue; + pr_info(" %-8s ", zone_names[i]); + if (arch_zone_lowest_possible_pfn[i] == + arch_zone_highest_possible_pfn[i]) + pr_cont("empty\n"); + else + pr_cont("[mem %#018Lx-%#018Lx]\n", + (u64)arch_zone_lowest_possible_pfn[i] + << PAGE_SHIFT, + ((u64)arch_zone_highest_possible_pfn[i] + << PAGE_SHIFT) - 1); + } + + /* Print out the PFNs ZONE_MOVABLE begins at in each node */ + pr_info("Movable zone start for each node\n"); + for (i = 0; i < MAX_NUMNODES; i++) { + if (zone_movable_pfn[i]) + pr_info(" Node %d: %#018Lx\n", i, + (u64)zone_movable_pfn[i] << PAGE_SHIFT); + } + + /* + * Print out the early node map, and initialize the + * subsection-map relative to active online memory ranges to + * enable future "sub-section" extensions of the memory map. + */ + pr_info("Early memory node ranges\n"); + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { + pr_info(" node %3d: [mem %#018Lx-%#018Lx]\n", nid, + (u64)start_pfn << PAGE_SHIFT, + ((u64)end_pfn << PAGE_SHIFT) - 1); + subsection_map_init(start_pfn, end_pfn - start_pfn); + } + + /* Initialise every node */ + mminit_verify_pageflags_layout(); + setup_nr_node_ids(); + for_each_online_node(nid) { + pg_data_t *pgdat = NODE_DATA(nid); + free_area_init_node(nid); + + /* Any memory on that node */ + if (pgdat->node_present_pages) + node_set_state(nid, N_MEMORY); + check_for_memory(pgdat, nid); + } + + memmap_init(); +} + +static int __init cmdline_parse_core(char *p, unsigned long *core, + unsigned long *percent) +{ + unsigned long long coremem; + char *endptr; + + if (!p) + return -EINVAL; + + /* Value may be a percentage of total memory, otherwise bytes */ + coremem = simple_strtoull(p, &endptr, 0); + if (*endptr == '%') { + /* Paranoid check for percent values greater than 100 */ + WARN_ON(coremem > 100); + + *percent = coremem; + } else { + coremem = memparse(p, &p); + /* Paranoid check that UL is enough for the coremem value */ + WARN_ON((coremem >> PAGE_SHIFT) > ULONG_MAX); + + *core = coremem >> PAGE_SHIFT; + *percent = 0UL; + } + return 0; +} + +/* + * kernelcore=size sets the amount of memory for use for allocations that + * cannot be reclaimed or migrated. + */ +static int __init cmdline_parse_kernelcore(char *p) +{ + /* parse kernelcore=mirror */ + if (parse_option_str(p, "mirror")) { + mirrored_kernelcore = true; + return 0; + } + + return cmdline_parse_core(p, &required_kernelcore, + &required_kernelcore_percent); +} + +/* + * movablecore=size sets the amount of memory for use for allocations that + * can be reclaimed or migrated. + */ +static int __init cmdline_parse_movablecore(char *p) +{ + return cmdline_parse_core(p, &required_movablecore, + &required_movablecore_percent); +} + +early_param("kernelcore", cmdline_parse_kernelcore); +early_param("movablecore", cmdline_parse_movablecore); + +void adjust_managed_page_count(struct page *page, long count) +{ + atomic_long_add(count, &page_zone(page)->managed_pages); + totalram_pages_add(count); +#ifdef CONFIG_HIGHMEM + if (PageHighMem(page)) + totalhigh_pages_add(count); +#endif +} +EXPORT_SYMBOL(adjust_managed_page_count); + +unsigned long free_reserved_area(void *start, void *end, int poison, const char *s) +{ + void *pos; + unsigned long pages = 0; + + start = (void *)PAGE_ALIGN((unsigned long)start); + end = (void *)((unsigned long)end & PAGE_MASK); + for (pos = start; pos < end; pos += PAGE_SIZE, pages++) { + struct page *page = virt_to_page(pos); + void *direct_map_addr; + + /* + * 'direct_map_addr' might be different from 'pos' + * because some architectures' virt_to_page() + * work with aliases. Getting the direct map + * address ensures that we get a _writeable_ + * alias for the memset(). + */ + direct_map_addr = page_address(page); + if ((unsigned int)poison <= 0xFF) + memset(direct_map_addr, poison, PAGE_SIZE); + + free_reserved_page(page); + } + + if (pages && s) + pr_info("Freeing %s memory: %ldK\n", + s, pages << (PAGE_SHIFT - 10)); + + return pages; +} + +#ifdef CONFIG_HIGHMEM +void free_highmem_page(struct page *page) +{ + __free_reserved_page(page); + totalram_pages_inc(); + atomic_long_inc(&page_zone(page)->managed_pages); + totalhigh_pages_inc(); +} +#endif + + +void __init mem_init_print_info(const char *str) +{ + unsigned long physpages, codesize, datasize, rosize, bss_size; + unsigned long init_code_size, init_data_size; + + physpages = get_num_physpages(); + codesize = _etext - _stext; + datasize = _edata - _sdata; + rosize = __end_rodata - __start_rodata; + bss_size = __bss_stop - __bss_start; + init_data_size = __init_end - __init_begin; + init_code_size = _einittext - _sinittext; + + /* + * Detect special cases and adjust section sizes accordingly: + * 1) .init.* may be embedded into .data sections + * 2) .init.text.* may be out of [__init_begin, __init_end], + * please refer to arch/tile/kernel/vmlinux.lds.S. + * 3) .rodata.* may be embedded into .text or .data sections. + */ +#define adj_init_size(start, end, size, pos, adj) \ + do { \ + if (&start[0] <= &pos[0] && &pos[0] < &end[0] && size > adj) \ + size -= adj; \ + } while (0) + + adj_init_size(__init_begin, __init_end, init_data_size, + _sinittext, init_code_size); + adj_init_size(_stext, _etext, codesize, _sinittext, init_code_size); + adj_init_size(_sdata, _edata, datasize, __init_begin, init_data_size); + adj_init_size(_stext, _etext, codesize, __start_rodata, rosize); + adj_init_size(_sdata, _edata, datasize, __start_rodata, rosize); + +#undef adj_init_size + + pr_info("Memory: %luK/%luK available (%luK kernel code, %luK rwdata, %luK rodata, %luK init, %luK bss, %luK reserved, %luK cma-reserved" +#ifdef CONFIG_HIGHMEM + ", %luK highmem" +#endif + "%s%s)\n", + nr_free_pages() << (PAGE_SHIFT - 10), + physpages << (PAGE_SHIFT - 10), + codesize >> 10, datasize >> 10, rosize >> 10, + (init_data_size + init_code_size) >> 10, bss_size >> 10, + (physpages - totalram_pages() - totalcma_pages) << (PAGE_SHIFT - 10), + totalcma_pages << (PAGE_SHIFT - 10), +#ifdef CONFIG_HIGHMEM + totalhigh_pages() << (PAGE_SHIFT - 10), +#endif + str ? ", " : "", str ? str : ""); +} + +/** + * set_dma_reserve - set the specified number of pages reserved in the first zone + * @new_dma_reserve: The number of pages to mark reserved + * + * The per-cpu batchsize and zone watermarks are determined by managed_pages. + * In the DMA zone, a significant percentage may be consumed by kernel image + * and other unfreeable allocations which can skew the watermarks badly. This + * function may optionally be used to account for unfreeable pages in the + * first zone (e.g., ZONE_DMA). The effect will be lower watermarks and + * smaller per-cpu batchsize. + */ +void __init set_dma_reserve(unsigned long new_dma_reserve) +{ + dma_reserve = new_dma_reserve; +} + +static int page_alloc_cpu_dead(unsigned int cpu) +{ + + lru_add_drain_cpu(cpu); + drain_pages(cpu); + + /* + * Spill the event counters of the dead processor + * into the current processors event counters. + * This artificially elevates the count of the current + * processor. + */ + vm_events_fold_cpu(cpu); + + /* + * Zero the differential counters of the dead processor + * so that the vm statistics are consistent. + * + * This is only okay since the processor is dead and cannot + * race with what we are doing. + */ + cpu_vm_stats_fold(cpu); + return 0; +} + +#ifdef CONFIG_NUMA +int hashdist = HASHDIST_DEFAULT; + +static int __init set_hashdist(char *str) +{ + if (!str) + return 0; + hashdist = simple_strtoul(str, &str, 0); + return 1; +} +__setup("hashdist=", set_hashdist); +#endif + +void __init page_alloc_init(void) +{ + int ret; + +#ifdef CONFIG_NUMA + if (num_node_state(N_MEMORY) == 1) + hashdist = 0; +#endif + + ret = cpuhp_setup_state_nocalls(CPUHP_PAGE_ALLOC_DEAD, + "mm/page_alloc:dead", NULL, + page_alloc_cpu_dead); + WARN_ON(ret < 0); +} + +/* + * calculate_totalreserve_pages - called when sysctl_lowmem_reserve_ratio + * or min_free_kbytes changes. + */ +static void calculate_totalreserve_pages(void) +{ + struct pglist_data *pgdat; + unsigned long reserve_pages = 0; + enum zone_type i, j; + + for_each_online_pgdat(pgdat) { + + pgdat->totalreserve_pages = 0; + + for (i = 0; i < MAX_NR_ZONES; i++) { + struct zone *zone = pgdat->node_zones + i; + long max = 0; + unsigned long managed_pages = zone_managed_pages(zone); + + /* Find valid and maximum lowmem_reserve in the zone */ + for (j = i; j < MAX_NR_ZONES; j++) { + if (zone->lowmem_reserve[j] > max) + max = zone->lowmem_reserve[j]; + } + + /* we treat the high watermark as reserved pages. */ + max += high_wmark_pages(zone); + + if (max > managed_pages) + max = managed_pages; + + pgdat->totalreserve_pages += max; + + reserve_pages += max; + } + } + totalreserve_pages = reserve_pages; +} + +/* + * setup_per_zone_lowmem_reserve - called whenever + * sysctl_lowmem_reserve_ratio changes. Ensures that each zone + * has a correct pages reserved value, so an adequate number of + * pages are left in the zone after a successful __alloc_pages(). + */ +static void setup_per_zone_lowmem_reserve(void) +{ + struct pglist_data *pgdat; + enum zone_type i, j; + + for_each_online_pgdat(pgdat) { + for (i = 0; i < MAX_NR_ZONES - 1; i++) { + struct zone *zone = &pgdat->node_zones[i]; + int ratio = sysctl_lowmem_reserve_ratio[i]; + bool clear = !ratio || !zone_managed_pages(zone); + unsigned long managed_pages = 0; + + for (j = i + 1; j < MAX_NR_ZONES; j++) { + struct zone *upper_zone = &pgdat->node_zones[j]; + + managed_pages += zone_managed_pages(upper_zone); + + if (clear) + zone->lowmem_reserve[j] = 0; + else + zone->lowmem_reserve[j] = managed_pages / ratio; + } + } + } + + /* update totalreserve_pages */ + calculate_totalreserve_pages(); +} + +static void __setup_per_zone_wmarks(void) +{ + unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10); + unsigned long lowmem_pages = 0; + struct zone *zone; + unsigned long flags; + + /* Calculate total number of !ZONE_HIGHMEM pages */ + for_each_zone(zone) { + if (!is_highmem(zone)) + lowmem_pages += zone_managed_pages(zone); + } + + for_each_zone(zone) { + u64 tmp; + + spin_lock_irqsave(&zone->lock, flags); + tmp = (u64)pages_min * zone_managed_pages(zone); + do_div(tmp, lowmem_pages); + if (is_highmem(zone)) { + /* + * __GFP_HIGH and PF_MEMALLOC allocations usually don't + * need highmem pages, so cap pages_min to a small + * value here. + * + * The WMARK_HIGH-WMARK_LOW and (WMARK_LOW-WMARK_MIN) + * deltas control async page reclaim, and so should + * not be capped for highmem. + */ + unsigned long min_pages; + + min_pages = zone_managed_pages(zone) / 1024; + min_pages = clamp(min_pages, SWAP_CLUSTER_MAX, 128UL); + zone->_watermark[WMARK_MIN] = min_pages; + } else { + /* + * If it's a lowmem zone, reserve a number of pages + * proportionate to the zone's size. + */ + zone->_watermark[WMARK_MIN] = tmp; + } + + /* + * Set the kswapd watermarks distance according to the + * scale factor in proportion to available memory, but + * ensure a minimum size on small systems. + */ + tmp = max_t(u64, tmp >> 2, + mult_frac(zone_managed_pages(zone), + watermark_scale_factor, 10000)); + + zone->watermark_boost = 0; + zone->_watermark[WMARK_LOW] = min_wmark_pages(zone) + tmp; + zone->_watermark[WMARK_HIGH] = min_wmark_pages(zone) + tmp * 2; + + spin_unlock_irqrestore(&zone->lock, flags); + } + + /* update totalreserve_pages */ + calculate_totalreserve_pages(); +} + +/** + * setup_per_zone_wmarks - called when min_free_kbytes changes + * or when memory is hot-{added|removed} + * + * Ensures that the watermark[min,low,high] values for each zone are set + * correctly with respect to min_free_kbytes. + */ +void setup_per_zone_wmarks(void) +{ + static DEFINE_SPINLOCK(lock); + + spin_lock(&lock); + __setup_per_zone_wmarks(); + spin_unlock(&lock); +} + +/* + * Initialise min_free_kbytes. + * + * For small machines we want it small (128k min). For large machines + * we want it large (256MB max). But it is not linear, because network + * bandwidth does not increase linearly with machine size. We use + * + * min_free_kbytes = 4 * sqrt(lowmem_kbytes), for better accuracy: + * min_free_kbytes = sqrt(lowmem_kbytes * 16) + * + * which yields + * + * 16MB: 512k + * 32MB: 724k + * 64MB: 1024k + * 128MB: 1448k + * 256MB: 2048k + * 512MB: 2896k + * 1024MB: 4096k + * 2048MB: 5792k + * 4096MB: 8192k + * 8192MB: 11584k + * 16384MB: 16384k + */ +int __meminit init_per_zone_wmark_min(void) +{ + unsigned long lowmem_kbytes; + int new_min_free_kbytes; + + lowmem_kbytes = nr_free_buffer_pages() * (PAGE_SIZE >> 10); + new_min_free_kbytes = int_sqrt(lowmem_kbytes * 16); + + if (new_min_free_kbytes > user_min_free_kbytes) { + min_free_kbytes = new_min_free_kbytes; + if (min_free_kbytes < 128) + min_free_kbytes = 128; + if (min_free_kbytes > 262144) + min_free_kbytes = 262144; + } else { + pr_warn("min_free_kbytes is not updated to %d because user defined value %d is preferred\n", + new_min_free_kbytes, user_min_free_kbytes); + } + setup_per_zone_wmarks(); + refresh_zone_stat_thresholds(); + setup_per_zone_lowmem_reserve(); + +#ifdef CONFIG_NUMA + setup_min_unmapped_ratio(); + setup_min_slab_ratio(); +#endif + + khugepaged_min_free_kbytes_update(); + + return 0; +} +postcore_initcall(init_per_zone_wmark_min) + +/* + * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so + * that we can call two helper functions whenever min_free_kbytes + * changes. + */ +int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write, + void *buffer, size_t *length, loff_t *ppos) +{ + int rc; + + rc = proc_dointvec_minmax(table, write, buffer, length, ppos); + if (rc) + return rc; + + if (write) { + user_min_free_kbytes = min_free_kbytes; + setup_per_zone_wmarks(); + } + return 0; +} + +int watermark_scale_factor_sysctl_handler(struct ctl_table *table, int write, + void *buffer, size_t *length, loff_t *ppos) +{ + int rc; + + rc = proc_dointvec_minmax(table, write, buffer, length, ppos); + if (rc) + return rc; + + if (write) + setup_per_zone_wmarks(); + + return 0; +} + +#ifdef CONFIG_NUMA +static void setup_min_unmapped_ratio(void) +{ + pg_data_t *pgdat; + struct zone *zone; + + for_each_online_pgdat(pgdat) + pgdat->min_unmapped_pages = 0; + + for_each_zone(zone) + zone->zone_pgdat->min_unmapped_pages += (zone_managed_pages(zone) * + sysctl_min_unmapped_ratio) / 100; +} + + +int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write, + void *buffer, size_t *length, loff_t *ppos) +{ + int rc; + + rc = proc_dointvec_minmax(table, write, buffer, length, ppos); + if (rc) + return rc; + + setup_min_unmapped_ratio(); + + return 0; +} + +static void setup_min_slab_ratio(void) +{ + pg_data_t *pgdat; + struct zone *zone; + + for_each_online_pgdat(pgdat) + pgdat->min_slab_pages = 0; + + for_each_zone(zone) + zone->zone_pgdat->min_slab_pages += (zone_managed_pages(zone) * + sysctl_min_slab_ratio) / 100; +} + +int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write, + void *buffer, size_t *length, loff_t *ppos) +{ + int rc; + + rc = proc_dointvec_minmax(table, write, buffer, length, ppos); + if (rc) + return rc; + + setup_min_slab_ratio(); + + return 0; +} +#endif + +/* + * lowmem_reserve_ratio_sysctl_handler - just a wrapper around + * proc_dointvec() so that we can call setup_per_zone_lowmem_reserve() + * whenever sysctl_lowmem_reserve_ratio changes. + * + * The reserve ratio obviously has absolutely no relation with the + * minimum watermarks. The lowmem reserve ratio can only make sense + * if in function of the boot time zone sizes. + */ +int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *table, int write, + void *buffer, size_t *length, loff_t *ppos) +{ + int i; + + proc_dointvec_minmax(table, write, buffer, length, ppos); + + for (i = 0; i < MAX_NR_ZONES; i++) { + if (sysctl_lowmem_reserve_ratio[i] < 1) + sysctl_lowmem_reserve_ratio[i] = 0; + } + + setup_per_zone_lowmem_reserve(); + return 0; +} + +static void __zone_pcp_update(struct zone *zone) +{ + unsigned int cpu; + + for_each_possible_cpu(cpu) + pageset_set_high_and_batch(zone, + per_cpu_ptr(zone->pageset, cpu)); +} + +/* + * percpu_pagelist_fraction - changes the pcp->high for each zone on each + * cpu. It is the fraction of total pages in each zone that a hot per cpu + * pagelist can have before it gets flushed back to buddy allocator. + */ +int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *table, int write, + void *buffer, size_t *length, loff_t *ppos) +{ + struct zone *zone; + int old_percpu_pagelist_fraction; + int ret; + + mutex_lock(&pcp_batch_high_lock); + old_percpu_pagelist_fraction = percpu_pagelist_fraction; + + ret = proc_dointvec_minmax(table, write, buffer, length, ppos); + if (!write || ret < 0) + goto out; + + /* Sanity checking to avoid pcp imbalance */ + if (percpu_pagelist_fraction && + percpu_pagelist_fraction < MIN_PERCPU_PAGELIST_FRACTION) { + percpu_pagelist_fraction = old_percpu_pagelist_fraction; + ret = -EINVAL; + goto out; + } + + /* No change? */ + if (percpu_pagelist_fraction == old_percpu_pagelist_fraction) + goto out; + + for_each_populated_zone(zone) + __zone_pcp_update(zone); +out: + mutex_unlock(&pcp_batch_high_lock); + return ret; +} + +#ifndef __HAVE_ARCH_RESERVED_KERNEL_PAGES +/* + * Returns the number of pages that arch has reserved but + * is not known to alloc_large_system_hash(). + */ +static unsigned long __init arch_reserved_kernel_pages(void) +{ + return 0; +} +#endif + +/* + * Adaptive scale is meant to reduce sizes of hash tables on large memory + * machines. As memory size is increased the scale is also increased but at + * slower pace. Starting from ADAPT_SCALE_BASE (64G), every time memory + * quadruples the scale is increased by one, which means the size of hash table + * only doubles, instead of quadrupling as well. + * Because 32-bit systems cannot have large physical memory, where this scaling + * makes sense, it is disabled on such platforms. + */ +#if __BITS_PER_LONG > 32 +#define ADAPT_SCALE_BASE (64ul << 30) +#define ADAPT_SCALE_SHIFT 2 +#define ADAPT_SCALE_NPAGES (ADAPT_SCALE_BASE >> PAGE_SHIFT) +#endif + +/* + * allocate a large system hash table from bootmem + * - it is assumed that the hash table must contain an exact power-of-2 + * quantity of entries + * - limit is the number of hash buckets, not the total allocation size + */ +void *__init alloc_large_system_hash(const char *tablename, + unsigned long bucketsize, + unsigned long numentries, + int scale, + int flags, + unsigned int *_hash_shift, + unsigned int *_hash_mask, + unsigned long low_limit, + unsigned long high_limit) +{ + unsigned long long max = high_limit; + unsigned long log2qty, size; + void *table = NULL; + gfp_t gfp_flags; + bool virt; + + /* allow the kernel cmdline to have a say */ + if (!numentries) { + /* round applicable memory size up to nearest megabyte */ + numentries = nr_kernel_pages; + numentries -= arch_reserved_kernel_pages(); + + /* It isn't necessary when PAGE_SIZE >= 1MB */ + if (PAGE_SHIFT < 20) + numentries = round_up(numentries, (1<<20)/PAGE_SIZE); + +#if __BITS_PER_LONG > 32 + if (!high_limit) { + unsigned long adapt; + + for (adapt = ADAPT_SCALE_NPAGES; adapt < numentries; + adapt <<= ADAPT_SCALE_SHIFT) + scale++; + } +#endif + + /* limit to 1 bucket per 2^scale bytes of low memory */ + if (scale > PAGE_SHIFT) + numentries >>= (scale - PAGE_SHIFT); + else + numentries <<= (PAGE_SHIFT - scale); + + /* Make sure we've got at least a 0-order allocation.. */ + if (unlikely(flags & HASH_SMALL)) { + /* Makes no sense without HASH_EARLY */ + WARN_ON(!(flags & HASH_EARLY)); + if (!(numentries >> *_hash_shift)) { + numentries = 1UL << *_hash_shift; + BUG_ON(!numentries); + } + } else if (unlikely((numentries * bucketsize) < PAGE_SIZE)) + numentries = PAGE_SIZE / bucketsize; + } + numentries = roundup_pow_of_two(numentries); + + /* limit allocation size to 1/16 total memory by default */ + if (max == 0) { + max = ((unsigned long long)nr_all_pages << PAGE_SHIFT) >> 4; + do_div(max, bucketsize); + } + max = min(max, 0x80000000ULL); + + if (numentries < low_limit) + numentries = low_limit; + if (numentries > max) + numentries = max; + + log2qty = ilog2(numentries); + + gfp_flags = (flags & HASH_ZERO) ? GFP_ATOMIC | __GFP_ZERO : GFP_ATOMIC; + do { + virt = false; + size = bucketsize << log2qty; + if (flags & HASH_EARLY) { + if (flags & HASH_ZERO) + table = memblock_alloc(size, SMP_CACHE_BYTES); + else + table = memblock_alloc_raw(size, + SMP_CACHE_BYTES); + } else if (get_order(size) >= MAX_ORDER || hashdist) { + table = __vmalloc(size, gfp_flags); + virt = true; + } else { + /* + * If bucketsize is not a power-of-two, we may free + * some pages at the end of hash table which + * alloc_pages_exact() automatically does + */ + table = alloc_pages_exact(size, gfp_flags); + kmemleak_alloc(table, size, 1, gfp_flags); + } + } while (!table && size > PAGE_SIZE && --log2qty); + + if (!table) + panic("Failed to allocate %s hash table\n", tablename); + + pr_info("%s hash table entries: %ld (order: %d, %lu bytes, %s)\n", + tablename, 1UL << log2qty, ilog2(size) - PAGE_SHIFT, size, + virt ? "vmalloc" : "linear"); + + if (_hash_shift) + *_hash_shift = log2qty; + if (_hash_mask) + *_hash_mask = (1 << log2qty) - 1; + + return table; +} + +/* + * This function checks whether pageblock includes unmovable pages or not. + * + * PageLRU check without isolation or lru_lock could race so that + * MIGRATE_MOVABLE block might include unmovable pages. And __PageMovable + * check without lock_page also may miss some movable non-lru pages at + * race condition. So you can't expect this function should be exact. + * + * Returns a page without holding a reference. If the caller wants to + * dereference that page (e.g., dumping), it has to make sure that it + * cannot get removed (e.g., via memory unplug) concurrently. + * + */ +struct page *has_unmovable_pages(struct zone *zone, struct page *page, + int migratetype, int flags) +{ + unsigned long iter = 0; + unsigned long pfn = page_to_pfn(page); + unsigned long offset = pfn % pageblock_nr_pages; + + if (is_migrate_cma_page(page)) { + /* + * CMA allocations (alloc_contig_range) really need to mark + * isolate CMA pageblocks even when they are not movable in fact + * so consider them movable here. + */ + if (is_migrate_cma(migratetype)) + return NULL; + + return page; + } + + for (; iter < pageblock_nr_pages - offset; iter++) { + if (!pfn_valid_within(pfn + iter)) + continue; + + page = pfn_to_page(pfn + iter); + + /* + * Both, bootmem allocations and memory holes are marked + * PG_reserved and are unmovable. We can even have unmovable + * allocations inside ZONE_MOVABLE, for example when + * specifying "movablecore". + */ + if (PageReserved(page)) + return page; + + /* + * If the zone is movable and we have ruled out all reserved + * pages then it should be reasonably safe to assume the rest + * is movable. + */ + if (zone_idx(zone) == ZONE_MOVABLE) + continue; + + /* + * Hugepages are not in LRU lists, but they're movable. + * THPs are on the LRU, but need to be counted as #small pages. + * We need not scan over tail pages because we don't + * handle each tail page individually in migration. + */ + if (PageHuge(page) || PageTransCompound(page)) { + struct page *head = compound_head(page); + unsigned int skip_pages; + + if (PageHuge(page)) { + if (!hugepage_migration_supported(page_hstate(head))) + return page; + } else if (!PageLRU(head) && !__PageMovable(head)) { + return page; + } + + skip_pages = compound_nr(head) - (page - head); + iter += skip_pages - 1; + continue; + } + + /* + * We can't use page_count without pin a page + * because another CPU can free compound page. + * This check already skips compound tails of THP + * because their page->_refcount is zero at all time. + */ + if (!page_ref_count(page)) { + if (PageBuddy(page)) + iter += (1 << buddy_order(page)) - 1; + continue; + } + + /* + * The HWPoisoned page may be not in buddy system, and + * page_count() is not 0. + */ + if ((flags & MEMORY_OFFLINE) && PageHWPoison(page)) + continue; + + /* + * We treat all PageOffline() pages as movable when offlining + * to give drivers a chance to decrement their reference count + * in MEM_GOING_OFFLINE in order to indicate that these pages + * can be offlined as there are no direct references anymore. + * For actually unmovable PageOffline() where the driver does + * not support this, we will fail later when trying to actually + * move these pages that still have a reference count > 0. + * (false negatives in this function only) + */ + if ((flags & MEMORY_OFFLINE) && PageOffline(page)) + continue; + + if (__PageMovable(page) || PageLRU(page)) + continue; + + /* + * If there are RECLAIMABLE pages, we need to check + * it. But now, memory offline itself doesn't call + * shrink_node_slabs() and it still to be fixed. + */ + return page; + } + return NULL; +} + +#ifdef CONFIG_CONTIG_ALLOC +static unsigned long pfn_max_align_down(unsigned long pfn) +{ + return pfn & ~(max_t(unsigned long, MAX_ORDER_NR_PAGES, + pageblock_nr_pages) - 1); +} + +static unsigned long pfn_max_align_up(unsigned long pfn) +{ + return ALIGN(pfn, max_t(unsigned long, MAX_ORDER_NR_PAGES, + pageblock_nr_pages)); +} + +/* [start, end) must belong to a single zone. */ +static int __alloc_contig_migrate_range(struct compact_control *cc, + unsigned long start, unsigned long end) +{ + /* This function is based on compact_zone() from compaction.c. */ + unsigned int nr_reclaimed; + unsigned long pfn = start; + unsigned int tries = 0; + int ret = 0; + struct migration_target_control mtc = { + .nid = zone_to_nid(cc->zone), + .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL, + }; + + migrate_prep(); + + while (pfn < end || !list_empty(&cc->migratepages)) { + if (fatal_signal_pending(current)) { + ret = -EINTR; + break; + } + + if (list_empty(&cc->migratepages)) { + cc->nr_migratepages = 0; + pfn = isolate_migratepages_range(cc, pfn, end); + if (!pfn) { + ret = -EINTR; + break; + } + tries = 0; + } else if (++tries == 5) { + ret = ret < 0 ? ret : -EBUSY; + break; + } + + nr_reclaimed = reclaim_clean_pages_from_list(cc->zone, + &cc->migratepages); + cc->nr_migratepages -= nr_reclaimed; + + ret = migrate_pages(&cc->migratepages, alloc_migration_target, + NULL, (unsigned long)&mtc, cc->mode, MR_CONTIG_RANGE); + } + if (ret < 0) { + putback_movable_pages(&cc->migratepages); + return ret; + } + return 0; +} + +/** + * alloc_contig_range() -- tries to allocate given range of pages + * @start: start PFN to allocate + * @end: one-past-the-last PFN to allocate + * @migratetype: migratetype of the underlaying pageblocks (either + * #MIGRATE_MOVABLE or #MIGRATE_CMA). All pageblocks + * in range must have the same migratetype and it must + * be either of the two. + * @gfp_mask: GFP mask to use during compaction + * + * The PFN range does not have to be pageblock or MAX_ORDER_NR_PAGES + * aligned. The PFN range must belong to a single zone. + * + * The first thing this routine does is attempt to MIGRATE_ISOLATE all + * pageblocks in the range. Once isolated, the pageblocks should not + * be modified by others. + * + * Return: zero on success or negative error code. On success all + * pages which PFN is in [start, end) are allocated for the caller and + * need to be freed with free_contig_range(). + */ +int alloc_contig_range(unsigned long start, unsigned long end, + unsigned migratetype, gfp_t gfp_mask) +{ + unsigned long outer_start, outer_end; + unsigned int order; + int ret = 0; + + struct compact_control cc = { + .nr_migratepages = 0, + .order = -1, + .zone = page_zone(pfn_to_page(start)), + .mode = MIGRATE_SYNC, + .ignore_skip_hint = true, + .no_set_skip_hint = true, + .gfp_mask = current_gfp_context(gfp_mask), + .alloc_contig = true, + }; + INIT_LIST_HEAD(&cc.migratepages); + + /* + * What we do here is we mark all pageblocks in range as + * MIGRATE_ISOLATE. Because pageblock and max order pages may + * have different sizes, and due to the way page allocator + * work, we align the range to biggest of the two pages so + * that page allocator won't try to merge buddies from + * different pageblocks and change MIGRATE_ISOLATE to some + * other migration type. + * + * Once the pageblocks are marked as MIGRATE_ISOLATE, we + * migrate the pages from an unaligned range (ie. pages that + * we are interested in). This will put all the pages in + * range back to page allocator as MIGRATE_ISOLATE. + * + * When this is done, we take the pages in range from page + * allocator removing them from the buddy system. This way + * page allocator will never consider using them. + * + * This lets us mark the pageblocks back as + * MIGRATE_CMA/MIGRATE_MOVABLE so that free pages in the + * aligned range but not in the unaligned, original range are + * put back to page allocator so that buddy can use them. + */ + + ret = start_isolate_page_range(pfn_max_align_down(start), + pfn_max_align_up(end), migratetype, 0); + if (ret) + return ret; + + /* + * In case of -EBUSY, we'd like to know which page causes problem. + * So, just fall through. test_pages_isolated() has a tracepoint + * which will report the busy page. + * + * It is possible that busy pages could become available before + * the call to test_pages_isolated, and the range will actually be + * allocated. So, if we fall through be sure to clear ret so that + * -EBUSY is not accidentally used or returned to caller. + */ + ret = __alloc_contig_migrate_range(&cc, start, end); + if (ret && ret != -EBUSY) + goto done; + ret =0; + + /* + * Pages from [start, end) are within a MAX_ORDER_NR_PAGES + * aligned blocks that are marked as MIGRATE_ISOLATE. What's + * more, all pages in [start, end) are free in page allocator. + * What we are going to do is to allocate all pages from + * [start, end) (that is remove them from page allocator). + * + * The only problem is that pages at the beginning and at the + * end of interesting range may be not aligned with pages that + * page allocator holds, ie. they can be part of higher order + * pages. Because of this, we reserve the bigger range and + * once this is done free the pages we are not interested in. + * + * We don't have to hold zone->lock here because the pages are + * isolated thus they won't get removed from buddy. + */ + + lru_add_drain_all(); + + order = 0; + outer_start = start; + while (!PageBuddy(pfn_to_page(outer_start))) { + if (++order >= MAX_ORDER) { + outer_start = start; + break; + } + outer_start &= ~0UL << order; + } + + if (outer_start != start) { + order = buddy_order(pfn_to_page(outer_start)); + + /* + * outer_start page could be small order buddy page and + * it doesn't include start page. Adjust outer_start + * in this case to report failed page properly + * on tracepoint in test_pages_isolated() + */ + if (outer_start + (1UL << order) <= start) + outer_start = start; + } + + /* Make sure the range is really isolated. */ + if (test_pages_isolated(outer_start, end, 0)) { + pr_info_ratelimited("%s: [%lx, %lx) PFNs busy\n", + __func__, outer_start, end); + ret = -EBUSY; + goto done; + } + + /* Grab isolated pages from freelists. */ + outer_end = isolate_freepages_range(&cc, outer_start, end); + if (!outer_end) { + ret = -EBUSY; + goto done; + } + + /* Free head and tail (if any) */ + if (start != outer_start) + free_contig_range(outer_start, start - outer_start); + if (end != outer_end) + free_contig_range(end, outer_end - end); + +done: + undo_isolate_page_range(pfn_max_align_down(start), + pfn_max_align_up(end), migratetype); + return ret; +} +EXPORT_SYMBOL(alloc_contig_range); + +static int __alloc_contig_pages(unsigned long start_pfn, + unsigned long nr_pages, gfp_t gfp_mask) +{ + unsigned long end_pfn = start_pfn + nr_pages; + + return alloc_contig_range(start_pfn, end_pfn, MIGRATE_MOVABLE, + gfp_mask); +} + +static bool pfn_range_valid_contig(struct zone *z, unsigned long start_pfn, + unsigned long nr_pages) +{ + unsigned long i, end_pfn = start_pfn + nr_pages; + struct page *page; + + for (i = start_pfn; i < end_pfn; i++) { + page = pfn_to_online_page(i); + if (!page) + return false; + + if (page_zone(page) != z) + return false; + + if (PageReserved(page)) + return false; + + if (page_count(page) > 0) + return false; + + if (PageHuge(page)) + return false; + } + return true; +} + +static bool zone_spans_last_pfn(const struct zone *zone, + unsigned long start_pfn, unsigned long nr_pages) +{ + unsigned long last_pfn = start_pfn + nr_pages - 1; + + return zone_spans_pfn(zone, last_pfn); +} + +/** + * alloc_contig_pages() -- tries to find and allocate contiguous range of pages + * @nr_pages: Number of contiguous pages to allocate + * @gfp_mask: GFP mask to limit search and used during compaction + * @nid: Target node + * @nodemask: Mask for other possible nodes + * + * This routine is a wrapper around alloc_contig_range(). It scans over zones + * on an applicable zonelist to find a contiguous pfn range which can then be + * tried for allocation with alloc_contig_range(). This routine is intended + * for allocation requests which can not be fulfilled with the buddy allocator. + * + * The allocated memory is always aligned to a page boundary. If nr_pages is a + * power of two then the alignment is guaranteed to be to the given nr_pages + * (e.g. 1GB request would be aligned to 1GB). + * + * Allocated pages can be freed with free_contig_range() or by manually calling + * __free_page() on each allocated page. + * + * Return: pointer to contiguous pages on success, or NULL if not successful. + */ +struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask, + int nid, nodemask_t *nodemask) +{ + unsigned long ret, pfn, flags; + struct zonelist *zonelist; + struct zone *zone; + struct zoneref *z; + + zonelist = node_zonelist(nid, gfp_mask); + for_each_zone_zonelist_nodemask(zone, z, zonelist, + gfp_zone(gfp_mask), nodemask) { + spin_lock_irqsave(&zone->lock, flags); + + pfn = ALIGN(zone->zone_start_pfn, nr_pages); + while (zone_spans_last_pfn(zone, pfn, nr_pages)) { + if (pfn_range_valid_contig(zone, pfn, nr_pages)) { + /* + * We release the zone lock here because + * alloc_contig_range() will also lock the zone + * at some point. If there's an allocation + * spinning on this lock, it may win the race + * and cause alloc_contig_range() to fail... + */ + spin_unlock_irqrestore(&zone->lock, flags); + ret = __alloc_contig_pages(pfn, nr_pages, + gfp_mask); + if (!ret) + return pfn_to_page(pfn); + spin_lock_irqsave(&zone->lock, flags); + } + pfn += nr_pages; + } + spin_unlock_irqrestore(&zone->lock, flags); + } + return NULL; +} +#endif /* CONFIG_CONTIG_ALLOC */ + +void free_contig_range(unsigned long pfn, unsigned int nr_pages) +{ + unsigned int count = 0; + + for (; nr_pages--; pfn++) { + struct page *page = pfn_to_page(pfn); + + count += page_count(page) != 1; + __free_page(page); + } + WARN(count != 0, "%d pages are still in use!\n", count); +} +EXPORT_SYMBOL(free_contig_range); + +/* + * The zone indicated has a new number of managed_pages; batch sizes and percpu + * page high values need to be recalulated. + */ +void __meminit zone_pcp_update(struct zone *zone) +{ + mutex_lock(&pcp_batch_high_lock); + __zone_pcp_update(zone); + mutex_unlock(&pcp_batch_high_lock); +} + +void zone_pcp_reset(struct zone *zone) +{ + unsigned long flags; + int cpu; + struct per_cpu_pageset *pset; + + /* avoid races with drain_pages() */ + local_irq_save(flags); + if (zone->pageset != &boot_pageset) { + for_each_online_cpu(cpu) { + pset = per_cpu_ptr(zone->pageset, cpu); + drain_zonestat(zone, pset); + } + free_percpu(zone->pageset); + zone->pageset = &boot_pageset; + } + local_irq_restore(flags); +} + +#ifdef CONFIG_MEMORY_HOTREMOVE +/* + * All pages in the range must be in a single zone, must not contain holes, + * must span full sections, and must be isolated before calling this function. + */ +void __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) +{ + unsigned long pfn = start_pfn; + struct page *page; + struct zone *zone; + unsigned int order; + unsigned long flags; + + offline_mem_sections(pfn, end_pfn); + zone = page_zone(pfn_to_page(pfn)); + spin_lock_irqsave(&zone->lock, flags); + while (pfn < end_pfn) { + page = pfn_to_page(pfn); + /* + * The HWPoisoned page may be not in buddy system, and + * page_count() is not 0. + */ + if (unlikely(!PageBuddy(page) && PageHWPoison(page))) { + pfn++; + continue; + } + /* + * At this point all remaining PageOffline() pages have a + * reference count of 0 and can simply be skipped. + */ + if (PageOffline(page)) { + BUG_ON(page_count(page)); + BUG_ON(PageBuddy(page)); + pfn++; + continue; + } + + BUG_ON(page_count(page)); + BUG_ON(!PageBuddy(page)); + order = buddy_order(page); + del_page_from_free_list(page, zone, order); + pfn += (1 << order); + } + spin_unlock_irqrestore(&zone->lock, flags); +} +#endif + +bool is_free_buddy_page(struct page *page) +{ + struct zone *zone = page_zone(page); + unsigned long pfn = page_to_pfn(page); + unsigned long flags; + unsigned int order; + + spin_lock_irqsave(&zone->lock, flags); + for (order = 0; order < MAX_ORDER; order++) { + struct page *page_head = page - (pfn & ((1 << order) - 1)); + + if (PageBuddy(page_head) && buddy_order(page_head) >= order) + break; + } + spin_unlock_irqrestore(&zone->lock, flags); + + return order < MAX_ORDER; +} + +#ifdef CONFIG_MEMORY_FAILURE +/* + * Break down a higher-order page in sub-pages, and keep our target out of + * buddy allocator. + */ +static void break_down_buddy_pages(struct zone *zone, struct page *page, + struct page *target, int low, int high, + int migratetype) +{ + unsigned long size = 1 << high; + struct page *current_buddy, *next_page; + + while (high > low) { + high--; + size >>= 1; + + if (target >= &page[size]) { + next_page = page + size; + current_buddy = page; + } else { + next_page = page; + current_buddy = page + size; + } + page = next_page; + + if (set_page_guard(zone, current_buddy, high, migratetype)) + continue; + + if (current_buddy != target) { + add_to_free_list(current_buddy, zone, high, migratetype); + set_buddy_order(current_buddy, high); + } + } +} + +/* + * Take a page that will be marked as poisoned off the buddy allocator. + */ +bool take_page_off_buddy(struct page *page) +{ + struct zone *zone = page_zone(page); + unsigned long pfn = page_to_pfn(page); + unsigned long flags; + unsigned int order; + bool ret = false; + + spin_lock_irqsave(&zone->lock, flags); + for (order = 0; order < MAX_ORDER; order++) { + struct page *page_head = page - (pfn & ((1 << order) - 1)); + int page_order = buddy_order(page_head); + + if (PageBuddy(page_head) && page_order >= order) { + unsigned long pfn_head = page_to_pfn(page_head); + int migratetype = get_pfnblock_migratetype(page_head, + pfn_head); + + del_page_from_free_list(page_head, zone, page_order); + break_down_buddy_pages(zone, page_head, page, 0, + page_order, migratetype); + if (!is_migrate_isolate(migratetype)) + __mod_zone_freepage_state(zone, -1, migratetype); + ret = true; + break; + } + if (page_count(page_head) > 0) + break; + } + spin_unlock_irqrestore(&zone->lock, flags); + return ret; +} +#endif + +#ifdef CONFIG_ZONE_DMA +bool has_managed_dma(void) +{ + struct pglist_data *pgdat; + + for_each_online_pgdat(pgdat) { + struct zone *zone = &pgdat->node_zones[ZONE_DMA]; + + if (managed_zone(zone)) + return true; + } + return false; +} +#endif /* CONFIG_ZONE_DMA */ diff --git a/mm/page_counter.c b/mm/page_counter.c new file mode 100644 index 000000000..b24a60b28 --- /dev/null +++ b/mm/page_counter.c @@ -0,0 +1,262 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Lockless hierarchical page accounting & limiting + * + * Copyright (C) 2014 Red Hat, Inc., Johannes Weiner + */ + +#include +#include +#include +#include +#include +#include +#include + +static void propagate_protected_usage(struct page_counter *c, + unsigned long usage) +{ + unsigned long protected, old_protected; + unsigned long low, min; + long delta; + + if (!c->parent) + return; + + min = READ_ONCE(c->min); + if (min || atomic_long_read(&c->min_usage)) { + protected = min(usage, min); + old_protected = atomic_long_xchg(&c->min_usage, protected); + delta = protected - old_protected; + if (delta) + atomic_long_add(delta, &c->parent->children_min_usage); + } + + low = READ_ONCE(c->low); + if (low || atomic_long_read(&c->low_usage)) { + protected = min(usage, low); + old_protected = atomic_long_xchg(&c->low_usage, protected); + delta = protected - old_protected; + if (delta) + atomic_long_add(delta, &c->parent->children_low_usage); + } +} + +/** + * page_counter_cancel - take pages out of the local counter + * @counter: counter + * @nr_pages: number of pages to cancel + */ +void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages) +{ + long new; + + new = atomic_long_sub_return(nr_pages, &counter->usage); + propagate_protected_usage(counter, new); + /* More uncharges than charges? */ + WARN_ON_ONCE(new < 0); +} + +/** + * page_counter_charge - hierarchically charge pages + * @counter: counter + * @nr_pages: number of pages to charge + * + * NOTE: This does not consider any configured counter limits. + */ +void page_counter_charge(struct page_counter *counter, unsigned long nr_pages) +{ + struct page_counter *c; + + for (c = counter; c; c = c->parent) { + long new; + + new = atomic_long_add_return(nr_pages, &c->usage); + propagate_protected_usage(c, new); + /* + * This is indeed racy, but we can live with some + * inaccuracy in the watermark. + */ + if (new > READ_ONCE(c->watermark)) + WRITE_ONCE(c->watermark, new); + } +} + +/** + * page_counter_try_charge - try to hierarchically charge pages + * @counter: counter + * @nr_pages: number of pages to charge + * @fail: points first counter to hit its limit, if any + * + * Returns %true on success, or %false and @fail if the counter or one + * of its ancestors has hit its configured limit. + */ +bool page_counter_try_charge(struct page_counter *counter, + unsigned long nr_pages, + struct page_counter **fail) +{ + struct page_counter *c; + + for (c = counter; c; c = c->parent) { + long new; + /* + * Charge speculatively to avoid an expensive CAS. If + * a bigger charge fails, it might falsely lock out a + * racing smaller charge and send it into reclaim + * early, but the error is limited to the difference + * between the two sizes, which is less than 2M/4M in + * case of a THP locking out a regular page charge. + * + * The atomic_long_add_return() implies a full memory + * barrier between incrementing the count and reading + * the limit. When racing with page_counter_set_max(), + * we either see the new limit or the setter sees the + * counter has changed and retries. + */ + new = atomic_long_add_return(nr_pages, &c->usage); + if (new > c->max) { + atomic_long_sub(nr_pages, &c->usage); + propagate_protected_usage(c, new); + /* + * This is racy, but we can live with some + * inaccuracy in the failcnt which is only used + * to report stats. + */ + data_race(c->failcnt++); + *fail = c; + goto failed; + } + propagate_protected_usage(c, new); + /* + * Just like with failcnt, we can live with some + * inaccuracy in the watermark. + */ + if (new > READ_ONCE(c->watermark)) + WRITE_ONCE(c->watermark, new); + } + return true; + +failed: + for (c = counter; c != *fail; c = c->parent) + page_counter_cancel(c, nr_pages); + + return false; +} + +/** + * page_counter_uncharge - hierarchically uncharge pages + * @counter: counter + * @nr_pages: number of pages to uncharge + */ +void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages) +{ + struct page_counter *c; + + for (c = counter; c; c = c->parent) + page_counter_cancel(c, nr_pages); +} + +/** + * page_counter_set_max - set the maximum number of pages allowed + * @counter: counter + * @nr_pages: limit to set + * + * Returns 0 on success, -EBUSY if the current number of pages on the + * counter already exceeds the specified limit. + * + * The caller must serialize invocations on the same counter. + */ +int page_counter_set_max(struct page_counter *counter, unsigned long nr_pages) +{ + for (;;) { + unsigned long old; + long usage; + + /* + * Update the limit while making sure that it's not + * below the concurrently-changing counter value. + * + * The xchg implies two full memory barriers before + * and after, so the read-swap-read is ordered and + * ensures coherency with page_counter_try_charge(): + * that function modifies the count before checking + * the limit, so if it sees the old limit, we see the + * modified counter and retry. + */ + usage = atomic_long_read(&counter->usage); + + if (usage > nr_pages) + return -EBUSY; + + old = xchg(&counter->max, nr_pages); + + if (atomic_long_read(&counter->usage) <= usage) + return 0; + + counter->max = old; + cond_resched(); + } +} + +/** + * page_counter_set_min - set the amount of protected memory + * @counter: counter + * @nr_pages: value to set + * + * The caller must serialize invocations on the same counter. + */ +void page_counter_set_min(struct page_counter *counter, unsigned long nr_pages) +{ + struct page_counter *c; + + WRITE_ONCE(counter->min, nr_pages); + + for (c = counter; c; c = c->parent) + propagate_protected_usage(c, atomic_long_read(&c->usage)); +} + +/** + * page_counter_set_low - set the amount of protected memory + * @counter: counter + * @nr_pages: value to set + * + * The caller must serialize invocations on the same counter. + */ +void page_counter_set_low(struct page_counter *counter, unsigned long nr_pages) +{ + struct page_counter *c; + + WRITE_ONCE(counter->low, nr_pages); + + for (c = counter; c; c = c->parent) + propagate_protected_usage(c, atomic_long_read(&c->usage)); +} + +/** + * page_counter_memparse - memparse() for page counter limits + * @buf: string to parse + * @max: string meaning maximum possible value + * @nr_pages: returns the result in number of pages + * + * Returns -EINVAL, or 0 and @nr_pages on success. @nr_pages will be + * limited to %PAGE_COUNTER_MAX. + */ +int page_counter_memparse(const char *buf, const char *max, + unsigned long *nr_pages) +{ + char *end; + u64 bytes; + + if (!strcmp(buf, max)) { + *nr_pages = PAGE_COUNTER_MAX; + return 0; + } + + bytes = memparse(buf, &end); + if (*end != '\0') + return -EINVAL; + + *nr_pages = min(bytes / PAGE_SIZE, (u64)PAGE_COUNTER_MAX); + + return 0; +} diff --git a/mm/page_ext.c b/mm/page_ext.c new file mode 100644 index 000000000..a3616f7a0 --- /dev/null +++ b/mm/page_ext.c @@ -0,0 +1,412 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * struct page extension + * + * This is the feature to manage memory for extended data per page. + * + * Until now, we must modify struct page itself to store extra data per page. + * This requires rebuilding the kernel and it is really time consuming process. + * And, sometimes, rebuild is impossible due to third party module dependency. + * At last, enlarging struct page could cause un-wanted system behaviour change. + * + * This feature is intended to overcome above mentioned problems. This feature + * allocates memory for extended data per page in certain place rather than + * the struct page itself. This memory can be accessed by the accessor + * functions provided by this code. During the boot process, it checks whether + * allocation of huge chunk of memory is needed or not. If not, it avoids + * allocating memory at all. With this advantage, we can include this feature + * into the kernel in default and can avoid rebuild and solve related problems. + * + * To help these things to work well, there are two callbacks for clients. One + * is the need callback which is mandatory if user wants to avoid useless + * memory allocation at boot-time. The other is optional, init callback, which + * is used to do proper initialization after memory is allocated. + * + * The need callback is used to decide whether extended memory allocation is + * needed or not. Sometimes users want to deactivate some features in this + * boot and extra memory would be unneccessary. In this case, to avoid + * allocating huge chunk of memory, each clients represent their need of + * extra memory through the need callback. If one of the need callbacks + * returns true, it means that someone needs extra memory so that + * page extension core should allocates memory for page extension. If + * none of need callbacks return true, memory isn't needed at all in this boot + * and page extension core can skip to allocate memory. As result, + * none of memory is wasted. + * + * When need callback returns true, page_ext checks if there is a request for + * extra memory through size in struct page_ext_operations. If it is non-zero, + * extra space is allocated for each page_ext entry and offset is returned to + * user through offset in struct page_ext_operations. + * + * The init callback is used to do proper initialization after page extension + * is completely initialized. In sparse memory system, extra memory is + * allocated some time later than memmap is allocated. In other words, lifetime + * of memory for page extension isn't same with memmap for struct page. + * Therefore, clients can't store extra data until page extension is + * initialized, even if pages are allocated and used freely. This could + * cause inadequate state of extra data per page, so, to prevent it, client + * can utilize this callback to initialize the state of it correctly. + */ + +static struct page_ext_operations *page_ext_ops[] = { +#ifdef CONFIG_PAGE_OWNER + &page_owner_ops, +#endif +#if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT) + &page_idle_ops, +#endif +}; + +unsigned long page_ext_size = sizeof(struct page_ext); + +static unsigned long total_usage; + +static bool __init invoke_need_callbacks(void) +{ + int i; + int entries = ARRAY_SIZE(page_ext_ops); + bool need = false; + + for (i = 0; i < entries; i++) { + if (page_ext_ops[i]->need && page_ext_ops[i]->need()) { + page_ext_ops[i]->offset = page_ext_size; + page_ext_size += page_ext_ops[i]->size; + need = true; + } + } + + return need; +} + +static void __init invoke_init_callbacks(void) +{ + int i; + int entries = ARRAY_SIZE(page_ext_ops); + + for (i = 0; i < entries; i++) { + if (page_ext_ops[i]->init) + page_ext_ops[i]->init(); + } +} + +static inline struct page_ext *get_entry(void *base, unsigned long index) +{ + return base + page_ext_size * index; +} + +#if !defined(CONFIG_SPARSEMEM) + + +void __meminit pgdat_page_ext_init(struct pglist_data *pgdat) +{ + pgdat->node_page_ext = NULL; +} + +struct page_ext *lookup_page_ext(const struct page *page) +{ + unsigned long pfn = page_to_pfn(page); + unsigned long index; + struct page_ext *base; + + base = NODE_DATA(page_to_nid(page))->node_page_ext; + /* + * The sanity checks the page allocator does upon freeing a + * page can reach here before the page_ext arrays are + * allocated when feeding a range of pages to the allocator + * for the first time during bootup or memory hotplug. + */ + if (unlikely(!base)) + return NULL; + index = pfn - round_down(node_start_pfn(page_to_nid(page)), + MAX_ORDER_NR_PAGES); + return get_entry(base, index); +} + +static int __init alloc_node_page_ext(int nid) +{ + struct page_ext *base; + unsigned long table_size; + unsigned long nr_pages; + + nr_pages = NODE_DATA(nid)->node_spanned_pages; + if (!nr_pages) + return 0; + + /* + * Need extra space if node range is not aligned with + * MAX_ORDER_NR_PAGES. When page allocator's buddy algorithm + * checks buddy's status, range could be out of exact node range. + */ + if (!IS_ALIGNED(node_start_pfn(nid), MAX_ORDER_NR_PAGES) || + !IS_ALIGNED(node_end_pfn(nid), MAX_ORDER_NR_PAGES)) + nr_pages += MAX_ORDER_NR_PAGES; + + table_size = page_ext_size * nr_pages; + + base = memblock_alloc_try_nid( + table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), + MEMBLOCK_ALLOC_ACCESSIBLE, nid); + if (!base) + return -ENOMEM; + NODE_DATA(nid)->node_page_ext = base; + total_usage += table_size; + return 0; +} + +void __init page_ext_init_flatmem(void) +{ + + int nid, fail; + + if (!invoke_need_callbacks()) + return; + + for_each_online_node(nid) { + fail = alloc_node_page_ext(nid); + if (fail) + goto fail; + } + pr_info("allocated %ld bytes of page_ext\n", total_usage); + invoke_init_callbacks(); + return; + +fail: + pr_crit("allocation of page_ext failed.\n"); + panic("Out of memory"); +} + +#else /* CONFIG_FLAT_NODE_MEM_MAP */ + +struct page_ext *lookup_page_ext(const struct page *page) +{ + unsigned long pfn = page_to_pfn(page); + struct mem_section *section = __pfn_to_section(pfn); + /* + * The sanity checks the page allocator does upon freeing a + * page can reach here before the page_ext arrays are + * allocated when feeding a range of pages to the allocator + * for the first time during bootup or memory hotplug. + */ + if (!section->page_ext) + return NULL; + return get_entry(section->page_ext, pfn); +} + +static void *__meminit alloc_page_ext(size_t size, int nid) +{ + gfp_t flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN; + void *addr = NULL; + + addr = alloc_pages_exact_nid(nid, size, flags); + if (addr) { + kmemleak_alloc(addr, size, 1, flags); + return addr; + } + + addr = vzalloc_node(size, nid); + + return addr; +} + +static int __meminit init_section_page_ext(unsigned long pfn, int nid) +{ + struct mem_section *section; + struct page_ext *base; + unsigned long table_size; + + section = __pfn_to_section(pfn); + + if (section->page_ext) + return 0; + + table_size = page_ext_size * PAGES_PER_SECTION; + base = alloc_page_ext(table_size, nid); + + /* + * The value stored in section->page_ext is (base - pfn) + * and it does not point to the memory block allocated above, + * causing kmemleak false positives. + */ + kmemleak_not_leak(base); + + if (!base) { + pr_err("page ext allocation failure\n"); + return -ENOMEM; + } + + /* + * The passed "pfn" may not be aligned to SECTION. For the calculation + * we need to apply a mask. + */ + pfn &= PAGE_SECTION_MASK; + section->page_ext = (void *)base - page_ext_size * pfn; + total_usage += table_size; + return 0; +} +#ifdef CONFIG_MEMORY_HOTPLUG +static void free_page_ext(void *addr) +{ + if (is_vmalloc_addr(addr)) { + vfree(addr); + } else { + struct page *page = virt_to_page(addr); + size_t table_size; + + table_size = page_ext_size * PAGES_PER_SECTION; + + BUG_ON(PageReserved(page)); + kmemleak_free(addr); + free_pages_exact(addr, table_size); + } +} + +static void __free_page_ext(unsigned long pfn) +{ + struct mem_section *ms; + struct page_ext *base; + + ms = __pfn_to_section(pfn); + if (!ms || !ms->page_ext) + return; + base = get_entry(ms->page_ext, pfn); + free_page_ext(base); + ms->page_ext = NULL; +} + +static int __meminit online_page_ext(unsigned long start_pfn, + unsigned long nr_pages, + int nid) +{ + unsigned long start, end, pfn; + int fail = 0; + + start = SECTION_ALIGN_DOWN(start_pfn); + end = SECTION_ALIGN_UP(start_pfn + nr_pages); + + if (nid == NUMA_NO_NODE) { + /* + * In this case, "nid" already exists and contains valid memory. + * "start_pfn" passed to us is a pfn which is an arg for + * online__pages(), and start_pfn should exist. + */ + nid = pfn_to_nid(start_pfn); + VM_BUG_ON(!node_state(nid, N_ONLINE)); + } + + for (pfn = start; !fail && pfn < end; pfn += PAGES_PER_SECTION) + fail = init_section_page_ext(pfn, nid); + if (!fail) + return 0; + + /* rollback */ + for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) + __free_page_ext(pfn); + + return -ENOMEM; +} + +static int __meminit offline_page_ext(unsigned long start_pfn, + unsigned long nr_pages, int nid) +{ + unsigned long start, end, pfn; + + start = SECTION_ALIGN_DOWN(start_pfn); + end = SECTION_ALIGN_UP(start_pfn + nr_pages); + + for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) + __free_page_ext(pfn); + return 0; + +} + +static int __meminit page_ext_callback(struct notifier_block *self, + unsigned long action, void *arg) +{ + struct memory_notify *mn = arg; + int ret = 0; + + switch (action) { + case MEM_GOING_ONLINE: + ret = online_page_ext(mn->start_pfn, + mn->nr_pages, mn->status_change_nid); + break; + case MEM_OFFLINE: + offline_page_ext(mn->start_pfn, + mn->nr_pages, mn->status_change_nid); + break; + case MEM_CANCEL_ONLINE: + offline_page_ext(mn->start_pfn, + mn->nr_pages, mn->status_change_nid); + break; + case MEM_GOING_OFFLINE: + break; + case MEM_ONLINE: + case MEM_CANCEL_OFFLINE: + break; + } + + return notifier_from_errno(ret); +} + +#endif + +void __init page_ext_init(void) +{ + unsigned long pfn; + int nid; + + if (!invoke_need_callbacks()) + return; + + for_each_node_state(nid, N_MEMORY) { + unsigned long start_pfn, end_pfn; + + start_pfn = node_start_pfn(nid); + end_pfn = node_end_pfn(nid); + /* + * start_pfn and end_pfn may not be aligned to SECTION and the + * page->flags of out of node pages are not initialized. So we + * scan [start_pfn, the biggest section's pfn < end_pfn) here. + */ + for (pfn = start_pfn; pfn < end_pfn; + pfn = ALIGN(pfn + 1, PAGES_PER_SECTION)) { + + if (!pfn_valid(pfn)) + continue; + /* + * Nodes's pfns can be overlapping. + * We know some arch can have a nodes layout such as + * -------------pfn--------------> + * N0 | N1 | N2 | N0 | N1 | N2|.... + */ + if (pfn_to_nid(pfn) != nid) + continue; + if (init_section_page_ext(pfn, nid)) + goto oom; + cond_resched(); + } + } + hotplug_memory_notifier(page_ext_callback, 0); + pr_info("allocated %ld bytes of page_ext\n", total_usage); + invoke_init_callbacks(); + return; + +oom: + panic("Out of memory"); +} + +void __meminit pgdat_page_ext_init(struct pglist_data *pgdat) +{ +} + +#endif diff --git a/mm/page_idle.c b/mm/page_idle.c new file mode 100644 index 000000000..057c61df1 --- /dev/null +++ b/mm/page_idle.c @@ -0,0 +1,235 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define BITMAP_CHUNK_SIZE sizeof(u64) +#define BITMAP_CHUNK_BITS (BITMAP_CHUNK_SIZE * BITS_PER_BYTE) + +/* + * Idle page tracking only considers user memory pages, for other types of + * pages the idle flag is always unset and an attempt to set it is silently + * ignored. + * + * We treat a page as a user memory page if it is on an LRU list, because it is + * always safe to pass such a page to rmap_walk(), which is essential for idle + * page tracking. With such an indicator of user pages we can skip isolated + * pages, but since there are not usually many of them, it will hardly affect + * the overall result. + * + * This function tries to get a user memory page by pfn as described above. + */ +static struct page *page_idle_get_page(unsigned long pfn) +{ + struct page *page = pfn_to_online_page(pfn); + pg_data_t *pgdat; + + if (!page || !PageLRU(page) || + !get_page_unless_zero(page)) + return NULL; + + pgdat = page_pgdat(page); + spin_lock_irq(&pgdat->lru_lock); + if (unlikely(!PageLRU(page))) { + put_page(page); + page = NULL; + } + spin_unlock_irq(&pgdat->lru_lock); + return page; +} + +static bool page_idle_clear_pte_refs_one(struct page *page, + struct vm_area_struct *vma, + unsigned long addr, void *arg) +{ + struct page_vma_mapped_walk pvmw = { + .page = page, + .vma = vma, + .address = addr, + }; + bool referenced = false; + + while (page_vma_mapped_walk(&pvmw)) { + addr = pvmw.address; + if (pvmw.pte) { + /* + * For PTE-mapped THP, one sub page is referenced, + * the whole THP is referenced. + */ + if (ptep_clear_young_notify(vma, addr, pvmw.pte)) + referenced = true; + } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { + if (pmdp_clear_young_notify(vma, addr, pvmw.pmd)) + referenced = true; + } else { + /* unexpected pmd-mapped page? */ + WARN_ON_ONCE(1); + } + } + + if (referenced) { + clear_page_idle(page); + /* + * We cleared the referenced bit in a mapping to this page. To + * avoid interference with page reclaim, mark it young so that + * page_referenced() will return > 0. + */ + set_page_young(page); + } + return true; +} + +static void page_idle_clear_pte_refs(struct page *page) +{ + /* + * Since rwc.arg is unused, rwc is effectively immutable, so we + * can make it static const to save some cycles and stack. + */ + static const struct rmap_walk_control rwc = { + .rmap_one = page_idle_clear_pte_refs_one, + .anon_lock = page_lock_anon_vma_read, + }; + bool need_lock; + + if (!page_mapped(page) || + !page_rmapping(page)) + return; + + need_lock = !PageAnon(page) || PageKsm(page); + if (need_lock && !trylock_page(page)) + return; + + rmap_walk(page, (struct rmap_walk_control *)&rwc); + + if (need_lock) + unlock_page(page); +} + +static ssize_t page_idle_bitmap_read(struct file *file, struct kobject *kobj, + struct bin_attribute *attr, char *buf, + loff_t pos, size_t count) +{ + u64 *out = (u64 *)buf; + struct page *page; + unsigned long pfn, end_pfn; + int bit; + + if (pos % BITMAP_CHUNK_SIZE || count % BITMAP_CHUNK_SIZE) + return -EINVAL; + + pfn = pos * BITS_PER_BYTE; + if (pfn >= max_pfn) + return 0; + + end_pfn = pfn + count * BITS_PER_BYTE; + if (end_pfn > max_pfn) + end_pfn = max_pfn; + + for (; pfn < end_pfn; pfn++) { + bit = pfn % BITMAP_CHUNK_BITS; + if (!bit) + *out = 0ULL; + page = page_idle_get_page(pfn); + if (page) { + if (page_is_idle(page)) { + /* + * The page might have been referenced via a + * pte, in which case it is not idle. Clear + * refs and recheck. + */ + page_idle_clear_pte_refs(page); + if (page_is_idle(page)) + *out |= 1ULL << bit; + } + put_page(page); + } + if (bit == BITMAP_CHUNK_BITS - 1) + out++; + cond_resched(); + } + return (char *)out - buf; +} + +static ssize_t page_idle_bitmap_write(struct file *file, struct kobject *kobj, + struct bin_attribute *attr, char *buf, + loff_t pos, size_t count) +{ + const u64 *in = (u64 *)buf; + struct page *page; + unsigned long pfn, end_pfn; + int bit; + + if (pos % BITMAP_CHUNK_SIZE || count % BITMAP_CHUNK_SIZE) + return -EINVAL; + + pfn = pos * BITS_PER_BYTE; + if (pfn >= max_pfn) + return -ENXIO; + + end_pfn = pfn + count * BITS_PER_BYTE; + if (end_pfn > max_pfn) + end_pfn = max_pfn; + + for (; pfn < end_pfn; pfn++) { + bit = pfn % BITMAP_CHUNK_BITS; + if ((*in >> bit) & 1) { + page = page_idle_get_page(pfn); + if (page) { + page_idle_clear_pte_refs(page); + set_page_idle(page); + put_page(page); + } + } + if (bit == BITMAP_CHUNK_BITS - 1) + in++; + cond_resched(); + } + return (char *)in - buf; +} + +static struct bin_attribute page_idle_bitmap_attr = + __BIN_ATTR(bitmap, 0600, + page_idle_bitmap_read, page_idle_bitmap_write, 0); + +static struct bin_attribute *page_idle_bin_attrs[] = { + &page_idle_bitmap_attr, + NULL, +}; + +static const struct attribute_group page_idle_attr_group = { + .bin_attrs = page_idle_bin_attrs, + .name = "page_idle", +}; + +#ifndef CONFIG_64BIT +static bool need_page_idle(void) +{ + return true; +} +struct page_ext_operations page_idle_ops = { + .need = need_page_idle, +}; +#endif + +static int __init page_idle_init(void) +{ + int err; + + err = sysfs_create_group(mm_kobj, &page_idle_attr_group); + if (err) { + pr_err("page_idle: register sysfs failed\n"); + return err; + } + return 0; +} +subsys_initcall(page_idle_init); diff --git a/mm/page_io.c b/mm/page_io.c new file mode 100644 index 000000000..f0ada4455 --- /dev/null +++ b/mm/page_io.c @@ -0,0 +1,417 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/mm/page_io.c + * + * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds + * + * Swap reorganised 29.12.95, + * Asynchronous swapping added 30.12.95. Stephen Tweedie + * Removed race in async swapping. 14.4.1996. Bruno Haible + * Add swap of shared pages through the page cache. 20.2.1998. Stephen Tweedie + * Always use brw_page, life becomes simpler. 12 May 1998 Eric Biederman + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static struct bio *get_swap_bio(gfp_t gfp_flags, + struct page *page, bio_end_io_t end_io) +{ + struct bio *bio; + + bio = bio_alloc(gfp_flags, 1); + if (bio) { + struct block_device *bdev; + + bio->bi_iter.bi_sector = map_swap_page(page, &bdev); + bio_set_dev(bio, bdev); + bio->bi_iter.bi_sector <<= PAGE_SHIFT - 9; + bio->bi_end_io = end_io; + + bio_add_page(bio, page, thp_size(page), 0); + } + return bio; +} + +void end_swap_bio_write(struct bio *bio) +{ + struct page *page = bio_first_page_all(bio); + + if (bio->bi_status) { + SetPageError(page); + /* + * We failed to write the page out to swap-space. + * Re-dirty the page in order to avoid it being reclaimed. + * Also print a dire warning that things will go BAD (tm) + * very quickly. + * + * Also clear PG_reclaim to avoid rotate_reclaimable_page() + */ + set_page_dirty(page); + pr_alert("Write-error on swap-device (%u:%u:%llu)\n", + MAJOR(bio_dev(bio)), MINOR(bio_dev(bio)), + (unsigned long long)bio->bi_iter.bi_sector); + ClearPageReclaim(page); + } + end_page_writeback(page); + bio_put(bio); +} + +static void end_swap_bio_read(struct bio *bio) +{ + struct page *page = bio_first_page_all(bio); + struct task_struct *waiter = bio->bi_private; + + if (bio->bi_status) { + SetPageError(page); + ClearPageUptodate(page); + pr_alert("Read-error on swap-device (%u:%u:%llu)\n", + MAJOR(bio_dev(bio)), MINOR(bio_dev(bio)), + (unsigned long long)bio->bi_iter.bi_sector); + goto out; + } + + SetPageUptodate(page); +out: + unlock_page(page); + WRITE_ONCE(bio->bi_private, NULL); + bio_put(bio); + if (waiter) { + blk_wake_io_task(waiter); + put_task_struct(waiter); + } +} + +int generic_swapfile_activate(struct swap_info_struct *sis, + struct file *swap_file, + sector_t *span) +{ + struct address_space *mapping = swap_file->f_mapping; + struct inode *inode = mapping->host; + unsigned blocks_per_page; + unsigned long page_no; + unsigned blkbits; + sector_t probe_block; + sector_t last_block; + sector_t lowest_block = -1; + sector_t highest_block = 0; + int nr_extents = 0; + int ret; + + blkbits = inode->i_blkbits; + blocks_per_page = PAGE_SIZE >> blkbits; + + /* + * Map all the blocks into the extent tree. This code doesn't try + * to be very smart. + */ + probe_block = 0; + page_no = 0; + last_block = i_size_read(inode) >> blkbits; + while ((probe_block + blocks_per_page) <= last_block && + page_no < sis->max) { + unsigned block_in_page; + sector_t first_block; + + cond_resched(); + + first_block = probe_block; + ret = bmap(inode, &first_block); + if (ret || !first_block) + goto bad_bmap; + + /* + * It must be PAGE_SIZE aligned on-disk + */ + if (first_block & (blocks_per_page - 1)) { + probe_block++; + goto reprobe; + } + + for (block_in_page = 1; block_in_page < blocks_per_page; + block_in_page++) { + sector_t block; + + block = probe_block + block_in_page; + ret = bmap(inode, &block); + if (ret || !block) + goto bad_bmap; + + if (block != first_block + block_in_page) { + /* Discontiguity */ + probe_block++; + goto reprobe; + } + } + + first_block >>= (PAGE_SHIFT - blkbits); + if (page_no) { /* exclude the header page */ + if (first_block < lowest_block) + lowest_block = first_block; + if (first_block > highest_block) + highest_block = first_block; + } + + /* + * We found a PAGE_SIZE-length, PAGE_SIZE-aligned run of blocks + */ + ret = add_swap_extent(sis, page_no, 1, first_block); + if (ret < 0) + goto out; + nr_extents += ret; + page_no++; + probe_block += blocks_per_page; +reprobe: + continue; + } + ret = nr_extents; + *span = 1 + highest_block - lowest_block; + if (page_no == 0) + page_no = 1; /* force Empty message */ + sis->max = page_no; + sis->pages = page_no - 1; + sis->highest_bit = page_no - 1; +out: + return ret; +bad_bmap: + pr_err("swapon: swapfile has holes\n"); + ret = -EINVAL; + goto out; +} + +/* + * We may have stale swap cache pages in memory: notice + * them here and get rid of the unnecessary final write. + */ +int swap_writepage(struct page *page, struct writeback_control *wbc) +{ + int ret = 0; + + if (try_to_free_swap(page)) { + unlock_page(page); + goto out; + } + /* + * Arch code may have to preserve more data than just the page + * contents, e.g. memory tags. + */ + ret = arch_prepare_to_swap(page); + if (ret) { + set_page_dirty(page); + unlock_page(page); + goto out; + } + if (frontswap_store(page) == 0) { + set_page_writeback(page); + unlock_page(page); + end_page_writeback(page); + goto out; + } + ret = __swap_writepage(page, wbc, end_swap_bio_write); +out: + return ret; +} + +static inline void count_swpout_vm_event(struct page *page) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (unlikely(PageTransHuge(page))) + count_vm_event(THP_SWPOUT); +#endif + count_vm_events(PSWPOUT, thp_nr_pages(page)); +} + +#if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) +static void bio_associate_blkg_from_page(struct bio *bio, struct page *page) +{ + struct cgroup_subsys_state *css; + + if (!page->mem_cgroup) + return; + + rcu_read_lock(); + css = cgroup_e_css(page->mem_cgroup->css.cgroup, &io_cgrp_subsys); + bio_associate_blkg_from_css(bio, css); + rcu_read_unlock(); +} +#else +#define bio_associate_blkg_from_page(bio, page) do { } while (0) +#endif /* CONFIG_MEMCG && CONFIG_BLK_CGROUP */ + +int __swap_writepage(struct page *page, struct writeback_control *wbc, + bio_end_io_t end_write_func) +{ + struct bio *bio; + int ret; + struct swap_info_struct *sis = page_swap_info(page); + + VM_BUG_ON_PAGE(!PageSwapCache(page), page); + if (data_race(sis->flags & SWP_FS_OPS)) { + struct kiocb kiocb; + struct file *swap_file = sis->swap_file; + struct address_space *mapping = swap_file->f_mapping; + struct bio_vec bv = { + .bv_page = page, + .bv_len = PAGE_SIZE, + .bv_offset = 0 + }; + struct iov_iter from; + + iov_iter_bvec(&from, WRITE, &bv, 1, PAGE_SIZE); + init_sync_kiocb(&kiocb, swap_file); + kiocb.ki_pos = page_file_offset(page); + + set_page_writeback(page); + unlock_page(page); + ret = mapping->a_ops->direct_IO(&kiocb, &from); + if (ret == PAGE_SIZE) { + count_vm_event(PSWPOUT); + ret = 0; + } else { + /* + * In the case of swap-over-nfs, this can be a + * temporary failure if the system has limited + * memory for allocating transmit buffers. + * Mark the page dirty and avoid + * rotate_reclaimable_page but rate-limit the + * messages but do not flag PageError like + * the normal direct-to-bio case as it could + * be temporary. + */ + set_page_dirty(page); + ClearPageReclaim(page); + pr_err_ratelimited("Write error on dio swapfile (%llu)\n", + page_file_offset(page)); + } + end_page_writeback(page); + return ret; + } + + ret = bdev_write_page(sis->bdev, swap_page_sector(page), page, wbc); + if (!ret) { + count_swpout_vm_event(page); + return 0; + } + + bio = get_swap_bio(GFP_NOIO, page, end_write_func); + if (bio == NULL) { + set_page_dirty(page); + unlock_page(page); + return -ENOMEM; + } + bio->bi_opf = REQ_OP_WRITE | REQ_SWAP | wbc_to_write_flags(wbc); + bio_associate_blkg_from_page(bio, page); + count_swpout_vm_event(page); + set_page_writeback(page); + unlock_page(page); + submit_bio(bio); + + return 0; +} + +int swap_readpage(struct page *page, bool synchronous) +{ + struct bio *bio; + int ret = 0; + struct swap_info_struct *sis = page_swap_info(page); + blk_qc_t qc; + struct gendisk *disk; + unsigned long pflags; + + VM_BUG_ON_PAGE(!PageSwapCache(page) && !synchronous, page); + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(PageUptodate(page), page); + + /* + * Count submission time as memory stall. When the device is congested, + * or the submitting cgroup IO-throttled, submission can be a + * significant part of overall IO time. + */ + psi_memstall_enter(&pflags); + + if (frontswap_load(page) == 0) { + SetPageUptodate(page); + unlock_page(page); + goto out; + } + + if (data_race(sis->flags & SWP_FS_OPS)) { + struct file *swap_file = sis->swap_file; + struct address_space *mapping = swap_file->f_mapping; + + ret = mapping->a_ops->readpage(swap_file, page); + if (!ret) + count_vm_event(PSWPIN); + goto out; + } + + if (sis->flags & SWP_SYNCHRONOUS_IO) { + ret = bdev_read_page(sis->bdev, swap_page_sector(page), page); + if (!ret) { + count_vm_event(PSWPIN); + goto out; + } + } + + ret = 0; + bio = get_swap_bio(GFP_KERNEL, page, end_swap_bio_read); + if (bio == NULL) { + unlock_page(page); + ret = -ENOMEM; + goto out; + } + disk = bio->bi_disk; + /* + * Keep this task valid during swap readpage because the oom killer may + * attempt to access it in the page fault retry time check. + */ + bio_set_op_attrs(bio, REQ_OP_READ, 0); + if (synchronous) { + bio->bi_opf |= REQ_HIPRI; + get_task_struct(current); + bio->bi_private = current; + } + count_vm_event(PSWPIN); + bio_get(bio); + qc = submit_bio(bio); + while (synchronous) { + set_current_state(TASK_UNINTERRUPTIBLE); + if (!READ_ONCE(bio->bi_private)) + break; + + if (!blk_poll(disk->queue, qc, true)) + blk_io_schedule(); + } + __set_current_state(TASK_RUNNING); + bio_put(bio); + +out: + psi_memstall_leave(&pflags); + return ret; +} + +int swap_set_page_dirty(struct page *page) +{ + struct swap_info_struct *sis = page_swap_info(page); + + if (data_race(sis->flags & SWP_FS_OPS)) { + struct address_space *mapping = sis->swap_file->f_mapping; + + VM_BUG_ON_PAGE(!PageSwapCache(page), page); + return mapping->a_ops->set_page_dirty(page); + } else { + return __set_page_dirty_no_writeback(page); + } +} diff --git a/mm/page_isolation.c b/mm/page_isolation.c new file mode 100644 index 000000000..abbf42214 --- /dev/null +++ b/mm/page_isolation.c @@ -0,0 +1,313 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/mm/page_isolation.c + */ + +#include +#include +#include +#include +#include +#include +#include +#include "internal.h" + +#define CREATE_TRACE_POINTS +#include + +static int set_migratetype_isolate(struct page *page, int migratetype, int isol_flags) +{ + struct zone *zone = page_zone(page); + struct page *unmovable; + unsigned long flags; + + spin_lock_irqsave(&zone->lock, flags); + + /* + * We assume the caller intended to SET migrate type to isolate. + * If it is already set, then someone else must have raced and + * set it before us. + */ + if (is_migrate_isolate_page(page)) { + spin_unlock_irqrestore(&zone->lock, flags); + return -EBUSY; + } + + /* + * FIXME: Now, memory hotplug doesn't call shrink_slab() by itself. + * We just check MOVABLE pages. + */ + unmovable = has_unmovable_pages(zone, page, migratetype, isol_flags); + if (!unmovable) { + unsigned long nr_pages; + int mt = get_pageblock_migratetype(page); + + set_pageblock_migratetype(page, MIGRATE_ISOLATE); + zone->nr_isolate_pageblock++; + nr_pages = move_freepages_block(zone, page, MIGRATE_ISOLATE, + NULL); + + __mod_zone_freepage_state(zone, -nr_pages, mt); + spin_unlock_irqrestore(&zone->lock, flags); + drain_all_pages(zone); + return 0; + } + + spin_unlock_irqrestore(&zone->lock, flags); + if (isol_flags & REPORT_FAILURE) { + /* + * printk() with zone->lock held will likely trigger a + * lockdep splat, so defer it here. + */ + dump_page(unmovable, "unmovable page"); + } + + return -EBUSY; +} + +static void unset_migratetype_isolate(struct page *page, unsigned migratetype) +{ + struct zone *zone; + unsigned long flags, nr_pages; + bool isolated_page = false; + unsigned int order; + unsigned long pfn, buddy_pfn; + struct page *buddy; + + zone = page_zone(page); + spin_lock_irqsave(&zone->lock, flags); + if (!is_migrate_isolate_page(page)) + goto out; + + /* + * Because freepage with more than pageblock_order on isolated + * pageblock is restricted to merge due to freepage counting problem, + * it is possible that there is free buddy page. + * move_freepages_block() doesn't care of merge so we need other + * approach in order to merge them. Isolation and free will make + * these pages to be merged. + */ + if (PageBuddy(page)) { + order = buddy_order(page); + if (order >= pageblock_order) { + pfn = page_to_pfn(page); + buddy_pfn = __find_buddy_pfn(pfn, order); + buddy = page + (buddy_pfn - pfn); + + if (pfn_valid_within(buddy_pfn) && + !is_migrate_isolate_page(buddy)) { + __isolate_free_page(page, order); + isolated_page = true; + } + } + } + + /* + * If we isolate freepage with more than pageblock_order, there + * should be no freepage in the range, so we could avoid costly + * pageblock scanning for freepage moving. + * + * We didn't actually touch any of the isolated pages, so place them + * to the tail of the freelist. This is an optimization for memory + * onlining - just onlined memory won't immediately be considered for + * allocation. + */ + if (!isolated_page) { + nr_pages = move_freepages_block(zone, page, migratetype, NULL); + __mod_zone_freepage_state(zone, nr_pages, migratetype); + } + set_pageblock_migratetype(page, migratetype); + if (isolated_page) + __putback_isolated_page(page, order, migratetype); + zone->nr_isolate_pageblock--; +out: + spin_unlock_irqrestore(&zone->lock, flags); +} + +static inline struct page * +__first_valid_page(unsigned long pfn, unsigned long nr_pages) +{ + int i; + + for (i = 0; i < nr_pages; i++) { + struct page *page; + + page = pfn_to_online_page(pfn + i); + if (!page) + continue; + return page; + } + return NULL; +} + +/** + * start_isolate_page_range() - make page-allocation-type of range of pages to + * be MIGRATE_ISOLATE. + * @start_pfn: The lower PFN of the range to be isolated. + * @end_pfn: The upper PFN of the range to be isolated. + * start_pfn/end_pfn must be aligned to pageblock_order. + * @migratetype: Migrate type to set in error recovery. + * @flags: The following flags are allowed (they can be combined in + * a bit mask) + * MEMORY_OFFLINE - isolate to offline (!allocate) memory + * e.g., skip over PageHWPoison() pages + * and PageOffline() pages. + * REPORT_FAILURE - report details about the failure to + * isolate the range + * + * Making page-allocation-type to be MIGRATE_ISOLATE means free pages in + * the range will never be allocated. Any free pages and pages freed in the + * future will not be allocated again. If specified range includes migrate types + * other than MOVABLE or CMA, this will fail with -EBUSY. For isolating all + * pages in the range finally, the caller have to free all pages in the range. + * test_page_isolated() can be used for test it. + * + * There is no high level synchronization mechanism that prevents two threads + * from trying to isolate overlapping ranges. If this happens, one thread + * will notice pageblocks in the overlapping range already set to isolate. + * This happens in set_migratetype_isolate, and set_migratetype_isolate + * returns an error. We then clean up by restoring the migration type on + * pageblocks we may have modified and return -EBUSY to caller. This + * prevents two threads from simultaneously working on overlapping ranges. + * + * Please note that there is no strong synchronization with the page allocator + * either. Pages might be freed while their page blocks are marked ISOLATED. + * In some cases pages might still end up on pcp lists and that would allow + * for their allocation even when they are in fact isolated already. Depending + * on how strong of a guarantee the caller needs drain_all_pages might be needed + * (e.g. __offline_pages will need to call it after check for isolated range for + * a next retry). + * + * Return: 0 on success and -EBUSY if any part of range cannot be isolated. + */ +int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, + unsigned migratetype, int flags) +{ + unsigned long pfn; + unsigned long undo_pfn; + struct page *page; + + BUG_ON(!IS_ALIGNED(start_pfn, pageblock_nr_pages)); + BUG_ON(!IS_ALIGNED(end_pfn, pageblock_nr_pages)); + + for (pfn = start_pfn; + pfn < end_pfn; + pfn += pageblock_nr_pages) { + page = __first_valid_page(pfn, pageblock_nr_pages); + if (page) { + if (set_migratetype_isolate(page, migratetype, flags)) { + undo_pfn = pfn; + goto undo; + } + } + } + return 0; +undo: + for (pfn = start_pfn; + pfn < undo_pfn; + pfn += pageblock_nr_pages) { + struct page *page = pfn_to_online_page(pfn); + if (!page) + continue; + unset_migratetype_isolate(page, migratetype); + } + + return -EBUSY; +} + +/* + * Make isolated pages available again. + */ +void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, + unsigned migratetype) +{ + unsigned long pfn; + struct page *page; + + BUG_ON(!IS_ALIGNED(start_pfn, pageblock_nr_pages)); + BUG_ON(!IS_ALIGNED(end_pfn, pageblock_nr_pages)); + + for (pfn = start_pfn; + pfn < end_pfn; + pfn += pageblock_nr_pages) { + page = __first_valid_page(pfn, pageblock_nr_pages); + if (!page || !is_migrate_isolate_page(page)) + continue; + unset_migratetype_isolate(page, migratetype); + } +} +/* + * Test all pages in the range is free(means isolated) or not. + * all pages in [start_pfn...end_pfn) must be in the same zone. + * zone->lock must be held before call this. + * + * Returns the last tested pfn. + */ +static unsigned long +__test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn, + int flags) +{ + struct page *page; + + while (pfn < end_pfn) { + if (!pfn_valid_within(pfn)) { + pfn++; + continue; + } + page = pfn_to_page(pfn); + if (PageBuddy(page)) + /* + * If the page is on a free list, it has to be on + * the correct MIGRATE_ISOLATE freelist. There is no + * simple way to verify that as VM_BUG_ON(), though. + */ + pfn += 1 << buddy_order(page); + else if ((flags & MEMORY_OFFLINE) && PageHWPoison(page)) + /* A HWPoisoned page cannot be also PageBuddy */ + pfn++; + else if ((flags & MEMORY_OFFLINE) && PageOffline(page) && + !page_count(page)) + /* + * The responsible driver agreed to skip PageOffline() + * pages when offlining memory by dropping its + * reference in MEM_GOING_OFFLINE. + */ + pfn++; + else + break; + } + + return pfn; +} + +/* Caller should ensure that requested range is in a single zone */ +int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn, + int isol_flags) +{ + unsigned long pfn, flags; + struct page *page; + struct zone *zone; + + /* + * Note: pageblock_nr_pages != MAX_ORDER. Then, chunks of free pages + * are not aligned to pageblock_nr_pages. + * Then we just check migratetype first. + */ + for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) { + page = __first_valid_page(pfn, pageblock_nr_pages); + if (page && !is_migrate_isolate_page(page)) + break; + } + page = __first_valid_page(start_pfn, end_pfn - start_pfn); + if ((pfn < end_pfn) || !page) + return -EBUSY; + /* Check all pages are free or marked as ISOLATED */ + zone = page_zone(page); + spin_lock_irqsave(&zone->lock, flags); + pfn = __test_page_isolated_in_pageblock(start_pfn, end_pfn, isol_flags); + spin_unlock_irqrestore(&zone->lock, flags); + + trace_test_pages_isolated(start_pfn, end_pfn, pfn); + + return pfn < end_pfn ? -EBUSY : 0; +} diff --git a/mm/page_owner.c b/mm/page_owner.c new file mode 100644 index 000000000..b735a8eaf --- /dev/null +++ b/mm/page_owner.c @@ -0,0 +1,654 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "internal.h" + +/* + * TODO: teach PAGE_OWNER_STACK_DEPTH (__dump_page_owner and save_stack) + * to use off stack temporal storage + */ +#define PAGE_OWNER_STACK_DEPTH (16) + +struct page_owner { + unsigned short order; + short last_migrate_reason; + gfp_t gfp_mask; + depot_stack_handle_t handle; + depot_stack_handle_t free_handle; +}; + +static bool page_owner_enabled = false; +DEFINE_STATIC_KEY_FALSE(page_owner_inited); + +static depot_stack_handle_t dummy_handle; +static depot_stack_handle_t failure_handle; +static depot_stack_handle_t early_handle; + +static void init_early_allocated_pages(void); + +static int __init early_page_owner_param(char *buf) +{ + if (!buf) + return -EINVAL; + + if (strcmp(buf, "on") == 0) + page_owner_enabled = true; + + return 0; +} +early_param("page_owner", early_page_owner_param); + +static bool need_page_owner(void) +{ + return page_owner_enabled; +} + +static __always_inline depot_stack_handle_t create_dummy_stack(void) +{ + unsigned long entries[4]; + unsigned int nr_entries; + + nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0); + return stack_depot_save(entries, nr_entries, GFP_KERNEL); +} + +static noinline void register_dummy_stack(void) +{ + dummy_handle = create_dummy_stack(); +} + +static noinline void register_failure_stack(void) +{ + failure_handle = create_dummy_stack(); +} + +static noinline void register_early_stack(void) +{ + early_handle = create_dummy_stack(); +} + +static void init_page_owner(void) +{ + if (!page_owner_enabled) + return; + + register_dummy_stack(); + register_failure_stack(); + register_early_stack(); + static_branch_enable(&page_owner_inited); + init_early_allocated_pages(); +} + +struct page_ext_operations page_owner_ops = { + .size = sizeof(struct page_owner), + .need = need_page_owner, + .init = init_page_owner, +}; + +static inline struct page_owner *get_page_owner(struct page_ext *page_ext) +{ + return (void *)page_ext + page_owner_ops.offset; +} + +static inline bool check_recursive_alloc(unsigned long *entries, + unsigned int nr_entries, + unsigned long ip) +{ + unsigned int i; + + for (i = 0; i < nr_entries; i++) { + if (entries[i] == ip) + return true; + } + return false; +} + +static noinline depot_stack_handle_t save_stack(gfp_t flags) +{ + unsigned long entries[PAGE_OWNER_STACK_DEPTH]; + depot_stack_handle_t handle; + unsigned int nr_entries; + + nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 2); + + /* + * We need to check recursion here because our request to + * stackdepot could trigger memory allocation to save new + * entry. New memory allocation would reach here and call + * stack_depot_save_entries() again if we don't catch it. There is + * still not enough memory in stackdepot so it would try to + * allocate memory again and loop forever. + */ + if (check_recursive_alloc(entries, nr_entries, _RET_IP_)) + return dummy_handle; + + handle = stack_depot_save(entries, nr_entries, flags); + if (!handle) + handle = failure_handle; + + return handle; +} + +void __reset_page_owner(struct page *page, unsigned int order) +{ + int i; + struct page_ext *page_ext; + depot_stack_handle_t handle = 0; + struct page_owner *page_owner; + + handle = save_stack(GFP_NOWAIT | __GFP_NOWARN); + + page_ext = lookup_page_ext(page); + if (unlikely(!page_ext)) + return; + for (i = 0; i < (1 << order); i++) { + __clear_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); + page_owner = get_page_owner(page_ext); + page_owner->free_handle = handle; + page_ext = page_ext_next(page_ext); + } +} + +static inline void __set_page_owner_handle(struct page *page, + struct page_ext *page_ext, depot_stack_handle_t handle, + unsigned int order, gfp_t gfp_mask) +{ + struct page_owner *page_owner; + int i; + + for (i = 0; i < (1 << order); i++) { + page_owner = get_page_owner(page_ext); + page_owner->handle = handle; + page_owner->order = order; + page_owner->gfp_mask = gfp_mask; + page_owner->last_migrate_reason = -1; + __set_bit(PAGE_EXT_OWNER, &page_ext->flags); + __set_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); + + page_ext = page_ext_next(page_ext); + } +} + +noinline void __set_page_owner(struct page *page, unsigned int order, + gfp_t gfp_mask) +{ + struct page_ext *page_ext = lookup_page_ext(page); + depot_stack_handle_t handle; + + if (unlikely(!page_ext)) + return; + + handle = save_stack(gfp_mask); + __set_page_owner_handle(page, page_ext, handle, order, gfp_mask); +} + +void __set_page_owner_migrate_reason(struct page *page, int reason) +{ + struct page_ext *page_ext = lookup_page_ext(page); + struct page_owner *page_owner; + + if (unlikely(!page_ext)) + return; + + page_owner = get_page_owner(page_ext); + page_owner->last_migrate_reason = reason; +} + +void __split_page_owner(struct page *page, unsigned int nr) +{ + int i; + struct page_ext *page_ext = lookup_page_ext(page); + struct page_owner *page_owner; + + if (unlikely(!page_ext)) + return; + + for (i = 0; i < nr; i++) { + page_owner = get_page_owner(page_ext); + page_owner->order = 0; + page_ext = page_ext_next(page_ext); + } +} + +void __copy_page_owner(struct page *oldpage, struct page *newpage) +{ + struct page_ext *old_ext = lookup_page_ext(oldpage); + struct page_ext *new_ext = lookup_page_ext(newpage); + struct page_owner *old_page_owner, *new_page_owner; + + if (unlikely(!old_ext || !new_ext)) + return; + + old_page_owner = get_page_owner(old_ext); + new_page_owner = get_page_owner(new_ext); + new_page_owner->order = old_page_owner->order; + new_page_owner->gfp_mask = old_page_owner->gfp_mask; + new_page_owner->last_migrate_reason = + old_page_owner->last_migrate_reason; + new_page_owner->handle = old_page_owner->handle; + + /* + * We don't clear the bit on the oldpage as it's going to be freed + * after migration. Until then, the info can be useful in case of + * a bug, and the overal stats will be off a bit only temporarily. + * Also, migrate_misplaced_transhuge_page() can still fail the + * migration and then we want the oldpage to retain the info. But + * in that case we also don't need to explicitly clear the info from + * the new page, which will be freed. + */ + __set_bit(PAGE_EXT_OWNER, &new_ext->flags); + __set_bit(PAGE_EXT_OWNER_ALLOCATED, &new_ext->flags); +} + +void pagetypeinfo_showmixedcount_print(struct seq_file *m, + pg_data_t *pgdat, struct zone *zone) +{ + struct page *page; + struct page_ext *page_ext; + struct page_owner *page_owner; + unsigned long pfn = zone->zone_start_pfn, block_end_pfn; + unsigned long end_pfn = pfn + zone->spanned_pages; + unsigned long count[MIGRATE_TYPES] = { 0, }; + int pageblock_mt, page_mt; + int i; + + /* Scan block by block. First and last block may be incomplete */ + pfn = zone->zone_start_pfn; + + /* + * Walk the zone in pageblock_nr_pages steps. If a page block spans + * a zone boundary, it will be double counted between zones. This does + * not matter as the mixed block count will still be correct + */ + for (; pfn < end_pfn; ) { + page = pfn_to_online_page(pfn); + if (!page) { + pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES); + continue; + } + + block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages); + block_end_pfn = min(block_end_pfn, end_pfn); + + pageblock_mt = get_pageblock_migratetype(page); + + for (; pfn < block_end_pfn; pfn++) { + if (!pfn_valid_within(pfn)) + continue; + + /* The pageblock is online, no need to recheck. */ + page = pfn_to_page(pfn); + + if (page_zone(page) != zone) + continue; + + if (PageBuddy(page)) { + unsigned long freepage_order; + + freepage_order = buddy_order_unsafe(page); + if (freepage_order < MAX_ORDER) + pfn += (1UL << freepage_order) - 1; + continue; + } + + if (PageReserved(page)) + continue; + + page_ext = lookup_page_ext(page); + if (unlikely(!page_ext)) + continue; + + if (!test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags)) + continue; + + page_owner = get_page_owner(page_ext); + page_mt = gfp_migratetype(page_owner->gfp_mask); + if (pageblock_mt != page_mt) { + if (is_migrate_cma(pageblock_mt)) + count[MIGRATE_MOVABLE]++; + else + count[pageblock_mt]++; + + pfn = block_end_pfn; + break; + } + pfn += (1UL << page_owner->order) - 1; + } + } + + /* Print counts */ + seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name); + for (i = 0; i < MIGRATE_TYPES; i++) + seq_printf(m, "%12lu ", count[i]); + seq_putc(m, '\n'); +} + +static ssize_t +print_page_owner(char __user *buf, size_t count, unsigned long pfn, + struct page *page, struct page_owner *page_owner, + depot_stack_handle_t handle) +{ + int ret, pageblock_mt, page_mt; + unsigned long *entries; + unsigned int nr_entries; + char *kbuf; + + count = min_t(size_t, count, PAGE_SIZE); + kbuf = kmalloc(count, GFP_KERNEL); + if (!kbuf) + return -ENOMEM; + + ret = snprintf(kbuf, count, + "Page allocated via order %u, mask %#x(%pGg)\n", + page_owner->order, page_owner->gfp_mask, + &page_owner->gfp_mask); + + if (ret >= count) + goto err; + + /* Print information relevant to grouping pages by mobility */ + pageblock_mt = get_pageblock_migratetype(page); + page_mt = gfp_migratetype(page_owner->gfp_mask); + ret += snprintf(kbuf + ret, count - ret, + "PFN %lu type %s Block %lu type %s Flags %#lx(%pGp)\n", + pfn, + migratetype_names[page_mt], + pfn >> pageblock_order, + migratetype_names[pageblock_mt], + page->flags, &page->flags); + + if (ret >= count) + goto err; + + nr_entries = stack_depot_fetch(handle, &entries); + ret += stack_trace_snprint(kbuf + ret, count - ret, entries, nr_entries, 0); + if (ret >= count) + goto err; + + if (page_owner->last_migrate_reason != -1) { + ret += snprintf(kbuf + ret, count - ret, + "Page has been migrated, last migrate reason: %s\n", + migrate_reason_names[page_owner->last_migrate_reason]); + if (ret >= count) + goto err; + } + + ret += snprintf(kbuf + ret, count - ret, "\n"); + if (ret >= count) + goto err; + + if (copy_to_user(buf, kbuf, ret)) + ret = -EFAULT; + + kfree(kbuf); + return ret; + +err: + kfree(kbuf); + return -ENOMEM; +} + +void __dump_page_owner(struct page *page) +{ + struct page_ext *page_ext = lookup_page_ext(page); + struct page_owner *page_owner; + depot_stack_handle_t handle; + unsigned long *entries; + unsigned int nr_entries; + gfp_t gfp_mask; + int mt; + + if (unlikely(!page_ext)) { + pr_alert("There is not page extension available.\n"); + return; + } + + page_owner = get_page_owner(page_ext); + gfp_mask = page_owner->gfp_mask; + mt = gfp_migratetype(gfp_mask); + + if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) { + pr_alert("page_owner info is not present (never set?)\n"); + return; + } + + if (test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags)) + pr_alert("page_owner tracks the page as allocated\n"); + else + pr_alert("page_owner tracks the page as freed\n"); + + pr_alert("page last allocated via order %u, migratetype %s, gfp_mask %#x(%pGg)\n", + page_owner->order, migratetype_names[mt], gfp_mask, &gfp_mask); + + handle = READ_ONCE(page_owner->handle); + if (!handle) { + pr_alert("page_owner allocation stack trace missing\n"); + } else { + nr_entries = stack_depot_fetch(handle, &entries); + stack_trace_print(entries, nr_entries, 0); + } + + handle = READ_ONCE(page_owner->free_handle); + if (!handle) { + pr_alert("page_owner free stack trace missing\n"); + } else { + nr_entries = stack_depot_fetch(handle, &entries); + pr_alert("page last free stack trace:\n"); + stack_trace_print(entries, nr_entries, 0); + } + + if (page_owner->last_migrate_reason != -1) + pr_alert("page has been migrated, last migrate reason: %s\n", + migrate_reason_names[page_owner->last_migrate_reason]); +} + +static ssize_t +read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos) +{ + unsigned long pfn; + struct page *page; + struct page_ext *page_ext; + struct page_owner *page_owner; + depot_stack_handle_t handle; + + if (!static_branch_unlikely(&page_owner_inited)) + return -EINVAL; + + page = NULL; + pfn = min_low_pfn + *ppos; + + /* Find a valid PFN or the start of a MAX_ORDER_NR_PAGES area */ + while (!pfn_valid(pfn) && (pfn & (MAX_ORDER_NR_PAGES - 1)) != 0) + pfn++; + + drain_all_pages(NULL); + + /* Find an allocated page */ + for (; pfn < max_pfn; pfn++) { + /* + * If the new page is in a new MAX_ORDER_NR_PAGES area, + * validate the area as existing, skip it if not + */ + if ((pfn & (MAX_ORDER_NR_PAGES - 1)) == 0 && !pfn_valid(pfn)) { + pfn += MAX_ORDER_NR_PAGES - 1; + continue; + } + + /* Check for holes within a MAX_ORDER area */ + if (!pfn_valid_within(pfn)) + continue; + + page = pfn_to_page(pfn); + if (PageBuddy(page)) { + unsigned long freepage_order = buddy_order_unsafe(page); + + if (freepage_order < MAX_ORDER) + pfn += (1UL << freepage_order) - 1; + continue; + } + + page_ext = lookup_page_ext(page); + if (unlikely(!page_ext)) + continue; + + /* + * Some pages could be missed by concurrent allocation or free, + * because we don't hold the zone lock. + */ + if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) + continue; + + /* + * Although we do have the info about past allocation of free + * pages, it's not relevant for current memory usage. + */ + if (!test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags)) + continue; + + page_owner = get_page_owner(page_ext); + + /* + * Don't print "tail" pages of high-order allocations as that + * would inflate the stats. + */ + if (!IS_ALIGNED(pfn, 1 << page_owner->order)) + continue; + + /* + * Access to page_ext->handle isn't synchronous so we should + * be careful to access it. + */ + handle = READ_ONCE(page_owner->handle); + if (!handle) + continue; + + /* Record the next PFN to read in the file offset */ + *ppos = (pfn - min_low_pfn) + 1; + + return print_page_owner(buf, count, pfn, page, + page_owner, handle); + } + + return 0; +} + +static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone) +{ + unsigned long pfn = zone->zone_start_pfn; + unsigned long end_pfn = zone_end_pfn(zone); + unsigned long count = 0; + + /* + * Walk the zone in pageblock_nr_pages steps. If a page block spans + * a zone boundary, it will be double counted between zones. This does + * not matter as the mixed block count will still be correct + */ + for (; pfn < end_pfn; ) { + unsigned long block_end_pfn; + + if (!pfn_valid(pfn)) { + pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES); + continue; + } + + block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages); + block_end_pfn = min(block_end_pfn, end_pfn); + + for (; pfn < block_end_pfn; pfn++) { + struct page *page; + struct page_ext *page_ext; + + if (!pfn_valid_within(pfn)) + continue; + + page = pfn_to_page(pfn); + + if (page_zone(page) != zone) + continue; + + /* + * To avoid having to grab zone->lock, be a little + * careful when reading buddy page order. The only + * danger is that we skip too much and potentially miss + * some early allocated pages, which is better than + * heavy lock contention. + */ + if (PageBuddy(page)) { + unsigned long order = buddy_order_unsafe(page); + + if (order > 0 && order < MAX_ORDER) + pfn += (1UL << order) - 1; + continue; + } + + if (PageReserved(page)) + continue; + + page_ext = lookup_page_ext(page); + if (unlikely(!page_ext)) + continue; + + /* Maybe overlapping zone */ + if (test_bit(PAGE_EXT_OWNER, &page_ext->flags)) + continue; + + /* Found early allocated page */ + __set_page_owner_handle(page, page_ext, early_handle, + 0, 0); + count++; + } + cond_resched(); + } + + pr_info("Node %d, zone %8s: page owner found early allocated %lu pages\n", + pgdat->node_id, zone->name, count); +} + +static void init_zones_in_node(pg_data_t *pgdat) +{ + struct zone *zone; + struct zone *node_zones = pgdat->node_zones; + + for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) { + if (!populated_zone(zone)) + continue; + + init_pages_in_zone(pgdat, zone); + } +} + +static void init_early_allocated_pages(void) +{ + pg_data_t *pgdat; + + for_each_online_pgdat(pgdat) + init_zones_in_node(pgdat); +} + +static const struct file_operations proc_page_owner_operations = { + .read = read_page_owner, +}; + +static int __init pageowner_init(void) +{ + if (!static_branch_unlikely(&page_owner_inited)) { + pr_info("page_owner is disabled\n"); + return 0; + } + + debugfs_create_file("page_owner", 0400, NULL, NULL, + &proc_page_owner_operations); + + return 0; +} +late_initcall(pageowner_init) diff --git a/mm/page_poison.c b/mm/page_poison.c new file mode 100644 index 000000000..ae0482cde --- /dev/null +++ b/mm/page_poison.c @@ -0,0 +1,144 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include + +static DEFINE_STATIC_KEY_FALSE_RO(want_page_poisoning); + +static int __init early_page_poison_param(char *buf) +{ + int ret; + bool tmp; + + ret = strtobool(buf, &tmp); + if (ret) + return ret; + + if (tmp) + static_branch_enable(&want_page_poisoning); + else + static_branch_disable(&want_page_poisoning); + + return 0; +} +early_param("page_poison", early_page_poison_param); + +/** + * page_poisoning_enabled - check if page poisoning is enabled + * + * Return true if page poisoning is enabled, or false if not. + */ +bool page_poisoning_enabled(void) +{ + /* + * Assumes that debug_pagealloc_enabled is set before + * memblock_free_all. + * Page poisoning is debug page alloc for some arches. If + * either of those options are enabled, enable poisoning. + */ + return (static_branch_unlikely(&want_page_poisoning) || + (!IS_ENABLED(CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC) && + debug_pagealloc_enabled())); +} +EXPORT_SYMBOL_GPL(page_poisoning_enabled); + +static void poison_page(struct page *page) +{ + void *addr = kmap_atomic(page); + + /* KASAN still think the page is in-use, so skip it. */ + kasan_disable_current(); + memset(addr, PAGE_POISON, PAGE_SIZE); + kasan_enable_current(); + kunmap_atomic(addr); +} + +static void poison_pages(struct page *page, int n) +{ + int i; + + for (i = 0; i < n; i++) + poison_page(page + i); +} + +static bool single_bit_flip(unsigned char a, unsigned char b) +{ + unsigned char error = a ^ b; + + return error && !(error & (error - 1)); +} + +static void check_poison_mem(unsigned char *mem, size_t bytes) +{ + static DEFINE_RATELIMIT_STATE(ratelimit, 5 * HZ, 10); + unsigned char *start; + unsigned char *end; + + if (IS_ENABLED(CONFIG_PAGE_POISONING_NO_SANITY)) + return; + + start = memchr_inv(mem, PAGE_POISON, bytes); + if (!start) + return; + + for (end = mem + bytes - 1; end > start; end--) { + if (*end != PAGE_POISON) + break; + } + + if (!__ratelimit(&ratelimit)) + return; + else if (start == end && single_bit_flip(*start, PAGE_POISON)) + pr_err("pagealloc: single bit error\n"); + else + pr_err("pagealloc: memory corruption\n"); + + print_hex_dump(KERN_ERR, "", DUMP_PREFIX_ADDRESS, 16, 1, start, + end - start + 1, 1); + dump_stack(); +} + +static void unpoison_page(struct page *page) +{ + void *addr; + + addr = kmap_atomic(page); + /* + * Page poisoning when enabled poisons each and every page + * that is freed to buddy. Thus no extra check is done to + * see if a page was poisoned. + */ + check_poison_mem(addr, PAGE_SIZE); + kunmap_atomic(addr); +} + +static void unpoison_pages(struct page *page, int n) +{ + int i; + + for (i = 0; i < n; i++) + unpoison_page(page + i); +} + +void kernel_poison_pages(struct page *page, int numpages, int enable) +{ + if (!page_poisoning_enabled()) + return; + + if (enable) + unpoison_pages(page, numpages); + else + poison_pages(page, numpages); +} + +#ifndef CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC +void __kernel_map_pages(struct page *page, int numpages, int enable) +{ + /* This function does nothing, all work is done via poison pages */ +} +#endif diff --git a/mm/page_reporting.c b/mm/page_reporting.c new file mode 100644 index 000000000..cd8e13d41 --- /dev/null +++ b/mm/page_reporting.c @@ -0,0 +1,364 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include + +#include "page_reporting.h" +#include "internal.h" + +#define PAGE_REPORTING_DELAY (2 * HZ) +static struct page_reporting_dev_info __rcu *pr_dev_info __read_mostly; + +enum { + PAGE_REPORTING_IDLE = 0, + PAGE_REPORTING_REQUESTED, + PAGE_REPORTING_ACTIVE +}; + +/* request page reporting */ +static void +__page_reporting_request(struct page_reporting_dev_info *prdev) +{ + unsigned int state; + + /* Check to see if we are in desired state */ + state = atomic_read(&prdev->state); + if (state == PAGE_REPORTING_REQUESTED) + return; + + /* + * If reporting is already active there is nothing we need to do. + * Test against 0 as that represents PAGE_REPORTING_IDLE. + */ + state = atomic_xchg(&prdev->state, PAGE_REPORTING_REQUESTED); + if (state != PAGE_REPORTING_IDLE) + return; + + /* + * Delay the start of work to allow a sizable queue to build. For + * now we are limiting this to running no more than once every + * couple of seconds. + */ + schedule_delayed_work(&prdev->work, PAGE_REPORTING_DELAY); +} + +/* notify prdev of free page reporting request */ +void __page_reporting_notify(void) +{ + struct page_reporting_dev_info *prdev; + + /* + * We use RCU to protect the pr_dev_info pointer. In almost all + * cases this should be present, however in the unlikely case of + * a shutdown this will be NULL and we should exit. + */ + rcu_read_lock(); + prdev = rcu_dereference(pr_dev_info); + if (likely(prdev)) + __page_reporting_request(prdev); + + rcu_read_unlock(); +} + +static void +page_reporting_drain(struct page_reporting_dev_info *prdev, + struct scatterlist *sgl, unsigned int nents, bool reported) +{ + struct scatterlist *sg = sgl; + + /* + * Drain the now reported pages back into their respective + * free lists/areas. We assume at least one page is populated. + */ + do { + struct page *page = sg_page(sg); + int mt = get_pageblock_migratetype(page); + unsigned int order = get_order(sg->length); + + __putback_isolated_page(page, order, mt); + + /* If the pages were not reported due to error skip flagging */ + if (!reported) + continue; + + /* + * If page was not comingled with another page we can + * consider the result to be "reported" since the page + * hasn't been modified, otherwise we will need to + * report on the new larger page when we make our way + * up to that higher order. + */ + if (PageBuddy(page) && buddy_order(page) == order) + __SetPageReported(page); + } while ((sg = sg_next(sg))); + + /* reinitialize scatterlist now that it is empty */ + sg_init_table(sgl, nents); +} + +/* + * The page reporting cycle consists of 4 stages, fill, report, drain, and + * idle. We will cycle through the first 3 stages until we cannot obtain a + * full scatterlist of pages, in that case we will switch to idle. + */ +static int +page_reporting_cycle(struct page_reporting_dev_info *prdev, struct zone *zone, + unsigned int order, unsigned int mt, + struct scatterlist *sgl, unsigned int *offset) +{ + struct free_area *area = &zone->free_area[order]; + struct list_head *list = &area->free_list[mt]; + unsigned int page_len = PAGE_SIZE << order; + struct page *page, *next; + long budget; + int err = 0; + + /* + * Perform early check, if free area is empty there is + * nothing to process so we can skip this free_list. + */ + if (list_empty(list)) + return err; + + spin_lock_irq(&zone->lock); + + /* + * Limit how many calls we will be making to the page reporting + * device for this list. By doing this we avoid processing any + * given list for too long. + * + * The current value used allows us enough calls to process over a + * sixteenth of the current list plus one additional call to handle + * any pages that may have already been present from the previous + * list processed. This should result in us reporting all pages on + * an idle system in about 30 seconds. + * + * The division here should be cheap since PAGE_REPORTING_CAPACITY + * should always be a power of 2. + */ + budget = DIV_ROUND_UP(area->nr_free, PAGE_REPORTING_CAPACITY * 16); + + /* loop through free list adding unreported pages to sg list */ + list_for_each_entry_safe(page, next, list, lru) { + /* We are going to skip over the reported pages. */ + if (PageReported(page)) + continue; + + /* + * If we fully consumed our budget then update our + * state to indicate that we are requesting additional + * processing and exit this list. + */ + if (budget < 0) { + atomic_set(&prdev->state, PAGE_REPORTING_REQUESTED); + next = page; + break; + } + + /* Attempt to pull page from list and place in scatterlist */ + if (*offset) { + if (!__isolate_free_page(page, order)) { + next = page; + break; + } + + /* Add page to scatter list */ + --(*offset); + sg_set_page(&sgl[*offset], page, page_len, 0); + + continue; + } + + /* + * Make the first non-reported page in the free list + * the new head of the free list before we release the + * zone lock. + */ + if (!list_is_first(&page->lru, list)) + list_rotate_to_front(&page->lru, list); + + /* release lock before waiting on report processing */ + spin_unlock_irq(&zone->lock); + + /* begin processing pages in local list */ + err = prdev->report(prdev, sgl, PAGE_REPORTING_CAPACITY); + + /* reset offset since the full list was reported */ + *offset = PAGE_REPORTING_CAPACITY; + + /* update budget to reflect call to report function */ + budget--; + + /* reacquire zone lock and resume processing */ + spin_lock_irq(&zone->lock); + + /* flush reported pages from the sg list */ + page_reporting_drain(prdev, sgl, PAGE_REPORTING_CAPACITY, !err); + + /* + * Reset next to first entry, the old next isn't valid + * since we dropped the lock to report the pages + */ + next = list_first_entry(list, struct page, lru); + + /* exit on error */ + if (err) + break; + } + + /* Rotate any leftover pages to the head of the freelist */ + if (&next->lru != list && !list_is_first(&next->lru, list)) + list_rotate_to_front(&next->lru, list); + + spin_unlock_irq(&zone->lock); + + return err; +} + +static int +page_reporting_process_zone(struct page_reporting_dev_info *prdev, + struct scatterlist *sgl, struct zone *zone) +{ + unsigned int order, mt, leftover, offset = PAGE_REPORTING_CAPACITY; + unsigned long watermark; + int err = 0; + + /* Generate minimum watermark to be able to guarantee progress */ + watermark = low_wmark_pages(zone) + + (PAGE_REPORTING_CAPACITY << PAGE_REPORTING_MIN_ORDER); + + /* + * Cancel request if insufficient free memory or if we failed + * to allocate page reporting statistics for the zone. + */ + if (!zone_watermark_ok(zone, 0, watermark, 0, ALLOC_CMA)) + return err; + + /* Process each free list starting from lowest order/mt */ + for (order = PAGE_REPORTING_MIN_ORDER; order < MAX_ORDER; order++) { + for (mt = 0; mt < MIGRATE_TYPES; mt++) { + /* We do not pull pages from the isolate free list */ + if (is_migrate_isolate(mt)) + continue; + + err = page_reporting_cycle(prdev, zone, order, mt, + sgl, &offset); + if (err) + return err; + } + } + + /* report the leftover pages before going idle */ + leftover = PAGE_REPORTING_CAPACITY - offset; + if (leftover) { + sgl = &sgl[offset]; + err = prdev->report(prdev, sgl, leftover); + + /* flush any remaining pages out from the last report */ + spin_lock_irq(&zone->lock); + page_reporting_drain(prdev, sgl, leftover, !err); + spin_unlock_irq(&zone->lock); + } + + return err; +} + +static void page_reporting_process(struct work_struct *work) +{ + struct delayed_work *d_work = to_delayed_work(work); + struct page_reporting_dev_info *prdev = + container_of(d_work, struct page_reporting_dev_info, work); + int err = 0, state = PAGE_REPORTING_ACTIVE; + struct scatterlist *sgl; + struct zone *zone; + + /* + * Change the state to "Active" so that we can track if there is + * anyone requests page reporting after we complete our pass. If + * the state is not altered by the end of the pass we will switch + * to idle and quit scheduling reporting runs. + */ + atomic_set(&prdev->state, state); + + /* allocate scatterlist to store pages being reported on */ + sgl = kmalloc_array(PAGE_REPORTING_CAPACITY, sizeof(*sgl), GFP_KERNEL); + if (!sgl) + goto err_out; + + sg_init_table(sgl, PAGE_REPORTING_CAPACITY); + + for_each_zone(zone) { + err = page_reporting_process_zone(prdev, sgl, zone); + if (err) + break; + } + + kfree(sgl); +err_out: + /* + * If the state has reverted back to requested then there may be + * additional pages to be processed. We will defer for 2s to allow + * more pages to accumulate. + */ + state = atomic_cmpxchg(&prdev->state, state, PAGE_REPORTING_IDLE); + if (state == PAGE_REPORTING_REQUESTED) + schedule_delayed_work(&prdev->work, PAGE_REPORTING_DELAY); +} + +static DEFINE_MUTEX(page_reporting_mutex); +DEFINE_STATIC_KEY_FALSE(page_reporting_enabled); + +int page_reporting_register(struct page_reporting_dev_info *prdev) +{ + int err = 0; + + mutex_lock(&page_reporting_mutex); + + /* nothing to do if already in use */ + if (rcu_access_pointer(pr_dev_info)) { + err = -EBUSY; + goto err_out; + } + + /* initialize state and work structures */ + atomic_set(&prdev->state, PAGE_REPORTING_IDLE); + INIT_DELAYED_WORK(&prdev->work, &page_reporting_process); + + /* Begin initial flush of zones */ + __page_reporting_request(prdev); + + /* Assign device to allow notifications */ + rcu_assign_pointer(pr_dev_info, prdev); + + /* enable page reporting notification */ + if (!static_key_enabled(&page_reporting_enabled)) { + static_branch_enable(&page_reporting_enabled); + pr_info("Free page reporting enabled\n"); + } +err_out: + mutex_unlock(&page_reporting_mutex); + + return err; +} +EXPORT_SYMBOL_GPL(page_reporting_register); + +void page_reporting_unregister(struct page_reporting_dev_info *prdev) +{ + mutex_lock(&page_reporting_mutex); + + if (rcu_access_pointer(pr_dev_info) == prdev) { + /* Disable page reporting notification */ + RCU_INIT_POINTER(pr_dev_info, NULL); + synchronize_rcu(); + + /* Flush any existing work, and lock it out */ + cancel_delayed_work_sync(&prdev->work); + } + + mutex_unlock(&page_reporting_mutex); +} +EXPORT_SYMBOL_GPL(page_reporting_unregister); diff --git a/mm/page_reporting.h b/mm/page_reporting.h new file mode 100644 index 000000000..2c385dd4d --- /dev/null +++ b/mm/page_reporting.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _MM_PAGE_REPORTING_H +#define _MM_PAGE_REPORTING_H + +#include +#include +#include +#include +#include +#include +#include + +#define PAGE_REPORTING_MIN_ORDER pageblock_order + +#ifdef CONFIG_PAGE_REPORTING +DECLARE_STATIC_KEY_FALSE(page_reporting_enabled); +void __page_reporting_notify(void); + +static inline bool page_reported(struct page *page) +{ + return static_branch_unlikely(&page_reporting_enabled) && + PageReported(page); +} + +/** + * page_reporting_notify_free - Free page notification to start page processing + * + * This function is meant to act as a screener for __page_reporting_notify + * which will determine if a give zone has crossed over the high-water mark + * that will justify us beginning page treatment. If we have crossed that + * threshold then it will start the process of pulling some pages and + * placing them in the batch list for treatment. + */ +static inline void page_reporting_notify_free(unsigned int order) +{ + /* Called from hot path in __free_one_page() */ + if (!static_branch_unlikely(&page_reporting_enabled)) + return; + + /* Determine if we have crossed reporting threshold */ + if (order < PAGE_REPORTING_MIN_ORDER) + return; + + /* This will add a few cycles, but should be called infrequently */ + __page_reporting_notify(); +} +#else /* CONFIG_PAGE_REPORTING */ +#define page_reported(_page) false + +static inline void page_reporting_notify_free(unsigned int order) +{ +} +#endif /* CONFIG_PAGE_REPORTING */ +#endif /*_MM_PAGE_REPORTING_H */ diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c new file mode 100644 index 000000000..610ebbee7 --- /dev/null +++ b/mm/page_vma_mapped.c @@ -0,0 +1,318 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include + +#include "internal.h" + +static inline bool not_found(struct page_vma_mapped_walk *pvmw) +{ + page_vma_mapped_walk_done(pvmw); + return false; +} + +static bool map_pte(struct page_vma_mapped_walk *pvmw) +{ + pvmw->pte = pte_offset_map(pvmw->pmd, pvmw->address); + if (!(pvmw->flags & PVMW_SYNC)) { + if (pvmw->flags & PVMW_MIGRATION) { + if (!is_swap_pte(*pvmw->pte)) + return false; + } else { + /* + * We get here when we are trying to unmap a private + * device page from the process address space. Such + * page is not CPU accessible and thus is mapped as + * a special swap entry, nonetheless it still does + * count as a valid regular mapping for the page (and + * is accounted as such in page maps count). + * + * So handle this special case as if it was a normal + * page mapping ie lock CPU page table and returns + * true. + * + * For more details on device private memory see HMM + * (include/linux/hmm.h or mm/hmm.c). + */ + if (is_swap_pte(*pvmw->pte)) { + swp_entry_t entry; + + /* Handle un-addressable ZONE_DEVICE memory */ + entry = pte_to_swp_entry(*pvmw->pte); + if (!is_device_private_entry(entry)) + return false; + } else if (!pte_present(*pvmw->pte)) + return false; + } + } + pvmw->ptl = pte_lockptr(pvmw->vma->vm_mm, pvmw->pmd); + spin_lock(pvmw->ptl); + return true; +} + +static inline bool pfn_is_match(struct page *page, unsigned long pfn) +{ + unsigned long page_pfn = page_to_pfn(page); + + /* normal page and hugetlbfs page */ + if (!PageTransCompound(page) || PageHuge(page)) + return page_pfn == pfn; + + /* THP can be referenced by any subpage */ + return pfn >= page_pfn && pfn - page_pfn < thp_nr_pages(page); +} + +/** + * check_pte - check if @pvmw->page is mapped at the @pvmw->pte + * + * page_vma_mapped_walk() found a place where @pvmw->page is *potentially* + * mapped. check_pte() has to validate this. + * + * @pvmw->pte may point to empty PTE, swap PTE or PTE pointing to arbitrary + * page. + * + * If PVMW_MIGRATION flag is set, returns true if @pvmw->pte contains migration + * entry that points to @pvmw->page or any subpage in case of THP. + * + * If PVMW_MIGRATION flag is not set, returns true if @pvmw->pte points to + * @pvmw->page or any subpage in case of THP. + * + * Otherwise, return false. + * + */ +static bool check_pte(struct page_vma_mapped_walk *pvmw) +{ + unsigned long pfn; + + if (pvmw->flags & PVMW_MIGRATION) { + swp_entry_t entry; + if (!is_swap_pte(*pvmw->pte)) + return false; + entry = pte_to_swp_entry(*pvmw->pte); + + if (!is_migration_entry(entry)) + return false; + + pfn = migration_entry_to_pfn(entry); + } else if (is_swap_pte(*pvmw->pte)) { + swp_entry_t entry; + + /* Handle un-addressable ZONE_DEVICE memory */ + entry = pte_to_swp_entry(*pvmw->pte); + if (!is_device_private_entry(entry)) + return false; + + pfn = device_private_entry_to_pfn(entry); + } else { + if (!pte_present(*pvmw->pte)) + return false; + + pfn = pte_pfn(*pvmw->pte); + } + + return pfn_is_match(pvmw->page, pfn); +} + +static void step_forward(struct page_vma_mapped_walk *pvmw, unsigned long size) +{ + pvmw->address = (pvmw->address + size) & ~(size - 1); + if (!pvmw->address) + pvmw->address = ULONG_MAX; +} + +/** + * page_vma_mapped_walk - check if @pvmw->page is mapped in @pvmw->vma at + * @pvmw->address + * @pvmw: pointer to struct page_vma_mapped_walk. page, vma, address and flags + * must be set. pmd, pte and ptl must be NULL. + * + * Returns true if the page is mapped in the vma. @pvmw->pmd and @pvmw->pte point + * to relevant page table entries. @pvmw->ptl is locked. @pvmw->address is + * adjusted if needed (for PTE-mapped THPs). + * + * If @pvmw->pmd is set but @pvmw->pte is not, you have found PMD-mapped page + * (usually THP). For PTE-mapped THP, you should run page_vma_mapped_walk() in + * a loop to find all PTEs that map the THP. + * + * For HugeTLB pages, @pvmw->pte is set to the relevant page table entry + * regardless of which page table level the page is mapped at. @pvmw->pmd is + * NULL. + * + * Retruns false if there are no more page table entries for the page in + * the vma. @pvmw->ptl is unlocked and @pvmw->pte is unmapped. + * + * If you need to stop the walk before page_vma_mapped_walk() returned false, + * use page_vma_mapped_walk_done(). It will do the housekeeping. + */ +bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) +{ + struct mm_struct *mm = pvmw->vma->vm_mm; + struct page *page = pvmw->page; + unsigned long end; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t pmde; + + /* The only possible pmd mapping has been handled on last iteration */ + if (pvmw->pmd && !pvmw->pte) + return not_found(pvmw); + + if (unlikely(PageHuge(page))) { + /* The only possible mapping was handled on last iteration */ + if (pvmw->pte) + return not_found(pvmw); + + /* when pud is not present, pte will be NULL */ + pvmw->pte = huge_pte_offset(mm, pvmw->address, page_size(page)); + if (!pvmw->pte) + return false; + + pvmw->ptl = huge_pte_lockptr(page_hstate(page), mm, pvmw->pte); + spin_lock(pvmw->ptl); + if (!check_pte(pvmw)) + return not_found(pvmw); + return true; + } + + /* + * Seek to next pte only makes sense for THP. + * But more important than that optimization, is to filter out + * any PageKsm page: whose page->index misleads vma_address() + * and vma_address_end() to disaster. + */ + end = PageTransCompound(page) ? + vma_address_end(page, pvmw->vma) : + pvmw->address + PAGE_SIZE; + if (pvmw->pte) + goto next_pte; +restart: + do { + pgd = pgd_offset(mm, pvmw->address); + if (!pgd_present(*pgd)) { + step_forward(pvmw, PGDIR_SIZE); + continue; + } + p4d = p4d_offset(pgd, pvmw->address); + if (!p4d_present(*p4d)) { + step_forward(pvmw, P4D_SIZE); + continue; + } + pud = pud_offset(p4d, pvmw->address); + if (!pud_present(*pud)) { + step_forward(pvmw, PUD_SIZE); + continue; + } + + pvmw->pmd = pmd_offset(pud, pvmw->address); + /* + * Make sure the pmd value isn't cached in a register by the + * compiler and used as a stale value after we've observed a + * subsequent update. + */ + pmde = READ_ONCE(*pvmw->pmd); + + if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) { + pvmw->ptl = pmd_lock(mm, pvmw->pmd); + pmde = *pvmw->pmd; + if (likely(pmd_trans_huge(pmde))) { + if (pvmw->flags & PVMW_MIGRATION) + return not_found(pvmw); + if (pmd_page(pmde) != page) + return not_found(pvmw); + return true; + } + if (!pmd_present(pmde)) { + swp_entry_t entry; + + if (!thp_migration_supported() || + !(pvmw->flags & PVMW_MIGRATION)) + return not_found(pvmw); + entry = pmd_to_swp_entry(pmde); + if (!is_migration_entry(entry) || + migration_entry_to_page(entry) != page) + return not_found(pvmw); + return true; + } + /* THP pmd was split under us: handle on pte level */ + spin_unlock(pvmw->ptl); + pvmw->ptl = NULL; + } else if (!pmd_present(pmde)) { + /* + * If PVMW_SYNC, take and drop THP pmd lock so that we + * cannot return prematurely, while zap_huge_pmd() has + * cleared *pmd but not decremented compound_mapcount(). + */ + if ((pvmw->flags & PVMW_SYNC) && + PageTransCompound(page)) { + spinlock_t *ptl = pmd_lock(mm, pvmw->pmd); + + spin_unlock(ptl); + } + step_forward(pvmw, PMD_SIZE); + continue; + } + if (!map_pte(pvmw)) + goto next_pte; +this_pte: + if (check_pte(pvmw)) + return true; +next_pte: + do { + pvmw->address += PAGE_SIZE; + if (pvmw->address >= end) + return not_found(pvmw); + /* Did we cross page table boundary? */ + if ((pvmw->address & (PMD_SIZE - PAGE_SIZE)) == 0) { + if (pvmw->ptl) { + spin_unlock(pvmw->ptl); + pvmw->ptl = NULL; + } + pte_unmap(pvmw->pte); + pvmw->pte = NULL; + goto restart; + } + pvmw->pte++; + if ((pvmw->flags & PVMW_SYNC) && !pvmw->ptl) { + pvmw->ptl = pte_lockptr(mm, pvmw->pmd); + spin_lock(pvmw->ptl); + } + } while (pte_none(*pvmw->pte)); + + if (!pvmw->ptl) { + pvmw->ptl = pte_lockptr(mm, pvmw->pmd); + spin_lock(pvmw->ptl); + } + goto this_pte; + } while (pvmw->address < end); + + return false; +} + +/** + * page_mapped_in_vma - check whether a page is really mapped in a VMA + * @page: the page to test + * @vma: the VMA to test + * + * Returns 1 if the page is mapped into the page tables of the VMA, 0 + * if the page is not mapped into the page tables of this VMA. Only + * valid for normal file or anonymous VMAs. + */ +int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma) +{ + struct page_vma_mapped_walk pvmw = { + .page = page, + .vma = vma, + .flags = PVMW_SYNC, + }; + + pvmw.address = vma_address(page, vma); + if (pvmw.address == -EFAULT) + return 0; + if (!page_vma_mapped_walk(&pvmw)) + return 0; + page_vma_mapped_walk_done(&pvmw); + return 1; +} diff --git a/mm/pagewalk.c b/mm/pagewalk.c new file mode 100644 index 000000000..371ec21a1 --- /dev/null +++ b/mm/pagewalk.c @@ -0,0 +1,563 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include + +/* + * We want to know the real level where a entry is located ignoring any + * folding of levels which may be happening. For example if p4d is folded then + * a missing entry found at level 1 (p4d) is actually at level 0 (pgd). + */ +static int real_depth(int depth) +{ + if (depth == 3 && PTRS_PER_PMD == 1) + depth = 2; + if (depth == 2 && PTRS_PER_PUD == 1) + depth = 1; + if (depth == 1 && PTRS_PER_P4D == 1) + depth = 0; + return depth; +} + +static int walk_pte_range_inner(pte_t *pte, unsigned long addr, + unsigned long end, struct mm_walk *walk) +{ + const struct mm_walk_ops *ops = walk->ops; + int err = 0; + + for (;;) { + err = ops->pte_entry(pte, addr, addr + PAGE_SIZE, walk); + if (err) + break; + if (addr >= end - PAGE_SIZE) + break; + addr += PAGE_SIZE; + pte++; + } + return err; +} + +static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + pte_t *pte; + int err = 0; + spinlock_t *ptl; + + if (walk->no_vma) { + pte = pte_offset_map(pmd, addr); + err = walk_pte_range_inner(pte, addr, end, walk); + pte_unmap(pte); + } else { + pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); + err = walk_pte_range_inner(pte, addr, end, walk); + pte_unmap_unlock(pte, ptl); + } + + return err; +} + +static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + pmd_t *pmd; + unsigned long next; + const struct mm_walk_ops *ops = walk->ops; + int err = 0; + int depth = real_depth(3); + + pmd = pmd_offset(pud, addr); + do { +again: + next = pmd_addr_end(addr, end); + if (pmd_none(*pmd)) { + if (ops->pte_hole) + err = ops->pte_hole(addr, next, depth, walk); + if (err) + break; + continue; + } + + walk->action = ACTION_SUBTREE; + + /* + * This implies that each ->pmd_entry() handler + * needs to know about pmd_trans_huge() pmds + */ + if (ops->pmd_entry) + err = ops->pmd_entry(pmd, addr, next, walk); + if (err) + break; + + if (walk->action == ACTION_AGAIN) + goto again; + + /* + * Check this here so we only break down trans_huge + * pages when we _need_ to + */ + if ((!walk->vma && (pmd_leaf(*pmd) || !pmd_present(*pmd))) || + walk->action == ACTION_CONTINUE || + !(ops->pte_entry)) + continue; + + if (walk->vma) { + split_huge_pmd(walk->vma, pmd, addr); + if (pmd_trans_unstable(pmd)) + goto again; + } + + err = walk_pte_range(pmd, addr, next, walk); + if (err) + break; + } while (pmd++, addr = next, addr != end); + + return err; +} + +static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + pud_t *pud; + unsigned long next; + const struct mm_walk_ops *ops = walk->ops; + int err = 0; + int depth = real_depth(2); + + pud = pud_offset(p4d, addr); + do { + again: + next = pud_addr_end(addr, end); + if (pud_none(*pud)) { + if (ops->pte_hole) + err = ops->pte_hole(addr, next, depth, walk); + if (err) + break; + continue; + } + + walk->action = ACTION_SUBTREE; + + if (ops->pud_entry) + err = ops->pud_entry(pud, addr, next, walk); + if (err) + break; + + if (walk->action == ACTION_AGAIN) + goto again; + + if ((!walk->vma && (pud_leaf(*pud) || !pud_present(*pud))) || + walk->action == ACTION_CONTINUE || + !(ops->pmd_entry || ops->pte_entry)) + continue; + + if (walk->vma) + split_huge_pud(walk->vma, pud, addr); + if (pud_none(*pud)) + goto again; + + err = walk_pmd_range(pud, addr, next, walk); + if (err) + break; + } while (pud++, addr = next, addr != end); + + return err; +} + +static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + p4d_t *p4d; + unsigned long next; + const struct mm_walk_ops *ops = walk->ops; + int err = 0; + int depth = real_depth(1); + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(p4d)) { + if (ops->pte_hole) + err = ops->pte_hole(addr, next, depth, walk); + if (err) + break; + continue; + } + if (ops->p4d_entry) { + err = ops->p4d_entry(p4d, addr, next, walk); + if (err) + break; + } + if (ops->pud_entry || ops->pmd_entry || ops->pte_entry) + err = walk_pud_range(p4d, addr, next, walk); + if (err) + break; + } while (p4d++, addr = next, addr != end); + + return err; +} + +static int walk_pgd_range(unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + pgd_t *pgd; + unsigned long next; + const struct mm_walk_ops *ops = walk->ops; + int err = 0; + + if (walk->pgd) + pgd = walk->pgd + pgd_index(addr); + else + pgd = pgd_offset(walk->mm, addr); + do { + next = pgd_addr_end(addr, end); + if (pgd_none_or_clear_bad(pgd)) { + if (ops->pte_hole) + err = ops->pte_hole(addr, next, 0, walk); + if (err) + break; + continue; + } + if (ops->pgd_entry) { + err = ops->pgd_entry(pgd, addr, next, walk); + if (err) + break; + } + if (ops->p4d_entry || ops->pud_entry || ops->pmd_entry || + ops->pte_entry) + err = walk_p4d_range(pgd, addr, next, walk); + if (err) + break; + } while (pgd++, addr = next, addr != end); + + return err; +} + +#ifdef CONFIG_HUGETLB_PAGE +static unsigned long hugetlb_entry_end(struct hstate *h, unsigned long addr, + unsigned long end) +{ + unsigned long boundary = (addr & huge_page_mask(h)) + huge_page_size(h); + return boundary < end ? boundary : end; +} + +static int walk_hugetlb_range(unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + struct vm_area_struct *vma = walk->vma; + struct hstate *h = hstate_vma(vma); + unsigned long next; + unsigned long hmask = huge_page_mask(h); + unsigned long sz = huge_page_size(h); + pte_t *pte; + const struct mm_walk_ops *ops = walk->ops; + int err = 0; + + do { + next = hugetlb_entry_end(h, addr, end); + pte = huge_pte_offset(walk->mm, addr & hmask, sz); + + if (pte) + err = ops->hugetlb_entry(pte, hmask, addr, next, walk); + else if (ops->pte_hole) + err = ops->pte_hole(addr, next, -1, walk); + + if (err) + break; + } while (addr = next, addr != end); + + return err; +} + +#else /* CONFIG_HUGETLB_PAGE */ +static int walk_hugetlb_range(unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + return 0; +} + +#endif /* CONFIG_HUGETLB_PAGE */ + +/* + * Decide whether we really walk over the current vma on [@start, @end) + * or skip it via the returned value. Return 0 if we do walk over the + * current vma, and return 1 if we skip the vma. Negative values means + * error, where we abort the current walk. + */ +static int walk_page_test(unsigned long start, unsigned long end, + struct mm_walk *walk) +{ + struct vm_area_struct *vma = walk->vma; + const struct mm_walk_ops *ops = walk->ops; + + if (ops->test_walk) + return ops->test_walk(start, end, walk); + + /* + * vma(VM_PFNMAP) doesn't have any valid struct pages behind VM_PFNMAP + * range, so we don't walk over it as we do for normal vmas. However, + * Some callers are interested in handling hole range and they don't + * want to just ignore any single address range. Such users certainly + * define their ->pte_hole() callbacks, so let's delegate them to handle + * vma(VM_PFNMAP). + */ + if (vma->vm_flags & VM_PFNMAP) { + int err = 1; + if (ops->pte_hole) + err = ops->pte_hole(start, end, -1, walk); + return err ? err : 1; + } + return 0; +} + +static int __walk_page_range(unsigned long start, unsigned long end, + struct mm_walk *walk) +{ + int err = 0; + struct vm_area_struct *vma = walk->vma; + const struct mm_walk_ops *ops = walk->ops; + + if (ops->pre_vma) { + err = ops->pre_vma(start, end, walk); + if (err) + return err; + } + + if (is_vm_hugetlb_page(vma)) { + if (ops->hugetlb_entry) + err = walk_hugetlb_range(start, end, walk); + } else + err = walk_pgd_range(start, end, walk); + + if (ops->post_vma) + ops->post_vma(walk); + + return err; +} + +/** + * walk_page_range - walk page table with caller specific callbacks + * @mm: mm_struct representing the target process of page table walk + * @start: start address of the virtual address range + * @end: end address of the virtual address range + * @ops: operation to call during the walk + * @private: private data for callbacks' usage + * + * Recursively walk the page table tree of the process represented by @mm + * within the virtual address range [@start, @end). During walking, we can do + * some caller-specific works for each entry, by setting up pmd_entry(), + * pte_entry(), and/or hugetlb_entry(). If you don't set up for some of these + * callbacks, the associated entries/pages are just ignored. + * The return values of these callbacks are commonly defined like below: + * + * - 0 : succeeded to handle the current entry, and if you don't reach the + * end address yet, continue to walk. + * - >0 : succeeded to handle the current entry, and return to the caller + * with caller specific value. + * - <0 : failed to handle the current entry, and return to the caller + * with error code. + * + * Before starting to walk page table, some callers want to check whether + * they really want to walk over the current vma, typically by checking + * its vm_flags. walk_page_test() and @ops->test_walk() are used for this + * purpose. + * + * If operations need to be staged before and committed after a vma is walked, + * there are two callbacks, pre_vma() and post_vma(). Note that post_vma(), + * since it is intended to handle commit-type operations, can't return any + * errors. + * + * struct mm_walk keeps current values of some common data like vma and pmd, + * which are useful for the access from callbacks. If you want to pass some + * caller-specific data to callbacks, @private should be helpful. + * + * Locking: + * Callers of walk_page_range() and walk_page_vma() should hold @mm->mmap_lock, + * because these function traverse vma list and/or access to vma's data. + */ +int walk_page_range(struct mm_struct *mm, unsigned long start, + unsigned long end, const struct mm_walk_ops *ops, + void *private) +{ + int err = 0; + unsigned long next; + struct vm_area_struct *vma; + struct mm_walk walk = { + .ops = ops, + .mm = mm, + .private = private, + }; + + if (start >= end) + return -EINVAL; + + if (!walk.mm) + return -EINVAL; + + mmap_assert_locked(walk.mm); + + vma = find_vma(walk.mm, start); + do { + if (!vma) { /* after the last vma */ + walk.vma = NULL; + next = end; + if (ops->pte_hole) + err = ops->pte_hole(start, next, -1, &walk); + } else if (start < vma->vm_start) { /* outside vma */ + walk.vma = NULL; + next = min(end, vma->vm_start); + if (ops->pte_hole) + err = ops->pte_hole(start, next, -1, &walk); + } else { /* inside vma */ + walk.vma = vma; + next = min(end, vma->vm_end); + vma = vma->vm_next; + + err = walk_page_test(start, next, &walk); + if (err > 0) { + /* + * positive return values are purely for + * controlling the pagewalk, so should never + * be passed to the callers. + */ + err = 0; + continue; + } + if (err < 0) + break; + err = __walk_page_range(start, next, &walk); + } + if (err) + break; + } while (start = next, start < end); + return err; +} + +/* + * Similar to walk_page_range() but can walk any page tables even if they are + * not backed by VMAs. Because 'unusual' entries may be walked this function + * will also not lock the PTEs for the pte_entry() callback. This is useful for + * walking the kernel pages tables or page tables for firmware. + */ +int walk_page_range_novma(struct mm_struct *mm, unsigned long start, + unsigned long end, const struct mm_walk_ops *ops, + pgd_t *pgd, + void *private) +{ + struct mm_walk walk = { + .ops = ops, + .mm = mm, + .pgd = pgd, + .private = private, + .no_vma = true + }; + + if (start >= end || !walk.mm) + return -EINVAL; + + mmap_assert_write_locked(walk.mm); + + return walk_pgd_range(start, end, &walk); +} + +int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops, + void *private) +{ + struct mm_walk walk = { + .ops = ops, + .mm = vma->vm_mm, + .vma = vma, + .private = private, + }; + int err; + + if (!walk.mm) + return -EINVAL; + + mmap_assert_locked(walk.mm); + + err = walk_page_test(vma->vm_start, vma->vm_end, &walk); + if (err > 0) + return 0; + if (err < 0) + return err; + return __walk_page_range(vma->vm_start, vma->vm_end, &walk); +} + +/** + * walk_page_mapping - walk all memory areas mapped into a struct address_space. + * @mapping: Pointer to the struct address_space + * @first_index: First page offset in the address_space + * @nr: Number of incremental page offsets to cover + * @ops: operation to call during the walk + * @private: private data for callbacks' usage + * + * This function walks all memory areas mapped into a struct address_space. + * The walk is limited to only the given page-size index range, but if + * the index boundaries cross a huge page-table entry, that entry will be + * included. + * + * Also see walk_page_range() for additional information. + * + * Locking: + * This function can't require that the struct mm_struct::mmap_lock is held, + * since @mapping may be mapped by multiple processes. Instead + * @mapping->i_mmap_rwsem must be held. This might have implications in the + * callbacks, and it's up tho the caller to ensure that the + * struct mm_struct::mmap_lock is not needed. + * + * Also this means that a caller can't rely on the struct + * vm_area_struct::vm_flags to be constant across a call, + * except for immutable flags. Callers requiring this shouldn't use + * this function. + * + * Return: 0 on success, negative error code on failure, positive number on + * caller defined premature termination. + */ +int walk_page_mapping(struct address_space *mapping, pgoff_t first_index, + pgoff_t nr, const struct mm_walk_ops *ops, + void *private) +{ + struct mm_walk walk = { + .ops = ops, + .private = private, + }; + struct vm_area_struct *vma; + pgoff_t vba, vea, cba, cea; + unsigned long start_addr, end_addr; + int err = 0; + + lockdep_assert_held(&mapping->i_mmap_rwsem); + vma_interval_tree_foreach(vma, &mapping->i_mmap, first_index, + first_index + nr - 1) { + /* Clip to the vma */ + vba = vma->vm_pgoff; + vea = vba + vma_pages(vma); + cba = first_index; + cba = max(cba, vba); + cea = first_index + nr; + cea = min(cea, vea); + + start_addr = ((cba - vba) << PAGE_SHIFT) + vma->vm_start; + end_addr = ((cea - vba) << PAGE_SHIFT) + vma->vm_start; + if (start_addr >= end_addr) + continue; + + walk.vma = vma; + walk.mm = vma->vm_mm; + + err = walk_page_test(vma->vm_start, vma->vm_end, &walk); + if (err > 0) { + err = 0; + break; + } else if (err < 0) + break; + + err = __walk_page_range(start_addr, end_addr, &walk); + if (err) + break; + } + + return err; +} diff --git a/mm/percpu-internal.h b/mm/percpu-internal.h new file mode 100644 index 000000000..095d7eaa0 --- /dev/null +++ b/mm/percpu-internal.h @@ -0,0 +1,285 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _MM_PERCPU_INTERNAL_H +#define _MM_PERCPU_INTERNAL_H + +#include +#include + +/* + * There are two chunk types: root and memcg-aware. + * Chunks of each type have separate slots list. + * + * Memcg-aware chunks have an attached vector of obj_cgroup pointers, which is + * used to store memcg membership data of a percpu object. Obj_cgroups are + * ref-counted pointers to a memory cgroup with an ability to switch dynamically + * to the parent memory cgroup. This allows to reclaim a deleted memory cgroup + * without reclaiming of all outstanding objects, which hold a reference at it. + */ +enum pcpu_chunk_type { + PCPU_CHUNK_ROOT, +#ifdef CONFIG_MEMCG_KMEM + PCPU_CHUNK_MEMCG, +#endif + PCPU_NR_CHUNK_TYPES, + PCPU_FAIL_ALLOC = PCPU_NR_CHUNK_TYPES +}; + +/* + * pcpu_block_md is the metadata block struct. + * Each chunk's bitmap is split into a number of full blocks. + * All units are in terms of bits. + * + * The scan hint is the largest known contiguous area before the contig hint. + * It is not necessarily the actual largest contig hint though. There is an + * invariant that the scan_hint_start > contig_hint_start iff + * scan_hint == contig_hint. This is necessary because when scanning forward, + * we don't know if a new contig hint would be better than the current one. + */ +struct pcpu_block_md { + int scan_hint; /* scan hint for block */ + int scan_hint_start; /* block relative starting + position of the scan hint */ + int contig_hint; /* contig hint for block */ + int contig_hint_start; /* block relative starting + position of the contig hint */ + int left_free; /* size of free space along + the left side of the block */ + int right_free; /* size of free space along + the right side of the block */ + int first_free; /* block position of first free */ + int nr_bits; /* total bits responsible for */ +}; + +struct pcpu_chunk { +#ifdef CONFIG_PERCPU_STATS + int nr_alloc; /* # of allocations */ + size_t max_alloc_size; /* largest allocation size */ +#endif + + struct list_head list; /* linked to pcpu_slot lists */ + int free_bytes; /* free bytes in the chunk */ + struct pcpu_block_md chunk_md; + void *base_addr; /* base address of this chunk */ + + unsigned long *alloc_map; /* allocation map */ + unsigned long *bound_map; /* boundary map */ + struct pcpu_block_md *md_blocks; /* metadata blocks */ + + void *data; /* chunk data */ + bool immutable; /* no [de]population allowed */ + int start_offset; /* the overlap with the previous + region to have a page aligned + base_addr */ + int end_offset; /* additional area required to + have the region end page + aligned */ +#ifdef CONFIG_MEMCG_KMEM + struct obj_cgroup **obj_cgroups; /* vector of object cgroups */ +#endif + + int nr_pages; /* # of pages served by this chunk */ + int nr_populated; /* # of populated pages */ + int nr_empty_pop_pages; /* # of empty populated pages */ + unsigned long populated[]; /* populated bitmap */ +}; + +extern spinlock_t pcpu_lock; + +extern struct list_head *pcpu_chunk_lists; +extern int pcpu_nr_slots; +extern int pcpu_nr_empty_pop_pages[]; + +extern struct pcpu_chunk *pcpu_first_chunk; +extern struct pcpu_chunk *pcpu_reserved_chunk; + +/** + * pcpu_chunk_nr_blocks - converts nr_pages to # of md_blocks + * @chunk: chunk of interest + * + * This conversion is from the number of physical pages that the chunk + * serves to the number of bitmap blocks used. + */ +static inline int pcpu_chunk_nr_blocks(struct pcpu_chunk *chunk) +{ + return chunk->nr_pages * PAGE_SIZE / PCPU_BITMAP_BLOCK_SIZE; +} + +/** + * pcpu_nr_pages_to_map_bits - converts the pages to size of bitmap + * @pages: number of physical pages + * + * This conversion is from physical pages to the number of bits + * required in the bitmap. + */ +static inline int pcpu_nr_pages_to_map_bits(int pages) +{ + return pages * PAGE_SIZE / PCPU_MIN_ALLOC_SIZE; +} + +/** + * pcpu_chunk_map_bits - helper to convert nr_pages to size of bitmap + * @chunk: chunk of interest + * + * This conversion is from the number of physical pages that the chunk + * serves to the number of bits in the bitmap. + */ +static inline int pcpu_chunk_map_bits(struct pcpu_chunk *chunk) +{ + return pcpu_nr_pages_to_map_bits(chunk->nr_pages); +} + +#ifdef CONFIG_MEMCG_KMEM +static inline enum pcpu_chunk_type pcpu_chunk_type(struct pcpu_chunk *chunk) +{ + if (chunk->obj_cgroups) + return PCPU_CHUNK_MEMCG; + return PCPU_CHUNK_ROOT; +} + +static inline bool pcpu_is_memcg_chunk(enum pcpu_chunk_type chunk_type) +{ + return chunk_type == PCPU_CHUNK_MEMCG; +} + +#else +static inline enum pcpu_chunk_type pcpu_chunk_type(struct pcpu_chunk *chunk) +{ + return PCPU_CHUNK_ROOT; +} + +static inline bool pcpu_is_memcg_chunk(enum pcpu_chunk_type chunk_type) +{ + return false; +} +#endif + +static inline struct list_head *pcpu_chunk_list(enum pcpu_chunk_type chunk_type) +{ + return &pcpu_chunk_lists[pcpu_nr_slots * + pcpu_is_memcg_chunk(chunk_type)]; +} + +#ifdef CONFIG_PERCPU_STATS + +#include + +struct percpu_stats { + u64 nr_alloc; /* lifetime # of allocations */ + u64 nr_dealloc; /* lifetime # of deallocations */ + u64 nr_cur_alloc; /* current # of allocations */ + u64 nr_max_alloc; /* max # of live allocations */ + u32 nr_chunks; /* current # of live chunks */ + u32 nr_max_chunks; /* max # of live chunks */ + size_t min_alloc_size; /* min allocaiton size */ + size_t max_alloc_size; /* max allocation size */ +}; + +extern struct percpu_stats pcpu_stats; +extern struct pcpu_alloc_info pcpu_stats_ai; + +/* + * For debug purposes. We don't care about the flexible array. + */ +static inline void pcpu_stats_save_ai(const struct pcpu_alloc_info *ai) +{ + memcpy(&pcpu_stats_ai, ai, sizeof(struct pcpu_alloc_info)); + + /* initialize min_alloc_size to unit_size */ + pcpu_stats.min_alloc_size = pcpu_stats_ai.unit_size; +} + +/* + * pcpu_stats_area_alloc - increment area allocation stats + * @chunk: the location of the area being allocated + * @size: size of area to allocate in bytes + * + * CONTEXT: + * pcpu_lock. + */ +static inline void pcpu_stats_area_alloc(struct pcpu_chunk *chunk, size_t size) +{ + lockdep_assert_held(&pcpu_lock); + + pcpu_stats.nr_alloc++; + pcpu_stats.nr_cur_alloc++; + pcpu_stats.nr_max_alloc = + max(pcpu_stats.nr_max_alloc, pcpu_stats.nr_cur_alloc); + pcpu_stats.min_alloc_size = + min(pcpu_stats.min_alloc_size, size); + pcpu_stats.max_alloc_size = + max(pcpu_stats.max_alloc_size, size); + + chunk->nr_alloc++; + chunk->max_alloc_size = max(chunk->max_alloc_size, size); +} + +/* + * pcpu_stats_area_dealloc - decrement allocation stats + * @chunk: the location of the area being deallocated + * + * CONTEXT: + * pcpu_lock. + */ +static inline void pcpu_stats_area_dealloc(struct pcpu_chunk *chunk) +{ + lockdep_assert_held(&pcpu_lock); + + pcpu_stats.nr_dealloc++; + pcpu_stats.nr_cur_alloc--; + + chunk->nr_alloc--; +} + +/* + * pcpu_stats_chunk_alloc - increment chunk stats + */ +static inline void pcpu_stats_chunk_alloc(void) +{ + unsigned long flags; + spin_lock_irqsave(&pcpu_lock, flags); + + pcpu_stats.nr_chunks++; + pcpu_stats.nr_max_chunks = + max(pcpu_stats.nr_max_chunks, pcpu_stats.nr_chunks); + + spin_unlock_irqrestore(&pcpu_lock, flags); +} + +/* + * pcpu_stats_chunk_dealloc - decrement chunk stats + */ +static inline void pcpu_stats_chunk_dealloc(void) +{ + unsigned long flags; + spin_lock_irqsave(&pcpu_lock, flags); + + pcpu_stats.nr_chunks--; + + spin_unlock_irqrestore(&pcpu_lock, flags); +} + +#else + +static inline void pcpu_stats_save_ai(const struct pcpu_alloc_info *ai) +{ +} + +static inline void pcpu_stats_area_alloc(struct pcpu_chunk *chunk, size_t size) +{ +} + +static inline void pcpu_stats_area_dealloc(struct pcpu_chunk *chunk) +{ +} + +static inline void pcpu_stats_chunk_alloc(void) +{ +} + +static inline void pcpu_stats_chunk_dealloc(void) +{ +} + +#endif /* !CONFIG_PERCPU_STATS */ + +#endif diff --git a/mm/percpu-km.c b/mm/percpu-km.c new file mode 100644 index 000000000..35c994107 --- /dev/null +++ b/mm/percpu-km.c @@ -0,0 +1,120 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * mm/percpu-km.c - kernel memory based chunk allocation + * + * Copyright (C) 2010 SUSE Linux Products GmbH + * Copyright (C) 2010 Tejun Heo + * + * Chunks are allocated as a contiguous kernel memory using gfp + * allocation. This is to be used on nommu architectures. + * + * To use percpu-km, + * + * - define CONFIG_NEED_PER_CPU_KM from the arch Kconfig. + * + * - CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK must not be defined. It's + * not compatible with PER_CPU_KM. EMBED_FIRST_CHUNK should work + * fine. + * + * - NUMA is not supported. When setting up the first chunk, + * @cpu_distance_fn should be NULL or report all CPUs to be nearer + * than or at LOCAL_DISTANCE. + * + * - It's best if the chunk size is power of two multiple of + * PAGE_SIZE. Because each chunk is allocated as a contiguous + * kernel memory block using alloc_pages(), memory will be wasted if + * chunk size is not aligned. percpu-km code will whine about it. + */ + +#if defined(CONFIG_SMP) && defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK) +#error "contiguous percpu allocation is incompatible with paged first chunk" +#endif + +#include + +static int pcpu_populate_chunk(struct pcpu_chunk *chunk, + int page_start, int page_end, gfp_t gfp) +{ + return 0; +} + +static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, + int page_start, int page_end) +{ + /* nada */ +} + +static struct pcpu_chunk *pcpu_create_chunk(enum pcpu_chunk_type type, + gfp_t gfp) +{ + const int nr_pages = pcpu_group_sizes[0] >> PAGE_SHIFT; + struct pcpu_chunk *chunk; + struct page *pages; + unsigned long flags; + int i; + + chunk = pcpu_alloc_chunk(type, gfp); + if (!chunk) + return NULL; + + pages = alloc_pages(gfp, order_base_2(nr_pages)); + if (!pages) { + pcpu_free_chunk(chunk); + return NULL; + } + + for (i = 0; i < nr_pages; i++) + pcpu_set_page_chunk(nth_page(pages, i), chunk); + + chunk->data = pages; + chunk->base_addr = page_address(pages); + + spin_lock_irqsave(&pcpu_lock, flags); + pcpu_chunk_populated(chunk, 0, nr_pages); + spin_unlock_irqrestore(&pcpu_lock, flags); + + pcpu_stats_chunk_alloc(); + trace_percpu_create_chunk(chunk->base_addr); + + return chunk; +} + +static void pcpu_destroy_chunk(struct pcpu_chunk *chunk) +{ + const int nr_pages = pcpu_group_sizes[0] >> PAGE_SHIFT; + + if (!chunk) + return; + + pcpu_stats_chunk_dealloc(); + trace_percpu_destroy_chunk(chunk->base_addr); + + if (chunk->data) + __free_pages(chunk->data, order_base_2(nr_pages)); + pcpu_free_chunk(chunk); +} + +static struct page *pcpu_addr_to_page(void *addr) +{ + return virt_to_page(addr); +} + +static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai) +{ + size_t nr_pages, alloc_pages; + + /* all units must be in a single group */ + if (ai->nr_groups != 1) { + pr_crit("can't handle more than one group\n"); + return -EINVAL; + } + + nr_pages = (ai->groups[0].nr_units * ai->unit_size) >> PAGE_SHIFT; + alloc_pages = roundup_pow_of_two(nr_pages); + + if (alloc_pages > nr_pages) + pr_warn("wasting %zu pages per chunk\n", + alloc_pages - nr_pages); + + return 0; +} diff --git a/mm/percpu-stats.c b/mm/percpu-stats.c new file mode 100644 index 000000000..f6026dbcd --- /dev/null +++ b/mm/percpu-stats.c @@ -0,0 +1,249 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * mm/percpu-debug.c + * + * Copyright (C) 2017 Facebook Inc. + * Copyright (C) 2017 Dennis Zhou + * + * Prints statistics about the percpu allocator and backing chunks. + */ +#include +#include +#include +#include +#include +#include + +#include "percpu-internal.h" + +#define P(X, Y) \ + seq_printf(m, " %-20s: %12lld\n", X, (long long int)Y) + +struct percpu_stats pcpu_stats; +struct pcpu_alloc_info pcpu_stats_ai; + +static int cmpint(const void *a, const void *b) +{ + return *(int *)a - *(int *)b; +} + +/* + * Iterates over all chunks to find the max nr_alloc entries. + */ +static int find_max_nr_alloc(void) +{ + struct pcpu_chunk *chunk; + int slot, max_nr_alloc; + enum pcpu_chunk_type type; + + max_nr_alloc = 0; + for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++) + for (slot = 0; slot < pcpu_nr_slots; slot++) + list_for_each_entry(chunk, &pcpu_chunk_list(type)[slot], + list) + max_nr_alloc = max(max_nr_alloc, + chunk->nr_alloc); + + return max_nr_alloc; +} + +/* + * Prints out chunk state. Fragmentation is considered between + * the beginning of the chunk to the last allocation. + * + * All statistics are in bytes unless stated otherwise. + */ +static void chunk_map_stats(struct seq_file *m, struct pcpu_chunk *chunk, + int *buffer) +{ + struct pcpu_block_md *chunk_md = &chunk->chunk_md; + int i, last_alloc, as_len, start, end; + int *alloc_sizes, *p; + /* statistics */ + int sum_frag = 0, max_frag = 0; + int cur_min_alloc = 0, cur_med_alloc = 0, cur_max_alloc = 0; + + alloc_sizes = buffer; + + /* + * find_last_bit returns the start value if nothing found. + * Therefore, we must determine if it is a failure of find_last_bit + * and set the appropriate value. + */ + last_alloc = find_last_bit(chunk->alloc_map, + pcpu_chunk_map_bits(chunk) - + chunk->end_offset / PCPU_MIN_ALLOC_SIZE - 1); + last_alloc = test_bit(last_alloc, chunk->alloc_map) ? + last_alloc + 1 : 0; + + as_len = 0; + start = chunk->start_offset / PCPU_MIN_ALLOC_SIZE; + + /* + * If a bit is set in the allocation map, the bound_map identifies + * where the allocation ends. If the allocation is not set, the + * bound_map does not identify free areas as it is only kept accurate + * on allocation, not free. + * + * Positive values are allocations and negative values are free + * fragments. + */ + while (start < last_alloc) { + if (test_bit(start, chunk->alloc_map)) { + end = find_next_bit(chunk->bound_map, last_alloc, + start + 1); + alloc_sizes[as_len] = 1; + } else { + end = find_next_bit(chunk->alloc_map, last_alloc, + start + 1); + alloc_sizes[as_len] = -1; + } + + alloc_sizes[as_len++] *= (end - start) * PCPU_MIN_ALLOC_SIZE; + + start = end; + } + + /* + * The negative values are free fragments and thus sorting gives the + * free fragments at the beginning in largest first order. + */ + if (as_len > 0) { + sort(alloc_sizes, as_len, sizeof(int), cmpint, NULL); + + /* iterate through the unallocated fragments */ + for (i = 0, p = alloc_sizes; *p < 0 && i < as_len; i++, p++) { + sum_frag -= *p; + max_frag = max(max_frag, -1 * (*p)); + } + + cur_min_alloc = alloc_sizes[i]; + cur_med_alloc = alloc_sizes[(i + as_len - 1) / 2]; + cur_max_alloc = alloc_sizes[as_len - 1]; + } + + P("nr_alloc", chunk->nr_alloc); + P("max_alloc_size", chunk->max_alloc_size); + P("empty_pop_pages", chunk->nr_empty_pop_pages); + P("first_bit", chunk_md->first_free); + P("free_bytes", chunk->free_bytes); + P("contig_bytes", chunk_md->contig_hint * PCPU_MIN_ALLOC_SIZE); + P("sum_frag", sum_frag); + P("max_frag", max_frag); + P("cur_min_alloc", cur_min_alloc); + P("cur_med_alloc", cur_med_alloc); + P("cur_max_alloc", cur_max_alloc); +#ifdef CONFIG_MEMCG_KMEM + P("memcg_aware", pcpu_is_memcg_chunk(pcpu_chunk_type(chunk))); +#endif + seq_putc(m, '\n'); +} + +static int percpu_stats_show(struct seq_file *m, void *v) +{ + struct pcpu_chunk *chunk; + int slot, max_nr_alloc; + int *buffer; + enum pcpu_chunk_type type; + int nr_empty_pop_pages; + +alloc_buffer: + spin_lock_irq(&pcpu_lock); + max_nr_alloc = find_max_nr_alloc(); + spin_unlock_irq(&pcpu_lock); + + /* there can be at most this many free and allocated fragments */ + buffer = vmalloc(array_size(sizeof(int), (2 * max_nr_alloc + 1))); + if (!buffer) + return -ENOMEM; + + spin_lock_irq(&pcpu_lock); + + /* if the buffer allocated earlier is too small */ + if (max_nr_alloc < find_max_nr_alloc()) { + spin_unlock_irq(&pcpu_lock); + vfree(buffer); + goto alloc_buffer; + } + + nr_empty_pop_pages = 0; + for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++) + nr_empty_pop_pages += pcpu_nr_empty_pop_pages[type]; + +#define PL(X) \ + seq_printf(m, " %-20s: %12lld\n", #X, (long long int)pcpu_stats_ai.X) + + seq_printf(m, + "Percpu Memory Statistics\n" + "Allocation Info:\n" + "----------------------------------------\n"); + PL(unit_size); + PL(static_size); + PL(reserved_size); + PL(dyn_size); + PL(atom_size); + PL(alloc_size); + seq_putc(m, '\n'); + +#undef PL + +#define PU(X) \ + seq_printf(m, " %-20s: %12llu\n", #X, (unsigned long long)pcpu_stats.X) + + seq_printf(m, + "Global Stats:\n" + "----------------------------------------\n"); + PU(nr_alloc); + PU(nr_dealloc); + PU(nr_cur_alloc); + PU(nr_max_alloc); + PU(nr_chunks); + PU(nr_max_chunks); + PU(min_alloc_size); + PU(max_alloc_size); + P("empty_pop_pages", nr_empty_pop_pages); + seq_putc(m, '\n'); + +#undef PU + + seq_printf(m, + "Per Chunk Stats:\n" + "----------------------------------------\n"); + + if (pcpu_reserved_chunk) { + seq_puts(m, "Chunk: <- Reserved Chunk\n"); + chunk_map_stats(m, pcpu_reserved_chunk, buffer); + } + + for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++) { + for (slot = 0; slot < pcpu_nr_slots; slot++) { + list_for_each_entry(chunk, &pcpu_chunk_list(type)[slot], + list) { + if (chunk == pcpu_first_chunk) { + seq_puts(m, "Chunk: <- First Chunk\n"); + chunk_map_stats(m, chunk, buffer); + } else { + seq_puts(m, "Chunk:\n"); + chunk_map_stats(m, chunk, buffer); + } + } + } + } + + spin_unlock_irq(&pcpu_lock); + + vfree(buffer); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(percpu_stats); + +static int __init init_percpu_stats_debugfs(void) +{ + debugfs_create_file("percpu_stats", 0444, NULL, NULL, + &percpu_stats_fops); + + return 0; +} + +late_initcall(init_percpu_stats_debugfs); diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c new file mode 100644 index 000000000..e46f7a691 --- /dev/null +++ b/mm/percpu-vm.c @@ -0,0 +1,379 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * mm/percpu-vm.c - vmalloc area based chunk allocation + * + * Copyright (C) 2010 SUSE Linux Products GmbH + * Copyright (C) 2010 Tejun Heo + * + * Chunks are mapped into vmalloc areas and populated page by page. + * This is the default chunk allocator. + */ + +static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk, + unsigned int cpu, int page_idx) +{ + /* must not be used on pre-mapped chunk */ + WARN_ON(chunk->immutable); + + return vmalloc_to_page((void *)pcpu_chunk_addr(chunk, cpu, page_idx)); +} + +/** + * pcpu_get_pages - get temp pages array + * + * Returns pointer to array of pointers to struct page which can be indexed + * with pcpu_page_idx(). Note that there is only one array and accesses + * should be serialized by pcpu_alloc_mutex. + * + * RETURNS: + * Pointer to temp pages array on success. + */ +static struct page **pcpu_get_pages(void) +{ + static struct page **pages; + size_t pages_size = pcpu_nr_units * pcpu_unit_pages * sizeof(pages[0]); + + lockdep_assert_held(&pcpu_alloc_mutex); + + if (!pages) + pages = pcpu_mem_zalloc(pages_size, GFP_KERNEL); + return pages; +} + +/** + * pcpu_free_pages - free pages which were allocated for @chunk + * @chunk: chunk pages were allocated for + * @pages: array of pages to be freed, indexed by pcpu_page_idx() + * @page_start: page index of the first page to be freed + * @page_end: page index of the last page to be freed + 1 + * + * Free pages [@page_start and @page_end) in @pages for all units. + * The pages were allocated for @chunk. + */ +static void pcpu_free_pages(struct pcpu_chunk *chunk, + struct page **pages, int page_start, int page_end) +{ + unsigned int cpu; + int i; + + for_each_possible_cpu(cpu) { + for (i = page_start; i < page_end; i++) { + struct page *page = pages[pcpu_page_idx(cpu, i)]; + + if (page) + __free_page(page); + } + } +} + +/** + * pcpu_alloc_pages - allocates pages for @chunk + * @chunk: target chunk + * @pages: array to put the allocated pages into, indexed by pcpu_page_idx() + * @page_start: page index of the first page to be allocated + * @page_end: page index of the last page to be allocated + 1 + * @gfp: allocation flags passed to the underlying allocator + * + * Allocate pages [@page_start,@page_end) into @pages for all units. + * The allocation is for @chunk. Percpu core doesn't care about the + * content of @pages and will pass it verbatim to pcpu_map_pages(). + */ +static int pcpu_alloc_pages(struct pcpu_chunk *chunk, + struct page **pages, int page_start, int page_end, + gfp_t gfp) +{ + unsigned int cpu, tcpu; + int i; + + gfp |= __GFP_HIGHMEM; + + for_each_possible_cpu(cpu) { + for (i = page_start; i < page_end; i++) { + struct page **pagep = &pages[pcpu_page_idx(cpu, i)]; + + *pagep = alloc_pages_node(cpu_to_node(cpu), gfp, 0); + if (!*pagep) + goto err; + } + } + return 0; + +err: + while (--i >= page_start) + __free_page(pages[pcpu_page_idx(cpu, i)]); + + for_each_possible_cpu(tcpu) { + if (tcpu == cpu) + break; + for (i = page_start; i < page_end; i++) + __free_page(pages[pcpu_page_idx(tcpu, i)]); + } + return -ENOMEM; +} + +/** + * pcpu_pre_unmap_flush - flush cache prior to unmapping + * @chunk: chunk the regions to be flushed belongs to + * @page_start: page index of the first page to be flushed + * @page_end: page index of the last page to be flushed + 1 + * + * Pages in [@page_start,@page_end) of @chunk are about to be + * unmapped. Flush cache. As each flushing trial can be very + * expensive, issue flush on the whole region at once rather than + * doing it for each cpu. This could be an overkill but is more + * scalable. + */ +static void pcpu_pre_unmap_flush(struct pcpu_chunk *chunk, + int page_start, int page_end) +{ + flush_cache_vunmap( + pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start), + pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end)); +} + +static void __pcpu_unmap_pages(unsigned long addr, int nr_pages) +{ + unmap_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT); +} + +/** + * pcpu_unmap_pages - unmap pages out of a pcpu_chunk + * @chunk: chunk of interest + * @pages: pages array which can be used to pass information to free + * @page_start: page index of the first page to unmap + * @page_end: page index of the last page to unmap + 1 + * + * For each cpu, unmap pages [@page_start,@page_end) out of @chunk. + * Corresponding elements in @pages were cleared by the caller and can + * be used to carry information to pcpu_free_pages() which will be + * called after all unmaps are finished. The caller should call + * proper pre/post flush functions. + */ +static void pcpu_unmap_pages(struct pcpu_chunk *chunk, + struct page **pages, int page_start, int page_end) +{ + unsigned int cpu; + int i; + + for_each_possible_cpu(cpu) { + for (i = page_start; i < page_end; i++) { + struct page *page; + + page = pcpu_chunk_page(chunk, cpu, i); + WARN_ON(!page); + pages[pcpu_page_idx(cpu, i)] = page; + } + __pcpu_unmap_pages(pcpu_chunk_addr(chunk, cpu, page_start), + page_end - page_start); + } +} + +/** + * pcpu_post_unmap_tlb_flush - flush TLB after unmapping + * @chunk: pcpu_chunk the regions to be flushed belong to + * @page_start: page index of the first page to be flushed + * @page_end: page index of the last page to be flushed + 1 + * + * Pages [@page_start,@page_end) of @chunk have been unmapped. Flush + * TLB for the regions. This can be skipped if the area is to be + * returned to vmalloc as vmalloc will handle TLB flushing lazily. + * + * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once + * for the whole region. + */ +static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk, + int page_start, int page_end) +{ + flush_tlb_kernel_range( + pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start), + pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end)); +} + +static int __pcpu_map_pages(unsigned long addr, struct page **pages, + int nr_pages) +{ + return map_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT, + PAGE_KERNEL, pages); +} + +/** + * pcpu_map_pages - map pages into a pcpu_chunk + * @chunk: chunk of interest + * @pages: pages array containing pages to be mapped + * @page_start: page index of the first page to map + * @page_end: page index of the last page to map + 1 + * + * For each cpu, map pages [@page_start,@page_end) into @chunk. The + * caller is responsible for calling pcpu_post_map_flush() after all + * mappings are complete. + * + * This function is responsible for setting up whatever is necessary for + * reverse lookup (addr -> chunk). + */ +static int pcpu_map_pages(struct pcpu_chunk *chunk, + struct page **pages, int page_start, int page_end) +{ + unsigned int cpu, tcpu; + int i, err; + + for_each_possible_cpu(cpu) { + err = __pcpu_map_pages(pcpu_chunk_addr(chunk, cpu, page_start), + &pages[pcpu_page_idx(cpu, page_start)], + page_end - page_start); + if (err < 0) + goto err; + + for (i = page_start; i < page_end; i++) + pcpu_set_page_chunk(pages[pcpu_page_idx(cpu, i)], + chunk); + } + return 0; +err: + for_each_possible_cpu(tcpu) { + if (tcpu == cpu) + break; + __pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start), + page_end - page_start); + } + pcpu_post_unmap_tlb_flush(chunk, page_start, page_end); + return err; +} + +/** + * pcpu_post_map_flush - flush cache after mapping + * @chunk: pcpu_chunk the regions to be flushed belong to + * @page_start: page index of the first page to be flushed + * @page_end: page index of the last page to be flushed + 1 + * + * Pages [@page_start,@page_end) of @chunk have been mapped. Flush + * cache. + * + * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once + * for the whole region. + */ +static void pcpu_post_map_flush(struct pcpu_chunk *chunk, + int page_start, int page_end) +{ + flush_cache_vmap( + pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start), + pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end)); +} + +/** + * pcpu_populate_chunk - populate and map an area of a pcpu_chunk + * @chunk: chunk of interest + * @page_start: the start page + * @page_end: the end page + * @gfp: allocation flags passed to the underlying memory allocator + * + * For each cpu, populate and map pages [@page_start,@page_end) into + * @chunk. + * + * CONTEXT: + * pcpu_alloc_mutex, does GFP_KERNEL allocation. + */ +static int pcpu_populate_chunk(struct pcpu_chunk *chunk, + int page_start, int page_end, gfp_t gfp) +{ + struct page **pages; + + pages = pcpu_get_pages(); + if (!pages) + return -ENOMEM; + + if (pcpu_alloc_pages(chunk, pages, page_start, page_end, gfp)) + return -ENOMEM; + + if (pcpu_map_pages(chunk, pages, page_start, page_end)) { + pcpu_free_pages(chunk, pages, page_start, page_end); + return -ENOMEM; + } + pcpu_post_map_flush(chunk, page_start, page_end); + + return 0; +} + +/** + * pcpu_depopulate_chunk - depopulate and unmap an area of a pcpu_chunk + * @chunk: chunk to depopulate + * @page_start: the start page + * @page_end: the end page + * + * For each cpu, depopulate and unmap pages [@page_start,@page_end) + * from @chunk. + * + * CONTEXT: + * pcpu_alloc_mutex. + */ +static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, + int page_start, int page_end) +{ + struct page **pages; + + /* + * If control reaches here, there must have been at least one + * successful population attempt so the temp pages array must + * be available now. + */ + pages = pcpu_get_pages(); + BUG_ON(!pages); + + /* unmap and free */ + pcpu_pre_unmap_flush(chunk, page_start, page_end); + + pcpu_unmap_pages(chunk, pages, page_start, page_end); + + /* no need to flush tlb, vmalloc will handle it lazily */ + + pcpu_free_pages(chunk, pages, page_start, page_end); +} + +static struct pcpu_chunk *pcpu_create_chunk(enum pcpu_chunk_type type, + gfp_t gfp) +{ + struct pcpu_chunk *chunk; + struct vm_struct **vms; + + chunk = pcpu_alloc_chunk(type, gfp); + if (!chunk) + return NULL; + + vms = pcpu_get_vm_areas(pcpu_group_offsets, pcpu_group_sizes, + pcpu_nr_groups, pcpu_atom_size); + if (!vms) { + pcpu_free_chunk(chunk); + return NULL; + } + + chunk->data = vms; + chunk->base_addr = vms[0]->addr - pcpu_group_offsets[0]; + + pcpu_stats_chunk_alloc(); + trace_percpu_create_chunk(chunk->base_addr); + + return chunk; +} + +static void pcpu_destroy_chunk(struct pcpu_chunk *chunk) +{ + if (!chunk) + return; + + pcpu_stats_chunk_dealloc(); + trace_percpu_destroy_chunk(chunk->base_addr); + + if (chunk->data) + pcpu_free_vm_areas(chunk->data, pcpu_nr_groups); + pcpu_free_chunk(chunk); +} + +static struct page *pcpu_addr_to_page(void *addr) +{ + return vmalloc_to_page(addr); +} + +static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai) +{ + /* no extra restriction */ + return 0; +} diff --git a/mm/percpu.c b/mm/percpu.c new file mode 100644 index 000000000..e12ab708f --- /dev/null +++ b/mm/percpu.c @@ -0,0 +1,3181 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * mm/percpu.c - percpu memory allocator + * + * Copyright (C) 2009 SUSE Linux Products GmbH + * Copyright (C) 2009 Tejun Heo + * + * Copyright (C) 2017 Facebook Inc. + * Copyright (C) 2017 Dennis Zhou + * + * The percpu allocator handles both static and dynamic areas. Percpu + * areas are allocated in chunks which are divided into units. There is + * a 1-to-1 mapping for units to possible cpus. These units are grouped + * based on NUMA properties of the machine. + * + * c0 c1 c2 + * ------------------- ------------------- ------------ + * | u0 | u1 | u2 | u3 | | u0 | u1 | u2 | u3 | | u0 | u1 | u + * ------------------- ...... ------------------- .... ------------ + * + * Allocation is done by offsets into a unit's address space. Ie., an + * area of 512 bytes at 6k in c1 occupies 512 bytes at 6k in c1:u0, + * c1:u1, c1:u2, etc. On NUMA machines, the mapping may be non-linear + * and even sparse. Access is handled by configuring percpu base + * registers according to the cpu to unit mappings and offsetting the + * base address using pcpu_unit_size. + * + * There is special consideration for the first chunk which must handle + * the static percpu variables in the kernel image as allocation services + * are not online yet. In short, the first chunk is structured like so: + * + * + * + * The static data is copied from the original section managed by the + * linker. The reserved section, if non-zero, primarily manages static + * percpu variables from kernel modules. Finally, the dynamic section + * takes care of normal allocations. + * + * The allocator organizes chunks into lists according to free size and + * memcg-awareness. To make a percpu allocation memcg-aware the __GFP_ACCOUNT + * flag should be passed. All memcg-aware allocations are sharing one set + * of chunks and all unaccounted allocations and allocations performed + * by processes belonging to the root memory cgroup are using the second set. + * + * The allocator tries to allocate from the fullest chunk first. Each chunk + * is managed by a bitmap with metadata blocks. The allocation map is updated + * on every allocation and free to reflect the current state while the boundary + * map is only updated on allocation. Each metadata block contains + * information to help mitigate the need to iterate over large portions + * of the bitmap. The reverse mapping from page to chunk is stored in + * the page's index. Lastly, units are lazily backed and grow in unison. + * + * There is a unique conversion that goes on here between bytes and bits. + * Each bit represents a fragment of size PCPU_MIN_ALLOC_SIZE. The chunk + * tracks the number of pages it is responsible for in nr_pages. Helper + * functions are used to convert from between the bytes, bits, and blocks. + * All hints are managed in bits unless explicitly stated. + * + * To use this allocator, arch code should do the following: + * + * - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate + * regular address to percpu pointer and back if they need to be + * different from the default + * + * - use pcpu_setup_first_chunk() during percpu area initialization to + * setup the first chunk containing the kernel static percpu area + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +#define CREATE_TRACE_POINTS +#include + +#include "percpu-internal.h" + +/* the slots are sorted by free bytes left, 1-31 bytes share the same slot */ +#define PCPU_SLOT_BASE_SHIFT 5 +/* chunks in slots below this are subject to being sidelined on failed alloc */ +#define PCPU_SLOT_FAIL_THRESHOLD 3 + +#define PCPU_EMPTY_POP_PAGES_LOW 2 +#define PCPU_EMPTY_POP_PAGES_HIGH 4 + +#ifdef CONFIG_SMP +/* default addr <-> pcpu_ptr mapping, override in asm/percpu.h if necessary */ +#ifndef __addr_to_pcpu_ptr +#define __addr_to_pcpu_ptr(addr) \ + (void __percpu *)((unsigned long)(addr) - \ + (unsigned long)pcpu_base_addr + \ + (unsigned long)__per_cpu_start) +#endif +#ifndef __pcpu_ptr_to_addr +#define __pcpu_ptr_to_addr(ptr) \ + (void __force *)((unsigned long)(ptr) + \ + (unsigned long)pcpu_base_addr - \ + (unsigned long)__per_cpu_start) +#endif +#else /* CONFIG_SMP */ +/* on UP, it's always identity mapped */ +#define __addr_to_pcpu_ptr(addr) (void __percpu *)(addr) +#define __pcpu_ptr_to_addr(ptr) (void __force *)(ptr) +#endif /* CONFIG_SMP */ + +static int pcpu_unit_pages __ro_after_init; +static int pcpu_unit_size __ro_after_init; +static int pcpu_nr_units __ro_after_init; +static int pcpu_atom_size __ro_after_init; +int pcpu_nr_slots __ro_after_init; +static size_t pcpu_chunk_struct_size __ro_after_init; + +/* cpus with the lowest and highest unit addresses */ +static unsigned int pcpu_low_unit_cpu __ro_after_init; +static unsigned int pcpu_high_unit_cpu __ro_after_init; + +/* the address of the first chunk which starts with the kernel static area */ +void *pcpu_base_addr __ro_after_init; +EXPORT_SYMBOL_GPL(pcpu_base_addr); + +static const int *pcpu_unit_map __ro_after_init; /* cpu -> unit */ +const unsigned long *pcpu_unit_offsets __ro_after_init; /* cpu -> unit offset */ + +/* group information, used for vm allocation */ +static int pcpu_nr_groups __ro_after_init; +static const unsigned long *pcpu_group_offsets __ro_after_init; +static const size_t *pcpu_group_sizes __ro_after_init; + +/* + * The first chunk which always exists. Note that unlike other + * chunks, this one can be allocated and mapped in several different + * ways and thus often doesn't live in the vmalloc area. + */ +struct pcpu_chunk *pcpu_first_chunk __ro_after_init; + +/* + * Optional reserved chunk. This chunk reserves part of the first + * chunk and serves it for reserved allocations. When the reserved + * region doesn't exist, the following variable is NULL. + */ +struct pcpu_chunk *pcpu_reserved_chunk __ro_after_init; + +DEFINE_SPINLOCK(pcpu_lock); /* all internal data structures */ +static DEFINE_MUTEX(pcpu_alloc_mutex); /* chunk create/destroy, [de]pop, map ext */ + +struct list_head *pcpu_chunk_lists __ro_after_init; /* chunk list slots */ + +/* chunks which need their map areas extended, protected by pcpu_lock */ +static LIST_HEAD(pcpu_map_extend_chunks); + +/* + * The number of empty populated pages by chunk type, protected by pcpu_lock. + * The reserved chunk doesn't contribute to the count. + */ +int pcpu_nr_empty_pop_pages[PCPU_NR_CHUNK_TYPES]; + +/* + * The number of populated pages in use by the allocator, protected by + * pcpu_lock. This number is kept per a unit per chunk (i.e. when a page gets + * allocated/deallocated, it is allocated/deallocated in all units of a chunk + * and increments/decrements this count by 1). + */ +static unsigned long pcpu_nr_populated; + +/* + * Balance work is used to populate or destroy chunks asynchronously. We + * try to keep the number of populated free pages between + * PCPU_EMPTY_POP_PAGES_LOW and HIGH for atomic allocations and at most one + * empty chunk. + */ +static void pcpu_balance_workfn(struct work_struct *work); +static DECLARE_WORK(pcpu_balance_work, pcpu_balance_workfn); +static bool pcpu_async_enabled __read_mostly; +static bool pcpu_atomic_alloc_failed; + +static void pcpu_schedule_balance_work(void) +{ + if (pcpu_async_enabled) + schedule_work(&pcpu_balance_work); +} + +/** + * pcpu_addr_in_chunk - check if the address is served from this chunk + * @chunk: chunk of interest + * @addr: percpu address + * + * RETURNS: + * True if the address is served from this chunk. + */ +static bool pcpu_addr_in_chunk(struct pcpu_chunk *chunk, void *addr) +{ + void *start_addr, *end_addr; + + if (!chunk) + return false; + + start_addr = chunk->base_addr + chunk->start_offset; + end_addr = chunk->base_addr + chunk->nr_pages * PAGE_SIZE - + chunk->end_offset; + + return addr >= start_addr && addr < end_addr; +} + +static int __pcpu_size_to_slot(int size) +{ + int highbit = fls(size); /* size is in bytes */ + return max(highbit - PCPU_SLOT_BASE_SHIFT + 2, 1); +} + +static int pcpu_size_to_slot(int size) +{ + if (size == pcpu_unit_size) + return pcpu_nr_slots - 1; + return __pcpu_size_to_slot(size); +} + +static int pcpu_chunk_slot(const struct pcpu_chunk *chunk) +{ + const struct pcpu_block_md *chunk_md = &chunk->chunk_md; + + if (chunk->free_bytes < PCPU_MIN_ALLOC_SIZE || + chunk_md->contig_hint == 0) + return 0; + + return pcpu_size_to_slot(chunk_md->contig_hint * PCPU_MIN_ALLOC_SIZE); +} + +/* set the pointer to a chunk in a page struct */ +static void pcpu_set_page_chunk(struct page *page, struct pcpu_chunk *pcpu) +{ + page->index = (unsigned long)pcpu; +} + +/* obtain pointer to a chunk from a page struct */ +static struct pcpu_chunk *pcpu_get_page_chunk(struct page *page) +{ + return (struct pcpu_chunk *)page->index; +} + +static int __maybe_unused pcpu_page_idx(unsigned int cpu, int page_idx) +{ + return pcpu_unit_map[cpu] * pcpu_unit_pages + page_idx; +} + +static unsigned long pcpu_unit_page_offset(unsigned int cpu, int page_idx) +{ + return pcpu_unit_offsets[cpu] + (page_idx << PAGE_SHIFT); +} + +static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk, + unsigned int cpu, int page_idx) +{ + return (unsigned long)chunk->base_addr + + pcpu_unit_page_offset(cpu, page_idx); +} + +/* + * The following are helper functions to help access bitmaps and convert + * between bitmap offsets to address offsets. + */ +static unsigned long *pcpu_index_alloc_map(struct pcpu_chunk *chunk, int index) +{ + return chunk->alloc_map + + (index * PCPU_BITMAP_BLOCK_BITS / BITS_PER_LONG); +} + +static unsigned long pcpu_off_to_block_index(int off) +{ + return off / PCPU_BITMAP_BLOCK_BITS; +} + +static unsigned long pcpu_off_to_block_off(int off) +{ + return off & (PCPU_BITMAP_BLOCK_BITS - 1); +} + +static unsigned long pcpu_block_off_to_off(int index, int off) +{ + return index * PCPU_BITMAP_BLOCK_BITS + off; +} + +/* + * pcpu_next_hint - determine which hint to use + * @block: block of interest + * @alloc_bits: size of allocation + * + * This determines if we should scan based on the scan_hint or first_free. + * In general, we want to scan from first_free to fulfill allocations by + * first fit. However, if we know a scan_hint at position scan_hint_start + * cannot fulfill an allocation, we can begin scanning from there knowing + * the contig_hint will be our fallback. + */ +static int pcpu_next_hint(struct pcpu_block_md *block, int alloc_bits) +{ + /* + * The three conditions below determine if we can skip past the + * scan_hint. First, does the scan hint exist. Second, is the + * contig_hint after the scan_hint (possibly not true iff + * contig_hint == scan_hint). Third, is the allocation request + * larger than the scan_hint. + */ + if (block->scan_hint && + block->contig_hint_start > block->scan_hint_start && + alloc_bits > block->scan_hint) + return block->scan_hint_start + block->scan_hint; + + return block->first_free; +} + +/** + * pcpu_next_md_free_region - finds the next hint free area + * @chunk: chunk of interest + * @bit_off: chunk offset + * @bits: size of free area + * + * Helper function for pcpu_for_each_md_free_region. It checks + * block->contig_hint and performs aggregation across blocks to find the + * next hint. It modifies bit_off and bits in-place to be consumed in the + * loop. + */ +static void pcpu_next_md_free_region(struct pcpu_chunk *chunk, int *bit_off, + int *bits) +{ + int i = pcpu_off_to_block_index(*bit_off); + int block_off = pcpu_off_to_block_off(*bit_off); + struct pcpu_block_md *block; + + *bits = 0; + for (block = chunk->md_blocks + i; i < pcpu_chunk_nr_blocks(chunk); + block++, i++) { + /* handles contig area across blocks */ + if (*bits) { + *bits += block->left_free; + if (block->left_free == PCPU_BITMAP_BLOCK_BITS) + continue; + return; + } + + /* + * This checks three things. First is there a contig_hint to + * check. Second, have we checked this hint before by + * comparing the block_off. Third, is this the same as the + * right contig hint. In the last case, it spills over into + * the next block and should be handled by the contig area + * across blocks code. + */ + *bits = block->contig_hint; + if (*bits && block->contig_hint_start >= block_off && + *bits + block->contig_hint_start < PCPU_BITMAP_BLOCK_BITS) { + *bit_off = pcpu_block_off_to_off(i, + block->contig_hint_start); + return; + } + /* reset to satisfy the second predicate above */ + block_off = 0; + + *bits = block->right_free; + *bit_off = (i + 1) * PCPU_BITMAP_BLOCK_BITS - block->right_free; + } +} + +/** + * pcpu_next_fit_region - finds fit areas for a given allocation request + * @chunk: chunk of interest + * @alloc_bits: size of allocation + * @align: alignment of area (max PAGE_SIZE) + * @bit_off: chunk offset + * @bits: size of free area + * + * Finds the next free region that is viable for use with a given size and + * alignment. This only returns if there is a valid area to be used for this + * allocation. block->first_free is returned if the allocation request fits + * within the block to see if the request can be fulfilled prior to the contig + * hint. + */ +static void pcpu_next_fit_region(struct pcpu_chunk *chunk, int alloc_bits, + int align, int *bit_off, int *bits) +{ + int i = pcpu_off_to_block_index(*bit_off); + int block_off = pcpu_off_to_block_off(*bit_off); + struct pcpu_block_md *block; + + *bits = 0; + for (block = chunk->md_blocks + i; i < pcpu_chunk_nr_blocks(chunk); + block++, i++) { + /* handles contig area across blocks */ + if (*bits) { + *bits += block->left_free; + if (*bits >= alloc_bits) + return; + if (block->left_free == PCPU_BITMAP_BLOCK_BITS) + continue; + } + + /* check block->contig_hint */ + *bits = ALIGN(block->contig_hint_start, align) - + block->contig_hint_start; + /* + * This uses the block offset to determine if this has been + * checked in the prior iteration. + */ + if (block->contig_hint && + block->contig_hint_start >= block_off && + block->contig_hint >= *bits + alloc_bits) { + int start = pcpu_next_hint(block, alloc_bits); + + *bits += alloc_bits + block->contig_hint_start - + start; + *bit_off = pcpu_block_off_to_off(i, start); + return; + } + /* reset to satisfy the second predicate above */ + block_off = 0; + + *bit_off = ALIGN(PCPU_BITMAP_BLOCK_BITS - block->right_free, + align); + *bits = PCPU_BITMAP_BLOCK_BITS - *bit_off; + *bit_off = pcpu_block_off_to_off(i, *bit_off); + if (*bits >= alloc_bits) + return; + } + + /* no valid offsets were found - fail condition */ + *bit_off = pcpu_chunk_map_bits(chunk); +} + +/* + * Metadata free area iterators. These perform aggregation of free areas + * based on the metadata blocks and return the offset @bit_off and size in + * bits of the free area @bits. pcpu_for_each_fit_region only returns when + * a fit is found for the allocation request. + */ +#define pcpu_for_each_md_free_region(chunk, bit_off, bits) \ + for (pcpu_next_md_free_region((chunk), &(bit_off), &(bits)); \ + (bit_off) < pcpu_chunk_map_bits((chunk)); \ + (bit_off) += (bits) + 1, \ + pcpu_next_md_free_region((chunk), &(bit_off), &(bits))) + +#define pcpu_for_each_fit_region(chunk, alloc_bits, align, bit_off, bits) \ + for (pcpu_next_fit_region((chunk), (alloc_bits), (align), &(bit_off), \ + &(bits)); \ + (bit_off) < pcpu_chunk_map_bits((chunk)); \ + (bit_off) += (bits), \ + pcpu_next_fit_region((chunk), (alloc_bits), (align), &(bit_off), \ + &(bits))) + +/** + * pcpu_mem_zalloc - allocate memory + * @size: bytes to allocate + * @gfp: allocation flags + * + * Allocate @size bytes. If @size is smaller than PAGE_SIZE, + * kzalloc() is used; otherwise, the equivalent of vzalloc() is used. + * This is to facilitate passing through whitelisted flags. The + * returned memory is always zeroed. + * + * RETURNS: + * Pointer to the allocated area on success, NULL on failure. + */ +static void *pcpu_mem_zalloc(size_t size, gfp_t gfp) +{ + if (WARN_ON_ONCE(!slab_is_available())) + return NULL; + + if (size <= PAGE_SIZE) + return kzalloc(size, gfp); + else + return __vmalloc(size, gfp | __GFP_ZERO); +} + +/** + * pcpu_mem_free - free memory + * @ptr: memory to free + * + * Free @ptr. @ptr should have been allocated using pcpu_mem_zalloc(). + */ +static void pcpu_mem_free(void *ptr) +{ + kvfree(ptr); +} + +static void __pcpu_chunk_move(struct pcpu_chunk *chunk, int slot, + bool move_front) +{ + if (chunk != pcpu_reserved_chunk) { + struct list_head *pcpu_slot; + + pcpu_slot = pcpu_chunk_list(pcpu_chunk_type(chunk)); + if (move_front) + list_move(&chunk->list, &pcpu_slot[slot]); + else + list_move_tail(&chunk->list, &pcpu_slot[slot]); + } +} + +static void pcpu_chunk_move(struct pcpu_chunk *chunk, int slot) +{ + __pcpu_chunk_move(chunk, slot, true); +} + +/** + * pcpu_chunk_relocate - put chunk in the appropriate chunk slot + * @chunk: chunk of interest + * @oslot: the previous slot it was on + * + * This function is called after an allocation or free changed @chunk. + * New slot according to the changed state is determined and @chunk is + * moved to the slot. Note that the reserved chunk is never put on + * chunk slots. + * + * CONTEXT: + * pcpu_lock. + */ +static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot) +{ + int nslot = pcpu_chunk_slot(chunk); + + if (oslot != nslot) + __pcpu_chunk_move(chunk, nslot, oslot < nslot); +} + +/* + * pcpu_update_empty_pages - update empty page counters + * @chunk: chunk of interest + * @nr: nr of empty pages + * + * This is used to keep track of the empty pages now based on the premise + * a md_block covers a page. The hint update functions recognize if a block + * is made full or broken to calculate deltas for keeping track of free pages. + */ +static inline void pcpu_update_empty_pages(struct pcpu_chunk *chunk, int nr) +{ + chunk->nr_empty_pop_pages += nr; + if (chunk != pcpu_reserved_chunk) + pcpu_nr_empty_pop_pages[pcpu_chunk_type(chunk)] += nr; +} + +/* + * pcpu_region_overlap - determines if two regions overlap + * @a: start of first region, inclusive + * @b: end of first region, exclusive + * @x: start of second region, inclusive + * @y: end of second region, exclusive + * + * This is used to determine if the hint region [a, b) overlaps with the + * allocated region [x, y). + */ +static inline bool pcpu_region_overlap(int a, int b, int x, int y) +{ + return (a < y) && (x < b); +} + +/** + * pcpu_block_update - updates a block given a free area + * @block: block of interest + * @start: start offset in block + * @end: end offset in block + * + * Updates a block given a known free area. The region [start, end) is + * expected to be the entirety of the free area within a block. Chooses + * the best starting offset if the contig hints are equal. + */ +static void pcpu_block_update(struct pcpu_block_md *block, int start, int end) +{ + int contig = end - start; + + block->first_free = min(block->first_free, start); + if (start == 0) + block->left_free = contig; + + if (end == block->nr_bits) + block->right_free = contig; + + if (contig > block->contig_hint) { + /* promote the old contig_hint to be the new scan_hint */ + if (start > block->contig_hint_start) { + if (block->contig_hint > block->scan_hint) { + block->scan_hint_start = + block->contig_hint_start; + block->scan_hint = block->contig_hint; + } else if (start < block->scan_hint_start) { + /* + * The old contig_hint == scan_hint. But, the + * new contig is larger so hold the invariant + * scan_hint_start < contig_hint_start. + */ + block->scan_hint = 0; + } + } else { + block->scan_hint = 0; + } + block->contig_hint_start = start; + block->contig_hint = contig; + } else if (contig == block->contig_hint) { + if (block->contig_hint_start && + (!start || + __ffs(start) > __ffs(block->contig_hint_start))) { + /* start has a better alignment so use it */ + block->contig_hint_start = start; + if (start < block->scan_hint_start && + block->contig_hint > block->scan_hint) + block->scan_hint = 0; + } else if (start > block->scan_hint_start || + block->contig_hint > block->scan_hint) { + /* + * Knowing contig == contig_hint, update the scan_hint + * if it is farther than or larger than the current + * scan_hint. + */ + block->scan_hint_start = start; + block->scan_hint = contig; + } + } else { + /* + * The region is smaller than the contig_hint. So only update + * the scan_hint if it is larger than or equal and farther than + * the current scan_hint. + */ + if ((start < block->contig_hint_start && + (contig > block->scan_hint || + (contig == block->scan_hint && + start > block->scan_hint_start)))) { + block->scan_hint_start = start; + block->scan_hint = contig; + } + } +} + +/* + * pcpu_block_update_scan - update a block given a free area from a scan + * @chunk: chunk of interest + * @bit_off: chunk offset + * @bits: size of free area + * + * Finding the final allocation spot first goes through pcpu_find_block_fit() + * to find a block that can hold the allocation and then pcpu_alloc_area() + * where a scan is used. When allocations require specific alignments, + * we can inadvertently create holes which will not be seen in the alloc + * or free paths. + * + * This takes a given free area hole and updates a block as it may change the + * scan_hint. We need to scan backwards to ensure we don't miss free bits + * from alignment. + */ +static void pcpu_block_update_scan(struct pcpu_chunk *chunk, int bit_off, + int bits) +{ + int s_off = pcpu_off_to_block_off(bit_off); + int e_off = s_off + bits; + int s_index, l_bit; + struct pcpu_block_md *block; + + if (e_off > PCPU_BITMAP_BLOCK_BITS) + return; + + s_index = pcpu_off_to_block_index(bit_off); + block = chunk->md_blocks + s_index; + + /* scan backwards in case of alignment skipping free bits */ + l_bit = find_last_bit(pcpu_index_alloc_map(chunk, s_index), s_off); + s_off = (s_off == l_bit) ? 0 : l_bit + 1; + + pcpu_block_update(block, s_off, e_off); +} + +/** + * pcpu_chunk_refresh_hint - updates metadata about a chunk + * @chunk: chunk of interest + * @full_scan: if we should scan from the beginning + * + * Iterates over the metadata blocks to find the largest contig area. + * A full scan can be avoided on the allocation path as this is triggered + * if we broke the contig_hint. In doing so, the scan_hint will be before + * the contig_hint or after if the scan_hint == contig_hint. This cannot + * be prevented on freeing as we want to find the largest area possibly + * spanning blocks. + */ +static void pcpu_chunk_refresh_hint(struct pcpu_chunk *chunk, bool full_scan) +{ + struct pcpu_block_md *chunk_md = &chunk->chunk_md; + int bit_off, bits; + + /* promote scan_hint to contig_hint */ + if (!full_scan && chunk_md->scan_hint) { + bit_off = chunk_md->scan_hint_start + chunk_md->scan_hint; + chunk_md->contig_hint_start = chunk_md->scan_hint_start; + chunk_md->contig_hint = chunk_md->scan_hint; + chunk_md->scan_hint = 0; + } else { + bit_off = chunk_md->first_free; + chunk_md->contig_hint = 0; + } + + bits = 0; + pcpu_for_each_md_free_region(chunk, bit_off, bits) + pcpu_block_update(chunk_md, bit_off, bit_off + bits); +} + +/** + * pcpu_block_refresh_hint + * @chunk: chunk of interest + * @index: index of the metadata block + * + * Scans over the block beginning at first_free and updates the block + * metadata accordingly. + */ +static void pcpu_block_refresh_hint(struct pcpu_chunk *chunk, int index) +{ + struct pcpu_block_md *block = chunk->md_blocks + index; + unsigned long *alloc_map = pcpu_index_alloc_map(chunk, index); + unsigned int rs, re, start; /* region start, region end */ + + /* promote scan_hint to contig_hint */ + if (block->scan_hint) { + start = block->scan_hint_start + block->scan_hint; + block->contig_hint_start = block->scan_hint_start; + block->contig_hint = block->scan_hint; + block->scan_hint = 0; + } else { + start = block->first_free; + block->contig_hint = 0; + } + + block->right_free = 0; + + /* iterate over free areas and update the contig hints */ + bitmap_for_each_clear_region(alloc_map, rs, re, start, + PCPU_BITMAP_BLOCK_BITS) + pcpu_block_update(block, rs, re); +} + +/** + * pcpu_block_update_hint_alloc - update hint on allocation path + * @chunk: chunk of interest + * @bit_off: chunk offset + * @bits: size of request + * + * Updates metadata for the allocation path. The metadata only has to be + * refreshed by a full scan iff the chunk's contig hint is broken. Block level + * scans are required if the block's contig hint is broken. + */ +static void pcpu_block_update_hint_alloc(struct pcpu_chunk *chunk, int bit_off, + int bits) +{ + struct pcpu_block_md *chunk_md = &chunk->chunk_md; + int nr_empty_pages = 0; + struct pcpu_block_md *s_block, *e_block, *block; + int s_index, e_index; /* block indexes of the freed allocation */ + int s_off, e_off; /* block offsets of the freed allocation */ + + /* + * Calculate per block offsets. + * The calculation uses an inclusive range, but the resulting offsets + * are [start, end). e_index always points to the last block in the + * range. + */ + s_index = pcpu_off_to_block_index(bit_off); + e_index = pcpu_off_to_block_index(bit_off + bits - 1); + s_off = pcpu_off_to_block_off(bit_off); + e_off = pcpu_off_to_block_off(bit_off + bits - 1) + 1; + + s_block = chunk->md_blocks + s_index; + e_block = chunk->md_blocks + e_index; + + /* + * Update s_block. + * block->first_free must be updated if the allocation takes its place. + * If the allocation breaks the contig_hint, a scan is required to + * restore this hint. + */ + if (s_block->contig_hint == PCPU_BITMAP_BLOCK_BITS) + nr_empty_pages++; + + if (s_off == s_block->first_free) + s_block->first_free = find_next_zero_bit( + pcpu_index_alloc_map(chunk, s_index), + PCPU_BITMAP_BLOCK_BITS, + s_off + bits); + + if (pcpu_region_overlap(s_block->scan_hint_start, + s_block->scan_hint_start + s_block->scan_hint, + s_off, + s_off + bits)) + s_block->scan_hint = 0; + + if (pcpu_region_overlap(s_block->contig_hint_start, + s_block->contig_hint_start + + s_block->contig_hint, + s_off, + s_off + bits)) { + /* block contig hint is broken - scan to fix it */ + if (!s_off) + s_block->left_free = 0; + pcpu_block_refresh_hint(chunk, s_index); + } else { + /* update left and right contig manually */ + s_block->left_free = min(s_block->left_free, s_off); + if (s_index == e_index) + s_block->right_free = min_t(int, s_block->right_free, + PCPU_BITMAP_BLOCK_BITS - e_off); + else + s_block->right_free = 0; + } + + /* + * Update e_block. + */ + if (s_index != e_index) { + if (e_block->contig_hint == PCPU_BITMAP_BLOCK_BITS) + nr_empty_pages++; + + /* + * When the allocation is across blocks, the end is along + * the left part of the e_block. + */ + e_block->first_free = find_next_zero_bit( + pcpu_index_alloc_map(chunk, e_index), + PCPU_BITMAP_BLOCK_BITS, e_off); + + if (e_off == PCPU_BITMAP_BLOCK_BITS) { + /* reset the block */ + e_block++; + } else { + if (e_off > e_block->scan_hint_start) + e_block->scan_hint = 0; + + e_block->left_free = 0; + if (e_off > e_block->contig_hint_start) { + /* contig hint is broken - scan to fix it */ + pcpu_block_refresh_hint(chunk, e_index); + } else { + e_block->right_free = + min_t(int, e_block->right_free, + PCPU_BITMAP_BLOCK_BITS - e_off); + } + } + + /* update in-between md_blocks */ + nr_empty_pages += (e_index - s_index - 1); + for (block = s_block + 1; block < e_block; block++) { + block->scan_hint = 0; + block->contig_hint = 0; + block->left_free = 0; + block->right_free = 0; + } + } + + if (nr_empty_pages) + pcpu_update_empty_pages(chunk, -nr_empty_pages); + + if (pcpu_region_overlap(chunk_md->scan_hint_start, + chunk_md->scan_hint_start + + chunk_md->scan_hint, + bit_off, + bit_off + bits)) + chunk_md->scan_hint = 0; + + /* + * The only time a full chunk scan is required is if the chunk + * contig hint is broken. Otherwise, it means a smaller space + * was used and therefore the chunk contig hint is still correct. + */ + if (pcpu_region_overlap(chunk_md->contig_hint_start, + chunk_md->contig_hint_start + + chunk_md->contig_hint, + bit_off, + bit_off + bits)) + pcpu_chunk_refresh_hint(chunk, false); +} + +/** + * pcpu_block_update_hint_free - updates the block hints on the free path + * @chunk: chunk of interest + * @bit_off: chunk offset + * @bits: size of request + * + * Updates metadata for the allocation path. This avoids a blind block + * refresh by making use of the block contig hints. If this fails, it scans + * forward and backward to determine the extent of the free area. This is + * capped at the boundary of blocks. + * + * A chunk update is triggered if a page becomes free, a block becomes free, + * or the free spans across blocks. This tradeoff is to minimize iterating + * over the block metadata to update chunk_md->contig_hint. + * chunk_md->contig_hint may be off by up to a page, but it will never be more + * than the available space. If the contig hint is contained in one block, it + * will be accurate. + */ +static void pcpu_block_update_hint_free(struct pcpu_chunk *chunk, int bit_off, + int bits) +{ + int nr_empty_pages = 0; + struct pcpu_block_md *s_block, *e_block, *block; + int s_index, e_index; /* block indexes of the freed allocation */ + int s_off, e_off; /* block offsets of the freed allocation */ + int start, end; /* start and end of the whole free area */ + + /* + * Calculate per block offsets. + * The calculation uses an inclusive range, but the resulting offsets + * are [start, end). e_index always points to the last block in the + * range. + */ + s_index = pcpu_off_to_block_index(bit_off); + e_index = pcpu_off_to_block_index(bit_off + bits - 1); + s_off = pcpu_off_to_block_off(bit_off); + e_off = pcpu_off_to_block_off(bit_off + bits - 1) + 1; + + s_block = chunk->md_blocks + s_index; + e_block = chunk->md_blocks + e_index; + + /* + * Check if the freed area aligns with the block->contig_hint. + * If it does, then the scan to find the beginning/end of the + * larger free area can be avoided. + * + * start and end refer to beginning and end of the free area + * within each their respective blocks. This is not necessarily + * the entire free area as it may span blocks past the beginning + * or end of the block. + */ + start = s_off; + if (s_off == s_block->contig_hint + s_block->contig_hint_start) { + start = s_block->contig_hint_start; + } else { + /* + * Scan backwards to find the extent of the free area. + * find_last_bit returns the starting bit, so if the start bit + * is returned, that means there was no last bit and the + * remainder of the chunk is free. + */ + int l_bit = find_last_bit(pcpu_index_alloc_map(chunk, s_index), + start); + start = (start == l_bit) ? 0 : l_bit + 1; + } + + end = e_off; + if (e_off == e_block->contig_hint_start) + end = e_block->contig_hint_start + e_block->contig_hint; + else + end = find_next_bit(pcpu_index_alloc_map(chunk, e_index), + PCPU_BITMAP_BLOCK_BITS, end); + + /* update s_block */ + e_off = (s_index == e_index) ? end : PCPU_BITMAP_BLOCK_BITS; + if (!start && e_off == PCPU_BITMAP_BLOCK_BITS) + nr_empty_pages++; + pcpu_block_update(s_block, start, e_off); + + /* freeing in the same block */ + if (s_index != e_index) { + /* update e_block */ + if (end == PCPU_BITMAP_BLOCK_BITS) + nr_empty_pages++; + pcpu_block_update(e_block, 0, end); + + /* reset md_blocks in the middle */ + nr_empty_pages += (e_index - s_index - 1); + for (block = s_block + 1; block < e_block; block++) { + block->first_free = 0; + block->scan_hint = 0; + block->contig_hint_start = 0; + block->contig_hint = PCPU_BITMAP_BLOCK_BITS; + block->left_free = PCPU_BITMAP_BLOCK_BITS; + block->right_free = PCPU_BITMAP_BLOCK_BITS; + } + } + + if (nr_empty_pages) + pcpu_update_empty_pages(chunk, nr_empty_pages); + + /* + * Refresh chunk metadata when the free makes a block free or spans + * across blocks. The contig_hint may be off by up to a page, but if + * the contig_hint is contained in a block, it will be accurate with + * the else condition below. + */ + if (((end - start) >= PCPU_BITMAP_BLOCK_BITS) || s_index != e_index) + pcpu_chunk_refresh_hint(chunk, true); + else + pcpu_block_update(&chunk->chunk_md, + pcpu_block_off_to_off(s_index, start), + end); +} + +/** + * pcpu_is_populated - determines if the region is populated + * @chunk: chunk of interest + * @bit_off: chunk offset + * @bits: size of area + * @next_off: return value for the next offset to start searching + * + * For atomic allocations, check if the backing pages are populated. + * + * RETURNS: + * Bool if the backing pages are populated. + * next_index is to skip over unpopulated blocks in pcpu_find_block_fit. + */ +static bool pcpu_is_populated(struct pcpu_chunk *chunk, int bit_off, int bits, + int *next_off) +{ + unsigned int page_start, page_end, rs, re; + + page_start = PFN_DOWN(bit_off * PCPU_MIN_ALLOC_SIZE); + page_end = PFN_UP((bit_off + bits) * PCPU_MIN_ALLOC_SIZE); + + rs = page_start; + bitmap_next_clear_region(chunk->populated, &rs, &re, page_end); + if (rs >= page_end) + return true; + + *next_off = re * PAGE_SIZE / PCPU_MIN_ALLOC_SIZE; + return false; +} + +/** + * pcpu_find_block_fit - finds the block index to start searching + * @chunk: chunk of interest + * @alloc_bits: size of request in allocation units + * @align: alignment of area (max PAGE_SIZE bytes) + * @pop_only: use populated regions only + * + * Given a chunk and an allocation spec, find the offset to begin searching + * for a free region. This iterates over the bitmap metadata blocks to + * find an offset that will be guaranteed to fit the requirements. It is + * not quite first fit as if the allocation does not fit in the contig hint + * of a block or chunk, it is skipped. This errs on the side of caution + * to prevent excess iteration. Poor alignment can cause the allocator to + * skip over blocks and chunks that have valid free areas. + * + * RETURNS: + * The offset in the bitmap to begin searching. + * -1 if no offset is found. + */ +static int pcpu_find_block_fit(struct pcpu_chunk *chunk, int alloc_bits, + size_t align, bool pop_only) +{ + struct pcpu_block_md *chunk_md = &chunk->chunk_md; + int bit_off, bits, next_off; + + /* + * Check to see if the allocation can fit in the chunk's contig hint. + * This is an optimization to prevent scanning by assuming if it + * cannot fit in the global hint, there is memory pressure and creating + * a new chunk would happen soon. + */ + bit_off = ALIGN(chunk_md->contig_hint_start, align) - + chunk_md->contig_hint_start; + if (bit_off + alloc_bits > chunk_md->contig_hint) + return -1; + + bit_off = pcpu_next_hint(chunk_md, alloc_bits); + bits = 0; + pcpu_for_each_fit_region(chunk, alloc_bits, align, bit_off, bits) { + if (!pop_only || pcpu_is_populated(chunk, bit_off, bits, + &next_off)) + break; + + bit_off = next_off; + bits = 0; + } + + if (bit_off == pcpu_chunk_map_bits(chunk)) + return -1; + + return bit_off; +} + +/* + * pcpu_find_zero_area - modified from bitmap_find_next_zero_area_off() + * @map: the address to base the search on + * @size: the bitmap size in bits + * @start: the bitnumber to start searching at + * @nr: the number of zeroed bits we're looking for + * @align_mask: alignment mask for zero area + * @largest_off: offset of the largest area skipped + * @largest_bits: size of the largest area skipped + * + * The @align_mask should be one less than a power of 2. + * + * This is a modified version of bitmap_find_next_zero_area_off() to remember + * the largest area that was skipped. This is imperfect, but in general is + * good enough. The largest remembered region is the largest failed region + * seen. This does not include anything we possibly skipped due to alignment. + * pcpu_block_update_scan() does scan backwards to try and recover what was + * lost to alignment. While this can cause scanning to miss earlier possible + * free areas, smaller allocations will eventually fill those holes. + */ +static unsigned long pcpu_find_zero_area(unsigned long *map, + unsigned long size, + unsigned long start, + unsigned long nr, + unsigned long align_mask, + unsigned long *largest_off, + unsigned long *largest_bits) +{ + unsigned long index, end, i, area_off, area_bits; +again: + index = find_next_zero_bit(map, size, start); + + /* Align allocation */ + index = __ALIGN_MASK(index, align_mask); + area_off = index; + + end = index + nr; + if (end > size) + return end; + i = find_next_bit(map, end, index); + if (i < end) { + area_bits = i - area_off; + /* remember largest unused area with best alignment */ + if (area_bits > *largest_bits || + (area_bits == *largest_bits && *largest_off && + (!area_off || __ffs(area_off) > __ffs(*largest_off)))) { + *largest_off = area_off; + *largest_bits = area_bits; + } + + start = i + 1; + goto again; + } + return index; +} + +/** + * pcpu_alloc_area - allocates an area from a pcpu_chunk + * @chunk: chunk of interest + * @alloc_bits: size of request in allocation units + * @align: alignment of area (max PAGE_SIZE) + * @start: bit_off to start searching + * + * This function takes in a @start offset to begin searching to fit an + * allocation of @alloc_bits with alignment @align. It needs to scan + * the allocation map because if it fits within the block's contig hint, + * @start will be block->first_free. This is an attempt to fill the + * allocation prior to breaking the contig hint. The allocation and + * boundary maps are updated accordingly if it confirms a valid + * free area. + * + * RETURNS: + * Allocated addr offset in @chunk on success. + * -1 if no matching area is found. + */ +static int pcpu_alloc_area(struct pcpu_chunk *chunk, int alloc_bits, + size_t align, int start) +{ + struct pcpu_block_md *chunk_md = &chunk->chunk_md; + size_t align_mask = (align) ? (align - 1) : 0; + unsigned long area_off = 0, area_bits = 0; + int bit_off, end, oslot; + + lockdep_assert_held(&pcpu_lock); + + oslot = pcpu_chunk_slot(chunk); + + /* + * Search to find a fit. + */ + end = min_t(int, start + alloc_bits + PCPU_BITMAP_BLOCK_BITS, + pcpu_chunk_map_bits(chunk)); + bit_off = pcpu_find_zero_area(chunk->alloc_map, end, start, alloc_bits, + align_mask, &area_off, &area_bits); + if (bit_off >= end) + return -1; + + if (area_bits) + pcpu_block_update_scan(chunk, area_off, area_bits); + + /* update alloc map */ + bitmap_set(chunk->alloc_map, bit_off, alloc_bits); + + /* update boundary map */ + set_bit(bit_off, chunk->bound_map); + bitmap_clear(chunk->bound_map, bit_off + 1, alloc_bits - 1); + set_bit(bit_off + alloc_bits, chunk->bound_map); + + chunk->free_bytes -= alloc_bits * PCPU_MIN_ALLOC_SIZE; + + /* update first free bit */ + if (bit_off == chunk_md->first_free) + chunk_md->first_free = find_next_zero_bit( + chunk->alloc_map, + pcpu_chunk_map_bits(chunk), + bit_off + alloc_bits); + + pcpu_block_update_hint_alloc(chunk, bit_off, alloc_bits); + + pcpu_chunk_relocate(chunk, oslot); + + return bit_off * PCPU_MIN_ALLOC_SIZE; +} + +/** + * pcpu_free_area - frees the corresponding offset + * @chunk: chunk of interest + * @off: addr offset into chunk + * + * This function determines the size of an allocation to free using + * the boundary bitmap and clears the allocation map. + * + * RETURNS: + * Number of freed bytes. + */ +static int pcpu_free_area(struct pcpu_chunk *chunk, int off) +{ + struct pcpu_block_md *chunk_md = &chunk->chunk_md; + int bit_off, bits, end, oslot, freed; + + lockdep_assert_held(&pcpu_lock); + pcpu_stats_area_dealloc(chunk); + + oslot = pcpu_chunk_slot(chunk); + + bit_off = off / PCPU_MIN_ALLOC_SIZE; + + /* find end index */ + end = find_next_bit(chunk->bound_map, pcpu_chunk_map_bits(chunk), + bit_off + 1); + bits = end - bit_off; + bitmap_clear(chunk->alloc_map, bit_off, bits); + + freed = bits * PCPU_MIN_ALLOC_SIZE; + + /* update metadata */ + chunk->free_bytes += freed; + + /* update first free bit */ + chunk_md->first_free = min(chunk_md->first_free, bit_off); + + pcpu_block_update_hint_free(chunk, bit_off, bits); + + pcpu_chunk_relocate(chunk, oslot); + + return freed; +} + +static void pcpu_init_md_block(struct pcpu_block_md *block, int nr_bits) +{ + block->scan_hint = 0; + block->contig_hint = nr_bits; + block->left_free = nr_bits; + block->right_free = nr_bits; + block->first_free = 0; + block->nr_bits = nr_bits; +} + +static void pcpu_init_md_blocks(struct pcpu_chunk *chunk) +{ + struct pcpu_block_md *md_block; + + /* init the chunk's block */ + pcpu_init_md_block(&chunk->chunk_md, pcpu_chunk_map_bits(chunk)); + + for (md_block = chunk->md_blocks; + md_block != chunk->md_blocks + pcpu_chunk_nr_blocks(chunk); + md_block++) + pcpu_init_md_block(md_block, PCPU_BITMAP_BLOCK_BITS); +} + +/** + * pcpu_alloc_first_chunk - creates chunks that serve the first chunk + * @tmp_addr: the start of the region served + * @map_size: size of the region served + * + * This is responsible for creating the chunks that serve the first chunk. The + * base_addr is page aligned down of @tmp_addr while the region end is page + * aligned up. Offsets are kept track of to determine the region served. All + * this is done to appease the bitmap allocator in avoiding partial blocks. + * + * RETURNS: + * Chunk serving the region at @tmp_addr of @map_size. + */ +static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, + int map_size) +{ + struct pcpu_chunk *chunk; + unsigned long aligned_addr, lcm_align; + int start_offset, offset_bits, region_size, region_bits; + size_t alloc_size; + + /* region calculations */ + aligned_addr = tmp_addr & PAGE_MASK; + + start_offset = tmp_addr - aligned_addr; + + /* + * Align the end of the region with the LCM of PAGE_SIZE and + * PCPU_BITMAP_BLOCK_SIZE. One of these constants is a multiple of + * the other. + */ + lcm_align = lcm(PAGE_SIZE, PCPU_BITMAP_BLOCK_SIZE); + region_size = ALIGN(start_offset + map_size, lcm_align); + + /* allocate chunk */ + alloc_size = struct_size(chunk, populated, + BITS_TO_LONGS(region_size >> PAGE_SHIFT)); + chunk = memblock_alloc(alloc_size, SMP_CACHE_BYTES); + if (!chunk) + panic("%s: Failed to allocate %zu bytes\n", __func__, + alloc_size); + + INIT_LIST_HEAD(&chunk->list); + + chunk->base_addr = (void *)aligned_addr; + chunk->start_offset = start_offset; + chunk->end_offset = region_size - chunk->start_offset - map_size; + + chunk->nr_pages = region_size >> PAGE_SHIFT; + region_bits = pcpu_chunk_map_bits(chunk); + + alloc_size = BITS_TO_LONGS(region_bits) * sizeof(chunk->alloc_map[0]); + chunk->alloc_map = memblock_alloc(alloc_size, SMP_CACHE_BYTES); + if (!chunk->alloc_map) + panic("%s: Failed to allocate %zu bytes\n", __func__, + alloc_size); + + alloc_size = + BITS_TO_LONGS(region_bits + 1) * sizeof(chunk->bound_map[0]); + chunk->bound_map = memblock_alloc(alloc_size, SMP_CACHE_BYTES); + if (!chunk->bound_map) + panic("%s: Failed to allocate %zu bytes\n", __func__, + alloc_size); + + alloc_size = pcpu_chunk_nr_blocks(chunk) * sizeof(chunk->md_blocks[0]); + chunk->md_blocks = memblock_alloc(alloc_size, SMP_CACHE_BYTES); + if (!chunk->md_blocks) + panic("%s: Failed to allocate %zu bytes\n", __func__, + alloc_size); + +#ifdef CONFIG_MEMCG_KMEM + /* first chunk isn't memcg-aware */ + chunk->obj_cgroups = NULL; +#endif + pcpu_init_md_blocks(chunk); + + /* manage populated page bitmap */ + chunk->immutable = true; + bitmap_fill(chunk->populated, chunk->nr_pages); + chunk->nr_populated = chunk->nr_pages; + chunk->nr_empty_pop_pages = chunk->nr_pages; + + chunk->free_bytes = map_size; + + if (chunk->start_offset) { + /* hide the beginning of the bitmap */ + offset_bits = chunk->start_offset / PCPU_MIN_ALLOC_SIZE; + bitmap_set(chunk->alloc_map, 0, offset_bits); + set_bit(0, chunk->bound_map); + set_bit(offset_bits, chunk->bound_map); + + chunk->chunk_md.first_free = offset_bits; + + pcpu_block_update_hint_alloc(chunk, 0, offset_bits); + } + + if (chunk->end_offset) { + /* hide the end of the bitmap */ + offset_bits = chunk->end_offset / PCPU_MIN_ALLOC_SIZE; + bitmap_set(chunk->alloc_map, + pcpu_chunk_map_bits(chunk) - offset_bits, + offset_bits); + set_bit((start_offset + map_size) / PCPU_MIN_ALLOC_SIZE, + chunk->bound_map); + set_bit(region_bits, chunk->bound_map); + + pcpu_block_update_hint_alloc(chunk, pcpu_chunk_map_bits(chunk) + - offset_bits, offset_bits); + } + + return chunk; +} + +static struct pcpu_chunk *pcpu_alloc_chunk(enum pcpu_chunk_type type, gfp_t gfp) +{ + struct pcpu_chunk *chunk; + int region_bits; + + chunk = pcpu_mem_zalloc(pcpu_chunk_struct_size, gfp); + if (!chunk) + return NULL; + + INIT_LIST_HEAD(&chunk->list); + chunk->nr_pages = pcpu_unit_pages; + region_bits = pcpu_chunk_map_bits(chunk); + + chunk->alloc_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits) * + sizeof(chunk->alloc_map[0]), gfp); + if (!chunk->alloc_map) + goto alloc_map_fail; + + chunk->bound_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits + 1) * + sizeof(chunk->bound_map[0]), gfp); + if (!chunk->bound_map) + goto bound_map_fail; + + chunk->md_blocks = pcpu_mem_zalloc(pcpu_chunk_nr_blocks(chunk) * + sizeof(chunk->md_blocks[0]), gfp); + if (!chunk->md_blocks) + goto md_blocks_fail; + +#ifdef CONFIG_MEMCG_KMEM + if (pcpu_is_memcg_chunk(type)) { + chunk->obj_cgroups = + pcpu_mem_zalloc(pcpu_chunk_map_bits(chunk) * + sizeof(struct obj_cgroup *), gfp); + if (!chunk->obj_cgroups) + goto objcg_fail; + } +#endif + + pcpu_init_md_blocks(chunk); + + /* init metadata */ + chunk->free_bytes = chunk->nr_pages * PAGE_SIZE; + + return chunk; + +#ifdef CONFIG_MEMCG_KMEM +objcg_fail: + pcpu_mem_free(chunk->md_blocks); +#endif +md_blocks_fail: + pcpu_mem_free(chunk->bound_map); +bound_map_fail: + pcpu_mem_free(chunk->alloc_map); +alloc_map_fail: + pcpu_mem_free(chunk); + + return NULL; +} + +static void pcpu_free_chunk(struct pcpu_chunk *chunk) +{ + if (!chunk) + return; +#ifdef CONFIG_MEMCG_KMEM + pcpu_mem_free(chunk->obj_cgroups); +#endif + pcpu_mem_free(chunk->md_blocks); + pcpu_mem_free(chunk->bound_map); + pcpu_mem_free(chunk->alloc_map); + pcpu_mem_free(chunk); +} + +/** + * pcpu_chunk_populated - post-population bookkeeping + * @chunk: pcpu_chunk which got populated + * @page_start: the start page + * @page_end: the end page + * + * Pages in [@page_start,@page_end) have been populated to @chunk. Update + * the bookkeeping information accordingly. Must be called after each + * successful population. + * + * If this is @for_alloc, do not increment pcpu_nr_empty_pop_pages because it + * is to serve an allocation in that area. + */ +static void pcpu_chunk_populated(struct pcpu_chunk *chunk, int page_start, + int page_end) +{ + int nr = page_end - page_start; + + lockdep_assert_held(&pcpu_lock); + + bitmap_set(chunk->populated, page_start, nr); + chunk->nr_populated += nr; + pcpu_nr_populated += nr; + + pcpu_update_empty_pages(chunk, nr); +} + +/** + * pcpu_chunk_depopulated - post-depopulation bookkeeping + * @chunk: pcpu_chunk which got depopulated + * @page_start: the start page + * @page_end: the end page + * + * Pages in [@page_start,@page_end) have been depopulated from @chunk. + * Update the bookkeeping information accordingly. Must be called after + * each successful depopulation. + */ +static void pcpu_chunk_depopulated(struct pcpu_chunk *chunk, + int page_start, int page_end) +{ + int nr = page_end - page_start; + + lockdep_assert_held(&pcpu_lock); + + bitmap_clear(chunk->populated, page_start, nr); + chunk->nr_populated -= nr; + pcpu_nr_populated -= nr; + + pcpu_update_empty_pages(chunk, -nr); +} + +/* + * Chunk management implementation. + * + * To allow different implementations, chunk alloc/free and + * [de]population are implemented in a separate file which is pulled + * into this file and compiled together. The following functions + * should be implemented. + * + * pcpu_populate_chunk - populate the specified range of a chunk + * pcpu_depopulate_chunk - depopulate the specified range of a chunk + * pcpu_create_chunk - create a new chunk + * pcpu_destroy_chunk - destroy a chunk, always preceded by full depop + * pcpu_addr_to_page - translate address to physical address + * pcpu_verify_alloc_info - check alloc_info is acceptable during init + */ +static int pcpu_populate_chunk(struct pcpu_chunk *chunk, + int page_start, int page_end, gfp_t gfp); +static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, + int page_start, int page_end); +static struct pcpu_chunk *pcpu_create_chunk(enum pcpu_chunk_type type, + gfp_t gfp); +static void pcpu_destroy_chunk(struct pcpu_chunk *chunk); +static struct page *pcpu_addr_to_page(void *addr); +static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai); + +#ifdef CONFIG_NEED_PER_CPU_KM +#include "percpu-km.c" +#else +#include "percpu-vm.c" +#endif + +/** + * pcpu_chunk_addr_search - determine chunk containing specified address + * @addr: address for which the chunk needs to be determined. + * + * This is an internal function that handles all but static allocations. + * Static percpu address values should never be passed into the allocator. + * + * RETURNS: + * The address of the found chunk. + */ +static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) +{ + /* is it in the dynamic region (first chunk)? */ + if (pcpu_addr_in_chunk(pcpu_first_chunk, addr)) + return pcpu_first_chunk; + + /* is it in the reserved region? */ + if (pcpu_addr_in_chunk(pcpu_reserved_chunk, addr)) + return pcpu_reserved_chunk; + + /* + * The address is relative to unit0 which might be unused and + * thus unmapped. Offset the address to the unit space of the + * current processor before looking it up in the vmalloc + * space. Note that any possible cpu id can be used here, so + * there's no need to worry about preemption or cpu hotplug. + */ + addr += pcpu_unit_offsets[raw_smp_processor_id()]; + return pcpu_get_page_chunk(pcpu_addr_to_page(addr)); +} + +#ifdef CONFIG_MEMCG_KMEM +static enum pcpu_chunk_type pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp, + struct obj_cgroup **objcgp) +{ + struct obj_cgroup *objcg; + + if (!memcg_kmem_enabled() || !(gfp & __GFP_ACCOUNT)) + return PCPU_CHUNK_ROOT; + + objcg = get_obj_cgroup_from_current(); + if (!objcg) + return PCPU_CHUNK_ROOT; + + if (obj_cgroup_charge(objcg, gfp, size * num_possible_cpus())) { + obj_cgroup_put(objcg); + return PCPU_FAIL_ALLOC; + } + + *objcgp = objcg; + return PCPU_CHUNK_MEMCG; +} + +static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg, + struct pcpu_chunk *chunk, int off, + size_t size) +{ + if (!objcg) + return; + + if (chunk) { + chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT] = objcg; + + rcu_read_lock(); + mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B, + size * num_possible_cpus()); + rcu_read_unlock(); + } else { + obj_cgroup_uncharge(objcg, size * num_possible_cpus()); + obj_cgroup_put(objcg); + } +} + +static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size) +{ + struct obj_cgroup *objcg; + + if (!pcpu_is_memcg_chunk(pcpu_chunk_type(chunk))) + return; + + objcg = chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT]; + chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT] = NULL; + + obj_cgroup_uncharge(objcg, size * num_possible_cpus()); + + rcu_read_lock(); + mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B, + -(size * num_possible_cpus())); + rcu_read_unlock(); + + obj_cgroup_put(objcg); +} + +#else /* CONFIG_MEMCG_KMEM */ +static enum pcpu_chunk_type +pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp, struct obj_cgroup **objcgp) +{ + return PCPU_CHUNK_ROOT; +} + +static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg, + struct pcpu_chunk *chunk, int off, + size_t size) +{ +} + +static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size) +{ +} +#endif /* CONFIG_MEMCG_KMEM */ + +/** + * pcpu_alloc - the percpu allocator + * @size: size of area to allocate in bytes + * @align: alignment of area (max PAGE_SIZE) + * @reserved: allocate from the reserved chunk if available + * @gfp: allocation flags + * + * Allocate percpu area of @size bytes aligned at @align. If @gfp doesn't + * contain %GFP_KERNEL, the allocation is atomic. If @gfp has __GFP_NOWARN + * then no warning will be triggered on invalid or failed allocation + * requests. + * + * RETURNS: + * Percpu pointer to the allocated area on success, NULL on failure. + */ +static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved, + gfp_t gfp) +{ + gfp_t pcpu_gfp; + bool is_atomic; + bool do_warn; + enum pcpu_chunk_type type; + struct list_head *pcpu_slot; + struct obj_cgroup *objcg = NULL; + static int warn_limit = 10; + struct pcpu_chunk *chunk, *next; + const char *err; + int slot, off, cpu, ret; + unsigned long flags; + void __percpu *ptr; + size_t bits, bit_align; + + gfp = current_gfp_context(gfp); + /* whitelisted flags that can be passed to the backing allocators */ + pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); + is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL; + do_warn = !(gfp & __GFP_NOWARN); + + /* + * There is now a minimum allocation size of PCPU_MIN_ALLOC_SIZE, + * therefore alignment must be a minimum of that many bytes. + * An allocation may have internal fragmentation from rounding up + * of up to PCPU_MIN_ALLOC_SIZE - 1 bytes. + */ + if (unlikely(align < PCPU_MIN_ALLOC_SIZE)) + align = PCPU_MIN_ALLOC_SIZE; + + size = ALIGN(size, PCPU_MIN_ALLOC_SIZE); + bits = size >> PCPU_MIN_ALLOC_SHIFT; + bit_align = align >> PCPU_MIN_ALLOC_SHIFT; + + if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE || + !is_power_of_2(align))) { + WARN(do_warn, "illegal size (%zu) or align (%zu) for percpu allocation\n", + size, align); + return NULL; + } + + type = pcpu_memcg_pre_alloc_hook(size, gfp, &objcg); + if (unlikely(type == PCPU_FAIL_ALLOC)) + return NULL; + pcpu_slot = pcpu_chunk_list(type); + + if (!is_atomic) { + /* + * pcpu_balance_workfn() allocates memory under this mutex, + * and it may wait for memory reclaim. Allow current task + * to become OOM victim, in case of memory pressure. + */ + if (gfp & __GFP_NOFAIL) { + mutex_lock(&pcpu_alloc_mutex); + } else if (mutex_lock_killable(&pcpu_alloc_mutex)) { + pcpu_memcg_post_alloc_hook(objcg, NULL, 0, size); + return NULL; + } + } + + spin_lock_irqsave(&pcpu_lock, flags); + + /* serve reserved allocations from the reserved chunk if available */ + if (reserved && pcpu_reserved_chunk) { + chunk = pcpu_reserved_chunk; + + off = pcpu_find_block_fit(chunk, bits, bit_align, is_atomic); + if (off < 0) { + err = "alloc from reserved chunk failed"; + goto fail_unlock; + } + + off = pcpu_alloc_area(chunk, bits, bit_align, off); + if (off >= 0) + goto area_found; + + err = "alloc from reserved chunk failed"; + goto fail_unlock; + } + +restart: + /* search through normal chunks */ + for (slot = pcpu_size_to_slot(size); slot < pcpu_nr_slots; slot++) { + list_for_each_entry_safe(chunk, next, &pcpu_slot[slot], list) { + off = pcpu_find_block_fit(chunk, bits, bit_align, + is_atomic); + if (off < 0) { + if (slot < PCPU_SLOT_FAIL_THRESHOLD) + pcpu_chunk_move(chunk, 0); + continue; + } + + off = pcpu_alloc_area(chunk, bits, bit_align, off); + if (off >= 0) + goto area_found; + + } + } + + spin_unlock_irqrestore(&pcpu_lock, flags); + + /* + * No space left. Create a new chunk. We don't want multiple + * tasks to create chunks simultaneously. Serialize and create iff + * there's still no empty chunk after grabbing the mutex. + */ + if (is_atomic) { + err = "atomic alloc failed, no space left"; + goto fail; + } + + if (list_empty(&pcpu_slot[pcpu_nr_slots - 1])) { + chunk = pcpu_create_chunk(type, pcpu_gfp); + if (!chunk) { + err = "failed to allocate new chunk"; + goto fail; + } + + spin_lock_irqsave(&pcpu_lock, flags); + pcpu_chunk_relocate(chunk, -1); + } else { + spin_lock_irqsave(&pcpu_lock, flags); + } + + goto restart; + +area_found: + pcpu_stats_area_alloc(chunk, size); + spin_unlock_irqrestore(&pcpu_lock, flags); + + /* populate if not all pages are already there */ + if (!is_atomic) { + unsigned int page_start, page_end, rs, re; + + page_start = PFN_DOWN(off); + page_end = PFN_UP(off + size); + + bitmap_for_each_clear_region(chunk->populated, rs, re, + page_start, page_end) { + WARN_ON(chunk->immutable); + + ret = pcpu_populate_chunk(chunk, rs, re, pcpu_gfp); + + spin_lock_irqsave(&pcpu_lock, flags); + if (ret) { + pcpu_free_area(chunk, off); + err = "failed to populate"; + goto fail_unlock; + } + pcpu_chunk_populated(chunk, rs, re); + spin_unlock_irqrestore(&pcpu_lock, flags); + } + + mutex_unlock(&pcpu_alloc_mutex); + } + + if (pcpu_nr_empty_pop_pages[type] < PCPU_EMPTY_POP_PAGES_LOW) + pcpu_schedule_balance_work(); + + /* clear the areas and return address relative to base address */ + for_each_possible_cpu(cpu) + memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size); + + ptr = __addr_to_pcpu_ptr(chunk->base_addr + off); + kmemleak_alloc_percpu(ptr, size, gfp); + + trace_percpu_alloc_percpu(reserved, is_atomic, size, align, + chunk->base_addr, off, ptr); + + pcpu_memcg_post_alloc_hook(objcg, chunk, off, size); + + return ptr; + +fail_unlock: + spin_unlock_irqrestore(&pcpu_lock, flags); +fail: + trace_percpu_alloc_percpu_fail(reserved, is_atomic, size, align); + + if (!is_atomic && do_warn && warn_limit) { + pr_warn("allocation failed, size=%zu align=%zu atomic=%d, %s\n", + size, align, is_atomic, err); + dump_stack(); + if (!--warn_limit) + pr_info("limit reached, disable warning\n"); + } + if (is_atomic) { + /* see the flag handling in pcpu_blance_workfn() */ + pcpu_atomic_alloc_failed = true; + pcpu_schedule_balance_work(); + } else { + mutex_unlock(&pcpu_alloc_mutex); + } + + pcpu_memcg_post_alloc_hook(objcg, NULL, 0, size); + + return NULL; +} + +/** + * __alloc_percpu_gfp - allocate dynamic percpu area + * @size: size of area to allocate in bytes + * @align: alignment of area (max PAGE_SIZE) + * @gfp: allocation flags + * + * Allocate zero-filled percpu area of @size bytes aligned at @align. If + * @gfp doesn't contain %GFP_KERNEL, the allocation doesn't block and can + * be called from any context but is a lot more likely to fail. If @gfp + * has __GFP_NOWARN then no warning will be triggered on invalid or failed + * allocation requests. + * + * RETURNS: + * Percpu pointer to the allocated area on success, NULL on failure. + */ +void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp) +{ + return pcpu_alloc(size, align, false, gfp); +} +EXPORT_SYMBOL_GPL(__alloc_percpu_gfp); + +/** + * __alloc_percpu - allocate dynamic percpu area + * @size: size of area to allocate in bytes + * @align: alignment of area (max PAGE_SIZE) + * + * Equivalent to __alloc_percpu_gfp(size, align, %GFP_KERNEL). + */ +void __percpu *__alloc_percpu(size_t size, size_t align) +{ + return pcpu_alloc(size, align, false, GFP_KERNEL); +} +EXPORT_SYMBOL_GPL(__alloc_percpu); + +/** + * __alloc_reserved_percpu - allocate reserved percpu area + * @size: size of area to allocate in bytes + * @align: alignment of area (max PAGE_SIZE) + * + * Allocate zero-filled percpu area of @size bytes aligned at @align + * from reserved percpu area if arch has set it up; otherwise, + * allocation is served from the same dynamic area. Might sleep. + * Might trigger writeouts. + * + * CONTEXT: + * Does GFP_KERNEL allocation. + * + * RETURNS: + * Percpu pointer to the allocated area on success, NULL on failure. + */ +void __percpu *__alloc_reserved_percpu(size_t size, size_t align) +{ + return pcpu_alloc(size, align, true, GFP_KERNEL); +} + +/** + * __pcpu_balance_workfn - manage the amount of free chunks and populated pages + * @type: chunk type + * + * Reclaim all fully free chunks except for the first one. This is also + * responsible for maintaining the pool of empty populated pages. However, + * it is possible that this is called when physical memory is scarce causing + * OOM killer to be triggered. We should avoid doing so until an actual + * allocation causes the failure as it is possible that requests can be + * serviced from already backed regions. + */ +static void __pcpu_balance_workfn(enum pcpu_chunk_type type) +{ + /* gfp flags passed to underlying allocators */ + const gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; + LIST_HEAD(to_free); + struct list_head *pcpu_slot = pcpu_chunk_list(type); + struct list_head *free_head = &pcpu_slot[pcpu_nr_slots - 1]; + struct pcpu_chunk *chunk, *next; + int slot, nr_to_pop, ret; + + /* + * There's no reason to keep around multiple unused chunks and VM + * areas can be scarce. Destroy all free chunks except for one. + */ + mutex_lock(&pcpu_alloc_mutex); + spin_lock_irq(&pcpu_lock); + + list_for_each_entry_safe(chunk, next, free_head, list) { + WARN_ON(chunk->immutable); + + /* spare the first one */ + if (chunk == list_first_entry(free_head, struct pcpu_chunk, list)) + continue; + + list_move(&chunk->list, &to_free); + } + + spin_unlock_irq(&pcpu_lock); + + list_for_each_entry_safe(chunk, next, &to_free, list) { + unsigned int rs, re; + + bitmap_for_each_set_region(chunk->populated, rs, re, 0, + chunk->nr_pages) { + pcpu_depopulate_chunk(chunk, rs, re); + spin_lock_irq(&pcpu_lock); + pcpu_chunk_depopulated(chunk, rs, re); + spin_unlock_irq(&pcpu_lock); + } + pcpu_destroy_chunk(chunk); + cond_resched(); + } + + /* + * Ensure there are certain number of free populated pages for + * atomic allocs. Fill up from the most packed so that atomic + * allocs don't increase fragmentation. If atomic allocation + * failed previously, always populate the maximum amount. This + * should prevent atomic allocs larger than PAGE_SIZE from keeping + * failing indefinitely; however, large atomic allocs are not + * something we support properly and can be highly unreliable and + * inefficient. + */ +retry_pop: + if (pcpu_atomic_alloc_failed) { + nr_to_pop = PCPU_EMPTY_POP_PAGES_HIGH; + /* best effort anyway, don't worry about synchronization */ + pcpu_atomic_alloc_failed = false; + } else { + nr_to_pop = clamp(PCPU_EMPTY_POP_PAGES_HIGH - + pcpu_nr_empty_pop_pages[type], + 0, PCPU_EMPTY_POP_PAGES_HIGH); + } + + for (slot = pcpu_size_to_slot(PAGE_SIZE); slot < pcpu_nr_slots; slot++) { + unsigned int nr_unpop = 0, rs, re; + + if (!nr_to_pop) + break; + + spin_lock_irq(&pcpu_lock); + list_for_each_entry(chunk, &pcpu_slot[slot], list) { + nr_unpop = chunk->nr_pages - chunk->nr_populated; + if (nr_unpop) + break; + } + spin_unlock_irq(&pcpu_lock); + + if (!nr_unpop) + continue; + + /* @chunk can't go away while pcpu_alloc_mutex is held */ + bitmap_for_each_clear_region(chunk->populated, rs, re, 0, + chunk->nr_pages) { + int nr = min_t(int, re - rs, nr_to_pop); + + ret = pcpu_populate_chunk(chunk, rs, rs + nr, gfp); + if (!ret) { + nr_to_pop -= nr; + spin_lock_irq(&pcpu_lock); + pcpu_chunk_populated(chunk, rs, rs + nr); + spin_unlock_irq(&pcpu_lock); + } else { + nr_to_pop = 0; + } + + if (!nr_to_pop) + break; + } + } + + if (nr_to_pop) { + /* ran out of chunks to populate, create a new one and retry */ + chunk = pcpu_create_chunk(type, gfp); + if (chunk) { + spin_lock_irq(&pcpu_lock); + pcpu_chunk_relocate(chunk, -1); + spin_unlock_irq(&pcpu_lock); + goto retry_pop; + } + } + + mutex_unlock(&pcpu_alloc_mutex); +} + +/** + * pcpu_balance_workfn - manage the amount of free chunks and populated pages + * @work: unused + * + * Call __pcpu_balance_workfn() for each chunk type. + */ +static void pcpu_balance_workfn(struct work_struct *work) +{ + enum pcpu_chunk_type type; + + for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++) + __pcpu_balance_workfn(type); +} + +/** + * free_percpu - free percpu area + * @ptr: pointer to area to free + * + * Free percpu area @ptr. + * + * CONTEXT: + * Can be called from atomic context. + */ +void free_percpu(void __percpu *ptr) +{ + void *addr; + struct pcpu_chunk *chunk; + unsigned long flags; + int size, off; + bool need_balance = false; + struct list_head *pcpu_slot; + + if (!ptr) + return; + + kmemleak_free_percpu(ptr); + + addr = __pcpu_ptr_to_addr(ptr); + + spin_lock_irqsave(&pcpu_lock, flags); + + chunk = pcpu_chunk_addr_search(addr); + off = addr - chunk->base_addr; + + size = pcpu_free_area(chunk, off); + + pcpu_slot = pcpu_chunk_list(pcpu_chunk_type(chunk)); + + pcpu_memcg_free_hook(chunk, off, size); + + /* if there are more than one fully free chunks, wake up grim reaper */ + if (chunk->free_bytes == pcpu_unit_size) { + struct pcpu_chunk *pos; + + list_for_each_entry(pos, &pcpu_slot[pcpu_nr_slots - 1], list) + if (pos != chunk) { + need_balance = true; + break; + } + } + + trace_percpu_free_percpu(chunk->base_addr, off, ptr); + + spin_unlock_irqrestore(&pcpu_lock, flags); + + if (need_balance) + pcpu_schedule_balance_work(); +} +EXPORT_SYMBOL_GPL(free_percpu); + +bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr) +{ +#ifdef CONFIG_SMP + const size_t static_size = __per_cpu_end - __per_cpu_start; + void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr); + unsigned int cpu; + + for_each_possible_cpu(cpu) { + void *start = per_cpu_ptr(base, cpu); + void *va = (void *)addr; + + if (va >= start && va < start + static_size) { + if (can_addr) { + *can_addr = (unsigned long) (va - start); + *can_addr += (unsigned long) + per_cpu_ptr(base, get_boot_cpu_id()); + } + return true; + } + } +#endif + /* on UP, can't distinguish from other static vars, always false */ + return false; +} + +/** + * is_kernel_percpu_address - test whether address is from static percpu area + * @addr: address to test + * + * Test whether @addr belongs to in-kernel static percpu area. Module + * static percpu areas are not considered. For those, use + * is_module_percpu_address(). + * + * RETURNS: + * %true if @addr is from in-kernel static percpu area, %false otherwise. + */ +bool is_kernel_percpu_address(unsigned long addr) +{ + return __is_kernel_percpu_address(addr, NULL); +} + +/** + * per_cpu_ptr_to_phys - convert translated percpu address to physical address + * @addr: the address to be converted to physical address + * + * Given @addr which is dereferenceable address obtained via one of + * percpu access macros, this function translates it into its physical + * address. The caller is responsible for ensuring @addr stays valid + * until this function finishes. + * + * percpu allocator has special setup for the first chunk, which currently + * supports either embedding in linear address space or vmalloc mapping, + * and, from the second one, the backing allocator (currently either vm or + * km) provides translation. + * + * The addr can be translated simply without checking if it falls into the + * first chunk. But the current code reflects better how percpu allocator + * actually works, and the verification can discover both bugs in percpu + * allocator itself and per_cpu_ptr_to_phys() callers. So we keep current + * code. + * + * RETURNS: + * The physical address for @addr. + */ +phys_addr_t per_cpu_ptr_to_phys(void *addr) +{ + void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr); + bool in_first_chunk = false; + unsigned long first_low, first_high; + unsigned int cpu; + + /* + * The following test on unit_low/high isn't strictly + * necessary but will speed up lookups of addresses which + * aren't in the first chunk. + * + * The address check is against full chunk sizes. pcpu_base_addr + * points to the beginning of the first chunk including the + * static region. Assumes good intent as the first chunk may + * not be full (ie. < pcpu_unit_pages in size). + */ + first_low = (unsigned long)pcpu_base_addr + + pcpu_unit_page_offset(pcpu_low_unit_cpu, 0); + first_high = (unsigned long)pcpu_base_addr + + pcpu_unit_page_offset(pcpu_high_unit_cpu, pcpu_unit_pages); + if ((unsigned long)addr >= first_low && + (unsigned long)addr < first_high) { + for_each_possible_cpu(cpu) { + void *start = per_cpu_ptr(base, cpu); + + if (addr >= start && addr < start + pcpu_unit_size) { + in_first_chunk = true; + break; + } + } + } + + if (in_first_chunk) { + if (!is_vmalloc_addr(addr)) + return __pa(addr); + else + return page_to_phys(vmalloc_to_page(addr)) + + offset_in_page(addr); + } else + return page_to_phys(pcpu_addr_to_page(addr)) + + offset_in_page(addr); +} + +/** + * pcpu_alloc_alloc_info - allocate percpu allocation info + * @nr_groups: the number of groups + * @nr_units: the number of units + * + * Allocate ai which is large enough for @nr_groups groups containing + * @nr_units units. The returned ai's groups[0].cpu_map points to the + * cpu_map array which is long enough for @nr_units and filled with + * NR_CPUS. It's the caller's responsibility to initialize cpu_map + * pointer of other groups. + * + * RETURNS: + * Pointer to the allocated pcpu_alloc_info on success, NULL on + * failure. + */ +struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, + int nr_units) +{ + struct pcpu_alloc_info *ai; + size_t base_size, ai_size; + void *ptr; + int unit; + + base_size = ALIGN(struct_size(ai, groups, nr_groups), + __alignof__(ai->groups[0].cpu_map[0])); + ai_size = base_size + nr_units * sizeof(ai->groups[0].cpu_map[0]); + + ptr = memblock_alloc(PFN_ALIGN(ai_size), PAGE_SIZE); + if (!ptr) + return NULL; + ai = ptr; + ptr += base_size; + + ai->groups[0].cpu_map = ptr; + + for (unit = 0; unit < nr_units; unit++) + ai->groups[0].cpu_map[unit] = NR_CPUS; + + ai->nr_groups = nr_groups; + ai->__ai_size = PFN_ALIGN(ai_size); + + return ai; +} + +/** + * pcpu_free_alloc_info - free percpu allocation info + * @ai: pcpu_alloc_info to free + * + * Free @ai which was allocated by pcpu_alloc_alloc_info(). + */ +void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai) +{ + memblock_free_early(__pa(ai), ai->__ai_size); +} + +/** + * pcpu_dump_alloc_info - print out information about pcpu_alloc_info + * @lvl: loglevel + * @ai: allocation info to dump + * + * Print out information about @ai using loglevel @lvl. + */ +static void pcpu_dump_alloc_info(const char *lvl, + const struct pcpu_alloc_info *ai) +{ + int group_width = 1, cpu_width = 1, width; + char empty_str[] = "--------"; + int alloc = 0, alloc_end = 0; + int group, v; + int upa, apl; /* units per alloc, allocs per line */ + + v = ai->nr_groups; + while (v /= 10) + group_width++; + + v = num_possible_cpus(); + while (v /= 10) + cpu_width++; + empty_str[min_t(int, cpu_width, sizeof(empty_str) - 1)] = '\0'; + + upa = ai->alloc_size / ai->unit_size; + width = upa * (cpu_width + 1) + group_width + 3; + apl = rounddown_pow_of_two(max(60 / width, 1)); + + printk("%spcpu-alloc: s%zu r%zu d%zu u%zu alloc=%zu*%zu", + lvl, ai->static_size, ai->reserved_size, ai->dyn_size, + ai->unit_size, ai->alloc_size / ai->atom_size, ai->atom_size); + + for (group = 0; group < ai->nr_groups; group++) { + const struct pcpu_group_info *gi = &ai->groups[group]; + int unit = 0, unit_end = 0; + + BUG_ON(gi->nr_units % upa); + for (alloc_end += gi->nr_units / upa; + alloc < alloc_end; alloc++) { + if (!(alloc % apl)) { + pr_cont("\n"); + printk("%spcpu-alloc: ", lvl); + } + pr_cont("[%0*d] ", group_width, group); + + for (unit_end += upa; unit < unit_end; unit++) + if (gi->cpu_map[unit] != NR_CPUS) + pr_cont("%0*d ", + cpu_width, gi->cpu_map[unit]); + else + pr_cont("%s ", empty_str); + } + } + pr_cont("\n"); +} + +/** + * pcpu_setup_first_chunk - initialize the first percpu chunk + * @ai: pcpu_alloc_info describing how to percpu area is shaped + * @base_addr: mapped address + * + * Initialize the first percpu chunk which contains the kernel static + * percpu area. This function is to be called from arch percpu area + * setup path. + * + * @ai contains all information necessary to initialize the first + * chunk and prime the dynamic percpu allocator. + * + * @ai->static_size is the size of static percpu area. + * + * @ai->reserved_size, if non-zero, specifies the amount of bytes to + * reserve after the static area in the first chunk. This reserves + * the first chunk such that it's available only through reserved + * percpu allocation. This is primarily used to serve module percpu + * static areas on architectures where the addressing model has + * limited offset range for symbol relocations to guarantee module + * percpu symbols fall inside the relocatable range. + * + * @ai->dyn_size determines the number of bytes available for dynamic + * allocation in the first chunk. The area between @ai->static_size + + * @ai->reserved_size + @ai->dyn_size and @ai->unit_size is unused. + * + * @ai->unit_size specifies unit size and must be aligned to PAGE_SIZE + * and equal to or larger than @ai->static_size + @ai->reserved_size + + * @ai->dyn_size. + * + * @ai->atom_size is the allocation atom size and used as alignment + * for vm areas. + * + * @ai->alloc_size is the allocation size and always multiple of + * @ai->atom_size. This is larger than @ai->atom_size if + * @ai->unit_size is larger than @ai->atom_size. + * + * @ai->nr_groups and @ai->groups describe virtual memory layout of + * percpu areas. Units which should be colocated are put into the + * same group. Dynamic VM areas will be allocated according to these + * groupings. If @ai->nr_groups is zero, a single group containing + * all units is assumed. + * + * The caller should have mapped the first chunk at @base_addr and + * copied static data to each unit. + * + * The first chunk will always contain a static and a dynamic region. + * However, the static region is not managed by any chunk. If the first + * chunk also contains a reserved region, it is served by two chunks - + * one for the reserved region and one for the dynamic region. They + * share the same vm, but use offset regions in the area allocation map. + * The chunk serving the dynamic region is circulated in the chunk slots + * and available for dynamic allocation like any other chunk. + */ +void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, + void *base_addr) +{ + size_t size_sum = ai->static_size + ai->reserved_size + ai->dyn_size; + size_t static_size, dyn_size; + struct pcpu_chunk *chunk; + unsigned long *group_offsets; + size_t *group_sizes; + unsigned long *unit_off; + unsigned int cpu; + int *unit_map; + int group, unit, i; + int map_size; + unsigned long tmp_addr; + size_t alloc_size; + enum pcpu_chunk_type type; + +#define PCPU_SETUP_BUG_ON(cond) do { \ + if (unlikely(cond)) { \ + pr_emerg("failed to initialize, %s\n", #cond); \ + pr_emerg("cpu_possible_mask=%*pb\n", \ + cpumask_pr_args(cpu_possible_mask)); \ + pcpu_dump_alloc_info(KERN_EMERG, ai); \ + BUG(); \ + } \ +} while (0) + + /* sanity checks */ + PCPU_SETUP_BUG_ON(ai->nr_groups <= 0); +#ifdef CONFIG_SMP + PCPU_SETUP_BUG_ON(!ai->static_size); + PCPU_SETUP_BUG_ON(offset_in_page(__per_cpu_start)); +#endif + PCPU_SETUP_BUG_ON(!base_addr); + PCPU_SETUP_BUG_ON(offset_in_page(base_addr)); + PCPU_SETUP_BUG_ON(ai->unit_size < size_sum); + PCPU_SETUP_BUG_ON(offset_in_page(ai->unit_size)); + PCPU_SETUP_BUG_ON(ai->unit_size < PCPU_MIN_UNIT_SIZE); + PCPU_SETUP_BUG_ON(!IS_ALIGNED(ai->unit_size, PCPU_BITMAP_BLOCK_SIZE)); + PCPU_SETUP_BUG_ON(ai->dyn_size < PERCPU_DYNAMIC_EARLY_SIZE); + PCPU_SETUP_BUG_ON(!ai->dyn_size); + PCPU_SETUP_BUG_ON(!IS_ALIGNED(ai->reserved_size, PCPU_MIN_ALLOC_SIZE)); + PCPU_SETUP_BUG_ON(!(IS_ALIGNED(PCPU_BITMAP_BLOCK_SIZE, PAGE_SIZE) || + IS_ALIGNED(PAGE_SIZE, PCPU_BITMAP_BLOCK_SIZE))); + PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0); + + /* process group information and build config tables accordingly */ + alloc_size = ai->nr_groups * sizeof(group_offsets[0]); + group_offsets = memblock_alloc(alloc_size, SMP_CACHE_BYTES); + if (!group_offsets) + panic("%s: Failed to allocate %zu bytes\n", __func__, + alloc_size); + + alloc_size = ai->nr_groups * sizeof(group_sizes[0]); + group_sizes = memblock_alloc(alloc_size, SMP_CACHE_BYTES); + if (!group_sizes) + panic("%s: Failed to allocate %zu bytes\n", __func__, + alloc_size); + + alloc_size = nr_cpu_ids * sizeof(unit_map[0]); + unit_map = memblock_alloc(alloc_size, SMP_CACHE_BYTES); + if (!unit_map) + panic("%s: Failed to allocate %zu bytes\n", __func__, + alloc_size); + + alloc_size = nr_cpu_ids * sizeof(unit_off[0]); + unit_off = memblock_alloc(alloc_size, SMP_CACHE_BYTES); + if (!unit_off) + panic("%s: Failed to allocate %zu bytes\n", __func__, + alloc_size); + + for (cpu = 0; cpu < nr_cpu_ids; cpu++) + unit_map[cpu] = UINT_MAX; + + pcpu_low_unit_cpu = NR_CPUS; + pcpu_high_unit_cpu = NR_CPUS; + + for (group = 0, unit = 0; group < ai->nr_groups; group++, unit += i) { + const struct pcpu_group_info *gi = &ai->groups[group]; + + group_offsets[group] = gi->base_offset; + group_sizes[group] = gi->nr_units * ai->unit_size; + + for (i = 0; i < gi->nr_units; i++) { + cpu = gi->cpu_map[i]; + if (cpu == NR_CPUS) + continue; + + PCPU_SETUP_BUG_ON(cpu >= nr_cpu_ids); + PCPU_SETUP_BUG_ON(!cpu_possible(cpu)); + PCPU_SETUP_BUG_ON(unit_map[cpu] != UINT_MAX); + + unit_map[cpu] = unit + i; + unit_off[cpu] = gi->base_offset + i * ai->unit_size; + + /* determine low/high unit_cpu */ + if (pcpu_low_unit_cpu == NR_CPUS || + unit_off[cpu] < unit_off[pcpu_low_unit_cpu]) + pcpu_low_unit_cpu = cpu; + if (pcpu_high_unit_cpu == NR_CPUS || + unit_off[cpu] > unit_off[pcpu_high_unit_cpu]) + pcpu_high_unit_cpu = cpu; + } + } + pcpu_nr_units = unit; + + for_each_possible_cpu(cpu) + PCPU_SETUP_BUG_ON(unit_map[cpu] == UINT_MAX); + + /* we're done parsing the input, undefine BUG macro and dump config */ +#undef PCPU_SETUP_BUG_ON + pcpu_dump_alloc_info(KERN_DEBUG, ai); + + pcpu_nr_groups = ai->nr_groups; + pcpu_group_offsets = group_offsets; + pcpu_group_sizes = group_sizes; + pcpu_unit_map = unit_map; + pcpu_unit_offsets = unit_off; + + /* determine basic parameters */ + pcpu_unit_pages = ai->unit_size >> PAGE_SHIFT; + pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT; + pcpu_atom_size = ai->atom_size; + pcpu_chunk_struct_size = struct_size(chunk, populated, + BITS_TO_LONGS(pcpu_unit_pages)); + + pcpu_stats_save_ai(ai); + + /* + * Allocate chunk slots. The additional last slot is for + * empty chunks. + */ + pcpu_nr_slots = __pcpu_size_to_slot(pcpu_unit_size) + 2; + pcpu_chunk_lists = memblock_alloc(pcpu_nr_slots * + sizeof(pcpu_chunk_lists[0]) * + PCPU_NR_CHUNK_TYPES, + SMP_CACHE_BYTES); + if (!pcpu_chunk_lists) + panic("%s: Failed to allocate %zu bytes\n", __func__, + pcpu_nr_slots * sizeof(pcpu_chunk_lists[0]) * + PCPU_NR_CHUNK_TYPES); + + for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++) + for (i = 0; i < pcpu_nr_slots; i++) + INIT_LIST_HEAD(&pcpu_chunk_list(type)[i]); + + /* + * The end of the static region needs to be aligned with the + * minimum allocation size as this offsets the reserved and + * dynamic region. The first chunk ends page aligned by + * expanding the dynamic region, therefore the dynamic region + * can be shrunk to compensate while still staying above the + * configured sizes. + */ + static_size = ALIGN(ai->static_size, PCPU_MIN_ALLOC_SIZE); + dyn_size = ai->dyn_size - (static_size - ai->static_size); + + /* + * Initialize first chunk. + * If the reserved_size is non-zero, this initializes the reserved + * chunk. If the reserved_size is zero, the reserved chunk is NULL + * and the dynamic region is initialized here. The first chunk, + * pcpu_first_chunk, will always point to the chunk that serves + * the dynamic region. + */ + tmp_addr = (unsigned long)base_addr + static_size; + map_size = ai->reserved_size ?: dyn_size; + chunk = pcpu_alloc_first_chunk(tmp_addr, map_size); + + /* init dynamic chunk if necessary */ + if (ai->reserved_size) { + pcpu_reserved_chunk = chunk; + + tmp_addr = (unsigned long)base_addr + static_size + + ai->reserved_size; + map_size = dyn_size; + chunk = pcpu_alloc_first_chunk(tmp_addr, map_size); + } + + /* link the first chunk in */ + pcpu_first_chunk = chunk; + pcpu_nr_empty_pop_pages[PCPU_CHUNK_ROOT] = pcpu_first_chunk->nr_empty_pop_pages; + pcpu_chunk_relocate(pcpu_first_chunk, -1); + + /* include all regions of the first chunk */ + pcpu_nr_populated += PFN_DOWN(size_sum); + + pcpu_stats_chunk_alloc(); + trace_percpu_create_chunk(base_addr); + + /* we're done */ + pcpu_base_addr = base_addr; +} + +#ifdef CONFIG_SMP + +const char * const pcpu_fc_names[PCPU_FC_NR] __initconst = { + [PCPU_FC_AUTO] = "auto", + [PCPU_FC_EMBED] = "embed", + [PCPU_FC_PAGE] = "page", +}; + +enum pcpu_fc pcpu_chosen_fc __initdata = PCPU_FC_AUTO; + +static int __init percpu_alloc_setup(char *str) +{ + if (!str) + return -EINVAL; + + if (0) + /* nada */; +#ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK + else if (!strcmp(str, "embed")) + pcpu_chosen_fc = PCPU_FC_EMBED; +#endif +#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK + else if (!strcmp(str, "page")) + pcpu_chosen_fc = PCPU_FC_PAGE; +#endif + else + pr_warn("unknown allocator %s specified\n", str); + + return 0; +} +early_param("percpu_alloc", percpu_alloc_setup); + +/* + * pcpu_embed_first_chunk() is used by the generic percpu setup. + * Build it if needed by the arch config or the generic setup is going + * to be used. + */ +#if defined(CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK) || \ + !defined(CONFIG_HAVE_SETUP_PER_CPU_AREA) +#define BUILD_EMBED_FIRST_CHUNK +#endif + +/* build pcpu_page_first_chunk() iff needed by the arch config */ +#if defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK) +#define BUILD_PAGE_FIRST_CHUNK +#endif + +/* pcpu_build_alloc_info() is used by both embed and page first chunk */ +#if defined(BUILD_EMBED_FIRST_CHUNK) || defined(BUILD_PAGE_FIRST_CHUNK) +/** + * pcpu_build_alloc_info - build alloc_info considering distances between CPUs + * @reserved_size: the size of reserved percpu area in bytes + * @dyn_size: minimum free size for dynamic allocation in bytes + * @atom_size: allocation atom size + * @cpu_distance_fn: callback to determine distance between cpus, optional + * + * This function determines grouping of units, their mappings to cpus + * and other parameters considering needed percpu size, allocation + * atom size and distances between CPUs. + * + * Groups are always multiples of atom size and CPUs which are of + * LOCAL_DISTANCE both ways are grouped together and share space for + * units in the same group. The returned configuration is guaranteed + * to have CPUs on different nodes on different groups and >=75% usage + * of allocated virtual address space. + * + * RETURNS: + * On success, pointer to the new allocation_info is returned. On + * failure, ERR_PTR value is returned. + */ +static struct pcpu_alloc_info * __init pcpu_build_alloc_info( + size_t reserved_size, size_t dyn_size, + size_t atom_size, + pcpu_fc_cpu_distance_fn_t cpu_distance_fn) +{ + static int group_map[NR_CPUS] __initdata; + static int group_cnt[NR_CPUS] __initdata; + const size_t static_size = __per_cpu_end - __per_cpu_start; + int nr_groups = 1, nr_units = 0; + size_t size_sum, min_unit_size, alloc_size; + int upa, max_upa, best_upa; /* units_per_alloc */ + int last_allocs, group, unit; + unsigned int cpu, tcpu; + struct pcpu_alloc_info *ai; + unsigned int *cpu_map; + + /* this function may be called multiple times */ + memset(group_map, 0, sizeof(group_map)); + memset(group_cnt, 0, sizeof(group_cnt)); + + /* calculate size_sum and ensure dyn_size is enough for early alloc */ + size_sum = PFN_ALIGN(static_size + reserved_size + + max_t(size_t, dyn_size, PERCPU_DYNAMIC_EARLY_SIZE)); + dyn_size = size_sum - static_size - reserved_size; + + /* + * Determine min_unit_size, alloc_size and max_upa such that + * alloc_size is multiple of atom_size and is the smallest + * which can accommodate 4k aligned segments which are equal to + * or larger than min_unit_size. + */ + min_unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE); + + /* determine the maximum # of units that can fit in an allocation */ + alloc_size = roundup(min_unit_size, atom_size); + upa = alloc_size / min_unit_size; + while (alloc_size % upa || (offset_in_page(alloc_size / upa))) + upa--; + max_upa = upa; + + /* group cpus according to their proximity */ + for_each_possible_cpu(cpu) { + group = 0; + next_group: + for_each_possible_cpu(tcpu) { + if (cpu == tcpu) + break; + if (group_map[tcpu] == group && cpu_distance_fn && + (cpu_distance_fn(cpu, tcpu) > LOCAL_DISTANCE || + cpu_distance_fn(tcpu, cpu) > LOCAL_DISTANCE)) { + group++; + nr_groups = max(nr_groups, group + 1); + goto next_group; + } + } + group_map[cpu] = group; + group_cnt[group]++; + } + + /* + * Wasted space is caused by a ratio imbalance of upa to group_cnt. + * Expand the unit_size until we use >= 75% of the units allocated. + * Related to atom_size, which could be much larger than the unit_size. + */ + last_allocs = INT_MAX; + for (upa = max_upa; upa; upa--) { + int allocs = 0, wasted = 0; + + if (alloc_size % upa || (offset_in_page(alloc_size / upa))) + continue; + + for (group = 0; group < nr_groups; group++) { + int this_allocs = DIV_ROUND_UP(group_cnt[group], upa); + allocs += this_allocs; + wasted += this_allocs * upa - group_cnt[group]; + } + + /* + * Don't accept if wastage is over 1/3. The + * greater-than comparison ensures upa==1 always + * passes the following check. + */ + if (wasted > num_possible_cpus() / 3) + continue; + + /* and then don't consume more memory */ + if (allocs > last_allocs) + break; + last_allocs = allocs; + best_upa = upa; + } + upa = best_upa; + + /* allocate and fill alloc_info */ + for (group = 0; group < nr_groups; group++) + nr_units += roundup(group_cnt[group], upa); + + ai = pcpu_alloc_alloc_info(nr_groups, nr_units); + if (!ai) + return ERR_PTR(-ENOMEM); + cpu_map = ai->groups[0].cpu_map; + + for (group = 0; group < nr_groups; group++) { + ai->groups[group].cpu_map = cpu_map; + cpu_map += roundup(group_cnt[group], upa); + } + + ai->static_size = static_size; + ai->reserved_size = reserved_size; + ai->dyn_size = dyn_size; + ai->unit_size = alloc_size / upa; + ai->atom_size = atom_size; + ai->alloc_size = alloc_size; + + for (group = 0, unit = 0; group < nr_groups; group++) { + struct pcpu_group_info *gi = &ai->groups[group]; + + /* + * Initialize base_offset as if all groups are located + * back-to-back. The caller should update this to + * reflect actual allocation. + */ + gi->base_offset = unit * ai->unit_size; + + for_each_possible_cpu(cpu) + if (group_map[cpu] == group) + gi->cpu_map[gi->nr_units++] = cpu; + gi->nr_units = roundup(gi->nr_units, upa); + unit += gi->nr_units; + } + BUG_ON(unit != nr_units); + + return ai; +} +#endif /* BUILD_EMBED_FIRST_CHUNK || BUILD_PAGE_FIRST_CHUNK */ + +#if defined(BUILD_EMBED_FIRST_CHUNK) +/** + * pcpu_embed_first_chunk - embed the first percpu chunk into bootmem + * @reserved_size: the size of reserved percpu area in bytes + * @dyn_size: minimum free size for dynamic allocation in bytes + * @atom_size: allocation atom size + * @cpu_distance_fn: callback to determine distance between cpus, optional + * @alloc_fn: function to allocate percpu page + * @free_fn: function to free percpu page + * + * This is a helper to ease setting up embedded first percpu chunk and + * can be called where pcpu_setup_first_chunk() is expected. + * + * If this function is used to setup the first chunk, it is allocated + * by calling @alloc_fn and used as-is without being mapped into + * vmalloc area. Allocations are always whole multiples of @atom_size + * aligned to @atom_size. + * + * This enables the first chunk to piggy back on the linear physical + * mapping which often uses larger page size. Please note that this + * can result in very sparse cpu->unit mapping on NUMA machines thus + * requiring large vmalloc address space. Don't use this allocator if + * vmalloc space is not orders of magnitude larger than distances + * between node memory addresses (ie. 32bit NUMA machines). + * + * @dyn_size specifies the minimum dynamic area size. + * + * If the needed size is smaller than the minimum or specified unit + * size, the leftover is returned using @free_fn. + * + * RETURNS: + * 0 on success, -errno on failure. + */ +int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, + size_t atom_size, + pcpu_fc_cpu_distance_fn_t cpu_distance_fn, + pcpu_fc_alloc_fn_t alloc_fn, + pcpu_fc_free_fn_t free_fn) +{ + void *base = (void *)ULONG_MAX; + void **areas = NULL; + struct pcpu_alloc_info *ai; + size_t size_sum, areas_size; + unsigned long max_distance; + int group, i, highest_group, rc = 0; + + ai = pcpu_build_alloc_info(reserved_size, dyn_size, atom_size, + cpu_distance_fn); + if (IS_ERR(ai)) + return PTR_ERR(ai); + + size_sum = ai->static_size + ai->reserved_size + ai->dyn_size; + areas_size = PFN_ALIGN(ai->nr_groups * sizeof(void *)); + + areas = memblock_alloc(areas_size, SMP_CACHE_BYTES); + if (!areas) { + rc = -ENOMEM; + goto out_free; + } + + /* allocate, copy and determine base address & max_distance */ + highest_group = 0; + for (group = 0; group < ai->nr_groups; group++) { + struct pcpu_group_info *gi = &ai->groups[group]; + unsigned int cpu = NR_CPUS; + void *ptr; + + for (i = 0; i < gi->nr_units && cpu == NR_CPUS; i++) + cpu = gi->cpu_map[i]; + BUG_ON(cpu == NR_CPUS); + + /* allocate space for the whole group */ + ptr = alloc_fn(cpu, gi->nr_units * ai->unit_size, atom_size); + if (!ptr) { + rc = -ENOMEM; + goto out_free_areas; + } + /* kmemleak tracks the percpu allocations separately */ + kmemleak_free(ptr); + areas[group] = ptr; + + base = min(ptr, base); + if (ptr > areas[highest_group]) + highest_group = group; + } + max_distance = areas[highest_group] - base; + max_distance += ai->unit_size * ai->groups[highest_group].nr_units; + + /* warn if maximum distance is further than 75% of vmalloc space */ + if (max_distance > VMALLOC_TOTAL * 3 / 4) { + pr_warn("max_distance=0x%lx too large for vmalloc space 0x%lx\n", + max_distance, VMALLOC_TOTAL); +#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK + /* and fail if we have fallback */ + rc = -EINVAL; + goto out_free_areas; +#endif + } + + /* + * Copy data and free unused parts. This should happen after all + * allocations are complete; otherwise, we may end up with + * overlapping groups. + */ + for (group = 0; group < ai->nr_groups; group++) { + struct pcpu_group_info *gi = &ai->groups[group]; + void *ptr = areas[group]; + + for (i = 0; i < gi->nr_units; i++, ptr += ai->unit_size) { + if (gi->cpu_map[i] == NR_CPUS) { + /* unused unit, free whole */ + free_fn(ptr, ai->unit_size); + continue; + } + /* copy and return the unused part */ + memcpy(ptr, __per_cpu_load, ai->static_size); + free_fn(ptr + size_sum, ai->unit_size - size_sum); + } + } + + /* base address is now known, determine group base offsets */ + for (group = 0; group < ai->nr_groups; group++) { + ai->groups[group].base_offset = areas[group] - base; + } + + pr_info("Embedded %zu pages/cpu s%zu r%zu d%zu u%zu\n", + PFN_DOWN(size_sum), ai->static_size, ai->reserved_size, + ai->dyn_size, ai->unit_size); + + pcpu_setup_first_chunk(ai, base); + goto out_free; + +out_free_areas: + for (group = 0; group < ai->nr_groups; group++) + if (areas[group]) + free_fn(areas[group], + ai->groups[group].nr_units * ai->unit_size); +out_free: + pcpu_free_alloc_info(ai); + if (areas) + memblock_free_early(__pa(areas), areas_size); + return rc; +} +#endif /* BUILD_EMBED_FIRST_CHUNK */ + +#ifdef BUILD_PAGE_FIRST_CHUNK +/** + * pcpu_page_first_chunk - map the first chunk using PAGE_SIZE pages + * @reserved_size: the size of reserved percpu area in bytes + * @alloc_fn: function to allocate percpu page, always called with PAGE_SIZE + * @free_fn: function to free percpu page, always called with PAGE_SIZE + * @populate_pte_fn: function to populate pte + * + * This is a helper to ease setting up page-remapped first percpu + * chunk and can be called where pcpu_setup_first_chunk() is expected. + * + * This is the basic allocator. Static percpu area is allocated + * page-by-page into vmalloc area. + * + * RETURNS: + * 0 on success, -errno on failure. + */ +int __init pcpu_page_first_chunk(size_t reserved_size, + pcpu_fc_alloc_fn_t alloc_fn, + pcpu_fc_free_fn_t free_fn, + pcpu_fc_populate_pte_fn_t populate_pte_fn) +{ + static struct vm_struct vm; + struct pcpu_alloc_info *ai; + char psize_str[16]; + int unit_pages; + size_t pages_size; + struct page **pages; + int unit, i, j, rc = 0; + int upa; + int nr_g0_units; + + snprintf(psize_str, sizeof(psize_str), "%luK", PAGE_SIZE >> 10); + + ai = pcpu_build_alloc_info(reserved_size, 0, PAGE_SIZE, NULL); + if (IS_ERR(ai)) + return PTR_ERR(ai); + BUG_ON(ai->nr_groups != 1); + upa = ai->alloc_size/ai->unit_size; + nr_g0_units = roundup(num_possible_cpus(), upa); + if (WARN_ON(ai->groups[0].nr_units != nr_g0_units)) { + pcpu_free_alloc_info(ai); + return -EINVAL; + } + + unit_pages = ai->unit_size >> PAGE_SHIFT; + + /* unaligned allocations can't be freed, round up to page size */ + pages_size = PFN_ALIGN(unit_pages * num_possible_cpus() * + sizeof(pages[0])); + pages = memblock_alloc(pages_size, SMP_CACHE_BYTES); + if (!pages) + panic("%s: Failed to allocate %zu bytes\n", __func__, + pages_size); + + /* allocate pages */ + j = 0; + for (unit = 0; unit < num_possible_cpus(); unit++) { + unsigned int cpu = ai->groups[0].cpu_map[unit]; + for (i = 0; i < unit_pages; i++) { + void *ptr; + + ptr = alloc_fn(cpu, PAGE_SIZE, PAGE_SIZE); + if (!ptr) { + pr_warn("failed to allocate %s page for cpu%u\n", + psize_str, cpu); + goto enomem; + } + /* kmemleak tracks the percpu allocations separately */ + kmemleak_free(ptr); + pages[j++] = virt_to_page(ptr); + } + } + + /* allocate vm area, map the pages and copy static data */ + vm.flags = VM_ALLOC; + vm.size = num_possible_cpus() * ai->unit_size; + vm_area_register_early(&vm, PAGE_SIZE); + + for (unit = 0; unit < num_possible_cpus(); unit++) { + unsigned long unit_addr = + (unsigned long)vm.addr + unit * ai->unit_size; + + for (i = 0; i < unit_pages; i++) + populate_pte_fn(unit_addr + (i << PAGE_SHIFT)); + + /* pte already populated, the following shouldn't fail */ + rc = __pcpu_map_pages(unit_addr, &pages[unit * unit_pages], + unit_pages); + if (rc < 0) + panic("failed to map percpu area, err=%d\n", rc); + + /* + * FIXME: Archs with virtual cache should flush local + * cache for the linear mapping here - something + * equivalent to flush_cache_vmap() on the local cpu. + * flush_cache_vmap() can't be used as most supporting + * data structures are not set up yet. + */ + + /* copy static data */ + memcpy((void *)unit_addr, __per_cpu_load, ai->static_size); + } + + /* we're ready, commit */ + pr_info("%d %s pages/cpu s%zu r%zu d%zu\n", + unit_pages, psize_str, ai->static_size, + ai->reserved_size, ai->dyn_size); + + pcpu_setup_first_chunk(ai, vm.addr); + goto out_free_ar; + +enomem: + while (--j >= 0) + free_fn(page_address(pages[j]), PAGE_SIZE); + rc = -ENOMEM; +out_free_ar: + memblock_free_early(__pa(pages), pages_size); + pcpu_free_alloc_info(ai); + return rc; +} +#endif /* BUILD_PAGE_FIRST_CHUNK */ + +#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA +/* + * Generic SMP percpu area setup. + * + * The embedding helper is used because its behavior closely resembles + * the original non-dynamic generic percpu area setup. This is + * important because many archs have addressing restrictions and might + * fail if the percpu area is located far away from the previous + * location. As an added bonus, in non-NUMA cases, embedding is + * generally a good idea TLB-wise because percpu area can piggy back + * on the physical linear memory mapping which uses large page + * mappings on applicable archs. + */ +unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; +EXPORT_SYMBOL(__per_cpu_offset); + +static void * __init pcpu_dfl_fc_alloc(unsigned int cpu, size_t size, + size_t align) +{ + return memblock_alloc_from(size, align, __pa(MAX_DMA_ADDRESS)); +} + +static void __init pcpu_dfl_fc_free(void *ptr, size_t size) +{ + memblock_free_early(__pa(ptr), size); +} + +void __init setup_per_cpu_areas(void) +{ + unsigned long delta; + unsigned int cpu; + int rc; + + /* + * Always reserve area for module percpu variables. That's + * what the legacy allocator did. + */ + rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, + PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, NULL, + pcpu_dfl_fc_alloc, pcpu_dfl_fc_free); + if (rc < 0) + panic("Failed to initialize percpu areas."); + + delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start; + for_each_possible_cpu(cpu) + __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu]; +} +#endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */ + +#else /* CONFIG_SMP */ + +/* + * UP percpu area setup. + * + * UP always uses km-based percpu allocator with identity mapping. + * Static percpu variables are indistinguishable from the usual static + * variables and don't require any special preparation. + */ +void __init setup_per_cpu_areas(void) +{ + const size_t unit_size = + roundup_pow_of_two(max_t(size_t, PCPU_MIN_UNIT_SIZE, + PERCPU_DYNAMIC_RESERVE)); + struct pcpu_alloc_info *ai; + void *fc; + + ai = pcpu_alloc_alloc_info(1, 1); + fc = memblock_alloc_from(unit_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); + if (!ai || !fc) + panic("Failed to allocate memory for percpu areas."); + /* kmemleak tracks the percpu allocations separately */ + kmemleak_free(fc); + + ai->dyn_size = unit_size; + ai->unit_size = unit_size; + ai->atom_size = unit_size; + ai->alloc_size = unit_size; + ai->groups[0].nr_units = 1; + ai->groups[0].cpu_map[0] = 0; + + pcpu_setup_first_chunk(ai, fc); + pcpu_free_alloc_info(ai); +} + +#endif /* CONFIG_SMP */ + +/* + * pcpu_nr_pages - calculate total number of populated backing pages + * + * This reflects the number of pages populated to back chunks. Metadata is + * excluded in the number exposed in meminfo as the number of backing pages + * scales with the number of cpus and can quickly outweigh the memory used for + * metadata. It also keeps this calculation nice and simple. + * + * RETURNS: + * Total number of populated backing pages in use by the allocator. + */ +unsigned long pcpu_nr_pages(void) +{ + return pcpu_nr_populated * pcpu_nr_units; +} + +/* + * Percpu allocator is initialized early during boot when neither slab or + * workqueue is available. Plug async management until everything is up + * and running. + */ +static int __init percpu_enable_async(void) +{ + pcpu_async_enabled = true; + return 0; +} +subsys_initcall(percpu_enable_async); diff --git a/mm/pgalloc-track.h b/mm/pgalloc-track.h new file mode 100644 index 000000000..1dcc86502 --- /dev/null +++ b/mm/pgalloc-track.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_PGALLLC_TRACK_H +#define _LINUX_PGALLLC_TRACK_H + +#if defined(CONFIG_MMU) +static inline p4d_t *p4d_alloc_track(struct mm_struct *mm, pgd_t *pgd, + unsigned long address, + pgtbl_mod_mask *mod_mask) +{ + if (unlikely(pgd_none(*pgd))) { + if (__p4d_alloc(mm, pgd, address)) + return NULL; + *mod_mask |= PGTBL_PGD_MODIFIED; + } + + return p4d_offset(pgd, address); +} + +static inline pud_t *pud_alloc_track(struct mm_struct *mm, p4d_t *p4d, + unsigned long address, + pgtbl_mod_mask *mod_mask) +{ + if (unlikely(p4d_none(*p4d))) { + if (__pud_alloc(mm, p4d, address)) + return NULL; + *mod_mask |= PGTBL_P4D_MODIFIED; + } + + return pud_offset(p4d, address); +} + +static inline pmd_t *pmd_alloc_track(struct mm_struct *mm, pud_t *pud, + unsigned long address, + pgtbl_mod_mask *mod_mask) +{ + if (unlikely(pud_none(*pud))) { + if (__pmd_alloc(mm, pud, address)) + return NULL; + *mod_mask |= PGTBL_PUD_MODIFIED; + } + + return pmd_offset(pud, address); +} +#endif /* CONFIG_MMU */ + +#define pte_alloc_kernel_track(pmd, address, mask) \ + ((unlikely(pmd_none(*(pmd))) && \ + (__pte_alloc_kernel(pmd) || ({*(mask)|=PGTBL_PMD_MODIFIED;0;})))?\ + NULL: pte_offset_kernel(pmd, address)) + +#endif /* _LINUX_PGALLLC_TRACK_H */ diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c new file mode 100644 index 000000000..4e640baf9 --- /dev/null +++ b/mm/pgtable-generic.c @@ -0,0 +1,222 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * mm/pgtable-generic.c + * + * Generic pgtable methods declared in linux/pgtable.h + * + * Copyright (C) 2010 Linus Torvalds + */ + +#include +#include +#include +#include + +/* + * If a p?d_bad entry is found while walking page tables, report + * the error, before resetting entry to p?d_none. Usually (but + * very seldom) called out from the p?d_none_or_clear_bad macros. + */ + +void pgd_clear_bad(pgd_t *pgd) +{ + pgd_ERROR(*pgd); + pgd_clear(pgd); +} + +#ifndef __PAGETABLE_P4D_FOLDED +void p4d_clear_bad(p4d_t *p4d) +{ + p4d_ERROR(*p4d); + p4d_clear(p4d); +} +#endif + +#ifndef __PAGETABLE_PUD_FOLDED +void pud_clear_bad(pud_t *pud) +{ + pud_ERROR(*pud); + pud_clear(pud); +} +#endif + +/* + * Note that the pmd variant below can't be stub'ed out just as for p4d/pud + * above. pmd folding is special and typically pmd_* macros refer to upper + * level even when folded + */ +void pmd_clear_bad(pmd_t *pmd) +{ + pmd_ERROR(*pmd); + pmd_clear(pmd); +} + +#ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS +/* + * Only sets the access flags (dirty, accessed), as well as write + * permission. Furthermore, we know it always gets set to a "more + * permissive" setting, which allows most architectures to optimize + * this. We return whether the PTE actually changed, which in turn + * instructs the caller to do things like update__mmu_cache. This + * used to be done in the caller, but sparc needs minor faults to + * force that call on sun4c so we changed this macro slightly + */ +int ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, + pte_t entry, int dirty) +{ + int changed = !pte_same(*ptep, entry); + if (changed) { + set_pte_at(vma->vm_mm, address, ptep, entry); + flush_tlb_fix_spurious_fault(vma, address); + } + return changed; +} +#endif + +#ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH +int ptep_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep) +{ + int young; + young = ptep_test_and_clear_young(vma, address, ptep); + if (young) + flush_tlb_page(vma, address); + return young; +} +#endif + +#ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH +pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address, + pte_t *ptep) +{ + struct mm_struct *mm = (vma)->vm_mm; + pte_t pte; + pte = ptep_get_and_clear(mm, address, ptep); + if (pte_accessible(mm, pte)) + flush_tlb_page(vma, address); + return pte; +} +#endif + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + +#ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS +int pmdp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, + pmd_t entry, int dirty) +{ + int changed = !pmd_same(*pmdp, entry); + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + if (changed) { + set_pmd_at(vma->vm_mm, address, pmdp, entry); + flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); + } + return changed; +} +#endif + +#ifndef __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH +int pmdp_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp) +{ + int young; + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + young = pmdp_test_and_clear_young(vma, address, pmdp); + if (young) + flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); + return young; +} +#endif + +#ifndef __HAVE_ARCH_PMDP_HUGE_CLEAR_FLUSH +pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmdp) +{ + pmd_t pmd; + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + VM_BUG_ON(pmd_present(*pmdp) && !pmd_trans_huge(*pmdp) && + !pmd_devmap(*pmdp)); + pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); + flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); + return pmd; +} + +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +pud_t pudp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address, + pud_t *pudp) +{ + pud_t pud; + + VM_BUG_ON(address & ~HPAGE_PUD_MASK); + VM_BUG_ON(!pud_trans_huge(*pudp) && !pud_devmap(*pudp)); + pud = pudp_huge_get_and_clear(vma->vm_mm, address, pudp); + flush_pud_tlb_range(vma, address, address + HPAGE_PUD_SIZE); + return pud; +} +#endif +#endif + +#ifndef __HAVE_ARCH_PGTABLE_DEPOSIT +void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, + pgtable_t pgtable) +{ + assert_spin_locked(pmd_lockptr(mm, pmdp)); + + /* FIFO */ + if (!pmd_huge_pte(mm, pmdp)) + INIT_LIST_HEAD(&pgtable->lru); + else + list_add(&pgtable->lru, &pmd_huge_pte(mm, pmdp)->lru); + pmd_huge_pte(mm, pmdp) = pgtable; +} +#endif + +#ifndef __HAVE_ARCH_PGTABLE_WITHDRAW +/* no "address" argument so destroys page coloring of some arch */ +pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp) +{ + pgtable_t pgtable; + + assert_spin_locked(pmd_lockptr(mm, pmdp)); + + /* FIFO */ + pgtable = pmd_huge_pte(mm, pmdp); + pmd_huge_pte(mm, pmdp) = list_first_entry_or_null(&pgtable->lru, + struct page, lru); + if (pmd_huge_pte(mm, pmdp)) + list_del(&pgtable->lru); + return pgtable; +} +#endif + +#ifndef __HAVE_ARCH_PMDP_INVALIDATE +pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmdp) +{ + pmd_t old = pmdp_establish(vma, address, pmdp, pmd_mkinvalid(*pmdp)); + flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); + return old; +} +#endif + +#ifndef pmdp_collapse_flush +pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmdp) +{ + /* + * pmd and hugepage pte format are same. So we could + * use the same function. + */ + pmd_t pmd; + + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + VM_BUG_ON(pmd_trans_huge(*pmdp)); + pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); + + /* collapse entails shooting down ptes not pmd */ + flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); + return pmd; +} +#endif +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c new file mode 100644 index 000000000..c90d722c6 --- /dev/null +++ b/mm/process_vm_access.c @@ -0,0 +1,305 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * linux/mm/process_vm_access.c + * + * Copyright (C) 2010-2011 Christopher Yeoh , IBM Corp. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/** + * process_vm_rw_pages - read/write pages from task specified + * @pages: array of pointers to pages we want to copy + * @offset: offset in page to start copying from/to + * @len: number of bytes to copy + * @iter: where to copy to/from locally + * @vm_write: 0 means copy from, 1 means copy to + * Returns 0 on success, error code otherwise + */ +static int process_vm_rw_pages(struct page **pages, + unsigned offset, + size_t len, + struct iov_iter *iter, + int vm_write) +{ + /* Do the copy for each page */ + while (len && iov_iter_count(iter)) { + struct page *page = *pages++; + size_t copy = PAGE_SIZE - offset; + size_t copied; + + if (copy > len) + copy = len; + + if (vm_write) + copied = copy_page_from_iter(page, offset, copy, iter); + else + copied = copy_page_to_iter(page, offset, copy, iter); + + len -= copied; + if (copied < copy && iov_iter_count(iter)) + return -EFAULT; + offset = 0; + } + return 0; +} + +/* Maximum number of pages kmalloc'd to hold struct page's during copy */ +#define PVM_MAX_KMALLOC_PAGES (PAGE_SIZE * 2) + +/** + * process_vm_rw_single_vec - read/write pages from task specified + * @addr: start memory address of target process + * @len: size of area to copy to/from + * @iter: where to copy to/from locally + * @process_pages: struct pages area that can store at least + * nr_pages_to_copy struct page pointers + * @mm: mm for task + * @task: task to read/write from + * @vm_write: 0 means copy from, 1 means copy to + * Returns 0 on success or on failure error code + */ +static int process_vm_rw_single_vec(unsigned long addr, + unsigned long len, + struct iov_iter *iter, + struct page **process_pages, + struct mm_struct *mm, + struct task_struct *task, + int vm_write) +{ + unsigned long pa = addr & PAGE_MASK; + unsigned long start_offset = addr - pa; + unsigned long nr_pages; + ssize_t rc = 0; + unsigned long max_pages_per_loop = PVM_MAX_KMALLOC_PAGES + / sizeof(struct pages *); + unsigned int flags = 0; + + /* Work out address and page range required */ + if (len == 0) + return 0; + nr_pages = (addr + len - 1) / PAGE_SIZE - addr / PAGE_SIZE + 1; + + if (vm_write) + flags |= FOLL_WRITE; + + while (!rc && nr_pages && iov_iter_count(iter)) { + int pinned_pages = min(nr_pages, max_pages_per_loop); + int locked = 1; + size_t bytes; + + /* + * Get the pages we're interested in. We must + * access remotely because task/mm might not + * current/current->mm + */ + mmap_read_lock(mm); + pinned_pages = pin_user_pages_remote(mm, pa, pinned_pages, + flags, process_pages, + NULL, &locked); + if (locked) + mmap_read_unlock(mm); + if (pinned_pages <= 0) + return -EFAULT; + + bytes = pinned_pages * PAGE_SIZE - start_offset; + if (bytes > len) + bytes = len; + + rc = process_vm_rw_pages(process_pages, + start_offset, bytes, iter, + vm_write); + len -= bytes; + start_offset = 0; + nr_pages -= pinned_pages; + pa += pinned_pages * PAGE_SIZE; + + /* If vm_write is set, the pages need to be made dirty: */ + unpin_user_pages_dirty_lock(process_pages, pinned_pages, + vm_write); + } + + return rc; +} + +/* Maximum number of entries for process pages array + which lives on stack */ +#define PVM_MAX_PP_ARRAY_COUNT 16 + +/** + * process_vm_rw_core - core of reading/writing pages from task specified + * @pid: PID of process to read/write from/to + * @iter: where to copy to/from locally + * @rvec: iovec array specifying where to copy to/from in the other process + * @riovcnt: size of rvec array + * @flags: currently unused + * @vm_write: 0 if reading from other process, 1 if writing to other process + * + * Returns the number of bytes read/written or error code. May + * return less bytes than expected if an error occurs during the copying + * process. + */ +static ssize_t process_vm_rw_core(pid_t pid, struct iov_iter *iter, + const struct iovec *rvec, + unsigned long riovcnt, + unsigned long flags, int vm_write) +{ + struct task_struct *task; + struct page *pp_stack[PVM_MAX_PP_ARRAY_COUNT]; + struct page **process_pages = pp_stack; + struct mm_struct *mm; + unsigned long i; + ssize_t rc = 0; + unsigned long nr_pages = 0; + unsigned long nr_pages_iov; + ssize_t iov_len; + size_t total_len = iov_iter_count(iter); + + /* + * Work out how many pages of struct pages we're going to need + * when eventually calling get_user_pages + */ + for (i = 0; i < riovcnt; i++) { + iov_len = rvec[i].iov_len; + if (iov_len > 0) { + nr_pages_iov = ((unsigned long)rvec[i].iov_base + + iov_len) + / PAGE_SIZE - (unsigned long)rvec[i].iov_base + / PAGE_SIZE + 1; + nr_pages = max(nr_pages, nr_pages_iov); + } + } + + if (nr_pages == 0) + return 0; + + if (nr_pages > PVM_MAX_PP_ARRAY_COUNT) { + /* For reliability don't try to kmalloc more than + 2 pages worth */ + process_pages = kmalloc(min_t(size_t, PVM_MAX_KMALLOC_PAGES, + sizeof(struct pages *)*nr_pages), + GFP_KERNEL); + + if (!process_pages) + return -ENOMEM; + } + + /* Get process information */ + task = find_get_task_by_vpid(pid); + if (!task) { + rc = -ESRCH; + goto free_proc_pages; + } + + mm = mm_access(task, PTRACE_MODE_ATTACH_REALCREDS); + if (!mm || IS_ERR(mm)) { + rc = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH; + /* + * Explicitly map EACCES to EPERM as EPERM is a more + * appropriate error code for process_vw_readv/writev + */ + if (rc == -EACCES) + rc = -EPERM; + goto put_task_struct; + } + + for (i = 0; i < riovcnt && iov_iter_count(iter) && !rc; i++) + rc = process_vm_rw_single_vec( + (unsigned long)rvec[i].iov_base, rvec[i].iov_len, + iter, process_pages, mm, task, vm_write); + + /* copied = space before - space after */ + total_len -= iov_iter_count(iter); + + /* If we have managed to copy any data at all then + we return the number of bytes copied. Otherwise + we return the error code */ + if (total_len) + rc = total_len; + + mmput(mm); + +put_task_struct: + put_task_struct(task); + +free_proc_pages: + if (process_pages != pp_stack) + kfree(process_pages); + return rc; +} + +/** + * process_vm_rw - check iovecs before calling core routine + * @pid: PID of process to read/write from/to + * @lvec: iovec array specifying where to copy to/from locally + * @liovcnt: size of lvec array + * @rvec: iovec array specifying where to copy to/from in the other process + * @riovcnt: size of rvec array + * @flags: currently unused + * @vm_write: 0 if reading from other process, 1 if writing to other process + * + * Returns the number of bytes read/written or error code. May + * return less bytes than expected if an error occurs during the copying + * process. + */ +static ssize_t process_vm_rw(pid_t pid, + const struct iovec __user *lvec, + unsigned long liovcnt, + const struct iovec __user *rvec, + unsigned long riovcnt, + unsigned long flags, int vm_write) +{ + struct iovec iovstack_l[UIO_FASTIOV]; + struct iovec iovstack_r[UIO_FASTIOV]; + struct iovec *iov_l = iovstack_l; + struct iovec *iov_r = iovstack_r; + struct iov_iter iter; + ssize_t rc; + int dir = vm_write ? WRITE : READ; + + if (flags != 0) + return -EINVAL; + + /* Check iovecs */ + rc = import_iovec(dir, lvec, liovcnt, UIO_FASTIOV, &iov_l, &iter); + if (rc < 0) + return rc; + if (!iov_iter_count(&iter)) + goto free_iov_l; + iov_r = iovec_from_user(rvec, riovcnt, UIO_FASTIOV, iovstack_r, + in_compat_syscall()); + if (IS_ERR(iov_r)) { + rc = PTR_ERR(iov_r); + goto free_iov_l; + } + rc = process_vm_rw_core(pid, &iter, iov_r, riovcnt, flags, vm_write); + if (iov_r != iovstack_r) + kfree(iov_r); +free_iov_l: + kfree(iov_l); + return rc; +} + +SYSCALL_DEFINE6(process_vm_readv, pid_t, pid, const struct iovec __user *, lvec, + unsigned long, liovcnt, const struct iovec __user *, rvec, + unsigned long, riovcnt, unsigned long, flags) +{ + return process_vm_rw(pid, lvec, liovcnt, rvec, riovcnt, flags, 0); +} + +SYSCALL_DEFINE6(process_vm_writev, pid_t, pid, + const struct iovec __user *, lvec, + unsigned long, liovcnt, const struct iovec __user *, rvec, + unsigned long, riovcnt, unsigned long, flags) +{ + return process_vm_rw(pid, lvec, liovcnt, rvec, riovcnt, flags, 1); +} diff --git a/mm/ptdump.c b/mm/ptdump.c new file mode 100644 index 000000000..a917bf55c --- /dev/null +++ b/mm/ptdump.c @@ -0,0 +1,154 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include + +#ifdef CONFIG_KASAN +/* + * This is an optimization for KASAN=y case. Since all kasan page tables + * eventually point to the kasan_early_shadow_page we could call note_page() + * right away without walking through lower level page tables. This saves + * us dozens of seconds (minutes for 5-level config) while checking for + * W+X mapping or reading kernel_page_tables debugfs file. + */ +static inline int note_kasan_page_table(struct mm_walk *walk, + unsigned long addr) +{ + struct ptdump_state *st = walk->private; + + st->note_page(st, addr, 4, pte_val(kasan_early_shadow_pte[0])); + + walk->action = ACTION_CONTINUE; + + return 0; +} +#endif + +static int ptdump_pgd_entry(pgd_t *pgd, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + struct ptdump_state *st = walk->private; + pgd_t val = READ_ONCE(*pgd); + +#if CONFIG_PGTABLE_LEVELS > 4 && defined(CONFIG_KASAN) + if (pgd_page(val) == virt_to_page(lm_alias(kasan_early_shadow_p4d))) + return note_kasan_page_table(walk, addr); +#endif + + if (st->effective_prot) + st->effective_prot(st, 0, pgd_val(val)); + + if (pgd_leaf(val)) + st->note_page(st, addr, 0, pgd_val(val)); + + return 0; +} + +static int ptdump_p4d_entry(p4d_t *p4d, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + struct ptdump_state *st = walk->private; + p4d_t val = READ_ONCE(*p4d); + +#if CONFIG_PGTABLE_LEVELS > 3 && defined(CONFIG_KASAN) + if (p4d_page(val) == virt_to_page(lm_alias(kasan_early_shadow_pud))) + return note_kasan_page_table(walk, addr); +#endif + + if (st->effective_prot) + st->effective_prot(st, 1, p4d_val(val)); + + if (p4d_leaf(val)) + st->note_page(st, addr, 1, p4d_val(val)); + + return 0; +} + +static int ptdump_pud_entry(pud_t *pud, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + struct ptdump_state *st = walk->private; + pud_t val = READ_ONCE(*pud); + +#if CONFIG_PGTABLE_LEVELS > 2 && defined(CONFIG_KASAN) + if (pud_page(val) == virt_to_page(lm_alias(kasan_early_shadow_pmd))) + return note_kasan_page_table(walk, addr); +#endif + + if (st->effective_prot) + st->effective_prot(st, 2, pud_val(val)); + + if (pud_leaf(val)) + st->note_page(st, addr, 2, pud_val(val)); + + return 0; +} + +static int ptdump_pmd_entry(pmd_t *pmd, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + struct ptdump_state *st = walk->private; + pmd_t val = READ_ONCE(*pmd); + +#if defined(CONFIG_KASAN) + if (pmd_page(val) == virt_to_page(lm_alias(kasan_early_shadow_pte))) + return note_kasan_page_table(walk, addr); +#endif + + if (st->effective_prot) + st->effective_prot(st, 3, pmd_val(val)); + if (pmd_leaf(val)) + st->note_page(st, addr, 3, pmd_val(val)); + + return 0; +} + +static int ptdump_pte_entry(pte_t *pte, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + struct ptdump_state *st = walk->private; + pte_t val = ptep_get(pte); + + if (st->effective_prot) + st->effective_prot(st, 4, pte_val(val)); + + st->note_page(st, addr, 4, pte_val(val)); + + return 0; +} + +static int ptdump_hole(unsigned long addr, unsigned long next, + int depth, struct mm_walk *walk) +{ + struct ptdump_state *st = walk->private; + + st->note_page(st, addr, depth, 0); + + return 0; +} + +static const struct mm_walk_ops ptdump_ops = { + .pgd_entry = ptdump_pgd_entry, + .p4d_entry = ptdump_p4d_entry, + .pud_entry = ptdump_pud_entry, + .pmd_entry = ptdump_pmd_entry, + .pte_entry = ptdump_pte_entry, + .pte_hole = ptdump_hole, +}; + +void ptdump_walk_pgd(struct ptdump_state *st, struct mm_struct *mm, pgd_t *pgd) +{ + const struct ptdump_range *range = st->range; + + mmap_write_lock(mm); + while (range->start != range->end) { + walk_page_range_novma(mm, range->start, range->end, + &ptdump_ops, pgd, st); + range++; + } + mmap_write_unlock(mm); + + /* Flush out the last page */ + st->note_page(st, 0, -1, 0); +} diff --git a/mm/readahead.c b/mm/readahead.c new file mode 100644 index 000000000..d30bcf4bc --- /dev/null +++ b/mm/readahead.c @@ -0,0 +1,641 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * mm/readahead.c - address_space-level file readahead. + * + * Copyright (C) 2002, Linus Torvalds + * + * 09Apr2002 Andrew Morton + * Initial version. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "internal.h" + +/* + * Initialise a struct file's readahead state. Assumes that the caller has + * memset *ra to zero. + */ +void +file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping) +{ + ra->ra_pages = inode_to_bdi(mapping->host)->ra_pages; + ra->prev_pos = -1; +} +EXPORT_SYMBOL_GPL(file_ra_state_init); + +/* + * see if a page needs releasing upon read_cache_pages() failure + * - the caller of read_cache_pages() may have set PG_private or PG_fscache + * before calling, such as the NFS fs marking pages that are cached locally + * on disk, thus we need to give the fs a chance to clean up in the event of + * an error + */ +static void read_cache_pages_invalidate_page(struct address_space *mapping, + struct page *page) +{ + if (page_has_private(page)) { + if (!trylock_page(page)) + BUG(); + page->mapping = mapping; + do_invalidatepage(page, 0, PAGE_SIZE); + page->mapping = NULL; + unlock_page(page); + } + put_page(page); +} + +/* + * release a list of pages, invalidating them first if need be + */ +static void read_cache_pages_invalidate_pages(struct address_space *mapping, + struct list_head *pages) +{ + struct page *victim; + + while (!list_empty(pages)) { + victim = lru_to_page(pages); + list_del(&victim->lru); + read_cache_pages_invalidate_page(mapping, victim); + } +} + +/** + * read_cache_pages - populate an address space with some pages & start reads against them + * @mapping: the address_space + * @pages: The address of a list_head which contains the target pages. These + * pages have their ->index populated and are otherwise uninitialised. + * @filler: callback routine for filling a single page. + * @data: private data for the callback routine. + * + * Hides the details of the LRU cache etc from the filesystems. + * + * Returns: %0 on success, error return by @filler otherwise + */ +int read_cache_pages(struct address_space *mapping, struct list_head *pages, + int (*filler)(void *, struct page *), void *data) +{ + struct page *page; + int ret = 0; + + while (!list_empty(pages)) { + page = lru_to_page(pages); + list_del(&page->lru); + if (add_to_page_cache_lru(page, mapping, page->index, + readahead_gfp_mask(mapping))) { + read_cache_pages_invalidate_page(mapping, page); + continue; + } + put_page(page); + + ret = filler(data, page); + if (unlikely(ret)) { + read_cache_pages_invalidate_pages(mapping, pages); + break; + } + task_io_account_read(PAGE_SIZE); + } + return ret; +} + +EXPORT_SYMBOL(read_cache_pages); + +static void read_pages(struct readahead_control *rac, struct list_head *pages, + bool skip_page) +{ + const struct address_space_operations *aops = rac->mapping->a_ops; + struct page *page; + struct blk_plug plug; + + if (!readahead_count(rac)) + goto out; + + blk_start_plug(&plug); + + if (aops->readahead) { + aops->readahead(rac); + /* Clean up the remaining pages */ + while ((page = readahead_page(rac))) { + unlock_page(page); + put_page(page); + } + } else if (aops->readpages) { + aops->readpages(rac->file, rac->mapping, pages, + readahead_count(rac)); + /* Clean up the remaining pages */ + put_pages_list(pages); + rac->_index += rac->_nr_pages; + rac->_nr_pages = 0; + } else { + while ((page = readahead_page(rac))) { + aops->readpage(rac->file, page); + put_page(page); + } + } + + blk_finish_plug(&plug); + + BUG_ON(!list_empty(pages)); + BUG_ON(readahead_count(rac)); + +out: + if (skip_page) + rac->_index++; +} + +/** + * page_cache_ra_unbounded - Start unchecked readahead. + * @ractl: Readahead control. + * @nr_to_read: The number of pages to read. + * @lookahead_size: Where to start the next readahead. + * + * This function is for filesystems to call when they want to start + * readahead beyond a file's stated i_size. This is almost certainly + * not the function you want to call. Use page_cache_async_readahead() + * or page_cache_sync_readahead() instead. + * + * Context: File is referenced by caller. Mutexes may be held by caller. + * May sleep, but will not reenter filesystem to reclaim memory. + */ +void page_cache_ra_unbounded(struct readahead_control *ractl, + unsigned long nr_to_read, unsigned long lookahead_size) +{ + struct address_space *mapping = ractl->mapping; + unsigned long index = readahead_index(ractl); + LIST_HEAD(page_pool); + gfp_t gfp_mask = readahead_gfp_mask(mapping); + unsigned long i; + + /* + * Partway through the readahead operation, we will have added + * locked pages to the page cache, but will not yet have submitted + * them for I/O. Adding another page may need to allocate memory, + * which can trigger memory reclaim. Telling the VM we're in + * the middle of a filesystem operation will cause it to not + * touch file-backed pages, preventing a deadlock. Most (all?) + * filesystems already specify __GFP_NOFS in their mapping's + * gfp_mask, but let's be explicit here. + */ + unsigned int nofs = memalloc_nofs_save(); + + /* + * Preallocate as many pages as we will need. + */ + for (i = 0; i < nr_to_read; i++) { + struct page *page = xa_load(&mapping->i_pages, index + i); + + BUG_ON(index + i != ractl->_index + ractl->_nr_pages); + + if (page && !xa_is_value(page)) { + /* + * Page already present? Kick off the current batch + * of contiguous pages before continuing with the + * next batch. This page may be the one we would + * have intended to mark as Readahead, but we don't + * have a stable reference to this page, and it's + * not worth getting one just for that. + */ + read_pages(ractl, &page_pool, true); + continue; + } + + page = __page_cache_alloc(gfp_mask); + if (!page) + break; + if (mapping->a_ops->readpages) { + page->index = index + i; + list_add(&page->lru, &page_pool); + } else if (add_to_page_cache_lru(page, mapping, index + i, + gfp_mask) < 0) { + put_page(page); + read_pages(ractl, &page_pool, true); + continue; + } + if (i == nr_to_read - lookahead_size) + SetPageReadahead(page); + ractl->_nr_pages++; + } + + /* + * Now start the IO. We ignore I/O errors - if the page is not + * uptodate then the caller will launch readpage again, and + * will then handle the error. + */ + read_pages(ractl, &page_pool, false); + memalloc_nofs_restore(nofs); +} +EXPORT_SYMBOL_GPL(page_cache_ra_unbounded); + +/* + * do_page_cache_ra() actually reads a chunk of disk. It allocates + * the pages first, then submits them for I/O. This avoids the very bad + * behaviour which would occur if page allocations are causing VM writeback. + * We really don't want to intermingle reads and writes like that. + */ +void do_page_cache_ra(struct readahead_control *ractl, + unsigned long nr_to_read, unsigned long lookahead_size) +{ + struct inode *inode = ractl->mapping->host; + unsigned long index = readahead_index(ractl); + loff_t isize = i_size_read(inode); + pgoff_t end_index; /* The last page we want to read */ + + if (isize == 0) + return; + + end_index = (isize - 1) >> PAGE_SHIFT; + if (index > end_index) + return; + /* Don't read past the page containing the last byte of the file */ + if (nr_to_read > end_index - index) + nr_to_read = end_index - index + 1; + + page_cache_ra_unbounded(ractl, nr_to_read, lookahead_size); +} + +/* + * Chunk the readahead into 2 megabyte units, so that we don't pin too much + * memory at once. + */ +void force_page_cache_ra(struct readahead_control *ractl, + struct file_ra_state *ra, unsigned long nr_to_read) +{ + struct address_space *mapping = ractl->mapping; + struct backing_dev_info *bdi = inode_to_bdi(mapping->host); + unsigned long max_pages, index; + + if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readpages && + !mapping->a_ops->readahead)) + return; + + /* + * If the request exceeds the readahead window, allow the read to + * be up to the optimal hardware IO size + */ + index = readahead_index(ractl); + max_pages = max_t(unsigned long, bdi->io_pages, ra->ra_pages); + nr_to_read = min_t(unsigned long, nr_to_read, max_pages); + while (nr_to_read) { + unsigned long this_chunk = (2 * 1024 * 1024) / PAGE_SIZE; + + if (this_chunk > nr_to_read) + this_chunk = nr_to_read; + ractl->_index = index; + do_page_cache_ra(ractl, this_chunk, 0); + + index += this_chunk; + nr_to_read -= this_chunk; + } +} + +/* + * Set the initial window size, round to next power of 2 and square + * for small size, x 4 for medium, and x 2 for large + * for 128k (32 page) max ra + * 1-8 page = 32k initial, > 8 page = 128k initial + */ +static unsigned long get_init_ra_size(unsigned long size, unsigned long max) +{ + unsigned long newsize = roundup_pow_of_two(size); + + if (newsize <= max / 32) + newsize = newsize * 4; + else if (newsize <= max / 4) + newsize = newsize * 2; + else + newsize = max; + + return newsize; +} + +/* + * Get the previous window size, ramp it up, and + * return it as the new window size. + */ +static unsigned long get_next_ra_size(struct file_ra_state *ra, + unsigned long max) +{ + unsigned long cur = ra->size; + + if (cur < max / 16) + return 4 * cur; + if (cur <= max / 2) + return 2 * cur; + return max; +} + +/* + * On-demand readahead design. + * + * The fields in struct file_ra_state represent the most-recently-executed + * readahead attempt: + * + * |<----- async_size ---------| + * |------------------- size -------------------->| + * |==================#===========================| + * ^start ^page marked with PG_readahead + * + * To overlap application thinking time and disk I/O time, we do + * `readahead pipelining': Do not wait until the application consumed all + * readahead pages and stalled on the missing page at readahead_index; + * Instead, submit an asynchronous readahead I/O as soon as there are + * only async_size pages left in the readahead window. Normally async_size + * will be equal to size, for maximum pipelining. + * + * In interleaved sequential reads, concurrent streams on the same fd can + * be invalidating each other's readahead state. So we flag the new readahead + * page at (start+size-async_size) with PG_readahead, and use it as readahead + * indicator. The flag won't be set on already cached pages, to avoid the + * readahead-for-nothing fuss, saving pointless page cache lookups. + * + * prev_pos tracks the last visited byte in the _previous_ read request. + * It should be maintained by the caller, and will be used for detecting + * small random reads. Note that the readahead algorithm checks loosely + * for sequential patterns. Hence interleaved reads might be served as + * sequential ones. + * + * There is a special-case: if the first page which the application tries to + * read happens to be the first page of the file, it is assumed that a linear + * read is about to happen and the window is immediately set to the initial size + * based on I/O request size and the max_readahead. + * + * The code ramps up the readahead size aggressively at first, but slow down as + * it approaches max_readhead. + */ + +/* + * Count contiguously cached pages from @index-1 to @index-@max, + * this count is a conservative estimation of + * - length of the sequential read sequence, or + * - thrashing threshold in memory tight systems + */ +static pgoff_t count_history_pages(struct address_space *mapping, + pgoff_t index, unsigned long max) +{ + pgoff_t head; + + rcu_read_lock(); + head = page_cache_prev_miss(mapping, index - 1, max); + rcu_read_unlock(); + + return index - 1 - head; +} + +/* + * page cache context based read-ahead + */ +static int try_context_readahead(struct address_space *mapping, + struct file_ra_state *ra, + pgoff_t index, + unsigned long req_size, + unsigned long max) +{ + pgoff_t size; + + size = count_history_pages(mapping, index, max); + + /* + * not enough history pages: + * it could be a random read + */ + if (size <= req_size) + return 0; + + /* + * starts from beginning of file: + * it is a strong indication of long-run stream (or whole-file-read) + */ + if (size >= index) + size *= 2; + + ra->start = index; + ra->size = min(size + req_size, max); + ra->async_size = 1; + + return 1; +} + +/* + * A minimal readahead algorithm for trivial sequential/random reads. + */ +static void ondemand_readahead(struct readahead_control *ractl, + struct file_ra_state *ra, bool hit_readahead_marker, + unsigned long req_size) +{ + struct backing_dev_info *bdi = inode_to_bdi(ractl->mapping->host); + unsigned long max_pages = ra->ra_pages; + unsigned long add_pages; + unsigned long index = readahead_index(ractl); + pgoff_t prev_index; + + /* + * If the request exceeds the readahead window, allow the read to + * be up to the optimal hardware IO size + */ + if (req_size > max_pages && bdi->io_pages > max_pages) + max_pages = min(req_size, bdi->io_pages); + + /* + * start of file + */ + if (!index) + goto initial_readahead; + + /* + * It's the expected callback index, assume sequential access. + * Ramp up sizes, and push forward the readahead window. + */ + if ((index == (ra->start + ra->size - ra->async_size) || + index == (ra->start + ra->size))) { + ra->start += ra->size; + ra->size = get_next_ra_size(ra, max_pages); + ra->async_size = ra->size; + goto readit; + } + + /* + * Hit a marked page without valid readahead state. + * E.g. interleaved reads. + * Query the pagecache for async_size, which normally equals to + * readahead size. Ramp it up and use it as the new readahead size. + */ + if (hit_readahead_marker) { + pgoff_t start; + + rcu_read_lock(); + start = page_cache_next_miss(ractl->mapping, index + 1, + max_pages); + rcu_read_unlock(); + + if (!start || start - index > max_pages) + return; + + ra->start = start; + ra->size = start - index; /* old async_size */ + ra->size += req_size; + ra->size = get_next_ra_size(ra, max_pages); + ra->async_size = ra->size; + goto readit; + } + + /* + * oversize read + */ + if (req_size > max_pages) + goto initial_readahead; + + /* + * sequential cache miss + * trivial case: (index - prev_index) == 1 + * unaligned reads: (index - prev_index) == 0 + */ + prev_index = (unsigned long long)ra->prev_pos >> PAGE_SHIFT; + if (index - prev_index <= 1UL) + goto initial_readahead; + + /* + * Query the page cache and look for the traces(cached history pages) + * that a sequential stream would leave behind. + */ + if (try_context_readahead(ractl->mapping, ra, index, req_size, + max_pages)) + goto readit; + + /* + * standalone, small random read + * Read as is, and do not pollute the readahead state. + */ + do_page_cache_ra(ractl, req_size, 0); + return; + +initial_readahead: + ra->start = index; + ra->size = get_init_ra_size(req_size, max_pages); + ra->async_size = ra->size > req_size ? ra->size - req_size : ra->size; + +readit: + /* + * Will this read hit the readahead marker made by itself? + * If so, trigger the readahead marker hit now, and merge + * the resulted next readahead window into the current one. + * Take care of maximum IO pages as above. + */ + if (index == ra->start && ra->size == ra->async_size) { + add_pages = get_next_ra_size(ra, max_pages); + if (ra->size + add_pages <= max_pages) { + ra->async_size = add_pages; + ra->size += add_pages; + } else { + ra->size = max_pages; + ra->async_size = max_pages >> 1; + } + } + + ractl->_index = ra->start; + do_page_cache_ra(ractl, ra->size, ra->async_size); +} + +void page_cache_sync_ra(struct readahead_control *ractl, + struct file_ra_state *ra, unsigned long req_count) +{ + bool do_forced_ra = ractl->file && (ractl->file->f_mode & FMODE_RANDOM); + + /* + * Even if read-ahead is disabled, issue this request as read-ahead + * as we'll need it to satisfy the requested range. The forced + * read-ahead will do the right thing and limit the read to just the + * requested range, which we'll set to 1 page for this case. + */ + if (!ra->ra_pages || blk_cgroup_congested()) { + if (!ractl->file) + return; + req_count = 1; + do_forced_ra = true; + } + + /* be dumb */ + if (do_forced_ra) { + force_page_cache_ra(ractl, ra, req_count); + return; + } + + /* do read-ahead */ + ondemand_readahead(ractl, ra, false, req_count); +} +EXPORT_SYMBOL_GPL(page_cache_sync_ra); + +void page_cache_async_ra(struct readahead_control *ractl, + struct file_ra_state *ra, struct page *page, + unsigned long req_count) +{ + /* no read-ahead */ + if (!ra->ra_pages) + return; + + /* + * Same bit is used for PG_readahead and PG_reclaim. + */ + if (PageWriteback(page)) + return; + + ClearPageReadahead(page); + + /* + * Defer asynchronous read-ahead on IO congestion. + */ + if (inode_read_congested(ractl->mapping->host)) + return; + + if (blk_cgroup_congested()) + return; + + /* do read-ahead */ + ondemand_readahead(ractl, ra, true, req_count); +} +EXPORT_SYMBOL_GPL(page_cache_async_ra); + +ssize_t ksys_readahead(int fd, loff_t offset, size_t count) +{ + ssize_t ret; + struct fd f; + + ret = -EBADF; + f = fdget(fd); + if (!f.file || !(f.file->f_mode & FMODE_READ)) + goto out; + + /* + * The readahead() syscall is intended to run only on files + * that can execute readahead. If readahead is not possible + * on this file, then we must return -EINVAL. + */ + ret = -EINVAL; + if (!f.file->f_mapping || !f.file->f_mapping->a_ops || + (!S_ISREG(file_inode(f.file)->i_mode) && + !S_ISBLK(file_inode(f.file)->i_mode))) + goto out; + + ret = vfs_fadvise(f.file, offset, count, POSIX_FADV_WILLNEED); +out: + fdput(f); + return ret; +} + +SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count) +{ + return ksys_readahead(fd, offset, count); +} diff --git a/mm/rmap.c b/mm/rmap.c new file mode 100644 index 000000000..e6f840be1 --- /dev/null +++ b/mm/rmap.c @@ -0,0 +1,2019 @@ +/* + * mm/rmap.c - physical to virtual reverse mappings + * + * Copyright 2001, Rik van Riel + * Released under the General Public License (GPL). + * + * Simple, low overhead reverse mapping scheme. + * Please try to keep this thing as modular as possible. + * + * Provides methods for unmapping each kind of mapped page: + * the anon methods track anonymous pages, and + * the file methods track pages belonging to an inode. + * + * Original design by Rik van Riel 2001 + * File methods by Dave McCracken 2003, 2004 + * Anonymous methods by Andrea Arcangeli 2004 + * Contributions by Hugh Dickins 2003, 2004 + */ + +/* + * Lock ordering in mm: + * + * inode->i_mutex (while writing or truncating, not reading or faulting) + * mm->mmap_lock + * page->flags PG_locked (lock_page) * (see huegtlbfs below) + * hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share) + * mapping->i_mmap_rwsem + * hugetlb_fault_mutex (hugetlbfs specific page fault mutex) + * anon_vma->rwsem + * mm->page_table_lock or pte_lock + * pgdat->lru_lock (in mark_page_accessed, isolate_lru_page) + * swap_lock (in swap_duplicate, swap_info_get) + * mmlist_lock (in mmput, drain_mmlist and others) + * mapping->private_lock (in __set_page_dirty_buffers) + * mem_cgroup_{begin,end}_page_stat (memcg->move_lock) + * i_pages lock (widely used) + * inode->i_lock (in set_page_dirty's __mark_inode_dirty) + * bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty) + * sb_lock (within inode_lock in fs/fs-writeback.c) + * i_pages lock (widely used, in set_page_dirty, + * in arch-dependent flush_dcache_mmap_lock, + * within bdi.wb->list_lock in __sync_single_inode) + * + * anon_vma->rwsem,mapping->i_mutex (memory_failure, collect_procs_anon) + * ->tasklist_lock + * pte map lock + * + * * hugetlbfs PageHuge() pages take locks in this order: + * mapping->i_mmap_rwsem + * hugetlb_fault_mutex (hugetlbfs specific page fault mutex) + * page->flags PG_locked (lock_page) + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include + +#include "internal.h" + +static struct kmem_cache *anon_vma_cachep; +static struct kmem_cache *anon_vma_chain_cachep; + +static inline struct anon_vma *anon_vma_alloc(void) +{ + struct anon_vma *anon_vma; + + anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL); + if (anon_vma) { + atomic_set(&anon_vma->refcount, 1); + anon_vma->num_children = 0; + anon_vma->num_active_vmas = 0; + anon_vma->parent = anon_vma; + /* + * Initialise the anon_vma root to point to itself. If called + * from fork, the root will be reset to the parents anon_vma. + */ + anon_vma->root = anon_vma; + } + + return anon_vma; +} + +static inline void anon_vma_free(struct anon_vma *anon_vma) +{ + VM_BUG_ON(atomic_read(&anon_vma->refcount)); + + /* + * Synchronize against page_lock_anon_vma_read() such that + * we can safely hold the lock without the anon_vma getting + * freed. + * + * Relies on the full mb implied by the atomic_dec_and_test() from + * put_anon_vma() against the acquire barrier implied by + * down_read_trylock() from page_lock_anon_vma_read(). This orders: + * + * page_lock_anon_vma_read() VS put_anon_vma() + * down_read_trylock() atomic_dec_and_test() + * LOCK MB + * atomic_read() rwsem_is_locked() + * + * LOCK should suffice since the actual taking of the lock must + * happen _before_ what follows. + */ + might_sleep(); + if (rwsem_is_locked(&anon_vma->root->rwsem)) { + anon_vma_lock_write(anon_vma); + anon_vma_unlock_write(anon_vma); + } + + kmem_cache_free(anon_vma_cachep, anon_vma); +} + +static inline struct anon_vma_chain *anon_vma_chain_alloc(gfp_t gfp) +{ + return kmem_cache_alloc(anon_vma_chain_cachep, gfp); +} + +static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain) +{ + kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain); +} + +static void anon_vma_chain_link(struct vm_area_struct *vma, + struct anon_vma_chain *avc, + struct anon_vma *anon_vma) +{ + avc->vma = vma; + avc->anon_vma = anon_vma; + list_add(&avc->same_vma, &vma->anon_vma_chain); + anon_vma_interval_tree_insert(avc, &anon_vma->rb_root); +} + +/** + * __anon_vma_prepare - attach an anon_vma to a memory region + * @vma: the memory region in question + * + * This makes sure the memory mapping described by 'vma' has + * an 'anon_vma' attached to it, so that we can associate the + * anonymous pages mapped into it with that anon_vma. + * + * The common case will be that we already have one, which + * is handled inline by anon_vma_prepare(). But if + * not we either need to find an adjacent mapping that we + * can re-use the anon_vma from (very common when the only + * reason for splitting a vma has been mprotect()), or we + * allocate a new one. + * + * Anon-vma allocations are very subtle, because we may have + * optimistically looked up an anon_vma in page_lock_anon_vma_read() + * and that may actually touch the spinlock even in the newly + * allocated vma (it depends on RCU to make sure that the + * anon_vma isn't actually destroyed). + * + * As a result, we need to do proper anon_vma locking even + * for the new allocation. At the same time, we do not want + * to do any locking for the common case of already having + * an anon_vma. + * + * This must be called with the mmap_lock held for reading. + */ +int __anon_vma_prepare(struct vm_area_struct *vma) +{ + struct mm_struct *mm = vma->vm_mm; + struct anon_vma *anon_vma, *allocated; + struct anon_vma_chain *avc; + + might_sleep(); + + avc = anon_vma_chain_alloc(GFP_KERNEL); + if (!avc) + goto out_enomem; + + anon_vma = find_mergeable_anon_vma(vma); + allocated = NULL; + if (!anon_vma) { + anon_vma = anon_vma_alloc(); + if (unlikely(!anon_vma)) + goto out_enomem_free_avc; + anon_vma->num_children++; /* self-parent link for new root */ + allocated = anon_vma; + } + + anon_vma_lock_write(anon_vma); + /* page_table_lock to protect against threads */ + spin_lock(&mm->page_table_lock); + if (likely(!vma->anon_vma)) { + vma->anon_vma = anon_vma; + anon_vma_chain_link(vma, avc, anon_vma); + anon_vma->num_active_vmas++; + allocated = NULL; + avc = NULL; + } + spin_unlock(&mm->page_table_lock); + anon_vma_unlock_write(anon_vma); + + if (unlikely(allocated)) + put_anon_vma(allocated); + if (unlikely(avc)) + anon_vma_chain_free(avc); + + return 0; + + out_enomem_free_avc: + anon_vma_chain_free(avc); + out_enomem: + return -ENOMEM; +} + +/* + * This is a useful helper function for locking the anon_vma root as + * we traverse the vma->anon_vma_chain, looping over anon_vma's that + * have the same vma. + * + * Such anon_vma's should have the same root, so you'd expect to see + * just a single mutex_lock for the whole traversal. + */ +static inline struct anon_vma *lock_anon_vma_root(struct anon_vma *root, struct anon_vma *anon_vma) +{ + struct anon_vma *new_root = anon_vma->root; + if (new_root != root) { + if (WARN_ON_ONCE(root)) + up_write(&root->rwsem); + root = new_root; + down_write(&root->rwsem); + } + return root; +} + +static inline void unlock_anon_vma_root(struct anon_vma *root) +{ + if (root) + up_write(&root->rwsem); +} + +/* + * Attach the anon_vmas from src to dst. + * Returns 0 on success, -ENOMEM on failure. + * + * anon_vma_clone() is called by __vma_split(), __split_vma(), copy_vma() and + * anon_vma_fork(). The first three want an exact copy of src, while the last + * one, anon_vma_fork(), may try to reuse an existing anon_vma to prevent + * endless growth of anon_vma. Since dst->anon_vma is set to NULL before call, + * we can identify this case by checking (!dst->anon_vma && src->anon_vma). + * + * If (!dst->anon_vma && src->anon_vma) is true, this function tries to find + * and reuse existing anon_vma which has no vmas and only one child anon_vma. + * This prevents degradation of anon_vma hierarchy to endless linear chain in + * case of constantly forking task. On the other hand, an anon_vma with more + * than one child isn't reused even if there was no alive vma, thus rmap + * walker has a good chance of avoiding scanning the whole hierarchy when it + * searches where page is mapped. + */ +int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) +{ + struct anon_vma_chain *avc, *pavc; + struct anon_vma *root = NULL; + + list_for_each_entry_reverse(pavc, &src->anon_vma_chain, same_vma) { + struct anon_vma *anon_vma; + + avc = anon_vma_chain_alloc(GFP_NOWAIT | __GFP_NOWARN); + if (unlikely(!avc)) { + unlock_anon_vma_root(root); + root = NULL; + avc = anon_vma_chain_alloc(GFP_KERNEL); + if (!avc) + goto enomem_failure; + } + anon_vma = pavc->anon_vma; + root = lock_anon_vma_root(root, anon_vma); + anon_vma_chain_link(dst, avc, anon_vma); + + /* + * Reuse existing anon_vma if it has no vma and only one + * anon_vma child. + * + * Root anon_vma is never reused: + * it has self-parent reference and at least one child. + */ + if (!dst->anon_vma && src->anon_vma && + anon_vma->num_children < 2 && + anon_vma->num_active_vmas == 0) + dst->anon_vma = anon_vma; + } + if (dst->anon_vma) + dst->anon_vma->num_active_vmas++; + unlock_anon_vma_root(root); + return 0; + + enomem_failure: + /* + * dst->anon_vma is dropped here otherwise its degree can be incorrectly + * decremented in unlink_anon_vmas(). + * We can safely do this because callers of anon_vma_clone() don't care + * about dst->anon_vma if anon_vma_clone() failed. + */ + dst->anon_vma = NULL; + unlink_anon_vmas(dst); + return -ENOMEM; +} + +/* + * Attach vma to its own anon_vma, as well as to the anon_vmas that + * the corresponding VMA in the parent process is attached to. + * Returns 0 on success, non-zero on failure. + */ +int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) +{ + struct anon_vma_chain *avc; + struct anon_vma *anon_vma; + int error; + + /* Don't bother if the parent process has no anon_vma here. */ + if (!pvma->anon_vma) + return 0; + + /* Drop inherited anon_vma, we'll reuse existing or allocate new. */ + vma->anon_vma = NULL; + + /* + * First, attach the new VMA to the parent VMA's anon_vmas, + * so rmap can find non-COWed pages in child processes. + */ + error = anon_vma_clone(vma, pvma); + if (error) + return error; + + /* An existing anon_vma has been reused, all done then. */ + if (vma->anon_vma) + return 0; + + /* Then add our own anon_vma. */ + anon_vma = anon_vma_alloc(); + if (!anon_vma) + goto out_error; + anon_vma->num_active_vmas++; + avc = anon_vma_chain_alloc(GFP_KERNEL); + if (!avc) + goto out_error_free_anon_vma; + + /* + * The root anon_vma's spinlock is the lock actually used when we + * lock any of the anon_vmas in this anon_vma tree. + */ + anon_vma->root = pvma->anon_vma->root; + anon_vma->parent = pvma->anon_vma; + /* + * With refcounts, an anon_vma can stay around longer than the + * process it belongs to. The root anon_vma needs to be pinned until + * this anon_vma is freed, because the lock lives in the root. + */ + get_anon_vma(anon_vma->root); + /* Mark this anon_vma as the one where our new (COWed) pages go. */ + vma->anon_vma = anon_vma; + anon_vma_lock_write(anon_vma); + anon_vma_chain_link(vma, avc, anon_vma); + anon_vma->parent->num_children++; + anon_vma_unlock_write(anon_vma); + + return 0; + + out_error_free_anon_vma: + put_anon_vma(anon_vma); + out_error: + unlink_anon_vmas(vma); + return -ENOMEM; +} + +void unlink_anon_vmas(struct vm_area_struct *vma) +{ + struct anon_vma_chain *avc, *next; + struct anon_vma *root = NULL; + + /* + * Unlink each anon_vma chained to the VMA. This list is ordered + * from newest to oldest, ensuring the root anon_vma gets freed last. + */ + list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { + struct anon_vma *anon_vma = avc->anon_vma; + + root = lock_anon_vma_root(root, anon_vma); + anon_vma_interval_tree_remove(avc, &anon_vma->rb_root); + + /* + * Leave empty anon_vmas on the list - we'll need + * to free them outside the lock. + */ + if (RB_EMPTY_ROOT(&anon_vma->rb_root.rb_root)) { + anon_vma->parent->num_children--; + continue; + } + + list_del(&avc->same_vma); + anon_vma_chain_free(avc); + } + if (vma->anon_vma) + vma->anon_vma->num_active_vmas--; + unlock_anon_vma_root(root); + + /* + * Iterate the list once more, it now only contains empty and unlinked + * anon_vmas, destroy them. Could not do before due to __put_anon_vma() + * needing to write-acquire the anon_vma->root->rwsem. + */ + list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { + struct anon_vma *anon_vma = avc->anon_vma; + + VM_WARN_ON(anon_vma->num_children); + VM_WARN_ON(anon_vma->num_active_vmas); + put_anon_vma(anon_vma); + + list_del(&avc->same_vma); + anon_vma_chain_free(avc); + } +} + +static void anon_vma_ctor(void *data) +{ + struct anon_vma *anon_vma = data; + + init_rwsem(&anon_vma->rwsem); + atomic_set(&anon_vma->refcount, 0); + anon_vma->rb_root = RB_ROOT_CACHED; +} + +void __init anon_vma_init(void) +{ + anon_vma_cachep = kmem_cache_create("anon_vma", sizeof(struct anon_vma), + 0, SLAB_TYPESAFE_BY_RCU|SLAB_PANIC|SLAB_ACCOUNT, + anon_vma_ctor); + anon_vma_chain_cachep = KMEM_CACHE(anon_vma_chain, + SLAB_PANIC|SLAB_ACCOUNT); +} + +/* + * Getting a lock on a stable anon_vma from a page off the LRU is tricky! + * + * Since there is no serialization what so ever against page_remove_rmap() + * the best this function can do is return a locked anon_vma that might + * have been relevant to this page. + * + * The page might have been remapped to a different anon_vma or the anon_vma + * returned may already be freed (and even reused). + * + * In case it was remapped to a different anon_vma, the new anon_vma will be a + * child of the old anon_vma, and the anon_vma lifetime rules will therefore + * ensure that any anon_vma obtained from the page will still be valid for as + * long as we observe page_mapped() [ hence all those page_mapped() tests ]. + * + * All users of this function must be very careful when walking the anon_vma + * chain and verify that the page in question is indeed mapped in it + * [ something equivalent to page_mapped_in_vma() ]. + * + * Since anon_vma's slab is SLAB_TYPESAFE_BY_RCU and we know from + * page_remove_rmap() that the anon_vma pointer from page->mapping is valid + * if there is a mapcount, we can dereference the anon_vma after observing + * those. + */ +struct anon_vma *page_get_anon_vma(struct page *page) +{ + struct anon_vma *anon_vma = NULL; + unsigned long anon_mapping; + + rcu_read_lock(); + anon_mapping = (unsigned long)READ_ONCE(page->mapping); + if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) + goto out; + if (!page_mapped(page)) + goto out; + + anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON); + if (!atomic_inc_not_zero(&anon_vma->refcount)) { + anon_vma = NULL; + goto out; + } + + /* + * If this page is still mapped, then its anon_vma cannot have been + * freed. But if it has been unmapped, we have no security against the + * anon_vma structure being freed and reused (for another anon_vma: + * SLAB_TYPESAFE_BY_RCU guarantees that - so the atomic_inc_not_zero() + * above cannot corrupt). + */ + if (!page_mapped(page)) { + rcu_read_unlock(); + put_anon_vma(anon_vma); + return NULL; + } +out: + rcu_read_unlock(); + + return anon_vma; +} + +/* + * Similar to page_get_anon_vma() except it locks the anon_vma. + * + * Its a little more complex as it tries to keep the fast path to a single + * atomic op -- the trylock. If we fail the trylock, we fall back to getting a + * reference like with page_get_anon_vma() and then block on the mutex. + */ +struct anon_vma *page_lock_anon_vma_read(struct page *page) +{ + struct anon_vma *anon_vma = NULL; + struct anon_vma *root_anon_vma; + unsigned long anon_mapping; + + rcu_read_lock(); + anon_mapping = (unsigned long)READ_ONCE(page->mapping); + if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) + goto out; + if (!page_mapped(page)) + goto out; + + anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON); + root_anon_vma = READ_ONCE(anon_vma->root); + if (down_read_trylock(&root_anon_vma->rwsem)) { + /* + * If the page is still mapped, then this anon_vma is still + * its anon_vma, and holding the mutex ensures that it will + * not go away, see anon_vma_free(). + */ + if (!page_mapped(page)) { + up_read(&root_anon_vma->rwsem); + anon_vma = NULL; + } + goto out; + } + + /* trylock failed, we got to sleep */ + if (!atomic_inc_not_zero(&anon_vma->refcount)) { + anon_vma = NULL; + goto out; + } + + if (!page_mapped(page)) { + rcu_read_unlock(); + put_anon_vma(anon_vma); + return NULL; + } + + /* we pinned the anon_vma, its safe to sleep */ + rcu_read_unlock(); + anon_vma_lock_read(anon_vma); + + if (atomic_dec_and_test(&anon_vma->refcount)) { + /* + * Oops, we held the last refcount, release the lock + * and bail -- can't simply use put_anon_vma() because + * we'll deadlock on the anon_vma_lock_write() recursion. + */ + anon_vma_unlock_read(anon_vma); + __put_anon_vma(anon_vma); + anon_vma = NULL; + } + + return anon_vma; + +out: + rcu_read_unlock(); + return anon_vma; +} + +void page_unlock_anon_vma_read(struct anon_vma *anon_vma) +{ + anon_vma_unlock_read(anon_vma); +} + +#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH +/* + * Flush TLB entries for recently unmapped pages from remote CPUs. It is + * important if a PTE was dirty when it was unmapped that it's flushed + * before any IO is initiated on the page to prevent lost writes. Similarly, + * it must be flushed before freeing to prevent data leakage. + */ +void try_to_unmap_flush(void) +{ + struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; + + if (!tlb_ubc->flush_required) + return; + + arch_tlbbatch_flush(&tlb_ubc->arch); + tlb_ubc->flush_required = false; + tlb_ubc->writable = false; +} + +/* Flush iff there are potentially writable TLB entries that can race with IO */ +void try_to_unmap_flush_dirty(void) +{ + struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; + + if (tlb_ubc->writable) + try_to_unmap_flush(); +} + +static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable) +{ + struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; + + arch_tlbbatch_add_mm(&tlb_ubc->arch, mm); + tlb_ubc->flush_required = true; + + /* + * Ensure compiler does not re-order the setting of tlb_flush_batched + * before the PTE is cleared. + */ + barrier(); + mm->tlb_flush_batched = true; + + /* + * If the PTE was dirty then it's best to assume it's writable. The + * caller must use try_to_unmap_flush_dirty() or try_to_unmap_flush() + * before the page is queued for IO. + */ + if (writable) + tlb_ubc->writable = true; +} + +/* + * Returns true if the TLB flush should be deferred to the end of a batch of + * unmap operations to reduce IPIs. + */ +static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) +{ + bool should_defer = false; + + if (!(flags & TTU_BATCH_FLUSH)) + return false; + + /* If remote CPUs need to be flushed then defer batch the flush */ + if (cpumask_any_but(mm_cpumask(mm), get_cpu()) < nr_cpu_ids) + should_defer = true; + put_cpu(); + + return should_defer; +} + +/* + * Reclaim unmaps pages under the PTL but do not flush the TLB prior to + * releasing the PTL if TLB flushes are batched. It's possible for a parallel + * operation such as mprotect or munmap to race between reclaim unmapping + * the page and flushing the page. If this race occurs, it potentially allows + * access to data via a stale TLB entry. Tracking all mm's that have TLB + * batching in flight would be expensive during reclaim so instead track + * whether TLB batching occurred in the past and if so then do a flush here + * if required. This will cost one additional flush per reclaim cycle paid + * by the first operation at risk such as mprotect and mumap. + * + * This must be called under the PTL so that an access to tlb_flush_batched + * that is potentially a "reclaim vs mprotect/munmap/etc" race will synchronise + * via the PTL. + */ +void flush_tlb_batched_pending(struct mm_struct *mm) +{ + if (data_race(mm->tlb_flush_batched)) { + flush_tlb_mm(mm); + + /* + * Do not allow the compiler to re-order the clearing of + * tlb_flush_batched before the tlb is flushed. + */ + barrier(); + mm->tlb_flush_batched = false; + } +} +#else +static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable) +{ +} + +static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) +{ + return false; +} +#endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ + +/* + * At what user virtual address is page expected in vma? + * Caller should check the page is actually part of the vma. + */ +unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) +{ + if (PageAnon(page)) { + struct anon_vma *page__anon_vma = page_anon_vma(page); + /* + * Note: swapoff's unuse_vma() is more efficient with this + * check, and needs it to match anon_vma when KSM is active. + */ + if (!vma->anon_vma || !page__anon_vma || + vma->anon_vma->root != page__anon_vma->root) + return -EFAULT; + } else if (!vma->vm_file) { + return -EFAULT; + } else if (vma->vm_file->f_mapping != compound_head(page)->mapping) { + return -EFAULT; + } + + return vma_address(page, vma); +} + +pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) +{ + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd = NULL; + pmd_t pmde; + + pgd = pgd_offset(mm, address); + if (!pgd_present(*pgd)) + goto out; + + p4d = p4d_offset(pgd, address); + if (!p4d_present(*p4d)) + goto out; + + pud = pud_offset(p4d, address); + if (!pud_present(*pud)) + goto out; + + pmd = pmd_offset(pud, address); + /* + * Some THP functions use the sequence pmdp_huge_clear_flush(), set_pmd_at() + * without holding anon_vma lock for write. So when looking for a + * genuine pmde (in which to find pte), test present and !THP together. + */ + pmde = *pmd; + barrier(); + if (!pmd_present(pmde) || pmd_trans_huge(pmde)) + pmd = NULL; +out: + return pmd; +} + +struct page_referenced_arg { + int mapcount; + int referenced; + unsigned long vm_flags; + struct mem_cgroup *memcg; +}; +/* + * arg: page_referenced_arg will be passed + */ +static bool page_referenced_one(struct page *page, struct vm_area_struct *vma, + unsigned long address, void *arg) +{ + struct page_referenced_arg *pra = arg; + struct page_vma_mapped_walk pvmw = { + .page = page, + .vma = vma, + .address = address, + }; + int referenced = 0; + + while (page_vma_mapped_walk(&pvmw)) { + address = pvmw.address; + + if (vma->vm_flags & VM_LOCKED) { + page_vma_mapped_walk_done(&pvmw); + pra->vm_flags |= VM_LOCKED; + return false; /* To break the loop */ + } + + if (pvmw.pte) { + if (ptep_clear_flush_young_notify(vma, address, + pvmw.pte)) { + /* + * Don't treat a reference through + * a sequentially read mapping as such. + * If the page has been used in another mapping, + * we will catch it; if this other mapping is + * already gone, the unmap path will have set + * PG_referenced or activated the page. + */ + if (likely(!(vma->vm_flags & VM_SEQ_READ))) + referenced++; + } + } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { + if (pmdp_clear_flush_young_notify(vma, address, + pvmw.pmd)) + referenced++; + } else { + /* unexpected pmd-mapped page? */ + WARN_ON_ONCE(1); + } + + pra->mapcount--; + } + + if (referenced) + clear_page_idle(page); + if (test_and_clear_page_young(page)) + referenced++; + + if (referenced) { + pra->referenced++; + pra->vm_flags |= vma->vm_flags; + } + + if (!pra->mapcount) + return false; /* To break the loop */ + + return true; +} + +static bool invalid_page_referenced_vma(struct vm_area_struct *vma, void *arg) +{ + struct page_referenced_arg *pra = arg; + struct mem_cgroup *memcg = pra->memcg; + + if (!mm_match_cgroup(vma->vm_mm, memcg)) + return true; + + return false; +} + +/** + * page_referenced - test if the page was referenced + * @page: the page to test + * @is_locked: caller holds lock on the page + * @memcg: target memory cgroup + * @vm_flags: collect encountered vma->vm_flags who actually referenced the page + * + * Quick test_and_clear_referenced for all mappings to a page, + * returns the number of ptes which referenced the page. + */ +int page_referenced(struct page *page, + int is_locked, + struct mem_cgroup *memcg, + unsigned long *vm_flags) +{ + int we_locked = 0; + struct page_referenced_arg pra = { + .mapcount = total_mapcount(page), + .memcg = memcg, + }; + struct rmap_walk_control rwc = { + .rmap_one = page_referenced_one, + .arg = (void *)&pra, + .anon_lock = page_lock_anon_vma_read, + }; + + *vm_flags = 0; + if (!pra.mapcount) + return 0; + + if (!page_rmapping(page)) + return 0; + + if (!is_locked && (!PageAnon(page) || PageKsm(page))) { + we_locked = trylock_page(page); + if (!we_locked) + return 1; + } + + /* + * If we are reclaiming on behalf of a cgroup, skip + * counting on behalf of references from different + * cgroups + */ + if (memcg) { + rwc.invalid_vma = invalid_page_referenced_vma; + } + + rmap_walk(page, &rwc); + *vm_flags = pra.vm_flags; + + if (we_locked) + unlock_page(page); + + return pra.referenced; +} + +static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, + unsigned long address, void *arg) +{ + struct page_vma_mapped_walk pvmw = { + .page = page, + .vma = vma, + .address = address, + .flags = PVMW_SYNC, + }; + struct mmu_notifier_range range; + int *cleaned = arg; + + /* + * We have to assume the worse case ie pmd for invalidation. Note that + * the page can not be free from this function. + */ + mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, + 0, vma, vma->vm_mm, address, + vma_address_end(page, vma)); + mmu_notifier_invalidate_range_start(&range); + + while (page_vma_mapped_walk(&pvmw)) { + int ret = 0; + + address = pvmw.address; + if (pvmw.pte) { + pte_t entry; + pte_t *pte = pvmw.pte; + + if (!pte_dirty(*pte) && !pte_write(*pte)) + continue; + + flush_cache_page(vma, address, pte_pfn(*pte)); + entry = ptep_clear_flush(vma, address, pte); + entry = pte_wrprotect(entry); + entry = pte_mkclean(entry); + set_pte_at(vma->vm_mm, address, pte, entry); + ret = 1; + } else { +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + pmd_t *pmd = pvmw.pmd; + pmd_t entry; + + if (!pmd_dirty(*pmd) && !pmd_write(*pmd)) + continue; + + flush_cache_page(vma, address, page_to_pfn(page)); + entry = pmdp_invalidate(vma, address, pmd); + entry = pmd_wrprotect(entry); + entry = pmd_mkclean(entry); + set_pmd_at(vma->vm_mm, address, pmd, entry); + ret = 1; +#else + /* unexpected pmd-mapped page? */ + WARN_ON_ONCE(1); +#endif + } + + /* + * No need to call mmu_notifier_invalidate_range() as we are + * downgrading page table protection not changing it to point + * to a new page. + * + * See Documentation/vm/mmu_notifier.rst + */ + if (ret) + (*cleaned)++; + } + + mmu_notifier_invalidate_range_end(&range); + + return true; +} + +static bool invalid_mkclean_vma(struct vm_area_struct *vma, void *arg) +{ + if (vma->vm_flags & VM_SHARED) + return false; + + return true; +} + +int page_mkclean(struct page *page) +{ + int cleaned = 0; + struct address_space *mapping; + struct rmap_walk_control rwc = { + .arg = (void *)&cleaned, + .rmap_one = page_mkclean_one, + .invalid_vma = invalid_mkclean_vma, + }; + + BUG_ON(!PageLocked(page)); + + if (!page_mapped(page)) + return 0; + + mapping = page_mapping(page); + if (!mapping) + return 0; + + rmap_walk(page, &rwc); + + return cleaned; +} +EXPORT_SYMBOL_GPL(page_mkclean); + +/** + * page_move_anon_rmap - move a page to our anon_vma + * @page: the page to move to our anon_vma + * @vma: the vma the page belongs to + * + * When a page belongs exclusively to one process after a COW event, + * that page can be moved into the anon_vma that belongs to just that + * process, so the rmap code will not search the parent or sibling + * processes. + */ +void page_move_anon_rmap(struct page *page, struct vm_area_struct *vma) +{ + struct anon_vma *anon_vma = vma->anon_vma; + + page = compound_head(page); + + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_VMA(!anon_vma, vma); + + anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON; + /* + * Ensure that anon_vma and the PAGE_MAPPING_ANON bit are written + * simultaneously, so a concurrent reader (eg page_referenced()'s + * PageAnon()) will not see one without the other. + */ + WRITE_ONCE(page->mapping, (struct address_space *) anon_vma); +} + +/** + * __page_set_anon_rmap - set up new anonymous rmap + * @page: Page or Hugepage to add to rmap + * @vma: VM area to add page to. + * @address: User virtual address of the mapping + * @exclusive: the page is exclusively owned by the current process + */ +static void __page_set_anon_rmap(struct page *page, + struct vm_area_struct *vma, unsigned long address, int exclusive) +{ + struct anon_vma *anon_vma = vma->anon_vma; + + BUG_ON(!anon_vma); + + if (PageAnon(page)) + return; + + /* + * If the page isn't exclusively mapped into this vma, + * we must use the _oldest_ possible anon_vma for the + * page mapping! + */ + if (!exclusive) + anon_vma = anon_vma->root; + + anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON; + page->mapping = (struct address_space *) anon_vma; + page->index = linear_page_index(vma, address); +} + +/** + * __page_check_anon_rmap - sanity check anonymous rmap addition + * @page: the page to add the mapping to + * @vma: the vm area in which the mapping is added + * @address: the user virtual address mapped + */ +static void __page_check_anon_rmap(struct page *page, + struct vm_area_struct *vma, unsigned long address) +{ + /* + * The page's anon-rmap details (mapping and index) are guaranteed to + * be set up correctly at this point. + * + * We have exclusion against page_add_anon_rmap because the caller + * always holds the page locked, except if called from page_dup_rmap, + * in which case the page is already known to be setup. + * + * We have exclusion against page_add_new_anon_rmap because those pages + * are initially only visible via the pagetables, and the pte is locked + * over the call to page_add_new_anon_rmap. + */ + VM_BUG_ON_PAGE(page_anon_vma(page)->root != vma->anon_vma->root, page); + VM_BUG_ON_PAGE(page_to_pgoff(page) != linear_page_index(vma, address), + page); +} + +/** + * page_add_anon_rmap - add pte mapping to an anonymous page + * @page: the page to add the mapping to + * @vma: the vm area in which the mapping is added + * @address: the user virtual address mapped + * @compound: charge the page as compound or small page + * + * The caller needs to hold the pte lock, and the page must be locked in + * the anon_vma case: to serialize mapping,index checking after setting, + * and to ensure that PageAnon is not being upgraded racily to PageKsm + * (but PageKsm is never downgraded to PageAnon). + */ +void page_add_anon_rmap(struct page *page, + struct vm_area_struct *vma, unsigned long address, bool compound) +{ + do_page_add_anon_rmap(page, vma, address, compound ? RMAP_COMPOUND : 0); +} + +/* + * Special version of the above for do_swap_page, which often runs + * into pages that are exclusively owned by the current process. + * Everybody else should continue to use page_add_anon_rmap above. + */ +void do_page_add_anon_rmap(struct page *page, + struct vm_area_struct *vma, unsigned long address, int flags) +{ + bool compound = flags & RMAP_COMPOUND; + bool first; + + if (unlikely(PageKsm(page))) + lock_page_memcg(page); + else + VM_BUG_ON_PAGE(!PageLocked(page), page); + + if (compound) { + atomic_t *mapcount; + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(!PageTransHuge(page), page); + mapcount = compound_mapcount_ptr(page); + first = atomic_inc_and_test(mapcount); + } else { + first = atomic_inc_and_test(&page->_mapcount); + } + + if (first) { + int nr = compound ? thp_nr_pages(page) : 1; + /* + * We use the irq-unsafe __{inc|mod}_zone_page_stat because + * these counters are not modified in interrupt context, and + * pte lock(a spinlock) is held, which implies preemption + * disabled. + */ + if (compound) + __inc_lruvec_page_state(page, NR_ANON_THPS); + __mod_lruvec_page_state(page, NR_ANON_MAPPED, nr); + } + + if (unlikely(PageKsm(page))) { + unlock_page_memcg(page); + return; + } + + /* address might be in next vma when migration races vma_adjust */ + if (first) + __page_set_anon_rmap(page, vma, address, + flags & RMAP_EXCLUSIVE); + else + __page_check_anon_rmap(page, vma, address); +} + +/** + * page_add_new_anon_rmap - add pte mapping to a new anonymous page + * @page: the page to add the mapping to + * @vma: the vm area in which the mapping is added + * @address: the user virtual address mapped + * @compound: charge the page as compound or small page + * + * Same as page_add_anon_rmap but must only be called on *new* pages. + * This means the inc-and-test can be bypassed. + * Page does not have to be locked. + */ +void page_add_new_anon_rmap(struct page *page, + struct vm_area_struct *vma, unsigned long address, bool compound) +{ + int nr = compound ? thp_nr_pages(page) : 1; + + VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma); + __SetPageSwapBacked(page); + if (compound) { + VM_BUG_ON_PAGE(!PageTransHuge(page), page); + /* increment count (starts at -1) */ + atomic_set(compound_mapcount_ptr(page), 0); + if (hpage_pincount_available(page)) + atomic_set(compound_pincount_ptr(page), 0); + + __inc_lruvec_page_state(page, NR_ANON_THPS); + } else { + /* Anon THP always mapped first with PMD */ + VM_BUG_ON_PAGE(PageTransCompound(page), page); + /* increment count (starts at -1) */ + atomic_set(&page->_mapcount, 0); + } + __mod_lruvec_page_state(page, NR_ANON_MAPPED, nr); + __page_set_anon_rmap(page, vma, address, 1); +} + +/** + * page_add_file_rmap - add pte mapping to a file page + * @page: the page to add the mapping to + * @compound: charge the page as compound or small page + * + * The caller needs to hold the pte lock. + */ +void page_add_file_rmap(struct page *page, bool compound) +{ + int i, nr = 1; + + VM_BUG_ON_PAGE(compound && !PageTransHuge(page), page); + lock_page_memcg(page); + if (compound && PageTransHuge(page)) { + for (i = 0, nr = 0; i < thp_nr_pages(page); i++) { + if (atomic_inc_and_test(&page[i]._mapcount)) + nr++; + } + if (!atomic_inc_and_test(compound_mapcount_ptr(page))) + goto out; + if (PageSwapBacked(page)) + __inc_node_page_state(page, NR_SHMEM_PMDMAPPED); + else + __inc_node_page_state(page, NR_FILE_PMDMAPPED); + } else { + if (PageTransCompound(page) && page_mapping(page)) { + VM_WARN_ON_ONCE(!PageLocked(page)); + + SetPageDoubleMap(compound_head(page)); + if (PageMlocked(page)) + clear_page_mlock(compound_head(page)); + } + if (!atomic_inc_and_test(&page->_mapcount)) + goto out; + } + __mod_lruvec_page_state(page, NR_FILE_MAPPED, nr); +out: + unlock_page_memcg(page); +} + +static void page_remove_file_rmap(struct page *page, bool compound) +{ + int i, nr = 1; + + VM_BUG_ON_PAGE(compound && !PageHead(page), page); + + /* Hugepages are not counted in NR_FILE_MAPPED for now. */ + if (unlikely(PageHuge(page))) { + /* hugetlb pages are always mapped with pmds */ + atomic_dec(compound_mapcount_ptr(page)); + return; + } + + /* page still mapped by someone else? */ + if (compound && PageTransHuge(page)) { + for (i = 0, nr = 0; i < thp_nr_pages(page); i++) { + if (atomic_add_negative(-1, &page[i]._mapcount)) + nr++; + } + if (!atomic_add_negative(-1, compound_mapcount_ptr(page))) + return; + if (PageSwapBacked(page)) + __dec_node_page_state(page, NR_SHMEM_PMDMAPPED); + else + __dec_node_page_state(page, NR_FILE_PMDMAPPED); + } else { + if (!atomic_add_negative(-1, &page->_mapcount)) + return; + } + + /* + * We use the irq-unsafe __{inc|mod}_lruvec_page_state because + * these counters are not modified in interrupt context, and + * pte lock(a spinlock) is held, which implies preemption disabled. + */ + __mod_lruvec_page_state(page, NR_FILE_MAPPED, -nr); + + if (unlikely(PageMlocked(page))) + clear_page_mlock(page); +} + +static void page_remove_anon_compound_rmap(struct page *page) +{ + int i, nr; + + if (!atomic_add_negative(-1, compound_mapcount_ptr(page))) + return; + + /* Hugepages are not counted in NR_ANON_PAGES for now. */ + if (unlikely(PageHuge(page))) + return; + + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + return; + + __dec_lruvec_page_state(page, NR_ANON_THPS); + + if (TestClearPageDoubleMap(page)) { + /* + * Subpages can be mapped with PTEs too. Check how many of + * them are still mapped. + */ + for (i = 0, nr = 0; i < thp_nr_pages(page); i++) { + if (atomic_add_negative(-1, &page[i]._mapcount)) + nr++; + } + + /* + * Queue the page for deferred split if at least one small + * page of the compound page is unmapped, but at least one + * small page is still mapped. + */ + if (nr && nr < thp_nr_pages(page)) + deferred_split_huge_page(page); + } else { + nr = thp_nr_pages(page); + } + + if (unlikely(PageMlocked(page))) + clear_page_mlock(page); + + if (nr) + __mod_lruvec_page_state(page, NR_ANON_MAPPED, -nr); +} + +/** + * page_remove_rmap - take down pte mapping from a page + * @page: page to remove mapping from + * @compound: uncharge the page as compound or small page + * + * The caller needs to hold the pte lock. + */ +void page_remove_rmap(struct page *page, bool compound) +{ + lock_page_memcg(page); + + if (!PageAnon(page)) { + page_remove_file_rmap(page, compound); + goto out; + } + + if (compound) { + page_remove_anon_compound_rmap(page); + goto out; + } + + /* page still mapped by someone else? */ + if (!atomic_add_negative(-1, &page->_mapcount)) + goto out; + + /* + * We use the irq-unsafe __{inc|mod}_zone_page_stat because + * these counters are not modified in interrupt context, and + * pte lock(a spinlock) is held, which implies preemption disabled. + */ + __dec_lruvec_page_state(page, NR_ANON_MAPPED); + + if (unlikely(PageMlocked(page))) + clear_page_mlock(page); + + if (PageTransCompound(page)) + deferred_split_huge_page(compound_head(page)); + + /* + * It would be tidy to reset the PageAnon mapping here, + * but that might overwrite a racing page_add_anon_rmap + * which increments mapcount after us but sets mapping + * before us: so leave the reset to free_unref_page, + * and remember that it's only reliable while mapped. + * Leaving it set also helps swapoff to reinstate ptes + * faster for those pages still in swapcache. + */ +out: + unlock_page_memcg(page); +} + +/* + * @arg: enum ttu_flags will be passed to this argument + */ +static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, + unsigned long address, void *arg) +{ + struct mm_struct *mm = vma->vm_mm; + struct page_vma_mapped_walk pvmw = { + .page = page, + .vma = vma, + .address = address, + }; + pte_t pteval; + struct page *subpage; + bool ret = true; + struct mmu_notifier_range range; + enum ttu_flags flags = (enum ttu_flags)(long)arg; + + /* + * When racing against e.g. zap_pte_range() on another cpu, + * in between its ptep_get_and_clear_full() and page_remove_rmap(), + * try_to_unmap() may return false when it is about to become true, + * if page table locking is skipped: use TTU_SYNC to wait for that. + */ + if (flags & TTU_SYNC) + pvmw.flags = PVMW_SYNC; + + /* munlock has nothing to gain from examining un-locked vmas */ + if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED)) + return true; + + if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION) && + is_zone_device_page(page) && !is_device_private_page(page)) + return true; + + if (flags & TTU_SPLIT_HUGE_PMD) { + split_huge_pmd_address(vma, address, + flags & TTU_SPLIT_FREEZE, page); + } + + /* + * For THP, we have to assume the worse case ie pmd for invalidation. + * For hugetlb, it could be much worse if we need to do pud + * invalidation in the case of pmd sharing. + * + * Note that the page can not be free in this function as call of + * try_to_unmap() must hold a reference on the page. + */ + range.end = PageKsm(page) ? + address + PAGE_SIZE : vma_address_end(page, vma); + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, + address, range.end); + if (PageHuge(page)) { + /* + * If sharing is possible, start and end will be adjusted + * accordingly. + */ + adjust_range_if_pmd_sharing_possible(vma, &range.start, + &range.end); + } + mmu_notifier_invalidate_range_start(&range); + + while (page_vma_mapped_walk(&pvmw)) { +#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION + /* PMD-mapped THP migration entry */ + if (!pvmw.pte && (flags & TTU_MIGRATION)) { + VM_BUG_ON_PAGE(PageHuge(page) || !PageTransCompound(page), page); + + set_pmd_migration_entry(&pvmw, page); + continue; + } +#endif + + /* + * If the page is mlock()d, we cannot swap it out. + * If it's recently referenced (perhaps page_referenced + * skipped over this mm) then we should reactivate it. + */ + if (!(flags & TTU_IGNORE_MLOCK)) { + if (vma->vm_flags & VM_LOCKED) { + /* PTE-mapped THP are never mlocked */ + if (!PageTransCompound(page)) { + /* + * Holding pte lock, we do *not* need + * mmap_lock here + */ + mlock_vma_page(page); + } + ret = false; + page_vma_mapped_walk_done(&pvmw); + break; + } + if (flags & TTU_MUNLOCK) + continue; + } + + /* Unexpected PMD-mapped THP? */ + VM_BUG_ON_PAGE(!pvmw.pte, page); + + subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte); + address = pvmw.address; + + if (PageHuge(page) && !PageAnon(page)) { + /* + * To call huge_pmd_unshare, i_mmap_rwsem must be + * held in write mode. Caller needs to explicitly + * do this outside rmap routines. + */ + VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); + if (huge_pmd_unshare(mm, vma, &address, pvmw.pte)) { + /* + * huge_pmd_unshare unmapped an entire PMD + * page. There is no way of knowing exactly + * which PMDs may be cached for this mm, so + * we must flush them all. start/end were + * already adjusted above to cover this range. + */ + flush_cache_range(vma, range.start, range.end); + flush_tlb_range(vma, range.start, range.end); + mmu_notifier_invalidate_range(mm, range.start, + range.end); + + /* + * The ref count of the PMD page was dropped + * which is part of the way map counting + * is done for shared PMDs. Return 'true' + * here. When there is no other sharing, + * huge_pmd_unshare returns false and we will + * unmap the actual page and drop map count + * to zero. + */ + page_vma_mapped_walk_done(&pvmw); + break; + } + } + + if (IS_ENABLED(CONFIG_MIGRATION) && + (flags & TTU_MIGRATION) && + is_zone_device_page(page)) { + swp_entry_t entry; + pte_t swp_pte; + + pteval = ptep_get_and_clear(mm, pvmw.address, pvmw.pte); + + /* + * Store the pfn of the page in a special migration + * pte. do_swap_page() will wait until the migration + * pte is removed and then restart fault handling. + */ + entry = make_migration_entry(page, 0); + swp_pte = swp_entry_to_pte(entry); + + /* + * pteval maps a zone device page and is therefore + * a swap pte. + */ + if (pte_swp_soft_dirty(pteval)) + swp_pte = pte_swp_mksoft_dirty(swp_pte); + if (pte_swp_uffd_wp(pteval)) + swp_pte = pte_swp_mkuffd_wp(swp_pte); + set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte); + /* + * No need to invalidate here it will synchronize on + * against the special swap migration pte. + * + * The assignment to subpage above was computed from a + * swap PTE which results in an invalid pointer. + * Since only PAGE_SIZE pages can currently be + * migrated, just set it to page. This will need to be + * changed when hugepage migrations to device private + * memory are supported. + */ + subpage = page; + goto discard; + } + + /* Nuke the page table entry. */ + flush_cache_page(vma, address, pte_pfn(*pvmw.pte)); + if (should_defer_flush(mm, flags)) { + /* + * We clear the PTE but do not flush so potentially + * a remote CPU could still be writing to the page. + * If the entry was previously clean then the + * architecture must guarantee that a clear->dirty + * transition on a cached TLB entry is written through + * and traps if the PTE is unmapped. + */ + pteval = ptep_get_and_clear(mm, address, pvmw.pte); + + set_tlb_ubc_flush_pending(mm, pte_dirty(pteval)); + } else { + pteval = ptep_clear_flush(vma, address, pvmw.pte); + } + + /* Move the dirty bit to the page. Now the pte is gone. */ + if (pte_dirty(pteval)) + set_page_dirty(page); + + /* Update high watermark before we lower rss */ + update_hiwater_rss(mm); + + if (PageHWPoison(page) && !(flags & TTU_IGNORE_HWPOISON)) { + pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); + if (PageHuge(page)) { + hugetlb_count_sub(compound_nr(page), mm); + set_huge_swap_pte_at(mm, address, + pvmw.pte, pteval, + vma_mmu_pagesize(vma)); + } else { + dec_mm_counter(mm, mm_counter(page)); + set_pte_at(mm, address, pvmw.pte, pteval); + } + + } else if (pte_unused(pteval) && !userfaultfd_armed(vma)) { + /* + * The guest indicated that the page content is of no + * interest anymore. Simply discard the pte, vmscan + * will take care of the rest. + * A future reference will then fault in a new zero + * page. When userfaultfd is active, we must not drop + * this page though, as its main user (postcopy + * migration) will not expect userfaults on already + * copied pages. + */ + dec_mm_counter(mm, mm_counter(page)); + /* We have to invalidate as we cleared the pte */ + mmu_notifier_invalidate_range(mm, address, + address + PAGE_SIZE); + } else if (IS_ENABLED(CONFIG_MIGRATION) && + (flags & (TTU_MIGRATION|TTU_SPLIT_FREEZE))) { + swp_entry_t entry; + pte_t swp_pte; + + if (arch_unmap_one(mm, vma, address, pteval) < 0) { + set_pte_at(mm, address, pvmw.pte, pteval); + ret = false; + page_vma_mapped_walk_done(&pvmw); + break; + } + + /* + * Store the pfn of the page in a special migration + * pte. do_swap_page() will wait until the migration + * pte is removed and then restart fault handling. + */ + entry = make_migration_entry(subpage, + pte_write(pteval)); + swp_pte = swp_entry_to_pte(entry); + if (pte_soft_dirty(pteval)) + swp_pte = pte_swp_mksoft_dirty(swp_pte); + if (pte_uffd_wp(pteval)) + swp_pte = pte_swp_mkuffd_wp(swp_pte); + set_pte_at(mm, address, pvmw.pte, swp_pte); + /* + * No need to invalidate here it will synchronize on + * against the special swap migration pte. + */ + } else if (PageAnon(page)) { + swp_entry_t entry = { .val = page_private(subpage) }; + pte_t swp_pte; + /* + * Store the swap location in the pte. + * See handle_pte_fault() ... + */ + if (unlikely(PageSwapBacked(page) != PageSwapCache(page))) { + WARN_ON_ONCE(1); + ret = false; + /* We have to invalidate as we cleared the pte */ + mmu_notifier_invalidate_range(mm, address, + address + PAGE_SIZE); + page_vma_mapped_walk_done(&pvmw); + break; + } + + /* MADV_FREE page check */ + if (!PageSwapBacked(page)) { + int ref_count, map_count; + + /* + * Synchronize with gup_pte_range(): + * - clear PTE; barrier; read refcount + * - inc refcount; barrier; read PTE + */ + smp_mb(); + + ref_count = page_ref_count(page); + map_count = page_mapcount(page); + + /* + * Order reads for page refcount and dirty flag + * (see comments in __remove_mapping()). + */ + smp_rmb(); + + /* + * The only page refs must be one from isolation + * plus the rmap(s) (dropped by discard:). + */ + if (ref_count == 1 + map_count && + !PageDirty(page)) { + /* Invalidate as we cleared the pte */ + mmu_notifier_invalidate_range(mm, + address, address + PAGE_SIZE); + dec_mm_counter(mm, MM_ANONPAGES); + goto discard; + } + + /* + * If the page was redirtied, it cannot be + * discarded. Remap the page to page table. + */ + set_pte_at(mm, address, pvmw.pte, pteval); + SetPageSwapBacked(page); + ret = false; + page_vma_mapped_walk_done(&pvmw); + break; + } + + if (swap_duplicate(entry) < 0) { + set_pte_at(mm, address, pvmw.pte, pteval); + ret = false; + page_vma_mapped_walk_done(&pvmw); + break; + } + if (arch_unmap_one(mm, vma, address, pteval) < 0) { + set_pte_at(mm, address, pvmw.pte, pteval); + ret = false; + page_vma_mapped_walk_done(&pvmw); + break; + } + if (list_empty(&mm->mmlist)) { + spin_lock(&mmlist_lock); + if (list_empty(&mm->mmlist)) + list_add(&mm->mmlist, &init_mm.mmlist); + spin_unlock(&mmlist_lock); + } + dec_mm_counter(mm, MM_ANONPAGES); + inc_mm_counter(mm, MM_SWAPENTS); + swp_pte = swp_entry_to_pte(entry); + if (pte_soft_dirty(pteval)) + swp_pte = pte_swp_mksoft_dirty(swp_pte); + if (pte_uffd_wp(pteval)) + swp_pte = pte_swp_mkuffd_wp(swp_pte); + set_pte_at(mm, address, pvmw.pte, swp_pte); + /* Invalidate as we cleared the pte */ + mmu_notifier_invalidate_range(mm, address, + address + PAGE_SIZE); + } else { + /* + * This is a locked file-backed page, thus it cannot + * be removed from the page cache and replaced by a new + * page before mmu_notifier_invalidate_range_end, so no + * concurrent thread might update its page table to + * point at new page while a device still is using this + * page. + * + * See Documentation/vm/mmu_notifier.rst + */ + dec_mm_counter(mm, mm_counter_file(page)); + } +discard: + /* + * No need to call mmu_notifier_invalidate_range() it has be + * done above for all cases requiring it to happen under page + * table lock before mmu_notifier_invalidate_range_end() + * + * See Documentation/vm/mmu_notifier.rst + */ + page_remove_rmap(subpage, PageHuge(page)); + put_page(page); + } + + mmu_notifier_invalidate_range_end(&range); + + return ret; +} + +static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg) +{ + return vma_is_temporary_stack(vma); +} + +static int page_not_mapped(struct page *page) +{ + return !page_mapped(page); +} + +/** + * try_to_unmap - try to remove all page table mappings to a page + * @page: the page to get unmapped + * @flags: action and flags + * + * Tries to remove all the page table entries which are mapping this + * page, used in the pageout path. Caller must hold the page lock. + * + * If unmap is successful, return true. Otherwise, false. + */ +bool try_to_unmap(struct page *page, enum ttu_flags flags) +{ + struct rmap_walk_control rwc = { + .rmap_one = try_to_unmap_one, + .arg = (void *)flags, + .done = page_not_mapped, + .anon_lock = page_lock_anon_vma_read, + }; + + /* + * During exec, a temporary VMA is setup and later moved. + * The VMA is moved under the anon_vma lock but not the + * page tables leading to a race where migration cannot + * find the migration ptes. Rather than increasing the + * locking requirements of exec(), migration skips + * temporary VMAs until after exec() completes. + */ + if ((flags & (TTU_MIGRATION|TTU_SPLIT_FREEZE)) + && !PageKsm(page) && PageAnon(page)) + rwc.invalid_vma = invalid_migration_vma; + + if (flags & TTU_RMAP_LOCKED) + rmap_walk_locked(page, &rwc); + else + rmap_walk(page, &rwc); + + /* + * When racing against e.g. zap_pte_range() on another cpu, + * in between its ptep_get_and_clear_full() and page_remove_rmap(), + * try_to_unmap() may return false when it is about to become true, + * if page table locking is skipped: use TTU_SYNC to wait for that. + */ + return !page_mapcount(page); +} + +/** + * try_to_munlock - try to munlock a page + * @page: the page to be munlocked + * + * Called from munlock code. Checks all of the VMAs mapping the page + * to make sure nobody else has this page mlocked. The page will be + * returned with PG_mlocked cleared if no other vmas have it mlocked. + */ + +void try_to_munlock(struct page *page) +{ + struct rmap_walk_control rwc = { + .rmap_one = try_to_unmap_one, + .arg = (void *)TTU_MUNLOCK, + .done = page_not_mapped, + .anon_lock = page_lock_anon_vma_read, + + }; + + VM_BUG_ON_PAGE(!PageLocked(page) || PageLRU(page), page); + VM_BUG_ON_PAGE(PageCompound(page) && PageDoubleMap(page), page); + + rmap_walk(page, &rwc); +} + +void __put_anon_vma(struct anon_vma *anon_vma) +{ + struct anon_vma *root = anon_vma->root; + + anon_vma_free(anon_vma); + if (root != anon_vma && atomic_dec_and_test(&root->refcount)) + anon_vma_free(root); +} + +static struct anon_vma *rmap_walk_anon_lock(struct page *page, + struct rmap_walk_control *rwc) +{ + struct anon_vma *anon_vma; + + if (rwc->anon_lock) + return rwc->anon_lock(page); + + /* + * Note: remove_migration_ptes() cannot use page_lock_anon_vma_read() + * because that depends on page_mapped(); but not all its usages + * are holding mmap_lock. Users without mmap_lock are required to + * take a reference count to prevent the anon_vma disappearing + */ + anon_vma = page_anon_vma(page); + if (!anon_vma) + return NULL; + + anon_vma_lock_read(anon_vma); + return anon_vma; +} + +/* + * rmap_walk_anon - do something to anonymous page using the object-based + * rmap method + * @page: the page to be handled + * @rwc: control variable according to each walk type + * + * Find all the mappings of a page using the mapping pointer and the vma chains + * contained in the anon_vma struct it points to. + * + * When called from try_to_munlock(), the mmap_lock of the mm containing the vma + * where the page was found will be held for write. So, we won't recheck + * vm_flags for that VMA. That should be OK, because that vma shouldn't be + * LOCKED. + */ +static void rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc, + bool locked) +{ + struct anon_vma *anon_vma; + pgoff_t pgoff_start, pgoff_end; + struct anon_vma_chain *avc; + + if (locked) { + anon_vma = page_anon_vma(page); + /* anon_vma disappear under us? */ + VM_BUG_ON_PAGE(!anon_vma, page); + } else { + anon_vma = rmap_walk_anon_lock(page, rwc); + } + if (!anon_vma) + return; + + pgoff_start = page_to_pgoff(page); + pgoff_end = pgoff_start + thp_nr_pages(page) - 1; + anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, + pgoff_start, pgoff_end) { + struct vm_area_struct *vma = avc->vma; + unsigned long address = vma_address(page, vma); + + VM_BUG_ON_VMA(address == -EFAULT, vma); + cond_resched(); + + if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) + continue; + + if (!rwc->rmap_one(page, vma, address, rwc->arg)) + break; + if (rwc->done && rwc->done(page)) + break; + } + + if (!locked) + anon_vma_unlock_read(anon_vma); +} + +/* + * rmap_walk_file - do something to file page using the object-based rmap method + * @page: the page to be handled + * @rwc: control variable according to each walk type + * + * Find all the mappings of a page using the mapping pointer and the vma chains + * contained in the address_space struct it points to. + * + * When called from try_to_munlock(), the mmap_lock of the mm containing the vma + * where the page was found will be held for write. So, we won't recheck + * vm_flags for that VMA. That should be OK, because that vma shouldn't be + * LOCKED. + */ +static void rmap_walk_file(struct page *page, struct rmap_walk_control *rwc, + bool locked) +{ + struct address_space *mapping = page_mapping(page); + pgoff_t pgoff_start, pgoff_end; + struct vm_area_struct *vma; + + /* + * The page lock not only makes sure that page->mapping cannot + * suddenly be NULLified by truncation, it makes sure that the + * structure at mapping cannot be freed and reused yet, + * so we can safely take mapping->i_mmap_rwsem. + */ + VM_BUG_ON_PAGE(!PageLocked(page), page); + + if (!mapping) + return; + + pgoff_start = page_to_pgoff(page); + pgoff_end = pgoff_start + thp_nr_pages(page) - 1; + if (!locked) + i_mmap_lock_read(mapping); + vma_interval_tree_foreach(vma, &mapping->i_mmap, + pgoff_start, pgoff_end) { + unsigned long address = vma_address(page, vma); + + VM_BUG_ON_VMA(address == -EFAULT, vma); + cond_resched(); + + if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) + continue; + + if (!rwc->rmap_one(page, vma, address, rwc->arg)) + goto done; + if (rwc->done && rwc->done(page)) + goto done; + } + +done: + if (!locked) + i_mmap_unlock_read(mapping); +} + +void rmap_walk(struct page *page, struct rmap_walk_control *rwc) +{ + if (unlikely(PageKsm(page))) + rmap_walk_ksm(page, rwc); + else if (PageAnon(page)) + rmap_walk_anon(page, rwc, false); + else + rmap_walk_file(page, rwc, false); +} + +/* Like rmap_walk, but caller holds relevant rmap lock */ +void rmap_walk_locked(struct page *page, struct rmap_walk_control *rwc) +{ + /* no ksm support for now */ + VM_BUG_ON_PAGE(PageKsm(page), page); + if (PageAnon(page)) + rmap_walk_anon(page, rwc, true); + else + rmap_walk_file(page, rwc, true); +} + +#ifdef CONFIG_HUGETLB_PAGE +/* + * The following two functions are for anonymous (private mapped) hugepages. + * Unlike common anonymous pages, anonymous hugepages have no accounting code + * and no lru code, because we handle hugepages differently from common pages. + */ +void hugepage_add_anon_rmap(struct page *page, + struct vm_area_struct *vma, unsigned long address) +{ + struct anon_vma *anon_vma = vma->anon_vma; + int first; + + BUG_ON(!PageLocked(page)); + BUG_ON(!anon_vma); + /* address might be in next vma when migration races vma_adjust */ + first = atomic_inc_and_test(compound_mapcount_ptr(page)); + if (first) + __page_set_anon_rmap(page, vma, address, 0); +} + +void hugepage_add_new_anon_rmap(struct page *page, + struct vm_area_struct *vma, unsigned long address) +{ + BUG_ON(address < vma->vm_start || address >= vma->vm_end); + atomic_set(compound_mapcount_ptr(page), 0); + if (hpage_pincount_available(page)) + atomic_set(compound_pincount_ptr(page), 0); + + __page_set_anon_rmap(page, vma, address, 1); +} +#endif /* CONFIG_HUGETLB_PAGE */ diff --git a/mm/rodata_test.c b/mm/rodata_test.c new file mode 100644 index 000000000..261337194 --- /dev/null +++ b/mm/rodata_test.c @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * rodata_test.c: functional test for mark_rodata_ro function + * + * (C) Copyright 2008 Intel Corporation + * Author: Arjan van de Ven + */ +#define pr_fmt(fmt) "rodata_test: " fmt + +#include +#include +#include + +static const int rodata_test_data = 0xC3; + +void rodata_test(void) +{ + unsigned long start, end; + int zero = 0; + + /* test 1: read the value */ + /* If this test fails, some previous testrun has clobbered the state */ + if (!rodata_test_data) { + pr_err("test 1 fails (start data)\n"); + return; + } + + /* test 2: write to the variable; this should fault */ + if (!copy_to_kernel_nofault((void *)&rodata_test_data, + (void *)&zero, sizeof(zero))) { + pr_err("test data was not read only\n"); + return; + } + + /* test 3: check the value hasn't changed */ + if (rodata_test_data == zero) { + pr_err("test data was changed\n"); + return; + } + + /* test 4: check if the rodata section is PAGE_SIZE aligned */ + start = (unsigned long)__start_rodata; + end = (unsigned long)__end_rodata; + if (start & (PAGE_SIZE - 1)) { + pr_err("start of .rodata is not page size aligned\n"); + return; + } + if (end & (PAGE_SIZE - 1)) { + pr_err("end of .rodata is not page size aligned\n"); + return; + } + + pr_info("all tests were successful\n"); +} diff --git a/mm/shmem.c b/mm/shmem.c new file mode 100644 index 000000000..e173d83b4 --- /dev/null +++ b/mm/shmem.c @@ -0,0 +1,4350 @@ +/* + * Resizable virtual memory filesystem for Linux. + * + * Copyright (C) 2000 Linus Torvalds. + * 2000 Transmeta Corp. + * 2000-2001 Christoph Rohland + * 2000-2001 SAP AG + * 2002 Red Hat Inc. + * Copyright (C) 2002-2011 Hugh Dickins. + * Copyright (C) 2011 Google Inc. + * Copyright (C) 2002-2005 VERITAS Software Corporation. + * Copyright (C) 2004 Andi Kleen, SuSE Labs + * + * Extended attribute support for tmpfs: + * Copyright (c) 2004, Luke Kenneth Casson Leighton + * Copyright (c) 2004 Red Hat, Inc., James Morris + * + * tiny-shmem: + * Copyright (c) 2004, 2008 Matt Mackall + * + * This file is released under the GPL. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include /* for arch/microblaze update_mmu_cache() */ + +static struct vfsmount *shm_mnt; + +#ifdef CONFIG_SHMEM +/* + * This virtual memory filesystem is heavily based on the ramfs. It + * extends ramfs by the ability to use swap and honor resource limits + * which makes it a completely usable filesystem. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "internal.h" + +#define BLOCKS_PER_PAGE (PAGE_SIZE/512) +#define VM_ACCT(size) (PAGE_ALIGN(size) >> PAGE_SHIFT) + +/* Pretend that each entry is of this size in directory's i_size */ +#define BOGO_DIRENT_SIZE 20 + +/* Symlink up to this size is kmalloc'ed instead of using a swappable page */ +#define SHORT_SYMLINK_LEN 128 + +/* + * shmem_fallocate communicates with shmem_fault or shmem_writepage via + * inode->i_private (with i_mutex making sure that it has only one user at + * a time): we would prefer not to enlarge the shmem inode just for that. + */ +struct shmem_falloc { + wait_queue_head_t *waitq; /* faults into hole wait for punch to end */ + pgoff_t start; /* start of range currently being fallocated */ + pgoff_t next; /* the next page offset to be fallocated */ + pgoff_t nr_falloced; /* how many new pages have been fallocated */ + pgoff_t nr_unswapped; /* how often writepage refused to swap out */ +}; + +struct shmem_options { + unsigned long long blocks; + unsigned long long inodes; + struct mempolicy *mpol; + kuid_t uid; + kgid_t gid; + umode_t mode; + bool full_inums; + int huge; + int seen; +#define SHMEM_SEEN_BLOCKS 1 +#define SHMEM_SEEN_INODES 2 +#define SHMEM_SEEN_HUGE 4 +#define SHMEM_SEEN_INUMS 8 +}; + +#ifdef CONFIG_TMPFS +static unsigned long shmem_default_max_blocks(void) +{ + return totalram_pages() / 2; +} + +static unsigned long shmem_default_max_inodes(void) +{ + unsigned long nr_pages = totalram_pages(); + + return min(nr_pages - totalhigh_pages(), nr_pages / 2); +} +#endif + +static bool shmem_should_replace_page(struct page *page, gfp_t gfp); +static int shmem_replace_page(struct page **pagep, gfp_t gfp, + struct shmem_inode_info *info, pgoff_t index); +static int shmem_swapin_page(struct inode *inode, pgoff_t index, + struct page **pagep, enum sgp_type sgp, + gfp_t gfp, struct vm_area_struct *vma, + vm_fault_t *fault_type); +static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, + struct page **pagep, enum sgp_type sgp, + gfp_t gfp, struct vm_area_struct *vma, + struct vm_fault *vmf, vm_fault_t *fault_type); + +int shmem_getpage(struct inode *inode, pgoff_t index, + struct page **pagep, enum sgp_type sgp) +{ + return shmem_getpage_gfp(inode, index, pagep, sgp, + mapping_gfp_mask(inode->i_mapping), NULL, NULL, NULL); +} + +static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb) +{ + return sb->s_fs_info; +} + +/* + * shmem_file_setup pre-accounts the whole fixed size of a VM object, + * for shared memory and for shared anonymous (/dev/zero) mappings + * (unless MAP_NORESERVE and sysctl_overcommit_memory <= 1), + * consistent with the pre-accounting of private mappings ... + */ +static inline int shmem_acct_size(unsigned long flags, loff_t size) +{ + return (flags & VM_NORESERVE) ? + 0 : security_vm_enough_memory_mm(current->mm, VM_ACCT(size)); +} + +static inline void shmem_unacct_size(unsigned long flags, loff_t size) +{ + if (!(flags & VM_NORESERVE)) + vm_unacct_memory(VM_ACCT(size)); +} + +static inline int shmem_reacct_size(unsigned long flags, + loff_t oldsize, loff_t newsize) +{ + if (!(flags & VM_NORESERVE)) { + if (VM_ACCT(newsize) > VM_ACCT(oldsize)) + return security_vm_enough_memory_mm(current->mm, + VM_ACCT(newsize) - VM_ACCT(oldsize)); + else if (VM_ACCT(newsize) < VM_ACCT(oldsize)) + vm_unacct_memory(VM_ACCT(oldsize) - VM_ACCT(newsize)); + } + return 0; +} + +/* + * ... whereas tmpfs objects are accounted incrementally as + * pages are allocated, in order to allow large sparse files. + * shmem_getpage reports shmem_acct_block failure as -ENOSPC not -ENOMEM, + * so that a failure on a sparse tmpfs mapping will give SIGBUS not OOM. + */ +static inline int shmem_acct_block(unsigned long flags, long pages) +{ + if (!(flags & VM_NORESERVE)) + return 0; + + return security_vm_enough_memory_mm(current->mm, + pages * VM_ACCT(PAGE_SIZE)); +} + +static inline void shmem_unacct_blocks(unsigned long flags, long pages) +{ + if (flags & VM_NORESERVE) + vm_unacct_memory(pages * VM_ACCT(PAGE_SIZE)); +} + +static inline bool shmem_inode_acct_block(struct inode *inode, long pages) +{ + struct shmem_inode_info *info = SHMEM_I(inode); + struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); + + if (shmem_acct_block(info->flags, pages)) + return false; + + if (sbinfo->max_blocks) { + if (percpu_counter_compare(&sbinfo->used_blocks, + sbinfo->max_blocks - pages) > 0) + goto unacct; + percpu_counter_add(&sbinfo->used_blocks, pages); + } + + return true; + +unacct: + shmem_unacct_blocks(info->flags, pages); + return false; +} + +static inline void shmem_inode_unacct_blocks(struct inode *inode, long pages) +{ + struct shmem_inode_info *info = SHMEM_I(inode); + struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); + + if (sbinfo->max_blocks) + percpu_counter_sub(&sbinfo->used_blocks, pages); + shmem_unacct_blocks(info->flags, pages); +} + +static const struct super_operations shmem_ops; +static const struct address_space_operations shmem_aops; +static const struct file_operations shmem_file_operations; +static const struct inode_operations shmem_inode_operations; +static const struct inode_operations shmem_dir_inode_operations; +static const struct inode_operations shmem_special_inode_operations; +static const struct vm_operations_struct shmem_vm_ops; +static struct file_system_type shmem_fs_type; + +bool vma_is_shmem(struct vm_area_struct *vma) +{ + return vma->vm_ops == &shmem_vm_ops; +} + +static LIST_HEAD(shmem_swaplist); +static DEFINE_MUTEX(shmem_swaplist_mutex); + +/* + * shmem_reserve_inode() performs bookkeeping to reserve a shmem inode, and + * produces a novel ino for the newly allocated inode. + * + * It may also be called when making a hard link to permit the space needed by + * each dentry. However, in that case, no new inode number is needed since that + * internally draws from another pool of inode numbers (currently global + * get_next_ino()). This case is indicated by passing NULL as inop. + */ +#define SHMEM_INO_BATCH 1024 +static int shmem_reserve_inode(struct super_block *sb, ino_t *inop) +{ + struct shmem_sb_info *sbinfo = SHMEM_SB(sb); + ino_t ino; + + if (!(sb->s_flags & SB_KERNMOUNT)) { + spin_lock(&sbinfo->stat_lock); + if (sbinfo->max_inodes) { + if (!sbinfo->free_inodes) { + spin_unlock(&sbinfo->stat_lock); + return -ENOSPC; + } + sbinfo->free_inodes--; + } + if (inop) { + ino = sbinfo->next_ino++; + if (unlikely(is_zero_ino(ino))) + ino = sbinfo->next_ino++; + if (unlikely(!sbinfo->full_inums && + ino > UINT_MAX)) { + /* + * Emulate get_next_ino uint wraparound for + * compatibility + */ + if (IS_ENABLED(CONFIG_64BIT)) + pr_warn("%s: inode number overflow on device %d, consider using inode64 mount option\n", + __func__, MINOR(sb->s_dev)); + sbinfo->next_ino = 1; + ino = sbinfo->next_ino++; + } + *inop = ino; + } + spin_unlock(&sbinfo->stat_lock); + } else if (inop) { + /* + * __shmem_file_setup, one of our callers, is lock-free: it + * doesn't hold stat_lock in shmem_reserve_inode since + * max_inodes is always 0, and is called from potentially + * unknown contexts. As such, use a per-cpu batched allocator + * which doesn't require the per-sb stat_lock unless we are at + * the batch boundary. + * + * We don't need to worry about inode{32,64} since SB_KERNMOUNT + * shmem mounts are not exposed to userspace, so we don't need + * to worry about things like glibc compatibility. + */ + ino_t *next_ino; + next_ino = per_cpu_ptr(sbinfo->ino_batch, get_cpu()); + ino = *next_ino; + if (unlikely(ino % SHMEM_INO_BATCH == 0)) { + spin_lock(&sbinfo->stat_lock); + ino = sbinfo->next_ino; + sbinfo->next_ino += SHMEM_INO_BATCH; + spin_unlock(&sbinfo->stat_lock); + if (unlikely(is_zero_ino(ino))) + ino++; + } + *inop = ino; + *next_ino = ++ino; + put_cpu(); + } + + return 0; +} + +static void shmem_free_inode(struct super_block *sb) +{ + struct shmem_sb_info *sbinfo = SHMEM_SB(sb); + if (sbinfo->max_inodes) { + spin_lock(&sbinfo->stat_lock); + sbinfo->free_inodes++; + spin_unlock(&sbinfo->stat_lock); + } +} + +/** + * shmem_recalc_inode - recalculate the block usage of an inode + * @inode: inode to recalc + * + * We have to calculate the free blocks since the mm can drop + * undirtied hole pages behind our back. + * + * But normally info->alloced == inode->i_mapping->nrpages + info->swapped + * So mm freed is info->alloced - (inode->i_mapping->nrpages + info->swapped) + * + * It has to be called with the spinlock held. + */ +static void shmem_recalc_inode(struct inode *inode) +{ + struct shmem_inode_info *info = SHMEM_I(inode); + long freed; + + freed = info->alloced - info->swapped - inode->i_mapping->nrpages; + if (freed > 0) { + info->alloced -= freed; + inode->i_blocks -= freed * BLOCKS_PER_PAGE; + shmem_inode_unacct_blocks(inode, freed); + } +} + +bool shmem_charge(struct inode *inode, long pages) +{ + struct shmem_inode_info *info = SHMEM_I(inode); + unsigned long flags; + + if (!shmem_inode_acct_block(inode, pages)) + return false; + + /* nrpages adjustment first, then shmem_recalc_inode() when balanced */ + inode->i_mapping->nrpages += pages; + + spin_lock_irqsave(&info->lock, flags); + info->alloced += pages; + inode->i_blocks += pages * BLOCKS_PER_PAGE; + shmem_recalc_inode(inode); + spin_unlock_irqrestore(&info->lock, flags); + + return true; +} + +void shmem_uncharge(struct inode *inode, long pages) +{ + struct shmem_inode_info *info = SHMEM_I(inode); + unsigned long flags; + + /* nrpages adjustment done by __delete_from_page_cache() or caller */ + + spin_lock_irqsave(&info->lock, flags); + info->alloced -= pages; + inode->i_blocks -= pages * BLOCKS_PER_PAGE; + shmem_recalc_inode(inode); + spin_unlock_irqrestore(&info->lock, flags); + + shmem_inode_unacct_blocks(inode, pages); +} + +/* + * Replace item expected in xarray by a new item, while holding xa_lock. + */ +static int shmem_replace_entry(struct address_space *mapping, + pgoff_t index, void *expected, void *replacement) +{ + XA_STATE(xas, &mapping->i_pages, index); + void *item; + + VM_BUG_ON(!expected); + VM_BUG_ON(!replacement); + item = xas_load(&xas); + if (item != expected) + return -ENOENT; + xas_store(&xas, replacement); + return 0; +} + +/* + * Sometimes, before we decide whether to proceed or to fail, we must check + * that an entry was not already brought back from swap by a racing thread. + * + * Checking page is not enough: by the time a SwapCache page is locked, it + * might be reused, and again be SwapCache, using the same swap as before. + */ +static bool shmem_confirm_swap(struct address_space *mapping, + pgoff_t index, swp_entry_t swap) +{ + return xa_load(&mapping->i_pages, index) == swp_to_radix_entry(swap); +} + +/* + * Definitions for "huge tmpfs": tmpfs mounted with the huge= option + * + * SHMEM_HUGE_NEVER: + * disables huge pages for the mount; + * SHMEM_HUGE_ALWAYS: + * enables huge pages for the mount; + * SHMEM_HUGE_WITHIN_SIZE: + * only allocate huge pages if the page will be fully within i_size, + * also respect fadvise()/madvise() hints; + * SHMEM_HUGE_ADVISE: + * only allocate huge pages if requested with fadvise()/madvise(); + */ + +#define SHMEM_HUGE_NEVER 0 +#define SHMEM_HUGE_ALWAYS 1 +#define SHMEM_HUGE_WITHIN_SIZE 2 +#define SHMEM_HUGE_ADVISE 3 + +/* + * Special values. + * Only can be set via /sys/kernel/mm/transparent_hugepage/shmem_enabled: + * + * SHMEM_HUGE_DENY: + * disables huge on shm_mnt and all mounts, for emergency use; + * SHMEM_HUGE_FORCE: + * enables huge on shm_mnt and all mounts, w/o needing option, for testing; + * + */ +#define SHMEM_HUGE_DENY (-1) +#define SHMEM_HUGE_FORCE (-2) + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +/* ifdef here to avoid bloating shmem.o when not necessary */ + +static int shmem_huge __read_mostly; + +#if defined(CONFIG_SYSFS) +static int shmem_parse_huge(const char *str) +{ + if (!strcmp(str, "never")) + return SHMEM_HUGE_NEVER; + if (!strcmp(str, "always")) + return SHMEM_HUGE_ALWAYS; + if (!strcmp(str, "within_size")) + return SHMEM_HUGE_WITHIN_SIZE; + if (!strcmp(str, "advise")) + return SHMEM_HUGE_ADVISE; + if (!strcmp(str, "deny")) + return SHMEM_HUGE_DENY; + if (!strcmp(str, "force")) + return SHMEM_HUGE_FORCE; + return -EINVAL; +} +#endif + +#if defined(CONFIG_SYSFS) || defined(CONFIG_TMPFS) +static const char *shmem_format_huge(int huge) +{ + switch (huge) { + case SHMEM_HUGE_NEVER: + return "never"; + case SHMEM_HUGE_ALWAYS: + return "always"; + case SHMEM_HUGE_WITHIN_SIZE: + return "within_size"; + case SHMEM_HUGE_ADVISE: + return "advise"; + case SHMEM_HUGE_DENY: + return "deny"; + case SHMEM_HUGE_FORCE: + return "force"; + default: + VM_BUG_ON(1); + return "bad_val"; + } +} +#endif + +static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, + struct shrink_control *sc, unsigned long nr_to_split) +{ + LIST_HEAD(list), *pos, *next; + LIST_HEAD(to_remove); + struct inode *inode; + struct shmem_inode_info *info; + struct page *page; + unsigned long batch = sc ? sc->nr_to_scan : 128; + int split = 0; + + if (list_empty(&sbinfo->shrinklist)) + return SHRINK_STOP; + + spin_lock(&sbinfo->shrinklist_lock); + list_for_each_safe(pos, next, &sbinfo->shrinklist) { + info = list_entry(pos, struct shmem_inode_info, shrinklist); + + /* pin the inode */ + inode = igrab(&info->vfs_inode); + + /* inode is about to be evicted */ + if (!inode) { + list_del_init(&info->shrinklist); + goto next; + } + + /* Check if there's anything to gain */ + if (round_up(inode->i_size, PAGE_SIZE) == + round_up(inode->i_size, HPAGE_PMD_SIZE)) { + list_move(&info->shrinklist, &to_remove); + goto next; + } + + list_move(&info->shrinklist, &list); +next: + sbinfo->shrinklist_len--; + if (!--batch) + break; + } + spin_unlock(&sbinfo->shrinklist_lock); + + list_for_each_safe(pos, next, &to_remove) { + info = list_entry(pos, struct shmem_inode_info, shrinklist); + inode = &info->vfs_inode; + list_del_init(&info->shrinklist); + iput(inode); + } + + list_for_each_safe(pos, next, &list) { + int ret; + + info = list_entry(pos, struct shmem_inode_info, shrinklist); + inode = &info->vfs_inode; + + if (nr_to_split && split >= nr_to_split) + goto move_back; + + page = find_get_page(inode->i_mapping, + (inode->i_size & HPAGE_PMD_MASK) >> PAGE_SHIFT); + if (!page) + goto drop; + + /* No huge page at the end of the file: nothing to split */ + if (!PageTransHuge(page)) { + put_page(page); + goto drop; + } + + /* + * Move the inode on the list back to shrinklist if we failed + * to lock the page at this time. + * + * Waiting for the lock may lead to deadlock in the + * reclaim path. + */ + if (!trylock_page(page)) { + put_page(page); + goto move_back; + } + + ret = split_huge_page(page); + unlock_page(page); + put_page(page); + + /* If split failed move the inode on the list back to shrinklist */ + if (ret) + goto move_back; + + split++; +drop: + list_del_init(&info->shrinklist); + goto put; +move_back: + /* + * Make sure the inode is either on the global list or deleted + * from any local list before iput() since it could be deleted + * in another thread once we put the inode (then the local list + * is corrupted). + */ + spin_lock(&sbinfo->shrinklist_lock); + list_move(&info->shrinklist, &sbinfo->shrinklist); + sbinfo->shrinklist_len++; + spin_unlock(&sbinfo->shrinklist_lock); +put: + iput(inode); + } + + return split; +} + +static long shmem_unused_huge_scan(struct super_block *sb, + struct shrink_control *sc) +{ + struct shmem_sb_info *sbinfo = SHMEM_SB(sb); + + if (!READ_ONCE(sbinfo->shrinklist_len)) + return SHRINK_STOP; + + return shmem_unused_huge_shrink(sbinfo, sc, 0); +} + +static long shmem_unused_huge_count(struct super_block *sb, + struct shrink_control *sc) +{ + struct shmem_sb_info *sbinfo = SHMEM_SB(sb); + return READ_ONCE(sbinfo->shrinklist_len); +} +#else /* !CONFIG_TRANSPARENT_HUGEPAGE */ + +#define shmem_huge SHMEM_HUGE_DENY + +static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, + struct shrink_control *sc, unsigned long nr_to_split) +{ + return 0; +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +static inline bool is_huge_enabled(struct shmem_sb_info *sbinfo) +{ + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && + (shmem_huge == SHMEM_HUGE_FORCE || sbinfo->huge) && + shmem_huge != SHMEM_HUGE_DENY) + return true; + return false; +} + +/* + * Like add_to_page_cache_locked, but error if expected item has gone. + */ +static int shmem_add_to_page_cache(struct page *page, + struct address_space *mapping, + pgoff_t index, void *expected, gfp_t gfp, + struct mm_struct *charge_mm) +{ + XA_STATE_ORDER(xas, &mapping->i_pages, index, compound_order(page)); + unsigned long i = 0; + unsigned long nr = compound_nr(page); + int error; + + VM_BUG_ON_PAGE(PageTail(page), page); + VM_BUG_ON_PAGE(index != round_down(index, nr), page); + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(!PageSwapBacked(page), page); + VM_BUG_ON(expected && PageTransHuge(page)); + + page_ref_add(page, nr); + page->mapping = mapping; + page->index = index; + + if (!PageSwapCache(page)) { + error = mem_cgroup_charge(page, charge_mm, gfp); + if (error) { + if (PageTransHuge(page)) { + count_vm_event(THP_FILE_FALLBACK); + count_vm_event(THP_FILE_FALLBACK_CHARGE); + } + goto error; + } + } + cgroup_throttle_swaprate(page, gfp); + + do { + void *entry; + xas_lock_irq(&xas); + entry = xas_find_conflict(&xas); + if (entry != expected) + xas_set_err(&xas, -EEXIST); + xas_create_range(&xas); + if (xas_error(&xas)) + goto unlock; +next: + xas_store(&xas, page); + if (++i < nr) { + xas_next(&xas); + goto next; + } + if (PageTransHuge(page)) { + count_vm_event(THP_FILE_ALLOC); + __inc_node_page_state(page, NR_SHMEM_THPS); + } + mapping->nrpages += nr; + __mod_lruvec_page_state(page, NR_FILE_PAGES, nr); + __mod_lruvec_page_state(page, NR_SHMEM, nr); +unlock: + xas_unlock_irq(&xas); + } while (xas_nomem(&xas, gfp)); + + if (xas_error(&xas)) { + error = xas_error(&xas); + goto error; + } + + return 0; +error: + page->mapping = NULL; + page_ref_sub(page, nr); + return error; +} + +/* + * Like delete_from_page_cache, but substitutes swap for page. + */ +static void shmem_delete_from_page_cache(struct page *page, void *radswap) +{ + struct address_space *mapping = page->mapping; + int error; + + VM_BUG_ON_PAGE(PageCompound(page), page); + + xa_lock_irq(&mapping->i_pages); + error = shmem_replace_entry(mapping, page->index, page, radswap); + page->mapping = NULL; + mapping->nrpages--; + __dec_lruvec_page_state(page, NR_FILE_PAGES); + __dec_lruvec_page_state(page, NR_SHMEM); + xa_unlock_irq(&mapping->i_pages); + put_page(page); + BUG_ON(error); +} + +/* + * Remove swap entry from page cache, free the swap and its page cache. + */ +static int shmem_free_swap(struct address_space *mapping, + pgoff_t index, void *radswap) +{ + void *old; + + old = xa_cmpxchg_irq(&mapping->i_pages, index, radswap, NULL, 0); + if (old != radswap) + return -ENOENT; + free_swap_and_cache(radix_to_swp_entry(radswap)); + return 0; +} + +/* + * Determine (in bytes) how many of the shmem object's pages mapped by the + * given offsets are swapped out. + * + * This is safe to call without i_mutex or the i_pages lock thanks to RCU, + * as long as the inode doesn't go away and racy results are not a problem. + */ +unsigned long shmem_partial_swap_usage(struct address_space *mapping, + pgoff_t start, pgoff_t end) +{ + XA_STATE(xas, &mapping->i_pages, start); + struct page *page; + unsigned long swapped = 0; + + rcu_read_lock(); + xas_for_each(&xas, page, end - 1) { + if (xas_retry(&xas, page)) + continue; + if (xa_is_value(page)) + swapped++; + + if (need_resched()) { + xas_pause(&xas); + cond_resched_rcu(); + } + } + + rcu_read_unlock(); + + return swapped << PAGE_SHIFT; +} + +/* + * Determine (in bytes) how many of the shmem object's pages mapped by the + * given vma is swapped out. + * + * This is safe to call without i_mutex or the i_pages lock thanks to RCU, + * as long as the inode doesn't go away and racy results are not a problem. + */ +unsigned long shmem_swap_usage(struct vm_area_struct *vma) +{ + struct inode *inode = file_inode(vma->vm_file); + struct shmem_inode_info *info = SHMEM_I(inode); + struct address_space *mapping = inode->i_mapping; + unsigned long swapped; + + /* Be careful as we don't hold info->lock */ + swapped = READ_ONCE(info->swapped); + + /* + * The easier cases are when the shmem object has nothing in swap, or + * the vma maps it whole. Then we can simply use the stats that we + * already track. + */ + if (!swapped) + return 0; + + if (!vma->vm_pgoff && vma->vm_end - vma->vm_start >= inode->i_size) + return swapped << PAGE_SHIFT; + + /* Here comes the more involved part */ + return shmem_partial_swap_usage(mapping, + linear_page_index(vma, vma->vm_start), + linear_page_index(vma, vma->vm_end)); +} + +/* + * SysV IPC SHM_UNLOCK restore Unevictable pages to their evictable lists. + */ +void shmem_unlock_mapping(struct address_space *mapping) +{ + struct pagevec pvec; + pgoff_t indices[PAGEVEC_SIZE]; + pgoff_t index = 0; + + pagevec_init(&pvec); + /* + * Minor point, but we might as well stop if someone else SHM_LOCKs it. + */ + while (!mapping_unevictable(mapping)) { + /* + * Avoid pagevec_lookup(): find_get_pages() returns 0 as if it + * has finished, if it hits a row of PAGEVEC_SIZE swap entries. + */ + pvec.nr = find_get_entries(mapping, index, + PAGEVEC_SIZE, pvec.pages, indices); + if (!pvec.nr) + break; + index = indices[pvec.nr - 1] + 1; + pagevec_remove_exceptionals(&pvec); + check_move_unevictable_pages(&pvec); + pagevec_release(&pvec); + cond_resched(); + } +} + +/* + * Check whether a hole-punch or truncation needs to split a huge page, + * returning true if no split was required, or the split has been successful. + * + * Eviction (or truncation to 0 size) should never need to split a huge page; + * but in rare cases might do so, if shmem_undo_range() failed to trylock on + * head, and then succeeded to trylock on tail. + * + * A split can only succeed when there are no additional references on the + * huge page: so the split below relies upon find_get_entries() having stopped + * when it found a subpage of the huge page, without getting further references. + */ +static bool shmem_punch_compound(struct page *page, pgoff_t start, pgoff_t end) +{ + if (!PageTransCompound(page)) + return true; + + /* Just proceed to delete a huge page wholly within the range punched */ + if (PageHead(page) && + page->index >= start && page->index + HPAGE_PMD_NR <= end) + return true; + + /* Try to split huge page, so we can truly punch the hole or truncate */ + return split_huge_page(page) >= 0; +} + +/* + * Remove range of pages and swap entries from page cache, and free them. + * If !unfalloc, truncate or punch hole; if unfalloc, undo failed fallocate. + */ +static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, + bool unfalloc) +{ + struct address_space *mapping = inode->i_mapping; + struct shmem_inode_info *info = SHMEM_I(inode); + pgoff_t start = (lstart + PAGE_SIZE - 1) >> PAGE_SHIFT; + pgoff_t end = (lend + 1) >> PAGE_SHIFT; + unsigned int partial_start = lstart & (PAGE_SIZE - 1); + unsigned int partial_end = (lend + 1) & (PAGE_SIZE - 1); + struct pagevec pvec; + pgoff_t indices[PAGEVEC_SIZE]; + long nr_swaps_freed = 0; + pgoff_t index; + int i; + + if (lend == -1) + end = -1; /* unsigned, so actually very big */ + + pagevec_init(&pvec); + index = start; + while (index < end) { + pvec.nr = find_get_entries(mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE), + pvec.pages, indices); + if (!pvec.nr) + break; + for (i = 0; i < pagevec_count(&pvec); i++) { + struct page *page = pvec.pages[i]; + + index = indices[i]; + if (index >= end) + break; + + if (xa_is_value(page)) { + if (unfalloc) + continue; + nr_swaps_freed += !shmem_free_swap(mapping, + index, page); + continue; + } + + VM_BUG_ON_PAGE(page_to_pgoff(page) != index, page); + + if (!trylock_page(page)) + continue; + + if ((!unfalloc || !PageUptodate(page)) && + page_mapping(page) == mapping) { + VM_BUG_ON_PAGE(PageWriteback(page), page); + if (shmem_punch_compound(page, start, end)) + truncate_inode_page(mapping, page); + } + unlock_page(page); + } + pagevec_remove_exceptionals(&pvec); + pagevec_release(&pvec); + cond_resched(); + index++; + } + + if (partial_start) { + struct page *page = NULL; + shmem_getpage(inode, start - 1, &page, SGP_READ); + if (page) { + unsigned int top = PAGE_SIZE; + if (start > end) { + top = partial_end; + partial_end = 0; + } + zero_user_segment(page, partial_start, top); + set_page_dirty(page); + unlock_page(page); + put_page(page); + } + } + if (partial_end) { + struct page *page = NULL; + shmem_getpage(inode, end, &page, SGP_READ); + if (page) { + zero_user_segment(page, 0, partial_end); + set_page_dirty(page); + unlock_page(page); + put_page(page); + } + } + if (start >= end) + return; + + index = start; + while (index < end) { + cond_resched(); + + pvec.nr = find_get_entries(mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE), + pvec.pages, indices); + if (!pvec.nr) { + /* If all gone or hole-punch or unfalloc, we're done */ + if (index == start || end != -1) + break; + /* But if truncating, restart to make sure all gone */ + index = start; + continue; + } + for (i = 0; i < pagevec_count(&pvec); i++) { + struct page *page = pvec.pages[i]; + + index = indices[i]; + if (index >= end) + break; + + if (xa_is_value(page)) { + if (unfalloc) + continue; + if (shmem_free_swap(mapping, index, page)) { + /* Swap was replaced by page: retry */ + index--; + break; + } + nr_swaps_freed++; + continue; + } + + lock_page(page); + + if (!unfalloc || !PageUptodate(page)) { + if (page_mapping(page) != mapping) { + /* Page was replaced by swap: retry */ + unlock_page(page); + index--; + break; + } + VM_BUG_ON_PAGE(PageWriteback(page), page); + if (shmem_punch_compound(page, start, end)) + truncate_inode_page(mapping, page); + else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { + /* Wipe the page and don't get stuck */ + clear_highpage(page); + flush_dcache_page(page); + set_page_dirty(page); + if (index < + round_up(start, HPAGE_PMD_NR)) + start = index + 1; + } + } + unlock_page(page); + } + pagevec_remove_exceptionals(&pvec); + pagevec_release(&pvec); + index++; + } + + spin_lock_irq(&info->lock); + info->swapped -= nr_swaps_freed; + shmem_recalc_inode(inode); + spin_unlock_irq(&info->lock); +} + +void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) +{ + shmem_undo_range(inode, lstart, lend, false); + inode->i_ctime = inode->i_mtime = current_time(inode); +} +EXPORT_SYMBOL_GPL(shmem_truncate_range); + +static int shmem_getattr(const struct path *path, struct kstat *stat, + u32 request_mask, unsigned int query_flags) +{ + struct inode *inode = path->dentry->d_inode; + struct shmem_inode_info *info = SHMEM_I(inode); + struct shmem_sb_info *sb_info = SHMEM_SB(inode->i_sb); + + if (info->alloced - info->swapped != inode->i_mapping->nrpages) { + spin_lock_irq(&info->lock); + shmem_recalc_inode(inode); + spin_unlock_irq(&info->lock); + } + generic_fillattr(inode, stat); + + if (is_huge_enabled(sb_info)) + stat->blksize = HPAGE_PMD_SIZE; + + return 0; +} + +static int shmem_setattr(struct dentry *dentry, struct iattr *attr) +{ + struct inode *inode = d_inode(dentry); + struct shmem_inode_info *info = SHMEM_I(inode); + struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); + int error; + + error = setattr_prepare(dentry, attr); + if (error) + return error; + + if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) { + loff_t oldsize = inode->i_size; + loff_t newsize = attr->ia_size; + + /* protected by i_mutex */ + if ((newsize < oldsize && (info->seals & F_SEAL_SHRINK)) || + (newsize > oldsize && (info->seals & F_SEAL_GROW))) + return -EPERM; + + if (newsize != oldsize) { + error = shmem_reacct_size(SHMEM_I(inode)->flags, + oldsize, newsize); + if (error) + return error; + i_size_write(inode, newsize); + inode->i_ctime = inode->i_mtime = current_time(inode); + } + if (newsize <= oldsize) { + loff_t holebegin = round_up(newsize, PAGE_SIZE); + if (oldsize > holebegin) + unmap_mapping_range(inode->i_mapping, + holebegin, 0, 1); + if (info->alloced) + shmem_truncate_range(inode, + newsize, (loff_t)-1); + /* unmap again to remove racily COWed private pages */ + if (oldsize > holebegin) + unmap_mapping_range(inode->i_mapping, + holebegin, 0, 1); + + /* + * Part of the huge page can be beyond i_size: subject + * to shrink under memory pressure. + */ + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { + spin_lock(&sbinfo->shrinklist_lock); + /* + * _careful to defend against unlocked access to + * ->shrink_list in shmem_unused_huge_shrink() + */ + if (list_empty_careful(&info->shrinklist)) { + list_add_tail(&info->shrinklist, + &sbinfo->shrinklist); + sbinfo->shrinklist_len++; + } + spin_unlock(&sbinfo->shrinklist_lock); + } + } + } + + setattr_copy(inode, attr); + if (attr->ia_valid & ATTR_MODE) + error = posix_acl_chmod(inode, inode->i_mode); + return error; +} + +static void shmem_evict_inode(struct inode *inode) +{ + struct shmem_inode_info *info = SHMEM_I(inode); + struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); + + if (inode->i_mapping->a_ops == &shmem_aops) { + shmem_unacct_size(info->flags, inode->i_size); + inode->i_size = 0; + shmem_truncate_range(inode, 0, (loff_t)-1); + if (!list_empty(&info->shrinklist)) { + spin_lock(&sbinfo->shrinklist_lock); + if (!list_empty(&info->shrinklist)) { + list_del_init(&info->shrinklist); + sbinfo->shrinklist_len--; + } + spin_unlock(&sbinfo->shrinklist_lock); + } + while (!list_empty(&info->swaplist)) { + /* Wait while shmem_unuse() is scanning this inode... */ + wait_var_event(&info->stop_eviction, + !atomic_read(&info->stop_eviction)); + mutex_lock(&shmem_swaplist_mutex); + /* ...but beware of the race if we peeked too early */ + if (!atomic_read(&info->stop_eviction)) + list_del_init(&info->swaplist); + mutex_unlock(&shmem_swaplist_mutex); + } + } + + simple_xattrs_free(&info->xattrs); + WARN_ON(inode->i_blocks); + shmem_free_inode(inode->i_sb); + clear_inode(inode); +} + +extern struct swap_info_struct *swap_info[]; + +static int shmem_find_swap_entries(struct address_space *mapping, + pgoff_t start, unsigned int nr_entries, + struct page **entries, pgoff_t *indices, + unsigned int type, bool frontswap) +{ + XA_STATE(xas, &mapping->i_pages, start); + struct page *page; + swp_entry_t entry; + unsigned int ret = 0; + + if (!nr_entries) + return 0; + + rcu_read_lock(); + xas_for_each(&xas, page, ULONG_MAX) { + if (xas_retry(&xas, page)) + continue; + + if (!xa_is_value(page)) + continue; + + entry = radix_to_swp_entry(page); + if (swp_type(entry) != type) + continue; + if (frontswap && + !frontswap_test(swap_info[type], swp_offset(entry))) + continue; + + indices[ret] = xas.xa_index; + entries[ret] = page; + + if (need_resched()) { + xas_pause(&xas); + cond_resched_rcu(); + } + if (++ret == nr_entries) + break; + } + rcu_read_unlock(); + + return ret; +} + +/* + * Move the swapped pages for an inode to page cache. Returns the count + * of pages swapped in, or the error in case of failure. + */ +static int shmem_unuse_swap_entries(struct inode *inode, struct pagevec pvec, + pgoff_t *indices) +{ + int i = 0; + int ret = 0; + int error = 0; + struct address_space *mapping = inode->i_mapping; + + for (i = 0; i < pvec.nr; i++) { + struct page *page = pvec.pages[i]; + + if (!xa_is_value(page)) + continue; + error = shmem_swapin_page(inode, indices[i], + &page, SGP_CACHE, + mapping_gfp_mask(mapping), + NULL, NULL); + if (error == 0) { + unlock_page(page); + put_page(page); + ret++; + } + if (error == -ENOMEM) + break; + error = 0; + } + return error ? error : ret; +} + +/* + * If swap found in inode, free it and move page from swapcache to filecache. + */ +static int shmem_unuse_inode(struct inode *inode, unsigned int type, + bool frontswap, unsigned long *fs_pages_to_unuse) +{ + struct address_space *mapping = inode->i_mapping; + pgoff_t start = 0; + struct pagevec pvec; + pgoff_t indices[PAGEVEC_SIZE]; + bool frontswap_partial = (frontswap && *fs_pages_to_unuse > 0); + int ret = 0; + + pagevec_init(&pvec); + do { + unsigned int nr_entries = PAGEVEC_SIZE; + + if (frontswap_partial && *fs_pages_to_unuse < PAGEVEC_SIZE) + nr_entries = *fs_pages_to_unuse; + + pvec.nr = shmem_find_swap_entries(mapping, start, nr_entries, + pvec.pages, indices, + type, frontswap); + if (pvec.nr == 0) { + ret = 0; + break; + } + + ret = shmem_unuse_swap_entries(inode, pvec, indices); + if (ret < 0) + break; + + if (frontswap_partial) { + *fs_pages_to_unuse -= ret; + if (*fs_pages_to_unuse == 0) { + ret = FRONTSWAP_PAGES_UNUSED; + break; + } + } + + start = indices[pvec.nr - 1]; + } while (true); + + return ret; +} + +/* + * Read all the shared memory data that resides in the swap + * device 'type' back into memory, so the swap device can be + * unused. + */ +int shmem_unuse(unsigned int type, bool frontswap, + unsigned long *fs_pages_to_unuse) +{ + struct shmem_inode_info *info, *next; + int error = 0; + + if (list_empty(&shmem_swaplist)) + return 0; + + mutex_lock(&shmem_swaplist_mutex); + list_for_each_entry_safe(info, next, &shmem_swaplist, swaplist) { + if (!info->swapped) { + list_del_init(&info->swaplist); + continue; + } + /* + * Drop the swaplist mutex while searching the inode for swap; + * but before doing so, make sure shmem_evict_inode() will not + * remove placeholder inode from swaplist, nor let it be freed + * (igrab() would protect from unlink, but not from unmount). + */ + atomic_inc(&info->stop_eviction); + mutex_unlock(&shmem_swaplist_mutex); + + error = shmem_unuse_inode(&info->vfs_inode, type, frontswap, + fs_pages_to_unuse); + cond_resched(); + + mutex_lock(&shmem_swaplist_mutex); + next = list_next_entry(info, swaplist); + if (!info->swapped) + list_del_init(&info->swaplist); + if (atomic_dec_and_test(&info->stop_eviction)) + wake_up_var(&info->stop_eviction); + if (error) + break; + } + mutex_unlock(&shmem_swaplist_mutex); + + return error; +} + +/* + * Move the page from the page cache to the swap cache. + */ +static int shmem_writepage(struct page *page, struct writeback_control *wbc) +{ + struct shmem_inode_info *info; + struct address_space *mapping; + struct inode *inode; + swp_entry_t swap; + pgoff_t index; + + VM_BUG_ON_PAGE(PageCompound(page), page); + BUG_ON(!PageLocked(page)); + mapping = page->mapping; + index = page->index; + inode = mapping->host; + info = SHMEM_I(inode); + if (info->flags & VM_LOCKED) + goto redirty; + if (!total_swap_pages) + goto redirty; + + /* + * Our capabilities prevent regular writeback or sync from ever calling + * shmem_writepage; but a stacking filesystem might use ->writepage of + * its underlying filesystem, in which case tmpfs should write out to + * swap only in response to memory pressure, and not for the writeback + * threads or sync. + */ + if (!wbc->for_reclaim) { + WARN_ON_ONCE(1); /* Still happens? Tell us about it! */ + goto redirty; + } + + /* + * This is somewhat ridiculous, but without plumbing a SWAP_MAP_FALLOC + * value into swapfile.c, the only way we can correctly account for a + * fallocated page arriving here is now to initialize it and write it. + * + * That's okay for a page already fallocated earlier, but if we have + * not yet completed the fallocation, then (a) we want to keep track + * of this page in case we have to undo it, and (b) it may not be a + * good idea to continue anyway, once we're pushing into swap. So + * reactivate the page, and let shmem_fallocate() quit when too many. + */ + if (!PageUptodate(page)) { + if (inode->i_private) { + struct shmem_falloc *shmem_falloc; + spin_lock(&inode->i_lock); + shmem_falloc = inode->i_private; + if (shmem_falloc && + !shmem_falloc->waitq && + index >= shmem_falloc->start && + index < shmem_falloc->next) + shmem_falloc->nr_unswapped++; + else + shmem_falloc = NULL; + spin_unlock(&inode->i_lock); + if (shmem_falloc) + goto redirty; + } + clear_highpage(page); + flush_dcache_page(page); + SetPageUptodate(page); + } + + swap = get_swap_page(page); + if (!swap.val) + goto redirty; + + /* + * Add inode to shmem_unuse()'s list of swapped-out inodes, + * if it's not already there. Do it now before the page is + * moved to swap cache, when its pagelock no longer protects + * the inode from eviction. But don't unlock the mutex until + * we've incremented swapped, because shmem_unuse_inode() will + * prune a !swapped inode from the swaplist under this mutex. + */ + mutex_lock(&shmem_swaplist_mutex); + if (list_empty(&info->swaplist)) + list_add(&info->swaplist, &shmem_swaplist); + + if (add_to_swap_cache(page, swap, + __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN, + NULL) == 0) { + spin_lock_irq(&info->lock); + shmem_recalc_inode(inode); + info->swapped++; + spin_unlock_irq(&info->lock); + + swap_shmem_alloc(swap); + shmem_delete_from_page_cache(page, swp_to_radix_entry(swap)); + + mutex_unlock(&shmem_swaplist_mutex); + BUG_ON(page_mapped(page)); + swap_writepage(page, wbc); + return 0; + } + + mutex_unlock(&shmem_swaplist_mutex); + put_swap_page(page, swap); +redirty: + set_page_dirty(page); + if (wbc->for_reclaim) + return AOP_WRITEPAGE_ACTIVATE; /* Return with page locked */ + unlock_page(page); + return 0; +} + +#if defined(CONFIG_NUMA) && defined(CONFIG_TMPFS) +static void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol) +{ + char buffer[64]; + + if (!mpol || mpol->mode == MPOL_DEFAULT) + return; /* show nothing */ + + mpol_to_str(buffer, sizeof(buffer), mpol); + + seq_printf(seq, ",mpol=%s", buffer); +} + +static struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) +{ + struct mempolicy *mpol = NULL; + if (sbinfo->mpol) { + spin_lock(&sbinfo->stat_lock); /* prevent replace/use races */ + mpol = sbinfo->mpol; + mpol_get(mpol); + spin_unlock(&sbinfo->stat_lock); + } + return mpol; +} +#else /* !CONFIG_NUMA || !CONFIG_TMPFS */ +static inline void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol) +{ +} +static inline struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) +{ + return NULL; +} +#endif /* CONFIG_NUMA && CONFIG_TMPFS */ +#ifndef CONFIG_NUMA +#define vm_policy vm_private_data +#endif + +static void shmem_pseudo_vma_init(struct vm_area_struct *vma, + struct shmem_inode_info *info, pgoff_t index) +{ + /* Create a pseudo vma that just contains the policy */ + vma_init(vma, NULL); + /* Bias interleave by inode number to distribute better across nodes */ + vma->vm_pgoff = index + info->vfs_inode.i_ino; + vma->vm_policy = mpol_shared_policy_lookup(&info->policy, index); +} + +static void shmem_pseudo_vma_destroy(struct vm_area_struct *vma) +{ + /* Drop reference taken by mpol_shared_policy_lookup() */ + mpol_cond_put(vma->vm_policy); +} + +static struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp, + struct shmem_inode_info *info, pgoff_t index) +{ + struct vm_area_struct pvma; + struct page *page; + struct vm_fault vmf; + + shmem_pseudo_vma_init(&pvma, info, index); + vmf.vma = &pvma; + vmf.address = 0; + page = swap_cluster_readahead(swap, gfp, &vmf); + shmem_pseudo_vma_destroy(&pvma); + + return page; +} + +static struct page *shmem_alloc_hugepage(gfp_t gfp, + struct shmem_inode_info *info, pgoff_t index) +{ + struct vm_area_struct pvma; + struct address_space *mapping = info->vfs_inode.i_mapping; + pgoff_t hindex; + struct page *page; + + hindex = round_down(index, HPAGE_PMD_NR); + if (xa_find(&mapping->i_pages, &hindex, hindex + HPAGE_PMD_NR - 1, + XA_PRESENT)) + return NULL; + + shmem_pseudo_vma_init(&pvma, info, hindex); + page = alloc_pages_vma(gfp | __GFP_COMP | __GFP_NORETRY | __GFP_NOWARN, + HPAGE_PMD_ORDER, &pvma, 0, numa_node_id(), true); + shmem_pseudo_vma_destroy(&pvma); + if (page) + prep_transhuge_page(page); + else + count_vm_event(THP_FILE_FALLBACK); + return page; +} + +static struct page *shmem_alloc_page(gfp_t gfp, + struct shmem_inode_info *info, pgoff_t index) +{ + struct vm_area_struct pvma; + struct page *page; + + shmem_pseudo_vma_init(&pvma, info, index); + page = alloc_page_vma(gfp, &pvma, 0); + shmem_pseudo_vma_destroy(&pvma); + + return page; +} + +static struct page *shmem_alloc_and_acct_page(gfp_t gfp, + struct inode *inode, + pgoff_t index, bool huge) +{ + struct shmem_inode_info *info = SHMEM_I(inode); + struct page *page; + int nr; + int err = -ENOSPC; + + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + huge = false; + nr = huge ? HPAGE_PMD_NR : 1; + + if (!shmem_inode_acct_block(inode, nr)) + goto failed; + + if (huge) + page = shmem_alloc_hugepage(gfp, info, index); + else + page = shmem_alloc_page(gfp, info, index); + if (page) { + __SetPageLocked(page); + __SetPageSwapBacked(page); + return page; + } + + err = -ENOMEM; + shmem_inode_unacct_blocks(inode, nr); +failed: + return ERR_PTR(err); +} + +/* + * When a page is moved from swapcache to shmem filecache (either by the + * usual swapin of shmem_getpage_gfp(), or by the less common swapoff of + * shmem_unuse_inode()), it may have been read in earlier from swap, in + * ignorance of the mapping it belongs to. If that mapping has special + * constraints (like the gma500 GEM driver, which requires RAM below 4GB), + * we may need to copy to a suitable page before moving to filecache. + * + * In a future release, this may well be extended to respect cpuset and + * NUMA mempolicy, and applied also to anonymous pages in do_swap_page(); + * but for now it is a simple matter of zone. + */ +static bool shmem_should_replace_page(struct page *page, gfp_t gfp) +{ + return page_zonenum(page) > gfp_zone(gfp); +} + +static int shmem_replace_page(struct page **pagep, gfp_t gfp, + struct shmem_inode_info *info, pgoff_t index) +{ + struct page *oldpage, *newpage; + struct address_space *swap_mapping; + swp_entry_t entry; + pgoff_t swap_index; + int error; + + oldpage = *pagep; + entry.val = page_private(oldpage); + swap_index = swp_offset(entry); + swap_mapping = page_mapping(oldpage); + + /* + * We have arrived here because our zones are constrained, so don't + * limit chance of success by further cpuset and node constraints. + */ + gfp &= ~GFP_CONSTRAINT_MASK; + newpage = shmem_alloc_page(gfp, info, index); + if (!newpage) + return -ENOMEM; + + get_page(newpage); + copy_highpage(newpage, oldpage); + flush_dcache_page(newpage); + + __SetPageLocked(newpage); + __SetPageSwapBacked(newpage); + SetPageUptodate(newpage); + set_page_private(newpage, entry.val); + SetPageSwapCache(newpage); + + /* + * Our caller will very soon move newpage out of swapcache, but it's + * a nice clean interface for us to replace oldpage by newpage there. + */ + xa_lock_irq(&swap_mapping->i_pages); + error = shmem_replace_entry(swap_mapping, swap_index, oldpage, newpage); + if (!error) { + mem_cgroup_migrate(oldpage, newpage); + __inc_lruvec_page_state(newpage, NR_FILE_PAGES); + __dec_lruvec_page_state(oldpage, NR_FILE_PAGES); + } + xa_unlock_irq(&swap_mapping->i_pages); + + if (unlikely(error)) { + /* + * Is this possible? I think not, now that our callers check + * both PageSwapCache and page_private after getting page lock; + * but be defensive. Reverse old to newpage for clear and free. + */ + oldpage = newpage; + } else { + lru_cache_add(newpage); + *pagep = newpage; + } + + ClearPageSwapCache(oldpage); + set_page_private(oldpage, 0); + + unlock_page(oldpage); + put_page(oldpage); + put_page(oldpage); + return error; +} + +/* + * Swap in the page pointed to by *pagep. + * Caller has to make sure that *pagep contains a valid swapped page. + * Returns 0 and the page in pagep if success. On failure, returns the + * error code and NULL in *pagep. + */ +static int shmem_swapin_page(struct inode *inode, pgoff_t index, + struct page **pagep, enum sgp_type sgp, + gfp_t gfp, struct vm_area_struct *vma, + vm_fault_t *fault_type) +{ + struct address_space *mapping = inode->i_mapping; + struct shmem_inode_info *info = SHMEM_I(inode); + struct mm_struct *charge_mm = vma ? vma->vm_mm : current->mm; + struct page *page; + swp_entry_t swap; + int error; + + VM_BUG_ON(!*pagep || !xa_is_value(*pagep)); + swap = radix_to_swp_entry(*pagep); + *pagep = NULL; + + /* Look it up and read it in.. */ + page = lookup_swap_cache(swap, NULL, 0); + if (!page) { + /* Or update major stats only when swapin succeeds?? */ + if (fault_type) { + *fault_type |= VM_FAULT_MAJOR; + count_vm_event(PGMAJFAULT); + count_memcg_event_mm(charge_mm, PGMAJFAULT); + } + /* Here we actually start the io */ + page = shmem_swapin(swap, gfp, info, index); + if (!page) { + error = -ENOMEM; + goto failed; + } + } + + /* We have to do this with page locked to prevent races */ + lock_page(page); + if (!PageSwapCache(page) || page_private(page) != swap.val || + !shmem_confirm_swap(mapping, index, swap)) { + error = -EEXIST; + goto unlock; + } + if (!PageUptodate(page)) { + error = -EIO; + goto failed; + } + wait_on_page_writeback(page); + + /* + * Some architectures may have to restore extra metadata to the + * physical page after reading from swap. + */ + arch_swap_restore(swap, page); + + if (shmem_should_replace_page(page, gfp)) { + error = shmem_replace_page(&page, gfp, info, index); + if (error) + goto failed; + } + + error = shmem_add_to_page_cache(page, mapping, index, + swp_to_radix_entry(swap), gfp, + charge_mm); + if (error) + goto failed; + + spin_lock_irq(&info->lock); + info->swapped--; + shmem_recalc_inode(inode); + spin_unlock_irq(&info->lock); + + if (sgp == SGP_WRITE) + mark_page_accessed(page); + + delete_from_swap_cache(page); + set_page_dirty(page); + swap_free(swap); + + *pagep = page; + return 0; +failed: + if (!shmem_confirm_swap(mapping, index, swap)) + error = -EEXIST; +unlock: + if (page) { + unlock_page(page); + put_page(page); + } + + return error; +} + +/* + * shmem_getpage_gfp - find page in cache, or get from swap, or allocate + * + * If we allocate a new one we do not mark it dirty. That's up to the + * vm. If we swap it in we mark it dirty since we also free the swap + * entry since a page cannot live in both the swap and page cache. + * + * vmf and fault_type are only supplied by shmem_fault: + * otherwise they are NULL. + */ +static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, + struct page **pagep, enum sgp_type sgp, gfp_t gfp, + struct vm_area_struct *vma, struct vm_fault *vmf, + vm_fault_t *fault_type) +{ + struct address_space *mapping = inode->i_mapping; + struct shmem_inode_info *info = SHMEM_I(inode); + struct shmem_sb_info *sbinfo; + struct mm_struct *charge_mm; + struct page *page; + enum sgp_type sgp_huge = sgp; + pgoff_t hindex = index; + int error; + int once = 0; + int alloced = 0; + + if (index > (MAX_LFS_FILESIZE >> PAGE_SHIFT)) + return -EFBIG; + if (sgp == SGP_NOHUGE || sgp == SGP_HUGE) + sgp = SGP_CACHE; +repeat: + if (sgp <= SGP_CACHE && + ((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) { + return -EINVAL; + } + + sbinfo = SHMEM_SB(inode->i_sb); + charge_mm = vma ? vma->vm_mm : current->mm; + + page = find_lock_entry(mapping, index); + if (xa_is_value(page)) { + error = shmem_swapin_page(inode, index, &page, + sgp, gfp, vma, fault_type); + if (error == -EEXIST) + goto repeat; + + *pagep = page; + return error; + } + + if (page) + hindex = page->index; + if (page && sgp == SGP_WRITE) + mark_page_accessed(page); + + /* fallocated page? */ + if (page && !PageUptodate(page)) { + if (sgp != SGP_READ) + goto clear; + unlock_page(page); + put_page(page); + page = NULL; + hindex = index; + } + if (page || sgp == SGP_READ) + goto out; + + /* + * Fast cache lookup did not find it: + * bring it back from swap or allocate. + */ + + if (vma && userfaultfd_missing(vma)) { + *fault_type = handle_userfault(vmf, VM_UFFD_MISSING); + return 0; + } + + /* shmem_symlink() */ + if (mapping->a_ops != &shmem_aops) + goto alloc_nohuge; + if (shmem_huge == SHMEM_HUGE_DENY || sgp_huge == SGP_NOHUGE) + goto alloc_nohuge; + if (shmem_huge == SHMEM_HUGE_FORCE) + goto alloc_huge; + switch (sbinfo->huge) { + case SHMEM_HUGE_NEVER: + goto alloc_nohuge; + case SHMEM_HUGE_WITHIN_SIZE: { + loff_t i_size; + pgoff_t off; + + off = round_up(index, HPAGE_PMD_NR); + i_size = round_up(i_size_read(inode), PAGE_SIZE); + if (i_size >= HPAGE_PMD_SIZE && + i_size >> PAGE_SHIFT >= off) + goto alloc_huge; + + fallthrough; + } + case SHMEM_HUGE_ADVISE: + if (sgp_huge == SGP_HUGE) + goto alloc_huge; + /* TODO: implement fadvise() hints */ + goto alloc_nohuge; + } + +alloc_huge: + page = shmem_alloc_and_acct_page(gfp, inode, index, true); + if (IS_ERR(page)) { +alloc_nohuge: + page = shmem_alloc_and_acct_page(gfp, inode, + index, false); + } + if (IS_ERR(page)) { + int retry = 5; + + error = PTR_ERR(page); + page = NULL; + if (error != -ENOSPC) + goto unlock; + /* + * Try to reclaim some space by splitting a huge page + * beyond i_size on the filesystem. + */ + while (retry--) { + int ret; + + ret = shmem_unused_huge_shrink(sbinfo, NULL, 1); + if (ret == SHRINK_STOP) + break; + if (ret) + goto alloc_nohuge; + } + goto unlock; + } + + if (PageTransHuge(page)) + hindex = round_down(index, HPAGE_PMD_NR); + else + hindex = index; + + if (sgp == SGP_WRITE) + __SetPageReferenced(page); + + error = shmem_add_to_page_cache(page, mapping, hindex, + NULL, gfp & GFP_RECLAIM_MASK, + charge_mm); + if (error) + goto unacct; + lru_cache_add(page); + + spin_lock_irq(&info->lock); + info->alloced += compound_nr(page); + inode->i_blocks += BLOCKS_PER_PAGE << compound_order(page); + shmem_recalc_inode(inode); + spin_unlock_irq(&info->lock); + alloced = true; + + if (PageTransHuge(page) && + DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE) < + hindex + HPAGE_PMD_NR - 1) { + /* + * Part of the huge page is beyond i_size: subject + * to shrink under memory pressure. + */ + spin_lock(&sbinfo->shrinklist_lock); + /* + * _careful to defend against unlocked access to + * ->shrink_list in shmem_unused_huge_shrink() + */ + if (list_empty_careful(&info->shrinklist)) { + list_add_tail(&info->shrinklist, + &sbinfo->shrinklist); + sbinfo->shrinklist_len++; + } + spin_unlock(&sbinfo->shrinklist_lock); + } + + /* + * Let SGP_FALLOC use the SGP_WRITE optimization on a new page. + */ + if (sgp == SGP_FALLOC) + sgp = SGP_WRITE; +clear: + /* + * Let SGP_WRITE caller clear ends if write does not fill page; + * but SGP_FALLOC on a page fallocated earlier must initialize + * it now, lest undo on failure cancel our earlier guarantee. + */ + if (sgp != SGP_WRITE && !PageUptodate(page)) { + int i; + + for (i = 0; i < compound_nr(page); i++) { + clear_highpage(page + i); + flush_dcache_page(page + i); + } + SetPageUptodate(page); + } + + /* Perhaps the file has been truncated since we checked */ + if (sgp <= SGP_CACHE && + ((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) { + if (alloced) { + ClearPageDirty(page); + delete_from_page_cache(page); + spin_lock_irq(&info->lock); + shmem_recalc_inode(inode); + spin_unlock_irq(&info->lock); + } + error = -EINVAL; + goto unlock; + } +out: + *pagep = page + index - hindex; + return 0; + + /* + * Error recovery. + */ +unacct: + shmem_inode_unacct_blocks(inode, compound_nr(page)); + + if (PageTransHuge(page)) { + unlock_page(page); + put_page(page); + goto alloc_nohuge; + } +unlock: + if (page) { + unlock_page(page); + put_page(page); + } + if (error == -ENOSPC && !once++) { + spin_lock_irq(&info->lock); + shmem_recalc_inode(inode); + spin_unlock_irq(&info->lock); + goto repeat; + } + if (error == -EEXIST) + goto repeat; + return error; +} + +/* + * This is like autoremove_wake_function, but it removes the wait queue + * entry unconditionally - even if something else had already woken the + * target. + */ +static int synchronous_wake_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) +{ + int ret = default_wake_function(wait, mode, sync, key); + list_del_init(&wait->entry); + return ret; +} + +static vm_fault_t shmem_fault(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + struct inode *inode = file_inode(vma->vm_file); + gfp_t gfp = mapping_gfp_mask(inode->i_mapping); + enum sgp_type sgp; + int err; + vm_fault_t ret = VM_FAULT_LOCKED; + + /* + * Trinity finds that probing a hole which tmpfs is punching can + * prevent the hole-punch from ever completing: which in turn + * locks writers out with its hold on i_mutex. So refrain from + * faulting pages into the hole while it's being punched. Although + * shmem_undo_range() does remove the additions, it may be unable to + * keep up, as each new page needs its own unmap_mapping_range() call, + * and the i_mmap tree grows ever slower to scan if new vmas are added. + * + * It does not matter if we sometimes reach this check just before the + * hole-punch begins, so that one fault then races with the punch: + * we just need to make racing faults a rare case. + * + * The implementation below would be much simpler if we just used a + * standard mutex or completion: but we cannot take i_mutex in fault, + * and bloating every shmem inode for this unlikely case would be sad. + */ + if (unlikely(inode->i_private)) { + struct shmem_falloc *shmem_falloc; + + spin_lock(&inode->i_lock); + shmem_falloc = inode->i_private; + if (shmem_falloc && + shmem_falloc->waitq && + vmf->pgoff >= shmem_falloc->start && + vmf->pgoff < shmem_falloc->next) { + struct file *fpin; + wait_queue_head_t *shmem_falloc_waitq; + DEFINE_WAIT_FUNC(shmem_fault_wait, synchronous_wake_function); + + ret = VM_FAULT_NOPAGE; + fpin = maybe_unlock_mmap_for_io(vmf, NULL); + if (fpin) + ret = VM_FAULT_RETRY; + + shmem_falloc_waitq = shmem_falloc->waitq; + prepare_to_wait(shmem_falloc_waitq, &shmem_fault_wait, + TASK_UNINTERRUPTIBLE); + spin_unlock(&inode->i_lock); + schedule(); + + /* + * shmem_falloc_waitq points into the shmem_fallocate() + * stack of the hole-punching task: shmem_falloc_waitq + * is usually invalid by the time we reach here, but + * finish_wait() does not dereference it in that case; + * though i_lock needed lest racing with wake_up_all(). + */ + spin_lock(&inode->i_lock); + finish_wait(shmem_falloc_waitq, &shmem_fault_wait); + spin_unlock(&inode->i_lock); + + if (fpin) + fput(fpin); + return ret; + } + spin_unlock(&inode->i_lock); + } + + sgp = SGP_CACHE; + + if ((vma->vm_flags & VM_NOHUGEPAGE) || + test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) + sgp = SGP_NOHUGE; + else if (vma->vm_flags & VM_HUGEPAGE) + sgp = SGP_HUGE; + + err = shmem_getpage_gfp(inode, vmf->pgoff, &vmf->page, sgp, + gfp, vma, vmf, &ret); + if (err) + return vmf_error(err); + return ret; +} + +unsigned long shmem_get_unmapped_area(struct file *file, + unsigned long uaddr, unsigned long len, + unsigned long pgoff, unsigned long flags) +{ + unsigned long (*get_area)(struct file *, + unsigned long, unsigned long, unsigned long, unsigned long); + unsigned long addr; + unsigned long offset; + unsigned long inflated_len; + unsigned long inflated_addr; + unsigned long inflated_offset; + + if (len > TASK_SIZE) + return -ENOMEM; + + get_area = current->mm->get_unmapped_area; + addr = get_area(file, uaddr, len, pgoff, flags); + + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + return addr; + if (IS_ERR_VALUE(addr)) + return addr; + if (addr & ~PAGE_MASK) + return addr; + if (addr > TASK_SIZE - len) + return addr; + + if (shmem_huge == SHMEM_HUGE_DENY) + return addr; + if (len < HPAGE_PMD_SIZE) + return addr; + if (flags & MAP_FIXED) + return addr; + /* + * Our priority is to support MAP_SHARED mapped hugely; + * and support MAP_PRIVATE mapped hugely too, until it is COWed. + * But if caller specified an address hint and we allocated area there + * successfully, respect that as before. + */ + if (uaddr == addr) + return addr; + + if (shmem_huge != SHMEM_HUGE_FORCE) { + struct super_block *sb; + + if (file) { + VM_BUG_ON(file->f_op != &shmem_file_operations); + sb = file_inode(file)->i_sb; + } else { + /* + * Called directly from mm/mmap.c, or drivers/char/mem.c + * for "/dev/zero", to create a shared anonymous object. + */ + if (IS_ERR(shm_mnt)) + return addr; + sb = shm_mnt->mnt_sb; + } + if (SHMEM_SB(sb)->huge == SHMEM_HUGE_NEVER) + return addr; + } + + offset = (pgoff << PAGE_SHIFT) & (HPAGE_PMD_SIZE-1); + if (offset && offset + len < 2 * HPAGE_PMD_SIZE) + return addr; + if ((addr & (HPAGE_PMD_SIZE-1)) == offset) + return addr; + + inflated_len = len + HPAGE_PMD_SIZE - PAGE_SIZE; + if (inflated_len > TASK_SIZE) + return addr; + if (inflated_len < len) + return addr; + + inflated_addr = get_area(NULL, uaddr, inflated_len, 0, flags); + if (IS_ERR_VALUE(inflated_addr)) + return addr; + if (inflated_addr & ~PAGE_MASK) + return addr; + + inflated_offset = inflated_addr & (HPAGE_PMD_SIZE-1); + inflated_addr += offset - inflated_offset; + if (inflated_offset > offset) + inflated_addr += HPAGE_PMD_SIZE; + + if (inflated_addr > TASK_SIZE - len) + return addr; + return inflated_addr; +} + +#ifdef CONFIG_NUMA +static int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *mpol) +{ + struct inode *inode = file_inode(vma->vm_file); + return mpol_set_shared_policy(&SHMEM_I(inode)->policy, vma, mpol); +} + +static struct mempolicy *shmem_get_policy(struct vm_area_struct *vma, + unsigned long addr) +{ + struct inode *inode = file_inode(vma->vm_file); + pgoff_t index; + + index = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; + return mpol_shared_policy_lookup(&SHMEM_I(inode)->policy, index); +} +#endif + +int shmem_lock(struct file *file, int lock, struct user_struct *user) +{ + struct inode *inode = file_inode(file); + struct shmem_inode_info *info = SHMEM_I(inode); + int retval = -ENOMEM; + + /* + * What serializes the accesses to info->flags? + * ipc_lock_object() when called from shmctl_do_lock(), + * no serialization needed when called from shm_destroy(). + */ + if (lock && !(info->flags & VM_LOCKED)) { + if (!user_shm_lock(inode->i_size, user)) + goto out_nomem; + info->flags |= VM_LOCKED; + mapping_set_unevictable(file->f_mapping); + } + if (!lock && (info->flags & VM_LOCKED) && user) { + user_shm_unlock(inode->i_size, user); + info->flags &= ~VM_LOCKED; + mapping_clear_unevictable(file->f_mapping); + } + retval = 0; + +out_nomem: + return retval; +} + +static int shmem_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct shmem_inode_info *info = SHMEM_I(file_inode(file)); + int ret; + + ret = seal_check_future_write(info->seals, vma); + if (ret) + return ret; + + /* arm64 - allow memory tagging on RAM-based files */ + vma->vm_flags |= VM_MTE_ALLOWED; + + file_accessed(file); + vma->vm_ops = &shmem_vm_ops; + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && + ((vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK) < + (vma->vm_end & HPAGE_PMD_MASK)) { + khugepaged_enter(vma, vma->vm_flags); + } + return 0; +} + +static struct inode *shmem_get_inode(struct super_block *sb, const struct inode *dir, + umode_t mode, dev_t dev, unsigned long flags) +{ + struct inode *inode; + struct shmem_inode_info *info; + struct shmem_sb_info *sbinfo = SHMEM_SB(sb); + ino_t ino; + + if (shmem_reserve_inode(sb, &ino)) + return NULL; + + inode = new_inode(sb); + if (inode) { + inode->i_ino = ino; + inode_init_owner(inode, dir, mode); + inode->i_blocks = 0; + inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); + inode->i_generation = prandom_u32(); + info = SHMEM_I(inode); + memset(info, 0, (char *)inode - (char *)info); + spin_lock_init(&info->lock); + atomic_set(&info->stop_eviction, 0); + info->seals = F_SEAL_SEAL; + info->flags = flags & VM_NORESERVE; + INIT_LIST_HEAD(&info->shrinklist); + INIT_LIST_HEAD(&info->swaplist); + simple_xattrs_init(&info->xattrs); + cache_no_acl(inode); + + switch (mode & S_IFMT) { + default: + inode->i_op = &shmem_special_inode_operations; + init_special_inode(inode, mode, dev); + break; + case S_IFREG: + inode->i_mapping->a_ops = &shmem_aops; + inode->i_op = &shmem_inode_operations; + inode->i_fop = &shmem_file_operations; + mpol_shared_policy_init(&info->policy, + shmem_get_sbmpol(sbinfo)); + break; + case S_IFDIR: + inc_nlink(inode); + /* Some things misbehave if size == 0 on a directory */ + inode->i_size = 2 * BOGO_DIRENT_SIZE; + inode->i_op = &shmem_dir_inode_operations; + inode->i_fop = &simple_dir_operations; + break; + case S_IFLNK: + /* + * Must not load anything in the rbtree, + * mpol_free_shared_policy will not be called. + */ + mpol_shared_policy_init(&info->policy, NULL); + break; + } + + lockdep_annotate_inode_mutex_key(inode); + } else + shmem_free_inode(sb); + return inode; +} + +bool shmem_mapping(struct address_space *mapping) +{ + return mapping->a_ops == &shmem_aops; +} + +static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, + pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + unsigned long src_addr, + bool zeropage, + struct page **pagep) +{ + struct inode *inode = file_inode(dst_vma->vm_file); + struct shmem_inode_info *info = SHMEM_I(inode); + struct address_space *mapping = inode->i_mapping; + gfp_t gfp = mapping_gfp_mask(mapping); + pgoff_t pgoff = linear_page_index(dst_vma, dst_addr); + spinlock_t *ptl; + void *page_kaddr; + struct page *page; + pte_t _dst_pte, *dst_pte; + int ret; + pgoff_t offset, max_off; + + ret = -ENOMEM; + if (!shmem_inode_acct_block(inode, 1)) { + /* + * We may have got a page, returned -ENOENT triggering a retry, + * and now we find ourselves with -ENOMEM. Release the page, to + * avoid a BUG_ON in our caller. + */ + if (unlikely(*pagep)) { + put_page(*pagep); + *pagep = NULL; + } + goto out; + } + + if (!*pagep) { + page = shmem_alloc_page(gfp, info, pgoff); + if (!page) + goto out_unacct_blocks; + + if (!zeropage) { /* mcopy_atomic */ + page_kaddr = kmap_atomic(page); + ret = copy_from_user(page_kaddr, + (const void __user *)src_addr, + PAGE_SIZE); + kunmap_atomic(page_kaddr); + + /* fallback to copy_from_user outside mmap_lock */ + if (unlikely(ret)) { + *pagep = page; + shmem_inode_unacct_blocks(inode, 1); + /* don't free the page */ + return -ENOENT; + } + } else { /* mfill_zeropage_atomic */ + clear_highpage(page); + } + } else { + page = *pagep; + *pagep = NULL; + } + + VM_BUG_ON(PageLocked(page) || PageSwapBacked(page)); + __SetPageLocked(page); + __SetPageSwapBacked(page); + __SetPageUptodate(page); + + ret = -EFAULT; + offset = linear_page_index(dst_vma, dst_addr); + max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + if (unlikely(offset >= max_off)) + goto out_release; + + ret = shmem_add_to_page_cache(page, mapping, pgoff, NULL, + gfp & GFP_RECLAIM_MASK, dst_mm); + if (ret) + goto out_release; + + _dst_pte = mk_pte(page, dst_vma->vm_page_prot); + if (dst_vma->vm_flags & VM_WRITE) + _dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte)); + else { + /* + * We don't set the pte dirty if the vma has no + * VM_WRITE permission, so mark the page dirty or it + * could be freed from under us. We could do it + * unconditionally before unlock_page(), but doing it + * only if VM_WRITE is not set is faster. + */ + set_page_dirty(page); + } + + dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl); + + ret = -EFAULT; + max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + if (unlikely(offset >= max_off)) + goto out_release_unlock; + + ret = -EEXIST; + if (!pte_none(*dst_pte)) + goto out_release_unlock; + + lru_cache_add(page); + + spin_lock_irq(&info->lock); + info->alloced++; + inode->i_blocks += BLOCKS_PER_PAGE; + shmem_recalc_inode(inode); + spin_unlock_irq(&info->lock); + + inc_mm_counter(dst_mm, mm_counter_file(page)); + page_add_file_rmap(page, false); + set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); + + /* No need to invalidate - it was non-present before */ + update_mmu_cache(dst_vma, dst_addr, dst_pte); + pte_unmap_unlock(dst_pte, ptl); + unlock_page(page); + ret = 0; +out: + return ret; +out_release_unlock: + pte_unmap_unlock(dst_pte, ptl); + ClearPageDirty(page); + delete_from_page_cache(page); +out_release: + unlock_page(page); + put_page(page); +out_unacct_blocks: + shmem_inode_unacct_blocks(inode, 1); + goto out; +} + +int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm, + pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + unsigned long src_addr, + struct page **pagep) +{ + return shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, + dst_addr, src_addr, false, pagep); +} + +int shmem_mfill_zeropage_pte(struct mm_struct *dst_mm, + pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr) +{ + struct page *page = NULL; + + return shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, + dst_addr, 0, true, &page); +} + +#ifdef CONFIG_TMPFS +static const struct inode_operations shmem_symlink_inode_operations; +static const struct inode_operations shmem_short_symlink_operations; + +#ifdef CONFIG_TMPFS_XATTR +static int shmem_initxattrs(struct inode *, const struct xattr *, void *); +#else +#define shmem_initxattrs NULL +#endif + +static int +shmem_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata) +{ + struct inode *inode = mapping->host; + struct shmem_inode_info *info = SHMEM_I(inode); + pgoff_t index = pos >> PAGE_SHIFT; + + /* i_mutex is held by caller */ + if (unlikely(info->seals & (F_SEAL_GROW | + F_SEAL_WRITE | F_SEAL_FUTURE_WRITE))) { + if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) + return -EPERM; + if ((info->seals & F_SEAL_GROW) && pos + len > inode->i_size) + return -EPERM; + } + + return shmem_getpage(inode, index, pagep, SGP_WRITE); +} + +static int +shmem_write_end(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) +{ + struct inode *inode = mapping->host; + + if (pos + copied > inode->i_size) + i_size_write(inode, pos + copied); + + if (!PageUptodate(page)) { + struct page *head = compound_head(page); + if (PageTransCompound(page)) { + int i; + + for (i = 0; i < HPAGE_PMD_NR; i++) { + if (head + i == page) + continue; + clear_highpage(head + i); + flush_dcache_page(head + i); + } + } + if (copied < PAGE_SIZE) { + unsigned from = pos & (PAGE_SIZE - 1); + zero_user_segments(page, 0, from, + from + copied, PAGE_SIZE); + } + SetPageUptodate(head); + } + set_page_dirty(page); + unlock_page(page); + put_page(page); + + return copied; +} + +static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file_inode(file); + struct address_space *mapping = inode->i_mapping; + pgoff_t index; + unsigned long offset; + enum sgp_type sgp = SGP_READ; + int error = 0; + ssize_t retval = 0; + loff_t *ppos = &iocb->ki_pos; + + /* + * Might this read be for a stacking filesystem? Then when reading + * holes of a sparse file, we actually need to allocate those pages, + * and even mark them dirty, so it cannot exceed the max_blocks limit. + */ + if (!iter_is_iovec(to)) + sgp = SGP_CACHE; + + index = *ppos >> PAGE_SHIFT; + offset = *ppos & ~PAGE_MASK; + + for (;;) { + struct page *page = NULL; + pgoff_t end_index; + unsigned long nr, ret; + loff_t i_size = i_size_read(inode); + + end_index = i_size >> PAGE_SHIFT; + if (index > end_index) + break; + if (index == end_index) { + nr = i_size & ~PAGE_MASK; + if (nr <= offset) + break; + } + + error = shmem_getpage(inode, index, &page, sgp); + if (error) { + if (error == -EINVAL) + error = 0; + break; + } + if (page) { + if (sgp == SGP_CACHE) + set_page_dirty(page); + unlock_page(page); + } + + /* + * We must evaluate after, since reads (unlike writes) + * are called without i_mutex protection against truncate + */ + nr = PAGE_SIZE; + i_size = i_size_read(inode); + end_index = i_size >> PAGE_SHIFT; + if (index == end_index) { + nr = i_size & ~PAGE_MASK; + if (nr <= offset) { + if (page) + put_page(page); + break; + } + } + nr -= offset; + + if (page) { + /* + * If users can be writing to this page using arbitrary + * virtual addresses, take care about potential aliasing + * before reading the page on the kernel side. + */ + if (mapping_writably_mapped(mapping)) + flush_dcache_page(page); + /* + * Mark the page accessed if we read the beginning. + */ + if (!offset) + mark_page_accessed(page); + } else { + page = ZERO_PAGE(0); + get_page(page); + } + + /* + * Ok, we have the page, and it's up-to-date, so + * now we can copy it to user space... + */ + ret = copy_page_to_iter(page, offset, nr, to); + retval += ret; + offset += ret; + index += offset >> PAGE_SHIFT; + offset &= ~PAGE_MASK; + + put_page(page); + if (!iov_iter_count(to)) + break; + if (ret < nr) { + error = -EFAULT; + break; + } + cond_resched(); + } + + *ppos = ((loff_t) index << PAGE_SHIFT) + offset; + file_accessed(file); + return retval ? retval : error; +} + +/* + * llseek SEEK_DATA or SEEK_HOLE through the page cache. + */ +static pgoff_t shmem_seek_hole_data(struct address_space *mapping, + pgoff_t index, pgoff_t end, int whence) +{ + struct page *page; + struct pagevec pvec; + pgoff_t indices[PAGEVEC_SIZE]; + bool done = false; + int i; + + pagevec_init(&pvec); + pvec.nr = 1; /* start small: we may be there already */ + while (!done) { + pvec.nr = find_get_entries(mapping, index, + pvec.nr, pvec.pages, indices); + if (!pvec.nr) { + if (whence == SEEK_DATA) + index = end; + break; + } + for (i = 0; i < pvec.nr; i++, index++) { + if (index < indices[i]) { + if (whence == SEEK_HOLE) { + done = true; + break; + } + index = indices[i]; + } + page = pvec.pages[i]; + if (page && !xa_is_value(page)) { + if (!PageUptodate(page)) + page = NULL; + } + if (index >= end || + (page && whence == SEEK_DATA) || + (!page && whence == SEEK_HOLE)) { + done = true; + break; + } + } + pagevec_remove_exceptionals(&pvec); + pagevec_release(&pvec); + pvec.nr = PAGEVEC_SIZE; + cond_resched(); + } + return index; +} + +static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence) +{ + struct address_space *mapping = file->f_mapping; + struct inode *inode = mapping->host; + pgoff_t start, end; + loff_t new_offset; + + if (whence != SEEK_DATA && whence != SEEK_HOLE) + return generic_file_llseek_size(file, offset, whence, + MAX_LFS_FILESIZE, i_size_read(inode)); + inode_lock(inode); + /* We're holding i_mutex so we can access i_size directly */ + + if (offset < 0 || offset >= inode->i_size) + offset = -ENXIO; + else { + start = offset >> PAGE_SHIFT; + end = (inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT; + new_offset = shmem_seek_hole_data(mapping, start, end, whence); + new_offset <<= PAGE_SHIFT; + if (new_offset > offset) { + if (new_offset < inode->i_size) + offset = new_offset; + else if (whence == SEEK_DATA) + offset = -ENXIO; + else + offset = inode->i_size; + } + } + + if (offset >= 0) + offset = vfs_setpos(file, offset, MAX_LFS_FILESIZE); + inode_unlock(inode); + return offset; +} + +static long shmem_fallocate(struct file *file, int mode, loff_t offset, + loff_t len) +{ + struct inode *inode = file_inode(file); + struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); + struct shmem_inode_info *info = SHMEM_I(inode); + struct shmem_falloc shmem_falloc; + pgoff_t start, index, end; + int error; + + if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) + return -EOPNOTSUPP; + + inode_lock(inode); + + if (mode & FALLOC_FL_PUNCH_HOLE) { + struct address_space *mapping = file->f_mapping; + loff_t unmap_start = round_up(offset, PAGE_SIZE); + loff_t unmap_end = round_down(offset + len, PAGE_SIZE) - 1; + DECLARE_WAIT_QUEUE_HEAD_ONSTACK(shmem_falloc_waitq); + + /* protected by i_mutex */ + if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) { + error = -EPERM; + goto out; + } + + shmem_falloc.waitq = &shmem_falloc_waitq; + shmem_falloc.start = (u64)unmap_start >> PAGE_SHIFT; + shmem_falloc.next = (unmap_end + 1) >> PAGE_SHIFT; + spin_lock(&inode->i_lock); + inode->i_private = &shmem_falloc; + spin_unlock(&inode->i_lock); + + if ((u64)unmap_end > (u64)unmap_start) + unmap_mapping_range(mapping, unmap_start, + 1 + unmap_end - unmap_start, 0); + shmem_truncate_range(inode, offset, offset + len - 1); + /* No need to unmap again: hole-punching leaves COWed pages */ + + spin_lock(&inode->i_lock); + inode->i_private = NULL; + wake_up_all(&shmem_falloc_waitq); + WARN_ON_ONCE(!list_empty(&shmem_falloc_waitq.head)); + spin_unlock(&inode->i_lock); + error = 0; + goto out; + } + + /* We need to check rlimit even when FALLOC_FL_KEEP_SIZE */ + error = inode_newsize_ok(inode, offset + len); + if (error) + goto out; + + if ((info->seals & F_SEAL_GROW) && offset + len > inode->i_size) { + error = -EPERM; + goto out; + } + + start = offset >> PAGE_SHIFT; + end = (offset + len + PAGE_SIZE - 1) >> PAGE_SHIFT; + /* Try to avoid a swapstorm if len is impossible to satisfy */ + if (sbinfo->max_blocks && end - start > sbinfo->max_blocks) { + error = -ENOSPC; + goto out; + } + + shmem_falloc.waitq = NULL; + shmem_falloc.start = start; + shmem_falloc.next = start; + shmem_falloc.nr_falloced = 0; + shmem_falloc.nr_unswapped = 0; + spin_lock(&inode->i_lock); + inode->i_private = &shmem_falloc; + spin_unlock(&inode->i_lock); + + for (index = start; index < end; index++) { + struct page *page; + + /* + * Good, the fallocate(2) manpage permits EINTR: we may have + * been interrupted because we are using up too much memory. + */ + if (signal_pending(current)) + error = -EINTR; + else if (shmem_falloc.nr_unswapped > shmem_falloc.nr_falloced) + error = -ENOMEM; + else + error = shmem_getpage(inode, index, &page, SGP_FALLOC); + if (error) { + /* Remove the !PageUptodate pages we added */ + if (index > start) { + shmem_undo_range(inode, + (loff_t)start << PAGE_SHIFT, + ((loff_t)index << PAGE_SHIFT) - 1, true); + } + goto undone; + } + + /* + * Inform shmem_writepage() how far we have reached. + * No need for lock or barrier: we have the page lock. + */ + shmem_falloc.next++; + if (!PageUptodate(page)) + shmem_falloc.nr_falloced++; + + /* + * If !PageUptodate, leave it that way so that freeable pages + * can be recognized if we need to rollback on error later. + * But set_page_dirty so that memory pressure will swap rather + * than free the pages we are allocating (and SGP_CACHE pages + * might still be clean: we now need to mark those dirty too). + */ + set_page_dirty(page); + unlock_page(page); + put_page(page); + cond_resched(); + } + + if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size) + i_size_write(inode, offset + len); + inode->i_ctime = current_time(inode); +undone: + spin_lock(&inode->i_lock); + inode->i_private = NULL; + spin_unlock(&inode->i_lock); +out: + inode_unlock(inode); + return error; +} + +static int shmem_statfs(struct dentry *dentry, struct kstatfs *buf) +{ + struct shmem_sb_info *sbinfo = SHMEM_SB(dentry->d_sb); + + buf->f_type = TMPFS_MAGIC; + buf->f_bsize = PAGE_SIZE; + buf->f_namelen = NAME_MAX; + if (sbinfo->max_blocks) { + buf->f_blocks = sbinfo->max_blocks; + buf->f_bavail = + buf->f_bfree = sbinfo->max_blocks - + percpu_counter_sum(&sbinfo->used_blocks); + } + if (sbinfo->max_inodes) { + buf->f_files = sbinfo->max_inodes; + buf->f_ffree = sbinfo->free_inodes; + } + /* else leave those fields 0 like simple_statfs */ + return 0; +} + +/* + * File creation. Allocate an inode, and we're done.. + */ +static int +shmem_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) +{ + struct inode *inode; + int error = -ENOSPC; + + inode = shmem_get_inode(dir->i_sb, dir, mode, dev, VM_NORESERVE); + if (inode) { + error = simple_acl_create(dir, inode); + if (error) + goto out_iput; + error = security_inode_init_security(inode, dir, + &dentry->d_name, + shmem_initxattrs, NULL); + if (error && error != -EOPNOTSUPP) + goto out_iput; + + error = 0; + dir->i_size += BOGO_DIRENT_SIZE; + dir->i_ctime = dir->i_mtime = current_time(dir); + d_instantiate(dentry, inode); + dget(dentry); /* Extra count - pin the dentry in core */ + } + return error; +out_iput: + iput(inode); + return error; +} + +static int +shmem_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + struct inode *inode; + int error = -ENOSPC; + + inode = shmem_get_inode(dir->i_sb, dir, mode, 0, VM_NORESERVE); + if (inode) { + error = security_inode_init_security(inode, dir, + NULL, + shmem_initxattrs, NULL); + if (error && error != -EOPNOTSUPP) + goto out_iput; + error = simple_acl_create(dir, inode); + if (error) + goto out_iput; + d_tmpfile(dentry, inode); + } + return error; +out_iput: + iput(inode); + return error; +} + +static int shmem_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + int error; + + if ((error = shmem_mknod(dir, dentry, mode | S_IFDIR, 0))) + return error; + inc_nlink(dir); + return 0; +} + +static int shmem_create(struct inode *dir, struct dentry *dentry, umode_t mode, + bool excl) +{ + return shmem_mknod(dir, dentry, mode | S_IFREG, 0); +} + +/* + * Link a file.. + */ +static int shmem_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) +{ + struct inode *inode = d_inode(old_dentry); + int ret = 0; + + /* + * No ordinary (disk based) filesystem counts links as inodes; + * but each new link needs a new dentry, pinning lowmem, and + * tmpfs dentries cannot be pruned until they are unlinked. + * But if an O_TMPFILE file is linked into the tmpfs, the + * first link must skip that, to get the accounting right. + */ + if (inode->i_nlink) { + ret = shmem_reserve_inode(inode->i_sb, NULL); + if (ret) + goto out; + } + + dir->i_size += BOGO_DIRENT_SIZE; + inode->i_ctime = dir->i_ctime = dir->i_mtime = current_time(inode); + inc_nlink(inode); + ihold(inode); /* New dentry reference */ + dget(dentry); /* Extra pinning count for the created dentry */ + d_instantiate(dentry, inode); +out: + return ret; +} + +static int shmem_unlink(struct inode *dir, struct dentry *dentry) +{ + struct inode *inode = d_inode(dentry); + + if (inode->i_nlink > 1 && !S_ISDIR(inode->i_mode)) + shmem_free_inode(inode->i_sb); + + dir->i_size -= BOGO_DIRENT_SIZE; + inode->i_ctime = dir->i_ctime = dir->i_mtime = current_time(inode); + drop_nlink(inode); + dput(dentry); /* Undo the count from "create" - this does all the work */ + return 0; +} + +static int shmem_rmdir(struct inode *dir, struct dentry *dentry) +{ + if (!simple_empty(dentry)) + return -ENOTEMPTY; + + drop_nlink(d_inode(dentry)); + drop_nlink(dir); + return shmem_unlink(dir, dentry); +} + +static int shmem_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) +{ + bool old_is_dir = d_is_dir(old_dentry); + bool new_is_dir = d_is_dir(new_dentry); + + if (old_dir != new_dir && old_is_dir != new_is_dir) { + if (old_is_dir) { + drop_nlink(old_dir); + inc_nlink(new_dir); + } else { + drop_nlink(new_dir); + inc_nlink(old_dir); + } + } + old_dir->i_ctime = old_dir->i_mtime = + new_dir->i_ctime = new_dir->i_mtime = + d_inode(old_dentry)->i_ctime = + d_inode(new_dentry)->i_ctime = current_time(old_dir); + + return 0; +} + +static int shmem_whiteout(struct inode *old_dir, struct dentry *old_dentry) +{ + struct dentry *whiteout; + int error; + + whiteout = d_alloc(old_dentry->d_parent, &old_dentry->d_name); + if (!whiteout) + return -ENOMEM; + + error = shmem_mknod(old_dir, whiteout, + S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV); + dput(whiteout); + if (error) + return error; + + /* + * Cheat and hash the whiteout while the old dentry is still in + * place, instead of playing games with FS_RENAME_DOES_D_MOVE. + * + * d_lookup() will consistently find one of them at this point, + * not sure which one, but that isn't even important. + */ + d_rehash(whiteout); + return 0; +} + +/* + * The VFS layer already does all the dentry stuff for rename, + * we just have to decrement the usage count for the target if + * it exists so that the VFS layer correctly free's it when it + * gets overwritten. + */ +static int shmem_rename2(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) +{ + struct inode *inode = d_inode(old_dentry); + int they_are_dirs = S_ISDIR(inode->i_mode); + + if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) + return -EINVAL; + + if (flags & RENAME_EXCHANGE) + return shmem_exchange(old_dir, old_dentry, new_dir, new_dentry); + + if (!simple_empty(new_dentry)) + return -ENOTEMPTY; + + if (flags & RENAME_WHITEOUT) { + int error; + + error = shmem_whiteout(old_dir, old_dentry); + if (error) + return error; + } + + if (d_really_is_positive(new_dentry)) { + (void) shmem_unlink(new_dir, new_dentry); + if (they_are_dirs) { + drop_nlink(d_inode(new_dentry)); + drop_nlink(old_dir); + } + } else if (they_are_dirs) { + drop_nlink(old_dir); + inc_nlink(new_dir); + } + + old_dir->i_size -= BOGO_DIRENT_SIZE; + new_dir->i_size += BOGO_DIRENT_SIZE; + old_dir->i_ctime = old_dir->i_mtime = + new_dir->i_ctime = new_dir->i_mtime = + inode->i_ctime = current_time(old_dir); + return 0; +} + +static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *symname) +{ + int error; + int len; + struct inode *inode; + struct page *page; + + len = strlen(symname) + 1; + if (len > PAGE_SIZE) + return -ENAMETOOLONG; + + inode = shmem_get_inode(dir->i_sb, dir, S_IFLNK | 0777, 0, + VM_NORESERVE); + if (!inode) + return -ENOSPC; + + error = security_inode_init_security(inode, dir, &dentry->d_name, + shmem_initxattrs, NULL); + if (error && error != -EOPNOTSUPP) { + iput(inode); + return error; + } + + inode->i_size = len-1; + if (len <= SHORT_SYMLINK_LEN) { + inode->i_link = kmemdup(symname, len, GFP_KERNEL); + if (!inode->i_link) { + iput(inode); + return -ENOMEM; + } + inode->i_op = &shmem_short_symlink_operations; + } else { + inode_nohighmem(inode); + error = shmem_getpage(inode, 0, &page, SGP_WRITE); + if (error) { + iput(inode); + return error; + } + inode->i_mapping->a_ops = &shmem_aops; + inode->i_op = &shmem_symlink_inode_operations; + memcpy(page_address(page), symname, len); + SetPageUptodate(page); + set_page_dirty(page); + unlock_page(page); + put_page(page); + } + dir->i_size += BOGO_DIRENT_SIZE; + dir->i_ctime = dir->i_mtime = current_time(dir); + d_instantiate(dentry, inode); + dget(dentry); + return 0; +} + +static void shmem_put_link(void *arg) +{ + mark_page_accessed(arg); + put_page(arg); +} + +static const char *shmem_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) +{ + struct page *page = NULL; + int error; + if (!dentry) { + page = find_get_page(inode->i_mapping, 0); + if (!page) + return ERR_PTR(-ECHILD); + if (!PageUptodate(page)) { + put_page(page); + return ERR_PTR(-ECHILD); + } + } else { + error = shmem_getpage(inode, 0, &page, SGP_READ); + if (error) + return ERR_PTR(error); + unlock_page(page); + } + set_delayed_call(done, shmem_put_link, page); + return page_address(page); +} + +#ifdef CONFIG_TMPFS_XATTR +/* + * Superblocks without xattr inode operations may get some security.* xattr + * support from the LSM "for free". As soon as we have any other xattrs + * like ACLs, we also need to implement the security.* handlers at + * filesystem level, though. + */ + +/* + * Callback for security_inode_init_security() for acquiring xattrs. + */ +static int shmem_initxattrs(struct inode *inode, + const struct xattr *xattr_array, + void *fs_info) +{ + struct shmem_inode_info *info = SHMEM_I(inode); + const struct xattr *xattr; + struct simple_xattr *new_xattr; + size_t len; + + for (xattr = xattr_array; xattr->name != NULL; xattr++) { + new_xattr = simple_xattr_alloc(xattr->value, xattr->value_len); + if (!new_xattr) + return -ENOMEM; + + len = strlen(xattr->name) + 1; + new_xattr->name = kmalloc(XATTR_SECURITY_PREFIX_LEN + len, + GFP_KERNEL); + if (!new_xattr->name) { + kvfree(new_xattr); + return -ENOMEM; + } + + memcpy(new_xattr->name, XATTR_SECURITY_PREFIX, + XATTR_SECURITY_PREFIX_LEN); + memcpy(new_xattr->name + XATTR_SECURITY_PREFIX_LEN, + xattr->name, len); + + simple_xattr_list_add(&info->xattrs, new_xattr); + } + + return 0; +} + +static int shmem_xattr_handler_get(const struct xattr_handler *handler, + struct dentry *unused, struct inode *inode, + const char *name, void *buffer, size_t size) +{ + struct shmem_inode_info *info = SHMEM_I(inode); + + name = xattr_full_name(handler, name); + return simple_xattr_get(&info->xattrs, name, buffer, size); +} + +static int shmem_xattr_handler_set(const struct xattr_handler *handler, + struct dentry *unused, struct inode *inode, + const char *name, const void *value, + size_t size, int flags) +{ + struct shmem_inode_info *info = SHMEM_I(inode); + + name = xattr_full_name(handler, name); + return simple_xattr_set(&info->xattrs, name, value, size, flags, NULL); +} + +static const struct xattr_handler shmem_security_xattr_handler = { + .prefix = XATTR_SECURITY_PREFIX, + .get = shmem_xattr_handler_get, + .set = shmem_xattr_handler_set, +}; + +static const struct xattr_handler shmem_trusted_xattr_handler = { + .prefix = XATTR_TRUSTED_PREFIX, + .get = shmem_xattr_handler_get, + .set = shmem_xattr_handler_set, +}; + +static const struct xattr_handler *shmem_xattr_handlers[] = { +#ifdef CONFIG_TMPFS_POSIX_ACL + &posix_acl_access_xattr_handler, + &posix_acl_default_xattr_handler, +#endif + &shmem_security_xattr_handler, + &shmem_trusted_xattr_handler, + NULL +}; + +static ssize_t shmem_listxattr(struct dentry *dentry, char *buffer, size_t size) +{ + struct shmem_inode_info *info = SHMEM_I(d_inode(dentry)); + return simple_xattr_list(d_inode(dentry), &info->xattrs, buffer, size); +} +#endif /* CONFIG_TMPFS_XATTR */ + +static const struct inode_operations shmem_short_symlink_operations = { + .get_link = simple_get_link, +#ifdef CONFIG_TMPFS_XATTR + .listxattr = shmem_listxattr, +#endif +}; + +static const struct inode_operations shmem_symlink_inode_operations = { + .get_link = shmem_get_link, +#ifdef CONFIG_TMPFS_XATTR + .listxattr = shmem_listxattr, +#endif +}; + +static struct dentry *shmem_get_parent(struct dentry *child) +{ + return ERR_PTR(-ESTALE); +} + +static int shmem_match(struct inode *ino, void *vfh) +{ + __u32 *fh = vfh; + __u64 inum = fh[2]; + inum = (inum << 32) | fh[1]; + return ino->i_ino == inum && fh[0] == ino->i_generation; +} + +/* Find any alias of inode, but prefer a hashed alias */ +static struct dentry *shmem_find_alias(struct inode *inode) +{ + struct dentry *alias = d_find_alias(inode); + + return alias ?: d_find_any_alias(inode); +} + + +static struct dentry *shmem_fh_to_dentry(struct super_block *sb, + struct fid *fid, int fh_len, int fh_type) +{ + struct inode *inode; + struct dentry *dentry = NULL; + u64 inum; + + if (fh_len < 3) + return NULL; + + inum = fid->raw[2]; + inum = (inum << 32) | fid->raw[1]; + + inode = ilookup5(sb, (unsigned long)(inum + fid->raw[0]), + shmem_match, fid->raw); + if (inode) { + dentry = shmem_find_alias(inode); + iput(inode); + } + + return dentry; +} + +static int shmem_encode_fh(struct inode *inode, __u32 *fh, int *len, + struct inode *parent) +{ + if (*len < 3) { + *len = 3; + return FILEID_INVALID; + } + + if (inode_unhashed(inode)) { + /* Unfortunately insert_inode_hash is not idempotent, + * so as we hash inodes here rather than at creation + * time, we need a lock to ensure we only try + * to do it once + */ + static DEFINE_SPINLOCK(lock); + spin_lock(&lock); + if (inode_unhashed(inode)) + __insert_inode_hash(inode, + inode->i_ino + inode->i_generation); + spin_unlock(&lock); + } + + fh[0] = inode->i_generation; + fh[1] = inode->i_ino; + fh[2] = ((__u64)inode->i_ino) >> 32; + + *len = 3; + return 1; +} + +static const struct export_operations shmem_export_ops = { + .get_parent = shmem_get_parent, + .encode_fh = shmem_encode_fh, + .fh_to_dentry = shmem_fh_to_dentry, +}; + +enum shmem_param { + Opt_gid, + Opt_huge, + Opt_mode, + Opt_mpol, + Opt_nr_blocks, + Opt_nr_inodes, + Opt_size, + Opt_uid, + Opt_inode32, + Opt_inode64, +}; + +static const struct constant_table shmem_param_enums_huge[] = { + {"never", SHMEM_HUGE_NEVER }, + {"always", SHMEM_HUGE_ALWAYS }, + {"within_size", SHMEM_HUGE_WITHIN_SIZE }, + {"advise", SHMEM_HUGE_ADVISE }, + {} +}; + +const struct fs_parameter_spec shmem_fs_parameters[] = { + fsparam_u32 ("gid", Opt_gid), + fsparam_enum ("huge", Opt_huge, shmem_param_enums_huge), + fsparam_u32oct("mode", Opt_mode), + fsparam_string("mpol", Opt_mpol), + fsparam_string("nr_blocks", Opt_nr_blocks), + fsparam_string("nr_inodes", Opt_nr_inodes), + fsparam_string("size", Opt_size), + fsparam_u32 ("uid", Opt_uid), + fsparam_flag ("inode32", Opt_inode32), + fsparam_flag ("inode64", Opt_inode64), + {} +}; + +static int shmem_parse_one(struct fs_context *fc, struct fs_parameter *param) +{ + struct shmem_options *ctx = fc->fs_private; + struct fs_parse_result result; + unsigned long long size; + char *rest; + int opt; + kuid_t kuid; + kgid_t kgid; + + opt = fs_parse(fc, shmem_fs_parameters, param, &result); + if (opt < 0) + return opt; + + switch (opt) { + case Opt_size: + size = memparse(param->string, &rest); + if (*rest == '%') { + size <<= PAGE_SHIFT; + size *= totalram_pages(); + do_div(size, 100); + rest++; + } + if (*rest) + goto bad_value; + ctx->blocks = DIV_ROUND_UP(size, PAGE_SIZE); + ctx->seen |= SHMEM_SEEN_BLOCKS; + break; + case Opt_nr_blocks: + ctx->blocks = memparse(param->string, &rest); + if (*rest) + goto bad_value; + ctx->seen |= SHMEM_SEEN_BLOCKS; + break; + case Opt_nr_inodes: + ctx->inodes = memparse(param->string, &rest); + if (*rest) + goto bad_value; + ctx->seen |= SHMEM_SEEN_INODES; + break; + case Opt_mode: + ctx->mode = result.uint_32 & 07777; + break; + case Opt_uid: + kuid = make_kuid(current_user_ns(), result.uint_32); + if (!uid_valid(kuid)) + goto bad_value; + + /* + * The requested uid must be representable in the + * filesystem's idmapping. + */ + if (!kuid_has_mapping(fc->user_ns, kuid)) + goto bad_value; + + ctx->uid = kuid; + break; + case Opt_gid: + kgid = make_kgid(current_user_ns(), result.uint_32); + if (!gid_valid(kgid)) + goto bad_value; + + /* + * The requested gid must be representable in the + * filesystem's idmapping. + */ + if (!kgid_has_mapping(fc->user_ns, kgid)) + goto bad_value; + + ctx->gid = kgid; + break; + case Opt_huge: + ctx->huge = result.uint_32; + if (ctx->huge != SHMEM_HUGE_NEVER && + !(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && + has_transparent_hugepage())) + goto unsupported_parameter; + ctx->seen |= SHMEM_SEEN_HUGE; + break; + case Opt_mpol: + if (IS_ENABLED(CONFIG_NUMA)) { + mpol_put(ctx->mpol); + ctx->mpol = NULL; + if (mpol_parse_str(param->string, &ctx->mpol)) + goto bad_value; + break; + } + goto unsupported_parameter; + case Opt_inode32: + ctx->full_inums = false; + ctx->seen |= SHMEM_SEEN_INUMS; + break; + case Opt_inode64: + if (sizeof(ino_t) < 8) { + return invalfc(fc, + "Cannot use inode64 with <64bit inums in kernel\n"); + } + ctx->full_inums = true; + ctx->seen |= SHMEM_SEEN_INUMS; + break; + } + return 0; + +unsupported_parameter: + return invalfc(fc, "Unsupported parameter '%s'", param->key); +bad_value: + return invalfc(fc, "Bad value for '%s'", param->key); +} + +static int shmem_parse_options(struct fs_context *fc, void *data) +{ + char *options = data; + + if (options) { + int err = security_sb_eat_lsm_opts(options, &fc->security); + if (err) + return err; + } + + while (options != NULL) { + char *this_char = options; + for (;;) { + /* + * NUL-terminate this option: unfortunately, + * mount options form a comma-separated list, + * but mpol's nodelist may also contain commas. + */ + options = strchr(options, ','); + if (options == NULL) + break; + options++; + if (!isdigit(*options)) { + options[-1] = '\0'; + break; + } + } + if (*this_char) { + char *value = strchr(this_char,'='); + size_t len = 0; + int err; + + if (value) { + *value++ = '\0'; + len = strlen(value); + } + err = vfs_parse_fs_string(fc, this_char, value, len); + if (err < 0) + return err; + } + } + return 0; +} + +/* + * Reconfigure a shmem filesystem. + * + * Note that we disallow change from limited->unlimited blocks/inodes while any + * are in use; but we must separately disallow unlimited->limited, because in + * that case we have no record of how much is already in use. + */ +static int shmem_reconfigure(struct fs_context *fc) +{ + struct shmem_options *ctx = fc->fs_private; + struct shmem_sb_info *sbinfo = SHMEM_SB(fc->root->d_sb); + unsigned long inodes; + const char *err; + + spin_lock(&sbinfo->stat_lock); + inodes = sbinfo->max_inodes - sbinfo->free_inodes; + if ((ctx->seen & SHMEM_SEEN_BLOCKS) && ctx->blocks) { + if (!sbinfo->max_blocks) { + err = "Cannot retroactively limit size"; + goto out; + } + if (percpu_counter_compare(&sbinfo->used_blocks, + ctx->blocks) > 0) { + err = "Too small a size for current use"; + goto out; + } + } + if ((ctx->seen & SHMEM_SEEN_INODES) && ctx->inodes) { + if (!sbinfo->max_inodes) { + err = "Cannot retroactively limit inodes"; + goto out; + } + if (ctx->inodes < inodes) { + err = "Too few inodes for current use"; + goto out; + } + } + + if ((ctx->seen & SHMEM_SEEN_INUMS) && !ctx->full_inums && + sbinfo->next_ino > UINT_MAX) { + err = "Current inum too high to switch to 32-bit inums"; + goto out; + } + + if (ctx->seen & SHMEM_SEEN_HUGE) + sbinfo->huge = ctx->huge; + if (ctx->seen & SHMEM_SEEN_INUMS) + sbinfo->full_inums = ctx->full_inums; + if (ctx->seen & SHMEM_SEEN_BLOCKS) + sbinfo->max_blocks = ctx->blocks; + if (ctx->seen & SHMEM_SEEN_INODES) { + sbinfo->max_inodes = ctx->inodes; + sbinfo->free_inodes = ctx->inodes - inodes; + } + + /* + * Preserve previous mempolicy unless mpol remount option was specified. + */ + if (ctx->mpol) { + mpol_put(sbinfo->mpol); + sbinfo->mpol = ctx->mpol; /* transfers initial ref */ + ctx->mpol = NULL; + } + spin_unlock(&sbinfo->stat_lock); + return 0; +out: + spin_unlock(&sbinfo->stat_lock); + return invalfc(fc, "%s", err); +} + +static int shmem_show_options(struct seq_file *seq, struct dentry *root) +{ + struct shmem_sb_info *sbinfo = SHMEM_SB(root->d_sb); + + if (sbinfo->max_blocks != shmem_default_max_blocks()) + seq_printf(seq, ",size=%luk", + sbinfo->max_blocks << (PAGE_SHIFT - 10)); + if (sbinfo->max_inodes != shmem_default_max_inodes()) + seq_printf(seq, ",nr_inodes=%lu", sbinfo->max_inodes); + if (sbinfo->mode != (0777 | S_ISVTX)) + seq_printf(seq, ",mode=%03ho", sbinfo->mode); + if (!uid_eq(sbinfo->uid, GLOBAL_ROOT_UID)) + seq_printf(seq, ",uid=%u", + from_kuid_munged(&init_user_ns, sbinfo->uid)); + if (!gid_eq(sbinfo->gid, GLOBAL_ROOT_GID)) + seq_printf(seq, ",gid=%u", + from_kgid_munged(&init_user_ns, sbinfo->gid)); + + /* + * Showing inode{64,32} might be useful even if it's the system default, + * since then people don't have to resort to checking both here and + * /proc/config.gz to confirm 64-bit inums were successfully applied + * (which may not even exist if IKCONFIG_PROC isn't enabled). + * + * We hide it when inode64 isn't the default and we are using 32-bit + * inodes, since that probably just means the feature isn't even under + * consideration. + * + * As such: + * + * +-----------------+-----------------+ + * | TMPFS_INODE64=y | TMPFS_INODE64=n | + * +------------------+-----------------+-----------------+ + * | full_inums=true | show | show | + * | full_inums=false | show | hide | + * +------------------+-----------------+-----------------+ + * + */ + if (IS_ENABLED(CONFIG_TMPFS_INODE64) || sbinfo->full_inums) + seq_printf(seq, ",inode%d", (sbinfo->full_inums ? 64 : 32)); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + /* Rightly or wrongly, show huge mount option unmasked by shmem_huge */ + if (sbinfo->huge) + seq_printf(seq, ",huge=%s", shmem_format_huge(sbinfo->huge)); +#endif + shmem_show_mpol(seq, sbinfo->mpol); + return 0; +} + +#endif /* CONFIG_TMPFS */ + +static void shmem_put_super(struct super_block *sb) +{ + struct shmem_sb_info *sbinfo = SHMEM_SB(sb); + + free_percpu(sbinfo->ino_batch); + percpu_counter_destroy(&sbinfo->used_blocks); + mpol_put(sbinfo->mpol); + kfree(sbinfo); + sb->s_fs_info = NULL; +} + +static int shmem_fill_super(struct super_block *sb, struct fs_context *fc) +{ + struct shmem_options *ctx = fc->fs_private; + struct inode *inode; + struct shmem_sb_info *sbinfo; + int err = -ENOMEM; + + /* Round up to L1_CACHE_BYTES to resist false sharing */ + sbinfo = kzalloc(max((int)sizeof(struct shmem_sb_info), + L1_CACHE_BYTES), GFP_KERNEL); + if (!sbinfo) + return -ENOMEM; + + sb->s_fs_info = sbinfo; + +#ifdef CONFIG_TMPFS + /* + * Per default we only allow half of the physical ram per + * tmpfs instance, limiting inodes to one per page of lowmem; + * but the internal instance is left unlimited. + */ + if (!(sb->s_flags & SB_KERNMOUNT)) { + if (!(ctx->seen & SHMEM_SEEN_BLOCKS)) + ctx->blocks = shmem_default_max_blocks(); + if (!(ctx->seen & SHMEM_SEEN_INODES)) + ctx->inodes = shmem_default_max_inodes(); + if (!(ctx->seen & SHMEM_SEEN_INUMS)) + ctx->full_inums = IS_ENABLED(CONFIG_TMPFS_INODE64); + } else { + sb->s_flags |= SB_NOUSER; + } + sb->s_export_op = &shmem_export_ops; + sb->s_flags |= SB_NOSEC; +#else + sb->s_flags |= SB_NOUSER; +#endif + sbinfo->max_blocks = ctx->blocks; + sbinfo->free_inodes = sbinfo->max_inodes = ctx->inodes; + if (sb->s_flags & SB_KERNMOUNT) { + sbinfo->ino_batch = alloc_percpu(ino_t); + if (!sbinfo->ino_batch) + goto failed; + } + sbinfo->uid = ctx->uid; + sbinfo->gid = ctx->gid; + sbinfo->full_inums = ctx->full_inums; + sbinfo->mode = ctx->mode; + sbinfo->huge = ctx->huge; + sbinfo->mpol = ctx->mpol; + ctx->mpol = NULL; + + spin_lock_init(&sbinfo->stat_lock); + if (percpu_counter_init(&sbinfo->used_blocks, 0, GFP_KERNEL)) + goto failed; + spin_lock_init(&sbinfo->shrinklist_lock); + INIT_LIST_HEAD(&sbinfo->shrinklist); + + sb->s_maxbytes = MAX_LFS_FILESIZE; + sb->s_blocksize = PAGE_SIZE; + sb->s_blocksize_bits = PAGE_SHIFT; + sb->s_magic = TMPFS_MAGIC; + sb->s_op = &shmem_ops; + sb->s_time_gran = 1; +#ifdef CONFIG_TMPFS_XATTR + sb->s_xattr = shmem_xattr_handlers; +#endif +#ifdef CONFIG_TMPFS_POSIX_ACL + sb->s_flags |= SB_POSIXACL; +#endif + uuid_gen(&sb->s_uuid); + + inode = shmem_get_inode(sb, NULL, S_IFDIR | sbinfo->mode, 0, VM_NORESERVE); + if (!inode) + goto failed; + inode->i_uid = sbinfo->uid; + inode->i_gid = sbinfo->gid; + sb->s_root = d_make_root(inode); + if (!sb->s_root) + goto failed; + return 0; + +failed: + shmem_put_super(sb); + return err; +} + +static int shmem_get_tree(struct fs_context *fc) +{ + return get_tree_nodev(fc, shmem_fill_super); +} + +static void shmem_free_fc(struct fs_context *fc) +{ + struct shmem_options *ctx = fc->fs_private; + + if (ctx) { + mpol_put(ctx->mpol); + kfree(ctx); + } +} + +static const struct fs_context_operations shmem_fs_context_ops = { + .free = shmem_free_fc, + .get_tree = shmem_get_tree, +#ifdef CONFIG_TMPFS + .parse_monolithic = shmem_parse_options, + .parse_param = shmem_parse_one, + .reconfigure = shmem_reconfigure, +#endif +}; + +static struct kmem_cache *shmem_inode_cachep; + +static struct inode *shmem_alloc_inode(struct super_block *sb) +{ + struct shmem_inode_info *info; + info = kmem_cache_alloc(shmem_inode_cachep, GFP_KERNEL); + if (!info) + return NULL; + return &info->vfs_inode; +} + +static void shmem_free_in_core_inode(struct inode *inode) +{ + if (S_ISLNK(inode->i_mode)) + kfree(inode->i_link); + kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode)); +} + +static void shmem_destroy_inode(struct inode *inode) +{ + if (S_ISREG(inode->i_mode)) + mpol_free_shared_policy(&SHMEM_I(inode)->policy); +} + +static void shmem_init_inode(void *foo) +{ + struct shmem_inode_info *info = foo; + inode_init_once(&info->vfs_inode); +} + +static void shmem_init_inodecache(void) +{ + shmem_inode_cachep = kmem_cache_create("shmem_inode_cache", + sizeof(struct shmem_inode_info), + 0, SLAB_PANIC|SLAB_ACCOUNT, shmem_init_inode); +} + +static void shmem_destroy_inodecache(void) +{ + kmem_cache_destroy(shmem_inode_cachep); +} + +static const struct address_space_operations shmem_aops = { + .writepage = shmem_writepage, + .set_page_dirty = __set_page_dirty_no_writeback, +#ifdef CONFIG_TMPFS + .write_begin = shmem_write_begin, + .write_end = shmem_write_end, +#endif +#ifdef CONFIG_MIGRATION + .migratepage = migrate_page, +#endif + .error_remove_page = generic_error_remove_page, +}; + +static const struct file_operations shmem_file_operations = { + .mmap = shmem_mmap, + .get_unmapped_area = shmem_get_unmapped_area, +#ifdef CONFIG_TMPFS + .llseek = shmem_file_llseek, + .read_iter = shmem_file_read_iter, + .write_iter = generic_file_write_iter, + .fsync = noop_fsync, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, + .fallocate = shmem_fallocate, +#endif +}; + +static const struct inode_operations shmem_inode_operations = { + .getattr = shmem_getattr, + .setattr = shmem_setattr, +#ifdef CONFIG_TMPFS_XATTR + .listxattr = shmem_listxattr, + .set_acl = simple_set_acl, +#endif +}; + +static const struct inode_operations shmem_dir_inode_operations = { +#ifdef CONFIG_TMPFS + .create = shmem_create, + .lookup = simple_lookup, + .link = shmem_link, + .unlink = shmem_unlink, + .symlink = shmem_symlink, + .mkdir = shmem_mkdir, + .rmdir = shmem_rmdir, + .mknod = shmem_mknod, + .rename = shmem_rename2, + .tmpfile = shmem_tmpfile, +#endif +#ifdef CONFIG_TMPFS_XATTR + .listxattr = shmem_listxattr, +#endif +#ifdef CONFIG_TMPFS_POSIX_ACL + .setattr = shmem_setattr, + .set_acl = simple_set_acl, +#endif +}; + +static const struct inode_operations shmem_special_inode_operations = { +#ifdef CONFIG_TMPFS_XATTR + .listxattr = shmem_listxattr, +#endif +#ifdef CONFIG_TMPFS_POSIX_ACL + .setattr = shmem_setattr, + .set_acl = simple_set_acl, +#endif +}; + +static const struct super_operations shmem_ops = { + .alloc_inode = shmem_alloc_inode, + .free_inode = shmem_free_in_core_inode, + .destroy_inode = shmem_destroy_inode, +#ifdef CONFIG_TMPFS + .statfs = shmem_statfs, + .show_options = shmem_show_options, +#endif + .evict_inode = shmem_evict_inode, + .drop_inode = generic_delete_inode, + .put_super = shmem_put_super, +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + .nr_cached_objects = shmem_unused_huge_count, + .free_cached_objects = shmem_unused_huge_scan, +#endif +}; + +static const struct vm_operations_struct shmem_vm_ops = { + .fault = shmem_fault, + .map_pages = filemap_map_pages, +#ifdef CONFIG_NUMA + .set_policy = shmem_set_policy, + .get_policy = shmem_get_policy, +#endif +}; + +int shmem_init_fs_context(struct fs_context *fc) +{ + struct shmem_options *ctx; + + ctx = kzalloc(sizeof(struct shmem_options), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + ctx->mode = 0777 | S_ISVTX; + ctx->uid = current_fsuid(); + ctx->gid = current_fsgid(); + + fc->fs_private = ctx; + fc->ops = &shmem_fs_context_ops; + return 0; +} + +static struct file_system_type shmem_fs_type = { + .owner = THIS_MODULE, + .name = "tmpfs", + .init_fs_context = shmem_init_fs_context, +#ifdef CONFIG_TMPFS + .parameters = shmem_fs_parameters, +#endif + .kill_sb = kill_litter_super, + .fs_flags = FS_USERNS_MOUNT | FS_THP_SUPPORT, +}; + +int __init shmem_init(void) +{ + int error; + + shmem_init_inodecache(); + + error = register_filesystem(&shmem_fs_type); + if (error) { + pr_err("Could not register tmpfs\n"); + goto out2; + } + + shm_mnt = kern_mount(&shmem_fs_type); + if (IS_ERR(shm_mnt)) { + error = PTR_ERR(shm_mnt); + pr_err("Could not kern_mount tmpfs\n"); + goto out1; + } + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (has_transparent_hugepage() && shmem_huge > SHMEM_HUGE_DENY) + SHMEM_SB(shm_mnt->mnt_sb)->huge = shmem_huge; + else + shmem_huge = 0; /* just in case it was patched */ +#endif + return 0; + +out1: + unregister_filesystem(&shmem_fs_type); +out2: + shmem_destroy_inodecache(); + shm_mnt = ERR_PTR(error); + return error; +} + +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && defined(CONFIG_SYSFS) +static ssize_t shmem_enabled_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + static const int values[] = { + SHMEM_HUGE_ALWAYS, + SHMEM_HUGE_WITHIN_SIZE, + SHMEM_HUGE_ADVISE, + SHMEM_HUGE_NEVER, + SHMEM_HUGE_DENY, + SHMEM_HUGE_FORCE, + }; + int i, count; + + for (i = 0, count = 0; i < ARRAY_SIZE(values); i++) { + const char *fmt = shmem_huge == values[i] ? "[%s] " : "%s "; + + count += sprintf(buf + count, fmt, + shmem_format_huge(values[i])); + } + buf[count - 1] = '\n'; + return count; +} + +static ssize_t shmem_enabled_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + char tmp[16]; + int huge; + + if (count + 1 > sizeof(tmp)) + return -EINVAL; + memcpy(tmp, buf, count); + tmp[count] = '\0'; + if (count && tmp[count - 1] == '\n') + tmp[count - 1] = '\0'; + + huge = shmem_parse_huge(tmp); + if (huge == -EINVAL) + return -EINVAL; + if (!has_transparent_hugepage() && + huge != SHMEM_HUGE_NEVER && huge != SHMEM_HUGE_DENY) + return -EINVAL; + + shmem_huge = huge; + if (shmem_huge > SHMEM_HUGE_DENY) + SHMEM_SB(shm_mnt->mnt_sb)->huge = shmem_huge; + return count; +} + +struct kobj_attribute shmem_enabled_attr = + __ATTR(shmem_enabled, 0644, shmem_enabled_show, shmem_enabled_store); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE && CONFIG_SYSFS */ + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +bool shmem_huge_enabled(struct vm_area_struct *vma) +{ + struct inode *inode = file_inode(vma->vm_file); + struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); + loff_t i_size; + pgoff_t off; + + if (!transhuge_vma_enabled(vma, vma->vm_flags)) + return false; + if (shmem_huge == SHMEM_HUGE_FORCE) + return true; + if (shmem_huge == SHMEM_HUGE_DENY) + return false; + switch (sbinfo->huge) { + case SHMEM_HUGE_NEVER: + return false; + case SHMEM_HUGE_ALWAYS: + return true; + case SHMEM_HUGE_WITHIN_SIZE: + off = round_up(vma->vm_pgoff, HPAGE_PMD_NR); + i_size = round_up(i_size_read(inode), PAGE_SIZE); + if (i_size >= HPAGE_PMD_SIZE && + i_size >> PAGE_SHIFT >= off) + return true; + fallthrough; + case SHMEM_HUGE_ADVISE: + /* TODO: implement fadvise() hints */ + return (vma->vm_flags & VM_HUGEPAGE); + default: + VM_BUG_ON(1); + return false; + } +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +#else /* !CONFIG_SHMEM */ + +/* + * tiny-shmem: simple shmemfs and tmpfs using ramfs code + * + * This is intended for small system where the benefits of the full + * shmem code (swap-backed and resource-limited) are outweighed by + * their complexity. On systems without swap this code should be + * effectively equivalent, but much lighter weight. + */ + +static struct file_system_type shmem_fs_type = { + .name = "tmpfs", + .init_fs_context = ramfs_init_fs_context, + .parameters = ramfs_fs_parameters, + .kill_sb = ramfs_kill_sb, + .fs_flags = FS_USERNS_MOUNT, +}; + +int __init shmem_init(void) +{ + BUG_ON(register_filesystem(&shmem_fs_type) != 0); + + shm_mnt = kern_mount(&shmem_fs_type); + BUG_ON(IS_ERR(shm_mnt)); + + return 0; +} + +int shmem_unuse(unsigned int type, bool frontswap, + unsigned long *fs_pages_to_unuse) +{ + return 0; +} + +int shmem_lock(struct file *file, int lock, struct user_struct *user) +{ + return 0; +} + +void shmem_unlock_mapping(struct address_space *mapping) +{ +} + +#ifdef CONFIG_MMU +unsigned long shmem_get_unmapped_area(struct file *file, + unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags) +{ + return current->mm->get_unmapped_area(file, addr, len, pgoff, flags); +} +#endif + +void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) +{ + truncate_inode_pages_range(inode->i_mapping, lstart, lend); +} +EXPORT_SYMBOL_GPL(shmem_truncate_range); + +#define shmem_vm_ops generic_file_vm_ops +#define shmem_file_operations ramfs_file_operations +#define shmem_get_inode(sb, dir, mode, dev, flags) ramfs_get_inode(sb, dir, mode, dev) +#define shmem_acct_size(flags, size) 0 +#define shmem_unacct_size(flags, size) do {} while (0) + +#endif /* CONFIG_SHMEM */ + +/* common code */ + +static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name, loff_t size, + unsigned long flags, unsigned int i_flags) +{ + struct inode *inode; + struct file *res; + + if (IS_ERR(mnt)) + return ERR_CAST(mnt); + + if (size < 0 || size > MAX_LFS_FILESIZE) + return ERR_PTR(-EINVAL); + + if (shmem_acct_size(flags, size)) + return ERR_PTR(-ENOMEM); + + inode = shmem_get_inode(mnt->mnt_sb, NULL, S_IFREG | S_IRWXUGO, 0, + flags); + if (unlikely(!inode)) { + shmem_unacct_size(flags, size); + return ERR_PTR(-ENOSPC); + } + inode->i_flags |= i_flags; + inode->i_size = size; + clear_nlink(inode); /* It is unlinked */ + res = ERR_PTR(ramfs_nommu_expand_for_mapping(inode, size)); + if (!IS_ERR(res)) + res = alloc_file_pseudo(inode, mnt, name, O_RDWR, + &shmem_file_operations); + if (IS_ERR(res)) + iput(inode); + return res; +} + +/** + * shmem_kernel_file_setup - get an unlinked file living in tmpfs which must be + * kernel internal. There will be NO LSM permission checks against the + * underlying inode. So users of this interface must do LSM checks at a + * higher layer. The users are the big_key and shm implementations. LSM + * checks are provided at the key or shm level rather than the inode. + * @name: name for dentry (to be seen in /proc//maps + * @size: size to be set for the file + * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size + */ +struct file *shmem_kernel_file_setup(const char *name, loff_t size, unsigned long flags) +{ + return __shmem_file_setup(shm_mnt, name, size, flags, S_PRIVATE); +} + +/** + * shmem_file_setup - get an unlinked file living in tmpfs + * @name: name for dentry (to be seen in /proc//maps + * @size: size to be set for the file + * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size + */ +struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags) +{ + return __shmem_file_setup(shm_mnt, name, size, flags, 0); +} +EXPORT_SYMBOL_GPL(shmem_file_setup); + +/** + * shmem_file_setup_with_mnt - get an unlinked file living in tmpfs + * @mnt: the tmpfs mount where the file will be created + * @name: name for dentry (to be seen in /proc//maps + * @size: size to be set for the file + * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size + */ +struct file *shmem_file_setup_with_mnt(struct vfsmount *mnt, const char *name, + loff_t size, unsigned long flags) +{ + return __shmem_file_setup(mnt, name, size, flags, 0); +} +EXPORT_SYMBOL_GPL(shmem_file_setup_with_mnt); + +/** + * shmem_zero_setup - setup a shared anonymous mapping + * @vma: the vma to be mmapped is prepared by do_mmap + */ +int shmem_zero_setup(struct vm_area_struct *vma) +{ + struct file *file; + loff_t size = vma->vm_end - vma->vm_start; + + /* + * Cloning a new file under mmap_lock leads to a lock ordering conflict + * between XFS directory reading and selinux: since this file is only + * accessible to the user through its mapping, use S_PRIVATE flag to + * bypass file security, in the same way as shmem_kernel_file_setup(). + */ + file = shmem_kernel_file_setup("dev/zero", size, vma->vm_flags); + if (IS_ERR(file)) + return PTR_ERR(file); + + if (vma->vm_file) + fput(vma->vm_file); + vma->vm_file = file; + vma->vm_ops = &shmem_vm_ops; + + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && + ((vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK) < + (vma->vm_end & HPAGE_PMD_MASK)) { + khugepaged_enter(vma, vma->vm_flags); + } + + return 0; +} + +/** + * shmem_read_mapping_page_gfp - read into page cache, using specified page allocation flags. + * @mapping: the page's address_space + * @index: the page index + * @gfp: the page allocator flags to use if allocating + * + * This behaves as a tmpfs "read_cache_page_gfp(mapping, index, gfp)", + * with any new page allocations done using the specified allocation flags. + * But read_cache_page_gfp() uses the ->readpage() method: which does not + * suit tmpfs, since it may have pages in swapcache, and needs to find those + * for itself; although drivers/gpu/drm i915 and ttm rely upon this support. + * + * i915_gem_object_get_pages_gtt() mixes __GFP_NORETRY | __GFP_NOWARN in + * with the mapping_gfp_mask(), to avoid OOMing the machine unnecessarily. + */ +struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, + pgoff_t index, gfp_t gfp) +{ +#ifdef CONFIG_SHMEM + struct inode *inode = mapping->host; + struct page *page; + int error; + + BUG_ON(mapping->a_ops != &shmem_aops); + error = shmem_getpage_gfp(inode, index, &page, SGP_CACHE, + gfp, NULL, NULL, NULL); + if (error) + page = ERR_PTR(error); + else + unlock_page(page); + return page; +#else + /* + * The tiny !SHMEM case uses ramfs without swap + */ + return read_cache_page_gfp(mapping, index, gfp); +#endif +} +EXPORT_SYMBOL_GPL(shmem_read_mapping_page_gfp); diff --git a/mm/shuffle.c b/mm/shuffle.c new file mode 100644 index 000000000..9c2e145a7 --- /dev/null +++ b/mm/shuffle.c @@ -0,0 +1,183 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright(c) 2018 Intel Corporation. All rights reserved. + +#include +#include +#include +#include +#include +#include "internal.h" +#include "shuffle.h" + +DEFINE_STATIC_KEY_FALSE(page_alloc_shuffle_key); + +static bool shuffle_param; +static int shuffle_show(char *buffer, const struct kernel_param *kp) +{ + return sprintf(buffer, "%c\n", shuffle_param ? 'Y' : 'N'); +} + +static __meminit int shuffle_store(const char *val, + const struct kernel_param *kp) +{ + int rc = param_set_bool(val, kp); + + if (rc < 0) + return rc; + if (shuffle_param) + static_branch_enable(&page_alloc_shuffle_key); + return 0; +} +module_param_call(shuffle, shuffle_store, shuffle_show, &shuffle_param, 0400); + +/* + * For two pages to be swapped in the shuffle, they must be free (on a + * 'free_area' lru), have the same order, and have the same migratetype. + */ +static struct page * __meminit shuffle_valid_page(struct zone *zone, + unsigned long pfn, int order) +{ + struct page *page = pfn_to_online_page(pfn); + + /* + * Given we're dealing with randomly selected pfns in a zone we + * need to ask questions like... + */ + + /* ... is the page managed by the buddy? */ + if (!page) + return NULL; + + /* ... is the page assigned to the same zone? */ + if (page_zone(page) != zone) + return NULL; + + /* ...is the page free and currently on a free_area list? */ + if (!PageBuddy(page)) + return NULL; + + /* + * ...is the page on the same list as the page we will + * shuffle it with? + */ + if (buddy_order(page) != order) + return NULL; + + return page; +} + +/* + * Fisher-Yates shuffle the freelist which prescribes iterating through an + * array, pfns in this case, and randomly swapping each entry with another in + * the span, end_pfn - start_pfn. + * + * To keep the implementation simple it does not attempt to correct for sources + * of bias in the distribution, like modulo bias or pseudo-random number + * generator bias. I.e. the expectation is that this shuffling raises the bar + * for attacks that exploit the predictability of page allocations, but need not + * be a perfect shuffle. + */ +#define SHUFFLE_RETRY 10 +void __meminit __shuffle_zone(struct zone *z) +{ + unsigned long i, flags; + unsigned long start_pfn = z->zone_start_pfn; + unsigned long end_pfn = zone_end_pfn(z); + const int order = SHUFFLE_ORDER; + const int order_pages = 1 << order; + + spin_lock_irqsave(&z->lock, flags); + start_pfn = ALIGN(start_pfn, order_pages); + for (i = start_pfn; i < end_pfn; i += order_pages) { + unsigned long j; + int migratetype, retry; + struct page *page_i, *page_j; + + /* + * We expect page_i, in the sub-range of a zone being added + * (@start_pfn to @end_pfn), to more likely be valid compared to + * page_j randomly selected in the span @zone_start_pfn to + * @spanned_pages. + */ + page_i = shuffle_valid_page(z, i, order); + if (!page_i) + continue; + + for (retry = 0; retry < SHUFFLE_RETRY; retry++) { + /* + * Pick a random order aligned page in the zone span as + * a swap target. If the selected pfn is a hole, retry + * up to SHUFFLE_RETRY attempts find a random valid pfn + * in the zone. + */ + j = z->zone_start_pfn + + ALIGN_DOWN(get_random_long() % z->spanned_pages, + order_pages); + page_j = shuffle_valid_page(z, j, order); + if (page_j && page_j != page_i) + break; + } + if (retry >= SHUFFLE_RETRY) { + pr_debug("%s: failed to swap %#lx\n", __func__, i); + continue; + } + + /* + * Each migratetype corresponds to its own list, make sure the + * types match otherwise we're moving pages to lists where they + * do not belong. + */ + migratetype = get_pageblock_migratetype(page_i); + if (get_pageblock_migratetype(page_j) != migratetype) { + pr_debug("%s: migratetype mismatch %#lx\n", __func__, i); + continue; + } + + list_swap(&page_i->lru, &page_j->lru); + + pr_debug("%s: swap: %#lx -> %#lx\n", __func__, i, j); + + /* take it easy on the zone lock */ + if ((i % (100 * order_pages)) == 0) { + spin_unlock_irqrestore(&z->lock, flags); + cond_resched(); + spin_lock_irqsave(&z->lock, flags); + } + } + spin_unlock_irqrestore(&z->lock, flags); +} + +/** + * shuffle_free_memory - reduce the predictability of the page allocator + * @pgdat: node page data + */ +void __meminit __shuffle_free_memory(pg_data_t *pgdat) +{ + struct zone *z; + + for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++) + shuffle_zone(z); +} + +bool shuffle_pick_tail(void) +{ + static u64 rand; + static u8 rand_bits; + bool ret; + + /* + * The lack of locking is deliberate. If 2 threads race to + * update the rand state it just adds to the entropy. + */ + if (rand_bits == 0) { + rand_bits = 64; + rand = get_random_u64(); + } + + ret = rand & 1; + + rand_bits--; + rand >>= 1; + + return ret; +} diff --git a/mm/shuffle.h b/mm/shuffle.h new file mode 100644 index 000000000..71b784f0b --- /dev/null +++ b/mm/shuffle.h @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright(c) 2018 Intel Corporation. All rights reserved. +#ifndef _MM_SHUFFLE_H +#define _MM_SHUFFLE_H +#include + +#define SHUFFLE_ORDER (MAX_ORDER-1) + +#ifdef CONFIG_SHUFFLE_PAGE_ALLOCATOR +DECLARE_STATIC_KEY_FALSE(page_alloc_shuffle_key); +extern void __shuffle_free_memory(pg_data_t *pgdat); +extern bool shuffle_pick_tail(void); +static inline void shuffle_free_memory(pg_data_t *pgdat) +{ + if (!static_branch_unlikely(&page_alloc_shuffle_key)) + return; + __shuffle_free_memory(pgdat); +} + +extern void __shuffle_zone(struct zone *z); +static inline void shuffle_zone(struct zone *z) +{ + if (!static_branch_unlikely(&page_alloc_shuffle_key)) + return; + __shuffle_zone(z); +} + +static inline bool is_shuffle_order(int order) +{ + if (!static_branch_unlikely(&page_alloc_shuffle_key)) + return false; + return order >= SHUFFLE_ORDER; +} +#else +static inline bool shuffle_pick_tail(void) +{ + return false; +} + +static inline void shuffle_free_memory(pg_data_t *pgdat) +{ +} + +static inline void shuffle_zone(struct zone *z) +{ +} + +static inline bool is_shuffle_order(int order) +{ + return false; +} +#endif +#endif /* _MM_SHUFFLE_H */ diff --git a/mm/slab.c b/mm/slab.c new file mode 100644 index 000000000..b2cc2cf7d --- /dev/null +++ b/mm/slab.c @@ -0,0 +1,4201 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/mm/slab.c + * Written by Mark Hemment, 1996/97. + * (markhe@nextd.demon.co.uk) + * + * kmem_cache_destroy() + some cleanup - 1999 Andrea Arcangeli + * + * Major cleanup, different bufctl logic, per-cpu arrays + * (c) 2000 Manfred Spraul + * + * Cleanup, make the head arrays unconditional, preparation for NUMA + * (c) 2002 Manfred Spraul + * + * An implementation of the Slab Allocator as described in outline in; + * UNIX Internals: The New Frontiers by Uresh Vahalia + * Pub: Prentice Hall ISBN 0-13-101908-2 + * or with a little more detail in; + * The Slab Allocator: An Object-Caching Kernel Memory Allocator + * Jeff Bonwick (Sun Microsystems). + * Presented at: USENIX Summer 1994 Technical Conference + * + * The memory is organized in caches, one cache for each object type. + * (e.g. inode_cache, dentry_cache, buffer_head, vm_area_struct) + * Each cache consists out of many slabs (they are small (usually one + * page long) and always contiguous), and each slab contains multiple + * initialized objects. + * + * This means, that your constructor is used only for newly allocated + * slabs and you must pass objects with the same initializations to + * kmem_cache_free. + * + * Each cache can only support one memory type (GFP_DMA, GFP_HIGHMEM, + * normal). If you need a special memory type, then must create a new + * cache for that memory type. + * + * In order to reduce fragmentation, the slabs are sorted in 3 groups: + * full slabs with 0 free objects + * partial slabs + * empty slabs with no allocated objects + * + * If partial slabs exist, then new allocations come from these slabs, + * otherwise from empty slabs or new slabs are allocated. + * + * kmem_cache_destroy() CAN CRASH if you try to allocate from the cache + * during kmem_cache_destroy(). The caller must prevent concurrent allocs. + * + * Each cache has a short per-cpu head array, most allocs + * and frees go into that array, and if that array overflows, then 1/2 + * of the entries in the array are given back into the global cache. + * The head array is strictly LIFO and should improve the cache hit rates. + * On SMP, it additionally reduces the spinlock operations. + * + * The c_cpuarray may not be read with enabled local interrupts - + * it's changed with a smp_call_function(). + * + * SMP synchronization: + * constructors and destructors are called without any locking. + * Several members in struct kmem_cache and struct slab never change, they + * are accessed without any locking. + * The per-cpu arrays are never accessed from the wrong cpu, no locking, + * and local interrupts are disabled so slab code is preempt-safe. + * The non-constant members are protected with a per-cache irq spinlock. + * + * Many thanks to Mark Hemment, who wrote another per-cpu slab patch + * in 2000 - many ideas in the current implementation are derived from + * his patch. + * + * Further notes from the original documentation: + * + * 11 April '97. Started multi-threading - markhe + * The global cache-chain is protected by the mutex 'slab_mutex'. + * The sem is only needed when accessing/extending the cache-chain, which + * can never happen inside an interrupt (kmem_cache_create(), + * kmem_cache_shrink() and kmem_cache_reap()). + * + * At present, each engine can be growing a cache. This should be blocked. + * + * 15 March 2005. NUMA slab allocator. + * Shai Fultheim . + * Shobhit Dayal + * Alok N Kataria + * Christoph Lameter + * + * Modified the slab allocator to be node aware on NUMA systems. + * Each node has its own list of partial, free and full slabs. + * All object allocations for a node occur from node specific slab lists. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include +#include +#include + +#include + +#include "internal.h" + +#include "slab.h" + +/* + * DEBUG - 1 for kmem_cache_create() to honour; SLAB_RED_ZONE & SLAB_POISON. + * 0 for faster, smaller code (especially in the critical paths). + * + * STATS - 1 to collect stats for /proc/slabinfo. + * 0 for faster, smaller code (especially in the critical paths). + * + * FORCED_DEBUG - 1 enables SLAB_RED_ZONE and SLAB_POISON (if possible) + */ + +#ifdef CONFIG_DEBUG_SLAB +#define DEBUG 1 +#define STATS 1 +#define FORCED_DEBUG 1 +#else +#define DEBUG 0 +#define STATS 0 +#define FORCED_DEBUG 0 +#endif + +/* Shouldn't this be in a header file somewhere? */ +#define BYTES_PER_WORD sizeof(void *) +#define REDZONE_ALIGN max(BYTES_PER_WORD, __alignof__(unsigned long long)) + +#ifndef ARCH_KMALLOC_FLAGS +#define ARCH_KMALLOC_FLAGS SLAB_HWCACHE_ALIGN +#endif + +#define FREELIST_BYTE_INDEX (((PAGE_SIZE >> BITS_PER_BYTE) \ + <= SLAB_OBJ_MIN_SIZE) ? 1 : 0) + +#if FREELIST_BYTE_INDEX +typedef unsigned char freelist_idx_t; +#else +typedef unsigned short freelist_idx_t; +#endif + +#define SLAB_OBJ_MAX_NUM ((1 << sizeof(freelist_idx_t) * BITS_PER_BYTE) - 1) + +/* + * struct array_cache + * + * Purpose: + * - LIFO ordering, to hand out cache-warm objects from _alloc + * - reduce the number of linked list operations + * - reduce spinlock operations + * + * The limit is stored in the per-cpu structure to reduce the data cache + * footprint. + * + */ +struct array_cache { + unsigned int avail; + unsigned int limit; + unsigned int batchcount; + unsigned int touched; + void *entry[]; /* + * Must have this definition in here for the proper + * alignment of array_cache. Also simplifies accessing + * the entries. + */ +}; + +struct alien_cache { + spinlock_t lock; + struct array_cache ac; +}; + +/* + * Need this for bootstrapping a per node allocator. + */ +#define NUM_INIT_LISTS (2 * MAX_NUMNODES) +static struct kmem_cache_node __initdata init_kmem_cache_node[NUM_INIT_LISTS]; +#define CACHE_CACHE 0 +#define SIZE_NODE (MAX_NUMNODES) + +static int drain_freelist(struct kmem_cache *cache, + struct kmem_cache_node *n, int tofree); +static void free_block(struct kmem_cache *cachep, void **objpp, int len, + int node, struct list_head *list); +static void slabs_destroy(struct kmem_cache *cachep, struct list_head *list); +static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp); +static void cache_reap(struct work_struct *unused); + +static inline void fixup_objfreelist_debug(struct kmem_cache *cachep, + void **list); +static inline void fixup_slab_list(struct kmem_cache *cachep, + struct kmem_cache_node *n, struct page *page, + void **list); +static int slab_early_init = 1; + +#define INDEX_NODE kmalloc_index(sizeof(struct kmem_cache_node)) + +static void kmem_cache_node_init(struct kmem_cache_node *parent) +{ + INIT_LIST_HEAD(&parent->slabs_full); + INIT_LIST_HEAD(&parent->slabs_partial); + INIT_LIST_HEAD(&parent->slabs_free); + parent->total_slabs = 0; + parent->free_slabs = 0; + parent->shared = NULL; + parent->alien = NULL; + parent->colour_next = 0; + spin_lock_init(&parent->list_lock); + parent->free_objects = 0; + parent->free_touched = 0; +} + +#define MAKE_LIST(cachep, listp, slab, nodeid) \ + do { \ + INIT_LIST_HEAD(listp); \ + list_splice(&get_node(cachep, nodeid)->slab, listp); \ + } while (0) + +#define MAKE_ALL_LISTS(cachep, ptr, nodeid) \ + do { \ + MAKE_LIST((cachep), (&(ptr)->slabs_full), slabs_full, nodeid); \ + MAKE_LIST((cachep), (&(ptr)->slabs_partial), slabs_partial, nodeid); \ + MAKE_LIST((cachep), (&(ptr)->slabs_free), slabs_free, nodeid); \ + } while (0) + +#define CFLGS_OBJFREELIST_SLAB ((slab_flags_t __force)0x40000000U) +#define CFLGS_OFF_SLAB ((slab_flags_t __force)0x80000000U) +#define OBJFREELIST_SLAB(x) ((x)->flags & CFLGS_OBJFREELIST_SLAB) +#define OFF_SLAB(x) ((x)->flags & CFLGS_OFF_SLAB) + +#define BATCHREFILL_LIMIT 16 +/* + * Optimization question: fewer reaps means less probability for unnessary + * cpucache drain/refill cycles. + * + * OTOH the cpuarrays can contain lots of objects, + * which could lock up otherwise freeable slabs. + */ +#define REAPTIMEOUT_AC (2*HZ) +#define REAPTIMEOUT_NODE (4*HZ) + +#if STATS +#define STATS_INC_ACTIVE(x) ((x)->num_active++) +#define STATS_DEC_ACTIVE(x) ((x)->num_active--) +#define STATS_INC_ALLOCED(x) ((x)->num_allocations++) +#define STATS_INC_GROWN(x) ((x)->grown++) +#define STATS_ADD_REAPED(x,y) ((x)->reaped += (y)) +#define STATS_SET_HIGH(x) \ + do { \ + if ((x)->num_active > (x)->high_mark) \ + (x)->high_mark = (x)->num_active; \ + } while (0) +#define STATS_INC_ERR(x) ((x)->errors++) +#define STATS_INC_NODEALLOCS(x) ((x)->node_allocs++) +#define STATS_INC_NODEFREES(x) ((x)->node_frees++) +#define STATS_INC_ACOVERFLOW(x) ((x)->node_overflow++) +#define STATS_SET_FREEABLE(x, i) \ + do { \ + if ((x)->max_freeable < i) \ + (x)->max_freeable = i; \ + } while (0) +#define STATS_INC_ALLOCHIT(x) atomic_inc(&(x)->allochit) +#define STATS_INC_ALLOCMISS(x) atomic_inc(&(x)->allocmiss) +#define STATS_INC_FREEHIT(x) atomic_inc(&(x)->freehit) +#define STATS_INC_FREEMISS(x) atomic_inc(&(x)->freemiss) +#else +#define STATS_INC_ACTIVE(x) do { } while (0) +#define STATS_DEC_ACTIVE(x) do { } while (0) +#define STATS_INC_ALLOCED(x) do { } while (0) +#define STATS_INC_GROWN(x) do { } while (0) +#define STATS_ADD_REAPED(x,y) do { (void)(y); } while (0) +#define STATS_SET_HIGH(x) do { } while (0) +#define STATS_INC_ERR(x) do { } while (0) +#define STATS_INC_NODEALLOCS(x) do { } while (0) +#define STATS_INC_NODEFREES(x) do { } while (0) +#define STATS_INC_ACOVERFLOW(x) do { } while (0) +#define STATS_SET_FREEABLE(x, i) do { } while (0) +#define STATS_INC_ALLOCHIT(x) do { } while (0) +#define STATS_INC_ALLOCMISS(x) do { } while (0) +#define STATS_INC_FREEHIT(x) do { } while (0) +#define STATS_INC_FREEMISS(x) do { } while (0) +#endif + +#if DEBUG + +/* + * memory layout of objects: + * 0 : objp + * 0 .. cachep->obj_offset - BYTES_PER_WORD - 1: padding. This ensures that + * the end of an object is aligned with the end of the real + * allocation. Catches writes behind the end of the allocation. + * cachep->obj_offset - BYTES_PER_WORD .. cachep->obj_offset - 1: + * redzone word. + * cachep->obj_offset: The real object. + * cachep->size - 2* BYTES_PER_WORD: redzone word [BYTES_PER_WORD long] + * cachep->size - 1* BYTES_PER_WORD: last caller address + * [BYTES_PER_WORD long] + */ +static int obj_offset(struct kmem_cache *cachep) +{ + return cachep->obj_offset; +} + +static unsigned long long *dbg_redzone1(struct kmem_cache *cachep, void *objp) +{ + BUG_ON(!(cachep->flags & SLAB_RED_ZONE)); + return (unsigned long long*) (objp + obj_offset(cachep) - + sizeof(unsigned long long)); +} + +static unsigned long long *dbg_redzone2(struct kmem_cache *cachep, void *objp) +{ + BUG_ON(!(cachep->flags & SLAB_RED_ZONE)); + if (cachep->flags & SLAB_STORE_USER) + return (unsigned long long *)(objp + cachep->size - + sizeof(unsigned long long) - + REDZONE_ALIGN); + return (unsigned long long *) (objp + cachep->size - + sizeof(unsigned long long)); +} + +static void **dbg_userword(struct kmem_cache *cachep, void *objp) +{ + BUG_ON(!(cachep->flags & SLAB_STORE_USER)); + return (void **)(objp + cachep->size - BYTES_PER_WORD); +} + +#else + +#define obj_offset(x) 0 +#define dbg_redzone1(cachep, objp) ({BUG(); (unsigned long long *)NULL;}) +#define dbg_redzone2(cachep, objp) ({BUG(); (unsigned long long *)NULL;}) +#define dbg_userword(cachep, objp) ({BUG(); (void **)NULL;}) + +#endif + +/* + * Do not go above this order unless 0 objects fit into the slab or + * overridden on the command line. + */ +#define SLAB_MAX_ORDER_HI 1 +#define SLAB_MAX_ORDER_LO 0 +static int slab_max_order = SLAB_MAX_ORDER_LO; +static bool slab_max_order_set __initdata; + +static inline void *index_to_obj(struct kmem_cache *cache, struct page *page, + unsigned int idx) +{ + return page->s_mem + cache->size * idx; +} + +#define BOOT_CPUCACHE_ENTRIES 1 +/* internal cache of cache description objs */ +static struct kmem_cache kmem_cache_boot = { + .batchcount = 1, + .limit = BOOT_CPUCACHE_ENTRIES, + .shared = 1, + .size = sizeof(struct kmem_cache), + .name = "kmem_cache", +}; + +static DEFINE_PER_CPU(struct delayed_work, slab_reap_work); + +static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep) +{ + return this_cpu_ptr(cachep->cpu_cache); +} + +/* + * Calculate the number of objects and left-over bytes for a given buffer size. + */ +static unsigned int cache_estimate(unsigned long gfporder, size_t buffer_size, + slab_flags_t flags, size_t *left_over) +{ + unsigned int num; + size_t slab_size = PAGE_SIZE << gfporder; + + /* + * The slab management structure can be either off the slab or + * on it. For the latter case, the memory allocated for a + * slab is used for: + * + * - @buffer_size bytes for each object + * - One freelist_idx_t for each object + * + * We don't need to consider alignment of freelist because + * freelist will be at the end of slab page. The objects will be + * at the correct alignment. + * + * If the slab management structure is off the slab, then the + * alignment will already be calculated into the size. Because + * the slabs are all pages aligned, the objects will be at the + * correct alignment when allocated. + */ + if (flags & (CFLGS_OBJFREELIST_SLAB | CFLGS_OFF_SLAB)) { + num = slab_size / buffer_size; + *left_over = slab_size % buffer_size; + } else { + num = slab_size / (buffer_size + sizeof(freelist_idx_t)); + *left_over = slab_size % + (buffer_size + sizeof(freelist_idx_t)); + } + + return num; +} + +#if DEBUG +#define slab_error(cachep, msg) __slab_error(__func__, cachep, msg) + +static void __slab_error(const char *function, struct kmem_cache *cachep, + char *msg) +{ + pr_err("slab error in %s(): cache `%s': %s\n", + function, cachep->name, msg); + dump_stack(); + add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); +} +#endif + +/* + * By default on NUMA we use alien caches to stage the freeing of + * objects allocated from other nodes. This causes massive memory + * inefficiencies when using fake NUMA setup to split memory into a + * large number of small nodes, so it can be disabled on the command + * line + */ + +static int use_alien_caches __read_mostly = 1; +static int __init noaliencache_setup(char *s) +{ + use_alien_caches = 0; + return 1; +} +__setup("noaliencache", noaliencache_setup); + +static int __init slab_max_order_setup(char *str) +{ + get_option(&str, &slab_max_order); + slab_max_order = slab_max_order < 0 ? 0 : + min(slab_max_order, MAX_ORDER - 1); + slab_max_order_set = true; + + return 1; +} +__setup("slab_max_order=", slab_max_order_setup); + +#ifdef CONFIG_NUMA +/* + * Special reaping functions for NUMA systems called from cache_reap(). + * These take care of doing round robin flushing of alien caches (containing + * objects freed on different nodes from which they were allocated) and the + * flushing of remote pcps by calling drain_node_pages. + */ +static DEFINE_PER_CPU(unsigned long, slab_reap_node); + +static void init_reap_node(int cpu) +{ + per_cpu(slab_reap_node, cpu) = next_node_in(cpu_to_mem(cpu), + node_online_map); +} + +static void next_reap_node(void) +{ + int node = __this_cpu_read(slab_reap_node); + + node = next_node_in(node, node_online_map); + __this_cpu_write(slab_reap_node, node); +} + +#else +#define init_reap_node(cpu) do { } while (0) +#define next_reap_node(void) do { } while (0) +#endif + +/* + * Initiate the reap timer running on the target CPU. We run at around 1 to 2Hz + * via the workqueue/eventd. + * Add the CPU number into the expiration time to minimize the possibility of + * the CPUs getting into lockstep and contending for the global cache chain + * lock. + */ +static void start_cpu_timer(int cpu) +{ + struct delayed_work *reap_work = &per_cpu(slab_reap_work, cpu); + + if (reap_work->work.func == NULL) { + init_reap_node(cpu); + INIT_DEFERRABLE_WORK(reap_work, cache_reap); + schedule_delayed_work_on(cpu, reap_work, + __round_jiffies_relative(HZ, cpu)); + } +} + +static void init_arraycache(struct array_cache *ac, int limit, int batch) +{ + if (ac) { + ac->avail = 0; + ac->limit = limit; + ac->batchcount = batch; + ac->touched = 0; + } +} + +static struct array_cache *alloc_arraycache(int node, int entries, + int batchcount, gfp_t gfp) +{ + size_t memsize = sizeof(void *) * entries + sizeof(struct array_cache); + struct array_cache *ac = NULL; + + ac = kmalloc_node(memsize, gfp, node); + /* + * The array_cache structures contain pointers to free object. + * However, when such objects are allocated or transferred to another + * cache the pointers are not cleared and they could be counted as + * valid references during a kmemleak scan. Therefore, kmemleak must + * not scan such objects. + */ + kmemleak_no_scan(ac); + init_arraycache(ac, entries, batchcount); + return ac; +} + +static noinline void cache_free_pfmemalloc(struct kmem_cache *cachep, + struct page *page, void *objp) +{ + struct kmem_cache_node *n; + int page_node; + LIST_HEAD(list); + + page_node = page_to_nid(page); + n = get_node(cachep, page_node); + + spin_lock(&n->list_lock); + free_block(cachep, &objp, 1, page_node, &list); + spin_unlock(&n->list_lock); + + slabs_destroy(cachep, &list); +} + +/* + * Transfer objects in one arraycache to another. + * Locking must be handled by the caller. + * + * Return the number of entries transferred. + */ +static int transfer_objects(struct array_cache *to, + struct array_cache *from, unsigned int max) +{ + /* Figure out how many entries to transfer */ + int nr = min3(from->avail, max, to->limit - to->avail); + + if (!nr) + return 0; + + memcpy(to->entry + to->avail, from->entry + from->avail -nr, + sizeof(void *) *nr); + + from->avail -= nr; + to->avail += nr; + return nr; +} + +/* &alien->lock must be held by alien callers. */ +static __always_inline void __free_one(struct array_cache *ac, void *objp) +{ + /* Avoid trivial double-free. */ + if (IS_ENABLED(CONFIG_SLAB_FREELIST_HARDENED) && + WARN_ON_ONCE(ac->avail > 0 && ac->entry[ac->avail - 1] == objp)) + return; + ac->entry[ac->avail++] = objp; +} + +#ifndef CONFIG_NUMA + +#define drain_alien_cache(cachep, alien) do { } while (0) +#define reap_alien(cachep, n) do { } while (0) + +static inline struct alien_cache **alloc_alien_cache(int node, + int limit, gfp_t gfp) +{ + return NULL; +} + +static inline void free_alien_cache(struct alien_cache **ac_ptr) +{ +} + +static inline int cache_free_alien(struct kmem_cache *cachep, void *objp) +{ + return 0; +} + +static inline void *alternate_node_alloc(struct kmem_cache *cachep, + gfp_t flags) +{ + return NULL; +} + +static inline void *____cache_alloc_node(struct kmem_cache *cachep, + gfp_t flags, int nodeid) +{ + return NULL; +} + +static inline gfp_t gfp_exact_node(gfp_t flags) +{ + return flags & ~__GFP_NOFAIL; +} + +#else /* CONFIG_NUMA */ + +static void *____cache_alloc_node(struct kmem_cache *, gfp_t, int); +static void *alternate_node_alloc(struct kmem_cache *, gfp_t); + +static struct alien_cache *__alloc_alien_cache(int node, int entries, + int batch, gfp_t gfp) +{ + size_t memsize = sizeof(void *) * entries + sizeof(struct alien_cache); + struct alien_cache *alc = NULL; + + alc = kmalloc_node(memsize, gfp, node); + if (alc) { + kmemleak_no_scan(alc); + init_arraycache(&alc->ac, entries, batch); + spin_lock_init(&alc->lock); + } + return alc; +} + +static struct alien_cache **alloc_alien_cache(int node, int limit, gfp_t gfp) +{ + struct alien_cache **alc_ptr; + int i; + + if (limit > 1) + limit = 12; + alc_ptr = kcalloc_node(nr_node_ids, sizeof(void *), gfp, node); + if (!alc_ptr) + return NULL; + + for_each_node(i) { + if (i == node || !node_online(i)) + continue; + alc_ptr[i] = __alloc_alien_cache(node, limit, 0xbaadf00d, gfp); + if (!alc_ptr[i]) { + for (i--; i >= 0; i--) + kfree(alc_ptr[i]); + kfree(alc_ptr); + return NULL; + } + } + return alc_ptr; +} + +static void free_alien_cache(struct alien_cache **alc_ptr) +{ + int i; + + if (!alc_ptr) + return; + for_each_node(i) + kfree(alc_ptr[i]); + kfree(alc_ptr); +} + +static void __drain_alien_cache(struct kmem_cache *cachep, + struct array_cache *ac, int node, + struct list_head *list) +{ + struct kmem_cache_node *n = get_node(cachep, node); + + if (ac->avail) { + spin_lock(&n->list_lock); + /* + * Stuff objects into the remote nodes shared array first. + * That way we could avoid the overhead of putting the objects + * into the free lists and getting them back later. + */ + if (n->shared) + transfer_objects(n->shared, ac, ac->limit); + + free_block(cachep, ac->entry, ac->avail, node, list); + ac->avail = 0; + spin_unlock(&n->list_lock); + } +} + +/* + * Called from cache_reap() to regularly drain alien caches round robin. + */ +static void reap_alien(struct kmem_cache *cachep, struct kmem_cache_node *n) +{ + int node = __this_cpu_read(slab_reap_node); + + if (n->alien) { + struct alien_cache *alc = n->alien[node]; + struct array_cache *ac; + + if (alc) { + ac = &alc->ac; + if (ac->avail && spin_trylock_irq(&alc->lock)) { + LIST_HEAD(list); + + __drain_alien_cache(cachep, ac, node, &list); + spin_unlock_irq(&alc->lock); + slabs_destroy(cachep, &list); + } + } + } +} + +static void drain_alien_cache(struct kmem_cache *cachep, + struct alien_cache **alien) +{ + int i = 0; + struct alien_cache *alc; + struct array_cache *ac; + unsigned long flags; + + for_each_online_node(i) { + alc = alien[i]; + if (alc) { + LIST_HEAD(list); + + ac = &alc->ac; + spin_lock_irqsave(&alc->lock, flags); + __drain_alien_cache(cachep, ac, i, &list); + spin_unlock_irqrestore(&alc->lock, flags); + slabs_destroy(cachep, &list); + } + } +} + +static int __cache_free_alien(struct kmem_cache *cachep, void *objp, + int node, int page_node) +{ + struct kmem_cache_node *n; + struct alien_cache *alien = NULL; + struct array_cache *ac; + LIST_HEAD(list); + + n = get_node(cachep, node); + STATS_INC_NODEFREES(cachep); + if (n->alien && n->alien[page_node]) { + alien = n->alien[page_node]; + ac = &alien->ac; + spin_lock(&alien->lock); + if (unlikely(ac->avail == ac->limit)) { + STATS_INC_ACOVERFLOW(cachep); + __drain_alien_cache(cachep, ac, page_node, &list); + } + __free_one(ac, objp); + spin_unlock(&alien->lock); + slabs_destroy(cachep, &list); + } else { + n = get_node(cachep, page_node); + spin_lock(&n->list_lock); + free_block(cachep, &objp, 1, page_node, &list); + spin_unlock(&n->list_lock); + slabs_destroy(cachep, &list); + } + return 1; +} + +static inline int cache_free_alien(struct kmem_cache *cachep, void *objp) +{ + int page_node = page_to_nid(virt_to_page(objp)); + int node = numa_mem_id(); + /* + * Make sure we are not freeing a object from another node to the array + * cache on this cpu. + */ + if (likely(node == page_node)) + return 0; + + return __cache_free_alien(cachep, objp, node, page_node); +} + +/* + * Construct gfp mask to allocate from a specific node but do not reclaim or + * warn about failures. + */ +static inline gfp_t gfp_exact_node(gfp_t flags) +{ + return (flags | __GFP_THISNODE | __GFP_NOWARN) & ~(__GFP_RECLAIM|__GFP_NOFAIL); +} +#endif + +static int init_cache_node(struct kmem_cache *cachep, int node, gfp_t gfp) +{ + struct kmem_cache_node *n; + + /* + * Set up the kmem_cache_node for cpu before we can + * begin anything. Make sure some other cpu on this + * node has not already allocated this + */ + n = get_node(cachep, node); + if (n) { + spin_lock_irq(&n->list_lock); + n->free_limit = (1 + nr_cpus_node(node)) * cachep->batchcount + + cachep->num; + spin_unlock_irq(&n->list_lock); + + return 0; + } + + n = kmalloc_node(sizeof(struct kmem_cache_node), gfp, node); + if (!n) + return -ENOMEM; + + kmem_cache_node_init(n); + n->next_reap = jiffies + REAPTIMEOUT_NODE + + ((unsigned long)cachep) % REAPTIMEOUT_NODE; + + n->free_limit = + (1 + nr_cpus_node(node)) * cachep->batchcount + cachep->num; + + /* + * The kmem_cache_nodes don't come and go as CPUs + * come and go. slab_mutex is sufficient + * protection here. + */ + cachep->node[node] = n; + + return 0; +} + +#if (defined(CONFIG_NUMA) && defined(CONFIG_MEMORY_HOTPLUG)) || defined(CONFIG_SMP) +/* + * Allocates and initializes node for a node on each slab cache, used for + * either memory or cpu hotplug. If memory is being hot-added, the kmem_cache_node + * will be allocated off-node since memory is not yet online for the new node. + * When hotplugging memory or a cpu, existing node are not replaced if + * already in use. + * + * Must hold slab_mutex. + */ +static int init_cache_node_node(int node) +{ + int ret; + struct kmem_cache *cachep; + + list_for_each_entry(cachep, &slab_caches, list) { + ret = init_cache_node(cachep, node, GFP_KERNEL); + if (ret) + return ret; + } + + return 0; +} +#endif + +static int setup_kmem_cache_node(struct kmem_cache *cachep, + int node, gfp_t gfp, bool force_change) +{ + int ret = -ENOMEM; + struct kmem_cache_node *n; + struct array_cache *old_shared = NULL; + struct array_cache *new_shared = NULL; + struct alien_cache **new_alien = NULL; + LIST_HEAD(list); + + if (use_alien_caches) { + new_alien = alloc_alien_cache(node, cachep->limit, gfp); + if (!new_alien) + goto fail; + } + + if (cachep->shared) { + new_shared = alloc_arraycache(node, + cachep->shared * cachep->batchcount, 0xbaadf00d, gfp); + if (!new_shared) + goto fail; + } + + ret = init_cache_node(cachep, node, gfp); + if (ret) + goto fail; + + n = get_node(cachep, node); + spin_lock_irq(&n->list_lock); + if (n->shared && force_change) { + free_block(cachep, n->shared->entry, + n->shared->avail, node, &list); + n->shared->avail = 0; + } + + if (!n->shared || force_change) { + old_shared = n->shared; + n->shared = new_shared; + new_shared = NULL; + } + + if (!n->alien) { + n->alien = new_alien; + new_alien = NULL; + } + + spin_unlock_irq(&n->list_lock); + slabs_destroy(cachep, &list); + + /* + * To protect lockless access to n->shared during irq disabled context. + * If n->shared isn't NULL in irq disabled context, accessing to it is + * guaranteed to be valid until irq is re-enabled, because it will be + * freed after synchronize_rcu(). + */ + if (old_shared && force_change) + synchronize_rcu(); + +fail: + kfree(old_shared); + kfree(new_shared); + free_alien_cache(new_alien); + + return ret; +} + +#ifdef CONFIG_SMP + +static void cpuup_canceled(long cpu) +{ + struct kmem_cache *cachep; + struct kmem_cache_node *n = NULL; + int node = cpu_to_mem(cpu); + const struct cpumask *mask = cpumask_of_node(node); + + list_for_each_entry(cachep, &slab_caches, list) { + struct array_cache *nc; + struct array_cache *shared; + struct alien_cache **alien; + LIST_HEAD(list); + + n = get_node(cachep, node); + if (!n) + continue; + + spin_lock_irq(&n->list_lock); + + /* Free limit for this kmem_cache_node */ + n->free_limit -= cachep->batchcount; + + /* cpu is dead; no one can alloc from it. */ + nc = per_cpu_ptr(cachep->cpu_cache, cpu); + free_block(cachep, nc->entry, nc->avail, node, &list); + nc->avail = 0; + + if (!cpumask_empty(mask)) { + spin_unlock_irq(&n->list_lock); + goto free_slab; + } + + shared = n->shared; + if (shared) { + free_block(cachep, shared->entry, + shared->avail, node, &list); + n->shared = NULL; + } + + alien = n->alien; + n->alien = NULL; + + spin_unlock_irq(&n->list_lock); + + kfree(shared); + if (alien) { + drain_alien_cache(cachep, alien); + free_alien_cache(alien); + } + +free_slab: + slabs_destroy(cachep, &list); + } + /* + * In the previous loop, all the objects were freed to + * the respective cache's slabs, now we can go ahead and + * shrink each nodelist to its limit. + */ + list_for_each_entry(cachep, &slab_caches, list) { + n = get_node(cachep, node); + if (!n) + continue; + drain_freelist(cachep, n, INT_MAX); + } +} + +static int cpuup_prepare(long cpu) +{ + struct kmem_cache *cachep; + int node = cpu_to_mem(cpu); + int err; + + /* + * We need to do this right in the beginning since + * alloc_arraycache's are going to use this list. + * kmalloc_node allows us to add the slab to the right + * kmem_cache_node and not this cpu's kmem_cache_node + */ + err = init_cache_node_node(node); + if (err < 0) + goto bad; + + /* + * Now we can go ahead with allocating the shared arrays and + * array caches + */ + list_for_each_entry(cachep, &slab_caches, list) { + err = setup_kmem_cache_node(cachep, node, GFP_KERNEL, false); + if (err) + goto bad; + } + + return 0; +bad: + cpuup_canceled(cpu); + return -ENOMEM; +} + +int slab_prepare_cpu(unsigned int cpu) +{ + int err; + + mutex_lock(&slab_mutex); + err = cpuup_prepare(cpu); + mutex_unlock(&slab_mutex); + return err; +} + +/* + * This is called for a failed online attempt and for a successful + * offline. + * + * Even if all the cpus of a node are down, we don't free the + * kmem_cache_node of any cache. This to avoid a race between cpu_down, and + * a kmalloc allocation from another cpu for memory from the node of + * the cpu going down. The kmem_cache_node structure is usually allocated from + * kmem_cache_create() and gets destroyed at kmem_cache_destroy(). + */ +int slab_dead_cpu(unsigned int cpu) +{ + mutex_lock(&slab_mutex); + cpuup_canceled(cpu); + mutex_unlock(&slab_mutex); + return 0; +} +#endif + +static int slab_online_cpu(unsigned int cpu) +{ + start_cpu_timer(cpu); + return 0; +} + +static int slab_offline_cpu(unsigned int cpu) +{ + /* + * Shutdown cache reaper. Note that the slab_mutex is held so + * that if cache_reap() is invoked it cannot do anything + * expensive but will only modify reap_work and reschedule the + * timer. + */ + cancel_delayed_work_sync(&per_cpu(slab_reap_work, cpu)); + /* Now the cache_reaper is guaranteed to be not running. */ + per_cpu(slab_reap_work, cpu).work.func = NULL; + return 0; +} + +#if defined(CONFIG_NUMA) && defined(CONFIG_MEMORY_HOTPLUG) +/* + * Drains freelist for a node on each slab cache, used for memory hot-remove. + * Returns -EBUSY if all objects cannot be drained so that the node is not + * removed. + * + * Must hold slab_mutex. + */ +static int __meminit drain_cache_node_node(int node) +{ + struct kmem_cache *cachep; + int ret = 0; + + list_for_each_entry(cachep, &slab_caches, list) { + struct kmem_cache_node *n; + + n = get_node(cachep, node); + if (!n) + continue; + + drain_freelist(cachep, n, INT_MAX); + + if (!list_empty(&n->slabs_full) || + !list_empty(&n->slabs_partial)) { + ret = -EBUSY; + break; + } + } + return ret; +} + +static int __meminit slab_memory_callback(struct notifier_block *self, + unsigned long action, void *arg) +{ + struct memory_notify *mnb = arg; + int ret = 0; + int nid; + + nid = mnb->status_change_nid; + if (nid < 0) + goto out; + + switch (action) { + case MEM_GOING_ONLINE: + mutex_lock(&slab_mutex); + ret = init_cache_node_node(nid); + mutex_unlock(&slab_mutex); + break; + case MEM_GOING_OFFLINE: + mutex_lock(&slab_mutex); + ret = drain_cache_node_node(nid); + mutex_unlock(&slab_mutex); + break; + case MEM_ONLINE: + case MEM_OFFLINE: + case MEM_CANCEL_ONLINE: + case MEM_CANCEL_OFFLINE: + break; + } +out: + return notifier_from_errno(ret); +} +#endif /* CONFIG_NUMA && CONFIG_MEMORY_HOTPLUG */ + +/* + * swap the static kmem_cache_node with kmalloced memory + */ +static void __init init_list(struct kmem_cache *cachep, struct kmem_cache_node *list, + int nodeid) +{ + struct kmem_cache_node *ptr; + + ptr = kmalloc_node(sizeof(struct kmem_cache_node), GFP_NOWAIT, nodeid); + BUG_ON(!ptr); + + memcpy(ptr, list, sizeof(struct kmem_cache_node)); + /* + * Do not assume that spinlocks can be initialized via memcpy: + */ + spin_lock_init(&ptr->list_lock); + + MAKE_ALL_LISTS(cachep, ptr, nodeid); + cachep->node[nodeid] = ptr; +} + +/* + * For setting up all the kmem_cache_node for cache whose buffer_size is same as + * size of kmem_cache_node. + */ +static void __init set_up_node(struct kmem_cache *cachep, int index) +{ + int node; + + for_each_online_node(node) { + cachep->node[node] = &init_kmem_cache_node[index + node]; + cachep->node[node]->next_reap = jiffies + + REAPTIMEOUT_NODE + + ((unsigned long)cachep) % REAPTIMEOUT_NODE; + } +} + +/* + * Initialisation. Called after the page allocator have been initialised and + * before smp_init(). + */ +void __init kmem_cache_init(void) +{ + int i; + + kmem_cache = &kmem_cache_boot; + + if (!IS_ENABLED(CONFIG_NUMA) || num_possible_nodes() == 1) + use_alien_caches = 0; + + for (i = 0; i < NUM_INIT_LISTS; i++) + kmem_cache_node_init(&init_kmem_cache_node[i]); + + /* + * Fragmentation resistance on low memory - only use bigger + * page orders on machines with more than 32MB of memory if + * not overridden on the command line. + */ + if (!slab_max_order_set && totalram_pages() > (32 << 20) >> PAGE_SHIFT) + slab_max_order = SLAB_MAX_ORDER_HI; + + /* Bootstrap is tricky, because several objects are allocated + * from caches that do not exist yet: + * 1) initialize the kmem_cache cache: it contains the struct + * kmem_cache structures of all caches, except kmem_cache itself: + * kmem_cache is statically allocated. + * Initially an __init data area is used for the head array and the + * kmem_cache_node structures, it's replaced with a kmalloc allocated + * array at the end of the bootstrap. + * 2) Create the first kmalloc cache. + * The struct kmem_cache for the new cache is allocated normally. + * An __init data area is used for the head array. + * 3) Create the remaining kmalloc caches, with minimally sized + * head arrays. + * 4) Replace the __init data head arrays for kmem_cache and the first + * kmalloc cache with kmalloc allocated arrays. + * 5) Replace the __init data for kmem_cache_node for kmem_cache and + * the other cache's with kmalloc allocated memory. + * 6) Resize the head arrays of the kmalloc caches to their final sizes. + */ + + /* 1) create the kmem_cache */ + + /* + * struct kmem_cache size depends on nr_node_ids & nr_cpu_ids + */ + create_boot_cache(kmem_cache, "kmem_cache", + offsetof(struct kmem_cache, node) + + nr_node_ids * sizeof(struct kmem_cache_node *), + SLAB_HWCACHE_ALIGN, 0, 0); + list_add(&kmem_cache->list, &slab_caches); + slab_state = PARTIAL; + + /* + * Initialize the caches that provide memory for the kmem_cache_node + * structures first. Without this, further allocations will bug. + */ + kmalloc_caches[KMALLOC_NORMAL][INDEX_NODE] = create_kmalloc_cache( + kmalloc_info[INDEX_NODE].name[KMALLOC_NORMAL], + kmalloc_info[INDEX_NODE].size, + ARCH_KMALLOC_FLAGS, 0, + kmalloc_info[INDEX_NODE].size); + slab_state = PARTIAL_NODE; + setup_kmalloc_cache_index_table(); + + slab_early_init = 0; + + /* 5) Replace the bootstrap kmem_cache_node */ + { + int nid; + + for_each_online_node(nid) { + init_list(kmem_cache, &init_kmem_cache_node[CACHE_CACHE + nid], nid); + + init_list(kmalloc_caches[KMALLOC_NORMAL][INDEX_NODE], + &init_kmem_cache_node[SIZE_NODE + nid], nid); + } + } + + create_kmalloc_caches(ARCH_KMALLOC_FLAGS); +} + +void __init kmem_cache_init_late(void) +{ + struct kmem_cache *cachep; + + /* 6) resize the head arrays to their final sizes */ + mutex_lock(&slab_mutex); + list_for_each_entry(cachep, &slab_caches, list) + if (enable_cpucache(cachep, GFP_NOWAIT)) + BUG(); + mutex_unlock(&slab_mutex); + + /* Done! */ + slab_state = FULL; + +#ifdef CONFIG_NUMA + /* + * Register a memory hotplug callback that initializes and frees + * node. + */ + hotplug_memory_notifier(slab_memory_callback, SLAB_CALLBACK_PRI); +#endif + + /* + * The reap timers are started later, with a module init call: That part + * of the kernel is not yet operational. + */ +} + +static int __init cpucache_init(void) +{ + int ret; + + /* + * Register the timers that return unneeded pages to the page allocator + */ + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "SLAB online", + slab_online_cpu, slab_offline_cpu); + WARN_ON(ret < 0); + + return 0; +} +__initcall(cpucache_init); + +static noinline void +slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid) +{ +#if DEBUG + struct kmem_cache_node *n; + unsigned long flags; + int node; + static DEFINE_RATELIMIT_STATE(slab_oom_rs, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); + + if ((gfpflags & __GFP_NOWARN) || !__ratelimit(&slab_oom_rs)) + return; + + pr_warn("SLAB: Unable to allocate memory on node %d, gfp=%#x(%pGg)\n", + nodeid, gfpflags, &gfpflags); + pr_warn(" cache: %s, object size: %d, order: %d\n", + cachep->name, cachep->size, cachep->gfporder); + + for_each_kmem_cache_node(cachep, node, n) { + unsigned long total_slabs, free_slabs, free_objs; + + spin_lock_irqsave(&n->list_lock, flags); + total_slabs = n->total_slabs; + free_slabs = n->free_slabs; + free_objs = n->free_objects; + spin_unlock_irqrestore(&n->list_lock, flags); + + pr_warn(" node %d: slabs: %ld/%ld, objs: %ld/%ld\n", + node, total_slabs - free_slabs, total_slabs, + (total_slabs * cachep->num) - free_objs, + total_slabs * cachep->num); + } +#endif +} + +/* + * Interface to system's page allocator. No need to hold the + * kmem_cache_node ->list_lock. + * + * If we requested dmaable memory, we will get it. Even if we + * did not request dmaable memory, we might get it, but that + * would be relatively rare and ignorable. + */ +static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, + int nodeid) +{ + struct page *page; + + flags |= cachep->allocflags; + + page = __alloc_pages_node(nodeid, flags, cachep->gfporder); + if (!page) { + slab_out_of_memory(cachep, flags, nodeid); + return NULL; + } + + account_slab_page(page, cachep->gfporder, cachep); + __SetPageSlab(page); + /* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */ + if (sk_memalloc_socks() && page_is_pfmemalloc(page)) + SetPageSlabPfmemalloc(page); + + return page; +} + +/* + * Interface to system's page release. + */ +static void kmem_freepages(struct kmem_cache *cachep, struct page *page) +{ + int order = cachep->gfporder; + + BUG_ON(!PageSlab(page)); + __ClearPageSlabPfmemalloc(page); + __ClearPageSlab(page); + page_mapcount_reset(page); + page->mapping = NULL; + + if (current->reclaim_state) + current->reclaim_state->reclaimed_slab += 1 << order; + unaccount_slab_page(page, order, cachep); + __free_pages(page, order); +} + +static void kmem_rcu_free(struct rcu_head *head) +{ + struct kmem_cache *cachep; + struct page *page; + + page = container_of(head, struct page, rcu_head); + cachep = page->slab_cache; + + kmem_freepages(cachep, page); +} + +#if DEBUG +static bool is_debug_pagealloc_cache(struct kmem_cache *cachep) +{ + if (debug_pagealloc_enabled_static() && OFF_SLAB(cachep) && + (cachep->size % PAGE_SIZE) == 0) + return true; + + return false; +} + +#ifdef CONFIG_DEBUG_PAGEALLOC +static void slab_kernel_map(struct kmem_cache *cachep, void *objp, int map) +{ + if (!is_debug_pagealloc_cache(cachep)) + return; + + kernel_map_pages(virt_to_page(objp), cachep->size / PAGE_SIZE, map); +} + +#else +static inline void slab_kernel_map(struct kmem_cache *cachep, void *objp, + int map) {} + +#endif + +static void poison_obj(struct kmem_cache *cachep, void *addr, unsigned char val) +{ + int size = cachep->object_size; + addr = &((char *)addr)[obj_offset(cachep)]; + + memset(addr, val, size); + *(unsigned char *)(addr + size - 1) = POISON_END; +} + +static void dump_line(char *data, int offset, int limit) +{ + int i; + unsigned char error = 0; + int bad_count = 0; + + pr_err("%03x: ", offset); + for (i = 0; i < limit; i++) { + if (data[offset + i] != POISON_FREE) { + error = data[offset + i]; + bad_count++; + } + } + print_hex_dump(KERN_CONT, "", 0, 16, 1, + &data[offset], limit, 1); + + if (bad_count == 1) { + error ^= POISON_FREE; + if (!(error & (error - 1))) { + pr_err("Single bit error detected. Probably bad RAM.\n"); +#ifdef CONFIG_X86 + pr_err("Run memtest86+ or a similar memory test tool.\n"); +#else + pr_err("Run a memory test tool.\n"); +#endif + } + } +} +#endif + +#if DEBUG + +static void print_objinfo(struct kmem_cache *cachep, void *objp, int lines) +{ + int i, size; + char *realobj; + + if (cachep->flags & SLAB_RED_ZONE) { + pr_err("Redzone: 0x%llx/0x%llx\n", + *dbg_redzone1(cachep, objp), + *dbg_redzone2(cachep, objp)); + } + + if (cachep->flags & SLAB_STORE_USER) + pr_err("Last user: (%pSR)\n", *dbg_userword(cachep, objp)); + realobj = (char *)objp + obj_offset(cachep); + size = cachep->object_size; + for (i = 0; i < size && lines; i += 16, lines--) { + int limit; + limit = 16; + if (i + limit > size) + limit = size - i; + dump_line(realobj, i, limit); + } +} + +static void check_poison_obj(struct kmem_cache *cachep, void *objp) +{ + char *realobj; + int size, i; + int lines = 0; + + if (is_debug_pagealloc_cache(cachep)) + return; + + realobj = (char *)objp + obj_offset(cachep); + size = cachep->object_size; + + for (i = 0; i < size; i++) { + char exp = POISON_FREE; + if (i == size - 1) + exp = POISON_END; + if (realobj[i] != exp) { + int limit; + /* Mismatch ! */ + /* Print header */ + if (lines == 0) { + pr_err("Slab corruption (%s): %s start=%px, len=%d\n", + print_tainted(), cachep->name, + realobj, size); + print_objinfo(cachep, objp, 0); + } + /* Hexdump the affected line */ + i = (i / 16) * 16; + limit = 16; + if (i + limit > size) + limit = size - i; + dump_line(realobj, i, limit); + i += 16; + lines++; + /* Limit to 5 lines */ + if (lines > 5) + break; + } + } + if (lines != 0) { + /* Print some data about the neighboring objects, if they + * exist: + */ + struct page *page = virt_to_head_page(objp); + unsigned int objnr; + + objnr = obj_to_index(cachep, page, objp); + if (objnr) { + objp = index_to_obj(cachep, page, objnr - 1); + realobj = (char *)objp + obj_offset(cachep); + pr_err("Prev obj: start=%px, len=%d\n", realobj, size); + print_objinfo(cachep, objp, 2); + } + if (objnr + 1 < cachep->num) { + objp = index_to_obj(cachep, page, objnr + 1); + realobj = (char *)objp + obj_offset(cachep); + pr_err("Next obj: start=%px, len=%d\n", realobj, size); + print_objinfo(cachep, objp, 2); + } + } +} +#endif + +#if DEBUG +static void slab_destroy_debugcheck(struct kmem_cache *cachep, + struct page *page) +{ + int i; + + if (OBJFREELIST_SLAB(cachep) && cachep->flags & SLAB_POISON) { + poison_obj(cachep, page->freelist - obj_offset(cachep), + POISON_FREE); + } + + for (i = 0; i < cachep->num; i++) { + void *objp = index_to_obj(cachep, page, i); + + if (cachep->flags & SLAB_POISON) { + check_poison_obj(cachep, objp); + slab_kernel_map(cachep, objp, 1); + } + if (cachep->flags & SLAB_RED_ZONE) { + if (*dbg_redzone1(cachep, objp) != RED_INACTIVE) + slab_error(cachep, "start of a freed object was overwritten"); + if (*dbg_redzone2(cachep, objp) != RED_INACTIVE) + slab_error(cachep, "end of a freed object was overwritten"); + } + } +} +#else +static void slab_destroy_debugcheck(struct kmem_cache *cachep, + struct page *page) +{ +} +#endif + +/** + * slab_destroy - destroy and release all objects in a slab + * @cachep: cache pointer being destroyed + * @page: page pointer being destroyed + * + * Destroy all the objs in a slab page, and release the mem back to the system. + * Before calling the slab page must have been unlinked from the cache. The + * kmem_cache_node ->list_lock is not held/needed. + */ +static void slab_destroy(struct kmem_cache *cachep, struct page *page) +{ + void *freelist; + + freelist = page->freelist; + slab_destroy_debugcheck(cachep, page); + if (unlikely(cachep->flags & SLAB_TYPESAFE_BY_RCU)) + call_rcu(&page->rcu_head, kmem_rcu_free); + else + kmem_freepages(cachep, page); + + /* + * From now on, we don't use freelist + * although actual page can be freed in rcu context + */ + if (OFF_SLAB(cachep)) + kmem_cache_free(cachep->freelist_cache, freelist); +} + +/* + * Update the size of the caches before calling slabs_destroy as it may + * recursively call kfree. + */ +static void slabs_destroy(struct kmem_cache *cachep, struct list_head *list) +{ + struct page *page, *n; + + list_for_each_entry_safe(page, n, list, slab_list) { + list_del(&page->slab_list); + slab_destroy(cachep, page); + } +} + +/** + * calculate_slab_order - calculate size (page order) of slabs + * @cachep: pointer to the cache that is being created + * @size: size of objects to be created in this cache. + * @flags: slab allocation flags + * + * Also calculates the number of objects per slab. + * + * This could be made much more intelligent. For now, try to avoid using + * high order pages for slabs. When the gfp() functions are more friendly + * towards high-order requests, this should be changed. + * + * Return: number of left-over bytes in a slab + */ +static size_t calculate_slab_order(struct kmem_cache *cachep, + size_t size, slab_flags_t flags) +{ + size_t left_over = 0; + int gfporder; + + for (gfporder = 0; gfporder <= KMALLOC_MAX_ORDER; gfporder++) { + unsigned int num; + size_t remainder; + + num = cache_estimate(gfporder, size, flags, &remainder); + if (!num) + continue; + + /* Can't handle number of objects more than SLAB_OBJ_MAX_NUM */ + if (num > SLAB_OBJ_MAX_NUM) + break; + + if (flags & CFLGS_OFF_SLAB) { + struct kmem_cache *freelist_cache; + size_t freelist_size; + + freelist_size = num * sizeof(freelist_idx_t); + freelist_cache = kmalloc_slab(freelist_size, 0u); + if (!freelist_cache) + continue; + + /* + * Needed to avoid possible looping condition + * in cache_grow_begin() + */ + if (OFF_SLAB(freelist_cache)) + continue; + + /* check if off slab has enough benefit */ + if (freelist_cache->size > cachep->size / 2) + continue; + } + + /* Found something acceptable - save it away */ + cachep->num = num; + cachep->gfporder = gfporder; + left_over = remainder; + + /* + * A VFS-reclaimable slab tends to have most allocations + * as GFP_NOFS and we really don't want to have to be allocating + * higher-order pages when we are unable to shrink dcache. + */ + if (flags & SLAB_RECLAIM_ACCOUNT) + break; + + /* + * Large number of objects is good, but very large slabs are + * currently bad for the gfp()s. + */ + if (gfporder >= slab_max_order) + break; + + /* + * Acceptable internal fragmentation? + */ + if (left_over * 8 <= (PAGE_SIZE << gfporder)) + break; + } + return left_over; +} + +static struct array_cache __percpu *alloc_kmem_cache_cpus( + struct kmem_cache *cachep, int entries, int batchcount) +{ + int cpu; + size_t size; + struct array_cache __percpu *cpu_cache; + + size = sizeof(void *) * entries + sizeof(struct array_cache); + cpu_cache = __alloc_percpu(size, sizeof(void *)); + + if (!cpu_cache) + return NULL; + + for_each_possible_cpu(cpu) { + init_arraycache(per_cpu_ptr(cpu_cache, cpu), + entries, batchcount); + } + + return cpu_cache; +} + +static int __ref setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp) +{ + if (slab_state >= FULL) + return enable_cpucache(cachep, gfp); + + cachep->cpu_cache = alloc_kmem_cache_cpus(cachep, 1, 1); + if (!cachep->cpu_cache) + return 1; + + if (slab_state == DOWN) { + /* Creation of first cache (kmem_cache). */ + set_up_node(kmem_cache, CACHE_CACHE); + } else if (slab_state == PARTIAL) { + /* For kmem_cache_node */ + set_up_node(cachep, SIZE_NODE); + } else { + int node; + + for_each_online_node(node) { + cachep->node[node] = kmalloc_node( + sizeof(struct kmem_cache_node), gfp, node); + BUG_ON(!cachep->node[node]); + kmem_cache_node_init(cachep->node[node]); + } + } + + cachep->node[numa_mem_id()]->next_reap = + jiffies + REAPTIMEOUT_NODE + + ((unsigned long)cachep) % REAPTIMEOUT_NODE; + + cpu_cache_get(cachep)->avail = 0; + cpu_cache_get(cachep)->limit = BOOT_CPUCACHE_ENTRIES; + cpu_cache_get(cachep)->batchcount = 1; + cpu_cache_get(cachep)->touched = 0; + cachep->batchcount = 1; + cachep->limit = BOOT_CPUCACHE_ENTRIES; + return 0; +} + +slab_flags_t kmem_cache_flags(unsigned int object_size, + slab_flags_t flags, const char *name) +{ + return flags; +} + +struct kmem_cache * +__kmem_cache_alias(const char *name, unsigned int size, unsigned int align, + slab_flags_t flags, void (*ctor)(void *)) +{ + struct kmem_cache *cachep; + + cachep = find_mergeable(size, align, flags, name, ctor); + if (cachep) { + cachep->refcount++; + + /* + * Adjust the object sizes so that we clear + * the complete object on kzalloc. + */ + cachep->object_size = max_t(int, cachep->object_size, size); + } + return cachep; +} + +static bool set_objfreelist_slab_cache(struct kmem_cache *cachep, + size_t size, slab_flags_t flags) +{ + size_t left; + + cachep->num = 0; + + /* + * If slab auto-initialization on free is enabled, store the freelist + * off-slab, so that its contents don't end up in one of the allocated + * objects. + */ + if (unlikely(slab_want_init_on_free(cachep))) + return false; + + if (cachep->ctor || flags & SLAB_TYPESAFE_BY_RCU) + return false; + + left = calculate_slab_order(cachep, size, + flags | CFLGS_OBJFREELIST_SLAB); + if (!cachep->num) + return false; + + if (cachep->num * sizeof(freelist_idx_t) > cachep->object_size) + return false; + + cachep->colour = left / cachep->colour_off; + + return true; +} + +static bool set_off_slab_cache(struct kmem_cache *cachep, + size_t size, slab_flags_t flags) +{ + size_t left; + + cachep->num = 0; + + /* + * Always use on-slab management when SLAB_NOLEAKTRACE + * to avoid recursive calls into kmemleak. + */ + if (flags & SLAB_NOLEAKTRACE) + return false; + + /* + * Size is large, assume best to place the slab management obj + * off-slab (should allow better packing of objs). + */ + left = calculate_slab_order(cachep, size, flags | CFLGS_OFF_SLAB); + if (!cachep->num) + return false; + + /* + * If the slab has been placed off-slab, and we have enough space then + * move it on-slab. This is at the expense of any extra colouring. + */ + if (left >= cachep->num * sizeof(freelist_idx_t)) + return false; + + cachep->colour = left / cachep->colour_off; + + return true; +} + +static bool set_on_slab_cache(struct kmem_cache *cachep, + size_t size, slab_flags_t flags) +{ + size_t left; + + cachep->num = 0; + + left = calculate_slab_order(cachep, size, flags); + if (!cachep->num) + return false; + + cachep->colour = left / cachep->colour_off; + + return true; +} + +/** + * __kmem_cache_create - Create a cache. + * @cachep: cache management descriptor + * @flags: SLAB flags + * + * Returns a ptr to the cache on success, NULL on failure. + * Cannot be called within a int, but can be interrupted. + * The @ctor is run when new pages are allocated by the cache. + * + * The flags are + * + * %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5) + * to catch references to uninitialised memory. + * + * %SLAB_RED_ZONE - Insert `Red' zones around the allocated memory to check + * for buffer overruns. + * + * %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware + * cacheline. This can be beneficial if you're counting cycles as closely + * as davem. + * + * Return: a pointer to the created cache or %NULL in case of error + */ +int __kmem_cache_create(struct kmem_cache *cachep, slab_flags_t flags) +{ + size_t ralign = BYTES_PER_WORD; + gfp_t gfp; + int err; + unsigned int size = cachep->size; + +#if DEBUG +#if FORCED_DEBUG + /* + * Enable redzoning and last user accounting, except for caches with + * large objects, if the increased size would increase the object size + * above the next power of two: caches with object sizes just above a + * power of two have a significant amount of internal fragmentation. + */ + if (size < 4096 || fls(size - 1) == fls(size-1 + REDZONE_ALIGN + + 2 * sizeof(unsigned long long))) + flags |= SLAB_RED_ZONE | SLAB_STORE_USER; + if (!(flags & SLAB_TYPESAFE_BY_RCU)) + flags |= SLAB_POISON; +#endif +#endif + + /* + * Check that size is in terms of words. This is needed to avoid + * unaligned accesses for some archs when redzoning is used, and makes + * sure any on-slab bufctl's are also correctly aligned. + */ + size = ALIGN(size, BYTES_PER_WORD); + + if (flags & SLAB_RED_ZONE) { + ralign = REDZONE_ALIGN; + /* If redzoning, ensure that the second redzone is suitably + * aligned, by adjusting the object size accordingly. */ + size = ALIGN(size, REDZONE_ALIGN); + } + + /* 3) caller mandated alignment */ + if (ralign < cachep->align) { + ralign = cachep->align; + } + /* disable debug if necessary */ + if (ralign > __alignof__(unsigned long long)) + flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER); + /* + * 4) Store it. + */ + cachep->align = ralign; + cachep->colour_off = cache_line_size(); + /* Offset must be a multiple of the alignment. */ + if (cachep->colour_off < cachep->align) + cachep->colour_off = cachep->align; + + if (slab_is_available()) + gfp = GFP_KERNEL; + else + gfp = GFP_NOWAIT; + +#if DEBUG + + /* + * Both debugging options require word-alignment which is calculated + * into align above. + */ + if (flags & SLAB_RED_ZONE) { + /* add space for red zone words */ + cachep->obj_offset += sizeof(unsigned long long); + size += 2 * sizeof(unsigned long long); + } + if (flags & SLAB_STORE_USER) { + /* user store requires one word storage behind the end of + * the real object. But if the second red zone needs to be + * aligned to 64 bits, we must allow that much space. + */ + if (flags & SLAB_RED_ZONE) + size += REDZONE_ALIGN; + else + size += BYTES_PER_WORD; + } +#endif + + kasan_cache_create(cachep, &size, &flags); + + size = ALIGN(size, cachep->align); + /* + * We should restrict the number of objects in a slab to implement + * byte sized index. Refer comment on SLAB_OBJ_MIN_SIZE definition. + */ + if (FREELIST_BYTE_INDEX && size < SLAB_OBJ_MIN_SIZE) + size = ALIGN(SLAB_OBJ_MIN_SIZE, cachep->align); + +#if DEBUG + /* + * To activate debug pagealloc, off-slab management is necessary + * requirement. In early phase of initialization, small sized slab + * doesn't get initialized so it would not be possible. So, we need + * to check size >= 256. It guarantees that all necessary small + * sized slab is initialized in current slab initialization sequence. + */ + if (debug_pagealloc_enabled_static() && (flags & SLAB_POISON) && + size >= 256 && cachep->object_size > cache_line_size()) { + if (size < PAGE_SIZE || size % PAGE_SIZE == 0) { + size_t tmp_size = ALIGN(size, PAGE_SIZE); + + if (set_off_slab_cache(cachep, tmp_size, flags)) { + flags |= CFLGS_OFF_SLAB; + cachep->obj_offset += tmp_size - size; + size = tmp_size; + goto done; + } + } + } +#endif + + if (set_objfreelist_slab_cache(cachep, size, flags)) { + flags |= CFLGS_OBJFREELIST_SLAB; + goto done; + } + + if (set_off_slab_cache(cachep, size, flags)) { + flags |= CFLGS_OFF_SLAB; + goto done; + } + + if (set_on_slab_cache(cachep, size, flags)) + goto done; + + return -E2BIG; + +done: + cachep->freelist_size = cachep->num * sizeof(freelist_idx_t); + cachep->flags = flags; + cachep->allocflags = __GFP_COMP; + if (flags & SLAB_CACHE_DMA) + cachep->allocflags |= GFP_DMA; + if (flags & SLAB_CACHE_DMA32) + cachep->allocflags |= GFP_DMA32; + if (flags & SLAB_RECLAIM_ACCOUNT) + cachep->allocflags |= __GFP_RECLAIMABLE; + cachep->size = size; + cachep->reciprocal_buffer_size = reciprocal_value(size); + +#if DEBUG + /* + * If we're going to use the generic kernel_map_pages() + * poisoning, then it's going to smash the contents of + * the redzone and userword anyhow, so switch them off. + */ + if (IS_ENABLED(CONFIG_PAGE_POISONING) && + (cachep->flags & SLAB_POISON) && + is_debug_pagealloc_cache(cachep)) + cachep->flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER); +#endif + + if (OFF_SLAB(cachep)) { + cachep->freelist_cache = + kmalloc_slab(cachep->freelist_size, 0u); + } + + err = setup_cpu_cache(cachep, gfp); + if (err) { + __kmem_cache_release(cachep); + return err; + } + + return 0; +} + +#if DEBUG +static void check_irq_off(void) +{ + BUG_ON(!irqs_disabled()); +} + +static void check_irq_on(void) +{ + BUG_ON(irqs_disabled()); +} + +static void check_mutex_acquired(void) +{ + BUG_ON(!mutex_is_locked(&slab_mutex)); +} + +static void check_spinlock_acquired(struct kmem_cache *cachep) +{ +#ifdef CONFIG_SMP + check_irq_off(); + assert_spin_locked(&get_node(cachep, numa_mem_id())->list_lock); +#endif +} + +static void check_spinlock_acquired_node(struct kmem_cache *cachep, int node) +{ +#ifdef CONFIG_SMP + check_irq_off(); + assert_spin_locked(&get_node(cachep, node)->list_lock); +#endif +} + +#else +#define check_irq_off() do { } while(0) +#define check_irq_on() do { } while(0) +#define check_mutex_acquired() do { } while(0) +#define check_spinlock_acquired(x) do { } while(0) +#define check_spinlock_acquired_node(x, y) do { } while(0) +#endif + +static void drain_array_locked(struct kmem_cache *cachep, struct array_cache *ac, + int node, bool free_all, struct list_head *list) +{ + int tofree; + + if (!ac || !ac->avail) + return; + + tofree = free_all ? ac->avail : (ac->limit + 4) / 5; + if (tofree > ac->avail) + tofree = (ac->avail + 1) / 2; + + free_block(cachep, ac->entry, tofree, node, list); + ac->avail -= tofree; + memmove(ac->entry, &(ac->entry[tofree]), sizeof(void *) * ac->avail); +} + +static void do_drain(void *arg) +{ + struct kmem_cache *cachep = arg; + struct array_cache *ac; + int node = numa_mem_id(); + struct kmem_cache_node *n; + LIST_HEAD(list); + + check_irq_off(); + ac = cpu_cache_get(cachep); + n = get_node(cachep, node); + spin_lock(&n->list_lock); + free_block(cachep, ac->entry, ac->avail, node, &list); + spin_unlock(&n->list_lock); + ac->avail = 0; + slabs_destroy(cachep, &list); +} + +static void drain_cpu_caches(struct kmem_cache *cachep) +{ + struct kmem_cache_node *n; + int node; + LIST_HEAD(list); + + on_each_cpu(do_drain, cachep, 1); + check_irq_on(); + for_each_kmem_cache_node(cachep, node, n) + if (n->alien) + drain_alien_cache(cachep, n->alien); + + for_each_kmem_cache_node(cachep, node, n) { + spin_lock_irq(&n->list_lock); + drain_array_locked(cachep, n->shared, node, true, &list); + spin_unlock_irq(&n->list_lock); + + slabs_destroy(cachep, &list); + } +} + +/* + * Remove slabs from the list of free slabs. + * Specify the number of slabs to drain in tofree. + * + * Returns the actual number of slabs released. + */ +static int drain_freelist(struct kmem_cache *cache, + struct kmem_cache_node *n, int tofree) +{ + struct list_head *p; + int nr_freed; + struct page *page; + + nr_freed = 0; + while (nr_freed < tofree && !list_empty(&n->slabs_free)) { + + spin_lock_irq(&n->list_lock); + p = n->slabs_free.prev; + if (p == &n->slabs_free) { + spin_unlock_irq(&n->list_lock); + goto out; + } + + page = list_entry(p, struct page, slab_list); + list_del(&page->slab_list); + n->free_slabs--; + n->total_slabs--; + /* + * Safe to drop the lock. The slab is no longer linked + * to the cache. + */ + n->free_objects -= cache->num; + spin_unlock_irq(&n->list_lock); + slab_destroy(cache, page); + nr_freed++; + } +out: + return nr_freed; +} + +bool __kmem_cache_empty(struct kmem_cache *s) +{ + int node; + struct kmem_cache_node *n; + + for_each_kmem_cache_node(s, node, n) + if (!list_empty(&n->slabs_full) || + !list_empty(&n->slabs_partial)) + return false; + return true; +} + +int __kmem_cache_shrink(struct kmem_cache *cachep) +{ + int ret = 0; + int node; + struct kmem_cache_node *n; + + drain_cpu_caches(cachep); + + check_irq_on(); + for_each_kmem_cache_node(cachep, node, n) { + drain_freelist(cachep, n, INT_MAX); + + ret += !list_empty(&n->slabs_full) || + !list_empty(&n->slabs_partial); + } + return (ret ? 1 : 0); +} + +int __kmem_cache_shutdown(struct kmem_cache *cachep) +{ + return __kmem_cache_shrink(cachep); +} + +void __kmem_cache_release(struct kmem_cache *cachep) +{ + int i; + struct kmem_cache_node *n; + + cache_random_seq_destroy(cachep); + + free_percpu(cachep->cpu_cache); + + /* NUMA: free the node structures */ + for_each_kmem_cache_node(cachep, i, n) { + kfree(n->shared); + free_alien_cache(n->alien); + kfree(n); + cachep->node[i] = NULL; + } +} + +/* + * Get the memory for a slab management obj. + * + * For a slab cache when the slab descriptor is off-slab, the + * slab descriptor can't come from the same cache which is being created, + * Because if it is the case, that means we defer the creation of + * the kmalloc_{dma,}_cache of size sizeof(slab descriptor) to this point. + * And we eventually call down to __kmem_cache_create(), which + * in turn looks up in the kmalloc_{dma,}_caches for the disired-size one. + * This is a "chicken-and-egg" problem. + * + * So the off-slab slab descriptor shall come from the kmalloc_{dma,}_caches, + * which are all initialized during kmem_cache_init(). + */ +static void *alloc_slabmgmt(struct kmem_cache *cachep, + struct page *page, int colour_off, + gfp_t local_flags, int nodeid) +{ + void *freelist; + void *addr = page_address(page); + + page->s_mem = addr + colour_off; + page->active = 0; + + if (OBJFREELIST_SLAB(cachep)) + freelist = NULL; + else if (OFF_SLAB(cachep)) { + /* Slab management obj is off-slab. */ + freelist = kmem_cache_alloc_node(cachep->freelist_cache, + local_flags, nodeid); + } else { + /* We will use last bytes at the slab for freelist */ + freelist = addr + (PAGE_SIZE << cachep->gfporder) - + cachep->freelist_size; + } + + return freelist; +} + +static inline freelist_idx_t get_free_obj(struct page *page, unsigned int idx) +{ + return ((freelist_idx_t *)page->freelist)[idx]; +} + +static inline void set_free_obj(struct page *page, + unsigned int idx, freelist_idx_t val) +{ + ((freelist_idx_t *)(page->freelist))[idx] = val; +} + +static void cache_init_objs_debug(struct kmem_cache *cachep, struct page *page) +{ +#if DEBUG + int i; + + for (i = 0; i < cachep->num; i++) { + void *objp = index_to_obj(cachep, page, i); + + if (cachep->flags & SLAB_STORE_USER) + *dbg_userword(cachep, objp) = NULL; + + if (cachep->flags & SLAB_RED_ZONE) { + *dbg_redzone1(cachep, objp) = RED_INACTIVE; + *dbg_redzone2(cachep, objp) = RED_INACTIVE; + } + /* + * Constructors are not allowed to allocate memory from the same + * cache which they are a constructor for. Otherwise, deadlock. + * They must also be threaded. + */ + if (cachep->ctor && !(cachep->flags & SLAB_POISON)) { + kasan_unpoison_object_data(cachep, + objp + obj_offset(cachep)); + cachep->ctor(objp + obj_offset(cachep)); + kasan_poison_object_data( + cachep, objp + obj_offset(cachep)); + } + + if (cachep->flags & SLAB_RED_ZONE) { + if (*dbg_redzone2(cachep, objp) != RED_INACTIVE) + slab_error(cachep, "constructor overwrote the end of an object"); + if (*dbg_redzone1(cachep, objp) != RED_INACTIVE) + slab_error(cachep, "constructor overwrote the start of an object"); + } + /* need to poison the objs? */ + if (cachep->flags & SLAB_POISON) { + poison_obj(cachep, objp, POISON_FREE); + slab_kernel_map(cachep, objp, 0); + } + } +#endif +} + +#ifdef CONFIG_SLAB_FREELIST_RANDOM +/* Hold information during a freelist initialization */ +union freelist_init_state { + struct { + unsigned int pos; + unsigned int *list; + unsigned int count; + }; + struct rnd_state rnd_state; +}; + +/* + * Initialize the state based on the randomization methode available. + * return true if the pre-computed list is available, false otherwize. + */ +static bool freelist_state_initialize(union freelist_init_state *state, + struct kmem_cache *cachep, + unsigned int count) +{ + bool ret; + unsigned int rand; + + /* Use best entropy available to define a random shift */ + rand = get_random_int(); + + /* Use a random state if the pre-computed list is not available */ + if (!cachep->random_seq) { + prandom_seed_state(&state->rnd_state, rand); + ret = false; + } else { + state->list = cachep->random_seq; + state->count = count; + state->pos = rand % count; + ret = true; + } + return ret; +} + +/* Get the next entry on the list and randomize it using a random shift */ +static freelist_idx_t next_random_slot(union freelist_init_state *state) +{ + if (state->pos >= state->count) + state->pos = 0; + return state->list[state->pos++]; +} + +/* Swap two freelist entries */ +static void swap_free_obj(struct page *page, unsigned int a, unsigned int b) +{ + swap(((freelist_idx_t *)page->freelist)[a], + ((freelist_idx_t *)page->freelist)[b]); +} + +/* + * Shuffle the freelist initialization state based on pre-computed lists. + * return true if the list was successfully shuffled, false otherwise. + */ +static bool shuffle_freelist(struct kmem_cache *cachep, struct page *page) +{ + unsigned int objfreelist = 0, i, rand, count = cachep->num; + union freelist_init_state state; + bool precomputed; + + if (count < 2) + return false; + + precomputed = freelist_state_initialize(&state, cachep, count); + + /* Take a random entry as the objfreelist */ + if (OBJFREELIST_SLAB(cachep)) { + if (!precomputed) + objfreelist = count - 1; + else + objfreelist = next_random_slot(&state); + page->freelist = index_to_obj(cachep, page, objfreelist) + + obj_offset(cachep); + count--; + } + + /* + * On early boot, generate the list dynamically. + * Later use a pre-computed list for speed. + */ + if (!precomputed) { + for (i = 0; i < count; i++) + set_free_obj(page, i, i); + + /* Fisher-Yates shuffle */ + for (i = count - 1; i > 0; i--) { + rand = prandom_u32_state(&state.rnd_state); + rand %= (i + 1); + swap_free_obj(page, i, rand); + } + } else { + for (i = 0; i < count; i++) + set_free_obj(page, i, next_random_slot(&state)); + } + + if (OBJFREELIST_SLAB(cachep)) + set_free_obj(page, cachep->num - 1, objfreelist); + + return true; +} +#else +static inline bool shuffle_freelist(struct kmem_cache *cachep, + struct page *page) +{ + return false; +} +#endif /* CONFIG_SLAB_FREELIST_RANDOM */ + +static void cache_init_objs(struct kmem_cache *cachep, + struct page *page) +{ + int i; + void *objp; + bool shuffled; + + cache_init_objs_debug(cachep, page); + + /* Try to randomize the freelist if enabled */ + shuffled = shuffle_freelist(cachep, page); + + if (!shuffled && OBJFREELIST_SLAB(cachep)) { + page->freelist = index_to_obj(cachep, page, cachep->num - 1) + + obj_offset(cachep); + } + + for (i = 0; i < cachep->num; i++) { + objp = index_to_obj(cachep, page, i); + objp = kasan_init_slab_obj(cachep, objp); + + /* constructor could break poison info */ + if (DEBUG == 0 && cachep->ctor) { + kasan_unpoison_object_data(cachep, objp); + cachep->ctor(objp); + kasan_poison_object_data(cachep, objp); + } + + if (!shuffled) + set_free_obj(page, i, i); + } +} + +static void *slab_get_obj(struct kmem_cache *cachep, struct page *page) +{ + void *objp; + + objp = index_to_obj(cachep, page, get_free_obj(page, page->active)); + page->active++; + + return objp; +} + +static void slab_put_obj(struct kmem_cache *cachep, + struct page *page, void *objp) +{ + unsigned int objnr = obj_to_index(cachep, page, objp); +#if DEBUG + unsigned int i; + + /* Verify double free bug */ + for (i = page->active; i < cachep->num; i++) { + if (get_free_obj(page, i) == objnr) { + pr_err("slab: double free detected in cache '%s', objp %px\n", + cachep->name, objp); + BUG(); + } + } +#endif + page->active--; + if (!page->freelist) + page->freelist = objp + obj_offset(cachep); + + set_free_obj(page, page->active, objnr); +} + +/* + * Map pages beginning at addr to the given cache and slab. This is required + * for the slab allocator to be able to lookup the cache and slab of a + * virtual address for kfree, ksize, and slab debugging. + */ +static void slab_map_pages(struct kmem_cache *cache, struct page *page, + void *freelist) +{ + page->slab_cache = cache; + page->freelist = freelist; +} + +/* + * Grow (by 1) the number of slabs within a cache. This is called by + * kmem_cache_alloc() when there are no active objs left in a cache. + */ +static struct page *cache_grow_begin(struct kmem_cache *cachep, + gfp_t flags, int nodeid) +{ + void *freelist; + size_t offset; + gfp_t local_flags; + int page_node; + struct kmem_cache_node *n; + struct page *page; + + /* + * Be lazy and only check for valid flags here, keeping it out of the + * critical path in kmem_cache_alloc(). + */ + if (unlikely(flags & GFP_SLAB_BUG_MASK)) + flags = kmalloc_fix_flags(flags); + + WARN_ON_ONCE(cachep->ctor && (flags & __GFP_ZERO)); + local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK); + + check_irq_off(); + if (gfpflags_allow_blocking(local_flags)) + local_irq_enable(); + + /* + * Get mem for the objs. Attempt to allocate a physical page from + * 'nodeid'. + */ + page = kmem_getpages(cachep, local_flags, nodeid); + if (!page) + goto failed; + + page_node = page_to_nid(page); + n = get_node(cachep, page_node); + + /* Get colour for the slab, and cal the next value. */ + n->colour_next++; + if (n->colour_next >= cachep->colour) + n->colour_next = 0; + + offset = n->colour_next; + if (offset >= cachep->colour) + offset = 0; + + offset *= cachep->colour_off; + + /* + * Call kasan_poison_slab() before calling alloc_slabmgmt(), so + * page_address() in the latter returns a non-tagged pointer, + * as it should be for slab pages. + */ + kasan_poison_slab(page); + + /* Get slab management. */ + freelist = alloc_slabmgmt(cachep, page, offset, + local_flags & ~GFP_CONSTRAINT_MASK, page_node); + if (OFF_SLAB(cachep) && !freelist) + goto opps1; + + slab_map_pages(cachep, page, freelist); + + cache_init_objs(cachep, page); + + if (gfpflags_allow_blocking(local_flags)) + local_irq_disable(); + + return page; + +opps1: + kmem_freepages(cachep, page); +failed: + if (gfpflags_allow_blocking(local_flags)) + local_irq_disable(); + return NULL; +} + +static void cache_grow_end(struct kmem_cache *cachep, struct page *page) +{ + struct kmem_cache_node *n; + void *list = NULL; + + check_irq_off(); + + if (!page) + return; + + INIT_LIST_HEAD(&page->slab_list); + n = get_node(cachep, page_to_nid(page)); + + spin_lock(&n->list_lock); + n->total_slabs++; + if (!page->active) { + list_add_tail(&page->slab_list, &n->slabs_free); + n->free_slabs++; + } else + fixup_slab_list(cachep, n, page, &list); + + STATS_INC_GROWN(cachep); + n->free_objects += cachep->num - page->active; + spin_unlock(&n->list_lock); + + fixup_objfreelist_debug(cachep, &list); +} + +#if DEBUG + +/* + * Perform extra freeing checks: + * - detect bad pointers. + * - POISON/RED_ZONE checking + */ +static void kfree_debugcheck(const void *objp) +{ + if (!virt_addr_valid(objp)) { + pr_err("kfree_debugcheck: out of range ptr %lxh\n", + (unsigned long)objp); + BUG(); + } +} + +static inline void verify_redzone_free(struct kmem_cache *cache, void *obj) +{ + unsigned long long redzone1, redzone2; + + redzone1 = *dbg_redzone1(cache, obj); + redzone2 = *dbg_redzone2(cache, obj); + + /* + * Redzone is ok. + */ + if (redzone1 == RED_ACTIVE && redzone2 == RED_ACTIVE) + return; + + if (redzone1 == RED_INACTIVE && redzone2 == RED_INACTIVE) + slab_error(cache, "double free detected"); + else + slab_error(cache, "memory outside object was overwritten"); + + pr_err("%px: redzone 1:0x%llx, redzone 2:0x%llx\n", + obj, redzone1, redzone2); +} + +static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp, + unsigned long caller) +{ + unsigned int objnr; + struct page *page; + + BUG_ON(virt_to_cache(objp) != cachep); + + objp -= obj_offset(cachep); + kfree_debugcheck(objp); + page = virt_to_head_page(objp); + + if (cachep->flags & SLAB_RED_ZONE) { + verify_redzone_free(cachep, objp); + *dbg_redzone1(cachep, objp) = RED_INACTIVE; + *dbg_redzone2(cachep, objp) = RED_INACTIVE; + } + if (cachep->flags & SLAB_STORE_USER) + *dbg_userword(cachep, objp) = (void *)caller; + + objnr = obj_to_index(cachep, page, objp); + + BUG_ON(objnr >= cachep->num); + BUG_ON(objp != index_to_obj(cachep, page, objnr)); + + if (cachep->flags & SLAB_POISON) { + poison_obj(cachep, objp, POISON_FREE); + slab_kernel_map(cachep, objp, 0); + } + return objp; +} + +#else +#define kfree_debugcheck(x) do { } while(0) +#define cache_free_debugcheck(x,objp,z) (objp) +#endif + +static inline void fixup_objfreelist_debug(struct kmem_cache *cachep, + void **list) +{ +#if DEBUG + void *next = *list; + void *objp; + + while (next) { + objp = next - obj_offset(cachep); + next = *(void **)next; + poison_obj(cachep, objp, POISON_FREE); + } +#endif +} + +static inline void fixup_slab_list(struct kmem_cache *cachep, + struct kmem_cache_node *n, struct page *page, + void **list) +{ + /* move slabp to correct slabp list: */ + list_del(&page->slab_list); + if (page->active == cachep->num) { + list_add(&page->slab_list, &n->slabs_full); + if (OBJFREELIST_SLAB(cachep)) { +#if DEBUG + /* Poisoning will be done without holding the lock */ + if (cachep->flags & SLAB_POISON) { + void **objp = page->freelist; + + *objp = *list; + *list = objp; + } +#endif + page->freelist = NULL; + } + } else + list_add(&page->slab_list, &n->slabs_partial); +} + +/* Try to find non-pfmemalloc slab if needed */ +static noinline struct page *get_valid_first_slab(struct kmem_cache_node *n, + struct page *page, bool pfmemalloc) +{ + if (!page) + return NULL; + + if (pfmemalloc) + return page; + + if (!PageSlabPfmemalloc(page)) + return page; + + /* No need to keep pfmemalloc slab if we have enough free objects */ + if (n->free_objects > n->free_limit) { + ClearPageSlabPfmemalloc(page); + return page; + } + + /* Move pfmemalloc slab to the end of list to speed up next search */ + list_del(&page->slab_list); + if (!page->active) { + list_add_tail(&page->slab_list, &n->slabs_free); + n->free_slabs++; + } else + list_add_tail(&page->slab_list, &n->slabs_partial); + + list_for_each_entry(page, &n->slabs_partial, slab_list) { + if (!PageSlabPfmemalloc(page)) + return page; + } + + n->free_touched = 1; + list_for_each_entry(page, &n->slabs_free, slab_list) { + if (!PageSlabPfmemalloc(page)) { + n->free_slabs--; + return page; + } + } + + return NULL; +} + +static struct page *get_first_slab(struct kmem_cache_node *n, bool pfmemalloc) +{ + struct page *page; + + assert_spin_locked(&n->list_lock); + page = list_first_entry_or_null(&n->slabs_partial, struct page, + slab_list); + if (!page) { + n->free_touched = 1; + page = list_first_entry_or_null(&n->slabs_free, struct page, + slab_list); + if (page) + n->free_slabs--; + } + + if (sk_memalloc_socks()) + page = get_valid_first_slab(n, page, pfmemalloc); + + return page; +} + +static noinline void *cache_alloc_pfmemalloc(struct kmem_cache *cachep, + struct kmem_cache_node *n, gfp_t flags) +{ + struct page *page; + void *obj; + void *list = NULL; + + if (!gfp_pfmemalloc_allowed(flags)) + return NULL; + + spin_lock(&n->list_lock); + page = get_first_slab(n, true); + if (!page) { + spin_unlock(&n->list_lock); + return NULL; + } + + obj = slab_get_obj(cachep, page); + n->free_objects--; + + fixup_slab_list(cachep, n, page, &list); + + spin_unlock(&n->list_lock); + fixup_objfreelist_debug(cachep, &list); + + return obj; +} + +/* + * Slab list should be fixed up by fixup_slab_list() for existing slab + * or cache_grow_end() for new slab + */ +static __always_inline int alloc_block(struct kmem_cache *cachep, + struct array_cache *ac, struct page *page, int batchcount) +{ + /* + * There must be at least one object available for + * allocation. + */ + BUG_ON(page->active >= cachep->num); + + while (page->active < cachep->num && batchcount--) { + STATS_INC_ALLOCED(cachep); + STATS_INC_ACTIVE(cachep); + STATS_SET_HIGH(cachep); + + ac->entry[ac->avail++] = slab_get_obj(cachep, page); + } + + return batchcount; +} + +static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags) +{ + int batchcount; + struct kmem_cache_node *n; + struct array_cache *ac, *shared; + int node; + void *list = NULL; + struct page *page; + + check_irq_off(); + node = numa_mem_id(); + + ac = cpu_cache_get(cachep); + batchcount = ac->batchcount; + if (!ac->touched && batchcount > BATCHREFILL_LIMIT) { + /* + * If there was little recent activity on this cache, then + * perform only a partial refill. Otherwise we could generate + * refill bouncing. + */ + batchcount = BATCHREFILL_LIMIT; + } + n = get_node(cachep, node); + + BUG_ON(ac->avail > 0 || !n); + shared = READ_ONCE(n->shared); + if (!n->free_objects && (!shared || !shared->avail)) + goto direct_grow; + + spin_lock(&n->list_lock); + shared = READ_ONCE(n->shared); + + /* See if we can refill from the shared array */ + if (shared && transfer_objects(ac, shared, batchcount)) { + shared->touched = 1; + goto alloc_done; + } + + while (batchcount > 0) { + /* Get slab alloc is to come from. */ + page = get_first_slab(n, false); + if (!page) + goto must_grow; + + check_spinlock_acquired(cachep); + + batchcount = alloc_block(cachep, ac, page, batchcount); + fixup_slab_list(cachep, n, page, &list); + } + +must_grow: + n->free_objects -= ac->avail; +alloc_done: + spin_unlock(&n->list_lock); + fixup_objfreelist_debug(cachep, &list); + +direct_grow: + if (unlikely(!ac->avail)) { + /* Check if we can use obj in pfmemalloc slab */ + if (sk_memalloc_socks()) { + void *obj = cache_alloc_pfmemalloc(cachep, n, flags); + + if (obj) + return obj; + } + + page = cache_grow_begin(cachep, gfp_exact_node(flags), node); + + /* + * cache_grow_begin() can reenable interrupts, + * then ac could change. + */ + ac = cpu_cache_get(cachep); + if (!ac->avail && page) + alloc_block(cachep, ac, page, batchcount); + cache_grow_end(cachep, page); + + if (!ac->avail) + return NULL; + } + ac->touched = 1; + + return ac->entry[--ac->avail]; +} + +static inline void cache_alloc_debugcheck_before(struct kmem_cache *cachep, + gfp_t flags) +{ + might_sleep_if(gfpflags_allow_blocking(flags)); +} + +#if DEBUG +static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, + gfp_t flags, void *objp, unsigned long caller) +{ + WARN_ON_ONCE(cachep->ctor && (flags & __GFP_ZERO)); + if (!objp) + return objp; + if (cachep->flags & SLAB_POISON) { + check_poison_obj(cachep, objp); + slab_kernel_map(cachep, objp, 1); + poison_obj(cachep, objp, POISON_INUSE); + } + if (cachep->flags & SLAB_STORE_USER) + *dbg_userword(cachep, objp) = (void *)caller; + + if (cachep->flags & SLAB_RED_ZONE) { + if (*dbg_redzone1(cachep, objp) != RED_INACTIVE || + *dbg_redzone2(cachep, objp) != RED_INACTIVE) { + slab_error(cachep, "double free, or memory outside object was overwritten"); + pr_err("%px: redzone 1:0x%llx, redzone 2:0x%llx\n", + objp, *dbg_redzone1(cachep, objp), + *dbg_redzone2(cachep, objp)); + } + *dbg_redzone1(cachep, objp) = RED_ACTIVE; + *dbg_redzone2(cachep, objp) = RED_ACTIVE; + } + + objp += obj_offset(cachep); + if (cachep->ctor && cachep->flags & SLAB_POISON) + cachep->ctor(objp); + if (ARCH_SLAB_MINALIGN && + ((unsigned long)objp & (ARCH_SLAB_MINALIGN-1))) { + pr_err("0x%px: not aligned to ARCH_SLAB_MINALIGN=%d\n", + objp, (int)ARCH_SLAB_MINALIGN); + } + return objp; +} +#else +#define cache_alloc_debugcheck_after(a,b,objp,d) (objp) +#endif + +static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags) +{ + void *objp; + struct array_cache *ac; + + check_irq_off(); + + ac = cpu_cache_get(cachep); + if (likely(ac->avail)) { + ac->touched = 1; + objp = ac->entry[--ac->avail]; + + STATS_INC_ALLOCHIT(cachep); + goto out; + } + + STATS_INC_ALLOCMISS(cachep); + objp = cache_alloc_refill(cachep, flags); + /* + * the 'ac' may be updated by cache_alloc_refill(), + * and kmemleak_erase() requires its correct value. + */ + ac = cpu_cache_get(cachep); + +out: + /* + * To avoid a false negative, if an object that is in one of the + * per-CPU caches is leaked, we need to make sure kmemleak doesn't + * treat the array pointers as a reference to the object. + */ + if (objp) + kmemleak_erase(&ac->entry[ac->avail]); + return objp; +} + +#ifdef CONFIG_NUMA +/* + * Try allocating on another node if PFA_SPREAD_SLAB is a mempolicy is set. + * + * If we are in_interrupt, then process context, including cpusets and + * mempolicy, may not apply and should not be used for allocation policy. + */ +static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags) +{ + int nid_alloc, nid_here; + + if (in_interrupt() || (flags & __GFP_THISNODE)) + return NULL; + nid_alloc = nid_here = numa_mem_id(); + if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD)) + nid_alloc = cpuset_slab_spread_node(); + else if (current->mempolicy) + nid_alloc = mempolicy_slab_node(); + if (nid_alloc != nid_here) + return ____cache_alloc_node(cachep, flags, nid_alloc); + return NULL; +} + +/* + * Fallback function if there was no memory available and no objects on a + * certain node and fall back is permitted. First we scan all the + * available node for available objects. If that fails then we + * perform an allocation without specifying a node. This allows the page + * allocator to do its reclaim / fallback magic. We then insert the + * slab into the proper nodelist and then allocate from it. + */ +static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags) +{ + struct zonelist *zonelist; + struct zoneref *z; + struct zone *zone; + enum zone_type highest_zoneidx = gfp_zone(flags); + void *obj = NULL; + struct page *page; + int nid; + unsigned int cpuset_mems_cookie; + + if (flags & __GFP_THISNODE) + return NULL; + +retry_cpuset: + cpuset_mems_cookie = read_mems_allowed_begin(); + zonelist = node_zonelist(mempolicy_slab_node(), flags); + +retry: + /* + * Look through allowed nodes for objects available + * from existing per node queues. + */ + for_each_zone_zonelist(zone, z, zonelist, highest_zoneidx) { + nid = zone_to_nid(zone); + + if (cpuset_zone_allowed(zone, flags) && + get_node(cache, nid) && + get_node(cache, nid)->free_objects) { + obj = ____cache_alloc_node(cache, + gfp_exact_node(flags), nid); + if (obj) + break; + } + } + + if (!obj) { + /* + * This allocation will be performed within the constraints + * of the current cpuset / memory policy requirements. + * We may trigger various forms of reclaim on the allowed + * set and go into memory reserves if necessary. + */ + page = cache_grow_begin(cache, flags, numa_mem_id()); + cache_grow_end(cache, page); + if (page) { + nid = page_to_nid(page); + obj = ____cache_alloc_node(cache, + gfp_exact_node(flags), nid); + + /* + * Another processor may allocate the objects in + * the slab since we are not holding any locks. + */ + if (!obj) + goto retry; + } + } + + if (unlikely(!obj && read_mems_allowed_retry(cpuset_mems_cookie))) + goto retry_cpuset; + return obj; +} + +/* + * A interface to enable slab creation on nodeid + */ +static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, + int nodeid) +{ + struct page *page; + struct kmem_cache_node *n; + void *obj = NULL; + void *list = NULL; + + VM_BUG_ON(nodeid < 0 || nodeid >= MAX_NUMNODES); + n = get_node(cachep, nodeid); + BUG_ON(!n); + + check_irq_off(); + spin_lock(&n->list_lock); + page = get_first_slab(n, false); + if (!page) + goto must_grow; + + check_spinlock_acquired_node(cachep, nodeid); + + STATS_INC_NODEALLOCS(cachep); + STATS_INC_ACTIVE(cachep); + STATS_SET_HIGH(cachep); + + BUG_ON(page->active == cachep->num); + + obj = slab_get_obj(cachep, page); + n->free_objects--; + + fixup_slab_list(cachep, n, page, &list); + + spin_unlock(&n->list_lock); + fixup_objfreelist_debug(cachep, &list); + return obj; + +must_grow: + spin_unlock(&n->list_lock); + page = cache_grow_begin(cachep, gfp_exact_node(flags), nodeid); + if (page) { + /* This slab isn't counted yet so don't update free_objects */ + obj = slab_get_obj(cachep, page); + } + cache_grow_end(cachep, page); + + return obj ? obj : fallback_alloc(cachep, flags); +} + +static __always_inline void * +slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, + unsigned long caller) +{ + unsigned long save_flags; + void *ptr; + int slab_node = numa_mem_id(); + struct obj_cgroup *objcg = NULL; + + flags &= gfp_allowed_mask; + cachep = slab_pre_alloc_hook(cachep, &objcg, 1, flags); + if (unlikely(!cachep)) + return NULL; + + cache_alloc_debugcheck_before(cachep, flags); + local_irq_save(save_flags); + + if (nodeid == NUMA_NO_NODE) + nodeid = slab_node; + + if (unlikely(!get_node(cachep, nodeid))) { + /* Node not bootstrapped yet */ + ptr = fallback_alloc(cachep, flags); + goto out; + } + + if (nodeid == slab_node) { + /* + * Use the locally cached objects if possible. + * However ____cache_alloc does not allow fallback + * to other nodes. It may fail while we still have + * objects on other nodes available. + */ + ptr = ____cache_alloc(cachep, flags); + if (ptr) + goto out; + } + /* ___cache_alloc_node can fall back to other nodes */ + ptr = ____cache_alloc_node(cachep, flags, nodeid); + out: + local_irq_restore(save_flags); + ptr = cache_alloc_debugcheck_after(cachep, flags, ptr, caller); + + if (unlikely(slab_want_init_on_alloc(flags, cachep)) && ptr) + memset(ptr, 0, cachep->object_size); + + slab_post_alloc_hook(cachep, objcg, flags, 1, &ptr); + return ptr; +} + +static __always_inline void * +__do_cache_alloc(struct kmem_cache *cache, gfp_t flags) +{ + void *objp; + + if (current->mempolicy || cpuset_do_slab_mem_spread()) { + objp = alternate_node_alloc(cache, flags); + if (objp) + goto out; + } + objp = ____cache_alloc(cache, flags); + + /* + * We may just have run out of memory on the local node. + * ____cache_alloc_node() knows how to locate memory on other nodes + */ + if (!objp) + objp = ____cache_alloc_node(cache, flags, numa_mem_id()); + + out: + return objp; +} +#else + +static __always_inline void * +__do_cache_alloc(struct kmem_cache *cachep, gfp_t flags) +{ + return ____cache_alloc(cachep, flags); +} + +#endif /* CONFIG_NUMA */ + +static __always_inline void * +slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller) +{ + unsigned long save_flags; + void *objp; + struct obj_cgroup *objcg = NULL; + + flags &= gfp_allowed_mask; + cachep = slab_pre_alloc_hook(cachep, &objcg, 1, flags); + if (unlikely(!cachep)) + return NULL; + + cache_alloc_debugcheck_before(cachep, flags); + local_irq_save(save_flags); + objp = __do_cache_alloc(cachep, flags); + local_irq_restore(save_flags); + objp = cache_alloc_debugcheck_after(cachep, flags, objp, caller); + prefetchw(objp); + + if (unlikely(slab_want_init_on_alloc(flags, cachep)) && objp) + memset(objp, 0, cachep->object_size); + + slab_post_alloc_hook(cachep, objcg, flags, 1, &objp); + return objp; +} + +/* + * Caller needs to acquire correct kmem_cache_node's list_lock + * @list: List of detached free slabs should be freed by caller + */ +static void free_block(struct kmem_cache *cachep, void **objpp, + int nr_objects, int node, struct list_head *list) +{ + int i; + struct kmem_cache_node *n = get_node(cachep, node); + struct page *page; + + n->free_objects += nr_objects; + + for (i = 0; i < nr_objects; i++) { + void *objp; + struct page *page; + + objp = objpp[i]; + + page = virt_to_head_page(objp); + list_del(&page->slab_list); + check_spinlock_acquired_node(cachep, node); + slab_put_obj(cachep, page, objp); + STATS_DEC_ACTIVE(cachep); + + /* fixup slab chains */ + if (page->active == 0) { + list_add(&page->slab_list, &n->slabs_free); + n->free_slabs++; + } else { + /* Unconditionally move a slab to the end of the + * partial list on free - maximum time for the + * other objects to be freed, too. + */ + list_add_tail(&page->slab_list, &n->slabs_partial); + } + } + + while (n->free_objects > n->free_limit && !list_empty(&n->slabs_free)) { + n->free_objects -= cachep->num; + + page = list_last_entry(&n->slabs_free, struct page, slab_list); + list_move(&page->slab_list, list); + n->free_slabs--; + n->total_slabs--; + } +} + +static void cache_flusharray(struct kmem_cache *cachep, struct array_cache *ac) +{ + int batchcount; + struct kmem_cache_node *n; + int node = numa_mem_id(); + LIST_HEAD(list); + + batchcount = ac->batchcount; + + check_irq_off(); + n = get_node(cachep, node); + spin_lock(&n->list_lock); + if (n->shared) { + struct array_cache *shared_array = n->shared; + int max = shared_array->limit - shared_array->avail; + if (max) { + if (batchcount > max) + batchcount = max; + memcpy(&(shared_array->entry[shared_array->avail]), + ac->entry, sizeof(void *) * batchcount); + shared_array->avail += batchcount; + goto free_done; + } + } + + free_block(cachep, ac->entry, batchcount, node, &list); +free_done: +#if STATS + { + int i = 0; + struct page *page; + + list_for_each_entry(page, &n->slabs_free, slab_list) { + BUG_ON(page->active); + + i++; + } + STATS_SET_FREEABLE(cachep, i); + } +#endif + spin_unlock(&n->list_lock); + ac->avail -= batchcount; + memmove(ac->entry, &(ac->entry[batchcount]), sizeof(void *)*ac->avail); + slabs_destroy(cachep, &list); +} + +/* + * Release an obj back to its cache. If the obj has a constructed state, it must + * be in this state _before_ it is released. Called with disabled ints. + */ +static __always_inline void __cache_free(struct kmem_cache *cachep, void *objp, + unsigned long caller) +{ + /* Put the object into the quarantine, don't touch it for now. */ + if (kasan_slab_free(cachep, objp, _RET_IP_)) + return; + + /* Use KCSAN to help debug racy use-after-free. */ + if (!(cachep->flags & SLAB_TYPESAFE_BY_RCU)) + __kcsan_check_access(objp, cachep->object_size, + KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ASSERT); + + ___cache_free(cachep, objp, caller); +} + +void ___cache_free(struct kmem_cache *cachep, void *objp, + unsigned long caller) +{ + struct array_cache *ac = cpu_cache_get(cachep); + + check_irq_off(); + if (unlikely(slab_want_init_on_free(cachep))) + memset(objp, 0, cachep->object_size); + kmemleak_free_recursive(objp, cachep->flags); + objp = cache_free_debugcheck(cachep, objp, caller); + memcg_slab_free_hook(cachep, &objp, 1); + + /* + * Skip calling cache_free_alien() when the platform is not numa. + * This will avoid cache misses that happen while accessing slabp (which + * is per page memory reference) to get nodeid. Instead use a global + * variable to skip the call, which is mostly likely to be present in + * the cache. + */ + if (nr_online_nodes > 1 && cache_free_alien(cachep, objp)) + return; + + if (ac->avail < ac->limit) { + STATS_INC_FREEHIT(cachep); + } else { + STATS_INC_FREEMISS(cachep); + cache_flusharray(cachep, ac); + } + + if (sk_memalloc_socks()) { + struct page *page = virt_to_head_page(objp); + + if (unlikely(PageSlabPfmemalloc(page))) { + cache_free_pfmemalloc(cachep, page, objp); + return; + } + } + + __free_one(ac, objp); +} + +/** + * kmem_cache_alloc - Allocate an object + * @cachep: The cache to allocate from. + * @flags: See kmalloc(). + * + * Allocate an object from this cache. The flags are only relevant + * if the cache has no available objects. + * + * Return: pointer to the new object or %NULL in case of error + */ +void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags) +{ + void *ret = slab_alloc(cachep, flags, _RET_IP_); + + trace_kmem_cache_alloc(_RET_IP_, ret, + cachep->object_size, cachep->size, flags); + + return ret; +} +EXPORT_SYMBOL(kmem_cache_alloc); + +static __always_inline void +cache_alloc_debugcheck_after_bulk(struct kmem_cache *s, gfp_t flags, + size_t size, void **p, unsigned long caller) +{ + size_t i; + + for (i = 0; i < size; i++) + p[i] = cache_alloc_debugcheck_after(s, flags, p[i], caller); +} + +int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, + void **p) +{ + size_t i; + struct obj_cgroup *objcg = NULL; + + s = slab_pre_alloc_hook(s, &objcg, size, flags); + if (!s) + return 0; + + cache_alloc_debugcheck_before(s, flags); + + local_irq_disable(); + for (i = 0; i < size; i++) { + void *objp = __do_cache_alloc(s, flags); + + if (unlikely(!objp)) + goto error; + p[i] = objp; + } + local_irq_enable(); + + cache_alloc_debugcheck_after_bulk(s, flags, size, p, _RET_IP_); + + /* Clear memory outside IRQ disabled section */ + if (unlikely(slab_want_init_on_alloc(flags, s))) + for (i = 0; i < size; i++) + memset(p[i], 0, s->object_size); + + slab_post_alloc_hook(s, objcg, flags, size, p); + /* FIXME: Trace call missing. Christoph would like a bulk variant */ + return size; +error: + local_irq_enable(); + cache_alloc_debugcheck_after_bulk(s, flags, i, p, _RET_IP_); + slab_post_alloc_hook(s, objcg, flags, i, p); + __kmem_cache_free_bulk(s, i, p); + return 0; +} +EXPORT_SYMBOL(kmem_cache_alloc_bulk); + +#ifdef CONFIG_TRACING +void * +kmem_cache_alloc_trace(struct kmem_cache *cachep, gfp_t flags, size_t size) +{ + void *ret; + + ret = slab_alloc(cachep, flags, _RET_IP_); + + ret = kasan_kmalloc(cachep, ret, size, flags); + trace_kmalloc(_RET_IP_, ret, + size, cachep->size, flags); + return ret; +} +EXPORT_SYMBOL(kmem_cache_alloc_trace); +#endif + +#ifdef CONFIG_NUMA +/** + * kmem_cache_alloc_node - Allocate an object on the specified node + * @cachep: The cache to allocate from. + * @flags: See kmalloc(). + * @nodeid: node number of the target node. + * + * Identical to kmem_cache_alloc but it will allocate memory on the given + * node, which can improve the performance for cpu bound structures. + * + * Fallback to other node is possible if __GFP_THISNODE is not set. + * + * Return: pointer to the new object or %NULL in case of error + */ +void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid) +{ + void *ret = slab_alloc_node(cachep, flags, nodeid, _RET_IP_); + + trace_kmem_cache_alloc_node(_RET_IP_, ret, + cachep->object_size, cachep->size, + flags, nodeid); + + return ret; +} +EXPORT_SYMBOL(kmem_cache_alloc_node); + +#ifdef CONFIG_TRACING +void *kmem_cache_alloc_node_trace(struct kmem_cache *cachep, + gfp_t flags, + int nodeid, + size_t size) +{ + void *ret; + + ret = slab_alloc_node(cachep, flags, nodeid, _RET_IP_); + + ret = kasan_kmalloc(cachep, ret, size, flags); + trace_kmalloc_node(_RET_IP_, ret, + size, cachep->size, + flags, nodeid); + return ret; +} +EXPORT_SYMBOL(kmem_cache_alloc_node_trace); +#endif + +static __always_inline void * +__do_kmalloc_node(size_t size, gfp_t flags, int node, unsigned long caller) +{ + struct kmem_cache *cachep; + void *ret; + + if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) + return NULL; + cachep = kmalloc_slab(size, flags); + if (unlikely(ZERO_OR_NULL_PTR(cachep))) + return cachep; + ret = kmem_cache_alloc_node_trace(cachep, flags, node, size); + ret = kasan_kmalloc(cachep, ret, size, flags); + + return ret; +} + +void *__kmalloc_node(size_t size, gfp_t flags, int node) +{ + return __do_kmalloc_node(size, flags, node, _RET_IP_); +} +EXPORT_SYMBOL(__kmalloc_node); + +void *__kmalloc_node_track_caller(size_t size, gfp_t flags, + int node, unsigned long caller) +{ + return __do_kmalloc_node(size, flags, node, caller); +} +EXPORT_SYMBOL(__kmalloc_node_track_caller); +#endif /* CONFIG_NUMA */ + +/** + * __do_kmalloc - allocate memory + * @size: how many bytes of memory are required. + * @flags: the type of memory to allocate (see kmalloc). + * @caller: function caller for debug tracking of the caller + * + * Return: pointer to the allocated memory or %NULL in case of error + */ +static __always_inline void *__do_kmalloc(size_t size, gfp_t flags, + unsigned long caller) +{ + struct kmem_cache *cachep; + void *ret; + + if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) + return NULL; + cachep = kmalloc_slab(size, flags); + if (unlikely(ZERO_OR_NULL_PTR(cachep))) + return cachep; + ret = slab_alloc(cachep, flags, caller); + + ret = kasan_kmalloc(cachep, ret, size, flags); + trace_kmalloc(caller, ret, + size, cachep->size, flags); + + return ret; +} + +void *__kmalloc(size_t size, gfp_t flags) +{ + return __do_kmalloc(size, flags, _RET_IP_); +} +EXPORT_SYMBOL(__kmalloc); + +void *__kmalloc_track_caller(size_t size, gfp_t flags, unsigned long caller) +{ + return __do_kmalloc(size, flags, caller); +} +EXPORT_SYMBOL(__kmalloc_track_caller); + +/** + * kmem_cache_free - Deallocate an object + * @cachep: The cache the allocation was from. + * @objp: The previously allocated object. + * + * Free an object which was previously allocated from this + * cache. + */ +void kmem_cache_free(struct kmem_cache *cachep, void *objp) +{ + unsigned long flags; + cachep = cache_from_obj(cachep, objp); + if (!cachep) + return; + + local_irq_save(flags); + debug_check_no_locks_freed(objp, cachep->object_size); + if (!(cachep->flags & SLAB_DEBUG_OBJECTS)) + debug_check_no_obj_freed(objp, cachep->object_size); + __cache_free(cachep, objp, _RET_IP_); + local_irq_restore(flags); + + trace_kmem_cache_free(_RET_IP_, objp); +} +EXPORT_SYMBOL(kmem_cache_free); + +void kmem_cache_free_bulk(struct kmem_cache *orig_s, size_t size, void **p) +{ + struct kmem_cache *s; + size_t i; + + local_irq_disable(); + for (i = 0; i < size; i++) { + void *objp = p[i]; + + if (!orig_s) /* called via kfree_bulk */ + s = virt_to_cache(objp); + else + s = cache_from_obj(orig_s, objp); + if (!s) + continue; + + debug_check_no_locks_freed(objp, s->object_size); + if (!(s->flags & SLAB_DEBUG_OBJECTS)) + debug_check_no_obj_freed(objp, s->object_size); + + __cache_free(s, objp, _RET_IP_); + } + local_irq_enable(); + + /* FIXME: add tracing */ +} +EXPORT_SYMBOL(kmem_cache_free_bulk); + +/** + * kfree - free previously allocated memory + * @objp: pointer returned by kmalloc. + * + * If @objp is NULL, no operation is performed. + * + * Don't free memory not originally allocated by kmalloc() + * or you will run into trouble. + */ +void kfree(const void *objp) +{ + struct kmem_cache *c; + unsigned long flags; + + trace_kfree(_RET_IP_, objp); + + if (unlikely(ZERO_OR_NULL_PTR(objp))) + return; + local_irq_save(flags); + kfree_debugcheck(objp); + c = virt_to_cache(objp); + if (!c) { + local_irq_restore(flags); + return; + } + debug_check_no_locks_freed(objp, c->object_size); + + debug_check_no_obj_freed(objp, c->object_size); + __cache_free(c, (void *)objp, _RET_IP_); + local_irq_restore(flags); +} +EXPORT_SYMBOL(kfree); + +/* + * This initializes kmem_cache_node or resizes various caches for all nodes. + */ +static int setup_kmem_cache_nodes(struct kmem_cache *cachep, gfp_t gfp) +{ + int ret; + int node; + struct kmem_cache_node *n; + + for_each_online_node(node) { + ret = setup_kmem_cache_node(cachep, node, gfp, true); + if (ret) + goto fail; + + } + + return 0; + +fail: + if (!cachep->list.next) { + /* Cache is not active yet. Roll back what we did */ + node--; + while (node >= 0) { + n = get_node(cachep, node); + if (n) { + kfree(n->shared); + free_alien_cache(n->alien); + kfree(n); + cachep->node[node] = NULL; + } + node--; + } + } + return -ENOMEM; +} + +/* Always called with the slab_mutex held */ +static int do_tune_cpucache(struct kmem_cache *cachep, int limit, + int batchcount, int shared, gfp_t gfp) +{ + struct array_cache __percpu *cpu_cache, *prev; + int cpu; + + cpu_cache = alloc_kmem_cache_cpus(cachep, limit, batchcount); + if (!cpu_cache) + return -ENOMEM; + + prev = cachep->cpu_cache; + cachep->cpu_cache = cpu_cache; + /* + * Without a previous cpu_cache there's no need to synchronize remote + * cpus, so skip the IPIs. + */ + if (prev) + kick_all_cpus_sync(); + + check_irq_on(); + cachep->batchcount = batchcount; + cachep->limit = limit; + cachep->shared = shared; + + if (!prev) + goto setup_node; + + for_each_online_cpu(cpu) { + LIST_HEAD(list); + int node; + struct kmem_cache_node *n; + struct array_cache *ac = per_cpu_ptr(prev, cpu); + + node = cpu_to_mem(cpu); + n = get_node(cachep, node); + spin_lock_irq(&n->list_lock); + free_block(cachep, ac->entry, ac->avail, node, &list); + spin_unlock_irq(&n->list_lock); + slabs_destroy(cachep, &list); + } + free_percpu(prev); + +setup_node: + return setup_kmem_cache_nodes(cachep, gfp); +} + +/* Called with slab_mutex held always */ +static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp) +{ + int err; + int limit = 0; + int shared = 0; + int batchcount = 0; + + err = cache_random_seq_create(cachep, cachep->num, gfp); + if (err) + goto end; + + if (limit && shared && batchcount) + goto skip_setup; + /* + * The head array serves three purposes: + * - create a LIFO ordering, i.e. return objects that are cache-warm + * - reduce the number of spinlock operations. + * - reduce the number of linked list operations on the slab and + * bufctl chains: array operations are cheaper. + * The numbers are guessed, we should auto-tune as described by + * Bonwick. + */ + if (cachep->size > 131072) + limit = 1; + else if (cachep->size > PAGE_SIZE) + limit = 8; + else if (cachep->size > 1024) + limit = 24; + else if (cachep->size > 256) + limit = 54; + else + limit = 120; + + /* + * CPU bound tasks (e.g. network routing) can exhibit cpu bound + * allocation behaviour: Most allocs on one cpu, most free operations + * on another cpu. For these cases, an efficient object passing between + * cpus is necessary. This is provided by a shared array. The array + * replaces Bonwick's magazine layer. + * On uniprocessor, it's functionally equivalent (but less efficient) + * to a larger limit. Thus disabled by default. + */ + shared = 0; + if (cachep->size <= PAGE_SIZE && num_possible_cpus() > 1) + shared = 8; + +#if DEBUG + /* + * With debugging enabled, large batchcount lead to excessively long + * periods with disabled local interrupts. Limit the batchcount + */ + if (limit > 32) + limit = 32; +#endif + batchcount = (limit + 1) / 2; +skip_setup: + err = do_tune_cpucache(cachep, limit, batchcount, shared, gfp); +end: + if (err) + pr_err("enable_cpucache failed for %s, error %d\n", + cachep->name, -err); + return err; +} + +/* + * Drain an array if it contains any elements taking the node lock only if + * necessary. Note that the node listlock also protects the array_cache + * if drain_array() is used on the shared array. + */ +static void drain_array(struct kmem_cache *cachep, struct kmem_cache_node *n, + struct array_cache *ac, int node) +{ + LIST_HEAD(list); + + /* ac from n->shared can be freed if we don't hold the slab_mutex. */ + check_mutex_acquired(); + + if (!ac || !ac->avail) + return; + + if (ac->touched) { + ac->touched = 0; + return; + } + + spin_lock_irq(&n->list_lock); + drain_array_locked(cachep, ac, node, false, &list); + spin_unlock_irq(&n->list_lock); + + slabs_destroy(cachep, &list); +} + +/** + * cache_reap - Reclaim memory from caches. + * @w: work descriptor + * + * Called from workqueue/eventd every few seconds. + * Purpose: + * - clear the per-cpu caches for this CPU. + * - return freeable pages to the main free memory pool. + * + * If we cannot acquire the cache chain mutex then just give up - we'll try + * again on the next iteration. + */ +static void cache_reap(struct work_struct *w) +{ + struct kmem_cache *searchp; + struct kmem_cache_node *n; + int node = numa_mem_id(); + struct delayed_work *work = to_delayed_work(w); + + if (!mutex_trylock(&slab_mutex)) + /* Give up. Setup the next iteration. */ + goto out; + + list_for_each_entry(searchp, &slab_caches, list) { + check_irq_on(); + + /* + * We only take the node lock if absolutely necessary and we + * have established with reasonable certainty that + * we can do some work if the lock was obtained. + */ + n = get_node(searchp, node); + + reap_alien(searchp, n); + + drain_array(searchp, n, cpu_cache_get(searchp), node); + + /* + * These are racy checks but it does not matter + * if we skip one check or scan twice. + */ + if (time_after(n->next_reap, jiffies)) + goto next; + + n->next_reap = jiffies + REAPTIMEOUT_NODE; + + drain_array(searchp, n, n->shared, node); + + if (n->free_touched) + n->free_touched = 0; + else { + int freed; + + freed = drain_freelist(searchp, n, (n->free_limit + + 5 * searchp->num - 1) / (5 * searchp->num)); + STATS_ADD_REAPED(searchp, freed); + } +next: + cond_resched(); + } + check_irq_on(); + mutex_unlock(&slab_mutex); + next_reap_node(); +out: + /* Set up the next iteration */ + schedule_delayed_work_on(smp_processor_id(), work, + round_jiffies_relative(REAPTIMEOUT_AC)); +} + +void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo) +{ + unsigned long active_objs, num_objs, active_slabs; + unsigned long total_slabs = 0, free_objs = 0, shared_avail = 0; + unsigned long free_slabs = 0; + int node; + struct kmem_cache_node *n; + + for_each_kmem_cache_node(cachep, node, n) { + check_irq_on(); + spin_lock_irq(&n->list_lock); + + total_slabs += n->total_slabs; + free_slabs += n->free_slabs; + free_objs += n->free_objects; + + if (n->shared) + shared_avail += n->shared->avail; + + spin_unlock_irq(&n->list_lock); + } + num_objs = total_slabs * cachep->num; + active_slabs = total_slabs - free_slabs; + active_objs = num_objs - free_objs; + + sinfo->active_objs = active_objs; + sinfo->num_objs = num_objs; + sinfo->active_slabs = active_slabs; + sinfo->num_slabs = total_slabs; + sinfo->shared_avail = shared_avail; + sinfo->limit = cachep->limit; + sinfo->batchcount = cachep->batchcount; + sinfo->shared = cachep->shared; + sinfo->objects_per_slab = cachep->num; + sinfo->cache_order = cachep->gfporder; +} + +void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *cachep) +{ +#if STATS + { /* node stats */ + unsigned long high = cachep->high_mark; + unsigned long allocs = cachep->num_allocations; + unsigned long grown = cachep->grown; + unsigned long reaped = cachep->reaped; + unsigned long errors = cachep->errors; + unsigned long max_freeable = cachep->max_freeable; + unsigned long node_allocs = cachep->node_allocs; + unsigned long node_frees = cachep->node_frees; + unsigned long overflows = cachep->node_overflow; + + seq_printf(m, " : globalstat %7lu %6lu %5lu %4lu %4lu %4lu %4lu %4lu %4lu", + allocs, high, grown, + reaped, errors, max_freeable, node_allocs, + node_frees, overflows); + } + /* cpu stats */ + { + unsigned long allochit = atomic_read(&cachep->allochit); + unsigned long allocmiss = atomic_read(&cachep->allocmiss); + unsigned long freehit = atomic_read(&cachep->freehit); + unsigned long freemiss = atomic_read(&cachep->freemiss); + + seq_printf(m, " : cpustat %6lu %6lu %6lu %6lu", + allochit, allocmiss, freehit, freemiss); + } +#endif +} + +#define MAX_SLABINFO_WRITE 128 +/** + * slabinfo_write - Tuning for the slab allocator + * @file: unused + * @buffer: user buffer + * @count: data length + * @ppos: unused + * + * Return: %0 on success, negative error code otherwise. + */ +ssize_t slabinfo_write(struct file *file, const char __user *buffer, + size_t count, loff_t *ppos) +{ + char kbuf[MAX_SLABINFO_WRITE + 1], *tmp; + int limit, batchcount, shared, res; + struct kmem_cache *cachep; + + if (count > MAX_SLABINFO_WRITE) + return -EINVAL; + if (copy_from_user(&kbuf, buffer, count)) + return -EFAULT; + kbuf[MAX_SLABINFO_WRITE] = '\0'; + + tmp = strchr(kbuf, ' '); + if (!tmp) + return -EINVAL; + *tmp = '\0'; + tmp++; + if (sscanf(tmp, " %d %d %d", &limit, &batchcount, &shared) != 3) + return -EINVAL; + + /* Find the cache in the chain of caches. */ + mutex_lock(&slab_mutex); + res = -EINVAL; + list_for_each_entry(cachep, &slab_caches, list) { + if (!strcmp(cachep->name, kbuf)) { + if (limit < 1 || batchcount < 1 || + batchcount > limit || shared < 0) { + res = 0; + } else { + res = do_tune_cpucache(cachep, limit, + batchcount, shared, + GFP_KERNEL); + } + break; + } + } + mutex_unlock(&slab_mutex); + if (res >= 0) + res = count; + return res; +} + +#ifdef CONFIG_HARDENED_USERCOPY +/* + * Rejects incorrectly sized objects and objects that are to be copied + * to/from userspace but do not fall entirely within the containing slab + * cache's usercopy region. + * + * Returns NULL if check passes, otherwise const char * to name of cache + * to indicate an error. + */ +void __check_heap_object(const void *ptr, unsigned long n, struct page *page, + bool to_user) +{ + struct kmem_cache *cachep; + unsigned int objnr; + unsigned long offset; + + ptr = kasan_reset_tag(ptr); + + /* Find and validate object. */ + cachep = page->slab_cache; + objnr = obj_to_index(cachep, page, (void *)ptr); + BUG_ON(objnr >= cachep->num); + + /* Find offset within object. */ + offset = ptr - index_to_obj(cachep, page, objnr) - obj_offset(cachep); + + /* Allow address range falling entirely within usercopy region. */ + if (offset >= cachep->useroffset && + offset - cachep->useroffset <= cachep->usersize && + n <= cachep->useroffset - offset + cachep->usersize) + return; + + /* + * If the copy is still within the allocated object, produce + * a warning instead of rejecting the copy. This is intended + * to be a temporary method to find any missing usercopy + * whitelists. + */ + if (usercopy_fallback && + offset <= cachep->object_size && + n <= cachep->object_size - offset) { + usercopy_warn("SLAB object", cachep->name, to_user, offset, n); + return; + } + + usercopy_abort("SLAB object", cachep->name, to_user, offset, n); +} +#endif /* CONFIG_HARDENED_USERCOPY */ + +/** + * __ksize -- Uninstrumented ksize. + * @objp: pointer to the object + * + * Unlike ksize(), __ksize() is uninstrumented, and does not provide the same + * safety checks as ksize() with KASAN instrumentation enabled. + * + * Return: size of the actual memory used by @objp in bytes + */ +size_t __ksize(const void *objp) +{ + struct kmem_cache *c; + size_t size; + + BUG_ON(!objp); + if (unlikely(objp == ZERO_SIZE_PTR)) + return 0; + + c = virt_to_cache(objp); + size = c ? c->object_size : 0; + + return size; +} +EXPORT_SYMBOL(__ksize); diff --git a/mm/slab.h b/mm/slab.h new file mode 100644 index 000000000..6952e10cf --- /dev/null +++ b/mm/slab.h @@ -0,0 +1,638 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef MM_SLAB_H +#define MM_SLAB_H +/* + * Internal slab definitions + */ + +#ifdef CONFIG_SLOB +/* + * Common fields provided in kmem_cache by all slab allocators + * This struct is either used directly by the allocator (SLOB) + * or the allocator must include definitions for all fields + * provided in kmem_cache_common in their definition of kmem_cache. + * + * Once we can do anonymous structs (C11 standard) we could put a + * anonymous struct definition in these allocators so that the + * separate allocations in the kmem_cache structure of SLAB and + * SLUB is no longer needed. + */ +struct kmem_cache { + unsigned int object_size;/* The original size of the object */ + unsigned int size; /* The aligned/padded/added on size */ + unsigned int align; /* Alignment as calculated */ + slab_flags_t flags; /* Active flags on the slab */ + unsigned int useroffset;/* Usercopy region offset */ + unsigned int usersize; /* Usercopy region size */ + const char *name; /* Slab name for sysfs */ + int refcount; /* Use counter */ + void (*ctor)(void *); /* Called on object slot creation */ + struct list_head list; /* List of all slab caches on the system */ +}; + +#endif /* CONFIG_SLOB */ + +#ifdef CONFIG_SLAB +#include +#endif + +#ifdef CONFIG_SLUB +#include +#endif + +#include +#include +#include +#include +#include +#include + +/* + * State of the slab allocator. + * + * This is used to describe the states of the allocator during bootup. + * Allocators use this to gradually bootstrap themselves. Most allocators + * have the problem that the structures used for managing slab caches are + * allocated from slab caches themselves. + */ +enum slab_state { + DOWN, /* No slab functionality yet */ + PARTIAL, /* SLUB: kmem_cache_node available */ + PARTIAL_NODE, /* SLAB: kmalloc size for node struct available */ + UP, /* Slab caches usable but not all extras yet */ + FULL /* Everything is working */ +}; + +extern enum slab_state slab_state; + +/* The slab cache mutex protects the management structures during changes */ +extern struct mutex slab_mutex; + +/* The list of all slab caches on the system */ +extern struct list_head slab_caches; + +/* The slab cache that manages slab cache information */ +extern struct kmem_cache *kmem_cache; + +/* A table of kmalloc cache names and sizes */ +extern const struct kmalloc_info_struct { + const char *name[NR_KMALLOC_TYPES]; + unsigned int size; +} kmalloc_info[]; + +#ifndef CONFIG_SLOB +/* Kmalloc array related functions */ +void setup_kmalloc_cache_index_table(void); +void create_kmalloc_caches(slab_flags_t); + +/* Find the kmalloc slab corresponding for a certain size */ +struct kmem_cache *kmalloc_slab(size_t, gfp_t); +#endif + +gfp_t kmalloc_fix_flags(gfp_t flags); + +/* Functions provided by the slab allocators */ +int __kmem_cache_create(struct kmem_cache *, slab_flags_t flags); + +struct kmem_cache *create_kmalloc_cache(const char *name, unsigned int size, + slab_flags_t flags, unsigned int useroffset, + unsigned int usersize); +extern void create_boot_cache(struct kmem_cache *, const char *name, + unsigned int size, slab_flags_t flags, + unsigned int useroffset, unsigned int usersize); + +int slab_unmergeable(struct kmem_cache *s); +struct kmem_cache *find_mergeable(unsigned size, unsigned align, + slab_flags_t flags, const char *name, void (*ctor)(void *)); +#ifndef CONFIG_SLOB +struct kmem_cache * +__kmem_cache_alias(const char *name, unsigned int size, unsigned int align, + slab_flags_t flags, void (*ctor)(void *)); + +slab_flags_t kmem_cache_flags(unsigned int object_size, + slab_flags_t flags, const char *name); +#else +static inline struct kmem_cache * +__kmem_cache_alias(const char *name, unsigned int size, unsigned int align, + slab_flags_t flags, void (*ctor)(void *)) +{ return NULL; } + +static inline slab_flags_t kmem_cache_flags(unsigned int object_size, + slab_flags_t flags, const char *name) +{ + return flags; +} +#endif + + +/* Legal flag mask for kmem_cache_create(), for various configurations */ +#define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | \ + SLAB_CACHE_DMA32 | SLAB_PANIC | \ + SLAB_TYPESAFE_BY_RCU | SLAB_DEBUG_OBJECTS ) + +#if defined(CONFIG_DEBUG_SLAB) +#define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER) +#elif defined(CONFIG_SLUB_DEBUG) +#define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \ + SLAB_TRACE | SLAB_CONSISTENCY_CHECKS) +#else +#define SLAB_DEBUG_FLAGS (0) +#endif + +#if defined(CONFIG_SLAB) +#define SLAB_CACHE_FLAGS (SLAB_MEM_SPREAD | SLAB_NOLEAKTRACE | \ + SLAB_RECLAIM_ACCOUNT | SLAB_TEMPORARY | \ + SLAB_ACCOUNT) +#elif defined(CONFIG_SLUB) +#define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE | SLAB_RECLAIM_ACCOUNT | \ + SLAB_TEMPORARY | SLAB_ACCOUNT) +#else +#define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE) +#endif + +/* Common flags available with current configuration */ +#define CACHE_CREATE_MASK (SLAB_CORE_FLAGS | SLAB_DEBUG_FLAGS | SLAB_CACHE_FLAGS) + +/* Common flags permitted for kmem_cache_create */ +#define SLAB_FLAGS_PERMITTED (SLAB_CORE_FLAGS | \ + SLAB_RED_ZONE | \ + SLAB_POISON | \ + SLAB_STORE_USER | \ + SLAB_TRACE | \ + SLAB_CONSISTENCY_CHECKS | \ + SLAB_MEM_SPREAD | \ + SLAB_NOLEAKTRACE | \ + SLAB_RECLAIM_ACCOUNT | \ + SLAB_TEMPORARY | \ + SLAB_ACCOUNT) + +bool __kmem_cache_empty(struct kmem_cache *); +int __kmem_cache_shutdown(struct kmem_cache *); +void __kmem_cache_release(struct kmem_cache *); +int __kmem_cache_shrink(struct kmem_cache *); +void slab_kmem_cache_release(struct kmem_cache *); + +struct seq_file; +struct file; + +struct slabinfo { + unsigned long active_objs; + unsigned long num_objs; + unsigned long active_slabs; + unsigned long num_slabs; + unsigned long shared_avail; + unsigned int limit; + unsigned int batchcount; + unsigned int shared; + unsigned int objects_per_slab; + unsigned int cache_order; +}; + +void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo); +void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *s); +ssize_t slabinfo_write(struct file *file, const char __user *buffer, + size_t count, loff_t *ppos); + +/* + * Generic implementation of bulk operations + * These are useful for situations in which the allocator cannot + * perform optimizations. In that case segments of the object listed + * may be allocated or freed using these operations. + */ +void __kmem_cache_free_bulk(struct kmem_cache *, size_t, void **); +int __kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **); + +static inline int cache_vmstat_idx(struct kmem_cache *s) +{ + return (s->flags & SLAB_RECLAIM_ACCOUNT) ? + NR_SLAB_RECLAIMABLE_B : NR_SLAB_UNRECLAIMABLE_B; +} + +#ifdef CONFIG_SLUB_DEBUG +#ifdef CONFIG_SLUB_DEBUG_ON +DECLARE_STATIC_KEY_TRUE(slub_debug_enabled); +#else +DECLARE_STATIC_KEY_FALSE(slub_debug_enabled); +#endif +extern void print_tracking(struct kmem_cache *s, void *object); +#else +static inline void print_tracking(struct kmem_cache *s, void *object) +{ +} +#endif + +/* + * Returns true if any of the specified slub_debug flags is enabled for the + * cache. Use only for flags parsed by setup_slub_debug() as it also enables + * the static key. + */ +static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t flags) +{ +#ifdef CONFIG_SLUB_DEBUG + VM_WARN_ON_ONCE(!(flags & SLAB_DEBUG_FLAGS)); + if (static_branch_unlikely(&slub_debug_enabled)) + return s->flags & flags; +#endif + return false; +} + +#ifdef CONFIG_MEMCG_KMEM +static inline struct obj_cgroup **page_obj_cgroups(struct page *page) +{ + /* + * page->mem_cgroup and page->obj_cgroups are sharing the same + * space. To distinguish between them in case we don't know for sure + * that the page is a slab page (e.g. page_cgroup_ino()), let's + * always set the lowest bit of obj_cgroups. + */ + return (struct obj_cgroup **) + ((unsigned long)page->obj_cgroups & ~0x1UL); +} + +static inline bool page_has_obj_cgroups(struct page *page) +{ + return ((unsigned long)page->obj_cgroups & 0x1UL); +} + +int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s, + gfp_t gfp); + +static inline void memcg_free_page_obj_cgroups(struct page *page) +{ + kfree(page_obj_cgroups(page)); + page->obj_cgroups = NULL; +} + +static inline size_t obj_full_size(struct kmem_cache *s) +{ + /* + * For each accounted object there is an extra space which is used + * to store obj_cgroup membership. Charge it too. + */ + return s->size + sizeof(struct obj_cgroup *); +} + +/* + * Returns false if the allocation should fail. + */ +static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s, + struct obj_cgroup **objcgp, + size_t objects, gfp_t flags) +{ + struct obj_cgroup *objcg; + + if (!memcg_kmem_enabled()) + return true; + + if (!(flags & __GFP_ACCOUNT) && !(s->flags & SLAB_ACCOUNT)) + return true; + + objcg = get_obj_cgroup_from_current(); + if (!objcg) + return true; + + if (obj_cgroup_charge(objcg, flags, objects * obj_full_size(s))) { + obj_cgroup_put(objcg); + return false; + } + + *objcgp = objcg; + return true; +} + +static inline void mod_objcg_state(struct obj_cgroup *objcg, + struct pglist_data *pgdat, + int idx, int nr) +{ + struct mem_cgroup *memcg; + struct lruvec *lruvec; + + rcu_read_lock(); + memcg = obj_cgroup_memcg(objcg); + lruvec = mem_cgroup_lruvec(memcg, pgdat); + mod_memcg_lruvec_state(lruvec, idx, nr); + rcu_read_unlock(); +} + +static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s, + struct obj_cgroup *objcg, + gfp_t flags, size_t size, + void **p) +{ + struct page *page; + unsigned long off; + size_t i; + + if (!memcg_kmem_enabled() || !objcg) + return; + + for (i = 0; i < size; i++) { + if (likely(p[i])) { + page = virt_to_head_page(p[i]); + + if (!page_has_obj_cgroups(page) && + memcg_alloc_page_obj_cgroups(page, s, flags)) { + obj_cgroup_uncharge(objcg, obj_full_size(s)); + continue; + } + + off = obj_to_index(s, page, p[i]); + obj_cgroup_get(objcg); + page_obj_cgroups(page)[off] = objcg; + mod_objcg_state(objcg, page_pgdat(page), + cache_vmstat_idx(s), obj_full_size(s)); + } else { + obj_cgroup_uncharge(objcg, obj_full_size(s)); + } + } + obj_cgroup_put(objcg); +} + +static inline void memcg_slab_free_hook(struct kmem_cache *s_orig, + void **p, int objects) +{ + struct kmem_cache *s; + struct obj_cgroup *objcg; + struct page *page; + unsigned int off; + int i; + + if (!memcg_kmem_enabled()) + return; + + for (i = 0; i < objects; i++) { + if (unlikely(!p[i])) + continue; + + page = virt_to_head_page(p[i]); + if (!page_has_obj_cgroups(page)) + continue; + + if (!s_orig) + s = page->slab_cache; + else + s = s_orig; + + off = obj_to_index(s, page, p[i]); + objcg = page_obj_cgroups(page)[off]; + if (!objcg) + continue; + + page_obj_cgroups(page)[off] = NULL; + obj_cgroup_uncharge(objcg, obj_full_size(s)); + mod_objcg_state(objcg, page_pgdat(page), cache_vmstat_idx(s), + -obj_full_size(s)); + obj_cgroup_put(objcg); + } +} + +#else /* CONFIG_MEMCG_KMEM */ +static inline bool page_has_obj_cgroups(struct page *page) +{ + return false; +} + +static inline struct mem_cgroup *memcg_from_slab_obj(void *ptr) +{ + return NULL; +} + +static inline int memcg_alloc_page_obj_cgroups(struct page *page, + struct kmem_cache *s, gfp_t gfp) +{ + return 0; +} + +static inline void memcg_free_page_obj_cgroups(struct page *page) +{ +} + +static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s, + struct obj_cgroup **objcgp, + size_t objects, gfp_t flags) +{ + return true; +} + +static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s, + struct obj_cgroup *objcg, + gfp_t flags, size_t size, + void **p) +{ +} + +static inline void memcg_slab_free_hook(struct kmem_cache *s, + void **p, int objects) +{ +} +#endif /* CONFIG_MEMCG_KMEM */ + +static inline struct kmem_cache *virt_to_cache(const void *obj) +{ + struct page *page; + + page = virt_to_head_page(obj); + if (WARN_ONCE(!PageSlab(page), "%s: Object is not a Slab page!\n", + __func__)) + return NULL; + return page->slab_cache; +} + +static __always_inline void account_slab_page(struct page *page, int order, + struct kmem_cache *s) +{ + mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s), + PAGE_SIZE << order); +} + +static __always_inline void unaccount_slab_page(struct page *page, int order, + struct kmem_cache *s) +{ + if (memcg_kmem_enabled()) + memcg_free_page_obj_cgroups(page); + + mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s), + -(PAGE_SIZE << order)); +} + +static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x) +{ + struct kmem_cache *cachep; + + if (!IS_ENABLED(CONFIG_SLAB_FREELIST_HARDENED) && + !kmem_cache_debug_flags(s, SLAB_CONSISTENCY_CHECKS)) + return s; + + cachep = virt_to_cache(x); + if (WARN(cachep && cachep != s, + "%s: Wrong slab cache. %s but object is from %s\n", + __func__, s->name, cachep->name)) + print_tracking(cachep, x); + return cachep; +} + +static inline size_t slab_ksize(const struct kmem_cache *s) +{ +#ifndef CONFIG_SLUB + return s->object_size; + +#else /* CONFIG_SLUB */ +# ifdef CONFIG_SLUB_DEBUG + /* + * Debugging requires use of the padding between object + * and whatever may come after it. + */ + if (s->flags & (SLAB_RED_ZONE | SLAB_POISON)) + return s->object_size; +# endif + if (s->flags & SLAB_KASAN) + return s->object_size; + /* + * If we have the need to store the freelist pointer + * back there or track user information then we can + * only use the space before that information. + */ + if (s->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_STORE_USER)) + return s->inuse; + /* + * Else we can use all the padding etc for the allocation + */ + return s->size; +#endif +} + +static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s, + struct obj_cgroup **objcgp, + size_t size, gfp_t flags) +{ + flags &= gfp_allowed_mask; + + fs_reclaim_acquire(flags); + fs_reclaim_release(flags); + + might_sleep_if(gfpflags_allow_blocking(flags)); + + if (should_failslab(s, flags)) + return NULL; + + if (!memcg_slab_pre_alloc_hook(s, objcgp, size, flags)) + return NULL; + + return s; +} + +static inline void slab_post_alloc_hook(struct kmem_cache *s, + struct obj_cgroup *objcg, + gfp_t flags, size_t size, void **p) +{ + size_t i; + + flags &= gfp_allowed_mask; + for (i = 0; i < size; i++) { + p[i] = kasan_slab_alloc(s, p[i], flags); + /* As p[i] might get tagged, call kmemleak hook after KASAN. */ + kmemleak_alloc_recursive(p[i], s->object_size, 1, + s->flags, flags); + } + + memcg_slab_post_alloc_hook(s, objcg, flags, size, p); +} + +#ifndef CONFIG_SLOB +/* + * The slab lists for all objects. + */ +struct kmem_cache_node { + spinlock_t list_lock; + +#ifdef CONFIG_SLAB + struct list_head slabs_partial; /* partial list first, better asm code */ + struct list_head slabs_full; + struct list_head slabs_free; + unsigned long total_slabs; /* length of all slab lists */ + unsigned long free_slabs; /* length of free slab list only */ + unsigned long free_objects; + unsigned int free_limit; + unsigned int colour_next; /* Per-node cache coloring */ + struct array_cache *shared; /* shared per node */ + struct alien_cache **alien; /* on other nodes */ + unsigned long next_reap; /* updated without locking */ + int free_touched; /* updated without locking */ +#endif + +#ifdef CONFIG_SLUB + unsigned long nr_partial; + struct list_head partial; +#ifdef CONFIG_SLUB_DEBUG + atomic_long_t nr_slabs; + atomic_long_t total_objects; + struct list_head full; +#endif +#endif + +}; + +static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node) +{ + return s->node[node]; +} + +/* + * Iterator over all nodes. The body will be executed for each node that has + * a kmem_cache_node structure allocated (which is true for all online nodes) + */ +#define for_each_kmem_cache_node(__s, __node, __n) \ + for (__node = 0; __node < nr_node_ids; __node++) \ + if ((__n = get_node(__s, __node))) + +#endif + +void *slab_start(struct seq_file *m, loff_t *pos); +void *slab_next(struct seq_file *m, void *p, loff_t *pos); +void slab_stop(struct seq_file *m, void *p); +int memcg_slab_show(struct seq_file *m, void *p); + +#if defined(CONFIG_SLAB) || defined(CONFIG_SLUB_DEBUG) +void dump_unreclaimable_slab(void); +#else +static inline void dump_unreclaimable_slab(void) +{ +} +#endif + +void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr); + +#ifdef CONFIG_SLAB_FREELIST_RANDOM +int cache_random_seq_create(struct kmem_cache *cachep, unsigned int count, + gfp_t gfp); +void cache_random_seq_destroy(struct kmem_cache *cachep); +#else +static inline int cache_random_seq_create(struct kmem_cache *cachep, + unsigned int count, gfp_t gfp) +{ + return 0; +} +static inline void cache_random_seq_destroy(struct kmem_cache *cachep) { } +#endif /* CONFIG_SLAB_FREELIST_RANDOM */ + +static inline bool slab_want_init_on_alloc(gfp_t flags, struct kmem_cache *c) +{ + if (static_branch_unlikely(&init_on_alloc)) { + if (c->ctor) + return false; + if (c->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)) + return flags & __GFP_ZERO; + return true; + } + return flags & __GFP_ZERO; +} + +static inline bool slab_want_init_on_free(struct kmem_cache *c) +{ + if (static_branch_unlikely(&init_on_free)) + return !(c->ctor || + (c->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON))); + return false; +} + +#endif /* MM_SLAB_H */ diff --git a/mm/slab_common.c b/mm/slab_common.c new file mode 100644 index 000000000..ec832904f --- /dev/null +++ b/mm/slab_common.c @@ -0,0 +1,1197 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Slab allocator functions that are independent of the allocator strategy + * + * (C) 2012 Christoph Lameter + */ +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define CREATE_TRACE_POINTS +#include + +#include "internal.h" + +#include "slab.h" + +enum slab_state slab_state; +LIST_HEAD(slab_caches); +DEFINE_MUTEX(slab_mutex); +struct kmem_cache *kmem_cache; + +#ifdef CONFIG_HARDENED_USERCOPY +bool usercopy_fallback __ro_after_init = + IS_ENABLED(CONFIG_HARDENED_USERCOPY_FALLBACK); +module_param(usercopy_fallback, bool, 0400); +MODULE_PARM_DESC(usercopy_fallback, + "WARN instead of reject usercopy whitelist violations"); +#endif + +static LIST_HEAD(slab_caches_to_rcu_destroy); +static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work); +static DECLARE_WORK(slab_caches_to_rcu_destroy_work, + slab_caches_to_rcu_destroy_workfn); + +/* + * Set of flags that will prevent slab merging + */ +#define SLAB_NEVER_MERGE (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \ + SLAB_TRACE | SLAB_TYPESAFE_BY_RCU | SLAB_NOLEAKTRACE | \ + SLAB_FAILSLAB | SLAB_KASAN) + +#define SLAB_MERGE_SAME (SLAB_RECLAIM_ACCOUNT | SLAB_CACHE_DMA | \ + SLAB_CACHE_DMA32 | SLAB_ACCOUNT) + +/* + * Merge control. If this is set then no merging of slab caches will occur. + */ +static bool slab_nomerge = !IS_ENABLED(CONFIG_SLAB_MERGE_DEFAULT); + +static int __init setup_slab_nomerge(char *str) +{ + slab_nomerge = true; + return 1; +} + +#ifdef CONFIG_SLUB +__setup_param("slub_nomerge", slub_nomerge, setup_slab_nomerge, 0); +#endif + +__setup("slab_nomerge", setup_slab_nomerge); + +/* + * Determine the size of a slab object + */ +unsigned int kmem_cache_size(struct kmem_cache *s) +{ + return s->object_size; +} +EXPORT_SYMBOL(kmem_cache_size); + +#ifdef CONFIG_DEBUG_VM +static int kmem_cache_sanity_check(const char *name, unsigned int size) +{ + if (!name || in_interrupt() || size > KMALLOC_MAX_SIZE) { + pr_err("kmem_cache_create(%s) integrity check failed\n", name); + return -EINVAL; + } + + WARN_ON(strchr(name, ' ')); /* It confuses parsers */ + return 0; +} +#else +static inline int kmem_cache_sanity_check(const char *name, unsigned int size) +{ + return 0; +} +#endif + +void __kmem_cache_free_bulk(struct kmem_cache *s, size_t nr, void **p) +{ + size_t i; + + for (i = 0; i < nr; i++) { + if (s) + kmem_cache_free(s, p[i]); + else + kfree(p[i]); + } +} + +int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t nr, + void **p) +{ + size_t i; + + for (i = 0; i < nr; i++) { + void *x = p[i] = kmem_cache_alloc(s, flags); + if (!x) { + __kmem_cache_free_bulk(s, i, p); + return 0; + } + } + return i; +} + +/* + * Figure out what the alignment of the objects will be given a set of + * flags, a user specified alignment and the size of the objects. + */ +static unsigned int calculate_alignment(slab_flags_t flags, + unsigned int align, unsigned int size) +{ + /* + * If the user wants hardware cache aligned objects then follow that + * suggestion if the object is sufficiently large. + * + * The hardware cache alignment cannot override the specified + * alignment though. If that is greater then use it. + */ + if (flags & SLAB_HWCACHE_ALIGN) { + unsigned int ralign; + + ralign = cache_line_size(); + while (size <= ralign / 2) + ralign /= 2; + align = max(align, ralign); + } + + if (align < ARCH_SLAB_MINALIGN) + align = ARCH_SLAB_MINALIGN; + + return ALIGN(align, sizeof(void *)); +} + +/* + * Find a mergeable slab cache + */ +int slab_unmergeable(struct kmem_cache *s) +{ + if (slab_nomerge || (s->flags & SLAB_NEVER_MERGE)) + return 1; + + if (s->ctor) + return 1; + + if (s->usersize) + return 1; + + /* + * We may have set a slab to be unmergeable during bootstrap. + */ + if (s->refcount < 0) + return 1; + + return 0; +} + +struct kmem_cache *find_mergeable(unsigned int size, unsigned int align, + slab_flags_t flags, const char *name, void (*ctor)(void *)) +{ + struct kmem_cache *s; + + if (slab_nomerge) + return NULL; + + if (ctor) + return NULL; + + size = ALIGN(size, sizeof(void *)); + align = calculate_alignment(flags, align, size); + size = ALIGN(size, align); + flags = kmem_cache_flags(size, flags, name); + + if (flags & SLAB_NEVER_MERGE) + return NULL; + + list_for_each_entry_reverse(s, &slab_caches, list) { + if (slab_unmergeable(s)) + continue; + + if (size > s->size) + continue; + + if ((flags & SLAB_MERGE_SAME) != (s->flags & SLAB_MERGE_SAME)) + continue; + /* + * Check if alignment is compatible. + * Courtesy of Adrian Drzewiecki + */ + if ((s->size & ~(align - 1)) != s->size) + continue; + + if (s->size - size >= sizeof(void *)) + continue; + + if (IS_ENABLED(CONFIG_SLAB) && align && + (align > s->align || s->align % align)) + continue; + + return s; + } + return NULL; +} + +static struct kmem_cache *create_cache(const char *name, + unsigned int object_size, unsigned int align, + slab_flags_t flags, unsigned int useroffset, + unsigned int usersize, void (*ctor)(void *), + struct kmem_cache *root_cache) +{ + struct kmem_cache *s; + int err; + + if (WARN_ON(useroffset + usersize > object_size)) + useroffset = usersize = 0; + + err = -ENOMEM; + s = kmem_cache_zalloc(kmem_cache, GFP_KERNEL); + if (!s) + goto out; + + s->name = name; + s->size = s->object_size = object_size; + s->align = align; + s->ctor = ctor; + s->useroffset = useroffset; + s->usersize = usersize; + + err = __kmem_cache_create(s, flags); + if (err) + goto out_free_cache; + + s->refcount = 1; + list_add(&s->list, &slab_caches); +out: + if (err) + return ERR_PTR(err); + return s; + +out_free_cache: + kmem_cache_free(kmem_cache, s); + goto out; +} + +/** + * kmem_cache_create_usercopy - Create a cache with a region suitable + * for copying to userspace + * @name: A string which is used in /proc/slabinfo to identify this cache. + * @size: The size of objects to be created in this cache. + * @align: The required alignment for the objects. + * @flags: SLAB flags + * @useroffset: Usercopy region offset + * @usersize: Usercopy region size + * @ctor: A constructor for the objects. + * + * Cannot be called within a interrupt, but can be interrupted. + * The @ctor is run when new pages are allocated by the cache. + * + * The flags are + * + * %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5) + * to catch references to uninitialised memory. + * + * %SLAB_RED_ZONE - Insert `Red` zones around the allocated memory to check + * for buffer overruns. + * + * %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware + * cacheline. This can be beneficial if you're counting cycles as closely + * as davem. + * + * Return: a pointer to the cache on success, NULL on failure. + */ +struct kmem_cache * +kmem_cache_create_usercopy(const char *name, + unsigned int size, unsigned int align, + slab_flags_t flags, + unsigned int useroffset, unsigned int usersize, + void (*ctor)(void *)) +{ + struct kmem_cache *s = NULL; + const char *cache_name; + int err; + + get_online_cpus(); + get_online_mems(); + + mutex_lock(&slab_mutex); + + err = kmem_cache_sanity_check(name, size); + if (err) { + goto out_unlock; + } + + /* Refuse requests with allocator specific flags */ + if (flags & ~SLAB_FLAGS_PERMITTED) { + err = -EINVAL; + goto out_unlock; + } + + /* + * Some allocators will constraint the set of valid flags to a subset + * of all flags. We expect them to define CACHE_CREATE_MASK in this + * case, and we'll just provide them with a sanitized version of the + * passed flags. + */ + flags &= CACHE_CREATE_MASK; + + /* Fail closed on bad usersize of useroffset values. */ + if (WARN_ON(!usersize && useroffset) || + WARN_ON(size < usersize || size - usersize < useroffset)) + usersize = useroffset = 0; + + if (!usersize) + s = __kmem_cache_alias(name, size, align, flags, ctor); + if (s) + goto out_unlock; + + cache_name = kstrdup_const(name, GFP_KERNEL); + if (!cache_name) { + err = -ENOMEM; + goto out_unlock; + } + + s = create_cache(cache_name, size, + calculate_alignment(flags, align, size), + flags, useroffset, usersize, ctor, NULL); + if (IS_ERR(s)) { + err = PTR_ERR(s); + kfree_const(cache_name); + } + +out_unlock: + mutex_unlock(&slab_mutex); + + put_online_mems(); + put_online_cpus(); + + if (err) { + if (flags & SLAB_PANIC) + panic("kmem_cache_create: Failed to create slab '%s'. Error %d\n", + name, err); + else { + pr_warn("kmem_cache_create(%s) failed with error %d\n", + name, err); + dump_stack(); + } + return NULL; + } + return s; +} +EXPORT_SYMBOL(kmem_cache_create_usercopy); + +/** + * kmem_cache_create - Create a cache. + * @name: A string which is used in /proc/slabinfo to identify this cache. + * @size: The size of objects to be created in this cache. + * @align: The required alignment for the objects. + * @flags: SLAB flags + * @ctor: A constructor for the objects. + * + * Cannot be called within a interrupt, but can be interrupted. + * The @ctor is run when new pages are allocated by the cache. + * + * The flags are + * + * %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5) + * to catch references to uninitialised memory. + * + * %SLAB_RED_ZONE - Insert `Red` zones around the allocated memory to check + * for buffer overruns. + * + * %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware + * cacheline. This can be beneficial if you're counting cycles as closely + * as davem. + * + * Return: a pointer to the cache on success, NULL on failure. + */ +struct kmem_cache * +kmem_cache_create(const char *name, unsigned int size, unsigned int align, + slab_flags_t flags, void (*ctor)(void *)) +{ + return kmem_cache_create_usercopy(name, size, align, flags, 0, 0, + ctor); +} +EXPORT_SYMBOL(kmem_cache_create); + +static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work) +{ + LIST_HEAD(to_destroy); + struct kmem_cache *s, *s2; + + /* + * On destruction, SLAB_TYPESAFE_BY_RCU kmem_caches are put on the + * @slab_caches_to_rcu_destroy list. The slab pages are freed + * through RCU and the associated kmem_cache are dereferenced + * while freeing the pages, so the kmem_caches should be freed only + * after the pending RCU operations are finished. As rcu_barrier() + * is a pretty slow operation, we batch all pending destructions + * asynchronously. + */ + mutex_lock(&slab_mutex); + list_splice_init(&slab_caches_to_rcu_destroy, &to_destroy); + mutex_unlock(&slab_mutex); + + if (list_empty(&to_destroy)) + return; + + rcu_barrier(); + + list_for_each_entry_safe(s, s2, &to_destroy, list) { +#ifdef SLAB_SUPPORTS_SYSFS + sysfs_slab_release(s); +#else + slab_kmem_cache_release(s); +#endif + } +} + +static int shutdown_cache(struct kmem_cache *s) +{ + /* free asan quarantined objects */ + kasan_cache_shutdown(s); + + if (__kmem_cache_shutdown(s) != 0) + return -EBUSY; + + list_del(&s->list); + + if (s->flags & SLAB_TYPESAFE_BY_RCU) { +#ifdef SLAB_SUPPORTS_SYSFS + sysfs_slab_unlink(s); +#endif + list_add_tail(&s->list, &slab_caches_to_rcu_destroy); + schedule_work(&slab_caches_to_rcu_destroy_work); + } else { +#ifdef SLAB_SUPPORTS_SYSFS + sysfs_slab_unlink(s); + sysfs_slab_release(s); +#else + slab_kmem_cache_release(s); +#endif + } + + return 0; +} + +void slab_kmem_cache_release(struct kmem_cache *s) +{ + __kmem_cache_release(s); + kfree_const(s->name); + kmem_cache_free(kmem_cache, s); +} + +void kmem_cache_destroy(struct kmem_cache *s) +{ + int err; + + if (unlikely(!s)) + return; + + get_online_cpus(); + get_online_mems(); + + mutex_lock(&slab_mutex); + + s->refcount--; + if (s->refcount) + goto out_unlock; + + err = shutdown_cache(s); + if (err) { + pr_err("kmem_cache_destroy %s: Slab cache still has objects\n", + s->name); + dump_stack(); + } +out_unlock: + mutex_unlock(&slab_mutex); + + put_online_mems(); + put_online_cpus(); +} +EXPORT_SYMBOL(kmem_cache_destroy); + +/** + * kmem_cache_shrink - Shrink a cache. + * @cachep: The cache to shrink. + * + * Releases as many slabs as possible for a cache. + * To help debugging, a zero exit status indicates all slabs were released. + * + * Return: %0 if all slabs were released, non-zero otherwise + */ +int kmem_cache_shrink(struct kmem_cache *cachep) +{ + int ret; + + get_online_cpus(); + get_online_mems(); + kasan_cache_shrink(cachep); + ret = __kmem_cache_shrink(cachep); + put_online_mems(); + put_online_cpus(); + return ret; +} +EXPORT_SYMBOL(kmem_cache_shrink); + +bool slab_is_available(void) +{ + return slab_state >= UP; +} + +#ifndef CONFIG_SLOB +/* Create a cache during boot when no slab services are available yet */ +void __init create_boot_cache(struct kmem_cache *s, const char *name, + unsigned int size, slab_flags_t flags, + unsigned int useroffset, unsigned int usersize) +{ + int err; + unsigned int align = ARCH_KMALLOC_MINALIGN; + + s->name = name; + s->size = s->object_size = size; + + /* + * For power of two sizes, guarantee natural alignment for kmalloc + * caches, regardless of SL*B debugging options. + */ + if (is_power_of_2(size)) + align = max(align, size); + s->align = calculate_alignment(flags, align, size); + + s->useroffset = useroffset; + s->usersize = usersize; + + err = __kmem_cache_create(s, flags); + + if (err) + panic("Creation of kmalloc slab %s size=%u failed. Reason %d\n", + name, size, err); + + s->refcount = -1; /* Exempt from merging for now */ +} + +struct kmem_cache *__init create_kmalloc_cache(const char *name, + unsigned int size, slab_flags_t flags, + unsigned int useroffset, unsigned int usersize) +{ + struct kmem_cache *s = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT); + + if (!s) + panic("Out of memory when creating slab %s\n", name); + + create_boot_cache(s, name, size, flags, useroffset, usersize); + list_add(&s->list, &slab_caches); + s->refcount = 1; + return s; +} + +struct kmem_cache * +kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1] __ro_after_init = +{ /* initialization for https://bugs.llvm.org/show_bug.cgi?id=42570 */ }; +EXPORT_SYMBOL(kmalloc_caches); + +/* + * Conversion table for small slabs sizes / 8 to the index in the + * kmalloc array. This is necessary for slabs < 192 since we have non power + * of two cache sizes there. The size of larger slabs can be determined using + * fls. + */ +static u8 size_index[24] __ro_after_init = { + 3, /* 8 */ + 4, /* 16 */ + 5, /* 24 */ + 5, /* 32 */ + 6, /* 40 */ + 6, /* 48 */ + 6, /* 56 */ + 6, /* 64 */ + 1, /* 72 */ + 1, /* 80 */ + 1, /* 88 */ + 1, /* 96 */ + 7, /* 104 */ + 7, /* 112 */ + 7, /* 120 */ + 7, /* 128 */ + 2, /* 136 */ + 2, /* 144 */ + 2, /* 152 */ + 2, /* 160 */ + 2, /* 168 */ + 2, /* 176 */ + 2, /* 184 */ + 2 /* 192 */ +}; + +static inline unsigned int size_index_elem(unsigned int bytes) +{ + return (bytes - 1) / 8; +} + +/* + * Find the kmem_cache structure that serves a given size of + * allocation + */ +struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags) +{ + unsigned int index; + + if (size <= 192) { + if (!size) + return ZERO_SIZE_PTR; + + index = size_index[size_index_elem(size)]; + } else { + if (WARN_ON_ONCE(size > KMALLOC_MAX_CACHE_SIZE)) + return NULL; + index = fls(size - 1); + } + + return kmalloc_caches[kmalloc_type(flags)][index]; +} + +#ifdef CONFIG_ZONE_DMA +#define INIT_KMALLOC_INFO(__size, __short_size) \ +{ \ + .name[KMALLOC_NORMAL] = "kmalloc-" #__short_size, \ + .name[KMALLOC_RECLAIM] = "kmalloc-rcl-" #__short_size, \ + .name[KMALLOC_DMA] = "dma-kmalloc-" #__short_size, \ + .size = __size, \ +} +#else +#define INIT_KMALLOC_INFO(__size, __short_size) \ +{ \ + .name[KMALLOC_NORMAL] = "kmalloc-" #__short_size, \ + .name[KMALLOC_RECLAIM] = "kmalloc-rcl-" #__short_size, \ + .size = __size, \ +} +#endif + +/* + * kmalloc_info[] is to make slub_debug=,kmalloc-xx option work at boot time. + * kmalloc_index() supports up to 2^26=64MB, so the final entry of the table is + * kmalloc-67108864. + */ +const struct kmalloc_info_struct kmalloc_info[] __initconst = { + INIT_KMALLOC_INFO(0, 0), + INIT_KMALLOC_INFO(96, 96), + INIT_KMALLOC_INFO(192, 192), + INIT_KMALLOC_INFO(8, 8), + INIT_KMALLOC_INFO(16, 16), + INIT_KMALLOC_INFO(32, 32), + INIT_KMALLOC_INFO(64, 64), + INIT_KMALLOC_INFO(128, 128), + INIT_KMALLOC_INFO(256, 256), + INIT_KMALLOC_INFO(512, 512), + INIT_KMALLOC_INFO(1024, 1k), + INIT_KMALLOC_INFO(2048, 2k), + INIT_KMALLOC_INFO(4096, 4k), + INIT_KMALLOC_INFO(8192, 8k), + INIT_KMALLOC_INFO(16384, 16k), + INIT_KMALLOC_INFO(32768, 32k), + INIT_KMALLOC_INFO(65536, 64k), + INIT_KMALLOC_INFO(131072, 128k), + INIT_KMALLOC_INFO(262144, 256k), + INIT_KMALLOC_INFO(524288, 512k), + INIT_KMALLOC_INFO(1048576, 1M), + INIT_KMALLOC_INFO(2097152, 2M), + INIT_KMALLOC_INFO(4194304, 4M), + INIT_KMALLOC_INFO(8388608, 8M), + INIT_KMALLOC_INFO(16777216, 16M), + INIT_KMALLOC_INFO(33554432, 32M), + INIT_KMALLOC_INFO(67108864, 64M) +}; + +/* + * Patch up the size_index table if we have strange large alignment + * requirements for the kmalloc array. This is only the case for + * MIPS it seems. The standard arches will not generate any code here. + * + * Largest permitted alignment is 256 bytes due to the way we + * handle the index determination for the smaller caches. + * + * Make sure that nothing crazy happens if someone starts tinkering + * around with ARCH_KMALLOC_MINALIGN + */ +void __init setup_kmalloc_cache_index_table(void) +{ + unsigned int i; + + BUILD_BUG_ON(KMALLOC_MIN_SIZE > 256 || + (KMALLOC_MIN_SIZE & (KMALLOC_MIN_SIZE - 1))); + + for (i = 8; i < KMALLOC_MIN_SIZE; i += 8) { + unsigned int elem = size_index_elem(i); + + if (elem >= ARRAY_SIZE(size_index)) + break; + size_index[elem] = KMALLOC_SHIFT_LOW; + } + + if (KMALLOC_MIN_SIZE >= 64) { + /* + * The 96 byte size cache is not used if the alignment + * is 64 byte. + */ + for (i = 64 + 8; i <= 96; i += 8) + size_index[size_index_elem(i)] = 7; + + } + + if (KMALLOC_MIN_SIZE >= 128) { + /* + * The 192 byte sized cache is not used if the alignment + * is 128 byte. Redirect kmalloc to use the 256 byte cache + * instead. + */ + for (i = 128 + 8; i <= 192; i += 8) + size_index[size_index_elem(i)] = 8; + } +} + +static void __init +new_kmalloc_cache(int idx, enum kmalloc_cache_type type, slab_flags_t flags) +{ + if (type == KMALLOC_RECLAIM) + flags |= SLAB_RECLAIM_ACCOUNT; + + kmalloc_caches[type][idx] = create_kmalloc_cache( + kmalloc_info[idx].name[type], + kmalloc_info[idx].size, flags, 0, + kmalloc_info[idx].size); +} + +/* + * Create the kmalloc array. Some of the regular kmalloc arrays + * may already have been created because they were needed to + * enable allocations for slab creation. + */ +void __init create_kmalloc_caches(slab_flags_t flags) +{ + int i; + enum kmalloc_cache_type type; + + for (type = KMALLOC_NORMAL; type <= KMALLOC_RECLAIM; type++) { + for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) { + if (!kmalloc_caches[type][i]) + new_kmalloc_cache(i, type, flags); + + /* + * Caches that are not of the two-to-the-power-of size. + * These have to be created immediately after the + * earlier power of two caches + */ + if (KMALLOC_MIN_SIZE <= 32 && i == 6 && + !kmalloc_caches[type][1]) + new_kmalloc_cache(1, type, flags); + if (KMALLOC_MIN_SIZE <= 64 && i == 7 && + !kmalloc_caches[type][2]) + new_kmalloc_cache(2, type, flags); + } + } + + /* Kmalloc array is now usable */ + slab_state = UP; + +#ifdef CONFIG_ZONE_DMA + for (i = 0; i <= KMALLOC_SHIFT_HIGH; i++) { + struct kmem_cache *s = kmalloc_caches[KMALLOC_NORMAL][i]; + + if (s) { + kmalloc_caches[KMALLOC_DMA][i] = create_kmalloc_cache( + kmalloc_info[i].name[KMALLOC_DMA], + kmalloc_info[i].size, + SLAB_CACHE_DMA | flags, 0, + kmalloc_info[i].size); + } + } +#endif +} +#endif /* !CONFIG_SLOB */ + +gfp_t kmalloc_fix_flags(gfp_t flags) +{ + gfp_t invalid_mask = flags & GFP_SLAB_BUG_MASK; + + flags &= ~GFP_SLAB_BUG_MASK; + pr_warn("Unexpected gfp: %#x (%pGg). Fixing up to gfp: %#x (%pGg). Fix your code!\n", + invalid_mask, &invalid_mask, flags, &flags); + dump_stack(); + + return flags; +} + +/* + * To avoid unnecessary overhead, we pass through large allocation requests + * directly to the page allocator. We use __GFP_COMP, because we will need to + * know the allocation order to free the pages properly in kfree. + */ +void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) +{ + void *ret = NULL; + struct page *page; + + if (unlikely(flags & GFP_SLAB_BUG_MASK)) + flags = kmalloc_fix_flags(flags); + + flags |= __GFP_COMP; + page = alloc_pages(flags, order); + if (likely(page)) { + ret = page_address(page); + mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B, + PAGE_SIZE << order); + } + ret = kasan_kmalloc_large(ret, size, flags); + /* As ret might get tagged, call kmemleak hook after KASAN. */ + kmemleak_alloc(ret, size, 1, flags); + return ret; +} +EXPORT_SYMBOL(kmalloc_order); + +#ifdef CONFIG_TRACING +void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) +{ + void *ret = kmalloc_order(size, flags, order); + trace_kmalloc(_RET_IP_, ret, size, PAGE_SIZE << order, flags); + return ret; +} +EXPORT_SYMBOL(kmalloc_order_trace); +#endif + +#ifdef CONFIG_SLAB_FREELIST_RANDOM +/* Randomize a generic freelist */ +static void freelist_randomize(struct rnd_state *state, unsigned int *list, + unsigned int count) +{ + unsigned int rand; + unsigned int i; + + for (i = 0; i < count; i++) + list[i] = i; + + /* Fisher-Yates shuffle */ + for (i = count - 1; i > 0; i--) { + rand = prandom_u32_state(state); + rand %= (i + 1); + swap(list[i], list[rand]); + } +} + +/* Create a random sequence per cache */ +int cache_random_seq_create(struct kmem_cache *cachep, unsigned int count, + gfp_t gfp) +{ + struct rnd_state state; + + if (count < 2 || cachep->random_seq) + return 0; + + cachep->random_seq = kcalloc(count, sizeof(unsigned int), gfp); + if (!cachep->random_seq) + return -ENOMEM; + + /* Get best entropy at this stage of boot */ + prandom_seed_state(&state, get_random_long()); + + freelist_randomize(&state, cachep->random_seq, count); + return 0; +} + +/* Destroy the per-cache random freelist sequence */ +void cache_random_seq_destroy(struct kmem_cache *cachep) +{ + kfree(cachep->random_seq); + cachep->random_seq = NULL; +} +#endif /* CONFIG_SLAB_FREELIST_RANDOM */ + +#if defined(CONFIG_SLAB) || defined(CONFIG_SLUB_DEBUG) +#ifdef CONFIG_SLAB +#define SLABINFO_RIGHTS (0600) +#else +#define SLABINFO_RIGHTS (0400) +#endif + +static void print_slabinfo_header(struct seq_file *m) +{ + /* + * Output format version, so at least we can change it + * without _too_ many complaints. + */ +#ifdef CONFIG_DEBUG_SLAB + seq_puts(m, "slabinfo - version: 2.1 (statistics)\n"); +#else + seq_puts(m, "slabinfo - version: 2.1\n"); +#endif + seq_puts(m, "# name "); + seq_puts(m, " : tunables "); + seq_puts(m, " : slabdata "); +#ifdef CONFIG_DEBUG_SLAB + seq_puts(m, " : globalstat "); + seq_puts(m, " : cpustat "); +#endif + seq_putc(m, '\n'); +} + +void *slab_start(struct seq_file *m, loff_t *pos) +{ + mutex_lock(&slab_mutex); + return seq_list_start(&slab_caches, *pos); +} + +void *slab_next(struct seq_file *m, void *p, loff_t *pos) +{ + return seq_list_next(p, &slab_caches, pos); +} + +void slab_stop(struct seq_file *m, void *p) +{ + mutex_unlock(&slab_mutex); +} + +static void cache_show(struct kmem_cache *s, struct seq_file *m) +{ + struct slabinfo sinfo; + + memset(&sinfo, 0, sizeof(sinfo)); + get_slabinfo(s, &sinfo); + + seq_printf(m, "%-17s %6lu %6lu %6u %4u %4d", + s->name, sinfo.active_objs, sinfo.num_objs, s->size, + sinfo.objects_per_slab, (1 << sinfo.cache_order)); + + seq_printf(m, " : tunables %4u %4u %4u", + sinfo.limit, sinfo.batchcount, sinfo.shared); + seq_printf(m, " : slabdata %6lu %6lu %6lu", + sinfo.active_slabs, sinfo.num_slabs, sinfo.shared_avail); + slabinfo_show_stats(m, s); + seq_putc(m, '\n'); +} + +static int slab_show(struct seq_file *m, void *p) +{ + struct kmem_cache *s = list_entry(p, struct kmem_cache, list); + + if (p == slab_caches.next) + print_slabinfo_header(m); + cache_show(s, m); + return 0; +} + +void dump_unreclaimable_slab(void) +{ + struct kmem_cache *s, *s2; + struct slabinfo sinfo; + + /* + * Here acquiring slab_mutex is risky since we don't prefer to get + * sleep in oom path. But, without mutex hold, it may introduce a + * risk of crash. + * Use mutex_trylock to protect the list traverse, dump nothing + * without acquiring the mutex. + */ + if (!mutex_trylock(&slab_mutex)) { + pr_warn("excessive unreclaimable slab but cannot dump stats\n"); + return; + } + + pr_info("Unreclaimable slab info:\n"); + pr_info("Name Used Total\n"); + + list_for_each_entry_safe(s, s2, &slab_caches, list) { + if (s->flags & SLAB_RECLAIM_ACCOUNT) + continue; + + get_slabinfo(s, &sinfo); + + if (sinfo.num_objs > 0) + pr_info("%-17s %10luKB %10luKB\n", s->name, + (sinfo.active_objs * s->size) / 1024, + (sinfo.num_objs * s->size) / 1024); + } + mutex_unlock(&slab_mutex); +} + +#if defined(CONFIG_MEMCG_KMEM) +int memcg_slab_show(struct seq_file *m, void *p) +{ + /* + * Deprecated. + * Please, take a look at tools/cgroup/slabinfo.py . + */ + return 0; +} +#endif + +/* + * slabinfo_op - iterator that generates /proc/slabinfo + * + * Output layout: + * cache-name + * num-active-objs + * total-objs + * object size + * num-active-slabs + * total-slabs + * num-pages-per-slab + * + further values on SMP and with statistics enabled + */ +static const struct seq_operations slabinfo_op = { + .start = slab_start, + .next = slab_next, + .stop = slab_stop, + .show = slab_show, +}; + +static int slabinfo_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &slabinfo_op); +} + +static const struct proc_ops slabinfo_proc_ops = { + .proc_flags = PROC_ENTRY_PERMANENT, + .proc_open = slabinfo_open, + .proc_read = seq_read, + .proc_write = slabinfo_write, + .proc_lseek = seq_lseek, + .proc_release = seq_release, +}; + +static int __init slab_proc_init(void) +{ + proc_create("slabinfo", SLABINFO_RIGHTS, NULL, &slabinfo_proc_ops); + return 0; +} +module_init(slab_proc_init); + +#endif /* CONFIG_SLAB || CONFIG_SLUB_DEBUG */ + +static __always_inline void *__do_krealloc(const void *p, size_t new_size, + gfp_t flags) +{ + void *ret; + size_t ks; + + ks = ksize(p); + + if (ks >= new_size) { + p = kasan_krealloc((void *)p, new_size, flags); + return (void *)p; + } + + ret = kmalloc_track_caller(new_size, flags); + if (ret && p) + memcpy(ret, p, ks); + + return ret; +} + +/** + * krealloc - reallocate memory. The contents will remain unchanged. + * @p: object to reallocate memory for. + * @new_size: how many bytes of memory are required. + * @flags: the type of memory to allocate. + * + * The contents of the object pointed to are preserved up to the + * lesser of the new and old sizes. If @p is %NULL, krealloc() + * behaves exactly like kmalloc(). If @new_size is 0 and @p is not a + * %NULL pointer, the object pointed to is freed. + * + * Return: pointer to the allocated memory or %NULL in case of error + */ +void *krealloc(const void *p, size_t new_size, gfp_t flags) +{ + void *ret; + + if (unlikely(!new_size)) { + kfree(p); + return ZERO_SIZE_PTR; + } + + ret = __do_krealloc(p, new_size, flags); + if (ret && kasan_reset_tag(p) != kasan_reset_tag(ret)) + kfree(p); + + return ret; +} +EXPORT_SYMBOL(krealloc); + +/** + * kfree_sensitive - Clear sensitive information in memory before freeing + * @p: object to free memory of + * + * The memory of the object @p points to is zeroed before freed. + * If @p is %NULL, kfree_sensitive() does nothing. + * + * Note: this function zeroes the whole allocated buffer which can be a good + * deal bigger than the requested buffer size passed to kmalloc(). So be + * careful when using this function in performance sensitive code. + */ +void kfree_sensitive(const void *p) +{ + size_t ks; + void *mem = (void *)p; + + ks = ksize(mem); + if (ks) + memzero_explicit(mem, ks); + kfree(mem); +} +EXPORT_SYMBOL(kfree_sensitive); + +/** + * ksize - get the actual amount of memory allocated for a given object + * @objp: Pointer to the object + * + * kmalloc may internally round up allocations and return more memory + * than requested. ksize() can be used to determine the actual amount of + * memory allocated. The caller may use this additional memory, even though + * a smaller amount of memory was initially specified with the kmalloc call. + * The caller must guarantee that objp points to a valid object previously + * allocated with either kmalloc() or kmem_cache_alloc(). The object + * must not be freed during the duration of the call. + * + * Return: size of the actual memory used by @objp in bytes + */ +size_t ksize(const void *objp) +{ + size_t size; + + /* + * We need to check that the pointed to object is valid, and only then + * unpoison the shadow memory below. We use __kasan_check_read(), to + * generate a more useful report at the time ksize() is called (rather + * than later where behaviour is undefined due to potential + * use-after-free or double-free). + * + * If the pointed to memory is invalid we return 0, to avoid users of + * ksize() writing to and potentially corrupting the memory region. + * + * We want to perform the check before __ksize(), to avoid potentially + * crashing in __ksize() due to accessing invalid metadata. + */ + if (unlikely(ZERO_OR_NULL_PTR(objp)) || !__kasan_check_read(objp, 1)) + return 0; + + size = __ksize(objp); + /* + * We assume that ksize callers could use whole allocated area, + * so we need to unpoison this area. + */ + kasan_unpoison_shadow(objp, size); + return size; +} +EXPORT_SYMBOL(ksize); + +/* Tracepoints definitions. */ +EXPORT_TRACEPOINT_SYMBOL(kmalloc); +EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc); +EXPORT_TRACEPOINT_SYMBOL(kmalloc_node); +EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc_node); +EXPORT_TRACEPOINT_SYMBOL(kfree); +EXPORT_TRACEPOINT_SYMBOL(kmem_cache_free); + +int should_failslab(struct kmem_cache *s, gfp_t gfpflags) +{ + if (__should_failslab(s, gfpflags)) + return -ENOMEM; + return 0; +} +ALLOW_ERROR_INJECTION(should_failslab, ERRNO); diff --git a/mm/slob.c b/mm/slob.c new file mode 100644 index 000000000..7cc9805c8 --- /dev/null +++ b/mm/slob.c @@ -0,0 +1,720 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * SLOB Allocator: Simple List Of Blocks + * + * Matt Mackall 12/30/03 + * + * NUMA support by Paul Mundt, 2007. + * + * How SLOB works: + * + * The core of SLOB is a traditional K&R style heap allocator, with + * support for returning aligned objects. The granularity of this + * allocator is as little as 2 bytes, however typically most architectures + * will require 4 bytes on 32-bit and 8 bytes on 64-bit. + * + * The slob heap is a set of linked list of pages from alloc_pages(), + * and within each page, there is a singly-linked list of free blocks + * (slob_t). The heap is grown on demand. To reduce fragmentation, + * heap pages are segregated into three lists, with objects less than + * 256 bytes, objects less than 1024 bytes, and all other objects. + * + * Allocation from heap involves first searching for a page with + * sufficient free blocks (using a next-fit-like approach) followed by + * a first-fit scan of the page. Deallocation inserts objects back + * into the free list in address order, so this is effectively an + * address-ordered first fit. + * + * Above this is an implementation of kmalloc/kfree. Blocks returned + * from kmalloc are prepended with a 4-byte header with the kmalloc size. + * If kmalloc is asked for objects of PAGE_SIZE or larger, it calls + * alloc_pages() directly, allocating compound pages so the page order + * does not have to be separately tracked. + * These objects are detected in kfree() because PageSlab() + * is false for them. + * + * SLAB is emulated on top of SLOB by simply calling constructors and + * destructors for every SLAB allocation. Objects are returned with the + * 4-byte alignment unless the SLAB_HWCACHE_ALIGN flag is set, in which + * case the low-level allocator will fragment blocks to create the proper + * alignment. Again, objects of page-size or greater are allocated by + * calling alloc_pages(). As SLAB objects know their size, no separate + * size bookkeeping is necessary and there is essentially no allocation + * space overhead, and compound pages aren't needed for multi-page + * allocations. + * + * NUMA support in SLOB is fairly simplistic, pushing most of the real + * logic down to the page allocator, and simply doing the node accounting + * on the upper levels. In the event that a node id is explicitly + * provided, __alloc_pages_node() with the specified node id is used + * instead. The common case (or when the node id isn't explicitly provided) + * will default to the current node, as per numa_node_id(). + * + * Node aware pages are still inserted in to the global freelist, and + * these are scanned for by matching against the node id encoded in the + * page flags. As a result, block allocations that can be satisfied from + * the freelist will only be done so on pages residing on the same node, + * in order to prevent random node placement. + */ + +#include +#include + +#include +#include /* struct reclaim_state */ +#include +#include +#include +#include +#include +#include + +#include + +#include + +#include "slab.h" +/* + * slob_block has a field 'units', which indicates size of block if +ve, + * or offset of next block if -ve (in SLOB_UNITs). + * + * Free blocks of size 1 unit simply contain the offset of the next block. + * Those with larger size contain their size in the first SLOB_UNIT of + * memory, and the offset of the next free block in the second SLOB_UNIT. + */ +#if PAGE_SIZE <= (32767 * 2) +typedef s16 slobidx_t; +#else +typedef s32 slobidx_t; +#endif + +struct slob_block { + slobidx_t units; +}; +typedef struct slob_block slob_t; + +/* + * All partially free slob pages go on these lists. + */ +#define SLOB_BREAK1 256 +#define SLOB_BREAK2 1024 +static LIST_HEAD(free_slob_small); +static LIST_HEAD(free_slob_medium); +static LIST_HEAD(free_slob_large); + +/* + * slob_page_free: true for pages on free_slob_pages list. + */ +static inline int slob_page_free(struct page *sp) +{ + return PageSlobFree(sp); +} + +static void set_slob_page_free(struct page *sp, struct list_head *list) +{ + list_add(&sp->slab_list, list); + __SetPageSlobFree(sp); +} + +static inline void clear_slob_page_free(struct page *sp) +{ + list_del(&sp->slab_list); + __ClearPageSlobFree(sp); +} + +#define SLOB_UNIT sizeof(slob_t) +#define SLOB_UNITS(size) DIV_ROUND_UP(size, SLOB_UNIT) + +/* + * struct slob_rcu is inserted at the tail of allocated slob blocks, which + * were created with a SLAB_TYPESAFE_BY_RCU slab. slob_rcu is used to free + * the block using call_rcu. + */ +struct slob_rcu { + struct rcu_head head; + int size; +}; + +/* + * slob_lock protects all slob allocator structures. + */ +static DEFINE_SPINLOCK(slob_lock); + +/* + * Encode the given size and next info into a free slob block s. + */ +static void set_slob(slob_t *s, slobidx_t size, slob_t *next) +{ + slob_t *base = (slob_t *)((unsigned long)s & PAGE_MASK); + slobidx_t offset = next - base; + + if (size > 1) { + s[0].units = size; + s[1].units = offset; + } else + s[0].units = -offset; +} + +/* + * Return the size of a slob block. + */ +static slobidx_t slob_units(slob_t *s) +{ + if (s->units > 0) + return s->units; + return 1; +} + +/* + * Return the next free slob block pointer after this one. + */ +static slob_t *slob_next(slob_t *s) +{ + slob_t *base = (slob_t *)((unsigned long)s & PAGE_MASK); + slobidx_t next; + + if (s[0].units < 0) + next = -s[0].units; + else + next = s[1].units; + return base+next; +} + +/* + * Returns true if s is the last free block in its page. + */ +static int slob_last(slob_t *s) +{ + return !((unsigned long)slob_next(s) & ~PAGE_MASK); +} + +static void *slob_new_pages(gfp_t gfp, int order, int node) +{ + struct page *page; + +#ifdef CONFIG_NUMA + if (node != NUMA_NO_NODE) + page = __alloc_pages_node(node, gfp, order); + else +#endif + page = alloc_pages(gfp, order); + + if (!page) + return NULL; + + mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE_B, + PAGE_SIZE << order); + return page_address(page); +} + +static void slob_free_pages(void *b, int order) +{ + struct page *sp = virt_to_page(b); + + if (current->reclaim_state) + current->reclaim_state->reclaimed_slab += 1 << order; + + mod_node_page_state(page_pgdat(sp), NR_SLAB_UNRECLAIMABLE_B, + -(PAGE_SIZE << order)); + __free_pages(sp, order); +} + +/* + * slob_page_alloc() - Allocate a slob block within a given slob_page sp. + * @sp: Page to look in. + * @size: Size of the allocation. + * @align: Allocation alignment. + * @align_offset: Offset in the allocated block that will be aligned. + * @page_removed_from_list: Return parameter. + * + * Tries to find a chunk of memory at least @size bytes big within @page. + * + * Return: Pointer to memory if allocated, %NULL otherwise. If the + * allocation fills up @page then the page is removed from the + * freelist, in this case @page_removed_from_list will be set to + * true (set to false otherwise). + */ +static void *slob_page_alloc(struct page *sp, size_t size, int align, + int align_offset, bool *page_removed_from_list) +{ + slob_t *prev, *cur, *aligned = NULL; + int delta = 0, units = SLOB_UNITS(size); + + *page_removed_from_list = false; + for (prev = NULL, cur = sp->freelist; ; prev = cur, cur = slob_next(cur)) { + slobidx_t avail = slob_units(cur); + + /* + * 'aligned' will hold the address of the slob block so that the + * address 'aligned'+'align_offset' is aligned according to the + * 'align' parameter. This is for kmalloc() which prepends the + * allocated block with its size, so that the block itself is + * aligned when needed. + */ + if (align) { + aligned = (slob_t *) + (ALIGN((unsigned long)cur + align_offset, align) + - align_offset); + delta = aligned - cur; + } + if (avail >= units + delta) { /* room enough? */ + slob_t *next; + + if (delta) { /* need to fragment head to align? */ + next = slob_next(cur); + set_slob(aligned, avail - delta, next); + set_slob(cur, delta, aligned); + prev = cur; + cur = aligned; + avail = slob_units(cur); + } + + next = slob_next(cur); + if (avail == units) { /* exact fit? unlink. */ + if (prev) + set_slob(prev, slob_units(prev), next); + else + sp->freelist = next; + } else { /* fragment */ + if (prev) + set_slob(prev, slob_units(prev), cur + units); + else + sp->freelist = cur + units; + set_slob(cur + units, avail - units, next); + } + + sp->units -= units; + if (!sp->units) { + clear_slob_page_free(sp); + *page_removed_from_list = true; + } + return cur; + } + if (slob_last(cur)) + return NULL; + } +} + +/* + * slob_alloc: entry point into the slob allocator. + */ +static void *slob_alloc(size_t size, gfp_t gfp, int align, int node, + int align_offset) +{ + struct page *sp; + struct list_head *slob_list; + slob_t *b = NULL; + unsigned long flags; + bool _unused; + + if (size < SLOB_BREAK1) + slob_list = &free_slob_small; + else if (size < SLOB_BREAK2) + slob_list = &free_slob_medium; + else + slob_list = &free_slob_large; + + spin_lock_irqsave(&slob_lock, flags); + /* Iterate through each partially free page, try to find room */ + list_for_each_entry(sp, slob_list, slab_list) { + bool page_removed_from_list = false; +#ifdef CONFIG_NUMA + /* + * If there's a node specification, search for a partial + * page with a matching node id in the freelist. + */ + if (node != NUMA_NO_NODE && page_to_nid(sp) != node) + continue; +#endif + /* Enough room on this page? */ + if (sp->units < SLOB_UNITS(size)) + continue; + + b = slob_page_alloc(sp, size, align, align_offset, &page_removed_from_list); + if (!b) + continue; + + /* + * If slob_page_alloc() removed sp from the list then we + * cannot call list functions on sp. If so allocation + * did not fragment the page anyway so optimisation is + * unnecessary. + */ + if (!page_removed_from_list) { + /* + * Improve fragment distribution and reduce our average + * search time by starting our next search here. (see + * Knuth vol 1, sec 2.5, pg 449) + */ + if (!list_is_first(&sp->slab_list, slob_list)) + list_rotate_to_front(&sp->slab_list, slob_list); + } + break; + } + spin_unlock_irqrestore(&slob_lock, flags); + + /* Not enough space: must allocate a new page */ + if (!b) { + b = slob_new_pages(gfp & ~__GFP_ZERO, 0, node); + if (!b) + return NULL; + sp = virt_to_page(b); + __SetPageSlab(sp); + + spin_lock_irqsave(&slob_lock, flags); + sp->units = SLOB_UNITS(PAGE_SIZE); + sp->freelist = b; + INIT_LIST_HEAD(&sp->slab_list); + set_slob(b, SLOB_UNITS(PAGE_SIZE), b + SLOB_UNITS(PAGE_SIZE)); + set_slob_page_free(sp, slob_list); + b = slob_page_alloc(sp, size, align, align_offset, &_unused); + BUG_ON(!b); + spin_unlock_irqrestore(&slob_lock, flags); + } + if (unlikely(gfp & __GFP_ZERO)) + memset(b, 0, size); + return b; +} + +/* + * slob_free: entry point into the slob allocator. + */ +static void slob_free(void *block, int size) +{ + struct page *sp; + slob_t *prev, *next, *b = (slob_t *)block; + slobidx_t units; + unsigned long flags; + struct list_head *slob_list; + + if (unlikely(ZERO_OR_NULL_PTR(block))) + return; + BUG_ON(!size); + + sp = virt_to_page(block); + units = SLOB_UNITS(size); + + spin_lock_irqsave(&slob_lock, flags); + + if (sp->units + units == SLOB_UNITS(PAGE_SIZE)) { + /* Go directly to page allocator. Do not pass slob allocator */ + if (slob_page_free(sp)) + clear_slob_page_free(sp); + spin_unlock_irqrestore(&slob_lock, flags); + __ClearPageSlab(sp); + page_mapcount_reset(sp); + slob_free_pages(b, 0); + return; + } + + if (!slob_page_free(sp)) { + /* This slob page is about to become partially free. Easy! */ + sp->units = units; + sp->freelist = b; + set_slob(b, units, + (void *)((unsigned long)(b + + SLOB_UNITS(PAGE_SIZE)) & PAGE_MASK)); + if (size < SLOB_BREAK1) + slob_list = &free_slob_small; + else if (size < SLOB_BREAK2) + slob_list = &free_slob_medium; + else + slob_list = &free_slob_large; + set_slob_page_free(sp, slob_list); + goto out; + } + + /* + * Otherwise the page is already partially free, so find reinsertion + * point. + */ + sp->units += units; + + if (b < (slob_t *)sp->freelist) { + if (b + units == sp->freelist) { + units += slob_units(sp->freelist); + sp->freelist = slob_next(sp->freelist); + } + set_slob(b, units, sp->freelist); + sp->freelist = b; + } else { + prev = sp->freelist; + next = slob_next(prev); + while (b > next) { + prev = next; + next = slob_next(prev); + } + + if (!slob_last(prev) && b + units == next) { + units += slob_units(next); + set_slob(b, units, slob_next(next)); + } else + set_slob(b, units, next); + + if (prev + slob_units(prev) == b) { + units = slob_units(b) + slob_units(prev); + set_slob(prev, units, slob_next(b)); + } else + set_slob(prev, slob_units(prev), b); + } +out: + spin_unlock_irqrestore(&slob_lock, flags); +} + +/* + * End of slob allocator proper. Begin kmem_cache_alloc and kmalloc frontend. + */ + +static __always_inline void * +__do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller) +{ + unsigned int *m; + int minalign = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); + void *ret; + + gfp &= gfp_allowed_mask; + + fs_reclaim_acquire(gfp); + fs_reclaim_release(gfp); + + if (size < PAGE_SIZE - minalign) { + int align = minalign; + + /* + * For power of two sizes, guarantee natural alignment for + * kmalloc()'d objects. + */ + if (is_power_of_2(size)) + align = max(minalign, (int) size); + + if (!size) + return ZERO_SIZE_PTR; + + m = slob_alloc(size + minalign, gfp, align, node, minalign); + + if (!m) + return NULL; + *m = size; + ret = (void *)m + minalign; + + trace_kmalloc_node(caller, ret, + size, size + minalign, gfp, node); + } else { + unsigned int order = get_order(size); + + if (likely(order)) + gfp |= __GFP_COMP; + ret = slob_new_pages(gfp, order, node); + + trace_kmalloc_node(caller, ret, + size, PAGE_SIZE << order, gfp, node); + } + + kmemleak_alloc(ret, size, 1, gfp); + return ret; +} + +void *__kmalloc(size_t size, gfp_t gfp) +{ + return __do_kmalloc_node(size, gfp, NUMA_NO_NODE, _RET_IP_); +} +EXPORT_SYMBOL(__kmalloc); + +void *__kmalloc_track_caller(size_t size, gfp_t gfp, unsigned long caller) +{ + return __do_kmalloc_node(size, gfp, NUMA_NO_NODE, caller); +} +EXPORT_SYMBOL(__kmalloc_track_caller); + +#ifdef CONFIG_NUMA +void *__kmalloc_node_track_caller(size_t size, gfp_t gfp, + int node, unsigned long caller) +{ + return __do_kmalloc_node(size, gfp, node, caller); +} +EXPORT_SYMBOL(__kmalloc_node_track_caller); +#endif + +void kfree(const void *block) +{ + struct page *sp; + + trace_kfree(_RET_IP_, block); + + if (unlikely(ZERO_OR_NULL_PTR(block))) + return; + kmemleak_free(block); + + sp = virt_to_page(block); + if (PageSlab(sp)) { + int align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); + unsigned int *m = (unsigned int *)(block - align); + slob_free(m, *m + align); + } else { + unsigned int order = compound_order(sp); + mod_node_page_state(page_pgdat(sp), NR_SLAB_UNRECLAIMABLE_B, + -(PAGE_SIZE << order)); + __free_pages(sp, order); + + } +} +EXPORT_SYMBOL(kfree); + +/* can't use ksize for kmem_cache_alloc memory, only kmalloc */ +size_t __ksize(const void *block) +{ + struct page *sp; + int align; + unsigned int *m; + + BUG_ON(!block); + if (unlikely(block == ZERO_SIZE_PTR)) + return 0; + + sp = virt_to_page(block); + if (unlikely(!PageSlab(sp))) + return page_size(sp); + + align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); + m = (unsigned int *)(block - align); + return SLOB_UNITS(*m) * SLOB_UNIT; +} +EXPORT_SYMBOL(__ksize); + +int __kmem_cache_create(struct kmem_cache *c, slab_flags_t flags) +{ + if (flags & SLAB_TYPESAFE_BY_RCU) { + /* leave room for rcu footer at the end of object */ + c->size += sizeof(struct slob_rcu); + } + c->flags = flags; + return 0; +} + +static void *slob_alloc_node(struct kmem_cache *c, gfp_t flags, int node) +{ + void *b; + + flags &= gfp_allowed_mask; + + fs_reclaim_acquire(flags); + fs_reclaim_release(flags); + + if (c->size < PAGE_SIZE) { + b = slob_alloc(c->size, flags, c->align, node, 0); + trace_kmem_cache_alloc_node(_RET_IP_, b, c->object_size, + SLOB_UNITS(c->size) * SLOB_UNIT, + flags, node); + } else { + b = slob_new_pages(flags, get_order(c->size), node); + trace_kmem_cache_alloc_node(_RET_IP_, b, c->object_size, + PAGE_SIZE << get_order(c->size), + flags, node); + } + + if (b && c->ctor) { + WARN_ON_ONCE(flags & __GFP_ZERO); + c->ctor(b); + } + + kmemleak_alloc_recursive(b, c->size, 1, c->flags, flags); + return b; +} + +void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags) +{ + return slob_alloc_node(cachep, flags, NUMA_NO_NODE); +} +EXPORT_SYMBOL(kmem_cache_alloc); + +#ifdef CONFIG_NUMA +void *__kmalloc_node(size_t size, gfp_t gfp, int node) +{ + return __do_kmalloc_node(size, gfp, node, _RET_IP_); +} +EXPORT_SYMBOL(__kmalloc_node); + +void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t gfp, int node) +{ + return slob_alloc_node(cachep, gfp, node); +} +EXPORT_SYMBOL(kmem_cache_alloc_node); +#endif + +static void __kmem_cache_free(void *b, int size) +{ + if (size < PAGE_SIZE) + slob_free(b, size); + else + slob_free_pages(b, get_order(size)); +} + +static void kmem_rcu_free(struct rcu_head *head) +{ + struct slob_rcu *slob_rcu = (struct slob_rcu *)head; + void *b = (void *)slob_rcu - (slob_rcu->size - sizeof(struct slob_rcu)); + + __kmem_cache_free(b, slob_rcu->size); +} + +void kmem_cache_free(struct kmem_cache *c, void *b) +{ + kmemleak_free_recursive(b, c->flags); + if (unlikely(c->flags & SLAB_TYPESAFE_BY_RCU)) { + struct slob_rcu *slob_rcu; + slob_rcu = b + (c->size - sizeof(struct slob_rcu)); + slob_rcu->size = c->size; + call_rcu(&slob_rcu->head, kmem_rcu_free); + } else { + __kmem_cache_free(b, c->size); + } + + trace_kmem_cache_free(_RET_IP_, b); +} +EXPORT_SYMBOL(kmem_cache_free); + +void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p) +{ + __kmem_cache_free_bulk(s, size, p); +} +EXPORT_SYMBOL(kmem_cache_free_bulk); + +int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, + void **p) +{ + return __kmem_cache_alloc_bulk(s, flags, size, p); +} +EXPORT_SYMBOL(kmem_cache_alloc_bulk); + +int __kmem_cache_shutdown(struct kmem_cache *c) +{ + /* No way to check for remaining objects */ + return 0; +} + +void __kmem_cache_release(struct kmem_cache *c) +{ +} + +int __kmem_cache_shrink(struct kmem_cache *d) +{ + return 0; +} + +struct kmem_cache kmem_cache_boot = { + .name = "kmem_cache", + .size = sizeof(struct kmem_cache), + .flags = SLAB_PANIC, + .align = ARCH_KMALLOC_MINALIGN, +}; + +void __init kmem_cache_init(void) +{ + kmem_cache = &kmem_cache_boot; + slab_state = UP; +} + +void __init kmem_cache_init_late(void) +{ + slab_state = FULL; +} diff --git a/mm/slub.c b/mm/slub.c new file mode 100644 index 000000000..b0f637519 --- /dev/null +++ b/mm/slub.c @@ -0,0 +1,5771 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * SLUB: A slab allocator that limits cache line use instead of queuing + * objects in per cpu and per node lists. + * + * The allocator synchronizes using per slab locks or atomic operatios + * and only uses a centralized lock to manage a pool of partial slabs. + * + * (C) 2007 SGI, Christoph Lameter + * (C) 2011 Linux Foundation, Christoph Lameter + */ + +#include +#include /* struct reclaim_state */ +#include +#include +#include +#include +#include +#include +#include "slab.h" +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "internal.h" + +/* + * Lock order: + * 1. slab_mutex (Global Mutex) + * 2. node->list_lock + * 3. slab_lock(page) (Only on some arches and for debugging) + * + * slab_mutex + * + * The role of the slab_mutex is to protect the list of all the slabs + * and to synchronize major metadata changes to slab cache structures. + * + * The slab_lock is only used for debugging and on arches that do not + * have the ability to do a cmpxchg_double. It only protects: + * A. page->freelist -> List of object free in a page + * B. page->inuse -> Number of objects in use + * C. page->objects -> Number of objects in page + * D. page->frozen -> frozen state + * + * If a slab is frozen then it is exempt from list management. It is not + * on any list except per cpu partial list. The processor that froze the + * slab is the one who can perform list operations on the page. Other + * processors may put objects onto the freelist but the processor that + * froze the slab is the only one that can retrieve the objects from the + * page's freelist. + * + * The list_lock protects the partial and full list on each node and + * the partial slab counter. If taken then no new slabs may be added or + * removed from the lists nor make the number of partial slabs be modified. + * (Note that the total number of slabs is an atomic value that may be + * modified without taking the list lock). + * + * The list_lock is a centralized lock and thus we avoid taking it as + * much as possible. As long as SLUB does not have to handle partial + * slabs, operations can continue without any centralized lock. F.e. + * allocating a long series of objects that fill up slabs does not require + * the list lock. + * Interrupts are disabled during allocation and deallocation in order to + * make the slab allocator safe to use in the context of an irq. In addition + * interrupts are disabled to ensure that the processor does not change + * while handling per_cpu slabs, due to kernel preemption. + * + * SLUB assigns one slab for allocation to each processor. + * Allocations only occur from these slabs called cpu slabs. + * + * Slabs with free elements are kept on a partial list and during regular + * operations no list for full slabs is used. If an object in a full slab is + * freed then the slab will show up again on the partial lists. + * We track full slabs for debugging purposes though because otherwise we + * cannot scan all objects. + * + * Slabs are freed when they become empty. Teardown and setup is + * minimal so we rely on the page allocators per cpu caches for + * fast frees and allocs. + * + * page->frozen The slab is frozen and exempt from list processing. + * This means that the slab is dedicated to a purpose + * such as satisfying allocations for a specific + * processor. Objects may be freed in the slab while + * it is frozen but slab_free will then skip the usual + * list operations. It is up to the processor holding + * the slab to integrate the slab into the slab lists + * when the slab is no longer needed. + * + * One use of this flag is to mark slabs that are + * used for allocations. Then such a slab becomes a cpu + * slab. The cpu slab may be equipped with an additional + * freelist that allows lockless access to + * free objects in addition to the regular freelist + * that requires the slab lock. + * + * SLAB_DEBUG_FLAGS Slab requires special handling due to debug + * options set. This moves slab handling out of + * the fast path and disables lockless freelists. + */ + +#ifdef CONFIG_SLUB_DEBUG +#ifdef CONFIG_SLUB_DEBUG_ON +DEFINE_STATIC_KEY_TRUE(slub_debug_enabled); +#else +DEFINE_STATIC_KEY_FALSE(slub_debug_enabled); +#endif +#endif + +static inline bool kmem_cache_debug(struct kmem_cache *s) +{ + return kmem_cache_debug_flags(s, SLAB_DEBUG_FLAGS); +} + +void *fixup_red_left(struct kmem_cache *s, void *p) +{ + if (kmem_cache_debug_flags(s, SLAB_RED_ZONE)) + p += s->red_left_pad; + + return p; +} + +static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s) +{ +#ifdef CONFIG_SLUB_CPU_PARTIAL + return !kmem_cache_debug(s); +#else + return false; +#endif +} + +/* + * Issues still to be resolved: + * + * - Support PAGE_ALLOC_DEBUG. Should be easy to do. + * + * - Variable sizing of the per node arrays + */ + +/* Enable to test recovery from slab corruption on boot */ +#undef SLUB_RESILIENCY_TEST + +/* Enable to log cmpxchg failures */ +#undef SLUB_DEBUG_CMPXCHG + +/* + * Mininum number of partial slabs. These will be left on the partial + * lists even if they are empty. kmem_cache_shrink may reclaim them. + */ +#define MIN_PARTIAL 5 + +/* + * Maximum number of desirable partial slabs. + * The existence of more partial slabs makes kmem_cache_shrink + * sort the partial list by the number of objects in use. + */ +#define MAX_PARTIAL 10 + +#define DEBUG_DEFAULT_FLAGS (SLAB_CONSISTENCY_CHECKS | SLAB_RED_ZONE | \ + SLAB_POISON | SLAB_STORE_USER) + +/* + * These debug flags cannot use CMPXCHG because there might be consistency + * issues when checking or reading debug information + */ +#define SLAB_NO_CMPXCHG (SLAB_CONSISTENCY_CHECKS | SLAB_STORE_USER | \ + SLAB_TRACE) + + +/* + * Debugging flags that require metadata to be stored in the slab. These get + * disabled when slub_debug=O is used and a cache's min order increases with + * metadata. + */ +#define DEBUG_METADATA_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER) + +#define OO_SHIFT 16 +#define OO_MASK ((1 << OO_SHIFT) - 1) +#define MAX_OBJS_PER_PAGE 32767 /* since page.objects is u15 */ + +/* Internal SLUB flags */ +/* Poison object */ +#define __OBJECT_POISON ((slab_flags_t __force)0x80000000U) +/* Use cmpxchg_double */ +#define __CMPXCHG_DOUBLE ((slab_flags_t __force)0x40000000U) + +/* + * Tracking user of a slab. + */ +#define TRACK_ADDRS_COUNT 16 +struct track { + unsigned long addr; /* Called from address */ +#ifdef CONFIG_STACKTRACE + unsigned long addrs[TRACK_ADDRS_COUNT]; /* Called from address */ +#endif + int cpu; /* Was running on cpu */ + int pid; /* Pid context */ + unsigned long when; /* When did the operation occur */ +}; + +enum track_item { TRACK_ALLOC, TRACK_FREE }; + +#ifdef CONFIG_SYSFS +static int sysfs_slab_add(struct kmem_cache *); +static int sysfs_slab_alias(struct kmem_cache *, const char *); +#else +static inline int sysfs_slab_add(struct kmem_cache *s) { return 0; } +static inline int sysfs_slab_alias(struct kmem_cache *s, const char *p) + { return 0; } +#endif + +static inline void stat(const struct kmem_cache *s, enum stat_item si) +{ +#ifdef CONFIG_SLUB_STATS + /* + * The rmw is racy on a preemptible kernel but this is acceptable, so + * avoid this_cpu_add()'s irq-disable overhead. + */ + raw_cpu_inc(s->cpu_slab->stat[si]); +#endif +} + +/******************************************************************** + * Core slab cache functions + *******************************************************************/ + +/* + * Returns freelist pointer (ptr). With hardening, this is obfuscated + * with an XOR of the address where the pointer is held and a per-cache + * random number. + */ +static inline void *freelist_ptr(const struct kmem_cache *s, void *ptr, + unsigned long ptr_addr) +{ +#ifdef CONFIG_SLAB_FREELIST_HARDENED + /* + * When CONFIG_KASAN_SW_TAGS is enabled, ptr_addr might be tagged. + * Normally, this doesn't cause any issues, as both set_freepointer() + * and get_freepointer() are called with a pointer with the same tag. + * However, there are some issues with CONFIG_SLUB_DEBUG code. For + * example, when __free_slub() iterates over objects in a cache, it + * passes untagged pointers to check_object(). check_object() in turns + * calls get_freepointer() with an untagged pointer, which causes the + * freepointer to be restored incorrectly. + */ + return (void *)((unsigned long)ptr ^ s->random ^ + swab((unsigned long)kasan_reset_tag((void *)ptr_addr))); +#else + return ptr; +#endif +} + +/* Returns the freelist pointer recorded at location ptr_addr. */ +static inline void *freelist_dereference(const struct kmem_cache *s, + void *ptr_addr) +{ + return freelist_ptr(s, (void *)*(unsigned long *)(ptr_addr), + (unsigned long)ptr_addr); +} + +static inline void *get_freepointer(struct kmem_cache *s, void *object) +{ + return freelist_dereference(s, object + s->offset); +} + +static void prefetch_freepointer(const struct kmem_cache *s, void *object) +{ + prefetch(object + s->offset); +} + +static inline void *get_freepointer_safe(struct kmem_cache *s, void *object) +{ + unsigned long freepointer_addr; + void *p; + + if (!debug_pagealloc_enabled_static()) + return get_freepointer(s, object); + + freepointer_addr = (unsigned long)object + s->offset; + copy_from_kernel_nofault(&p, (void **)freepointer_addr, sizeof(p)); + return freelist_ptr(s, p, freepointer_addr); +} + +static inline void set_freepointer(struct kmem_cache *s, void *object, void *fp) +{ + unsigned long freeptr_addr = (unsigned long)object + s->offset; + +#ifdef CONFIG_SLAB_FREELIST_HARDENED + BUG_ON(object == fp); /* naive detection of double free or corruption */ +#endif + + *(void **)freeptr_addr = freelist_ptr(s, fp, freeptr_addr); +} + +/* Loop over all objects in a slab */ +#define for_each_object(__p, __s, __addr, __objects) \ + for (__p = fixup_red_left(__s, __addr); \ + __p < (__addr) + (__objects) * (__s)->size; \ + __p += (__s)->size) + +static inline unsigned int order_objects(unsigned int order, unsigned int size) +{ + return ((unsigned int)PAGE_SIZE << order) / size; +} + +static inline struct kmem_cache_order_objects oo_make(unsigned int order, + unsigned int size) +{ + struct kmem_cache_order_objects x = { + (order << OO_SHIFT) + order_objects(order, size) + }; + + return x; +} + +static inline unsigned int oo_order(struct kmem_cache_order_objects x) +{ + return x.x >> OO_SHIFT; +} + +static inline unsigned int oo_objects(struct kmem_cache_order_objects x) +{ + return x.x & OO_MASK; +} + +/* + * Per slab locking using the pagelock + */ +static __always_inline void slab_lock(struct page *page) +{ + VM_BUG_ON_PAGE(PageTail(page), page); + bit_spin_lock(PG_locked, &page->flags); +} + +static __always_inline void slab_unlock(struct page *page) +{ + VM_BUG_ON_PAGE(PageTail(page), page); + __bit_spin_unlock(PG_locked, &page->flags); +} + +/* Interrupts must be disabled (for the fallback code to work right) */ +static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct page *page, + void *freelist_old, unsigned long counters_old, + void *freelist_new, unsigned long counters_new, + const char *n) +{ + VM_BUG_ON(!irqs_disabled()); +#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \ + defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE) + if (s->flags & __CMPXCHG_DOUBLE) { + if (cmpxchg_double(&page->freelist, &page->counters, + freelist_old, counters_old, + freelist_new, counters_new)) + return true; + } else +#endif + { + slab_lock(page); + if (page->freelist == freelist_old && + page->counters == counters_old) { + page->freelist = freelist_new; + page->counters = counters_new; + slab_unlock(page); + return true; + } + slab_unlock(page); + } + + cpu_relax(); + stat(s, CMPXCHG_DOUBLE_FAIL); + +#ifdef SLUB_DEBUG_CMPXCHG + pr_info("%s %s: cmpxchg double redo ", n, s->name); +#endif + + return false; +} + +static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page, + void *freelist_old, unsigned long counters_old, + void *freelist_new, unsigned long counters_new, + const char *n) +{ +#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \ + defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE) + if (s->flags & __CMPXCHG_DOUBLE) { + if (cmpxchg_double(&page->freelist, &page->counters, + freelist_old, counters_old, + freelist_new, counters_new)) + return true; + } else +#endif + { + unsigned long flags; + + local_irq_save(flags); + slab_lock(page); + if (page->freelist == freelist_old && + page->counters == counters_old) { + page->freelist = freelist_new; + page->counters = counters_new; + slab_unlock(page); + local_irq_restore(flags); + return true; + } + slab_unlock(page); + local_irq_restore(flags); + } + + cpu_relax(); + stat(s, CMPXCHG_DOUBLE_FAIL); + +#ifdef SLUB_DEBUG_CMPXCHG + pr_info("%s %s: cmpxchg double redo ", n, s->name); +#endif + + return false; +} + +#ifdef CONFIG_SLUB_DEBUG +static unsigned long object_map[BITS_TO_LONGS(MAX_OBJS_PER_PAGE)]; +static DEFINE_SPINLOCK(object_map_lock); + +/* + * Determine a map of object in use on a page. + * + * Node listlock must be held to guarantee that the page does + * not vanish from under us. + */ +static unsigned long *get_map(struct kmem_cache *s, struct page *page) + __acquires(&object_map_lock) +{ + void *p; + void *addr = page_address(page); + + VM_BUG_ON(!irqs_disabled()); + + spin_lock(&object_map_lock); + + bitmap_zero(object_map, page->objects); + + for (p = page->freelist; p; p = get_freepointer(s, p)) + set_bit(__obj_to_index(s, addr, p), object_map); + + return object_map; +} + +static void put_map(unsigned long *map) __releases(&object_map_lock) +{ + VM_BUG_ON(map != object_map); + spin_unlock(&object_map_lock); +} + +static inline unsigned int size_from_object(struct kmem_cache *s) +{ + if (s->flags & SLAB_RED_ZONE) + return s->size - s->red_left_pad; + + return s->size; +} + +static inline void *restore_red_left(struct kmem_cache *s, void *p) +{ + if (s->flags & SLAB_RED_ZONE) + p -= s->red_left_pad; + + return p; +} + +/* + * Debug settings: + */ +#if defined(CONFIG_SLUB_DEBUG_ON) +static slab_flags_t slub_debug = DEBUG_DEFAULT_FLAGS; +#else +static slab_flags_t slub_debug; +#endif + +static char *slub_debug_string; +static int disable_higher_order_debug; + +/* + * slub is about to manipulate internal object metadata. This memory lies + * outside the range of the allocated object, so accessing it would normally + * be reported by kasan as a bounds error. metadata_access_enable() is used + * to tell kasan that these accesses are OK. + */ +static inline void metadata_access_enable(void) +{ + kasan_disable_current(); +} + +static inline void metadata_access_disable(void) +{ + kasan_enable_current(); +} + +/* + * Object debugging + */ + +/* Verify that a pointer has an address that is valid within a slab page */ +static inline int check_valid_pointer(struct kmem_cache *s, + struct page *page, void *object) +{ + void *base; + + if (!object) + return 1; + + base = page_address(page); + object = kasan_reset_tag(object); + object = restore_red_left(s, object); + if (object < base || object >= base + page->objects * s->size || + (object - base) % s->size) { + return 0; + } + + return 1; +} + +static void print_section(char *level, char *text, u8 *addr, + unsigned int length) +{ + metadata_access_enable(); + print_hex_dump(level, text, DUMP_PREFIX_ADDRESS, 16, 1, addr, + length, 1); + metadata_access_disable(); +} + +/* + * See comment in calculate_sizes(). + */ +static inline bool freeptr_outside_object(struct kmem_cache *s) +{ + return s->offset >= s->inuse; +} + +/* + * Return offset of the end of info block which is inuse + free pointer if + * not overlapping with object. + */ +static inline unsigned int get_info_end(struct kmem_cache *s) +{ + if (freeptr_outside_object(s)) + return s->inuse + sizeof(void *); + else + return s->inuse; +} + +static struct track *get_track(struct kmem_cache *s, void *object, + enum track_item alloc) +{ + struct track *p; + + p = object + get_info_end(s); + + return p + alloc; +} + +static void set_track(struct kmem_cache *s, void *object, + enum track_item alloc, unsigned long addr) +{ + struct track *p = get_track(s, object, alloc); + + if (addr) { +#ifdef CONFIG_STACKTRACE + unsigned int nr_entries; + + metadata_access_enable(); + nr_entries = stack_trace_save(p->addrs, TRACK_ADDRS_COUNT, 3); + metadata_access_disable(); + + if (nr_entries < TRACK_ADDRS_COUNT) + p->addrs[nr_entries] = 0; +#endif + p->addr = addr; + p->cpu = smp_processor_id(); + p->pid = current->pid; + p->when = jiffies; + } else { + memset(p, 0, sizeof(struct track)); + } +} + +static void init_tracking(struct kmem_cache *s, void *object) +{ + if (!(s->flags & SLAB_STORE_USER)) + return; + + set_track(s, object, TRACK_FREE, 0UL); + set_track(s, object, TRACK_ALLOC, 0UL); +} + +static void print_track(const char *s, struct track *t, unsigned long pr_time) +{ + if (!t->addr) + return; + + pr_err("INFO: %s in %pS age=%lu cpu=%u pid=%d\n", + s, (void *)t->addr, pr_time - t->when, t->cpu, t->pid); +#ifdef CONFIG_STACKTRACE + { + int i; + for (i = 0; i < TRACK_ADDRS_COUNT; i++) + if (t->addrs[i]) + pr_err("\t%pS\n", (void *)t->addrs[i]); + else + break; + } +#endif +} + +void print_tracking(struct kmem_cache *s, void *object) +{ + unsigned long pr_time = jiffies; + if (!(s->flags & SLAB_STORE_USER)) + return; + + print_track("Allocated", get_track(s, object, TRACK_ALLOC), pr_time); + print_track("Freed", get_track(s, object, TRACK_FREE), pr_time); +} + +static void print_page_info(struct page *page) +{ + pr_err("INFO: Slab 0x%p objects=%u used=%u fp=0x%p flags=0x%04lx\n", + page, page->objects, page->inuse, page->freelist, page->flags); + +} + +static void slab_bug(struct kmem_cache *s, char *fmt, ...) +{ + struct va_format vaf; + va_list args; + + va_start(args, fmt); + vaf.fmt = fmt; + vaf.va = &args; + pr_err("=============================================================================\n"); + pr_err("BUG %s (%s): %pV\n", s->name, print_tainted(), &vaf); + pr_err("-----------------------------------------------------------------------------\n\n"); + + add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); + va_end(args); +} + +static void slab_fix(struct kmem_cache *s, char *fmt, ...) +{ + struct va_format vaf; + va_list args; + + va_start(args, fmt); + vaf.fmt = fmt; + vaf.va = &args; + pr_err("FIX %s: %pV\n", s->name, &vaf); + va_end(args); +} + +static bool freelist_corrupted(struct kmem_cache *s, struct page *page, + void **freelist, void *nextfree) +{ + if ((s->flags & SLAB_CONSISTENCY_CHECKS) && + !check_valid_pointer(s, page, nextfree) && freelist) { + object_err(s, page, *freelist, "Freechain corrupt"); + *freelist = NULL; + slab_fix(s, "Isolate corrupted freechain"); + return true; + } + + return false; +} + +static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) +{ + unsigned int off; /* Offset of last byte */ + u8 *addr = page_address(page); + + print_tracking(s, p); + + print_page_info(page); + + pr_err("INFO: Object 0x%p @offset=%tu fp=0x%p\n\n", + p, p - addr, get_freepointer(s, p)); + + if (s->flags & SLAB_RED_ZONE) + print_section(KERN_ERR, "Redzone ", p - s->red_left_pad, + s->red_left_pad); + else if (p > addr + 16) + print_section(KERN_ERR, "Bytes b4 ", p - 16, 16); + + print_section(KERN_ERR, "Object ", p, + min_t(unsigned int, s->object_size, PAGE_SIZE)); + if (s->flags & SLAB_RED_ZONE) + print_section(KERN_ERR, "Redzone ", p + s->object_size, + s->inuse - s->object_size); + + off = get_info_end(s); + + if (s->flags & SLAB_STORE_USER) + off += 2 * sizeof(struct track); + + off += kasan_metadata_size(s); + + if (off != size_from_object(s)) + /* Beginning of the filler is the free pointer */ + print_section(KERN_ERR, "Padding ", p + off, + size_from_object(s) - off); + + dump_stack(); +} + +void object_err(struct kmem_cache *s, struct page *page, + u8 *object, char *reason) +{ + slab_bug(s, "%s", reason); + print_trailer(s, page, object); +} + +static __printf(3, 4) void slab_err(struct kmem_cache *s, struct page *page, + const char *fmt, ...) +{ + va_list args; + char buf[100]; + + va_start(args, fmt); + vsnprintf(buf, sizeof(buf), fmt, args); + va_end(args); + slab_bug(s, "%s", buf); + print_page_info(page); + dump_stack(); +} + +static void init_object(struct kmem_cache *s, void *object, u8 val) +{ + u8 *p = object; + + if (s->flags & SLAB_RED_ZONE) + memset(p - s->red_left_pad, val, s->red_left_pad); + + if (s->flags & __OBJECT_POISON) { + memset(p, POISON_FREE, s->object_size - 1); + p[s->object_size - 1] = POISON_END; + } + + if (s->flags & SLAB_RED_ZONE) + memset(p + s->object_size, val, s->inuse - s->object_size); +} + +static void restore_bytes(struct kmem_cache *s, char *message, u8 data, + void *from, void *to) +{ + slab_fix(s, "Restoring 0x%p-0x%p=0x%x\n", from, to - 1, data); + memset(from, data, to - from); +} + +static int check_bytes_and_report(struct kmem_cache *s, struct page *page, + u8 *object, char *what, + u8 *start, unsigned int value, unsigned int bytes) +{ + u8 *fault; + u8 *end; + u8 *addr = page_address(page); + + metadata_access_enable(); + fault = memchr_inv(start, value, bytes); + metadata_access_disable(); + if (!fault) + return 1; + + end = start + bytes; + while (end > fault && end[-1] == value) + end--; + + slab_bug(s, "%s overwritten", what); + pr_err("INFO: 0x%p-0x%p @offset=%tu. First byte 0x%x instead of 0x%x\n", + fault, end - 1, fault - addr, + fault[0], value); + print_trailer(s, page, object); + + restore_bytes(s, what, value, fault, end); + return 0; +} + +/* + * Object layout: + * + * object address + * Bytes of the object to be managed. + * If the freepointer may overlay the object then the free + * pointer is at the middle of the object. + * + * Poisoning uses 0x6b (POISON_FREE) and the last byte is + * 0xa5 (POISON_END) + * + * object + s->object_size + * Padding to reach word boundary. This is also used for Redzoning. + * Padding is extended by another word if Redzoning is enabled and + * object_size == inuse. + * + * We fill with 0xbb (RED_INACTIVE) for inactive objects and with + * 0xcc (RED_ACTIVE) for objects in use. + * + * object + s->inuse + * Meta data starts here. + * + * A. Free pointer (if we cannot overwrite object on free) + * B. Tracking data for SLAB_STORE_USER + * C. Padding to reach required alignment boundary or at mininum + * one word if debugging is on to be able to detect writes + * before the word boundary. + * + * Padding is done using 0x5a (POISON_INUSE) + * + * object + s->size + * Nothing is used beyond s->size. + * + * If slabcaches are merged then the object_size and inuse boundaries are mostly + * ignored. And therefore no slab options that rely on these boundaries + * may be used with merged slabcaches. + */ + +static int check_pad_bytes(struct kmem_cache *s, struct page *page, u8 *p) +{ + unsigned long off = get_info_end(s); /* The end of info */ + + if (s->flags & SLAB_STORE_USER) + /* We also have user information there */ + off += 2 * sizeof(struct track); + + off += kasan_metadata_size(s); + + if (size_from_object(s) == off) + return 1; + + return check_bytes_and_report(s, page, p, "Object padding", + p + off, POISON_INUSE, size_from_object(s) - off); +} + +/* Check the pad bytes at the end of a slab page */ +static int slab_pad_check(struct kmem_cache *s, struct page *page) +{ + u8 *start; + u8 *fault; + u8 *end; + u8 *pad; + int length; + int remainder; + + if (!(s->flags & SLAB_POISON)) + return 1; + + start = page_address(page); + length = page_size(page); + end = start + length; + remainder = length % s->size; + if (!remainder) + return 1; + + pad = end - remainder; + metadata_access_enable(); + fault = memchr_inv(pad, POISON_INUSE, remainder); + metadata_access_disable(); + if (!fault) + return 1; + while (end > fault && end[-1] == POISON_INUSE) + end--; + + slab_err(s, page, "Padding overwritten. 0x%p-0x%p @offset=%tu", + fault, end - 1, fault - start); + print_section(KERN_ERR, "Padding ", pad, remainder); + + restore_bytes(s, "slab padding", POISON_INUSE, fault, end); + return 0; +} + +static int check_object(struct kmem_cache *s, struct page *page, + void *object, u8 val) +{ + u8 *p = object; + u8 *endobject = object + s->object_size; + + if (s->flags & SLAB_RED_ZONE) { + if (!check_bytes_and_report(s, page, object, "Left Redzone", + object - s->red_left_pad, val, s->red_left_pad)) + return 0; + + if (!check_bytes_and_report(s, page, object, "Right Redzone", + endobject, val, s->inuse - s->object_size)) + return 0; + } else { + if ((s->flags & SLAB_POISON) && s->object_size < s->inuse) { + check_bytes_and_report(s, page, p, "Alignment padding", + endobject, POISON_INUSE, + s->inuse - s->object_size); + } + } + + if (s->flags & SLAB_POISON) { + if (val != SLUB_RED_ACTIVE && (s->flags & __OBJECT_POISON) && + (!check_bytes_and_report(s, page, p, "Poison", p, + POISON_FREE, s->object_size - 1) || + !check_bytes_and_report(s, page, p, "End Poison", + p + s->object_size - 1, POISON_END, 1))) + return 0; + /* + * check_pad_bytes cleans up on its own. + */ + check_pad_bytes(s, page, p); + } + + if (!freeptr_outside_object(s) && val == SLUB_RED_ACTIVE) + /* + * Object and freepointer overlap. Cannot check + * freepointer while object is allocated. + */ + return 1; + + /* Check free pointer validity */ + if (!check_valid_pointer(s, page, get_freepointer(s, p))) { + object_err(s, page, p, "Freepointer corrupt"); + /* + * No choice but to zap it and thus lose the remainder + * of the free objects in this slab. May cause + * another error because the object count is now wrong. + */ + set_freepointer(s, p, NULL); + return 0; + } + return 1; +} + +static int check_slab(struct kmem_cache *s, struct page *page) +{ + int maxobj; + + VM_BUG_ON(!irqs_disabled()); + + if (!PageSlab(page)) { + slab_err(s, page, "Not a valid slab page"); + return 0; + } + + maxobj = order_objects(compound_order(page), s->size); + if (page->objects > maxobj) { + slab_err(s, page, "objects %u > max %u", + page->objects, maxobj); + return 0; + } + if (page->inuse > page->objects) { + slab_err(s, page, "inuse %u > max %u", + page->inuse, page->objects); + return 0; + } + /* Slab_pad_check fixes things up after itself */ + slab_pad_check(s, page); + return 1; +} + +/* + * Determine if a certain object on a page is on the freelist. Must hold the + * slab lock to guarantee that the chains are in a consistent state. + */ +static int on_freelist(struct kmem_cache *s, struct page *page, void *search) +{ + int nr = 0; + void *fp; + void *object = NULL; + int max_objects; + + fp = page->freelist; + while (fp && nr <= page->objects) { + if (fp == search) + return 1; + if (!check_valid_pointer(s, page, fp)) { + if (object) { + object_err(s, page, object, + "Freechain corrupt"); + set_freepointer(s, object, NULL); + } else { + slab_err(s, page, "Freepointer corrupt"); + page->freelist = NULL; + page->inuse = page->objects; + slab_fix(s, "Freelist cleared"); + return 0; + } + break; + } + object = fp; + fp = get_freepointer(s, object); + nr++; + } + + max_objects = order_objects(compound_order(page), s->size); + if (max_objects > MAX_OBJS_PER_PAGE) + max_objects = MAX_OBJS_PER_PAGE; + + if (page->objects != max_objects) { + slab_err(s, page, "Wrong number of objects. Found %d but should be %d", + page->objects, max_objects); + page->objects = max_objects; + slab_fix(s, "Number of objects adjusted."); + } + if (page->inuse != page->objects - nr) { + slab_err(s, page, "Wrong object count. Counter is %d but counted were %d", + page->inuse, page->objects - nr); + page->inuse = page->objects - nr; + slab_fix(s, "Object count adjusted."); + } + return search == NULL; +} + +static void trace(struct kmem_cache *s, struct page *page, void *object, + int alloc) +{ + if (s->flags & SLAB_TRACE) { + pr_info("TRACE %s %s 0x%p inuse=%d fp=0x%p\n", + s->name, + alloc ? "alloc" : "free", + object, page->inuse, + page->freelist); + + if (!alloc) + print_section(KERN_INFO, "Object ", (void *)object, + s->object_size); + + dump_stack(); + } +} + +/* + * Tracking of fully allocated slabs for debugging purposes. + */ +static void add_full(struct kmem_cache *s, + struct kmem_cache_node *n, struct page *page) +{ + if (!(s->flags & SLAB_STORE_USER)) + return; + + lockdep_assert_held(&n->list_lock); + list_add(&page->slab_list, &n->full); +} + +static void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page) +{ + if (!(s->flags & SLAB_STORE_USER)) + return; + + lockdep_assert_held(&n->list_lock); + list_del(&page->slab_list); +} + +/* Tracking of the number of slabs for debugging purposes */ +static inline unsigned long slabs_node(struct kmem_cache *s, int node) +{ + struct kmem_cache_node *n = get_node(s, node); + + return atomic_long_read(&n->nr_slabs); +} + +static inline unsigned long node_nr_slabs(struct kmem_cache_node *n) +{ + return atomic_long_read(&n->nr_slabs); +} + +static inline void inc_slabs_node(struct kmem_cache *s, int node, int objects) +{ + struct kmem_cache_node *n = get_node(s, node); + + /* + * May be called early in order to allocate a slab for the + * kmem_cache_node structure. Solve the chicken-egg + * dilemma by deferring the increment of the count during + * bootstrap (see early_kmem_cache_node_alloc). + */ + if (likely(n)) { + atomic_long_inc(&n->nr_slabs); + atomic_long_add(objects, &n->total_objects); + } +} +static inline void dec_slabs_node(struct kmem_cache *s, int node, int objects) +{ + struct kmem_cache_node *n = get_node(s, node); + + atomic_long_dec(&n->nr_slabs); + atomic_long_sub(objects, &n->total_objects); +} + +/* Object debug checks for alloc/free paths */ +static void setup_object_debug(struct kmem_cache *s, struct page *page, + void *object) +{ + if (!kmem_cache_debug_flags(s, SLAB_STORE_USER|SLAB_RED_ZONE|__OBJECT_POISON)) + return; + + init_object(s, object, SLUB_RED_INACTIVE); + init_tracking(s, object); +} + +static +void setup_page_debug(struct kmem_cache *s, struct page *page, void *addr) +{ + if (!kmem_cache_debug_flags(s, SLAB_POISON)) + return; + + metadata_access_enable(); + memset(addr, POISON_INUSE, page_size(page)); + metadata_access_disable(); +} + +static inline int alloc_consistency_checks(struct kmem_cache *s, + struct page *page, void *object) +{ + if (!check_slab(s, page)) + return 0; + + if (!check_valid_pointer(s, page, object)) { + object_err(s, page, object, "Freelist Pointer check fails"); + return 0; + } + + if (!check_object(s, page, object, SLUB_RED_INACTIVE)) + return 0; + + return 1; +} + +static noinline int alloc_debug_processing(struct kmem_cache *s, + struct page *page, + void *object, unsigned long addr) +{ + if (s->flags & SLAB_CONSISTENCY_CHECKS) { + if (!alloc_consistency_checks(s, page, object)) + goto bad; + } + + /* Success perform special debug activities for allocs */ + if (s->flags & SLAB_STORE_USER) + set_track(s, object, TRACK_ALLOC, addr); + trace(s, page, object, 1); + init_object(s, object, SLUB_RED_ACTIVE); + return 1; + +bad: + if (PageSlab(page)) { + /* + * If this is a slab page then lets do the best we can + * to avoid issues in the future. Marking all objects + * as used avoids touching the remaining objects. + */ + slab_fix(s, "Marking all objects used"); + page->inuse = page->objects; + page->freelist = NULL; + } + return 0; +} + +static inline int free_consistency_checks(struct kmem_cache *s, + struct page *page, void *object, unsigned long addr) +{ + if (!check_valid_pointer(s, page, object)) { + slab_err(s, page, "Invalid object pointer 0x%p", object); + return 0; + } + + if (on_freelist(s, page, object)) { + object_err(s, page, object, "Object already free"); + return 0; + } + + if (!check_object(s, page, object, SLUB_RED_ACTIVE)) + return 0; + + if (unlikely(s != page->slab_cache)) { + if (!PageSlab(page)) { + slab_err(s, page, "Attempt to free object(0x%p) outside of slab", + object); + } else if (!page->slab_cache) { + pr_err("SLUB : no slab for object 0x%p.\n", + object); + dump_stack(); + } else + object_err(s, page, object, + "page slab pointer corrupt."); + return 0; + } + return 1; +} + +/* Supports checking bulk free of a constructed freelist */ +static noinline int free_debug_processing( + struct kmem_cache *s, struct page *page, + void *head, void *tail, int bulk_cnt, + unsigned long addr) +{ + struct kmem_cache_node *n = get_node(s, page_to_nid(page)); + void *object = head; + int cnt = 0; + unsigned long flags; + int ret = 0; + + spin_lock_irqsave(&n->list_lock, flags); + slab_lock(page); + + if (s->flags & SLAB_CONSISTENCY_CHECKS) { + if (!check_slab(s, page)) + goto out; + } + +next_object: + cnt++; + + if (s->flags & SLAB_CONSISTENCY_CHECKS) { + if (!free_consistency_checks(s, page, object, addr)) + goto out; + } + + if (s->flags & SLAB_STORE_USER) + set_track(s, object, TRACK_FREE, addr); + trace(s, page, object, 0); + /* Freepointer not overwritten by init_object(), SLAB_POISON moved it */ + init_object(s, object, SLUB_RED_INACTIVE); + + /* Reached end of constructed freelist yet? */ + if (object != tail) { + object = get_freepointer(s, object); + goto next_object; + } + ret = 1; + +out: + if (cnt != bulk_cnt) + slab_err(s, page, "Bulk freelist count(%d) invalid(%d)\n", + bulk_cnt, cnt); + + slab_unlock(page); + spin_unlock_irqrestore(&n->list_lock, flags); + if (!ret) + slab_fix(s, "Object at 0x%p not freed", object); + return ret; +} + +/* + * Parse a block of slub_debug options. Blocks are delimited by ';' + * + * @str: start of block + * @flags: returns parsed flags, or DEBUG_DEFAULT_FLAGS if none specified + * @slabs: return start of list of slabs, or NULL when there's no list + * @init: assume this is initial parsing and not per-kmem-create parsing + * + * returns the start of next block if there's any, or NULL + */ +static char * +parse_slub_debug_flags(char *str, slab_flags_t *flags, char **slabs, bool init) +{ + bool higher_order_disable = false; + + /* Skip any completely empty blocks */ + while (*str && *str == ';') + str++; + + if (*str == ',') { + /* + * No options but restriction on slabs. This means full + * debugging for slabs matching a pattern. + */ + *flags = DEBUG_DEFAULT_FLAGS; + goto check_slabs; + } + *flags = 0; + + /* Determine which debug features should be switched on */ + for (; *str && *str != ',' && *str != ';'; str++) { + switch (tolower(*str)) { + case '-': + *flags = 0; + break; + case 'f': + *flags |= SLAB_CONSISTENCY_CHECKS; + break; + case 'z': + *flags |= SLAB_RED_ZONE; + break; + case 'p': + *flags |= SLAB_POISON; + break; + case 'u': + *flags |= SLAB_STORE_USER; + break; + case 't': + *flags |= SLAB_TRACE; + break; + case 'a': + *flags |= SLAB_FAILSLAB; + break; + case 'o': + /* + * Avoid enabling debugging on caches if its minimum + * order would increase as a result. + */ + higher_order_disable = true; + break; + default: + if (init) + pr_err("slub_debug option '%c' unknown. skipped\n", *str); + } + } +check_slabs: + if (*str == ',') + *slabs = ++str; + else + *slabs = NULL; + + /* Skip over the slab list */ + while (*str && *str != ';') + str++; + + /* Skip any completely empty blocks */ + while (*str && *str == ';') + str++; + + if (init && higher_order_disable) + disable_higher_order_debug = 1; + + if (*str) + return str; + else + return NULL; +} + +static int __init setup_slub_debug(char *str) +{ + slab_flags_t flags; + char *saved_str; + char *slab_list; + bool global_slub_debug_changed = false; + bool slab_list_specified = false; + + slub_debug = DEBUG_DEFAULT_FLAGS; + if (*str++ != '=' || !*str) + /* + * No options specified. Switch on full debugging. + */ + goto out; + + saved_str = str; + while (str) { + str = parse_slub_debug_flags(str, &flags, &slab_list, true); + + if (!slab_list) { + slub_debug = flags; + global_slub_debug_changed = true; + } else { + slab_list_specified = true; + } + } + + /* + * For backwards compatibility, a single list of flags with list of + * slabs means debugging is only enabled for those slabs, so the global + * slub_debug should be 0. We can extended that to multiple lists as + * long as there is no option specifying flags without a slab list. + */ + if (slab_list_specified) { + if (!global_slub_debug_changed) + slub_debug = 0; + slub_debug_string = saved_str; + } +out: + if (slub_debug != 0 || slub_debug_string) + static_branch_enable(&slub_debug_enabled); + if ((static_branch_unlikely(&init_on_alloc) || + static_branch_unlikely(&init_on_free)) && + (slub_debug & SLAB_POISON)) + pr_info("mem auto-init: SLAB_POISON will take precedence over init_on_alloc/init_on_free\n"); + return 1; +} + +__setup("slub_debug", setup_slub_debug); + +/* + * kmem_cache_flags - apply debugging options to the cache + * @object_size: the size of an object without meta data + * @flags: flags to set + * @name: name of the cache + * + * Debug option(s) are applied to @flags. In addition to the debug + * option(s), if a slab name (or multiple) is specified i.e. + * slub_debug=,, ... + * then only the select slabs will receive the debug option(s). + */ +slab_flags_t kmem_cache_flags(unsigned int object_size, + slab_flags_t flags, const char *name) +{ + char *iter; + size_t len; + char *next_block; + slab_flags_t block_flags; + + len = strlen(name); + next_block = slub_debug_string; + /* Go through all blocks of debug options, see if any matches our slab's name */ + while (next_block) { + next_block = parse_slub_debug_flags(next_block, &block_flags, &iter, false); + if (!iter) + continue; + /* Found a block that has a slab list, search it */ + while (*iter) { + char *end, *glob; + size_t cmplen; + + end = strchrnul(iter, ','); + if (next_block && next_block < end) + end = next_block - 1; + + glob = strnchr(iter, end - iter, '*'); + if (glob) + cmplen = glob - iter; + else + cmplen = max_t(size_t, len, (end - iter)); + + if (!strncmp(name, iter, cmplen)) { + flags |= block_flags; + return flags; + } + + if (!*end || *end == ';') + break; + iter = end + 1; + } + } + + return flags | slub_debug; +} +#else /* !CONFIG_SLUB_DEBUG */ +static inline void setup_object_debug(struct kmem_cache *s, + struct page *page, void *object) {} +static inline +void setup_page_debug(struct kmem_cache *s, struct page *page, void *addr) {} + +static inline int alloc_debug_processing(struct kmem_cache *s, + struct page *page, void *object, unsigned long addr) { return 0; } + +static inline int free_debug_processing( + struct kmem_cache *s, struct page *page, + void *head, void *tail, int bulk_cnt, + unsigned long addr) { return 0; } + +static inline int slab_pad_check(struct kmem_cache *s, struct page *page) + { return 1; } +static inline int check_object(struct kmem_cache *s, struct page *page, + void *object, u8 val) { return 1; } +static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n, + struct page *page) {} +static inline void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, + struct page *page) {} +slab_flags_t kmem_cache_flags(unsigned int object_size, + slab_flags_t flags, const char *name) +{ + return flags; +} +#define slub_debug 0 + +#define disable_higher_order_debug 0 + +static inline unsigned long slabs_node(struct kmem_cache *s, int node) + { return 0; } +static inline unsigned long node_nr_slabs(struct kmem_cache_node *n) + { return 0; } +static inline void inc_slabs_node(struct kmem_cache *s, int node, + int objects) {} +static inline void dec_slabs_node(struct kmem_cache *s, int node, + int objects) {} + +static bool freelist_corrupted(struct kmem_cache *s, struct page *page, + void **freelist, void *nextfree) +{ + return false; +} +#endif /* CONFIG_SLUB_DEBUG */ + +/* + * Hooks for other subsystems that check memory allocations. In a typical + * production configuration these hooks all should produce no code at all. + */ +static inline void *kmalloc_large_node_hook(void *ptr, size_t size, gfp_t flags) +{ + ptr = kasan_kmalloc_large(ptr, size, flags); + /* As ptr might get tagged, call kmemleak hook after KASAN. */ + kmemleak_alloc(ptr, size, 1, flags); + return ptr; +} + +static __always_inline void kfree_hook(void *x) +{ + kmemleak_free(x); + kasan_kfree_large(x, _RET_IP_); +} + +static __always_inline bool slab_free_hook(struct kmem_cache *s, void *x) +{ + kmemleak_free_recursive(x, s->flags); + + /* + * Trouble is that we may no longer disable interrupts in the fast path + * So in order to make the debug calls that expect irqs to be + * disabled we need to disable interrupts temporarily. + */ +#ifdef CONFIG_LOCKDEP + { + unsigned long flags; + + local_irq_save(flags); + debug_check_no_locks_freed(x, s->object_size); + local_irq_restore(flags); + } +#endif + if (!(s->flags & SLAB_DEBUG_OBJECTS)) + debug_check_no_obj_freed(x, s->object_size); + + /* Use KCSAN to help debug racy use-after-free. */ + if (!(s->flags & SLAB_TYPESAFE_BY_RCU)) + __kcsan_check_access(x, s->object_size, + KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ASSERT); + + /* KASAN might put x into memory quarantine, delaying its reuse */ + return kasan_slab_free(s, x, _RET_IP_); +} + +static inline bool slab_free_freelist_hook(struct kmem_cache *s, + void **head, void **tail, + int *cnt) +{ + + void *object; + void *next = *head; + void *old_tail = *tail ? *tail : *head; + int rsize; + + /* Head and tail of the reconstructed freelist */ + *head = NULL; + *tail = NULL; + + do { + object = next; + next = get_freepointer(s, object); + + if (slab_want_init_on_free(s)) { + /* + * Clear the object and the metadata, but don't touch + * the redzone. + */ + memset(object, 0, s->object_size); + rsize = (s->flags & SLAB_RED_ZONE) ? s->red_left_pad + : 0; + memset((char *)object + s->inuse, 0, + s->size - s->inuse - rsize); + + } + /* If object's reuse doesn't have to be delayed */ + if (!slab_free_hook(s, object)) { + /* Move object to the new freelist */ + set_freepointer(s, object, *head); + *head = object; + if (!*tail) + *tail = object; + } else { + /* + * Adjust the reconstructed freelist depth + * accordingly if object's reuse is delayed. + */ + --(*cnt); + } + } while (object != old_tail); + + if (*head == *tail) + *tail = NULL; + + return *head != NULL; +} + +static void *setup_object(struct kmem_cache *s, struct page *page, + void *object) +{ + setup_object_debug(s, page, object); + object = kasan_init_slab_obj(s, object); + if (unlikely(s->ctor)) { + kasan_unpoison_object_data(s, object); + s->ctor(object); + kasan_poison_object_data(s, object); + } + return object; +} + +/* + * Slab allocation and freeing + */ +static inline struct page *alloc_slab_page(struct kmem_cache *s, + gfp_t flags, int node, struct kmem_cache_order_objects oo) +{ + struct page *page; + unsigned int order = oo_order(oo); + + if (node == NUMA_NO_NODE) + page = alloc_pages(flags, order); + else + page = __alloc_pages_node(node, flags, order); + + if (page) + account_slab_page(page, order, s); + + return page; +} + +#ifdef CONFIG_SLAB_FREELIST_RANDOM +/* Pre-initialize the random sequence cache */ +static int init_cache_random_seq(struct kmem_cache *s) +{ + unsigned int count = oo_objects(s->oo); + int err; + + /* Bailout if already initialised */ + if (s->random_seq) + return 0; + + err = cache_random_seq_create(s, count, GFP_KERNEL); + if (err) { + pr_err("SLUB: Unable to initialize free list for %s\n", + s->name); + return err; + } + + /* Transform to an offset on the set of pages */ + if (s->random_seq) { + unsigned int i; + + for (i = 0; i < count; i++) + s->random_seq[i] *= s->size; + } + return 0; +} + +/* Initialize each random sequence freelist per cache */ +static void __init init_freelist_randomization(void) +{ + struct kmem_cache *s; + + mutex_lock(&slab_mutex); + + list_for_each_entry(s, &slab_caches, list) + init_cache_random_seq(s); + + mutex_unlock(&slab_mutex); +} + +/* Get the next entry on the pre-computed freelist randomized */ +static void *next_freelist_entry(struct kmem_cache *s, struct page *page, + unsigned long *pos, void *start, + unsigned long page_limit, + unsigned long freelist_count) +{ + unsigned int idx; + + /* + * If the target page allocation failed, the number of objects on the + * page might be smaller than the usual size defined by the cache. + */ + do { + idx = s->random_seq[*pos]; + *pos += 1; + if (*pos >= freelist_count) + *pos = 0; + } while (unlikely(idx >= page_limit)); + + return (char *)start + idx; +} + +/* Shuffle the single linked freelist based on a random pre-computed sequence */ +static bool shuffle_freelist(struct kmem_cache *s, struct page *page) +{ + void *start; + void *cur; + void *next; + unsigned long idx, pos, page_limit, freelist_count; + + if (page->objects < 2 || !s->random_seq) + return false; + + freelist_count = oo_objects(s->oo); + pos = get_random_int() % freelist_count; + + page_limit = page->objects * s->size; + start = fixup_red_left(s, page_address(page)); + + /* First entry is used as the base of the freelist */ + cur = next_freelist_entry(s, page, &pos, start, page_limit, + freelist_count); + cur = setup_object(s, page, cur); + page->freelist = cur; + + for (idx = 1; idx < page->objects; idx++) { + next = next_freelist_entry(s, page, &pos, start, page_limit, + freelist_count); + next = setup_object(s, page, next); + set_freepointer(s, cur, next); + cur = next; + } + set_freepointer(s, cur, NULL); + + return true; +} +#else +static inline int init_cache_random_seq(struct kmem_cache *s) +{ + return 0; +} +static inline void init_freelist_randomization(void) { } +static inline bool shuffle_freelist(struct kmem_cache *s, struct page *page) +{ + return false; +} +#endif /* CONFIG_SLAB_FREELIST_RANDOM */ + +static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) +{ + struct page *page; + struct kmem_cache_order_objects oo = s->oo; + gfp_t alloc_gfp; + void *start, *p, *next; + int idx; + bool shuffle; + + flags &= gfp_allowed_mask; + + if (gfpflags_allow_blocking(flags)) + local_irq_enable(); + + flags |= s->allocflags; + + /* + * Let the initial higher-order allocation fail under memory pressure + * so we fall-back to the minimum order allocation. + */ + alloc_gfp = (flags | __GFP_NOWARN | __GFP_NORETRY) & ~__GFP_NOFAIL; + if ((alloc_gfp & __GFP_DIRECT_RECLAIM) && oo_order(oo) > oo_order(s->min)) + alloc_gfp = (alloc_gfp | __GFP_NOMEMALLOC) & ~(__GFP_RECLAIM|__GFP_NOFAIL); + + page = alloc_slab_page(s, alloc_gfp, node, oo); + if (unlikely(!page)) { + oo = s->min; + alloc_gfp = flags; + /* + * Allocation may have failed due to fragmentation. + * Try a lower order alloc if possible + */ + page = alloc_slab_page(s, alloc_gfp, node, oo); + if (unlikely(!page)) + goto out; + stat(s, ORDER_FALLBACK); + } + + page->objects = oo_objects(oo); + + page->slab_cache = s; + __SetPageSlab(page); + if (page_is_pfmemalloc(page)) + SetPageSlabPfmemalloc(page); + + kasan_poison_slab(page); + + start = page_address(page); + + setup_page_debug(s, page, start); + + shuffle = shuffle_freelist(s, page); + + if (!shuffle) { + start = fixup_red_left(s, start); + start = setup_object(s, page, start); + page->freelist = start; + for (idx = 0, p = start; idx < page->objects - 1; idx++) { + next = p + s->size; + next = setup_object(s, page, next); + set_freepointer(s, p, next); + p = next; + } + set_freepointer(s, p, NULL); + } + + page->inuse = page->objects; + page->frozen = 1; + +out: + if (gfpflags_allow_blocking(flags)) + local_irq_disable(); + if (!page) + return NULL; + + inc_slabs_node(s, page_to_nid(page), page->objects); + + return page; +} + +static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node) +{ + if (unlikely(flags & GFP_SLAB_BUG_MASK)) + flags = kmalloc_fix_flags(flags); + + return allocate_slab(s, + flags & (GFP_RECLAIM_MASK | GFP_CONSTRAINT_MASK), node); +} + +static void __free_slab(struct kmem_cache *s, struct page *page) +{ + int order = compound_order(page); + int pages = 1 << order; + + if (kmem_cache_debug_flags(s, SLAB_CONSISTENCY_CHECKS)) { + void *p; + + slab_pad_check(s, page); + for_each_object(p, s, page_address(page), + page->objects) + check_object(s, page, p, SLUB_RED_INACTIVE); + } + + __ClearPageSlabPfmemalloc(page); + __ClearPageSlab(page); + + page->mapping = NULL; + if (current->reclaim_state) + current->reclaim_state->reclaimed_slab += pages; + unaccount_slab_page(page, order, s); + __free_pages(page, order); +} + +static void rcu_free_slab(struct rcu_head *h) +{ + struct page *page = container_of(h, struct page, rcu_head); + + __free_slab(page->slab_cache, page); +} + +static void free_slab(struct kmem_cache *s, struct page *page) +{ + if (unlikely(s->flags & SLAB_TYPESAFE_BY_RCU)) { + call_rcu(&page->rcu_head, rcu_free_slab); + } else + __free_slab(s, page); +} + +static void discard_slab(struct kmem_cache *s, struct page *page) +{ + dec_slabs_node(s, page_to_nid(page), page->objects); + free_slab(s, page); +} + +/* + * Management of partially allocated slabs. + */ +static inline void +__add_partial(struct kmem_cache_node *n, struct page *page, int tail) +{ + n->nr_partial++; + if (tail == DEACTIVATE_TO_TAIL) + list_add_tail(&page->slab_list, &n->partial); + else + list_add(&page->slab_list, &n->partial); +} + +static inline void add_partial(struct kmem_cache_node *n, + struct page *page, int tail) +{ + lockdep_assert_held(&n->list_lock); + __add_partial(n, page, tail); +} + +static inline void remove_partial(struct kmem_cache_node *n, + struct page *page) +{ + lockdep_assert_held(&n->list_lock); + list_del(&page->slab_list); + n->nr_partial--; +} + +/* + * Remove slab from the partial list, freeze it and + * return the pointer to the freelist. + * + * Returns a list of objects or NULL if it fails. + */ +static inline void *acquire_slab(struct kmem_cache *s, + struct kmem_cache_node *n, struct page *page, + int mode, int *objects) +{ + void *freelist; + unsigned long counters; + struct page new; + + lockdep_assert_held(&n->list_lock); + + /* + * Zap the freelist and set the frozen bit. + * The old freelist is the list of objects for the + * per cpu allocation list. + */ + freelist = page->freelist; + counters = page->counters; + new.counters = counters; + *objects = new.objects - new.inuse; + if (mode) { + new.inuse = page->objects; + new.freelist = NULL; + } else { + new.freelist = freelist; + } + + VM_BUG_ON(new.frozen); + new.frozen = 1; + + if (!__cmpxchg_double_slab(s, page, + freelist, counters, + new.freelist, new.counters, + "acquire_slab")) + return NULL; + + remove_partial(n, page); + WARN_ON(!freelist); + return freelist; +} + +static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain); +static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags); + +/* + * Try to allocate a partial slab from a specific node. + */ +static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, + struct kmem_cache_cpu *c, gfp_t flags) +{ + struct page *page, *page2; + void *object = NULL; + unsigned int available = 0; + int objects; + + /* + * Racy check. If we mistakenly see no partial slabs then we + * just allocate an empty slab. If we mistakenly try to get a + * partial slab and there is none available then get_partial() + * will return NULL. + */ + if (!n || !n->nr_partial) + return NULL; + + spin_lock(&n->list_lock); + list_for_each_entry_safe(page, page2, &n->partial, slab_list) { + void *t; + + if (!pfmemalloc_match(page, flags)) + continue; + + t = acquire_slab(s, n, page, object == NULL, &objects); + if (!t) + break; + + available += objects; + if (!object) { + c->page = page; + stat(s, ALLOC_FROM_PARTIAL); + object = t; + } else { + put_cpu_partial(s, page, 0); + stat(s, CPU_PARTIAL_NODE); + } + if (!kmem_cache_has_cpu_partial(s) + || available > slub_cpu_partial(s) / 2) + break; + + } + spin_unlock(&n->list_lock); + return object; +} + +/* + * Get a page from somewhere. Search in increasing NUMA distances. + */ +static void *get_any_partial(struct kmem_cache *s, gfp_t flags, + struct kmem_cache_cpu *c) +{ +#ifdef CONFIG_NUMA + struct zonelist *zonelist; + struct zoneref *z; + struct zone *zone; + enum zone_type highest_zoneidx = gfp_zone(flags); + void *object; + unsigned int cpuset_mems_cookie; + + /* + * The defrag ratio allows a configuration of the tradeoffs between + * inter node defragmentation and node local allocations. A lower + * defrag_ratio increases the tendency to do local allocations + * instead of attempting to obtain partial slabs from other nodes. + * + * If the defrag_ratio is set to 0 then kmalloc() always + * returns node local objects. If the ratio is higher then kmalloc() + * may return off node objects because partial slabs are obtained + * from other nodes and filled up. + * + * If /sys/kernel/slab/xx/remote_node_defrag_ratio is set to 100 + * (which makes defrag_ratio = 1000) then every (well almost) + * allocation will first attempt to defrag slab caches on other nodes. + * This means scanning over all nodes to look for partial slabs which + * may be expensive if we do it every time we are trying to find a slab + * with available objects. + */ + if (!s->remote_node_defrag_ratio || + get_cycles() % 1024 > s->remote_node_defrag_ratio) + return NULL; + + do { + cpuset_mems_cookie = read_mems_allowed_begin(); + zonelist = node_zonelist(mempolicy_slab_node(), flags); + for_each_zone_zonelist(zone, z, zonelist, highest_zoneidx) { + struct kmem_cache_node *n; + + n = get_node(s, zone_to_nid(zone)); + + if (n && cpuset_zone_allowed(zone, flags) && + n->nr_partial > s->min_partial) { + object = get_partial_node(s, n, c, flags); + if (object) { + /* + * Don't check read_mems_allowed_retry() + * here - if mems_allowed was updated in + * parallel, that was a harmless race + * between allocation and the cpuset + * update + */ + return object; + } + } + } + } while (read_mems_allowed_retry(cpuset_mems_cookie)); +#endif /* CONFIG_NUMA */ + return NULL; +} + +/* + * Get a partial page, lock it and return it. + */ +static void *get_partial(struct kmem_cache *s, gfp_t flags, int node, + struct kmem_cache_cpu *c) +{ + void *object; + int searchnode = node; + + if (node == NUMA_NO_NODE) + searchnode = numa_mem_id(); + + object = get_partial_node(s, get_node(s, searchnode), c, flags); + if (object || node != NUMA_NO_NODE) + return object; + + return get_any_partial(s, flags, c); +} + +#ifdef CONFIG_PREEMPTION +/* + * Calculate the next globally unique transaction for disambiguation + * during cmpxchg. The transactions start with the cpu number and are then + * incremented by CONFIG_NR_CPUS. + */ +#define TID_STEP roundup_pow_of_two(CONFIG_NR_CPUS) +#else +/* + * No preemption supported therefore also no need to check for + * different cpus. + */ +#define TID_STEP 1 +#endif + +static inline unsigned long next_tid(unsigned long tid) +{ + return tid + TID_STEP; +} + +#ifdef SLUB_DEBUG_CMPXCHG +static inline unsigned int tid_to_cpu(unsigned long tid) +{ + return tid % TID_STEP; +} + +static inline unsigned long tid_to_event(unsigned long tid) +{ + return tid / TID_STEP; +} +#endif + +static inline unsigned int init_tid(int cpu) +{ + return cpu; +} + +static inline void note_cmpxchg_failure(const char *n, + const struct kmem_cache *s, unsigned long tid) +{ +#ifdef SLUB_DEBUG_CMPXCHG + unsigned long actual_tid = __this_cpu_read(s->cpu_slab->tid); + + pr_info("%s %s: cmpxchg redo ", n, s->name); + +#ifdef CONFIG_PREEMPTION + if (tid_to_cpu(tid) != tid_to_cpu(actual_tid)) + pr_warn("due to cpu change %d -> %d\n", + tid_to_cpu(tid), tid_to_cpu(actual_tid)); + else +#endif + if (tid_to_event(tid) != tid_to_event(actual_tid)) + pr_warn("due to cpu running other code. Event %ld->%ld\n", + tid_to_event(tid), tid_to_event(actual_tid)); + else + pr_warn("for unknown reason: actual=%lx was=%lx target=%lx\n", + actual_tid, tid, next_tid(tid)); +#endif + stat(s, CMPXCHG_DOUBLE_CPU_FAIL); +} + +static void init_kmem_cache_cpus(struct kmem_cache *s) +{ + int cpu; + + for_each_possible_cpu(cpu) + per_cpu_ptr(s->cpu_slab, cpu)->tid = init_tid(cpu); +} + +/* + * Remove the cpu slab + */ +static void deactivate_slab(struct kmem_cache *s, struct page *page, + void *freelist, struct kmem_cache_cpu *c) +{ + enum slab_modes { M_NONE, M_PARTIAL, M_FULL, M_FREE }; + struct kmem_cache_node *n = get_node(s, page_to_nid(page)); + int lock = 0; + enum slab_modes l = M_NONE, m = M_NONE; + void *nextfree; + int tail = DEACTIVATE_TO_HEAD; + struct page new; + struct page old; + + if (page->freelist) { + stat(s, DEACTIVATE_REMOTE_FREES); + tail = DEACTIVATE_TO_TAIL; + } + + /* + * Stage one: Free all available per cpu objects back + * to the page freelist while it is still frozen. Leave the + * last one. + * + * There is no need to take the list->lock because the page + * is still frozen. + */ + while (freelist && (nextfree = get_freepointer(s, freelist))) { + void *prior; + unsigned long counters; + + /* + * If 'nextfree' is invalid, it is possible that the object at + * 'freelist' is already corrupted. So isolate all objects + * starting at 'freelist'. + */ + if (freelist_corrupted(s, page, &freelist, nextfree)) + break; + + do { + prior = page->freelist; + counters = page->counters; + set_freepointer(s, freelist, prior); + new.counters = counters; + new.inuse--; + VM_BUG_ON(!new.frozen); + + } while (!__cmpxchg_double_slab(s, page, + prior, counters, + freelist, new.counters, + "drain percpu freelist")); + + freelist = nextfree; + } + + /* + * Stage two: Ensure that the page is unfrozen while the + * list presence reflects the actual number of objects + * during unfreeze. + * + * We setup the list membership and then perform a cmpxchg + * with the count. If there is a mismatch then the page + * is not unfrozen but the page is on the wrong list. + * + * Then we restart the process which may have to remove + * the page from the list that we just put it on again + * because the number of objects in the slab may have + * changed. + */ +redo: + + old.freelist = page->freelist; + old.counters = page->counters; + VM_BUG_ON(!old.frozen); + + /* Determine target state of the slab */ + new.counters = old.counters; + if (freelist) { + new.inuse--; + set_freepointer(s, freelist, old.freelist); + new.freelist = freelist; + } else + new.freelist = old.freelist; + + new.frozen = 0; + + if (!new.inuse && n->nr_partial >= s->min_partial) + m = M_FREE; + else if (new.freelist) { + m = M_PARTIAL; + if (!lock) { + lock = 1; + /* + * Taking the spinlock removes the possibility + * that acquire_slab() will see a slab page that + * is frozen + */ + spin_lock(&n->list_lock); + } + } else { + m = M_FULL; +#ifdef CONFIG_SLUB_DEBUG + if ((s->flags & SLAB_STORE_USER) && !lock) { + lock = 1; + /* + * This also ensures that the scanning of full + * slabs from diagnostic functions will not see + * any frozen slabs. + */ + spin_lock(&n->list_lock); + } +#endif + } + + if (l != m) { + if (l == M_PARTIAL) + remove_partial(n, page); + else if (l == M_FULL) + remove_full(s, n, page); + + if (m == M_PARTIAL) + add_partial(n, page, tail); + else if (m == M_FULL) + add_full(s, n, page); + } + + l = m; + if (!__cmpxchg_double_slab(s, page, + old.freelist, old.counters, + new.freelist, new.counters, + "unfreezing slab")) + goto redo; + + if (lock) + spin_unlock(&n->list_lock); + + if (m == M_PARTIAL) + stat(s, tail); + else if (m == M_FULL) + stat(s, DEACTIVATE_FULL); + else if (m == M_FREE) { + stat(s, DEACTIVATE_EMPTY); + discard_slab(s, page); + stat(s, FREE_SLAB); + } + + c->page = NULL; + c->freelist = NULL; + c->tid = next_tid(c->tid); +} + +/* + * Unfreeze all the cpu partial slabs. + * + * This function must be called with interrupts disabled + * for the cpu using c (or some other guarantee must be there + * to guarantee no concurrent accesses). + */ +static void unfreeze_partials(struct kmem_cache *s, + struct kmem_cache_cpu *c) +{ +#ifdef CONFIG_SLUB_CPU_PARTIAL + struct kmem_cache_node *n = NULL, *n2 = NULL; + struct page *page, *discard_page = NULL; + + while ((page = slub_percpu_partial(c))) { + struct page new; + struct page old; + + slub_set_percpu_partial(c, page); + + n2 = get_node(s, page_to_nid(page)); + if (n != n2) { + if (n) + spin_unlock(&n->list_lock); + + n = n2; + spin_lock(&n->list_lock); + } + + do { + + old.freelist = page->freelist; + old.counters = page->counters; + VM_BUG_ON(!old.frozen); + + new.counters = old.counters; + new.freelist = old.freelist; + + new.frozen = 0; + + } while (!__cmpxchg_double_slab(s, page, + old.freelist, old.counters, + new.freelist, new.counters, + "unfreezing slab")); + + if (unlikely(!new.inuse && n->nr_partial >= s->min_partial)) { + page->next = discard_page; + discard_page = page; + } else { + add_partial(n, page, DEACTIVATE_TO_TAIL); + stat(s, FREE_ADD_PARTIAL); + } + } + + if (n) + spin_unlock(&n->list_lock); + + while (discard_page) { + page = discard_page; + discard_page = discard_page->next; + + stat(s, DEACTIVATE_EMPTY); + discard_slab(s, page); + stat(s, FREE_SLAB); + } +#endif /* CONFIG_SLUB_CPU_PARTIAL */ +} + +/* + * Put a page that was just frozen (in __slab_free|get_partial_node) into a + * partial page slot if available. + * + * If we did not find a slot then simply move all the partials to the + * per node partial list. + */ +static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) +{ +#ifdef CONFIG_SLUB_CPU_PARTIAL + struct page *oldpage; + int pages; + int pobjects; + + preempt_disable(); + do { + pages = 0; + pobjects = 0; + oldpage = this_cpu_read(s->cpu_slab->partial); + + if (oldpage) { + pobjects = oldpage->pobjects; + pages = oldpage->pages; + if (drain && pobjects > slub_cpu_partial(s)) { + unsigned long flags; + /* + * partial array is full. Move the existing + * set to the per node partial list. + */ + local_irq_save(flags); + unfreeze_partials(s, this_cpu_ptr(s->cpu_slab)); + local_irq_restore(flags); + oldpage = NULL; + pobjects = 0; + pages = 0; + stat(s, CPU_PARTIAL_DRAIN); + } + } + + pages++; + pobjects += page->objects - page->inuse; + + page->pages = pages; + page->pobjects = pobjects; + page->next = oldpage; + + } while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) + != oldpage); + if (unlikely(!slub_cpu_partial(s))) { + unsigned long flags; + + local_irq_save(flags); + unfreeze_partials(s, this_cpu_ptr(s->cpu_slab)); + local_irq_restore(flags); + } + preempt_enable(); +#endif /* CONFIG_SLUB_CPU_PARTIAL */ +} + +static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c) +{ + stat(s, CPUSLAB_FLUSH); + deactivate_slab(s, c->page, c->freelist, c); +} + +/* + * Flush cpu slab. + * + * Called from IPI handler with interrupts disabled. + */ +static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu) +{ + struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu); + + if (c->page) + flush_slab(s, c); + + unfreeze_partials(s, c); +} + +static void flush_cpu_slab(void *d) +{ + struct kmem_cache *s = d; + + __flush_cpu_slab(s, smp_processor_id()); +} + +static bool has_cpu_slab(int cpu, void *info) +{ + struct kmem_cache *s = info; + struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu); + + return c->page || slub_percpu_partial(c); +} + +static void flush_all(struct kmem_cache *s) +{ + on_each_cpu_cond(has_cpu_slab, flush_cpu_slab, s, 1); +} + +/* + * Use the cpu notifier to insure that the cpu slabs are flushed when + * necessary. + */ +static int slub_cpu_dead(unsigned int cpu) +{ + struct kmem_cache *s; + unsigned long flags; + + mutex_lock(&slab_mutex); + list_for_each_entry(s, &slab_caches, list) { + local_irq_save(flags); + __flush_cpu_slab(s, cpu); + local_irq_restore(flags); + } + mutex_unlock(&slab_mutex); + return 0; +} + +/* + * Check if the objects in a per cpu structure fit numa + * locality expectations. + */ +static inline int node_match(struct page *page, int node) +{ +#ifdef CONFIG_NUMA + if (node != NUMA_NO_NODE && page_to_nid(page) != node) + return 0; +#endif + return 1; +} + +#ifdef CONFIG_SLUB_DEBUG +static int count_free(struct page *page) +{ + return page->objects - page->inuse; +} + +static inline unsigned long node_nr_objs(struct kmem_cache_node *n) +{ + return atomic_long_read(&n->total_objects); +} +#endif /* CONFIG_SLUB_DEBUG */ + +#if defined(CONFIG_SLUB_DEBUG) || defined(CONFIG_SYSFS) +static unsigned long count_partial(struct kmem_cache_node *n, + int (*get_count)(struct page *)) +{ + unsigned long flags; + unsigned long x = 0; + struct page *page; + + spin_lock_irqsave(&n->list_lock, flags); + list_for_each_entry(page, &n->partial, slab_list) + x += get_count(page); + spin_unlock_irqrestore(&n->list_lock, flags); + return x; +} +#endif /* CONFIG_SLUB_DEBUG || CONFIG_SYSFS */ + +static noinline void +slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid) +{ +#ifdef CONFIG_SLUB_DEBUG + static DEFINE_RATELIMIT_STATE(slub_oom_rs, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); + int node; + struct kmem_cache_node *n; + + if ((gfpflags & __GFP_NOWARN) || !__ratelimit(&slub_oom_rs)) + return; + + pr_warn("SLUB: Unable to allocate memory on node %d, gfp=%#x(%pGg)\n", + nid, gfpflags, &gfpflags); + pr_warn(" cache: %s, object size: %u, buffer size: %u, default order: %u, min order: %u\n", + s->name, s->object_size, s->size, oo_order(s->oo), + oo_order(s->min)); + + if (oo_order(s->min) > get_order(s->object_size)) + pr_warn(" %s debugging increased min order, use slub_debug=O to disable.\n", + s->name); + + for_each_kmem_cache_node(s, node, n) { + unsigned long nr_slabs; + unsigned long nr_objs; + unsigned long nr_free; + + nr_free = count_partial(n, count_free); + nr_slabs = node_nr_slabs(n); + nr_objs = node_nr_objs(n); + + pr_warn(" node %d: slabs: %ld, objs: %ld, free: %ld\n", + node, nr_slabs, nr_objs, nr_free); + } +#endif +} + +static inline void *new_slab_objects(struct kmem_cache *s, gfp_t flags, + int node, struct kmem_cache_cpu **pc) +{ + void *freelist; + struct kmem_cache_cpu *c = *pc; + struct page *page; + + WARN_ON_ONCE(s->ctor && (flags & __GFP_ZERO)); + + freelist = get_partial(s, flags, node, c); + + if (freelist) + return freelist; + + page = new_slab(s, flags, node); + if (page) { + c = raw_cpu_ptr(s->cpu_slab); + if (c->page) + flush_slab(s, c); + + /* + * No other reference to the page yet so we can + * muck around with it freely without cmpxchg + */ + freelist = page->freelist; + page->freelist = NULL; + + stat(s, ALLOC_SLAB); + c->page = page; + *pc = c; + } + + return freelist; +} + +static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags) +{ + if (unlikely(PageSlabPfmemalloc(page))) + return gfp_pfmemalloc_allowed(gfpflags); + + return true; +} + +/* + * Check the page->freelist of a page and either transfer the freelist to the + * per cpu freelist or deactivate the page. + * + * The page is still frozen if the return value is not NULL. + * + * If this function returns NULL then the page has been unfrozen. + * + * This function must be called with interrupt disabled. + */ +static inline void *get_freelist(struct kmem_cache *s, struct page *page) +{ + struct page new; + unsigned long counters; + void *freelist; + + do { + freelist = page->freelist; + counters = page->counters; + + new.counters = counters; + VM_BUG_ON(!new.frozen); + + new.inuse = page->objects; + new.frozen = freelist != NULL; + + } while (!__cmpxchg_double_slab(s, page, + freelist, counters, + NULL, new.counters, + "get_freelist")); + + return freelist; +} + +/* + * Slow path. The lockless freelist is empty or we need to perform + * debugging duties. + * + * Processing is still very fast if new objects have been freed to the + * regular freelist. In that case we simply take over the regular freelist + * as the lockless freelist and zap the regular freelist. + * + * If that is not working then we fall back to the partial lists. We take the + * first element of the freelist as the object to allocate now and move the + * rest of the freelist to the lockless freelist. + * + * And if we were unable to get a new slab from the partial slab lists then + * we need to allocate a new slab. This is the slowest path since it involves + * a call to the page allocator and the setup of a new slab. + * + * Version of __slab_alloc to use when we know that interrupts are + * already disabled (which is the case for bulk allocation). + */ +static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, + unsigned long addr, struct kmem_cache_cpu *c) +{ + void *freelist; + struct page *page; + + stat(s, ALLOC_SLOWPATH); + + page = c->page; + if (!page) { + /* + * if the node is not online or has no normal memory, just + * ignore the node constraint + */ + if (unlikely(node != NUMA_NO_NODE && + !node_state(node, N_NORMAL_MEMORY))) + node = NUMA_NO_NODE; + goto new_slab; + } +redo: + + if (unlikely(!node_match(page, node))) { + /* + * same as above but node_match() being false already + * implies node != NUMA_NO_NODE + */ + if (!node_state(node, N_NORMAL_MEMORY)) { + node = NUMA_NO_NODE; + goto redo; + } else { + stat(s, ALLOC_NODE_MISMATCH); + deactivate_slab(s, page, c->freelist, c); + goto new_slab; + } + } + + /* + * By rights, we should be searching for a slab page that was + * PFMEMALLOC but right now, we are losing the pfmemalloc + * information when the page leaves the per-cpu allocator + */ + if (unlikely(!pfmemalloc_match(page, gfpflags))) { + deactivate_slab(s, page, c->freelist, c); + goto new_slab; + } + + /* must check again c->freelist in case of cpu migration or IRQ */ + freelist = c->freelist; + if (freelist) + goto load_freelist; + + freelist = get_freelist(s, page); + + if (!freelist) { + c->page = NULL; + c->tid = next_tid(c->tid); + stat(s, DEACTIVATE_BYPASS); + goto new_slab; + } + + stat(s, ALLOC_REFILL); + +load_freelist: + /* + * freelist is pointing to the list of objects to be used. + * page is pointing to the page from which the objects are obtained. + * That page must be frozen for per cpu allocations to work. + */ + VM_BUG_ON(!c->page->frozen); + c->freelist = get_freepointer(s, freelist); + c->tid = next_tid(c->tid); + return freelist; + +new_slab: + + if (slub_percpu_partial(c)) { + page = c->page = slub_percpu_partial(c); + slub_set_percpu_partial(c, page); + stat(s, CPU_PARTIAL_ALLOC); + goto redo; + } + + freelist = new_slab_objects(s, gfpflags, node, &c); + + if (unlikely(!freelist)) { + slab_out_of_memory(s, gfpflags, node); + return NULL; + } + + page = c->page; + if (likely(!kmem_cache_debug(s) && pfmemalloc_match(page, gfpflags))) + goto load_freelist; + + /* Only entered in the debug case */ + if (kmem_cache_debug(s) && + !alloc_debug_processing(s, page, freelist, addr)) + goto new_slab; /* Slab failed checks. Next slab needed */ + + deactivate_slab(s, page, get_freepointer(s, freelist), c); + return freelist; +} + +/* + * Another one that disabled interrupt and compensates for possible + * cpu changes by refetching the per cpu area pointer. + */ +static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, + unsigned long addr, struct kmem_cache_cpu *c) +{ + void *p; + unsigned long flags; + + local_irq_save(flags); +#ifdef CONFIG_PREEMPTION + /* + * We may have been preempted and rescheduled on a different + * cpu before disabling interrupts. Need to reload cpu area + * pointer. + */ + c = this_cpu_ptr(s->cpu_slab); +#endif + + p = ___slab_alloc(s, gfpflags, node, addr, c); + local_irq_restore(flags); + return p; +} + +/* + * If the object has been wiped upon free, make sure it's fully initialized by + * zeroing out freelist pointer. + */ +static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s, + void *obj) +{ + if (unlikely(slab_want_init_on_free(s)) && obj) + memset((void *)((char *)obj + s->offset), 0, sizeof(void *)); +} + +/* + * Inlined fastpath so that allocation functions (kmalloc, kmem_cache_alloc) + * have the fastpath folded into their functions. So no function call + * overhead for requests that can be satisfied on the fastpath. + * + * The fastpath works by first checking if the lockless freelist can be used. + * If not then __slab_alloc is called for slow processing. + * + * Otherwise we can simply pick the next object from the lockless free list. + */ +static __always_inline void *slab_alloc_node(struct kmem_cache *s, + gfp_t gfpflags, int node, unsigned long addr) +{ + void *object; + struct kmem_cache_cpu *c; + struct page *page; + unsigned long tid; + struct obj_cgroup *objcg = NULL; + + s = slab_pre_alloc_hook(s, &objcg, 1, gfpflags); + if (!s) + return NULL; +redo: + /* + * Must read kmem_cache cpu data via this cpu ptr. Preemption is + * enabled. We may switch back and forth between cpus while + * reading from one cpu area. That does not matter as long + * as we end up on the original cpu again when doing the cmpxchg. + * + * We should guarantee that tid and kmem_cache are retrieved on + * the same cpu. It could be different if CONFIG_PREEMPTION so we need + * to check if it is matched or not. + */ + do { + tid = this_cpu_read(s->cpu_slab->tid); + c = raw_cpu_ptr(s->cpu_slab); + } while (IS_ENABLED(CONFIG_PREEMPTION) && + unlikely(tid != READ_ONCE(c->tid))); + + /* + * Irqless object alloc/free algorithm used here depends on sequence + * of fetching cpu_slab's data. tid should be fetched before anything + * on c to guarantee that object and page associated with previous tid + * won't be used with current tid. If we fetch tid first, object and + * page could be one associated with next tid and our alloc/free + * request will be failed. In this case, we will retry. So, no problem. + */ + barrier(); + + /* + * The transaction ids are globally unique per cpu and per operation on + * a per cpu queue. Thus they can be guarantee that the cmpxchg_double + * occurs on the right processor and that there was no operation on the + * linked list in between. + */ + + object = c->freelist; + page = c->page; + if (unlikely(!object || !page || !node_match(page, node))) { + object = __slab_alloc(s, gfpflags, node, addr, c); + } else { + void *next_object = get_freepointer_safe(s, object); + + /* + * The cmpxchg will only match if there was no additional + * operation and if we are on the right processor. + * + * The cmpxchg does the following atomically (without lock + * semantics!) + * 1. Relocate first pointer to the current per cpu area. + * 2. Verify that tid and freelist have not been changed + * 3. If they were not changed replace tid and freelist + * + * Since this is without lock semantics the protection is only + * against code executing on this cpu *not* from access by + * other cpus. + */ + if (unlikely(!this_cpu_cmpxchg_double( + s->cpu_slab->freelist, s->cpu_slab->tid, + object, tid, + next_object, next_tid(tid)))) { + + note_cmpxchg_failure("slab_alloc", s, tid); + goto redo; + } + prefetch_freepointer(s, next_object); + stat(s, ALLOC_FASTPATH); + } + + maybe_wipe_obj_freeptr(s, object); + + if (unlikely(slab_want_init_on_alloc(gfpflags, s)) && object) + memset(object, 0, s->object_size); + + slab_post_alloc_hook(s, objcg, gfpflags, 1, &object); + + return object; +} + +static __always_inline void *slab_alloc(struct kmem_cache *s, + gfp_t gfpflags, unsigned long addr) +{ + return slab_alloc_node(s, gfpflags, NUMA_NO_NODE, addr); +} + +void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags) +{ + void *ret = slab_alloc(s, gfpflags, _RET_IP_); + + trace_kmem_cache_alloc(_RET_IP_, ret, s->object_size, + s->size, gfpflags); + + return ret; +} +EXPORT_SYMBOL(kmem_cache_alloc); + +#ifdef CONFIG_TRACING +void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size) +{ + void *ret = slab_alloc(s, gfpflags, _RET_IP_); + trace_kmalloc(_RET_IP_, ret, size, s->size, gfpflags); + ret = kasan_kmalloc(s, ret, size, gfpflags); + return ret; +} +EXPORT_SYMBOL(kmem_cache_alloc_trace); +#endif + +#ifdef CONFIG_NUMA +void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node) +{ + void *ret = slab_alloc_node(s, gfpflags, node, _RET_IP_); + + trace_kmem_cache_alloc_node(_RET_IP_, ret, + s->object_size, s->size, gfpflags, node); + + return ret; +} +EXPORT_SYMBOL(kmem_cache_alloc_node); + +#ifdef CONFIG_TRACING +void *kmem_cache_alloc_node_trace(struct kmem_cache *s, + gfp_t gfpflags, + int node, size_t size) +{ + void *ret = slab_alloc_node(s, gfpflags, node, _RET_IP_); + + trace_kmalloc_node(_RET_IP_, ret, + size, s->size, gfpflags, node); + + ret = kasan_kmalloc(s, ret, size, gfpflags); + return ret; +} +EXPORT_SYMBOL(kmem_cache_alloc_node_trace); +#endif +#endif /* CONFIG_NUMA */ + +/* + * Slow path handling. This may still be called frequently since objects + * have a longer lifetime than the cpu slabs in most processing loads. + * + * So we still attempt to reduce cache line usage. Just take the slab + * lock and free the item. If there is no additional partial page + * handling required then we can return immediately. + */ +static void __slab_free(struct kmem_cache *s, struct page *page, + void *head, void *tail, int cnt, + unsigned long addr) + +{ + void *prior; + int was_frozen; + struct page new; + unsigned long counters; + struct kmem_cache_node *n = NULL; + unsigned long flags; + + stat(s, FREE_SLOWPATH); + + if (kmem_cache_debug(s) && + !free_debug_processing(s, page, head, tail, cnt, addr)) + return; + + do { + if (unlikely(n)) { + spin_unlock_irqrestore(&n->list_lock, flags); + n = NULL; + } + prior = page->freelist; + counters = page->counters; + set_freepointer(s, tail, prior); + new.counters = counters; + was_frozen = new.frozen; + new.inuse -= cnt; + if ((!new.inuse || !prior) && !was_frozen) { + + if (kmem_cache_has_cpu_partial(s) && !prior) { + + /* + * Slab was on no list before and will be + * partially empty + * We can defer the list move and instead + * freeze it. + */ + new.frozen = 1; + + } else { /* Needs to be taken off a list */ + + n = get_node(s, page_to_nid(page)); + /* + * Speculatively acquire the list_lock. + * If the cmpxchg does not succeed then we may + * drop the list_lock without any processing. + * + * Otherwise the list_lock will synchronize with + * other processors updating the list of slabs. + */ + spin_lock_irqsave(&n->list_lock, flags); + + } + } + + } while (!cmpxchg_double_slab(s, page, + prior, counters, + head, new.counters, + "__slab_free")); + + if (likely(!n)) { + + if (likely(was_frozen)) { + /* + * The list lock was not taken therefore no list + * activity can be necessary. + */ + stat(s, FREE_FROZEN); + } else if (new.frozen) { + /* + * If we just froze the page then put it onto the + * per cpu partial list. + */ + put_cpu_partial(s, page, 1); + stat(s, CPU_PARTIAL_FREE); + } + + return; + } + + if (unlikely(!new.inuse && n->nr_partial >= s->min_partial)) + goto slab_empty; + + /* + * Objects left in the slab. If it was not on the partial list before + * then add it. + */ + if (!kmem_cache_has_cpu_partial(s) && unlikely(!prior)) { + remove_full(s, n, page); + add_partial(n, page, DEACTIVATE_TO_TAIL); + stat(s, FREE_ADD_PARTIAL); + } + spin_unlock_irqrestore(&n->list_lock, flags); + return; + +slab_empty: + if (prior) { + /* + * Slab on the partial list. + */ + remove_partial(n, page); + stat(s, FREE_REMOVE_PARTIAL); + } else { + /* Slab must be on the full list */ + remove_full(s, n, page); + } + + spin_unlock_irqrestore(&n->list_lock, flags); + stat(s, FREE_SLAB); + discard_slab(s, page); +} + +/* + * Fastpath with forced inlining to produce a kfree and kmem_cache_free that + * can perform fastpath freeing without additional function calls. + * + * The fastpath is only possible if we are freeing to the current cpu slab + * of this processor. This typically the case if we have just allocated + * the item before. + * + * If fastpath is not possible then fall back to __slab_free where we deal + * with all sorts of special processing. + * + * Bulk free of a freelist with several objects (all pointing to the + * same page) possible by specifying head and tail ptr, plus objects + * count (cnt). Bulk free indicated by tail pointer being set. + */ +static __always_inline void do_slab_free(struct kmem_cache *s, + struct page *page, void *head, void *tail, + int cnt, unsigned long addr) +{ + void *tail_obj = tail ? : head; + struct kmem_cache_cpu *c; + unsigned long tid; + + /* memcg_slab_free_hook() is already called for bulk free. */ + if (!tail) + memcg_slab_free_hook(s, &head, 1); +redo: + /* + * Determine the currently cpus per cpu slab. + * The cpu may change afterward. However that does not matter since + * data is retrieved via this pointer. If we are on the same cpu + * during the cmpxchg then the free will succeed. + */ + do { + tid = this_cpu_read(s->cpu_slab->tid); + c = raw_cpu_ptr(s->cpu_slab); + } while (IS_ENABLED(CONFIG_PREEMPTION) && + unlikely(tid != READ_ONCE(c->tid))); + + /* Same with comment on barrier() in slab_alloc_node() */ + barrier(); + + if (likely(page == c->page)) { + void **freelist = READ_ONCE(c->freelist); + + set_freepointer(s, tail_obj, freelist); + + if (unlikely(!this_cpu_cmpxchg_double( + s->cpu_slab->freelist, s->cpu_slab->tid, + freelist, tid, + head, next_tid(tid)))) { + + note_cmpxchg_failure("slab_free", s, tid); + goto redo; + } + stat(s, FREE_FASTPATH); + } else + __slab_free(s, page, head, tail_obj, cnt, addr); + +} + +static __always_inline void slab_free(struct kmem_cache *s, struct page *page, + void *head, void *tail, int cnt, + unsigned long addr) +{ + /* + * With KASAN enabled slab_free_freelist_hook modifies the freelist + * to remove objects, whose reuse must be delayed. + */ + if (slab_free_freelist_hook(s, &head, &tail, &cnt)) + do_slab_free(s, page, head, tail, cnt, addr); +} + +#ifdef CONFIG_KASAN_GENERIC +void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr) +{ + do_slab_free(cache, virt_to_head_page(x), x, NULL, 1, addr); +} +#endif + +void kmem_cache_free(struct kmem_cache *s, void *x) +{ + s = cache_from_obj(s, x); + if (!s) + return; + slab_free(s, virt_to_head_page(x), x, NULL, 1, _RET_IP_); + trace_kmem_cache_free(_RET_IP_, x); +} +EXPORT_SYMBOL(kmem_cache_free); + +struct detached_freelist { + struct page *page; + void *tail; + void *freelist; + int cnt; + struct kmem_cache *s; +}; + +/* + * This function progressively scans the array with free objects (with + * a limited look ahead) and extract objects belonging to the same + * page. It builds a detached freelist directly within the given + * page/objects. This can happen without any need for + * synchronization, because the objects are owned by running process. + * The freelist is build up as a single linked list in the objects. + * The idea is, that this detached freelist can then be bulk + * transferred to the real freelist(s), but only requiring a single + * synchronization primitive. Look ahead in the array is limited due + * to performance reasons. + */ +static inline +int build_detached_freelist(struct kmem_cache *s, size_t size, + void **p, struct detached_freelist *df) +{ + size_t first_skipped_index = 0; + int lookahead = 3; + void *object; + struct page *page; + + /* Always re-init detached_freelist */ + df->page = NULL; + + do { + object = p[--size]; + /* Do we need !ZERO_OR_NULL_PTR(object) here? (for kfree) */ + } while (!object && size); + + if (!object) + return 0; + + page = virt_to_head_page(object); + if (!s) { + /* Handle kalloc'ed objects */ + if (unlikely(!PageSlab(page))) { + BUG_ON(!PageCompound(page)); + kfree_hook(object); + __free_pages(page, compound_order(page)); + p[size] = NULL; /* mark object processed */ + return size; + } + /* Derive kmem_cache from object */ + df->s = page->slab_cache; + } else { + df->s = cache_from_obj(s, object); /* Support for memcg */ + } + + /* Start new detached freelist */ + df->page = page; + set_freepointer(df->s, object, NULL); + df->tail = object; + df->freelist = object; + p[size] = NULL; /* mark object processed */ + df->cnt = 1; + + while (size) { + object = p[--size]; + if (!object) + continue; /* Skip processed objects */ + + /* df->page is always set at this point */ + if (df->page == virt_to_head_page(object)) { + /* Opportunity build freelist */ + set_freepointer(df->s, object, df->freelist); + df->freelist = object; + df->cnt++; + p[size] = NULL; /* mark object processed */ + + continue; + } + + /* Limit look ahead search */ + if (!--lookahead) + break; + + if (!first_skipped_index) + first_skipped_index = size + 1; + } + + return first_skipped_index; +} + +/* Note that interrupts must be enabled when calling this function. */ +void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p) +{ + if (WARN_ON(!size)) + return; + + memcg_slab_free_hook(s, p, size); + do { + struct detached_freelist df; + + size = build_detached_freelist(s, size, p, &df); + if (!df.page) + continue; + + slab_free(df.s, df.page, df.freelist, df.tail, df.cnt,_RET_IP_); + } while (likely(size)); +} +EXPORT_SYMBOL(kmem_cache_free_bulk); + +/* Note that interrupts must be enabled when calling this function. */ +int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, + void **p) +{ + struct kmem_cache_cpu *c; + int i; + struct obj_cgroup *objcg = NULL; + + /* memcg and kmem_cache debug support */ + s = slab_pre_alloc_hook(s, &objcg, size, flags); + if (unlikely(!s)) + return false; + /* + * Drain objects in the per cpu slab, while disabling local + * IRQs, which protects against PREEMPT and interrupts + * handlers invoking normal fastpath. + */ + local_irq_disable(); + c = this_cpu_ptr(s->cpu_slab); + + for (i = 0; i < size; i++) { + void *object = c->freelist; + + if (unlikely(!object)) { + /* + * We may have removed an object from c->freelist using + * the fastpath in the previous iteration; in that case, + * c->tid has not been bumped yet. + * Since ___slab_alloc() may reenable interrupts while + * allocating memory, we should bump c->tid now. + */ + c->tid = next_tid(c->tid); + + /* + * Invoking slow path likely have side-effect + * of re-populating per CPU c->freelist + */ + p[i] = ___slab_alloc(s, flags, NUMA_NO_NODE, + _RET_IP_, c); + if (unlikely(!p[i])) + goto error; + + c = this_cpu_ptr(s->cpu_slab); + maybe_wipe_obj_freeptr(s, p[i]); + + continue; /* goto for-loop */ + } + c->freelist = get_freepointer(s, object); + p[i] = object; + maybe_wipe_obj_freeptr(s, p[i]); + } + c->tid = next_tid(c->tid); + local_irq_enable(); + + /* Clear memory outside IRQ disabled fastpath loop */ + if (unlikely(slab_want_init_on_alloc(flags, s))) { + int j; + + for (j = 0; j < i; j++) + memset(p[j], 0, s->object_size); + } + + /* memcg and kmem_cache debug support */ + slab_post_alloc_hook(s, objcg, flags, size, p); + return i; +error: + local_irq_enable(); + slab_post_alloc_hook(s, objcg, flags, i, p); + __kmem_cache_free_bulk(s, i, p); + return 0; +} +EXPORT_SYMBOL(kmem_cache_alloc_bulk); + + +/* + * Object placement in a slab is made very easy because we always start at + * offset 0. If we tune the size of the object to the alignment then we can + * get the required alignment by putting one properly sized object after + * another. + * + * Notice that the allocation order determines the sizes of the per cpu + * caches. Each processor has always one slab available for allocations. + * Increasing the allocation order reduces the number of times that slabs + * must be moved on and off the partial lists and is therefore a factor in + * locking overhead. + */ + +/* + * Mininum / Maximum order of slab pages. This influences locking overhead + * and slab fragmentation. A higher order reduces the number of partial slabs + * and increases the number of allocations possible without having to + * take the list_lock. + */ +static unsigned int slub_min_order; +static unsigned int slub_max_order = PAGE_ALLOC_COSTLY_ORDER; +static unsigned int slub_min_objects; + +/* + * Calculate the order of allocation given an slab object size. + * + * The order of allocation has significant impact on performance and other + * system components. Generally order 0 allocations should be preferred since + * order 0 does not cause fragmentation in the page allocator. Larger objects + * be problematic to put into order 0 slabs because there may be too much + * unused space left. We go to a higher order if more than 1/16th of the slab + * would be wasted. + * + * In order to reach satisfactory performance we must ensure that a minimum + * number of objects is in one slab. Otherwise we may generate too much + * activity on the partial lists which requires taking the list_lock. This is + * less a concern for large slabs though which are rarely used. + * + * slub_max_order specifies the order where we begin to stop considering the + * number of objects in a slab as critical. If we reach slub_max_order then + * we try to keep the page order as low as possible. So we accept more waste + * of space in favor of a small page order. + * + * Higher order allocations also allow the placement of more objects in a + * slab and thereby reduce object handling overhead. If the user has + * requested a higher mininum order then we start with that one instead of + * the smallest order which will fit the object. + */ +static inline unsigned int slab_order(unsigned int size, + unsigned int min_objects, unsigned int max_order, + unsigned int fract_leftover) +{ + unsigned int min_order = slub_min_order; + unsigned int order; + + if (order_objects(min_order, size) > MAX_OBJS_PER_PAGE) + return get_order(size * MAX_OBJS_PER_PAGE) - 1; + + for (order = max(min_order, (unsigned int)get_order(min_objects * size)); + order <= max_order; order++) { + + unsigned int slab_size = (unsigned int)PAGE_SIZE << order; + unsigned int rem; + + rem = slab_size % size; + + if (rem <= slab_size / fract_leftover) + break; + } + + return order; +} + +static inline int calculate_order(unsigned int size) +{ + unsigned int order; + unsigned int min_objects; + unsigned int max_objects; + + /* + * Attempt to find best configuration for a slab. This + * works by first attempting to generate a layout with + * the best configuration and backing off gradually. + * + * First we increase the acceptable waste in a slab. Then + * we reduce the minimum objects required in a slab. + */ + min_objects = slub_min_objects; + if (!min_objects) + min_objects = 4 * (fls(nr_cpu_ids) + 1); + max_objects = order_objects(slub_max_order, size); + min_objects = min(min_objects, max_objects); + + while (min_objects > 1) { + unsigned int fraction; + + fraction = 16; + while (fraction >= 4) { + order = slab_order(size, min_objects, + slub_max_order, fraction); + if (order <= slub_max_order) + return order; + fraction /= 2; + } + min_objects--; + } + + /* + * We were unable to place multiple objects in a slab. Now + * lets see if we can place a single object there. + */ + order = slab_order(size, 1, slub_max_order, 1); + if (order <= slub_max_order) + return order; + + /* + * Doh this slab cannot be placed using slub_max_order. + */ + order = slab_order(size, 1, MAX_ORDER, 1); + if (order < MAX_ORDER) + return order; + return -ENOSYS; +} + +static void +init_kmem_cache_node(struct kmem_cache_node *n) +{ + n->nr_partial = 0; + spin_lock_init(&n->list_lock); + INIT_LIST_HEAD(&n->partial); +#ifdef CONFIG_SLUB_DEBUG + atomic_long_set(&n->nr_slabs, 0); + atomic_long_set(&n->total_objects, 0); + INIT_LIST_HEAD(&n->full); +#endif +} + +static inline int alloc_kmem_cache_cpus(struct kmem_cache *s) +{ + BUILD_BUG_ON(PERCPU_DYNAMIC_EARLY_SIZE < + KMALLOC_SHIFT_HIGH * sizeof(struct kmem_cache_cpu)); + + /* + * Must align to double word boundary for the double cmpxchg + * instructions to work; see __pcpu_double_call_return_bool(). + */ + s->cpu_slab = __alloc_percpu(sizeof(struct kmem_cache_cpu), + 2 * sizeof(void *)); + + if (!s->cpu_slab) + return 0; + + init_kmem_cache_cpus(s); + + return 1; +} + +static struct kmem_cache *kmem_cache_node; + +/* + * No kmalloc_node yet so do it by hand. We know that this is the first + * slab on the node for this slabcache. There are no concurrent accesses + * possible. + * + * Note that this function only works on the kmem_cache_node + * when allocating for the kmem_cache_node. This is used for bootstrapping + * memory on a fresh node that has no slab structures yet. + */ +static void early_kmem_cache_node_alloc(int node) +{ + struct page *page; + struct kmem_cache_node *n; + + BUG_ON(kmem_cache_node->size < sizeof(struct kmem_cache_node)); + + page = new_slab(kmem_cache_node, GFP_NOWAIT, node); + + BUG_ON(!page); + if (page_to_nid(page) != node) { + pr_err("SLUB: Unable to allocate memory from node %d\n", node); + pr_err("SLUB: Allocating a useless per node structure in order to be able to continue\n"); + } + + n = page->freelist; + BUG_ON(!n); +#ifdef CONFIG_SLUB_DEBUG + init_object(kmem_cache_node, n, SLUB_RED_ACTIVE); + init_tracking(kmem_cache_node, n); +#endif + n = kasan_kmalloc(kmem_cache_node, n, sizeof(struct kmem_cache_node), + GFP_KERNEL); + page->freelist = get_freepointer(kmem_cache_node, n); + page->inuse = 1; + page->frozen = 0; + kmem_cache_node->node[node] = n; + init_kmem_cache_node(n); + inc_slabs_node(kmem_cache_node, node, page->objects); + + /* + * No locks need to be taken here as it has just been + * initialized and there is no concurrent access. + */ + __add_partial(n, page, DEACTIVATE_TO_HEAD); +} + +static void free_kmem_cache_nodes(struct kmem_cache *s) +{ + int node; + struct kmem_cache_node *n; + + for_each_kmem_cache_node(s, node, n) { + s->node[node] = NULL; + kmem_cache_free(kmem_cache_node, n); + } +} + +void __kmem_cache_release(struct kmem_cache *s) +{ + cache_random_seq_destroy(s); + free_percpu(s->cpu_slab); + free_kmem_cache_nodes(s); +} + +static int init_kmem_cache_nodes(struct kmem_cache *s) +{ + int node; + + for_each_node_state(node, N_NORMAL_MEMORY) { + struct kmem_cache_node *n; + + if (slab_state == DOWN) { + early_kmem_cache_node_alloc(node); + continue; + } + n = kmem_cache_alloc_node(kmem_cache_node, + GFP_KERNEL, node); + + if (!n) { + free_kmem_cache_nodes(s); + return 0; + } + + init_kmem_cache_node(n); + s->node[node] = n; + } + return 1; +} + +static void set_min_partial(struct kmem_cache *s, unsigned long min) +{ + if (min < MIN_PARTIAL) + min = MIN_PARTIAL; + else if (min > MAX_PARTIAL) + min = MAX_PARTIAL; + s->min_partial = min; +} + +static void set_cpu_partial(struct kmem_cache *s) +{ +#ifdef CONFIG_SLUB_CPU_PARTIAL + /* + * cpu_partial determined the maximum number of objects kept in the + * per cpu partial lists of a processor. + * + * Per cpu partial lists mainly contain slabs that just have one + * object freed. If they are used for allocation then they can be + * filled up again with minimal effort. The slab will never hit the + * per node partial lists and therefore no locking will be required. + * + * This setting also determines + * + * A) The number of objects from per cpu partial slabs dumped to the + * per node list when we reach the limit. + * B) The number of objects in cpu partial slabs to extract from the + * per node list when we run out of per cpu objects. We only fetch + * 50% to keep some capacity around for frees. + */ + if (!kmem_cache_has_cpu_partial(s)) + slub_set_cpu_partial(s, 0); + else if (s->size >= PAGE_SIZE) + slub_set_cpu_partial(s, 2); + else if (s->size >= 1024) + slub_set_cpu_partial(s, 6); + else if (s->size >= 256) + slub_set_cpu_partial(s, 13); + else + slub_set_cpu_partial(s, 30); +#endif +} + +/* + * calculate_sizes() determines the order and the distribution of data within + * a slab object. + */ +static int calculate_sizes(struct kmem_cache *s, int forced_order) +{ + slab_flags_t flags = s->flags; + unsigned int size = s->object_size; + unsigned int order; + + /* + * Round up object size to the next word boundary. We can only + * place the free pointer at word boundaries and this determines + * the possible location of the free pointer. + */ + size = ALIGN(size, sizeof(void *)); + +#ifdef CONFIG_SLUB_DEBUG + /* + * Determine if we can poison the object itself. If the user of + * the slab may touch the object after free or before allocation + * then we should never poison the object itself. + */ + if ((flags & SLAB_POISON) && !(flags & SLAB_TYPESAFE_BY_RCU) && + !s->ctor) + s->flags |= __OBJECT_POISON; + else + s->flags &= ~__OBJECT_POISON; + + + /* + * If we are Redzoning then check if there is some space between the + * end of the object and the free pointer. If not then add an + * additional word to have some bytes to store Redzone information. + */ + if ((flags & SLAB_RED_ZONE) && size == s->object_size) + size += sizeof(void *); +#endif + + /* + * With that we have determined the number of bytes in actual use + * by the object and redzoning. + */ + s->inuse = size; + + if ((flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)) || + ((flags & SLAB_RED_ZONE) && s->object_size < sizeof(void *)) || + s->ctor) { + /* + * Relocate free pointer after the object if it is not + * permitted to overwrite the first word of the object on + * kmem_cache_free. + * + * This is the case if we do RCU, have a constructor or + * destructor, are poisoning the objects, or are + * redzoning an object smaller than sizeof(void *). + * + * The assumption that s->offset >= s->inuse means free + * pointer is outside of the object is used in the + * freeptr_outside_object() function. If that is no + * longer true, the function needs to be modified. + */ + s->offset = size; + size += sizeof(void *); + } else { + /* + * Store freelist pointer near middle of object to keep + * it away from the edges of the object to avoid small + * sized over/underflows from neighboring allocations. + */ + s->offset = ALIGN_DOWN(s->object_size / 2, sizeof(void *)); + } + +#ifdef CONFIG_SLUB_DEBUG + if (flags & SLAB_STORE_USER) + /* + * Need to store information about allocs and frees after + * the object. + */ + size += 2 * sizeof(struct track); +#endif + + kasan_cache_create(s, &size, &s->flags); +#ifdef CONFIG_SLUB_DEBUG + if (flags & SLAB_RED_ZONE) { + /* + * Add some empty padding so that we can catch + * overwrites from earlier objects rather than let + * tracking information or the free pointer be + * corrupted if a user writes before the start + * of the object. + */ + size += sizeof(void *); + + s->red_left_pad = sizeof(void *); + s->red_left_pad = ALIGN(s->red_left_pad, s->align); + size += s->red_left_pad; + } +#endif + + /* + * SLUB stores one object immediately after another beginning from + * offset 0. In order to align the objects we have to simply size + * each object to conform to the alignment. + */ + size = ALIGN(size, s->align); + s->size = size; + s->reciprocal_size = reciprocal_value(size); + if (forced_order >= 0) + order = forced_order; + else + order = calculate_order(size); + + if ((int)order < 0) + return 0; + + s->allocflags = 0; + if (order) + s->allocflags |= __GFP_COMP; + + if (s->flags & SLAB_CACHE_DMA) + s->allocflags |= GFP_DMA; + + if (s->flags & SLAB_CACHE_DMA32) + s->allocflags |= GFP_DMA32; + + if (s->flags & SLAB_RECLAIM_ACCOUNT) + s->allocflags |= __GFP_RECLAIMABLE; + + /* + * Determine the number of objects per slab + */ + s->oo = oo_make(order, size); + s->min = oo_make(get_order(size), size); + if (oo_objects(s->oo) > oo_objects(s->max)) + s->max = s->oo; + + return !!oo_objects(s->oo); +} + +static int kmem_cache_open(struct kmem_cache *s, slab_flags_t flags) +{ + s->flags = kmem_cache_flags(s->size, flags, s->name); +#ifdef CONFIG_SLAB_FREELIST_HARDENED + s->random = get_random_long(); +#endif + + if (!calculate_sizes(s, -1)) + goto error; + if (disable_higher_order_debug) { + /* + * Disable debugging flags that store metadata if the min slab + * order increased. + */ + if (get_order(s->size) > get_order(s->object_size)) { + s->flags &= ~DEBUG_METADATA_FLAGS; + s->offset = 0; + if (!calculate_sizes(s, -1)) + goto error; + } + } + +#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \ + defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE) + if (system_has_cmpxchg_double() && (s->flags & SLAB_NO_CMPXCHG) == 0) + /* Enable fast mode */ + s->flags |= __CMPXCHG_DOUBLE; +#endif + + /* + * The larger the object size is, the more pages we want on the partial + * list to avoid pounding the page allocator excessively. + */ + set_min_partial(s, ilog2(s->size) / 2); + + set_cpu_partial(s); + +#ifdef CONFIG_NUMA + s->remote_node_defrag_ratio = 1000; +#endif + + /* Initialize the pre-computed randomized freelist if slab is up */ + if (slab_state >= UP) { + if (init_cache_random_seq(s)) + goto error; + } + + if (!init_kmem_cache_nodes(s)) + goto error; + + if (alloc_kmem_cache_cpus(s)) + return 0; + +error: + __kmem_cache_release(s); + return -EINVAL; +} + +static void list_slab_objects(struct kmem_cache *s, struct page *page, + const char *text) +{ +#ifdef CONFIG_SLUB_DEBUG + void *addr = page_address(page); + unsigned long *map; + void *p; + + slab_err(s, page, text, s->name); + slab_lock(page); + + map = get_map(s, page); + for_each_object(p, s, addr, page->objects) { + + if (!test_bit(__obj_to_index(s, addr, p), map)) { + pr_err("INFO: Object 0x%p @offset=%tu\n", p, p - addr); + print_tracking(s, p); + } + } + put_map(map); + slab_unlock(page); +#endif +} + +/* + * Attempt to free all partial slabs on a node. + * This is called from __kmem_cache_shutdown(). We must take list_lock + * because sysfs file might still access partial list after the shutdowning. + */ +static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n) +{ + LIST_HEAD(discard); + struct page *page, *h; + + BUG_ON(irqs_disabled()); + spin_lock_irq(&n->list_lock); + list_for_each_entry_safe(page, h, &n->partial, slab_list) { + if (!page->inuse) { + remove_partial(n, page); + list_add(&page->slab_list, &discard); + } else { + list_slab_objects(s, page, + "Objects remaining in %s on __kmem_cache_shutdown()"); + } + } + spin_unlock_irq(&n->list_lock); + + list_for_each_entry_safe(page, h, &discard, slab_list) + discard_slab(s, page); +} + +bool __kmem_cache_empty(struct kmem_cache *s) +{ + int node; + struct kmem_cache_node *n; + + for_each_kmem_cache_node(s, node, n) + if (n->nr_partial || slabs_node(s, node)) + return false; + return true; +} + +/* + * Release all resources used by a slab cache. + */ +int __kmem_cache_shutdown(struct kmem_cache *s) +{ + int node; + struct kmem_cache_node *n; + + flush_all(s); + /* Attempt to free all objects */ + for_each_kmem_cache_node(s, node, n) { + free_partial(s, n); + if (n->nr_partial || slabs_node(s, node)) + return 1; + } + return 0; +} + +/******************************************************************** + * Kmalloc subsystem + *******************************************************************/ + +static int __init setup_slub_min_order(char *str) +{ + get_option(&str, (int *)&slub_min_order); + + return 1; +} + +__setup("slub_min_order=", setup_slub_min_order); + +static int __init setup_slub_max_order(char *str) +{ + get_option(&str, (int *)&slub_max_order); + slub_max_order = min(slub_max_order, (unsigned int)MAX_ORDER - 1); + + return 1; +} + +__setup("slub_max_order=", setup_slub_max_order); + +static int __init setup_slub_min_objects(char *str) +{ + get_option(&str, (int *)&slub_min_objects); + + return 1; +} + +__setup("slub_min_objects=", setup_slub_min_objects); + +void *__kmalloc(size_t size, gfp_t flags) +{ + struct kmem_cache *s; + void *ret; + + if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) + return kmalloc_large(size, flags); + + s = kmalloc_slab(size, flags); + + if (unlikely(ZERO_OR_NULL_PTR(s))) + return s; + + ret = slab_alloc(s, flags, _RET_IP_); + + trace_kmalloc(_RET_IP_, ret, size, s->size, flags); + + ret = kasan_kmalloc(s, ret, size, flags); + + return ret; +} +EXPORT_SYMBOL(__kmalloc); + +#ifdef CONFIG_NUMA +static void *kmalloc_large_node(size_t size, gfp_t flags, int node) +{ + struct page *page; + void *ptr = NULL; + unsigned int order = get_order(size); + + flags |= __GFP_COMP; + page = alloc_pages_node(node, flags, order); + if (page) { + ptr = page_address(page); + mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B, + PAGE_SIZE << order); + } + + return kmalloc_large_node_hook(ptr, size, flags); +} + +void *__kmalloc_node(size_t size, gfp_t flags, int node) +{ + struct kmem_cache *s; + void *ret; + + if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) { + ret = kmalloc_large_node(size, flags, node); + + trace_kmalloc_node(_RET_IP_, ret, + size, PAGE_SIZE << get_order(size), + flags, node); + + return ret; + } + + s = kmalloc_slab(size, flags); + + if (unlikely(ZERO_OR_NULL_PTR(s))) + return s; + + ret = slab_alloc_node(s, flags, node, _RET_IP_); + + trace_kmalloc_node(_RET_IP_, ret, size, s->size, flags, node); + + ret = kasan_kmalloc(s, ret, size, flags); + + return ret; +} +EXPORT_SYMBOL(__kmalloc_node); +#endif /* CONFIG_NUMA */ + +#ifdef CONFIG_HARDENED_USERCOPY +/* + * Rejects incorrectly sized objects and objects that are to be copied + * to/from userspace but do not fall entirely within the containing slab + * cache's usercopy region. + * + * Returns NULL if check passes, otherwise const char * to name of cache + * to indicate an error. + */ +void __check_heap_object(const void *ptr, unsigned long n, struct page *page, + bool to_user) +{ + struct kmem_cache *s; + unsigned int offset; + size_t object_size; + + ptr = kasan_reset_tag(ptr); + + /* Find object and usable object size. */ + s = page->slab_cache; + + /* Reject impossible pointers. */ + if (ptr < page_address(page)) + usercopy_abort("SLUB object not in SLUB page?!", NULL, + to_user, 0, n); + + /* Find offset within object. */ + offset = (ptr - page_address(page)) % s->size; + + /* Adjust for redzone and reject if within the redzone. */ + if (kmem_cache_debug_flags(s, SLAB_RED_ZONE)) { + if (offset < s->red_left_pad) + usercopy_abort("SLUB object in left red zone", + s->name, to_user, offset, n); + offset -= s->red_left_pad; + } + + /* Allow address range falling entirely within usercopy region. */ + if (offset >= s->useroffset && + offset - s->useroffset <= s->usersize && + n <= s->useroffset - offset + s->usersize) + return; + + /* + * If the copy is still within the allocated object, produce + * a warning instead of rejecting the copy. This is intended + * to be a temporary method to find any missing usercopy + * whitelists. + */ + object_size = slab_ksize(s); + if (usercopy_fallback && + offset <= object_size && n <= object_size - offset) { + usercopy_warn("SLUB object", s->name, to_user, offset, n); + return; + } + + usercopy_abort("SLUB object", s->name, to_user, offset, n); +} +#endif /* CONFIG_HARDENED_USERCOPY */ + +size_t __ksize(const void *object) +{ + struct page *page; + + if (unlikely(object == ZERO_SIZE_PTR)) + return 0; + + page = virt_to_head_page(object); + + if (unlikely(!PageSlab(page))) { + WARN_ON(!PageCompound(page)); + return page_size(page); + } + + return slab_ksize(page->slab_cache); +} +EXPORT_SYMBOL(__ksize); + +void kfree(const void *x) +{ + struct page *page; + void *object = (void *)x; + + trace_kfree(_RET_IP_, x); + + if (unlikely(ZERO_OR_NULL_PTR(x))) + return; + + page = virt_to_head_page(x); + if (unlikely(!PageSlab(page))) { + unsigned int order = compound_order(page); + + BUG_ON(!PageCompound(page)); + kfree_hook(object); + mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B, + -(PAGE_SIZE << order)); + __free_pages(page, order); + return; + } + slab_free(page->slab_cache, page, object, NULL, 1, _RET_IP_); +} +EXPORT_SYMBOL(kfree); + +#define SHRINK_PROMOTE_MAX 32 + +/* + * kmem_cache_shrink discards empty slabs and promotes the slabs filled + * up most to the head of the partial lists. New allocations will then + * fill those up and thus they can be removed from the partial lists. + * + * The slabs with the least items are placed last. This results in them + * being allocated from last increasing the chance that the last objects + * are freed in them. + */ +int __kmem_cache_shrink(struct kmem_cache *s) +{ + int node; + int i; + struct kmem_cache_node *n; + struct page *page; + struct page *t; + struct list_head discard; + struct list_head promote[SHRINK_PROMOTE_MAX]; + unsigned long flags; + int ret = 0; + + flush_all(s); + for_each_kmem_cache_node(s, node, n) { + INIT_LIST_HEAD(&discard); + for (i = 0; i < SHRINK_PROMOTE_MAX; i++) + INIT_LIST_HEAD(promote + i); + + spin_lock_irqsave(&n->list_lock, flags); + + /* + * Build lists of slabs to discard or promote. + * + * Note that concurrent frees may occur while we hold the + * list_lock. page->inuse here is the upper limit. + */ + list_for_each_entry_safe(page, t, &n->partial, slab_list) { + int free = page->objects - page->inuse; + + /* Do not reread page->inuse */ + barrier(); + + /* We do not keep full slabs on the list */ + BUG_ON(free <= 0); + + if (free == page->objects) { + list_move(&page->slab_list, &discard); + n->nr_partial--; + } else if (free <= SHRINK_PROMOTE_MAX) + list_move(&page->slab_list, promote + free - 1); + } + + /* + * Promote the slabs filled up most to the head of the + * partial list. + */ + for (i = SHRINK_PROMOTE_MAX - 1; i >= 0; i--) + list_splice(promote + i, &n->partial); + + spin_unlock_irqrestore(&n->list_lock, flags); + + /* Release empty slabs */ + list_for_each_entry_safe(page, t, &discard, slab_list) + discard_slab(s, page); + + if (slabs_node(s, node)) + ret = 1; + } + + return ret; +} + +static int slab_mem_going_offline_callback(void *arg) +{ + struct kmem_cache *s; + + mutex_lock(&slab_mutex); + list_for_each_entry(s, &slab_caches, list) + __kmem_cache_shrink(s); + mutex_unlock(&slab_mutex); + + return 0; +} + +static void slab_mem_offline_callback(void *arg) +{ + struct kmem_cache_node *n; + struct kmem_cache *s; + struct memory_notify *marg = arg; + int offline_node; + + offline_node = marg->status_change_nid_normal; + + /* + * If the node still has available memory. we need kmem_cache_node + * for it yet. + */ + if (offline_node < 0) + return; + + mutex_lock(&slab_mutex); + list_for_each_entry(s, &slab_caches, list) { + n = get_node(s, offline_node); + if (n) { + /* + * if n->nr_slabs > 0, slabs still exist on the node + * that is going down. We were unable to free them, + * and offline_pages() function shouldn't call this + * callback. So, we must fail. + */ + BUG_ON(slabs_node(s, offline_node)); + + s->node[offline_node] = NULL; + kmem_cache_free(kmem_cache_node, n); + } + } + mutex_unlock(&slab_mutex); +} + +static int slab_mem_going_online_callback(void *arg) +{ + struct kmem_cache_node *n; + struct kmem_cache *s; + struct memory_notify *marg = arg; + int nid = marg->status_change_nid_normal; + int ret = 0; + + /* + * If the node's memory is already available, then kmem_cache_node is + * already created. Nothing to do. + */ + if (nid < 0) + return 0; + + /* + * We are bringing a node online. No memory is available yet. We must + * allocate a kmem_cache_node structure in order to bring the node + * online. + */ + mutex_lock(&slab_mutex); + list_for_each_entry(s, &slab_caches, list) { + /* + * XXX: kmem_cache_alloc_node will fallback to other nodes + * since memory is not yet available from the node that + * is brought up. + */ + n = kmem_cache_alloc(kmem_cache_node, GFP_KERNEL); + if (!n) { + ret = -ENOMEM; + goto out; + } + init_kmem_cache_node(n); + s->node[nid] = n; + } +out: + mutex_unlock(&slab_mutex); + return ret; +} + +static int slab_memory_callback(struct notifier_block *self, + unsigned long action, void *arg) +{ + int ret = 0; + + switch (action) { + case MEM_GOING_ONLINE: + ret = slab_mem_going_online_callback(arg); + break; + case MEM_GOING_OFFLINE: + ret = slab_mem_going_offline_callback(arg); + break; + case MEM_OFFLINE: + case MEM_CANCEL_ONLINE: + slab_mem_offline_callback(arg); + break; + case MEM_ONLINE: + case MEM_CANCEL_OFFLINE: + break; + } + if (ret) + ret = notifier_from_errno(ret); + else + ret = NOTIFY_OK; + return ret; +} + +static struct notifier_block slab_memory_callback_nb = { + .notifier_call = slab_memory_callback, + .priority = SLAB_CALLBACK_PRI, +}; + +/******************************************************************** + * Basic setup of slabs + *******************************************************************/ + +/* + * Used for early kmem_cache structures that were allocated using + * the page allocator. Allocate them properly then fix up the pointers + * that may be pointing to the wrong kmem_cache structure. + */ + +static struct kmem_cache * __init bootstrap(struct kmem_cache *static_cache) +{ + int node; + struct kmem_cache *s = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT); + struct kmem_cache_node *n; + + memcpy(s, static_cache, kmem_cache->object_size); + + /* + * This runs very early, and only the boot processor is supposed to be + * up. Even if it weren't true, IRQs are not up so we couldn't fire + * IPIs around. + */ + __flush_cpu_slab(s, smp_processor_id()); + for_each_kmem_cache_node(s, node, n) { + struct page *p; + + list_for_each_entry(p, &n->partial, slab_list) + p->slab_cache = s; + +#ifdef CONFIG_SLUB_DEBUG + list_for_each_entry(p, &n->full, slab_list) + p->slab_cache = s; +#endif + } + list_add(&s->list, &slab_caches); + return s; +} + +void __init kmem_cache_init(void) +{ + static __initdata struct kmem_cache boot_kmem_cache, + boot_kmem_cache_node; + + if (debug_guardpage_minorder()) + slub_max_order = 0; + + kmem_cache_node = &boot_kmem_cache_node; + kmem_cache = &boot_kmem_cache; + + create_boot_cache(kmem_cache_node, "kmem_cache_node", + sizeof(struct kmem_cache_node), SLAB_HWCACHE_ALIGN, 0, 0); + + register_hotmemory_notifier(&slab_memory_callback_nb); + + /* Able to allocate the per node structures */ + slab_state = PARTIAL; + + create_boot_cache(kmem_cache, "kmem_cache", + offsetof(struct kmem_cache, node) + + nr_node_ids * sizeof(struct kmem_cache_node *), + SLAB_HWCACHE_ALIGN, 0, 0); + + kmem_cache = bootstrap(&boot_kmem_cache); + kmem_cache_node = bootstrap(&boot_kmem_cache_node); + + /* Now we can use the kmem_cache to allocate kmalloc slabs */ + setup_kmalloc_cache_index_table(); + create_kmalloc_caches(0); + + /* Setup random freelists for each cache */ + init_freelist_randomization(); + + cpuhp_setup_state_nocalls(CPUHP_SLUB_DEAD, "slub:dead", NULL, + slub_cpu_dead); + + pr_info("SLUB: HWalign=%d, Order=%u-%u, MinObjects=%u, CPUs=%u, Nodes=%u\n", + cache_line_size(), + slub_min_order, slub_max_order, slub_min_objects, + nr_cpu_ids, nr_node_ids); +} + +void __init kmem_cache_init_late(void) +{ +} + +struct kmem_cache * +__kmem_cache_alias(const char *name, unsigned int size, unsigned int align, + slab_flags_t flags, void (*ctor)(void *)) +{ + struct kmem_cache *s; + + s = find_mergeable(size, align, flags, name, ctor); + if (s) { + s->refcount++; + + /* + * Adjust the object sizes so that we clear + * the complete object on kzalloc. + */ + s->object_size = max(s->object_size, size); + s->inuse = max(s->inuse, ALIGN(size, sizeof(void *))); + + if (sysfs_slab_alias(s, name)) { + s->refcount--; + s = NULL; + } + } + + return s; +} + +int __kmem_cache_create(struct kmem_cache *s, slab_flags_t flags) +{ + int err; + + err = kmem_cache_open(s, flags); + if (err) + return err; + + /* Mutex is not taken during early boot */ + if (slab_state <= UP) + return 0; + + err = sysfs_slab_add(s); + if (err) + __kmem_cache_release(s); + + return err; +} + +void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller) +{ + struct kmem_cache *s; + void *ret; + + if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) + return kmalloc_large(size, gfpflags); + + s = kmalloc_slab(size, gfpflags); + + if (unlikely(ZERO_OR_NULL_PTR(s))) + return s; + + ret = slab_alloc(s, gfpflags, caller); + + /* Honor the call site pointer we received. */ + trace_kmalloc(caller, ret, size, s->size, gfpflags); + + return ret; +} +EXPORT_SYMBOL(__kmalloc_track_caller); + +#ifdef CONFIG_NUMA +void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags, + int node, unsigned long caller) +{ + struct kmem_cache *s; + void *ret; + + if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) { + ret = kmalloc_large_node(size, gfpflags, node); + + trace_kmalloc_node(caller, ret, + size, PAGE_SIZE << get_order(size), + gfpflags, node); + + return ret; + } + + s = kmalloc_slab(size, gfpflags); + + if (unlikely(ZERO_OR_NULL_PTR(s))) + return s; + + ret = slab_alloc_node(s, gfpflags, node, caller); + + /* Honor the call site pointer we received. */ + trace_kmalloc_node(caller, ret, size, s->size, gfpflags, node); + + return ret; +} +EXPORT_SYMBOL(__kmalloc_node_track_caller); +#endif + +#ifdef CONFIG_SYSFS +static int count_inuse(struct page *page) +{ + return page->inuse; +} + +static int count_total(struct page *page) +{ + return page->objects; +} +#endif + +#ifdef CONFIG_SLUB_DEBUG +static void validate_slab(struct kmem_cache *s, struct page *page) +{ + void *p; + void *addr = page_address(page); + unsigned long *map; + + slab_lock(page); + + if (!check_slab(s, page) || !on_freelist(s, page, NULL)) + goto unlock; + + /* Now we know that a valid freelist exists */ + map = get_map(s, page); + for_each_object(p, s, addr, page->objects) { + u8 val = test_bit(__obj_to_index(s, addr, p), map) ? + SLUB_RED_INACTIVE : SLUB_RED_ACTIVE; + + if (!check_object(s, page, p, val)) + break; + } + put_map(map); +unlock: + slab_unlock(page); +} + +static int validate_slab_node(struct kmem_cache *s, + struct kmem_cache_node *n) +{ + unsigned long count = 0; + struct page *page; + unsigned long flags; + + spin_lock_irqsave(&n->list_lock, flags); + + list_for_each_entry(page, &n->partial, slab_list) { + validate_slab(s, page); + count++; + } + if (count != n->nr_partial) + pr_err("SLUB %s: %ld partial slabs counted but counter=%ld\n", + s->name, count, n->nr_partial); + + if (!(s->flags & SLAB_STORE_USER)) + goto out; + + list_for_each_entry(page, &n->full, slab_list) { + validate_slab(s, page); + count++; + } + if (count != atomic_long_read(&n->nr_slabs)) + pr_err("SLUB: %s %ld slabs counted but counter=%ld\n", + s->name, count, atomic_long_read(&n->nr_slabs)); + +out: + spin_unlock_irqrestore(&n->list_lock, flags); + return count; +} + +static long validate_slab_cache(struct kmem_cache *s) +{ + int node; + unsigned long count = 0; + struct kmem_cache_node *n; + + flush_all(s); + for_each_kmem_cache_node(s, node, n) + count += validate_slab_node(s, n); + + return count; +} +/* + * Generate lists of code addresses where slabcache objects are allocated + * and freed. + */ + +struct location { + unsigned long count; + unsigned long addr; + long long sum_time; + long min_time; + long max_time; + long min_pid; + long max_pid; + DECLARE_BITMAP(cpus, NR_CPUS); + nodemask_t nodes; +}; + +struct loc_track { + unsigned long max; + unsigned long count; + struct location *loc; +}; + +static void free_loc_track(struct loc_track *t) +{ + if (t->max) + free_pages((unsigned long)t->loc, + get_order(sizeof(struct location) * t->max)); +} + +static int alloc_loc_track(struct loc_track *t, unsigned long max, gfp_t flags) +{ + struct location *l; + int order; + + order = get_order(sizeof(struct location) * max); + + l = (void *)__get_free_pages(flags, order); + if (!l) + return 0; + + if (t->count) { + memcpy(l, t->loc, sizeof(struct location) * t->count); + free_loc_track(t); + } + t->max = max; + t->loc = l; + return 1; +} + +static int add_location(struct loc_track *t, struct kmem_cache *s, + const struct track *track) +{ + long start, end, pos; + struct location *l; + unsigned long caddr; + unsigned long age = jiffies - track->when; + + start = -1; + end = t->count; + + for ( ; ; ) { + pos = start + (end - start + 1) / 2; + + /* + * There is nothing at "end". If we end up there + * we need to add something to before end. + */ + if (pos == end) + break; + + caddr = t->loc[pos].addr; + if (track->addr == caddr) { + + l = &t->loc[pos]; + l->count++; + if (track->when) { + l->sum_time += age; + if (age < l->min_time) + l->min_time = age; + if (age > l->max_time) + l->max_time = age; + + if (track->pid < l->min_pid) + l->min_pid = track->pid; + if (track->pid > l->max_pid) + l->max_pid = track->pid; + + cpumask_set_cpu(track->cpu, + to_cpumask(l->cpus)); + } + node_set(page_to_nid(virt_to_page(track)), l->nodes); + return 1; + } + + if (track->addr < caddr) + end = pos; + else + start = pos; + } + + /* + * Not found. Insert new tracking element. + */ + if (t->count >= t->max && !alloc_loc_track(t, 2 * t->max, GFP_ATOMIC)) + return 0; + + l = t->loc + pos; + if (pos < t->count) + memmove(l + 1, l, + (t->count - pos) * sizeof(struct location)); + t->count++; + l->count = 1; + l->addr = track->addr; + l->sum_time = age; + l->min_time = age; + l->max_time = age; + l->min_pid = track->pid; + l->max_pid = track->pid; + cpumask_clear(to_cpumask(l->cpus)); + cpumask_set_cpu(track->cpu, to_cpumask(l->cpus)); + nodes_clear(l->nodes); + node_set(page_to_nid(virt_to_page(track)), l->nodes); + return 1; +} + +static void process_slab(struct loc_track *t, struct kmem_cache *s, + struct page *page, enum track_item alloc) +{ + void *addr = page_address(page); + void *p; + unsigned long *map; + + map = get_map(s, page); + for_each_object(p, s, addr, page->objects) + if (!test_bit(__obj_to_index(s, addr, p), map)) + add_location(t, s, get_track(s, p, alloc)); + put_map(map); +} + +static int list_locations(struct kmem_cache *s, char *buf, + enum track_item alloc) +{ + int len = 0; + unsigned long i; + struct loc_track t = { 0, 0, NULL }; + int node; + struct kmem_cache_node *n; + + if (!alloc_loc_track(&t, PAGE_SIZE / sizeof(struct location), + GFP_KERNEL)) { + return sprintf(buf, "Out of memory\n"); + } + /* Push back cpu slabs */ + flush_all(s); + + for_each_kmem_cache_node(s, node, n) { + unsigned long flags; + struct page *page; + + if (!atomic_long_read(&n->nr_slabs)) + continue; + + spin_lock_irqsave(&n->list_lock, flags); + list_for_each_entry(page, &n->partial, slab_list) + process_slab(&t, s, page, alloc); + list_for_each_entry(page, &n->full, slab_list) + process_slab(&t, s, page, alloc); + spin_unlock_irqrestore(&n->list_lock, flags); + } + + for (i = 0; i < t.count; i++) { + struct location *l = &t.loc[i]; + + if (len > PAGE_SIZE - KSYM_SYMBOL_LEN - 100) + break; + len += sprintf(buf + len, "%7ld ", l->count); + + if (l->addr) + len += sprintf(buf + len, "%pS", (void *)l->addr); + else + len += sprintf(buf + len, ""); + + if (l->sum_time != l->min_time) { + len += sprintf(buf + len, " age=%ld/%ld/%ld", + l->min_time, + (long)div_u64(l->sum_time, l->count), + l->max_time); + } else + len += sprintf(buf + len, " age=%ld", + l->min_time); + + if (l->min_pid != l->max_pid) + len += sprintf(buf + len, " pid=%ld-%ld", + l->min_pid, l->max_pid); + else + len += sprintf(buf + len, " pid=%ld", + l->min_pid); + + if (num_online_cpus() > 1 && + !cpumask_empty(to_cpumask(l->cpus)) && + len < PAGE_SIZE - 60) + len += scnprintf(buf + len, PAGE_SIZE - len - 50, + " cpus=%*pbl", + cpumask_pr_args(to_cpumask(l->cpus))); + + if (nr_online_nodes > 1 && !nodes_empty(l->nodes) && + len < PAGE_SIZE - 60) + len += scnprintf(buf + len, PAGE_SIZE - len - 50, + " nodes=%*pbl", + nodemask_pr_args(&l->nodes)); + + len += sprintf(buf + len, "\n"); + } + + free_loc_track(&t); + if (!t.count) + len += sprintf(buf, "No data\n"); + return len; +} +#endif /* CONFIG_SLUB_DEBUG */ + +#ifdef SLUB_RESILIENCY_TEST +static void __init resiliency_test(void) +{ + u8 *p; + int type = KMALLOC_NORMAL; + + BUILD_BUG_ON(KMALLOC_MIN_SIZE > 16 || KMALLOC_SHIFT_HIGH < 10); + + pr_err("SLUB resiliency testing\n"); + pr_err("-----------------------\n"); + pr_err("A. Corruption after allocation\n"); + + p = kzalloc(16, GFP_KERNEL); + p[16] = 0x12; + pr_err("\n1. kmalloc-16: Clobber Redzone/next pointer 0x12->0x%p\n\n", + p + 16); + + validate_slab_cache(kmalloc_caches[type][4]); + + /* Hmmm... The next two are dangerous */ + p = kzalloc(32, GFP_KERNEL); + p[32 + sizeof(void *)] = 0x34; + pr_err("\n2. kmalloc-32: Clobber next pointer/next slab 0x34 -> -0x%p\n", + p); + pr_err("If allocated object is overwritten then not detectable\n\n"); + + validate_slab_cache(kmalloc_caches[type][5]); + p = kzalloc(64, GFP_KERNEL); + p += 64 + (get_cycles() & 0xff) * sizeof(void *); + *p = 0x56; + pr_err("\n3. kmalloc-64: corrupting random byte 0x56->0x%p\n", + p); + pr_err("If allocated object is overwritten then not detectable\n\n"); + validate_slab_cache(kmalloc_caches[type][6]); + + pr_err("\nB. Corruption after free\n"); + p = kzalloc(128, GFP_KERNEL); + kfree(p); + *p = 0x78; + pr_err("1. kmalloc-128: Clobber first word 0x78->0x%p\n\n", p); + validate_slab_cache(kmalloc_caches[type][7]); + + p = kzalloc(256, GFP_KERNEL); + kfree(p); + p[50] = 0x9a; + pr_err("\n2. kmalloc-256: Clobber 50th byte 0x9a->0x%p\n\n", p); + validate_slab_cache(kmalloc_caches[type][8]); + + p = kzalloc(512, GFP_KERNEL); + kfree(p); + p[512] = 0xab; + pr_err("\n3. kmalloc-512: Clobber redzone 0xab->0x%p\n\n", p); + validate_slab_cache(kmalloc_caches[type][9]); +} +#else +#ifdef CONFIG_SYSFS +static void resiliency_test(void) {}; +#endif +#endif /* SLUB_RESILIENCY_TEST */ + +#ifdef CONFIG_SYSFS +enum slab_stat_type { + SL_ALL, /* All slabs */ + SL_PARTIAL, /* Only partially allocated slabs */ + SL_CPU, /* Only slabs used for cpu caches */ + SL_OBJECTS, /* Determine allocated objects not slabs */ + SL_TOTAL /* Determine object capacity not slabs */ +}; + +#define SO_ALL (1 << SL_ALL) +#define SO_PARTIAL (1 << SL_PARTIAL) +#define SO_CPU (1 << SL_CPU) +#define SO_OBJECTS (1 << SL_OBJECTS) +#define SO_TOTAL (1 << SL_TOTAL) + +#ifdef CONFIG_MEMCG +static bool memcg_sysfs_enabled = IS_ENABLED(CONFIG_SLUB_MEMCG_SYSFS_ON); + +static int __init setup_slub_memcg_sysfs(char *str) +{ + int v; + + if (get_option(&str, &v) > 0) + memcg_sysfs_enabled = v; + + return 1; +} + +__setup("slub_memcg_sysfs=", setup_slub_memcg_sysfs); +#endif + +static ssize_t show_slab_objects(struct kmem_cache *s, + char *buf, unsigned long flags) +{ + unsigned long total = 0; + int node; + int x; + unsigned long *nodes; + + nodes = kcalloc(nr_node_ids, sizeof(unsigned long), GFP_KERNEL); + if (!nodes) + return -ENOMEM; + + if (flags & SO_CPU) { + int cpu; + + for_each_possible_cpu(cpu) { + struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, + cpu); + int node; + struct page *page; + + page = READ_ONCE(c->page); + if (!page) + continue; + + node = page_to_nid(page); + if (flags & SO_TOTAL) + x = page->objects; + else if (flags & SO_OBJECTS) + x = page->inuse; + else + x = 1; + + total += x; + nodes[node] += x; + + page = slub_percpu_partial_read_once(c); + if (page) { + node = page_to_nid(page); + if (flags & SO_TOTAL) + WARN_ON_ONCE(1); + else if (flags & SO_OBJECTS) + WARN_ON_ONCE(1); + else + x = page->pages; + total += x; + nodes[node] += x; + } + } + } + + /* + * It is impossible to take "mem_hotplug_lock" here with "kernfs_mutex" + * already held which will conflict with an existing lock order: + * + * mem_hotplug_lock->slab_mutex->kernfs_mutex + * + * We don't really need mem_hotplug_lock (to hold off + * slab_mem_going_offline_callback) here because slab's memory hot + * unplug code doesn't destroy the kmem_cache->node[] data. + */ + +#ifdef CONFIG_SLUB_DEBUG + if (flags & SO_ALL) { + struct kmem_cache_node *n; + + for_each_kmem_cache_node(s, node, n) { + + if (flags & SO_TOTAL) + x = atomic_long_read(&n->total_objects); + else if (flags & SO_OBJECTS) + x = atomic_long_read(&n->total_objects) - + count_partial(n, count_free); + else + x = atomic_long_read(&n->nr_slabs); + total += x; + nodes[node] += x; + } + + } else +#endif + if (flags & SO_PARTIAL) { + struct kmem_cache_node *n; + + for_each_kmem_cache_node(s, node, n) { + if (flags & SO_TOTAL) + x = count_partial(n, count_total); + else if (flags & SO_OBJECTS) + x = count_partial(n, count_inuse); + else + x = n->nr_partial; + total += x; + nodes[node] += x; + } + } + x = sprintf(buf, "%lu", total); +#ifdef CONFIG_NUMA + for (node = 0; node < nr_node_ids; node++) + if (nodes[node]) + x += sprintf(buf + x, " N%d=%lu", + node, nodes[node]); +#endif + kfree(nodes); + return x + sprintf(buf + x, "\n"); +} + +#define to_slab_attr(n) container_of(n, struct slab_attribute, attr) +#define to_slab(n) container_of(n, struct kmem_cache, kobj) + +struct slab_attribute { + struct attribute attr; + ssize_t (*show)(struct kmem_cache *s, char *buf); + ssize_t (*store)(struct kmem_cache *s, const char *x, size_t count); +}; + +#define SLAB_ATTR_RO(_name) \ + static struct slab_attribute _name##_attr = \ + __ATTR(_name, 0400, _name##_show, NULL) + +#define SLAB_ATTR(_name) \ + static struct slab_attribute _name##_attr = \ + __ATTR(_name, 0600, _name##_show, _name##_store) + +static ssize_t slab_size_show(struct kmem_cache *s, char *buf) +{ + return sprintf(buf, "%u\n", s->size); +} +SLAB_ATTR_RO(slab_size); + +static ssize_t align_show(struct kmem_cache *s, char *buf) +{ + return sprintf(buf, "%u\n", s->align); +} +SLAB_ATTR_RO(align); + +static ssize_t object_size_show(struct kmem_cache *s, char *buf) +{ + return sprintf(buf, "%u\n", s->object_size); +} +SLAB_ATTR_RO(object_size); + +static ssize_t objs_per_slab_show(struct kmem_cache *s, char *buf) +{ + return sprintf(buf, "%u\n", oo_objects(s->oo)); +} +SLAB_ATTR_RO(objs_per_slab); + +static ssize_t order_show(struct kmem_cache *s, char *buf) +{ + return sprintf(buf, "%u\n", oo_order(s->oo)); +} +SLAB_ATTR_RO(order); + +static ssize_t min_partial_show(struct kmem_cache *s, char *buf) +{ + return sprintf(buf, "%lu\n", s->min_partial); +} + +static ssize_t min_partial_store(struct kmem_cache *s, const char *buf, + size_t length) +{ + unsigned long min; + int err; + + err = kstrtoul(buf, 10, &min); + if (err) + return err; + + set_min_partial(s, min); + return length; +} +SLAB_ATTR(min_partial); + +static ssize_t cpu_partial_show(struct kmem_cache *s, char *buf) +{ + return sprintf(buf, "%u\n", slub_cpu_partial(s)); +} + +static ssize_t cpu_partial_store(struct kmem_cache *s, const char *buf, + size_t length) +{ + unsigned int objects; + int err; + + err = kstrtouint(buf, 10, &objects); + if (err) + return err; + if (objects && !kmem_cache_has_cpu_partial(s)) + return -EINVAL; + + slub_set_cpu_partial(s, objects); + flush_all(s); + return length; +} +SLAB_ATTR(cpu_partial); + +static ssize_t ctor_show(struct kmem_cache *s, char *buf) +{ + if (!s->ctor) + return 0; + return sprintf(buf, "%pS\n", s->ctor); +} +SLAB_ATTR_RO(ctor); + +static ssize_t aliases_show(struct kmem_cache *s, char *buf) +{ + return sprintf(buf, "%d\n", s->refcount < 0 ? 0 : s->refcount - 1); +} +SLAB_ATTR_RO(aliases); + +static ssize_t partial_show(struct kmem_cache *s, char *buf) +{ + return show_slab_objects(s, buf, SO_PARTIAL); +} +SLAB_ATTR_RO(partial); + +static ssize_t cpu_slabs_show(struct kmem_cache *s, char *buf) +{ + return show_slab_objects(s, buf, SO_CPU); +} +SLAB_ATTR_RO(cpu_slabs); + +static ssize_t objects_show(struct kmem_cache *s, char *buf) +{ + return show_slab_objects(s, buf, SO_ALL|SO_OBJECTS); +} +SLAB_ATTR_RO(objects); + +static ssize_t objects_partial_show(struct kmem_cache *s, char *buf) +{ + return show_slab_objects(s, buf, SO_PARTIAL|SO_OBJECTS); +} +SLAB_ATTR_RO(objects_partial); + +static ssize_t slabs_cpu_partial_show(struct kmem_cache *s, char *buf) +{ + int objects = 0; + int pages = 0; + int cpu; + int len; + + for_each_online_cpu(cpu) { + struct page *page; + + page = slub_percpu_partial(per_cpu_ptr(s->cpu_slab, cpu)); + + if (page) { + pages += page->pages; + objects += page->pobjects; + } + } + + len = sprintf(buf, "%d(%d)", objects, pages); + +#ifdef CONFIG_SMP + for_each_online_cpu(cpu) { + struct page *page; + + page = slub_percpu_partial(per_cpu_ptr(s->cpu_slab, cpu)); + + if (page && len < PAGE_SIZE - 20) + len += sprintf(buf + len, " C%d=%d(%d)", cpu, + page->pobjects, page->pages); + } +#endif + return len + sprintf(buf + len, "\n"); +} +SLAB_ATTR_RO(slabs_cpu_partial); + +static ssize_t reclaim_account_show(struct kmem_cache *s, char *buf) +{ + return sprintf(buf, "%d\n", !!(s->flags & SLAB_RECLAIM_ACCOUNT)); +} +SLAB_ATTR_RO(reclaim_account); + +static ssize_t hwcache_align_show(struct kmem_cache *s, char *buf) +{ + return sprintf(buf, "%d\n", !!(s->flags & SLAB_HWCACHE_ALIGN)); +} +SLAB_ATTR_RO(hwcache_align); + +#ifdef CONFIG_ZONE_DMA +static ssize_t cache_dma_show(struct kmem_cache *s, char *buf) +{ + return sprintf(buf, "%d\n", !!(s->flags & SLAB_CACHE_DMA)); +} +SLAB_ATTR_RO(cache_dma); +#endif + +static ssize_t usersize_show(struct kmem_cache *s, char *buf) +{ + return sprintf(buf, "%u\n", s->usersize); +} +SLAB_ATTR_RO(usersize); + +static ssize_t destroy_by_rcu_show(struct kmem_cache *s, char *buf) +{ + return sprintf(buf, "%d\n", !!(s->flags & SLAB_TYPESAFE_BY_RCU)); +} +SLAB_ATTR_RO(destroy_by_rcu); + +#ifdef CONFIG_SLUB_DEBUG +static ssize_t slabs_show(struct kmem_cache *s, char *buf) +{ + return show_slab_objects(s, buf, SO_ALL); +} +SLAB_ATTR_RO(slabs); + +static ssize_t total_objects_show(struct kmem_cache *s, char *buf) +{ + return show_slab_objects(s, buf, SO_ALL|SO_TOTAL); +} +SLAB_ATTR_RO(total_objects); + +static ssize_t sanity_checks_show(struct kmem_cache *s, char *buf) +{ + return sprintf(buf, "%d\n", !!(s->flags & SLAB_CONSISTENCY_CHECKS)); +} +SLAB_ATTR_RO(sanity_checks); + +static ssize_t trace_show(struct kmem_cache *s, char *buf) +{ + return sprintf(buf, "%d\n", !!(s->flags & SLAB_TRACE)); +} +SLAB_ATTR_RO(trace); + +static ssize_t red_zone_show(struct kmem_cache *s, char *buf) +{ + return sprintf(buf, "%d\n", !!(s->flags & SLAB_RED_ZONE)); +} + +SLAB_ATTR_RO(red_zone); + +static ssize_t poison_show(struct kmem_cache *s, char *buf) +{ + return sprintf(buf, "%d\n", !!(s->flags & SLAB_POISON)); +} + +SLAB_ATTR_RO(poison); + +static ssize_t store_user_show(struct kmem_cache *s, char *buf) +{ + return sprintf(buf, "%d\n", !!(s->flags & SLAB_STORE_USER)); +} + +SLAB_ATTR_RO(store_user); + +static ssize_t validate_show(struct kmem_cache *s, char *buf) +{ + return 0; +} + +static ssize_t validate_store(struct kmem_cache *s, + const char *buf, size_t length) +{ + int ret = -EINVAL; + + if (buf[0] == '1') { + ret = validate_slab_cache(s); + if (ret >= 0) + ret = length; + } + return ret; +} +SLAB_ATTR(validate); + +static ssize_t alloc_calls_show(struct kmem_cache *s, char *buf) +{ + if (!(s->flags & SLAB_STORE_USER)) + return -ENOSYS; + return list_locations(s, buf, TRACK_ALLOC); +} +SLAB_ATTR_RO(alloc_calls); + +static ssize_t free_calls_show(struct kmem_cache *s, char *buf) +{ + if (!(s->flags & SLAB_STORE_USER)) + return -ENOSYS; + return list_locations(s, buf, TRACK_FREE); +} +SLAB_ATTR_RO(free_calls); +#endif /* CONFIG_SLUB_DEBUG */ + +#ifdef CONFIG_FAILSLAB +static ssize_t failslab_show(struct kmem_cache *s, char *buf) +{ + return sprintf(buf, "%d\n", !!(s->flags & SLAB_FAILSLAB)); +} +SLAB_ATTR_RO(failslab); +#endif + +static ssize_t shrink_show(struct kmem_cache *s, char *buf) +{ + return 0; +} + +static ssize_t shrink_store(struct kmem_cache *s, + const char *buf, size_t length) +{ + if (buf[0] == '1') + kmem_cache_shrink(s); + else + return -EINVAL; + return length; +} +SLAB_ATTR(shrink); + +#ifdef CONFIG_NUMA +static ssize_t remote_node_defrag_ratio_show(struct kmem_cache *s, char *buf) +{ + return sprintf(buf, "%u\n", s->remote_node_defrag_ratio / 10); +} + +static ssize_t remote_node_defrag_ratio_store(struct kmem_cache *s, + const char *buf, size_t length) +{ + unsigned int ratio; + int err; + + err = kstrtouint(buf, 10, &ratio); + if (err) + return err; + if (ratio > 100) + return -ERANGE; + + s->remote_node_defrag_ratio = ratio * 10; + + return length; +} +SLAB_ATTR(remote_node_defrag_ratio); +#endif + +#ifdef CONFIG_SLUB_STATS +static int show_stat(struct kmem_cache *s, char *buf, enum stat_item si) +{ + unsigned long sum = 0; + int cpu; + int len; + int *data = kmalloc_array(nr_cpu_ids, sizeof(int), GFP_KERNEL); + + if (!data) + return -ENOMEM; + + for_each_online_cpu(cpu) { + unsigned x = per_cpu_ptr(s->cpu_slab, cpu)->stat[si]; + + data[cpu] = x; + sum += x; + } + + len = sprintf(buf, "%lu", sum); + +#ifdef CONFIG_SMP + for_each_online_cpu(cpu) { + if (data[cpu] && len < PAGE_SIZE - 20) + len += sprintf(buf + len, " C%d=%u", cpu, data[cpu]); + } +#endif + kfree(data); + return len + sprintf(buf + len, "\n"); +} + +static void clear_stat(struct kmem_cache *s, enum stat_item si) +{ + int cpu; + + for_each_online_cpu(cpu) + per_cpu_ptr(s->cpu_slab, cpu)->stat[si] = 0; +} + +#define STAT_ATTR(si, text) \ +static ssize_t text##_show(struct kmem_cache *s, char *buf) \ +{ \ + return show_stat(s, buf, si); \ +} \ +static ssize_t text##_store(struct kmem_cache *s, \ + const char *buf, size_t length) \ +{ \ + if (buf[0] != '0') \ + return -EINVAL; \ + clear_stat(s, si); \ + return length; \ +} \ +SLAB_ATTR(text); \ + +STAT_ATTR(ALLOC_FASTPATH, alloc_fastpath); +STAT_ATTR(ALLOC_SLOWPATH, alloc_slowpath); +STAT_ATTR(FREE_FASTPATH, free_fastpath); +STAT_ATTR(FREE_SLOWPATH, free_slowpath); +STAT_ATTR(FREE_FROZEN, free_frozen); +STAT_ATTR(FREE_ADD_PARTIAL, free_add_partial); +STAT_ATTR(FREE_REMOVE_PARTIAL, free_remove_partial); +STAT_ATTR(ALLOC_FROM_PARTIAL, alloc_from_partial); +STAT_ATTR(ALLOC_SLAB, alloc_slab); +STAT_ATTR(ALLOC_REFILL, alloc_refill); +STAT_ATTR(ALLOC_NODE_MISMATCH, alloc_node_mismatch); +STAT_ATTR(FREE_SLAB, free_slab); +STAT_ATTR(CPUSLAB_FLUSH, cpuslab_flush); +STAT_ATTR(DEACTIVATE_FULL, deactivate_full); +STAT_ATTR(DEACTIVATE_EMPTY, deactivate_empty); +STAT_ATTR(DEACTIVATE_TO_HEAD, deactivate_to_head); +STAT_ATTR(DEACTIVATE_TO_TAIL, deactivate_to_tail); +STAT_ATTR(DEACTIVATE_REMOTE_FREES, deactivate_remote_frees); +STAT_ATTR(DEACTIVATE_BYPASS, deactivate_bypass); +STAT_ATTR(ORDER_FALLBACK, order_fallback); +STAT_ATTR(CMPXCHG_DOUBLE_CPU_FAIL, cmpxchg_double_cpu_fail); +STAT_ATTR(CMPXCHG_DOUBLE_FAIL, cmpxchg_double_fail); +STAT_ATTR(CPU_PARTIAL_ALLOC, cpu_partial_alloc); +STAT_ATTR(CPU_PARTIAL_FREE, cpu_partial_free); +STAT_ATTR(CPU_PARTIAL_NODE, cpu_partial_node); +STAT_ATTR(CPU_PARTIAL_DRAIN, cpu_partial_drain); +#endif /* CONFIG_SLUB_STATS */ + +static struct attribute *slab_attrs[] = { + &slab_size_attr.attr, + &object_size_attr.attr, + &objs_per_slab_attr.attr, + &order_attr.attr, + &min_partial_attr.attr, + &cpu_partial_attr.attr, + &objects_attr.attr, + &objects_partial_attr.attr, + &partial_attr.attr, + &cpu_slabs_attr.attr, + &ctor_attr.attr, + &aliases_attr.attr, + &align_attr.attr, + &hwcache_align_attr.attr, + &reclaim_account_attr.attr, + &destroy_by_rcu_attr.attr, + &shrink_attr.attr, + &slabs_cpu_partial_attr.attr, +#ifdef CONFIG_SLUB_DEBUG + &total_objects_attr.attr, + &slabs_attr.attr, + &sanity_checks_attr.attr, + &trace_attr.attr, + &red_zone_attr.attr, + &poison_attr.attr, + &store_user_attr.attr, + &validate_attr.attr, + &alloc_calls_attr.attr, + &free_calls_attr.attr, +#endif +#ifdef CONFIG_ZONE_DMA + &cache_dma_attr.attr, +#endif +#ifdef CONFIG_NUMA + &remote_node_defrag_ratio_attr.attr, +#endif +#ifdef CONFIG_SLUB_STATS + &alloc_fastpath_attr.attr, + &alloc_slowpath_attr.attr, + &free_fastpath_attr.attr, + &free_slowpath_attr.attr, + &free_frozen_attr.attr, + &free_add_partial_attr.attr, + &free_remove_partial_attr.attr, + &alloc_from_partial_attr.attr, + &alloc_slab_attr.attr, + &alloc_refill_attr.attr, + &alloc_node_mismatch_attr.attr, + &free_slab_attr.attr, + &cpuslab_flush_attr.attr, + &deactivate_full_attr.attr, + &deactivate_empty_attr.attr, + &deactivate_to_head_attr.attr, + &deactivate_to_tail_attr.attr, + &deactivate_remote_frees_attr.attr, + &deactivate_bypass_attr.attr, + &order_fallback_attr.attr, + &cmpxchg_double_fail_attr.attr, + &cmpxchg_double_cpu_fail_attr.attr, + &cpu_partial_alloc_attr.attr, + &cpu_partial_free_attr.attr, + &cpu_partial_node_attr.attr, + &cpu_partial_drain_attr.attr, +#endif +#ifdef CONFIG_FAILSLAB + &failslab_attr.attr, +#endif + &usersize_attr.attr, + + NULL +}; + +static const struct attribute_group slab_attr_group = { + .attrs = slab_attrs, +}; + +static ssize_t slab_attr_show(struct kobject *kobj, + struct attribute *attr, + char *buf) +{ + struct slab_attribute *attribute; + struct kmem_cache *s; + int err; + + attribute = to_slab_attr(attr); + s = to_slab(kobj); + + if (!attribute->show) + return -EIO; + + err = attribute->show(s, buf); + + return err; +} + +static ssize_t slab_attr_store(struct kobject *kobj, + struct attribute *attr, + const char *buf, size_t len) +{ + struct slab_attribute *attribute; + struct kmem_cache *s; + int err; + + attribute = to_slab_attr(attr); + s = to_slab(kobj); + + if (!attribute->store) + return -EIO; + + err = attribute->store(s, buf, len); + return err; +} + +static void kmem_cache_release(struct kobject *k) +{ + slab_kmem_cache_release(to_slab(k)); +} + +static const struct sysfs_ops slab_sysfs_ops = { + .show = slab_attr_show, + .store = slab_attr_store, +}; + +static struct kobj_type slab_ktype = { + .sysfs_ops = &slab_sysfs_ops, + .release = kmem_cache_release, +}; + +static struct kset *slab_kset; + +static inline struct kset *cache_kset(struct kmem_cache *s) +{ + return slab_kset; +} + +#define ID_STR_LENGTH 64 + +/* Create a unique string id for a slab cache: + * + * Format :[flags-]size + */ +static char *create_unique_id(struct kmem_cache *s) +{ + char *name = kmalloc(ID_STR_LENGTH, GFP_KERNEL); + char *p = name; + + if (!name) + return ERR_PTR(-ENOMEM); + + *p++ = ':'; + /* + * First flags affecting slabcache operations. We will only + * get here for aliasable slabs so we do not need to support + * too many flags. The flags here must cover all flags that + * are matched during merging to guarantee that the id is + * unique. + */ + if (s->flags & SLAB_CACHE_DMA) + *p++ = 'd'; + if (s->flags & SLAB_CACHE_DMA32) + *p++ = 'D'; + if (s->flags & SLAB_RECLAIM_ACCOUNT) + *p++ = 'a'; + if (s->flags & SLAB_CONSISTENCY_CHECKS) + *p++ = 'F'; + if (s->flags & SLAB_ACCOUNT) + *p++ = 'A'; + if (p != name + 1) + *p++ = '-'; + p += sprintf(p, "%07u", s->size); + + BUG_ON(p > name + ID_STR_LENGTH - 1); + return name; +} + +static int sysfs_slab_add(struct kmem_cache *s) +{ + int err; + const char *name; + struct kset *kset = cache_kset(s); + int unmergeable = slab_unmergeable(s); + + if (!kset) { + kobject_init(&s->kobj, &slab_ktype); + return 0; + } + + if (!unmergeable && disable_higher_order_debug && + (slub_debug & DEBUG_METADATA_FLAGS)) + unmergeable = 1; + + if (unmergeable) { + /* + * Slabcache can never be merged so we can use the name proper. + * This is typically the case for debug situations. In that + * case we can catch duplicate names easily. + */ + sysfs_remove_link(&slab_kset->kobj, s->name); + name = s->name; + } else { + /* + * Create a unique name for the slab as a target + * for the symlinks. + */ + name = create_unique_id(s); + if (IS_ERR(name)) + return PTR_ERR(name); + } + + s->kobj.kset = kset; + err = kobject_init_and_add(&s->kobj, &slab_ktype, NULL, "%s", name); + if (err) + goto out; + + err = sysfs_create_group(&s->kobj, &slab_attr_group); + if (err) + goto out_del_kobj; + + if (!unmergeable) { + /* Setup first alias */ + sysfs_slab_alias(s, s->name); + } +out: + if (!unmergeable) + kfree(name); + return err; +out_del_kobj: + kobject_del(&s->kobj); + goto out; +} + +void sysfs_slab_unlink(struct kmem_cache *s) +{ + if (slab_state >= FULL) + kobject_del(&s->kobj); +} + +void sysfs_slab_release(struct kmem_cache *s) +{ + if (slab_state >= FULL) + kobject_put(&s->kobj); +} + +/* + * Need to buffer aliases during bootup until sysfs becomes + * available lest we lose that information. + */ +struct saved_alias { + struct kmem_cache *s; + const char *name; + struct saved_alias *next; +}; + +static struct saved_alias *alias_list; + +static int sysfs_slab_alias(struct kmem_cache *s, const char *name) +{ + struct saved_alias *al; + + if (slab_state == FULL) { + /* + * If we have a leftover link then remove it. + */ + sysfs_remove_link(&slab_kset->kobj, name); + return sysfs_create_link(&slab_kset->kobj, &s->kobj, name); + } + + al = kmalloc(sizeof(struct saved_alias), GFP_KERNEL); + if (!al) + return -ENOMEM; + + al->s = s; + al->name = name; + al->next = alias_list; + alias_list = al; + return 0; +} + +static int __init slab_sysfs_init(void) +{ + struct kmem_cache *s; + int err; + + mutex_lock(&slab_mutex); + + slab_kset = kset_create_and_add("slab", NULL, kernel_kobj); + if (!slab_kset) { + mutex_unlock(&slab_mutex); + pr_err("Cannot register slab subsystem.\n"); + return -ENOSYS; + } + + slab_state = FULL; + + list_for_each_entry(s, &slab_caches, list) { + err = sysfs_slab_add(s); + if (err) + pr_err("SLUB: Unable to add boot slab %s to sysfs\n", + s->name); + } + + while (alias_list) { + struct saved_alias *al = alias_list; + + alias_list = alias_list->next; + err = sysfs_slab_alias(al->s, al->name); + if (err) + pr_err("SLUB: Unable to add boot slab alias %s to sysfs\n", + al->name); + kfree(al); + } + + mutex_unlock(&slab_mutex); + resiliency_test(); + return 0; +} + +__initcall(slab_sysfs_init); +#endif /* CONFIG_SYSFS */ + +/* + * The /proc/slabinfo ABI + */ +#ifdef CONFIG_SLUB_DEBUG +void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo) +{ + unsigned long nr_slabs = 0; + unsigned long nr_objs = 0; + unsigned long nr_free = 0; + int node; + struct kmem_cache_node *n; + + for_each_kmem_cache_node(s, node, n) { + nr_slabs += node_nr_slabs(n); + nr_objs += node_nr_objs(n); + nr_free += count_partial(n, count_free); + } + + sinfo->active_objs = nr_objs - nr_free; + sinfo->num_objs = nr_objs; + sinfo->active_slabs = nr_slabs; + sinfo->num_slabs = nr_slabs; + sinfo->objects_per_slab = oo_objects(s->oo); + sinfo->cache_order = oo_order(s->oo); +} + +void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *s) +{ +} + +ssize_t slabinfo_write(struct file *file, const char __user *buffer, + size_t count, loff_t *ppos) +{ + return -EIO; +} +#endif /* CONFIG_SLUB_DEBUG */ diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c new file mode 100644 index 000000000..16183d85a --- /dev/null +++ b/mm/sparse-vmemmap.c @@ -0,0 +1,265 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Virtual Memory Map support + * + * (C) 2007 sgi. Christoph Lameter. + * + * Virtual memory maps allow VM primitives pfn_to_page, page_to_pfn, + * virt_to_page, page_address() to be implemented as a base offset + * calculation without memory access. + * + * However, virtual mappings need a page table and TLBs. Many Linux + * architectures already map their physical space using 1-1 mappings + * via TLBs. For those arches the virtual memory map is essentially + * for free if we use the same page size as the 1-1 mappings. In that + * case the overhead consists of a few additional pages that are + * allocated to create a view of memory for vmemmap. + * + * The architecture is expected to provide a vmemmap_populate() function + * to instantiate the mapping. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * Allocate a block of memory to be used to back the virtual memory map + * or to back the page tables that are used to create the mapping. + * Uses the main allocators if they are available, else bootmem. + */ + +static void * __ref __earlyonly_bootmem_alloc(int node, + unsigned long size, + unsigned long align, + unsigned long goal) +{ + return memblock_alloc_try_nid_raw(size, align, goal, + MEMBLOCK_ALLOC_ACCESSIBLE, node); +} + +void * __meminit vmemmap_alloc_block(unsigned long size, int node) +{ + /* If the main allocator is up use that, fallback to bootmem. */ + if (slab_is_available()) { + gfp_t gfp_mask = GFP_KERNEL|__GFP_RETRY_MAYFAIL|__GFP_NOWARN; + int order = get_order(size); + static bool warned; + struct page *page; + + page = alloc_pages_node(node, gfp_mask, order); + if (page) + return page_address(page); + + if (!warned) { + warn_alloc(gfp_mask & ~__GFP_NOWARN, NULL, + "vmemmap alloc failure: order:%u", order); + warned = true; + } + return NULL; + } else + return __earlyonly_bootmem_alloc(node, size, size, + __pa(MAX_DMA_ADDRESS)); +} + +static void * __meminit altmap_alloc_block_buf(unsigned long size, + struct vmem_altmap *altmap); + +/* need to make sure size is all the same during early stage */ +void * __meminit vmemmap_alloc_block_buf(unsigned long size, int node, + struct vmem_altmap *altmap) +{ + void *ptr; + + if (altmap) + return altmap_alloc_block_buf(size, altmap); + + ptr = sparse_buffer_alloc(size); + if (!ptr) + ptr = vmemmap_alloc_block(size, node); + return ptr; +} + +static unsigned long __meminit vmem_altmap_next_pfn(struct vmem_altmap *altmap) +{ + return altmap->base_pfn + altmap->reserve + altmap->alloc + + altmap->align; +} + +static unsigned long __meminit vmem_altmap_nr_free(struct vmem_altmap *altmap) +{ + unsigned long allocated = altmap->alloc + altmap->align; + + if (altmap->free > allocated) + return altmap->free - allocated; + return 0; +} + +static void * __meminit altmap_alloc_block_buf(unsigned long size, + struct vmem_altmap *altmap) +{ + unsigned long pfn, nr_pfns, nr_align; + + if (size & ~PAGE_MASK) { + pr_warn_once("%s: allocations must be multiple of PAGE_SIZE (%ld)\n", + __func__, size); + return NULL; + } + + pfn = vmem_altmap_next_pfn(altmap); + nr_pfns = size >> PAGE_SHIFT; + nr_align = 1UL << find_first_bit(&nr_pfns, BITS_PER_LONG); + nr_align = ALIGN(pfn, nr_align) - pfn; + if (nr_pfns + nr_align > vmem_altmap_nr_free(altmap)) + return NULL; + + altmap->alloc += nr_pfns; + altmap->align += nr_align; + pfn += nr_align; + + pr_debug("%s: pfn: %#lx alloc: %ld align: %ld nr: %#lx\n", + __func__, pfn, altmap->alloc, altmap->align, nr_pfns); + return __va(__pfn_to_phys(pfn)); +} + +void __meminit vmemmap_verify(pte_t *pte, int node, + unsigned long start, unsigned long end) +{ + unsigned long pfn = pte_pfn(*pte); + int actual_node = early_pfn_to_nid(pfn); + + if (node_distance(actual_node, node) > LOCAL_DISTANCE) + pr_warn("[%lx-%lx] potential offnode page_structs\n", + start, end - 1); +} + +pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node, + struct vmem_altmap *altmap) +{ + pte_t *pte = pte_offset_kernel(pmd, addr); + if (pte_none(*pte)) { + pte_t entry; + void *p; + + p = vmemmap_alloc_block_buf(PAGE_SIZE, node, altmap); + if (!p) + return NULL; + entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL); + set_pte_at(&init_mm, addr, pte, entry); + } + return pte; +} + +static void * __meminit vmemmap_alloc_block_zero(unsigned long size, int node) +{ + void *p = vmemmap_alloc_block(size, node); + + if (!p) + return NULL; + memset(p, 0, size); + + return p; +} + +pmd_t * __meminit vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node) +{ + pmd_t *pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) { + void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node); + if (!p) + return NULL; + pmd_populate_kernel(&init_mm, pmd, p); + } + return pmd; +} + +pud_t * __meminit vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node) +{ + pud_t *pud = pud_offset(p4d, addr); + if (pud_none(*pud)) { + void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node); + if (!p) + return NULL; + pud_populate(&init_mm, pud, p); + } + return pud; +} + +p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node) +{ + p4d_t *p4d = p4d_offset(pgd, addr); + if (p4d_none(*p4d)) { + void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node); + if (!p) + return NULL; + p4d_populate(&init_mm, p4d, p); + } + return p4d; +} + +pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node) +{ + pgd_t *pgd = pgd_offset_k(addr); + if (pgd_none(*pgd)) { + void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node); + if (!p) + return NULL; + pgd_populate(&init_mm, pgd, p); + } + return pgd; +} + +int __meminit vmemmap_populate_basepages(unsigned long start, unsigned long end, + int node, struct vmem_altmap *altmap) +{ + unsigned long addr = start; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + for (; addr < end; addr += PAGE_SIZE) { + pgd = vmemmap_pgd_populate(addr, node); + if (!pgd) + return -ENOMEM; + p4d = vmemmap_p4d_populate(pgd, addr, node); + if (!p4d) + return -ENOMEM; + pud = vmemmap_pud_populate(p4d, addr, node); + if (!pud) + return -ENOMEM; + pmd = vmemmap_pmd_populate(pud, addr, node); + if (!pmd) + return -ENOMEM; + pte = vmemmap_pte_populate(pmd, addr, node, altmap); + if (!pte) + return -ENOMEM; + vmemmap_verify(pte, node, addr, addr + PAGE_SIZE); + } + + return 0; +} + +struct page * __meminit __populate_section_memmap(unsigned long pfn, + unsigned long nr_pages, int nid, struct vmem_altmap *altmap) +{ + unsigned long start = (unsigned long) pfn_to_page(pfn); + unsigned long end = start + nr_pages * sizeof(struct page); + + if (WARN_ON_ONCE(!IS_ALIGNED(pfn, PAGES_PER_SUBSECTION) || + !IS_ALIGNED(nr_pages, PAGES_PER_SUBSECTION))) + return NULL; + + if (vmemmap_populate(start, end, nid, altmap)) + return NULL; + + return pfn_to_page(pfn); +} diff --git a/mm/sparse.c b/mm/sparse.c new file mode 100644 index 000000000..33406ea2e --- /dev/null +++ b/mm/sparse.c @@ -0,0 +1,974 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * sparse memory mappings. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "internal.h" +#include + +/* + * Permanent SPARSEMEM data: + * + * 1) mem_section - memory sections, mem_map's for valid memory + */ +#ifdef CONFIG_SPARSEMEM_EXTREME +struct mem_section **mem_section; +#else +struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT] + ____cacheline_internodealigned_in_smp; +#endif +EXPORT_SYMBOL(mem_section); + +#ifdef NODE_NOT_IN_PAGE_FLAGS +/* + * If we did not store the node number in the page then we have to + * do a lookup in the section_to_node_table in order to find which + * node the page belongs to. + */ +#if MAX_NUMNODES <= 256 +static u8 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned; +#else +static u16 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned; +#endif + +int page_to_nid(const struct page *page) +{ + return section_to_node_table[page_to_section(page)]; +} +EXPORT_SYMBOL(page_to_nid); + +static void set_section_nid(unsigned long section_nr, int nid) +{ + section_to_node_table[section_nr] = nid; +} +#else /* !NODE_NOT_IN_PAGE_FLAGS */ +static inline void set_section_nid(unsigned long section_nr, int nid) +{ +} +#endif + +#ifdef CONFIG_SPARSEMEM_EXTREME +static noinline struct mem_section __ref *sparse_index_alloc(int nid) +{ + struct mem_section *section = NULL; + unsigned long array_size = SECTIONS_PER_ROOT * + sizeof(struct mem_section); + + if (slab_is_available()) { + section = kzalloc_node(array_size, GFP_KERNEL, nid); + } else { + section = memblock_alloc_node(array_size, SMP_CACHE_BYTES, + nid); + if (!section) + panic("%s: Failed to allocate %lu bytes nid=%d\n", + __func__, array_size, nid); + } + + return section; +} + +static int __meminit sparse_index_init(unsigned long section_nr, int nid) +{ + unsigned long root = SECTION_NR_TO_ROOT(section_nr); + struct mem_section *section; + + /* + * An existing section is possible in the sub-section hotplug + * case. First hot-add instantiates, follow-on hot-add reuses + * the existing section. + * + * The mem_hotplug_lock resolves the apparent race below. + */ + if (mem_section[root]) + return 0; + + section = sparse_index_alloc(nid); + if (!section) + return -ENOMEM; + + mem_section[root] = section; + + return 0; +} +#else /* !SPARSEMEM_EXTREME */ +static inline int sparse_index_init(unsigned long section_nr, int nid) +{ + return 0; +} +#endif + +#ifdef CONFIG_SPARSEMEM_EXTREME +unsigned long __section_nr(struct mem_section *ms) +{ + unsigned long root_nr; + struct mem_section *root = NULL; + + for (root_nr = 0; root_nr < NR_SECTION_ROOTS; root_nr++) { + root = __nr_to_section(root_nr * SECTIONS_PER_ROOT); + if (!root) + continue; + + if ((ms >= root) && (ms < (root + SECTIONS_PER_ROOT))) + break; + } + + VM_BUG_ON(!root); + + return (root_nr * SECTIONS_PER_ROOT) + (ms - root); +} +#else +unsigned long __section_nr(struct mem_section *ms) +{ + return (unsigned long)(ms - mem_section[0]); +} +#endif + +/* + * During early boot, before section_mem_map is used for an actual + * mem_map, we use section_mem_map to store the section's NUMA + * node. This keeps us from having to use another data structure. The + * node information is cleared just before we store the real mem_map. + */ +static inline unsigned long sparse_encode_early_nid(int nid) +{ + return (nid << SECTION_NID_SHIFT); +} + +static inline int sparse_early_nid(struct mem_section *section) +{ + return (section->section_mem_map >> SECTION_NID_SHIFT); +} + +/* Validate the physical addressing limitations of the model */ +void __meminit mminit_validate_memmodel_limits(unsigned long *start_pfn, + unsigned long *end_pfn) +{ + unsigned long max_sparsemem_pfn = 1UL << (MAX_PHYSMEM_BITS-PAGE_SHIFT); + + /* + * Sanity checks - do not allow an architecture to pass + * in larger pfns than the maximum scope of sparsemem: + */ + if (*start_pfn > max_sparsemem_pfn) { + mminit_dprintk(MMINIT_WARNING, "pfnvalidation", + "Start of range %lu -> %lu exceeds SPARSEMEM max %lu\n", + *start_pfn, *end_pfn, max_sparsemem_pfn); + WARN_ON_ONCE(1); + *start_pfn = max_sparsemem_pfn; + *end_pfn = max_sparsemem_pfn; + } else if (*end_pfn > max_sparsemem_pfn) { + mminit_dprintk(MMINIT_WARNING, "pfnvalidation", + "End of range %lu -> %lu exceeds SPARSEMEM max %lu\n", + *start_pfn, *end_pfn, max_sparsemem_pfn); + WARN_ON_ONCE(1); + *end_pfn = max_sparsemem_pfn; + } +} + +/* + * There are a number of times that we loop over NR_MEM_SECTIONS, + * looking for section_present() on each. But, when we have very + * large physical address spaces, NR_MEM_SECTIONS can also be + * very large which makes the loops quite long. + * + * Keeping track of this gives us an easy way to break out of + * those loops early. + */ +unsigned long __highest_present_section_nr; +static void section_mark_present(struct mem_section *ms) +{ + unsigned long section_nr = __section_nr(ms); + + if (section_nr > __highest_present_section_nr) + __highest_present_section_nr = section_nr; + + ms->section_mem_map |= SECTION_MARKED_PRESENT; +} + +#define for_each_present_section_nr(start, section_nr) \ + for (section_nr = next_present_section_nr(start-1); \ + ((section_nr != -1) && \ + (section_nr <= __highest_present_section_nr)); \ + section_nr = next_present_section_nr(section_nr)) + +static inline unsigned long first_present_section_nr(void) +{ + return next_present_section_nr(-1); +} + +#ifdef CONFIG_SPARSEMEM_VMEMMAP +static void subsection_mask_set(unsigned long *map, unsigned long pfn, + unsigned long nr_pages) +{ + int idx = subsection_map_index(pfn); + int end = subsection_map_index(pfn + nr_pages - 1); + + bitmap_set(map, idx, end - idx + 1); +} + +void __init subsection_map_init(unsigned long pfn, unsigned long nr_pages) +{ + int end_sec = pfn_to_section_nr(pfn + nr_pages - 1); + unsigned long nr, start_sec = pfn_to_section_nr(pfn); + + if (!nr_pages) + return; + + for (nr = start_sec; nr <= end_sec; nr++) { + struct mem_section *ms; + unsigned long pfns; + + pfns = min(nr_pages, PAGES_PER_SECTION + - (pfn & ~PAGE_SECTION_MASK)); + ms = __nr_to_section(nr); + subsection_mask_set(ms->usage->subsection_map, pfn, pfns); + + pr_debug("%s: sec: %lu pfns: %lu set(%d, %d)\n", __func__, nr, + pfns, subsection_map_index(pfn), + subsection_map_index(pfn + pfns - 1)); + + pfn += pfns; + nr_pages -= pfns; + } +} +#else +void __init subsection_map_init(unsigned long pfn, unsigned long nr_pages) +{ +} +#endif + +/* Record a memory area against a node. */ +static void __init memory_present(int nid, unsigned long start, unsigned long end) +{ + unsigned long pfn; + +#ifdef CONFIG_SPARSEMEM_EXTREME + if (unlikely(!mem_section)) { + unsigned long size, align; + + size = sizeof(struct mem_section*) * NR_SECTION_ROOTS; + align = 1 << (INTERNODE_CACHE_SHIFT); + mem_section = memblock_alloc(size, align); + if (!mem_section) + panic("%s: Failed to allocate %lu bytes align=0x%lx\n", + __func__, size, align); + } +#endif + + start &= PAGE_SECTION_MASK; + mminit_validate_memmodel_limits(&start, &end); + for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) { + unsigned long section = pfn_to_section_nr(pfn); + struct mem_section *ms; + + sparse_index_init(section, nid); + set_section_nid(section, nid); + + ms = __nr_to_section(section); + if (!ms->section_mem_map) { + ms->section_mem_map = sparse_encode_early_nid(nid) | + SECTION_IS_ONLINE; + section_mark_present(ms); + } + } +} + +/* + * Mark all memblocks as present using memory_present(). + * This is a convenience function that is useful to mark all of the systems + * memory as present during initialization. + */ +static void __init memblocks_present(void) +{ + unsigned long start, end; + int i, nid; + + for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, &nid) + memory_present(nid, start, end); +} + +/* + * Subtle, we encode the real pfn into the mem_map such that + * the identity pfn - section_mem_map will return the actual + * physical page frame number. + */ +static unsigned long sparse_encode_mem_map(struct page *mem_map, unsigned long pnum) +{ + unsigned long coded_mem_map = + (unsigned long)(mem_map - (section_nr_to_pfn(pnum))); + BUILD_BUG_ON(SECTION_MAP_LAST_BIT > (1UL<section_mem_map &= ~SECTION_MAP_MASK; + ms->section_mem_map |= sparse_encode_mem_map(mem_map, pnum) + | SECTION_HAS_MEM_MAP | flags; + ms->usage = usage; +} + +static unsigned long usemap_size(void) +{ + return BITS_TO_LONGS(SECTION_BLOCKFLAGS_BITS) * sizeof(unsigned long); +} + +size_t mem_section_usage_size(void) +{ + return sizeof(struct mem_section_usage) + usemap_size(); +} + +#ifdef CONFIG_MEMORY_HOTREMOVE +static struct mem_section_usage * __init +sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat, + unsigned long size) +{ + struct mem_section_usage *usage; + unsigned long goal, limit; + int nid; + /* + * A page may contain usemaps for other sections preventing the + * page being freed and making a section unremovable while + * other sections referencing the usemap remain active. Similarly, + * a pgdat can prevent a section being removed. If section A + * contains a pgdat and section B contains the usemap, both + * sections become inter-dependent. This allocates usemaps + * from the same section as the pgdat where possible to avoid + * this problem. + */ + goal = __pa(pgdat) & (PAGE_SECTION_MASK << PAGE_SHIFT); + limit = goal + (1UL << PA_SECTION_SHIFT); + nid = early_pfn_to_nid(goal >> PAGE_SHIFT); +again: + usage = memblock_alloc_try_nid(size, SMP_CACHE_BYTES, goal, limit, nid); + if (!usage && limit) { + limit = 0; + goto again; + } + return usage; +} + +static void __init check_usemap_section_nr(int nid, + struct mem_section_usage *usage) +{ + unsigned long usemap_snr, pgdat_snr; + static unsigned long old_usemap_snr; + static unsigned long old_pgdat_snr; + struct pglist_data *pgdat = NODE_DATA(nid); + int usemap_nid; + + /* First call */ + if (!old_usemap_snr) { + old_usemap_snr = NR_MEM_SECTIONS; + old_pgdat_snr = NR_MEM_SECTIONS; + } + + usemap_snr = pfn_to_section_nr(__pa(usage) >> PAGE_SHIFT); + pgdat_snr = pfn_to_section_nr(__pa(pgdat) >> PAGE_SHIFT); + if (usemap_snr == pgdat_snr) + return; + + if (old_usemap_snr == usemap_snr && old_pgdat_snr == pgdat_snr) + /* skip redundant message */ + return; + + old_usemap_snr = usemap_snr; + old_pgdat_snr = pgdat_snr; + + usemap_nid = sparse_early_nid(__nr_to_section(usemap_snr)); + if (usemap_nid != nid) { + pr_info("node %d must be removed before remove section %ld\n", + nid, usemap_snr); + return; + } + /* + * There is a circular dependency. + * Some platforms allow un-removable section because they will just + * gather other removable sections for dynamic partitioning. + * Just notify un-removable section's number here. + */ + pr_info("Section %ld and %ld (node %d) have a circular dependency on usemap and pgdat allocations\n", + usemap_snr, pgdat_snr, nid); +} +#else +static struct mem_section_usage * __init +sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat, + unsigned long size) +{ + return memblock_alloc_node(size, SMP_CACHE_BYTES, pgdat->node_id); +} + +static void __init check_usemap_section_nr(int nid, + struct mem_section_usage *usage) +{ +} +#endif /* CONFIG_MEMORY_HOTREMOVE */ + +#ifdef CONFIG_SPARSEMEM_VMEMMAP +static unsigned long __init section_map_size(void) +{ + return ALIGN(sizeof(struct page) * PAGES_PER_SECTION, PMD_SIZE); +} + +#else +static unsigned long __init section_map_size(void) +{ + return PAGE_ALIGN(sizeof(struct page) * PAGES_PER_SECTION); +} + +struct page __init *__populate_section_memmap(unsigned long pfn, + unsigned long nr_pages, int nid, struct vmem_altmap *altmap) +{ + unsigned long size = section_map_size(); + struct page *map = sparse_buffer_alloc(size); + phys_addr_t addr = __pa(MAX_DMA_ADDRESS); + + if (map) + return map; + + map = memblock_alloc_try_nid_raw(size, size, addr, + MEMBLOCK_ALLOC_ACCESSIBLE, nid); + if (!map) + panic("%s: Failed to allocate %lu bytes align=0x%lx nid=%d from=%pa\n", + __func__, size, PAGE_SIZE, nid, &addr); + + return map; +} +#endif /* !CONFIG_SPARSEMEM_VMEMMAP */ + +static void *sparsemap_buf __meminitdata; +static void *sparsemap_buf_end __meminitdata; + +static inline void __meminit sparse_buffer_free(unsigned long size) +{ + WARN_ON(!sparsemap_buf || size == 0); + memblock_free_early(__pa(sparsemap_buf), size); +} + +static void __init sparse_buffer_init(unsigned long size, int nid) +{ + phys_addr_t addr = __pa(MAX_DMA_ADDRESS); + WARN_ON(sparsemap_buf); /* forgot to call sparse_buffer_fini()? */ + /* + * Pre-allocated buffer is mainly used by __populate_section_memmap + * and we want it to be properly aligned to the section size - this is + * especially the case for VMEMMAP which maps memmap to PMDs + */ + sparsemap_buf = memblock_alloc_exact_nid_raw(size, section_map_size(), + addr, MEMBLOCK_ALLOC_ACCESSIBLE, nid); + sparsemap_buf_end = sparsemap_buf + size; +} + +static void __init sparse_buffer_fini(void) +{ + unsigned long size = sparsemap_buf_end - sparsemap_buf; + + if (sparsemap_buf && size > 0) + sparse_buffer_free(size); + sparsemap_buf = NULL; +} + +void * __meminit sparse_buffer_alloc(unsigned long size) +{ + void *ptr = NULL; + + if (sparsemap_buf) { + ptr = (void *) roundup((unsigned long)sparsemap_buf, size); + if (ptr + size > sparsemap_buf_end) + ptr = NULL; + else { + /* Free redundant aligned space */ + if ((unsigned long)(ptr - sparsemap_buf) > 0) + sparse_buffer_free((unsigned long)(ptr - sparsemap_buf)); + sparsemap_buf = ptr + size; + } + } + return ptr; +} + +void __weak __meminit vmemmap_populate_print_last(void) +{ +} + +/* + * Initialize sparse on a specific node. The node spans [pnum_begin, pnum_end) + * And number of present sections in this node is map_count. + */ +static void __init sparse_init_nid(int nid, unsigned long pnum_begin, + unsigned long pnum_end, + unsigned long map_count) +{ + struct mem_section_usage *usage; + unsigned long pnum; + struct page *map; + + usage = sparse_early_usemaps_alloc_pgdat_section(NODE_DATA(nid), + mem_section_usage_size() * map_count); + if (!usage) { + pr_err("%s: node[%d] usemap allocation failed", __func__, nid); + goto failed; + } + sparse_buffer_init(map_count * section_map_size(), nid); + for_each_present_section_nr(pnum_begin, pnum) { + unsigned long pfn = section_nr_to_pfn(pnum); + + if (pnum >= pnum_end) + break; + + map = __populate_section_memmap(pfn, PAGES_PER_SECTION, + nid, NULL); + if (!map) { + pr_err("%s: node[%d] memory map backing failed. Some memory will not be available.", + __func__, nid); + pnum_begin = pnum; + sparse_buffer_fini(); + goto failed; + } + check_usemap_section_nr(nid, usage); + sparse_init_one_section(__nr_to_section(pnum), pnum, map, usage, + SECTION_IS_EARLY); + usage = (void *) usage + mem_section_usage_size(); + } + sparse_buffer_fini(); + return; +failed: + /* We failed to allocate, mark all the following pnums as not present */ + for_each_present_section_nr(pnum_begin, pnum) { + struct mem_section *ms; + + if (pnum >= pnum_end) + break; + ms = __nr_to_section(pnum); + ms->section_mem_map = 0; + } +} + +/* + * Allocate the accumulated non-linear sections, allocate a mem_map + * for each and record the physical to section mapping. + */ +void __init sparse_init(void) +{ + unsigned long pnum_end, pnum_begin, map_count = 1; + int nid_begin; + + memblocks_present(); + + pnum_begin = first_present_section_nr(); + nid_begin = sparse_early_nid(__nr_to_section(pnum_begin)); + + /* Setup pageblock_order for HUGETLB_PAGE_SIZE_VARIABLE */ + set_pageblock_order(); + + for_each_present_section_nr(pnum_begin + 1, pnum_end) { + int nid = sparse_early_nid(__nr_to_section(pnum_end)); + + if (nid == nid_begin) { + map_count++; + continue; + } + /* Init node with sections in range [pnum_begin, pnum_end) */ + sparse_init_nid(nid_begin, pnum_begin, pnum_end, map_count); + nid_begin = nid; + pnum_begin = pnum_end; + map_count = 1; + } + /* cover the last node */ + sparse_init_nid(nid_begin, pnum_begin, pnum_end, map_count); + vmemmap_populate_print_last(); +} + +#ifdef CONFIG_MEMORY_HOTPLUG + +/* Mark all memory sections within the pfn range as online */ +void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn) +{ + unsigned long pfn; + + for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) { + unsigned long section_nr = pfn_to_section_nr(pfn); + struct mem_section *ms; + + /* onlining code should never touch invalid ranges */ + if (WARN_ON(!valid_section_nr(section_nr))) + continue; + + ms = __nr_to_section(section_nr); + ms->section_mem_map |= SECTION_IS_ONLINE; + } +} + +#ifdef CONFIG_MEMORY_HOTREMOVE +/* Mark all memory sections within the pfn range as offline */ +void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn) +{ + unsigned long pfn; + + for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) { + unsigned long section_nr = pfn_to_section_nr(pfn); + struct mem_section *ms; + + /* + * TODO this needs some double checking. Offlining code makes + * sure to check pfn_valid but those checks might be just bogus + */ + if (WARN_ON(!valid_section_nr(section_nr))) + continue; + + ms = __nr_to_section(section_nr); + ms->section_mem_map &= ~SECTION_IS_ONLINE; + } +} +#endif + +#ifdef CONFIG_SPARSEMEM_VMEMMAP +static struct page * __meminit populate_section_memmap(unsigned long pfn, + unsigned long nr_pages, int nid, struct vmem_altmap *altmap) +{ + return __populate_section_memmap(pfn, nr_pages, nid, altmap); +} + +static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages, + struct vmem_altmap *altmap) +{ + unsigned long start = (unsigned long) pfn_to_page(pfn); + unsigned long end = start + nr_pages * sizeof(struct page); + + vmemmap_free(start, end, altmap); +} +static void free_map_bootmem(struct page *memmap) +{ + unsigned long start = (unsigned long)memmap; + unsigned long end = (unsigned long)(memmap + PAGES_PER_SECTION); + + vmemmap_free(start, end, NULL); +} + +static int clear_subsection_map(unsigned long pfn, unsigned long nr_pages) +{ + DECLARE_BITMAP(map, SUBSECTIONS_PER_SECTION) = { 0 }; + DECLARE_BITMAP(tmp, SUBSECTIONS_PER_SECTION) = { 0 }; + struct mem_section *ms = __pfn_to_section(pfn); + unsigned long *subsection_map = ms->usage + ? &ms->usage->subsection_map[0] : NULL; + + subsection_mask_set(map, pfn, nr_pages); + if (subsection_map) + bitmap_and(tmp, map, subsection_map, SUBSECTIONS_PER_SECTION); + + if (WARN(!subsection_map || !bitmap_equal(tmp, map, SUBSECTIONS_PER_SECTION), + "section already deactivated (%#lx + %ld)\n", + pfn, nr_pages)) + return -EINVAL; + + bitmap_xor(subsection_map, map, subsection_map, SUBSECTIONS_PER_SECTION); + return 0; +} + +static bool is_subsection_map_empty(struct mem_section *ms) +{ + return bitmap_empty(&ms->usage->subsection_map[0], + SUBSECTIONS_PER_SECTION); +} + +static int fill_subsection_map(unsigned long pfn, unsigned long nr_pages) +{ + struct mem_section *ms = __pfn_to_section(pfn); + DECLARE_BITMAP(map, SUBSECTIONS_PER_SECTION) = { 0 }; + unsigned long *subsection_map; + int rc = 0; + + subsection_mask_set(map, pfn, nr_pages); + + subsection_map = &ms->usage->subsection_map[0]; + + if (bitmap_empty(map, SUBSECTIONS_PER_SECTION)) + rc = -EINVAL; + else if (bitmap_intersects(map, subsection_map, SUBSECTIONS_PER_SECTION)) + rc = -EEXIST; + else + bitmap_or(subsection_map, map, subsection_map, + SUBSECTIONS_PER_SECTION); + + return rc; +} +#else +struct page * __meminit populate_section_memmap(unsigned long pfn, + unsigned long nr_pages, int nid, struct vmem_altmap *altmap) +{ + return kvmalloc_node(array_size(sizeof(struct page), + PAGES_PER_SECTION), GFP_KERNEL, nid); +} + +static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages, + struct vmem_altmap *altmap) +{ + kvfree(pfn_to_page(pfn)); +} + +static void free_map_bootmem(struct page *memmap) +{ + unsigned long maps_section_nr, removing_section_nr, i; + unsigned long magic, nr_pages; + struct page *page = virt_to_page(memmap); + + nr_pages = PAGE_ALIGN(PAGES_PER_SECTION * sizeof(struct page)) + >> PAGE_SHIFT; + + for (i = 0; i < nr_pages; i++, page++) { + magic = (unsigned long) page->freelist; + + BUG_ON(magic == NODE_INFO); + + maps_section_nr = pfn_to_section_nr(page_to_pfn(page)); + removing_section_nr = page_private(page); + + /* + * When this function is called, the removing section is + * logical offlined state. This means all pages are isolated + * from page allocator. If removing section's memmap is placed + * on the same section, it must not be freed. + * If it is freed, page allocator may allocate it which will + * be removed physically soon. + */ + if (maps_section_nr != removing_section_nr) + put_page_bootmem(page); + } +} + +static int clear_subsection_map(unsigned long pfn, unsigned long nr_pages) +{ + return 0; +} + +static bool is_subsection_map_empty(struct mem_section *ms) +{ + return true; +} + +static int fill_subsection_map(unsigned long pfn, unsigned long nr_pages) +{ + return 0; +} +#endif /* CONFIG_SPARSEMEM_VMEMMAP */ + +/* + * To deactivate a memory region, there are 3 cases to handle across + * two configurations (SPARSEMEM_VMEMMAP={y,n}): + * + * 1. deactivation of a partial hot-added section (only possible in + * the SPARSEMEM_VMEMMAP=y case). + * a) section was present at memory init. + * b) section was hot-added post memory init. + * 2. deactivation of a complete hot-added section. + * 3. deactivation of a complete section from memory init. + * + * For 1, when subsection_map does not empty we will not be freeing the + * usage map, but still need to free the vmemmap range. + * + * For 2 and 3, the SPARSEMEM_VMEMMAP={y,n} cases are unified + */ +static void section_deactivate(unsigned long pfn, unsigned long nr_pages, + struct vmem_altmap *altmap) +{ + struct mem_section *ms = __pfn_to_section(pfn); + bool section_is_early = early_section(ms); + struct page *memmap = NULL; + bool empty; + + if (clear_subsection_map(pfn, nr_pages)) + return; + + empty = is_subsection_map_empty(ms); + if (empty) { + unsigned long section_nr = pfn_to_section_nr(pfn); + + /* + * When removing an early section, the usage map is kept (as the + * usage maps of other sections fall into the same page). It + * will be re-used when re-adding the section - which is then no + * longer an early section. If the usage map is PageReserved, it + * was allocated during boot. + */ + if (!PageReserved(virt_to_page(ms->usage))) { + kfree(ms->usage); + ms->usage = NULL; + } + memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr); + /* + * Mark the section invalid so that valid_section() + * return false. This prevents code from dereferencing + * ms->usage array. + */ + ms->section_mem_map &= ~SECTION_HAS_MEM_MAP; + } + + /* + * The memmap of early sections is always fully populated. See + * section_activate() and pfn_valid() . + */ + if (!section_is_early) + depopulate_section_memmap(pfn, nr_pages, altmap); + else if (memmap) + free_map_bootmem(memmap); + + if (empty) + ms->section_mem_map = (unsigned long)NULL; +} + +static struct page * __meminit section_activate(int nid, unsigned long pfn, + unsigned long nr_pages, struct vmem_altmap *altmap) +{ + struct mem_section *ms = __pfn_to_section(pfn); + struct mem_section_usage *usage = NULL; + struct page *memmap; + int rc = 0; + + if (!ms->usage) { + usage = kzalloc(mem_section_usage_size(), GFP_KERNEL); + if (!usage) + return ERR_PTR(-ENOMEM); + ms->usage = usage; + } + + rc = fill_subsection_map(pfn, nr_pages); + if (rc) { + if (usage) + ms->usage = NULL; + kfree(usage); + return ERR_PTR(rc); + } + + /* + * The early init code does not consider partially populated + * initial sections, it simply assumes that memory will never be + * referenced. If we hot-add memory into such a section then we + * do not need to populate the memmap and can simply reuse what + * is already there. + */ + if (nr_pages < PAGES_PER_SECTION && early_section(ms)) + return pfn_to_page(pfn); + + memmap = populate_section_memmap(pfn, nr_pages, nid, altmap); + if (!memmap) { + section_deactivate(pfn, nr_pages, altmap); + return ERR_PTR(-ENOMEM); + } + + return memmap; +} + +/** + * sparse_add_section - add a memory section, or populate an existing one + * @nid: The node to add section on + * @start_pfn: start pfn of the memory range + * @nr_pages: number of pfns to add in the section + * @altmap: device page map + * + * This is only intended for hotplug. + * + * Note that only VMEMMAP supports sub-section aligned hotplug, + * the proper alignment and size are gated by check_pfn_span(). + * + * + * Return: + * * 0 - On success. + * * -EEXIST - Section has been present. + * * -ENOMEM - Out of memory. + */ +int __meminit sparse_add_section(int nid, unsigned long start_pfn, + unsigned long nr_pages, struct vmem_altmap *altmap) +{ + unsigned long section_nr = pfn_to_section_nr(start_pfn); + struct mem_section *ms; + struct page *memmap; + int ret; + + ret = sparse_index_init(section_nr, nid); + if (ret < 0) + return ret; + + memmap = section_activate(nid, start_pfn, nr_pages, altmap); + if (IS_ERR(memmap)) + return PTR_ERR(memmap); + + /* + * Poison uninitialized struct pages in order to catch invalid flags + * combinations. + */ + page_init_poison(memmap, sizeof(struct page) * nr_pages); + + ms = __nr_to_section(section_nr); + set_section_nid(section_nr, nid); + section_mark_present(ms); + + /* Align memmap to section boundary in the subsection case */ + if (section_nr_to_pfn(section_nr) != start_pfn) + memmap = pfn_to_page(section_nr_to_pfn(section_nr)); + sparse_init_one_section(ms, section_nr, memmap, ms->usage, 0); + + return 0; +} + +#ifdef CONFIG_MEMORY_FAILURE +static void clear_hwpoisoned_pages(struct page *memmap, int nr_pages) +{ + int i; + + /* + * A further optimization is to have per section refcounted + * num_poisoned_pages. But that would need more space per memmap, so + * for now just do a quick global check to speed up this routine in the + * absence of bad pages. + */ + if (atomic_long_read(&num_poisoned_pages) == 0) + return; + + for (i = 0; i < nr_pages; i++) { + if (PageHWPoison(&memmap[i])) { + num_poisoned_pages_dec(); + ClearPageHWPoison(&memmap[i]); + } + } +} +#else +static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages) +{ +} +#endif + +void sparse_remove_section(struct mem_section *ms, unsigned long pfn, + unsigned long nr_pages, unsigned long map_offset, + struct vmem_altmap *altmap) +{ + clear_hwpoisoned_pages(pfn_to_page(pfn) + map_offset, + nr_pages - map_offset); + section_deactivate(pfn, nr_pages, altmap); +} +#endif /* CONFIG_MEMORY_HOTPLUG */ diff --git a/mm/swap.c b/mm/swap.c new file mode 100644 index 000000000..47a47681c --- /dev/null +++ b/mm/swap.c @@ -0,0 +1,1215 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/mm/swap.c + * + * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds + */ + +/* + * This file contains the default values for the operation of the + * Linux VM subsystem. Fine-tuning documentation can be found in + * Documentation/admin-guide/sysctl/vm.rst. + * Started 18.12.91 + * Swap aging added 23.2.95, Stephen Tweedie. + * Buffermem limits added 12.3.98, Rik van Riel. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "internal.h" + +#define CREATE_TRACE_POINTS +#include + +/* How many pages do we try to swap or page in/out together? */ +int page_cluster; + +/* Protecting only lru_rotate.pvec which requires disabling interrupts */ +struct lru_rotate { + local_lock_t lock; + struct pagevec pvec; +}; +static DEFINE_PER_CPU(struct lru_rotate, lru_rotate) = { + .lock = INIT_LOCAL_LOCK(lock), +}; + +/* + * The following struct pagevec are grouped together because they are protected + * by disabling preemption (and interrupts remain enabled). + */ +struct lru_pvecs { + local_lock_t lock; + struct pagevec lru_add; + struct pagevec lru_deactivate_file; + struct pagevec lru_deactivate; + struct pagevec lru_lazyfree; +#ifdef CONFIG_SMP + struct pagevec activate_page; +#endif +}; +static DEFINE_PER_CPU(struct lru_pvecs, lru_pvecs) = { + .lock = INIT_LOCAL_LOCK(lock), +}; + +/* + * This path almost never happens for VM activity - pages are normally + * freed via pagevecs. But it gets used by networking. + */ +static void __page_cache_release(struct page *page) +{ + if (PageLRU(page)) { + pg_data_t *pgdat = page_pgdat(page); + struct lruvec *lruvec; + unsigned long flags; + + spin_lock_irqsave(&pgdat->lru_lock, flags); + lruvec = mem_cgroup_page_lruvec(page, pgdat); + VM_BUG_ON_PAGE(!PageLRU(page), page); + __ClearPageLRU(page); + del_page_from_lru_list(page, lruvec, page_off_lru(page)); + spin_unlock_irqrestore(&pgdat->lru_lock, flags); + } + __ClearPageWaiters(page); +} + +static void __put_single_page(struct page *page) +{ + __page_cache_release(page); + mem_cgroup_uncharge(page); + free_unref_page(page); +} + +static void __put_compound_page(struct page *page) +{ + /* + * __page_cache_release() is supposed to be called for thp, not for + * hugetlb. This is because hugetlb page does never have PageLRU set + * (it's never listed to any LRU lists) and no memcg routines should + * be called for hugetlb (it has a separate hugetlb_cgroup.) + */ + if (!PageHuge(page)) + __page_cache_release(page); + destroy_compound_page(page); +} + +void __put_page(struct page *page) +{ + if (is_zone_device_page(page)) { + put_dev_pagemap(page->pgmap); + + /* + * The page belongs to the device that created pgmap. Do + * not return it to page allocator. + */ + return; + } + + if (unlikely(PageCompound(page))) + __put_compound_page(page); + else + __put_single_page(page); +} +EXPORT_SYMBOL(__put_page); + +/** + * put_pages_list() - release a list of pages + * @pages: list of pages threaded on page->lru + * + * Release a list of pages which are strung together on page.lru. Currently + * used by read_cache_pages() and related error recovery code. + */ +void put_pages_list(struct list_head *pages) +{ + while (!list_empty(pages)) { + struct page *victim; + + victim = lru_to_page(pages); + list_del(&victim->lru); + put_page(victim); + } +} +EXPORT_SYMBOL(put_pages_list); + +/* + * get_kernel_pages() - pin kernel pages in memory + * @kiov: An array of struct kvec structures + * @nr_segs: number of segments to pin + * @write: pinning for read/write, currently ignored + * @pages: array that receives pointers to the pages pinned. + * Should be at least nr_segs long. + * + * Returns number of pages pinned. This may be fewer than the number + * requested. If nr_pages is 0 or negative, returns 0. If no pages + * were pinned, returns -errno. Each page returned must be released + * with a put_page() call when it is finished with. + */ +int get_kernel_pages(const struct kvec *kiov, int nr_segs, int write, + struct page **pages) +{ + int seg; + + for (seg = 0; seg < nr_segs; seg++) { + if (WARN_ON(kiov[seg].iov_len != PAGE_SIZE)) + return seg; + + pages[seg] = kmap_to_page(kiov[seg].iov_base); + get_page(pages[seg]); + } + + return seg; +} +EXPORT_SYMBOL_GPL(get_kernel_pages); + +/* + * get_kernel_page() - pin a kernel page in memory + * @start: starting kernel address + * @write: pinning for read/write, currently ignored + * @pages: array that receives pointer to the page pinned. + * Must be at least nr_segs long. + * + * Returns 1 if page is pinned. If the page was not pinned, returns + * -errno. The page returned must be released with a put_page() call + * when it is finished with. + */ +int get_kernel_page(unsigned long start, int write, struct page **pages) +{ + const struct kvec kiov = { + .iov_base = (void *)start, + .iov_len = PAGE_SIZE + }; + + return get_kernel_pages(&kiov, 1, write, pages); +} +EXPORT_SYMBOL_GPL(get_kernel_page); + +static void pagevec_lru_move_fn(struct pagevec *pvec, + void (*move_fn)(struct page *page, struct lruvec *lruvec, void *arg), + void *arg) +{ + int i; + struct pglist_data *pgdat = NULL; + struct lruvec *lruvec; + unsigned long flags = 0; + + for (i = 0; i < pagevec_count(pvec); i++) { + struct page *page = pvec->pages[i]; + struct pglist_data *pagepgdat = page_pgdat(page); + + if (pagepgdat != pgdat) { + if (pgdat) + spin_unlock_irqrestore(&pgdat->lru_lock, flags); + pgdat = pagepgdat; + spin_lock_irqsave(&pgdat->lru_lock, flags); + } + + lruvec = mem_cgroup_page_lruvec(page, pgdat); + (*move_fn)(page, lruvec, arg); + } + if (pgdat) + spin_unlock_irqrestore(&pgdat->lru_lock, flags); + release_pages(pvec->pages, pvec->nr); + pagevec_reinit(pvec); +} + +static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec, + void *arg) +{ + int *pgmoved = arg; + + if (PageLRU(page) && !PageUnevictable(page)) { + del_page_from_lru_list(page, lruvec, page_lru(page)); + ClearPageActive(page); + add_page_to_lru_list_tail(page, lruvec, page_lru(page)); + (*pgmoved) += thp_nr_pages(page); + } +} + +/* + * pagevec_move_tail() must be called with IRQ disabled. + * Otherwise this may cause nasty races. + */ +static void pagevec_move_tail(struct pagevec *pvec) +{ + int pgmoved = 0; + + pagevec_lru_move_fn(pvec, pagevec_move_tail_fn, &pgmoved); + __count_vm_events(PGROTATED, pgmoved); +} + +/* + * Writeback is about to end against a page which has been marked for immediate + * reclaim. If it still appears to be reclaimable, move it to the tail of the + * inactive list. + */ +void rotate_reclaimable_page(struct page *page) +{ + if (!PageLocked(page) && !PageDirty(page) && + !PageUnevictable(page) && PageLRU(page)) { + struct pagevec *pvec; + unsigned long flags; + + get_page(page); + local_lock_irqsave(&lru_rotate.lock, flags); + pvec = this_cpu_ptr(&lru_rotate.pvec); + if (!pagevec_add(pvec, page) || PageCompound(page)) + pagevec_move_tail(pvec); + local_unlock_irqrestore(&lru_rotate.lock, flags); + } +} + +void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages) +{ + do { + unsigned long lrusize; + + /* Record cost event */ + if (file) + lruvec->file_cost += nr_pages; + else + lruvec->anon_cost += nr_pages; + + /* + * Decay previous events + * + * Because workloads change over time (and to avoid + * overflow) we keep these statistics as a floating + * average, which ends up weighing recent refaults + * more than old ones. + */ + lrusize = lruvec_page_state(lruvec, NR_INACTIVE_ANON) + + lruvec_page_state(lruvec, NR_ACTIVE_ANON) + + lruvec_page_state(lruvec, NR_INACTIVE_FILE) + + lruvec_page_state(lruvec, NR_ACTIVE_FILE); + + if (lruvec->file_cost + lruvec->anon_cost > lrusize / 4) { + lruvec->file_cost /= 2; + lruvec->anon_cost /= 2; + } + } while ((lruvec = parent_lruvec(lruvec))); +} + +void lru_note_cost_page(struct page *page) +{ + lru_note_cost(mem_cgroup_page_lruvec(page, page_pgdat(page)), + page_is_file_lru(page), thp_nr_pages(page)); +} + +static void __activate_page(struct page *page, struct lruvec *lruvec, + void *arg) +{ + if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { + int lru = page_lru_base_type(page); + int nr_pages = thp_nr_pages(page); + + del_page_from_lru_list(page, lruvec, lru); + SetPageActive(page); + lru += LRU_ACTIVE; + add_page_to_lru_list(page, lruvec, lru); + trace_mm_lru_activate(page); + + __count_vm_events(PGACTIVATE, nr_pages); + __count_memcg_events(lruvec_memcg(lruvec), PGACTIVATE, + nr_pages); + } +} + +#ifdef CONFIG_SMP +static void activate_page_drain(int cpu) +{ + struct pagevec *pvec = &per_cpu(lru_pvecs.activate_page, cpu); + + if (pagevec_count(pvec)) + pagevec_lru_move_fn(pvec, __activate_page, NULL); +} + +static bool need_activate_page_drain(int cpu) +{ + return pagevec_count(&per_cpu(lru_pvecs.activate_page, cpu)) != 0; +} + +static void activate_page(struct page *page) +{ + page = compound_head(page); + if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { + struct pagevec *pvec; + + local_lock(&lru_pvecs.lock); + pvec = this_cpu_ptr(&lru_pvecs.activate_page); + get_page(page); + if (!pagevec_add(pvec, page) || PageCompound(page)) + pagevec_lru_move_fn(pvec, __activate_page, NULL); + local_unlock(&lru_pvecs.lock); + } +} + +#else +static inline void activate_page_drain(int cpu) +{ +} + +static void activate_page(struct page *page) +{ + pg_data_t *pgdat = page_pgdat(page); + + page = compound_head(page); + spin_lock_irq(&pgdat->lru_lock); + __activate_page(page, mem_cgroup_page_lruvec(page, pgdat), NULL); + spin_unlock_irq(&pgdat->lru_lock); +} +#endif + +static void __lru_cache_activate_page(struct page *page) +{ + struct pagevec *pvec; + int i; + + local_lock(&lru_pvecs.lock); + pvec = this_cpu_ptr(&lru_pvecs.lru_add); + + /* + * Search backwards on the optimistic assumption that the page being + * activated has just been added to this pagevec. Note that only + * the local pagevec is examined as a !PageLRU page could be in the + * process of being released, reclaimed, migrated or on a remote + * pagevec that is currently being drained. Furthermore, marking + * a remote pagevec's page PageActive potentially hits a race where + * a page is marked PageActive just after it is added to the inactive + * list causing accounting errors and BUG_ON checks to trigger. + */ + for (i = pagevec_count(pvec) - 1; i >= 0; i--) { + struct page *pagevec_page = pvec->pages[i]; + + if (pagevec_page == page) { + SetPageActive(page); + break; + } + } + + local_unlock(&lru_pvecs.lock); +} + +/* + * Mark a page as having seen activity. + * + * inactive,unreferenced -> inactive,referenced + * inactive,referenced -> active,unreferenced + * active,unreferenced -> active,referenced + * + * When a newly allocated page is not yet visible, so safe for non-atomic ops, + * __SetPageReferenced(page) may be substituted for mark_page_accessed(page). + */ +void mark_page_accessed(struct page *page) +{ + page = compound_head(page); + + if (!PageReferenced(page)) { + SetPageReferenced(page); + } else if (PageUnevictable(page)) { + /* + * Unevictable pages are on the "LRU_UNEVICTABLE" list. But, + * this list is never rotated or maintained, so marking an + * evictable page accessed has no effect. + */ + } else if (!PageActive(page)) { + /* + * If the page is on the LRU, queue it for activation via + * lru_pvecs.activate_page. Otherwise, assume the page is on a + * pagevec, mark it active and it'll be moved to the active + * LRU on the next drain. + */ + if (PageLRU(page)) + activate_page(page); + else + __lru_cache_activate_page(page); + ClearPageReferenced(page); + workingset_activation(page); + } + if (page_is_idle(page)) + clear_page_idle(page); +} +EXPORT_SYMBOL(mark_page_accessed); + +/** + * lru_cache_add - add a page to a page list + * @page: the page to be added to the LRU. + * + * Queue the page for addition to the LRU via pagevec. The decision on whether + * to add the page to the [in]active [file|anon] list is deferred until the + * pagevec is drained. This gives a chance for the caller of lru_cache_add() + * have the page added to the active list using mark_page_accessed(). + */ +void lru_cache_add(struct page *page) +{ + struct pagevec *pvec; + + VM_BUG_ON_PAGE(PageActive(page) && PageUnevictable(page), page); + VM_BUG_ON_PAGE(PageLRU(page), page); + + get_page(page); + local_lock(&lru_pvecs.lock); + pvec = this_cpu_ptr(&lru_pvecs.lru_add); + if (!pagevec_add(pvec, page) || PageCompound(page)) + __pagevec_lru_add(pvec); + local_unlock(&lru_pvecs.lock); +} +EXPORT_SYMBOL(lru_cache_add); + +/** + * lru_cache_add_inactive_or_unevictable + * @page: the page to be added to LRU + * @vma: vma in which page is mapped for determining reclaimability + * + * Place @page on the inactive or unevictable LRU list, depending on its + * evictability. + */ +void lru_cache_add_inactive_or_unevictable(struct page *page, + struct vm_area_struct *vma) +{ + bool unevictable; + + VM_BUG_ON_PAGE(PageLRU(page), page); + + unevictable = (vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) == VM_LOCKED; + if (unlikely(unevictable) && !TestSetPageMlocked(page)) { + int nr_pages = thp_nr_pages(page); + /* + * We use the irq-unsafe __mod_zone_page_stat because this + * counter is not modified from interrupt context, and the pte + * lock is held(spinlock), which implies preemption disabled. + */ + __mod_zone_page_state(page_zone(page), NR_MLOCK, nr_pages); + count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages); + } + lru_cache_add(page); +} + +/* + * If the page can not be invalidated, it is moved to the + * inactive list to speed up its reclaim. It is moved to the + * head of the list, rather than the tail, to give the flusher + * threads some time to write it out, as this is much more + * effective than the single-page writeout from reclaim. + * + * If the page isn't page_mapped and dirty/writeback, the page + * could reclaim asap using PG_reclaim. + * + * 1. active, mapped page -> none + * 2. active, dirty/writeback page -> inactive, head, PG_reclaim + * 3. inactive, mapped page -> none + * 4. inactive, dirty/writeback page -> inactive, head, PG_reclaim + * 5. inactive, clean -> inactive, tail + * 6. Others -> none + * + * In 4, why it moves inactive's head, the VM expects the page would + * be write it out by flusher threads as this is much more effective + * than the single-page writeout from reclaim. + */ +static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec, + void *arg) +{ + int lru; + bool active; + int nr_pages = thp_nr_pages(page); + + if (!PageLRU(page)) + return; + + if (PageUnevictable(page)) + return; + + /* Some processes are using the page */ + if (page_mapped(page)) + return; + + active = PageActive(page); + lru = page_lru_base_type(page); + + del_page_from_lru_list(page, lruvec, lru + active); + ClearPageActive(page); + ClearPageReferenced(page); + + if (PageWriteback(page) || PageDirty(page)) { + /* + * PG_reclaim could be raced with end_page_writeback + * It can make readahead confusing. But race window + * is _really_ small and it's non-critical problem. + */ + add_page_to_lru_list(page, lruvec, lru); + SetPageReclaim(page); + } else { + /* + * The page's writeback ends up during pagevec + * We moves tha page into tail of inactive. + */ + add_page_to_lru_list_tail(page, lruvec, lru); + __count_vm_events(PGROTATED, nr_pages); + } + + if (active) { + __count_vm_events(PGDEACTIVATE, nr_pages); + __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, + nr_pages); + } +} + +static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec, + void *arg) +{ + if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) { + int lru = page_lru_base_type(page); + int nr_pages = thp_nr_pages(page); + + del_page_from_lru_list(page, lruvec, lru + LRU_ACTIVE); + ClearPageActive(page); + ClearPageReferenced(page); + add_page_to_lru_list(page, lruvec, lru); + + __count_vm_events(PGDEACTIVATE, nr_pages); + __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, + nr_pages); + } +} + +static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec, + void *arg) +{ + if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) && + !PageSwapCache(page) && !PageUnevictable(page)) { + bool active = PageActive(page); + int nr_pages = thp_nr_pages(page); + + del_page_from_lru_list(page, lruvec, + LRU_INACTIVE_ANON + active); + ClearPageActive(page); + ClearPageReferenced(page); + /* + * Lazyfree pages are clean anonymous pages. They have + * PG_swapbacked flag cleared, to distinguish them from normal + * anonymous pages + */ + ClearPageSwapBacked(page); + add_page_to_lru_list(page, lruvec, LRU_INACTIVE_FILE); + + __count_vm_events(PGLAZYFREE, nr_pages); + __count_memcg_events(lruvec_memcg(lruvec), PGLAZYFREE, + nr_pages); + } +} + +/* + * Drain pages out of the cpu's pagevecs. + * Either "cpu" is the current CPU, and preemption has already been + * disabled; or "cpu" is being hot-unplugged, and is already dead. + */ +void lru_add_drain_cpu(int cpu) +{ + struct pagevec *pvec = &per_cpu(lru_pvecs.lru_add, cpu); + + if (pagevec_count(pvec)) + __pagevec_lru_add(pvec); + + pvec = &per_cpu(lru_rotate.pvec, cpu); + /* Disabling interrupts below acts as a compiler barrier. */ + if (data_race(pagevec_count(pvec))) { + unsigned long flags; + + /* No harm done if a racing interrupt already did this */ + local_lock_irqsave(&lru_rotate.lock, flags); + pagevec_move_tail(pvec); + local_unlock_irqrestore(&lru_rotate.lock, flags); + } + + pvec = &per_cpu(lru_pvecs.lru_deactivate_file, cpu); + if (pagevec_count(pvec)) + pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL); + + pvec = &per_cpu(lru_pvecs.lru_deactivate, cpu); + if (pagevec_count(pvec)) + pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); + + pvec = &per_cpu(lru_pvecs.lru_lazyfree, cpu); + if (pagevec_count(pvec)) + pagevec_lru_move_fn(pvec, lru_lazyfree_fn, NULL); + + activate_page_drain(cpu); +} + +/** + * deactivate_file_page - forcefully deactivate a file page + * @page: page to deactivate + * + * This function hints the VM that @page is a good reclaim candidate, + * for example if its invalidation fails due to the page being dirty + * or under writeback. + */ +void deactivate_file_page(struct page *page) +{ + /* + * In a workload with many unevictable page such as mprotect, + * unevictable page deactivation for accelerating reclaim is pointless. + */ + if (PageUnevictable(page)) + return; + + if (likely(get_page_unless_zero(page))) { + struct pagevec *pvec; + + local_lock(&lru_pvecs.lock); + pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate_file); + + if (!pagevec_add(pvec, page) || PageCompound(page)) + pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL); + local_unlock(&lru_pvecs.lock); + } +} + +/* + * deactivate_page - deactivate a page + * @page: page to deactivate + * + * deactivate_page() moves @page to the inactive list if @page was on the active + * list and was not an unevictable page. This is done to accelerate the reclaim + * of @page. + */ +void deactivate_page(struct page *page) +{ + if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) { + struct pagevec *pvec; + + local_lock(&lru_pvecs.lock); + pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate); + get_page(page); + if (!pagevec_add(pvec, page) || PageCompound(page)) + pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); + local_unlock(&lru_pvecs.lock); + } +} + +/** + * mark_page_lazyfree - make an anon page lazyfree + * @page: page to deactivate + * + * mark_page_lazyfree() moves @page to the inactive file list. + * This is done to accelerate the reclaim of @page. + */ +void mark_page_lazyfree(struct page *page) +{ + if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) && + !PageSwapCache(page) && !PageUnevictable(page)) { + struct pagevec *pvec; + + local_lock(&lru_pvecs.lock); + pvec = this_cpu_ptr(&lru_pvecs.lru_lazyfree); + get_page(page); + if (!pagevec_add(pvec, page) || PageCompound(page)) + pagevec_lru_move_fn(pvec, lru_lazyfree_fn, NULL); + local_unlock(&lru_pvecs.lock); + } +} + +void lru_add_drain(void) +{ + local_lock(&lru_pvecs.lock); + lru_add_drain_cpu(smp_processor_id()); + local_unlock(&lru_pvecs.lock); +} + +void lru_add_drain_cpu_zone(struct zone *zone) +{ + local_lock(&lru_pvecs.lock); + lru_add_drain_cpu(smp_processor_id()); + drain_local_pages(zone); + local_unlock(&lru_pvecs.lock); +} + +#ifdef CONFIG_SMP + +static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); + +static void lru_add_drain_per_cpu(struct work_struct *dummy) +{ + lru_add_drain(); +} + +/* + * Doesn't need any cpu hotplug locking because we do rely on per-cpu + * kworkers being shut down before our page_alloc_cpu_dead callback is + * executed on the offlined cpu. + * Calling this function with cpu hotplug locks held can actually lead + * to obscure indirect dependencies via WQ context. + */ +void lru_add_drain_all(void) +{ + /* + * lru_drain_gen - Global pages generation number + * + * (A) Definition: global lru_drain_gen = x implies that all generations + * 0 < n <= x are already *scheduled* for draining. + * + * This is an optimization for the highly-contended use case where a + * user space workload keeps constantly generating a flow of pages for + * each CPU. + */ + static unsigned int lru_drain_gen; + static struct cpumask has_work; + static DEFINE_MUTEX(lock); + unsigned cpu, this_gen; + + /* + * Make sure nobody triggers this path before mm_percpu_wq is fully + * initialized. + */ + if (WARN_ON(!mm_percpu_wq)) + return; + + /* + * Guarantee pagevec counter stores visible by this CPU are visible to + * other CPUs before loading the current drain generation. + */ + smp_mb(); + + /* + * (B) Locally cache global LRU draining generation number + * + * The read barrier ensures that the counter is loaded before the mutex + * is taken. It pairs with smp_mb() inside the mutex critical section + * at (D). + */ + this_gen = smp_load_acquire(&lru_drain_gen); + + mutex_lock(&lock); + + /* + * (C) Exit the draining operation if a newer generation, from another + * lru_add_drain_all(), was already scheduled for draining. Check (A). + */ + if (unlikely(this_gen != lru_drain_gen)) + goto done; + + /* + * (D) Increment global generation number + * + * Pairs with smp_load_acquire() at (B), outside of the critical + * section. Use a full memory barrier to guarantee that the new global + * drain generation number is stored before loading pagevec counters. + * + * This pairing must be done here, before the for_each_online_cpu loop + * below which drains the page vectors. + * + * Let x, y, and z represent some system CPU numbers, where x < y < z. + * Assume CPU #z is is in the middle of the for_each_online_cpu loop + * below and has already reached CPU #y's per-cpu data. CPU #x comes + * along, adds some pages to its per-cpu vectors, then calls + * lru_add_drain_all(). + * + * If the paired barrier is done at any later step, e.g. after the + * loop, CPU #x will just exit at (C) and miss flushing out all of its + * added pages. + */ + WRITE_ONCE(lru_drain_gen, lru_drain_gen + 1); + smp_mb(); + + cpumask_clear(&has_work); + for_each_online_cpu(cpu) { + struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); + + if (pagevec_count(&per_cpu(lru_pvecs.lru_add, cpu)) || + data_race(pagevec_count(&per_cpu(lru_rotate.pvec, cpu))) || + pagevec_count(&per_cpu(lru_pvecs.lru_deactivate_file, cpu)) || + pagevec_count(&per_cpu(lru_pvecs.lru_deactivate, cpu)) || + pagevec_count(&per_cpu(lru_pvecs.lru_lazyfree, cpu)) || + need_activate_page_drain(cpu)) { + INIT_WORK(work, lru_add_drain_per_cpu); + queue_work_on(cpu, mm_percpu_wq, work); + __cpumask_set_cpu(cpu, &has_work); + } + } + + for_each_cpu(cpu, &has_work) + flush_work(&per_cpu(lru_add_drain_work, cpu)); + +done: + mutex_unlock(&lock); +} +#else +void lru_add_drain_all(void) +{ + lru_add_drain(); +} +#endif /* CONFIG_SMP */ + +/** + * release_pages - batched put_page() + * @pages: array of pages to release + * @nr: number of pages + * + * Decrement the reference count on all the pages in @pages. If it + * fell to zero, remove the page from the LRU and free it. + */ +void release_pages(struct page **pages, int nr) +{ + int i; + LIST_HEAD(pages_to_free); + struct pglist_data *locked_pgdat = NULL; + struct lruvec *lruvec; + unsigned long flags; + unsigned int lock_batch; + + for (i = 0; i < nr; i++) { + struct page *page = pages[i]; + + /* + * Make sure the IRQ-safe lock-holding time does not get + * excessive with a continuous string of pages from the + * same pgdat. The lock is held only if pgdat != NULL. + */ + if (locked_pgdat && ++lock_batch == SWAP_CLUSTER_MAX) { + spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags); + locked_pgdat = NULL; + } + + page = compound_head(page); + if (is_huge_zero_page(page)) + continue; + + if (is_zone_device_page(page)) { + if (locked_pgdat) { + spin_unlock_irqrestore(&locked_pgdat->lru_lock, + flags); + locked_pgdat = NULL; + } + /* + * ZONE_DEVICE pages that return 'false' from + * page_is_devmap_managed() do not require special + * processing, and instead, expect a call to + * put_page_testzero(). + */ + if (page_is_devmap_managed(page)) { + put_devmap_managed_page(page); + continue; + } + } + + if (!put_page_testzero(page)) + continue; + + if (PageCompound(page)) { + if (locked_pgdat) { + spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags); + locked_pgdat = NULL; + } + __put_compound_page(page); + continue; + } + + if (PageLRU(page)) { + struct pglist_data *pgdat = page_pgdat(page); + + if (pgdat != locked_pgdat) { + if (locked_pgdat) + spin_unlock_irqrestore(&locked_pgdat->lru_lock, + flags); + lock_batch = 0; + locked_pgdat = pgdat; + spin_lock_irqsave(&locked_pgdat->lru_lock, flags); + } + + lruvec = mem_cgroup_page_lruvec(page, locked_pgdat); + VM_BUG_ON_PAGE(!PageLRU(page), page); + __ClearPageLRU(page); + del_page_from_lru_list(page, lruvec, page_off_lru(page)); + } + + __ClearPageWaiters(page); + + list_add(&page->lru, &pages_to_free); + } + if (locked_pgdat) + spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags); + + mem_cgroup_uncharge_list(&pages_to_free); + free_unref_page_list(&pages_to_free); +} +EXPORT_SYMBOL(release_pages); + +/* + * The pages which we're about to release may be in the deferred lru-addition + * queues. That would prevent them from really being freed right now. That's + * OK from a correctness point of view but is inefficient - those pages may be + * cache-warm and we want to give them back to the page allocator ASAP. + * + * So __pagevec_release() will drain those queues here. __pagevec_lru_add() + * and __pagevec_lru_add_active() call release_pages() directly to avoid + * mutual recursion. + */ +void __pagevec_release(struct pagevec *pvec) +{ + if (!pvec->percpu_pvec_drained) { + lru_add_drain(); + pvec->percpu_pvec_drained = true; + } + release_pages(pvec->pages, pagevec_count(pvec)); + pagevec_reinit(pvec); +} +EXPORT_SYMBOL(__pagevec_release); + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +/* used by __split_huge_page_refcount() */ +void lru_add_page_tail(struct page *page, struct page *page_tail, + struct lruvec *lruvec, struct list_head *list) +{ + VM_BUG_ON_PAGE(!PageHead(page), page); + VM_BUG_ON_PAGE(PageCompound(page_tail), page); + VM_BUG_ON_PAGE(PageLRU(page_tail), page); + lockdep_assert_held(&lruvec_pgdat(lruvec)->lru_lock); + + if (!list) + SetPageLRU(page_tail); + + if (likely(PageLRU(page))) + list_add_tail(&page_tail->lru, &page->lru); + else if (list) { + /* page reclaim is reclaiming a huge page */ + get_page(page_tail); + list_add_tail(&page_tail->lru, list); + } else { + /* + * Head page has not yet been counted, as an hpage, + * so we must account for each subpage individually. + * + * Put page_tail on the list at the correct position + * so they all end up in order. + */ + add_page_to_lru_list_tail(page_tail, lruvec, + page_lru(page_tail)); + } +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec, + void *arg) +{ + enum lru_list lru; + int was_unevictable = TestClearPageUnevictable(page); + int nr_pages = thp_nr_pages(page); + + VM_BUG_ON_PAGE(PageLRU(page), page); + + /* + * Page becomes evictable in two ways: + * 1) Within LRU lock [munlock_vma_page() and __munlock_pagevec()]. + * 2) Before acquiring LRU lock to put the page to correct LRU and then + * a) do PageLRU check with lock [check_move_unevictable_pages] + * b) do PageLRU check before lock [clear_page_mlock] + * + * (1) & (2a) are ok as LRU lock will serialize them. For (2b), we need + * following strict ordering: + * + * #0: __pagevec_lru_add_fn #1: clear_page_mlock + * + * SetPageLRU() TestClearPageMlocked() + * smp_mb() // explicit ordering // above provides strict + * // ordering + * PageMlocked() PageLRU() + * + * + * if '#1' does not observe setting of PG_lru by '#0' and fails + * isolation, the explicit barrier will make sure that page_evictable + * check will put the page in correct LRU. Without smp_mb(), SetPageLRU + * can be reordered after PageMlocked check and can make '#1' to fail + * the isolation of the page whose Mlocked bit is cleared (#0 is also + * looking at the same page) and the evictable page will be stranded + * in an unevictable LRU. + */ + SetPageLRU(page); + smp_mb__after_atomic(); + + if (page_evictable(page)) { + lru = page_lru(page); + if (was_unevictable) + __count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages); + } else { + lru = LRU_UNEVICTABLE; + ClearPageActive(page); + SetPageUnevictable(page); + if (!was_unevictable) + __count_vm_events(UNEVICTABLE_PGCULLED, nr_pages); + } + + add_page_to_lru_list(page, lruvec, lru); + trace_mm_lru_insertion(page, lru); +} + +/* + * Add the passed pages to the LRU, then drop the caller's refcount + * on them. Reinitialises the caller's pagevec. + */ +void __pagevec_lru_add(struct pagevec *pvec) +{ + pagevec_lru_move_fn(pvec, __pagevec_lru_add_fn, NULL); +} + +/** + * pagevec_lookup_entries - gang pagecache lookup + * @pvec: Where the resulting entries are placed + * @mapping: The address_space to search + * @start: The starting entry index + * @nr_entries: The maximum number of pages + * @indices: The cache indices corresponding to the entries in @pvec + * + * pagevec_lookup_entries() will search for and return a group of up + * to @nr_pages pages and shadow entries in the mapping. All + * entries are placed in @pvec. pagevec_lookup_entries() takes a + * reference against actual pages in @pvec. + * + * The search returns a group of mapping-contiguous entries with + * ascending indexes. There may be holes in the indices due to + * not-present entries. + * + * Only one subpage of a Transparent Huge Page is returned in one call: + * allowing truncate_inode_pages_range() to evict the whole THP without + * cycling through a pagevec of extra references. + * + * pagevec_lookup_entries() returns the number of entries which were + * found. + */ +unsigned pagevec_lookup_entries(struct pagevec *pvec, + struct address_space *mapping, + pgoff_t start, unsigned nr_entries, + pgoff_t *indices) +{ + pvec->nr = find_get_entries(mapping, start, nr_entries, + pvec->pages, indices); + return pagevec_count(pvec); +} + +/** + * pagevec_remove_exceptionals - pagevec exceptionals pruning + * @pvec: The pagevec to prune + * + * pagevec_lookup_entries() fills both pages and exceptional radix + * tree entries into the pagevec. This function prunes all + * exceptionals from @pvec without leaving holes, so that it can be + * passed on to page-only pagevec operations. + */ +void pagevec_remove_exceptionals(struct pagevec *pvec) +{ + int i, j; + + for (i = 0, j = 0; i < pagevec_count(pvec); i++) { + struct page *page = pvec->pages[i]; + if (!xa_is_value(page)) + pvec->pages[j++] = page; + } + pvec->nr = j; +} + +/** + * pagevec_lookup_range - gang pagecache lookup + * @pvec: Where the resulting pages are placed + * @mapping: The address_space to search + * @start: The starting page index + * @end: The final page index + * + * pagevec_lookup_range() will search for & return a group of up to PAGEVEC_SIZE + * pages in the mapping starting from index @start and upto index @end + * (inclusive). The pages are placed in @pvec. pagevec_lookup() takes a + * reference against the pages in @pvec. + * + * The search returns a group of mapping-contiguous pages with ascending + * indexes. There may be holes in the indices due to not-present pages. We + * also update @start to index the next page for the traversal. + * + * pagevec_lookup_range() returns the number of pages which were found. If this + * number is smaller than PAGEVEC_SIZE, the end of specified range has been + * reached. + */ +unsigned pagevec_lookup_range(struct pagevec *pvec, + struct address_space *mapping, pgoff_t *start, pgoff_t end) +{ + pvec->nr = find_get_pages_range(mapping, start, end, PAGEVEC_SIZE, + pvec->pages); + return pagevec_count(pvec); +} +EXPORT_SYMBOL(pagevec_lookup_range); + +unsigned pagevec_lookup_range_tag(struct pagevec *pvec, + struct address_space *mapping, pgoff_t *index, pgoff_t end, + xa_mark_t tag) +{ + pvec->nr = find_get_pages_range_tag(mapping, index, end, tag, + PAGEVEC_SIZE, pvec->pages); + return pagevec_count(pvec); +} +EXPORT_SYMBOL(pagevec_lookup_range_tag); + +unsigned pagevec_lookup_range_nr_tag(struct pagevec *pvec, + struct address_space *mapping, pgoff_t *index, pgoff_t end, + xa_mark_t tag, unsigned max_pages) +{ + pvec->nr = find_get_pages_range_tag(mapping, index, end, tag, + min_t(unsigned int, max_pages, PAGEVEC_SIZE), pvec->pages); + return pagevec_count(pvec); +} +EXPORT_SYMBOL(pagevec_lookup_range_nr_tag); +/* + * Perform any setup for the swap system + */ +void __init swap_setup(void) +{ + unsigned long megs = totalram_pages() >> (20 - PAGE_SHIFT); + + /* Use a smaller cluster for small-memory machines */ + if (megs < 16) + page_cluster = 2; + else + page_cluster = 3; + /* + * Right now other parts of the system means that we + * _really_ don't want to cluster much more + */ +} + +#ifdef CONFIG_DEV_PAGEMAP_OPS +void put_devmap_managed_page(struct page *page) +{ + int count; + + if (WARN_ON_ONCE(!page_is_devmap_managed(page))) + return; + + count = page_ref_dec_return(page); + + /* + * devmap page refcounts are 1-based, rather than 0-based: if + * refcount is 1, then the page is free and the refcount is + * stable because nobody holds a reference on the page. + */ + if (count == 1) + free_devmap_managed_page(page); + else if (!count) + __put_page(page); +} +EXPORT_SYMBOL(put_devmap_managed_page); +#endif diff --git a/mm/swap_cgroup.c b/mm/swap_cgroup.c new file mode 100644 index 000000000..7f34343c0 --- /dev/null +++ b/mm/swap_cgroup.c @@ -0,0 +1,227 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include + +#include /* depends on mm.h include */ + +static DEFINE_MUTEX(swap_cgroup_mutex); +struct swap_cgroup_ctrl { + struct page **map; + unsigned long length; + spinlock_t lock; +}; + +static struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES]; + +struct swap_cgroup { + unsigned short id; +}; +#define SC_PER_PAGE (PAGE_SIZE/sizeof(struct swap_cgroup)) + +/* + * SwapCgroup implements "lookup" and "exchange" operations. + * In typical usage, this swap_cgroup is accessed via memcg's charge/uncharge + * against SwapCache. At swap_free(), this is accessed directly from swap. + * + * This means, + * - we have no race in "exchange" when we're accessed via SwapCache because + * SwapCache(and its swp_entry) is under lock. + * - When called via swap_free(), there is no user of this entry and no race. + * Then, we don't need lock around "exchange". + * + * TODO: we can push these buffers out to HIGHMEM. + */ + +/* + * allocate buffer for swap_cgroup. + */ +static int swap_cgroup_prepare(int type) +{ + struct page *page; + struct swap_cgroup_ctrl *ctrl; + unsigned long idx, max; + + ctrl = &swap_cgroup_ctrl[type]; + + for (idx = 0; idx < ctrl->length; idx++) { + page = alloc_page(GFP_KERNEL | __GFP_ZERO); + if (!page) + goto not_enough_page; + ctrl->map[idx] = page; + + if (!(idx % SWAP_CLUSTER_MAX)) + cond_resched(); + } + return 0; +not_enough_page: + max = idx; + for (idx = 0; idx < max; idx++) + __free_page(ctrl->map[idx]); + + return -ENOMEM; +} + +static struct swap_cgroup *__lookup_swap_cgroup(struct swap_cgroup_ctrl *ctrl, + pgoff_t offset) +{ + struct page *mappage; + struct swap_cgroup *sc; + + mappage = ctrl->map[offset / SC_PER_PAGE]; + sc = page_address(mappage); + return sc + offset % SC_PER_PAGE; +} + +static struct swap_cgroup *lookup_swap_cgroup(swp_entry_t ent, + struct swap_cgroup_ctrl **ctrlp) +{ + pgoff_t offset = swp_offset(ent); + struct swap_cgroup_ctrl *ctrl; + + ctrl = &swap_cgroup_ctrl[swp_type(ent)]; + if (ctrlp) + *ctrlp = ctrl; + return __lookup_swap_cgroup(ctrl, offset); +} + +/** + * swap_cgroup_cmpxchg - cmpxchg mem_cgroup's id for this swp_entry. + * @ent: swap entry to be cmpxchged + * @old: old id + * @new: new id + * + * Returns old id at success, 0 at failure. + * (There is no mem_cgroup using 0 as its id) + */ +unsigned short swap_cgroup_cmpxchg(swp_entry_t ent, + unsigned short old, unsigned short new) +{ + struct swap_cgroup_ctrl *ctrl; + struct swap_cgroup *sc; + unsigned long flags; + unsigned short retval; + + sc = lookup_swap_cgroup(ent, &ctrl); + + spin_lock_irqsave(&ctrl->lock, flags); + retval = sc->id; + if (retval == old) + sc->id = new; + else + retval = 0; + spin_unlock_irqrestore(&ctrl->lock, flags); + return retval; +} + +/** + * swap_cgroup_record - record mem_cgroup for a set of swap entries + * @ent: the first swap entry to be recorded into + * @id: mem_cgroup to be recorded + * @nr_ents: number of swap entries to be recorded + * + * Returns old value at success, 0 at failure. + * (Of course, old value can be 0.) + */ +unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id, + unsigned int nr_ents) +{ + struct swap_cgroup_ctrl *ctrl; + struct swap_cgroup *sc; + unsigned short old; + unsigned long flags; + pgoff_t offset = swp_offset(ent); + pgoff_t end = offset + nr_ents; + + sc = lookup_swap_cgroup(ent, &ctrl); + + spin_lock_irqsave(&ctrl->lock, flags); + old = sc->id; + for (;;) { + VM_BUG_ON(sc->id != old); + sc->id = id; + offset++; + if (offset == end) + break; + if (offset % SC_PER_PAGE) + sc++; + else + sc = __lookup_swap_cgroup(ctrl, offset); + } + spin_unlock_irqrestore(&ctrl->lock, flags); + + return old; +} + +/** + * lookup_swap_cgroup_id - lookup mem_cgroup id tied to swap entry + * @ent: swap entry to be looked up. + * + * Returns ID of mem_cgroup at success. 0 at failure. (0 is invalid ID) + */ +unsigned short lookup_swap_cgroup_id(swp_entry_t ent) +{ + return lookup_swap_cgroup(ent, NULL)->id; +} + +int swap_cgroup_swapon(int type, unsigned long max_pages) +{ + void *array; + unsigned long array_size; + unsigned long length; + struct swap_cgroup_ctrl *ctrl; + + length = DIV_ROUND_UP(max_pages, SC_PER_PAGE); + array_size = length * sizeof(void *); + + array = vzalloc(array_size); + if (!array) + goto nomem; + + ctrl = &swap_cgroup_ctrl[type]; + mutex_lock(&swap_cgroup_mutex); + ctrl->length = length; + ctrl->map = array; + spin_lock_init(&ctrl->lock); + if (swap_cgroup_prepare(type)) { + /* memory shortage */ + ctrl->map = NULL; + ctrl->length = 0; + mutex_unlock(&swap_cgroup_mutex); + vfree(array); + goto nomem; + } + mutex_unlock(&swap_cgroup_mutex); + + return 0; +nomem: + pr_info("couldn't allocate enough memory for swap_cgroup\n"); + pr_info("swap_cgroup can be disabled by swapaccount=0 boot option\n"); + return -ENOMEM; +} + +void swap_cgroup_swapoff(int type) +{ + struct page **map; + unsigned long i, length; + struct swap_cgroup_ctrl *ctrl; + + mutex_lock(&swap_cgroup_mutex); + ctrl = &swap_cgroup_ctrl[type]; + map = ctrl->map; + length = ctrl->length; + ctrl->map = NULL; + ctrl->length = 0; + mutex_unlock(&swap_cgroup_mutex); + + if (map) { + for (i = 0; i < length; i++) { + struct page *page = map[i]; + if (page) + __free_page(page); + if (!(i % SWAP_CLUSTER_MAX)) + cond_resched(); + } + vfree(map); + } +} diff --git a/mm/swap_slots.c b/mm/swap_slots.c new file mode 100644 index 000000000..0357fbe70 --- /dev/null +++ b/mm/swap_slots.c @@ -0,0 +1,354 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Manage cache of swap slots to be used for and returned from + * swap. + * + * Copyright(c) 2016 Intel Corporation. + * + * Author: Tim Chen + * + * We allocate the swap slots from the global pool and put + * it into local per cpu caches. This has the advantage + * of no needing to acquire the swap_info lock every time + * we need a new slot. + * + * There is also opportunity to simply return the slot + * to local caches without needing to acquire swap_info + * lock. We do not reuse the returned slots directly but + * move them back to the global pool in a batch. This + * allows the slots to coaellesce and reduce fragmentation. + * + * The swap entry allocated is marked with SWAP_HAS_CACHE + * flag in map_count that prevents it from being allocated + * again from the global pool. + * + * The swap slots cache is protected by a mutex instead of + * a spin lock as when we search for slots with scan_swap_map, + * we can possibly sleep. + */ + +#include +#include +#include +#include +#include +#include + +static DEFINE_PER_CPU(struct swap_slots_cache, swp_slots); +static bool swap_slot_cache_active; +bool swap_slot_cache_enabled; +static bool swap_slot_cache_initialized; +static DEFINE_MUTEX(swap_slots_cache_mutex); +/* Serialize swap slots cache enable/disable operations */ +static DEFINE_MUTEX(swap_slots_cache_enable_mutex); + +static void __drain_swap_slots_cache(unsigned int type); +static void deactivate_swap_slots_cache(void); +static void reactivate_swap_slots_cache(void); + +#define use_swap_slot_cache (swap_slot_cache_active && swap_slot_cache_enabled) +#define SLOTS_CACHE 0x1 +#define SLOTS_CACHE_RET 0x2 + +static void deactivate_swap_slots_cache(void) +{ + mutex_lock(&swap_slots_cache_mutex); + swap_slot_cache_active = false; + __drain_swap_slots_cache(SLOTS_CACHE|SLOTS_CACHE_RET); + mutex_unlock(&swap_slots_cache_mutex); +} + +static void reactivate_swap_slots_cache(void) +{ + mutex_lock(&swap_slots_cache_mutex); + swap_slot_cache_active = true; + mutex_unlock(&swap_slots_cache_mutex); +} + +/* Must not be called with cpu hot plug lock */ +void disable_swap_slots_cache_lock(void) +{ + mutex_lock(&swap_slots_cache_enable_mutex); + swap_slot_cache_enabled = false; + if (swap_slot_cache_initialized) { + /* serialize with cpu hotplug operations */ + get_online_cpus(); + __drain_swap_slots_cache(SLOTS_CACHE|SLOTS_CACHE_RET); + put_online_cpus(); + } +} + +static void __reenable_swap_slots_cache(void) +{ + swap_slot_cache_enabled = has_usable_swap(); +} + +void reenable_swap_slots_cache_unlock(void) +{ + __reenable_swap_slots_cache(); + mutex_unlock(&swap_slots_cache_enable_mutex); +} + +static bool check_cache_active(void) +{ + long pages; + + if (!swap_slot_cache_enabled) + return false; + + pages = get_nr_swap_pages(); + if (!swap_slot_cache_active) { + if (pages > num_online_cpus() * + THRESHOLD_ACTIVATE_SWAP_SLOTS_CACHE) + reactivate_swap_slots_cache(); + goto out; + } + + /* if global pool of slot caches too low, deactivate cache */ + if (pages < num_online_cpus() * THRESHOLD_DEACTIVATE_SWAP_SLOTS_CACHE) + deactivate_swap_slots_cache(); +out: + return swap_slot_cache_active; +} + +static int alloc_swap_slot_cache(unsigned int cpu) +{ + struct swap_slots_cache *cache; + swp_entry_t *slots, *slots_ret; + + /* + * Do allocation outside swap_slots_cache_mutex + * as kvzalloc could trigger reclaim and get_swap_page, + * which can lock swap_slots_cache_mutex. + */ + slots = kvcalloc(SWAP_SLOTS_CACHE_SIZE, sizeof(swp_entry_t), + GFP_KERNEL); + if (!slots) + return -ENOMEM; + + slots_ret = kvcalloc(SWAP_SLOTS_CACHE_SIZE, sizeof(swp_entry_t), + GFP_KERNEL); + if (!slots_ret) { + kvfree(slots); + return -ENOMEM; + } + + mutex_lock(&swap_slots_cache_mutex); + cache = &per_cpu(swp_slots, cpu); + if (cache->slots || cache->slots_ret) { + /* cache already allocated */ + mutex_unlock(&swap_slots_cache_mutex); + + kvfree(slots); + kvfree(slots_ret); + + return 0; + } + + if (!cache->lock_initialized) { + mutex_init(&cache->alloc_lock); + spin_lock_init(&cache->free_lock); + cache->lock_initialized = true; + } + cache->nr = 0; + cache->cur = 0; + cache->n_ret = 0; + /* + * We initialized alloc_lock and free_lock earlier. We use + * !cache->slots or !cache->slots_ret to know if it is safe to acquire + * the corresponding lock and use the cache. Memory barrier below + * ensures the assumption. + */ + mb(); + cache->slots = slots; + cache->slots_ret = slots_ret; + mutex_unlock(&swap_slots_cache_mutex); + return 0; +} + +static void drain_slots_cache_cpu(unsigned int cpu, unsigned int type, + bool free_slots) +{ + struct swap_slots_cache *cache; + swp_entry_t *slots = NULL; + + cache = &per_cpu(swp_slots, cpu); + if ((type & SLOTS_CACHE) && cache->slots) { + mutex_lock(&cache->alloc_lock); + swapcache_free_entries(cache->slots + cache->cur, cache->nr); + cache->cur = 0; + cache->nr = 0; + if (free_slots && cache->slots) { + kvfree(cache->slots); + cache->slots = NULL; + } + mutex_unlock(&cache->alloc_lock); + } + if ((type & SLOTS_CACHE_RET) && cache->slots_ret) { + spin_lock_irq(&cache->free_lock); + swapcache_free_entries(cache->slots_ret, cache->n_ret); + cache->n_ret = 0; + if (free_slots && cache->slots_ret) { + slots = cache->slots_ret; + cache->slots_ret = NULL; + } + spin_unlock_irq(&cache->free_lock); + if (slots) + kvfree(slots); + } +} + +static void __drain_swap_slots_cache(unsigned int type) +{ + unsigned int cpu; + + /* + * This function is called during + * 1) swapoff, when we have to make sure no + * left over slots are in cache when we remove + * a swap device; + * 2) disabling of swap slot cache, when we run low + * on swap slots when allocating memory and need + * to return swap slots to global pool. + * + * We cannot acquire cpu hot plug lock here as + * this function can be invoked in the cpu + * hot plug path: + * cpu_up -> lock cpu_hotplug -> cpu hotplug state callback + * -> memory allocation -> direct reclaim -> get_swap_page + * -> drain_swap_slots_cache + * + * Hence the loop over current online cpu below could miss cpu that + * is being brought online but not yet marked as online. + * That is okay as we do not schedule and run anything on a + * cpu before it has been marked online. Hence, we will not + * fill any swap slots in slots cache of such cpu. + * There are no slots on such cpu that need to be drained. + */ + for_each_online_cpu(cpu) + drain_slots_cache_cpu(cpu, type, false); +} + +static int free_slot_cache(unsigned int cpu) +{ + mutex_lock(&swap_slots_cache_mutex); + drain_slots_cache_cpu(cpu, SLOTS_CACHE | SLOTS_CACHE_RET, true); + mutex_unlock(&swap_slots_cache_mutex); + return 0; +} + +void enable_swap_slots_cache(void) +{ + mutex_lock(&swap_slots_cache_enable_mutex); + if (!swap_slot_cache_initialized) { + int ret; + + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "swap_slots_cache", + alloc_swap_slot_cache, free_slot_cache); + if (WARN_ONCE(ret < 0, "Cache allocation failed (%s), operating " + "without swap slots cache.\n", __func__)) + goto out_unlock; + + swap_slot_cache_initialized = true; + } + + __reenable_swap_slots_cache(); +out_unlock: + mutex_unlock(&swap_slots_cache_enable_mutex); +} + +/* called with swap slot cache's alloc lock held */ +static int refill_swap_slots_cache(struct swap_slots_cache *cache) +{ + if (!use_swap_slot_cache || cache->nr) + return 0; + + cache->cur = 0; + if (swap_slot_cache_active) + cache->nr = get_swap_pages(SWAP_SLOTS_CACHE_SIZE, + cache->slots, 1); + + return cache->nr; +} + +int free_swap_slot(swp_entry_t entry) +{ + struct swap_slots_cache *cache; + + cache = raw_cpu_ptr(&swp_slots); + if (likely(use_swap_slot_cache && cache->slots_ret)) { + spin_lock_irq(&cache->free_lock); + /* Swap slots cache may be deactivated before acquiring lock */ + if (!use_swap_slot_cache || !cache->slots_ret) { + spin_unlock_irq(&cache->free_lock); + goto direct_free; + } + if (cache->n_ret >= SWAP_SLOTS_CACHE_SIZE) { + /* + * Return slots to global pool. + * The current swap_map value is SWAP_HAS_CACHE. + * Set it to 0 to indicate it is available for + * allocation in global pool + */ + swapcache_free_entries(cache->slots_ret, cache->n_ret); + cache->n_ret = 0; + } + cache->slots_ret[cache->n_ret++] = entry; + spin_unlock_irq(&cache->free_lock); + } else { +direct_free: + swapcache_free_entries(&entry, 1); + } + + return 0; +} + +swp_entry_t get_swap_page(struct page *page) +{ + swp_entry_t entry; + struct swap_slots_cache *cache; + + entry.val = 0; + + if (PageTransHuge(page)) { + if (IS_ENABLED(CONFIG_THP_SWAP)) + get_swap_pages(1, &entry, HPAGE_PMD_NR); + goto out; + } + + /* + * Preemption is allowed here, because we may sleep + * in refill_swap_slots_cache(). But it is safe, because + * accesses to the per-CPU data structure are protected by the + * mutex cache->alloc_lock. + * + * The alloc path here does not touch cache->slots_ret + * so cache->free_lock is not taken. + */ + cache = raw_cpu_ptr(&swp_slots); + + if (likely(check_cache_active() && cache->slots)) { + mutex_lock(&cache->alloc_lock); + if (cache->slots) { +repeat: + if (cache->nr) { + entry = cache->slots[cache->cur]; + cache->slots[cache->cur++].val = 0; + cache->nr--; + } else if (refill_swap_slots_cache(cache)) { + goto repeat; + } + } + mutex_unlock(&cache->alloc_lock); + if (entry.val) + goto out; + } + + get_swap_pages(1, &entry, 1); +out: + if (mem_cgroup_try_charge_swap(page, entry)) { + put_swap_page(page, entry); + entry.val = 0; + } + return entry; +} diff --git a/mm/swap_state.c b/mm/swap_state.c new file mode 100644 index 000000000..5c5cb2d67 --- /dev/null +++ b/mm/swap_state.c @@ -0,0 +1,953 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/mm/swap_state.c + * + * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds + * Swap reorganised 29.12.95, Stephen Tweedie + * + * Rewritten to use page cache, (C) 1998 Stephen Tweedie + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "internal.h" + +/* + * swapper_space is a fiction, retained to simplify the path through + * vmscan's shrink_page_list. + */ +static const struct address_space_operations swap_aops = { + .writepage = swap_writepage, + .set_page_dirty = swap_set_page_dirty, +#ifdef CONFIG_MIGRATION + .migratepage = migrate_page, +#endif +}; + +struct address_space *swapper_spaces[MAX_SWAPFILES] __read_mostly; +static unsigned int nr_swapper_spaces[MAX_SWAPFILES] __read_mostly; +static bool enable_vma_readahead __read_mostly = true; + +#define SWAP_RA_WIN_SHIFT (PAGE_SHIFT / 2) +#define SWAP_RA_HITS_MASK ((1UL << SWAP_RA_WIN_SHIFT) - 1) +#define SWAP_RA_HITS_MAX SWAP_RA_HITS_MASK +#define SWAP_RA_WIN_MASK (~PAGE_MASK & ~SWAP_RA_HITS_MASK) + +#define SWAP_RA_HITS(v) ((v) & SWAP_RA_HITS_MASK) +#define SWAP_RA_WIN(v) (((v) & SWAP_RA_WIN_MASK) >> SWAP_RA_WIN_SHIFT) +#define SWAP_RA_ADDR(v) ((v) & PAGE_MASK) + +#define SWAP_RA_VAL(addr, win, hits) \ + (((addr) & PAGE_MASK) | \ + (((win) << SWAP_RA_WIN_SHIFT) & SWAP_RA_WIN_MASK) | \ + ((hits) & SWAP_RA_HITS_MASK)) + +/* Initial readahead hits is 4 to start up with a small window */ +#define GET_SWAP_RA_VAL(vma) \ + (atomic_long_read(&(vma)->swap_readahead_info) ? : 4) + +#define INC_CACHE_INFO(x) data_race(swap_cache_info.x++) +#define ADD_CACHE_INFO(x, nr) data_race(swap_cache_info.x += (nr)) + +static struct { + unsigned long add_total; + unsigned long del_total; + unsigned long find_success; + unsigned long find_total; +} swap_cache_info; + +unsigned long total_swapcache_pages(void) +{ + unsigned int i, j, nr; + unsigned long ret = 0; + struct address_space *spaces; + struct swap_info_struct *si; + + for (i = 0; i < MAX_SWAPFILES; i++) { + swp_entry_t entry = swp_entry(i, 1); + + /* Avoid get_swap_device() to warn for bad swap entry */ + if (!swp_swap_info(entry)) + continue; + /* Prevent swapoff to free swapper_spaces */ + si = get_swap_device(entry); + if (!si) + continue; + nr = nr_swapper_spaces[i]; + spaces = swapper_spaces[i]; + for (j = 0; j < nr; j++) + ret += spaces[j].nrpages; + put_swap_device(si); + } + return ret; +} + +static atomic_t swapin_readahead_hits = ATOMIC_INIT(4); + +void show_swap_cache_info(void) +{ + printk("%lu pages in swap cache\n", total_swapcache_pages()); + printk("Swap cache stats: add %lu, delete %lu, find %lu/%lu\n", + swap_cache_info.add_total, swap_cache_info.del_total, + swap_cache_info.find_success, swap_cache_info.find_total); + printk("Free swap = %ldkB\n", + get_nr_swap_pages() << (PAGE_SHIFT - 10)); + printk("Total swap = %lukB\n", total_swap_pages << (PAGE_SHIFT - 10)); +} + +void *get_shadow_from_swap_cache(swp_entry_t entry) +{ + struct address_space *address_space = swap_address_space(entry); + pgoff_t idx = swp_offset(entry); + struct page *page; + + page = find_get_entry(address_space, idx); + if (xa_is_value(page)) + return page; + if (page) + put_page(page); + return NULL; +} + +/* + * add_to_swap_cache resembles add_to_page_cache_locked on swapper_space, + * but sets SwapCache flag and private instead of mapping and index. + */ +int add_to_swap_cache(struct page *page, swp_entry_t entry, + gfp_t gfp, void **shadowp) +{ + struct address_space *address_space = swap_address_space(entry); + pgoff_t idx = swp_offset(entry); + XA_STATE_ORDER(xas, &address_space->i_pages, idx, compound_order(page)); + unsigned long i, nr = thp_nr_pages(page); + void *old; + + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(PageSwapCache(page), page); + VM_BUG_ON_PAGE(!PageSwapBacked(page), page); + + page_ref_add(page, nr); + SetPageSwapCache(page); + + do { + unsigned long nr_shadows = 0; + + xas_lock_irq(&xas); + xas_create_range(&xas); + if (xas_error(&xas)) + goto unlock; + for (i = 0; i < nr; i++) { + VM_BUG_ON_PAGE(xas.xa_index != idx + i, page); + old = xas_load(&xas); + if (xa_is_value(old)) { + nr_shadows++; + if (shadowp) + *shadowp = old; + } + set_page_private(page + i, entry.val + i); + xas_store(&xas, page); + xas_next(&xas); + } + address_space->nrexceptional -= nr_shadows; + address_space->nrpages += nr; + __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, nr); + ADD_CACHE_INFO(add_total, nr); +unlock: + xas_unlock_irq(&xas); + } while (xas_nomem(&xas, gfp)); + + if (!xas_error(&xas)) + return 0; + + ClearPageSwapCache(page); + page_ref_sub(page, nr); + return xas_error(&xas); +} + +/* + * This must be called only on pages that have + * been verified to be in the swap cache. + */ +void __delete_from_swap_cache(struct page *page, + swp_entry_t entry, void *shadow) +{ + struct address_space *address_space = swap_address_space(entry); + int i, nr = thp_nr_pages(page); + pgoff_t idx = swp_offset(entry); + XA_STATE(xas, &address_space->i_pages, idx); + + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(!PageSwapCache(page), page); + VM_BUG_ON_PAGE(PageWriteback(page), page); + + for (i = 0; i < nr; i++) { + void *entry = xas_store(&xas, shadow); + VM_BUG_ON_PAGE(entry != page, entry); + set_page_private(page + i, 0); + xas_next(&xas); + } + ClearPageSwapCache(page); + if (shadow) + address_space->nrexceptional += nr; + address_space->nrpages -= nr; + __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, -nr); + ADD_CACHE_INFO(del_total, nr); +} + +/** + * add_to_swap - allocate swap space for a page + * @page: page we want to move to swap + * + * Allocate swap space for the page and add the page to the + * swap cache. Caller needs to hold the page lock. + */ +int add_to_swap(struct page *page) +{ + swp_entry_t entry; + int err; + + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(!PageUptodate(page), page); + + entry = get_swap_page(page); + if (!entry.val) + return 0; + + /* + * XArray node allocations from PF_MEMALLOC contexts could + * completely exhaust the page allocator. __GFP_NOMEMALLOC + * stops emergency reserves from being allocated. + * + * TODO: this could cause a theoretical memory reclaim + * deadlock in the swap out path. + */ + /* + * Add it to the swap cache. + */ + err = add_to_swap_cache(page, entry, + __GFP_HIGH|__GFP_NOMEMALLOC|__GFP_NOWARN, NULL); + if (err) + /* + * add_to_swap_cache() doesn't return -EEXIST, so we can safely + * clear SWAP_HAS_CACHE flag. + */ + goto fail; + /* + * Normally the page will be dirtied in unmap because its pte should be + * dirty. A special case is MADV_FREE page. The page's pte could have + * dirty bit cleared but the page's SwapBacked bit is still set because + * clearing the dirty bit and SwapBacked bit has no lock protected. For + * such page, unmap will not set dirty bit for it, so page reclaim will + * not write the page out. This can cause data corruption when the page + * is swap in later. Always setting the dirty bit for the page solves + * the problem. + */ + set_page_dirty(page); + + return 1; + +fail: + put_swap_page(page, entry); + return 0; +} + +/* + * This must be called only on pages that have + * been verified to be in the swap cache and locked. + * It will never put the page into the free list, + * the caller has a reference on the page. + */ +void delete_from_swap_cache(struct page *page) +{ + swp_entry_t entry = { .val = page_private(page) }; + struct address_space *address_space = swap_address_space(entry); + + xa_lock_irq(&address_space->i_pages); + __delete_from_swap_cache(page, entry, NULL); + xa_unlock_irq(&address_space->i_pages); + + put_swap_page(page, entry); + page_ref_sub(page, thp_nr_pages(page)); +} + +void clear_shadow_from_swap_cache(int type, unsigned long begin, + unsigned long end) +{ + unsigned long curr = begin; + void *old; + + for (;;) { + unsigned long nr_shadows = 0; + swp_entry_t entry = swp_entry(type, curr); + struct address_space *address_space = swap_address_space(entry); + XA_STATE(xas, &address_space->i_pages, curr); + + xa_lock_irq(&address_space->i_pages); + xas_for_each(&xas, old, end) { + if (!xa_is_value(old)) + continue; + xas_store(&xas, NULL); + nr_shadows++; + } + address_space->nrexceptional -= nr_shadows; + xa_unlock_irq(&address_space->i_pages); + + /* search the next swapcache until we meet end */ + curr >>= SWAP_ADDRESS_SPACE_SHIFT; + curr++; + curr <<= SWAP_ADDRESS_SPACE_SHIFT; + if (curr > end) + break; + } +} + +/* + * If we are the only user, then try to free up the swap cache. + * + * Its ok to check for PageSwapCache without the page lock + * here because we are going to recheck again inside + * try_to_free_swap() _with_ the lock. + * - Marcelo + */ +static inline void free_swap_cache(struct page *page) +{ + if (PageSwapCache(page) && !page_mapped(page) && trylock_page(page)) { + try_to_free_swap(page); + unlock_page(page); + } +} + +/* + * Perform a free_page(), also freeing any swap cache associated with + * this page if it is the last user of the page. + */ +void free_page_and_swap_cache(struct page *page) +{ + free_swap_cache(page); + if (!is_huge_zero_page(page)) + put_page(page); +} + +/* + * Passed an array of pages, drop them all from swapcache and then release + * them. They are removed from the LRU and freed if this is their last use. + */ +void free_pages_and_swap_cache(struct page **pages, int nr) +{ + struct page **pagep = pages; + int i; + + lru_add_drain(); + for (i = 0; i < nr; i++) + free_swap_cache(pagep[i]); + release_pages(pagep, nr); +} + +static inline bool swap_use_vma_readahead(void) +{ + return READ_ONCE(enable_vma_readahead) && !atomic_read(&nr_rotate_swap); +} + +/* + * Lookup a swap entry in the swap cache. A found page will be returned + * unlocked and with its refcount incremented - we rely on the kernel + * lock getting page table operations atomic even if we drop the page + * lock before returning. + */ +struct page *lookup_swap_cache(swp_entry_t entry, struct vm_area_struct *vma, + unsigned long addr) +{ + struct page *page; + struct swap_info_struct *si; + + si = get_swap_device(entry); + if (!si) + return NULL; + page = find_get_page(swap_address_space(entry), swp_offset(entry)); + put_swap_device(si); + + INC_CACHE_INFO(find_total); + if (page) { + bool vma_ra = swap_use_vma_readahead(); + bool readahead; + + INC_CACHE_INFO(find_success); + /* + * At the moment, we don't support PG_readahead for anon THP + * so let's bail out rather than confusing the readahead stat. + */ + if (unlikely(PageTransCompound(page))) + return page; + + readahead = TestClearPageReadahead(page); + if (vma && vma_ra) { + unsigned long ra_val; + int win, hits; + + ra_val = GET_SWAP_RA_VAL(vma); + win = SWAP_RA_WIN(ra_val); + hits = SWAP_RA_HITS(ra_val); + if (readahead) + hits = min_t(int, hits + 1, SWAP_RA_HITS_MAX); + atomic_long_set(&vma->swap_readahead_info, + SWAP_RA_VAL(addr, win, hits)); + } + + if (readahead) { + count_vm_event(SWAP_RA_HIT); + if (!vma || !vma_ra) + atomic_inc(&swapin_readahead_hits); + } + } + + return page; +} + +/** + * find_get_incore_page - Find and get a page from the page or swap caches. + * @mapping: The address_space to search. + * @index: The page cache index. + * + * This differs from find_get_page() in that it will also look for the + * page in the swap cache. + * + * Return: The found page or %NULL. + */ +struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index) +{ + swp_entry_t swp; + struct swap_info_struct *si; + struct page *page = find_get_entry(mapping, index); + + if (!page) + return page; + if (!xa_is_value(page)) + return find_subpage(page, index); + if (!shmem_mapping(mapping)) + return NULL; + + swp = radix_to_swp_entry(page); + /* Prevent swapoff from happening to us */ + si = get_swap_device(swp); + if (!si) + return NULL; + page = find_get_page(swap_address_space(swp), swp_offset(swp)); + put_swap_device(si); + return page; +} + +struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, + struct vm_area_struct *vma, unsigned long addr, + bool *new_page_allocated) +{ + struct swap_info_struct *si; + struct page *page; + void *shadow = NULL; + + *new_page_allocated = false; + + for (;;) { + int err; + /* + * First check the swap cache. Since this is normally + * called after lookup_swap_cache() failed, re-calling + * that would confuse statistics. + */ + si = get_swap_device(entry); + if (!si) + return NULL; + page = find_get_page(swap_address_space(entry), + swp_offset(entry)); + put_swap_device(si); + if (page) + return page; + + /* + * Just skip read ahead for unused swap slot. + * During swap_off when swap_slot_cache is disabled, + * we have to handle the race between putting + * swap entry in swap cache and marking swap slot + * as SWAP_HAS_CACHE. That's done in later part of code or + * else swap_off will be aborted if we return NULL. + */ + if (!__swp_swapcount(entry) && swap_slot_cache_enabled) + return NULL; + + /* + * Get a new page to read into from swap. Allocate it now, + * before marking swap_map SWAP_HAS_CACHE, when -EEXIST will + * cause any racers to loop around until we add it to cache. + */ + page = alloc_page_vma(gfp_mask, vma, addr); + if (!page) + return NULL; + + /* + * Swap entry may have been freed since our caller observed it. + */ + err = swapcache_prepare(entry); + if (!err) + break; + + put_page(page); + if (err != -EEXIST) + return NULL; + + /* + * We might race against __delete_from_swap_cache(), and + * stumble across a swap_map entry whose SWAP_HAS_CACHE + * has not yet been cleared. Or race against another + * __read_swap_cache_async(), which has set SWAP_HAS_CACHE + * in swap_map, but not yet added its page to swap cache. + */ + schedule_timeout_uninterruptible(1); + } + + /* + * The swap entry is ours to swap in. Prepare the new page. + */ + + __SetPageLocked(page); + __SetPageSwapBacked(page); + + /* May fail (-ENOMEM) if XArray node allocation failed. */ + if (add_to_swap_cache(page, entry, gfp_mask & GFP_RECLAIM_MASK, &shadow)) { + put_swap_page(page, entry); + goto fail_unlock; + } + + if (mem_cgroup_charge(page, NULL, gfp_mask)) { + delete_from_swap_cache(page); + goto fail_unlock; + } + + if (shadow) + workingset_refault(page, shadow); + + /* Caller will initiate read into locked page */ + SetPageWorkingset(page); + lru_cache_add(page); + *new_page_allocated = true; + return page; + +fail_unlock: + unlock_page(page); + put_page(page); + return NULL; +} + +/* + * Locate a page of swap in physical memory, reserving swap cache space + * and reading the disk if it is not already cached. + * A failure return means that either the page allocation failed or that + * the swap entry is no longer in use. + */ +struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, + struct vm_area_struct *vma, unsigned long addr, bool do_poll) +{ + bool page_was_allocated; + struct page *retpage = __read_swap_cache_async(entry, gfp_mask, + vma, addr, &page_was_allocated); + + if (page_was_allocated) + swap_readpage(retpage, do_poll); + + return retpage; +} + +static unsigned int __swapin_nr_pages(unsigned long prev_offset, + unsigned long offset, + int hits, + int max_pages, + int prev_win) +{ + unsigned int pages, last_ra; + + /* + * This heuristic has been found to work well on both sequential and + * random loads, swapping to hard disk or to SSD: please don't ask + * what the "+ 2" means, it just happens to work well, that's all. + */ + pages = hits + 2; + if (pages == 2) { + /* + * We can have no readahead hits to judge by: but must not get + * stuck here forever, so check for an adjacent offset instead + * (and don't even bother to check whether swap type is same). + */ + if (offset != prev_offset + 1 && offset != prev_offset - 1) + pages = 1; + } else { + unsigned int roundup = 4; + while (roundup < pages) + roundup <<= 1; + pages = roundup; + } + + if (pages > max_pages) + pages = max_pages; + + /* Don't shrink readahead too fast */ + last_ra = prev_win / 2; + if (pages < last_ra) + pages = last_ra; + + return pages; +} + +static unsigned long swapin_nr_pages(unsigned long offset) +{ + static unsigned long prev_offset; + unsigned int hits, pages, max_pages; + static atomic_t last_readahead_pages; + + max_pages = 1 << READ_ONCE(page_cluster); + if (max_pages <= 1) + return 1; + + hits = atomic_xchg(&swapin_readahead_hits, 0); + pages = __swapin_nr_pages(READ_ONCE(prev_offset), offset, hits, + max_pages, + atomic_read(&last_readahead_pages)); + if (!hits) + WRITE_ONCE(prev_offset, offset); + atomic_set(&last_readahead_pages, pages); + + return pages; +} + +/** + * swap_cluster_readahead - swap in pages in hope we need them soon + * @entry: swap entry of this memory + * @gfp_mask: memory allocation flags + * @vmf: fault information + * + * Returns the struct page for entry and addr, after queueing swapin. + * + * Primitive swap readahead code. We simply read an aligned block of + * (1 << page_cluster) entries in the swap area. This method is chosen + * because it doesn't cost us any seek time. We also make sure to queue + * the 'original' request together with the readahead ones... + * + * This has been extended to use the NUMA policies from the mm triggering + * the readahead. + * + * Caller must hold read mmap_lock if vmf->vma is not NULL. + */ +struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask, + struct vm_fault *vmf) +{ + struct page *page; + unsigned long entry_offset = swp_offset(entry); + unsigned long offset = entry_offset; + unsigned long start_offset, end_offset; + unsigned long mask; + struct swap_info_struct *si = swp_swap_info(entry); + struct blk_plug plug; + bool do_poll = true, page_allocated; + struct vm_area_struct *vma = vmf->vma; + unsigned long addr = vmf->address; + + mask = swapin_nr_pages(offset) - 1; + if (!mask) + goto skip; + + /* Test swap type to make sure the dereference is safe */ + if (likely(si->flags & (SWP_BLKDEV | SWP_FS_OPS))) { + struct inode *inode = si->swap_file->f_mapping->host; + if (inode_read_congested(inode)) + goto skip; + } + + do_poll = false; + /* Read a page_cluster sized and aligned cluster around offset. */ + start_offset = offset & ~mask; + end_offset = offset | mask; + if (!start_offset) /* First page is swap header. */ + start_offset++; + if (end_offset >= si->max) + end_offset = si->max - 1; + + blk_start_plug(&plug); + for (offset = start_offset; offset <= end_offset ; offset++) { + /* Ok, do the async read-ahead now */ + page = __read_swap_cache_async( + swp_entry(swp_type(entry), offset), + gfp_mask, vma, addr, &page_allocated); + if (!page) + continue; + if (page_allocated) { + swap_readpage(page, false); + if (offset != entry_offset) { + SetPageReadahead(page); + count_vm_event(SWAP_RA); + } + } + put_page(page); + } + blk_finish_plug(&plug); + + lru_add_drain(); /* Push any new pages onto the LRU now */ +skip: + return read_swap_cache_async(entry, gfp_mask, vma, addr, do_poll); +} + +int init_swap_address_space(unsigned int type, unsigned long nr_pages) +{ + struct address_space *spaces, *space; + unsigned int i, nr; + + nr = DIV_ROUND_UP(nr_pages, SWAP_ADDRESS_SPACE_PAGES); + spaces = kvcalloc(nr, sizeof(struct address_space), GFP_KERNEL); + if (!spaces) + return -ENOMEM; + for (i = 0; i < nr; i++) { + space = spaces + i; + xa_init_flags(&space->i_pages, XA_FLAGS_LOCK_IRQ); + atomic_set(&space->i_mmap_writable, 0); + space->a_ops = &swap_aops; + /* swap cache doesn't use writeback related tags */ + mapping_set_no_writeback_tags(space); + } + nr_swapper_spaces[type] = nr; + swapper_spaces[type] = spaces; + + return 0; +} + +void exit_swap_address_space(unsigned int type) +{ + kvfree(swapper_spaces[type]); + nr_swapper_spaces[type] = 0; + swapper_spaces[type] = NULL; +} + +static inline void swap_ra_clamp_pfn(struct vm_area_struct *vma, + unsigned long faddr, + unsigned long lpfn, + unsigned long rpfn, + unsigned long *start, + unsigned long *end) +{ + *start = max3(lpfn, PFN_DOWN(vma->vm_start), + PFN_DOWN(faddr & PMD_MASK)); + *end = min3(rpfn, PFN_DOWN(vma->vm_end), + PFN_DOWN((faddr & PMD_MASK) + PMD_SIZE)); +} + +static void swap_ra_info(struct vm_fault *vmf, + struct vma_swap_readahead *ra_info) +{ + struct vm_area_struct *vma = vmf->vma; + unsigned long ra_val; + swp_entry_t entry; + unsigned long faddr, pfn, fpfn; + unsigned long start, end; + pte_t *pte, *orig_pte; + unsigned int max_win, hits, prev_win, win, left; +#ifndef CONFIG_64BIT + pte_t *tpte; +#endif + + max_win = 1 << min_t(unsigned int, READ_ONCE(page_cluster), + SWAP_RA_ORDER_CEILING); + if (max_win == 1) { + ra_info->win = 1; + return; + } + + faddr = vmf->address; + orig_pte = pte = pte_offset_map(vmf->pmd, faddr); + entry = pte_to_swp_entry(*pte); + if ((unlikely(non_swap_entry(entry)))) { + pte_unmap(orig_pte); + return; + } + + fpfn = PFN_DOWN(faddr); + ra_val = GET_SWAP_RA_VAL(vma); + pfn = PFN_DOWN(SWAP_RA_ADDR(ra_val)); + prev_win = SWAP_RA_WIN(ra_val); + hits = SWAP_RA_HITS(ra_val); + ra_info->win = win = __swapin_nr_pages(pfn, fpfn, hits, + max_win, prev_win); + atomic_long_set(&vma->swap_readahead_info, + SWAP_RA_VAL(faddr, win, 0)); + + if (win == 1) { + pte_unmap(orig_pte); + return; + } + + /* Copy the PTEs because the page table may be unmapped */ + if (fpfn == pfn + 1) + swap_ra_clamp_pfn(vma, faddr, fpfn, fpfn + win, &start, &end); + else if (pfn == fpfn + 1) + swap_ra_clamp_pfn(vma, faddr, fpfn - win + 1, fpfn + 1, + &start, &end); + else { + left = (win - 1) / 2; + swap_ra_clamp_pfn(vma, faddr, fpfn - left, fpfn + win - left, + &start, &end); + } + ra_info->nr_pte = end - start; + ra_info->offset = fpfn - start; + pte -= ra_info->offset; +#ifdef CONFIG_64BIT + ra_info->ptes = pte; +#else + tpte = ra_info->ptes; + for (pfn = start; pfn != end; pfn++) + *tpte++ = *pte++; +#endif + pte_unmap(orig_pte); +} + +/** + * swap_vma_readahead - swap in pages in hope we need them soon + * @fentry: swap entry of this memory + * @gfp_mask: memory allocation flags + * @vmf: fault information + * + * Returns the struct page for entry and addr, after queueing swapin. + * + * Primitive swap readahead code. We simply read in a few pages whoes + * virtual addresses are around the fault address in the same vma. + * + * Caller must hold read mmap_lock if vmf->vma is not NULL. + * + */ +static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask, + struct vm_fault *vmf) +{ + struct blk_plug plug; + struct vm_area_struct *vma = vmf->vma; + struct page *page; + pte_t *pte, pentry; + swp_entry_t entry; + unsigned int i; + bool page_allocated; + struct vma_swap_readahead ra_info = {0,}; + + swap_ra_info(vmf, &ra_info); + if (ra_info.win == 1) + goto skip; + + blk_start_plug(&plug); + for (i = 0, pte = ra_info.ptes; i < ra_info.nr_pte; + i++, pte++) { + pentry = *pte; + if (pte_none(pentry)) + continue; + if (pte_present(pentry)) + continue; + entry = pte_to_swp_entry(pentry); + if (unlikely(non_swap_entry(entry))) + continue; + page = __read_swap_cache_async(entry, gfp_mask, vma, + vmf->address, &page_allocated); + if (!page) + continue; + if (page_allocated) { + swap_readpage(page, false); + if (i != ra_info.offset) { + SetPageReadahead(page); + count_vm_event(SWAP_RA); + } + } + put_page(page); + } + blk_finish_plug(&plug); + lru_add_drain(); +skip: + return read_swap_cache_async(fentry, gfp_mask, vma, vmf->address, + ra_info.win == 1); +} + +/** + * swapin_readahead - swap in pages in hope we need them soon + * @entry: swap entry of this memory + * @gfp_mask: memory allocation flags + * @vmf: fault information + * + * Returns the struct page for entry and addr, after queueing swapin. + * + * It's a main entry function for swap readahead. By the configuration, + * it will read ahead blocks by cluster-based(ie, physical disk based) + * or vma-based(ie, virtual address based on faulty address) readahead. + */ +struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, + struct vm_fault *vmf) +{ + return swap_use_vma_readahead() ? + swap_vma_readahead(entry, gfp_mask, vmf) : + swap_cluster_readahead(entry, gfp_mask, vmf); +} + +#ifdef CONFIG_SYSFS +static ssize_t vma_ra_enabled_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%s\n", enable_vma_readahead ? "true" : "false"); +} +static ssize_t vma_ra_enabled_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + if (!strncmp(buf, "true", 4) || !strncmp(buf, "1", 1)) + enable_vma_readahead = true; + else if (!strncmp(buf, "false", 5) || !strncmp(buf, "0", 1)) + enable_vma_readahead = false; + else + return -EINVAL; + + return count; +} +static struct kobj_attribute vma_ra_enabled_attr = + __ATTR(vma_ra_enabled, 0644, vma_ra_enabled_show, + vma_ra_enabled_store); + +static struct attribute *swap_attrs[] = { + &vma_ra_enabled_attr.attr, + NULL, +}; + +static struct attribute_group swap_attr_group = { + .attrs = swap_attrs, +}; + +static int __init swap_init_sysfs(void) +{ + int err; + struct kobject *swap_kobj; + + swap_kobj = kobject_create_and_add("swap", mm_kobj); + if (!swap_kobj) { + pr_err("failed to create swap kobject\n"); + return -ENOMEM; + } + err = sysfs_create_group(swap_kobj, &swap_attr_group); + if (err) { + pr_err("failed to register swap group\n"); + goto delete_obj; + } + return 0; + +delete_obj: + kobject_put(swap_kobj); + return err; +} +subsys_initcall(swap_init_sysfs); +#endif diff --git a/mm/swapfile.c b/mm/swapfile.c new file mode 100644 index 000000000..86ade667a --- /dev/null +++ b/mm/swapfile.c @@ -0,0 +1,3862 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/mm/swapfile.c + * + * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds + * Swap reorganised 29.12.95, Stephen Tweedie + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +static bool swap_count_continued(struct swap_info_struct *, pgoff_t, + unsigned char); +static void free_swap_count_continuations(struct swap_info_struct *); +static sector_t map_swap_entry(swp_entry_t, struct block_device**); + +DEFINE_SPINLOCK(swap_lock); +static unsigned int nr_swapfiles; +atomic_long_t nr_swap_pages; +/* + * Some modules use swappable objects and may try to swap them out under + * memory pressure (via the shrinker). Before doing so, they may wish to + * check to see if any swap space is available. + */ +EXPORT_SYMBOL_GPL(nr_swap_pages); +/* protected with swap_lock. reading in vm_swap_full() doesn't need lock */ +long total_swap_pages; +static int least_priority = -1; + +static const char Bad_file[] = "Bad swap file entry "; +static const char Unused_file[] = "Unused swap file entry "; +static const char Bad_offset[] = "Bad swap offset entry "; +static const char Unused_offset[] = "Unused swap offset entry "; + +/* + * all active swap_info_structs + * protected with swap_lock, and ordered by priority. + */ +PLIST_HEAD(swap_active_head); + +/* + * all available (active, not full) swap_info_structs + * protected with swap_avail_lock, ordered by priority. + * This is used by get_swap_page() instead of swap_active_head + * because swap_active_head includes all swap_info_structs, + * but get_swap_page() doesn't need to look at full ones. + * This uses its own lock instead of swap_lock because when a + * swap_info_struct changes between not-full/full, it needs to + * add/remove itself to/from this list, but the swap_info_struct->lock + * is held and the locking order requires swap_lock to be taken + * before any swap_info_struct->lock. + */ +static struct plist_head *swap_avail_heads; +static DEFINE_SPINLOCK(swap_avail_lock); + +struct swap_info_struct *swap_info[MAX_SWAPFILES]; + +static DEFINE_MUTEX(swapon_mutex); + +static DECLARE_WAIT_QUEUE_HEAD(proc_poll_wait); +/* Activity counter to indicate that a swapon or swapoff has occurred */ +static atomic_t proc_poll_event = ATOMIC_INIT(0); + +atomic_t nr_rotate_swap = ATOMIC_INIT(0); + +static struct swap_info_struct *swap_type_to_swap_info(int type) +{ + if (type >= READ_ONCE(nr_swapfiles)) + return NULL; + + smp_rmb(); /* Pairs with smp_wmb in alloc_swap_info. */ + return READ_ONCE(swap_info[type]); +} + +static inline unsigned char swap_count(unsigned char ent) +{ + return ent & ~SWAP_HAS_CACHE; /* may include COUNT_CONTINUED flag */ +} + +/* Reclaim the swap entry anyway if possible */ +#define TTRS_ANYWAY 0x1 +/* + * Reclaim the swap entry if there are no more mappings of the + * corresponding page + */ +#define TTRS_UNMAPPED 0x2 +/* Reclaim the swap entry if swap is getting full*/ +#define TTRS_FULL 0x4 + +/* returns 1 if swap entry is freed */ +static int __try_to_reclaim_swap(struct swap_info_struct *si, + unsigned long offset, unsigned long flags) +{ + swp_entry_t entry = swp_entry(si->type, offset); + struct page *page; + int ret = 0; + + page = find_get_page(swap_address_space(entry), offset); + if (!page) + return 0; + /* + * When this function is called from scan_swap_map_slots() and it's + * called by vmscan.c at reclaiming pages. So, we hold a lock on a page, + * here. We have to use trylock for avoiding deadlock. This is a special + * case and you should use try_to_free_swap() with explicit lock_page() + * in usual operations. + */ + if (trylock_page(page)) { + if ((flags & TTRS_ANYWAY) || + ((flags & TTRS_UNMAPPED) && !page_mapped(page)) || + ((flags & TTRS_FULL) && mem_cgroup_swap_full(page))) + ret = try_to_free_swap(page); + unlock_page(page); + } + put_page(page); + return ret; +} + +static inline struct swap_extent *first_se(struct swap_info_struct *sis) +{ + struct rb_node *rb = rb_first(&sis->swap_extent_root); + return rb_entry(rb, struct swap_extent, rb_node); +} + +static inline struct swap_extent *next_se(struct swap_extent *se) +{ + struct rb_node *rb = rb_next(&se->rb_node); + return rb ? rb_entry(rb, struct swap_extent, rb_node) : NULL; +} + +/* + * swapon tell device that all the old swap contents can be discarded, + * to allow the swap device to optimize its wear-levelling. + */ +static int discard_swap(struct swap_info_struct *si) +{ + struct swap_extent *se; + sector_t start_block; + sector_t nr_blocks; + int err = 0; + + /* Do not discard the swap header page! */ + se = first_se(si); + start_block = (se->start_block + 1) << (PAGE_SHIFT - 9); + nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9); + if (nr_blocks) { + err = blkdev_issue_discard(si->bdev, start_block, + nr_blocks, GFP_KERNEL, 0); + if (err) + return err; + cond_resched(); + } + + for (se = next_se(se); se; se = next_se(se)) { + start_block = se->start_block << (PAGE_SHIFT - 9); + nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9); + + err = blkdev_issue_discard(si->bdev, start_block, + nr_blocks, GFP_KERNEL, 0); + if (err) + break; + + cond_resched(); + } + return err; /* That will often be -EOPNOTSUPP */ +} + +static struct swap_extent * +offset_to_swap_extent(struct swap_info_struct *sis, unsigned long offset) +{ + struct swap_extent *se; + struct rb_node *rb; + + rb = sis->swap_extent_root.rb_node; + while (rb) { + se = rb_entry(rb, struct swap_extent, rb_node); + if (offset < se->start_page) + rb = rb->rb_left; + else if (offset >= se->start_page + se->nr_pages) + rb = rb->rb_right; + else + return se; + } + /* It *must* be present */ + BUG(); +} + +sector_t swap_page_sector(struct page *page) +{ + struct swap_info_struct *sis = page_swap_info(page); + struct swap_extent *se; + sector_t sector; + pgoff_t offset; + + offset = __page_file_index(page); + se = offset_to_swap_extent(sis, offset); + sector = se->start_block + (offset - se->start_page); + return sector << (PAGE_SHIFT - 9); +} + +/* + * swap allocation tell device that a cluster of swap can now be discarded, + * to allow the swap device to optimize its wear-levelling. + */ +static void discard_swap_cluster(struct swap_info_struct *si, + pgoff_t start_page, pgoff_t nr_pages) +{ + struct swap_extent *se = offset_to_swap_extent(si, start_page); + + while (nr_pages) { + pgoff_t offset = start_page - se->start_page; + sector_t start_block = se->start_block + offset; + sector_t nr_blocks = se->nr_pages - offset; + + if (nr_blocks > nr_pages) + nr_blocks = nr_pages; + start_page += nr_blocks; + nr_pages -= nr_blocks; + + start_block <<= PAGE_SHIFT - 9; + nr_blocks <<= PAGE_SHIFT - 9; + if (blkdev_issue_discard(si->bdev, start_block, + nr_blocks, GFP_NOIO, 0)) + break; + + se = next_se(se); + } +} + +#ifdef CONFIG_THP_SWAP +#define SWAPFILE_CLUSTER HPAGE_PMD_NR + +#define swap_entry_size(size) (size) +#else +#define SWAPFILE_CLUSTER 256 + +/* + * Define swap_entry_size() as constant to let compiler to optimize + * out some code if !CONFIG_THP_SWAP + */ +#define swap_entry_size(size) 1 +#endif +#define LATENCY_LIMIT 256 + +static inline void cluster_set_flag(struct swap_cluster_info *info, + unsigned int flag) +{ + info->flags = flag; +} + +static inline unsigned int cluster_count(struct swap_cluster_info *info) +{ + return info->data; +} + +static inline void cluster_set_count(struct swap_cluster_info *info, + unsigned int c) +{ + info->data = c; +} + +static inline void cluster_set_count_flag(struct swap_cluster_info *info, + unsigned int c, unsigned int f) +{ + info->flags = f; + info->data = c; +} + +static inline unsigned int cluster_next(struct swap_cluster_info *info) +{ + return info->data; +} + +static inline void cluster_set_next(struct swap_cluster_info *info, + unsigned int n) +{ + info->data = n; +} + +static inline void cluster_set_next_flag(struct swap_cluster_info *info, + unsigned int n, unsigned int f) +{ + info->flags = f; + info->data = n; +} + +static inline bool cluster_is_free(struct swap_cluster_info *info) +{ + return info->flags & CLUSTER_FLAG_FREE; +} + +static inline bool cluster_is_null(struct swap_cluster_info *info) +{ + return info->flags & CLUSTER_FLAG_NEXT_NULL; +} + +static inline void cluster_set_null(struct swap_cluster_info *info) +{ + info->flags = CLUSTER_FLAG_NEXT_NULL; + info->data = 0; +} + +static inline bool cluster_is_huge(struct swap_cluster_info *info) +{ + if (IS_ENABLED(CONFIG_THP_SWAP)) + return info->flags & CLUSTER_FLAG_HUGE; + return false; +} + +static inline void cluster_clear_huge(struct swap_cluster_info *info) +{ + info->flags &= ~CLUSTER_FLAG_HUGE; +} + +static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si, + unsigned long offset) +{ + struct swap_cluster_info *ci; + + ci = si->cluster_info; + if (ci) { + ci += offset / SWAPFILE_CLUSTER; + spin_lock(&ci->lock); + } + return ci; +} + +static inline void unlock_cluster(struct swap_cluster_info *ci) +{ + if (ci) + spin_unlock(&ci->lock); +} + +/* + * Determine the locking method in use for this device. Return + * swap_cluster_info if SSD-style cluster-based locking is in place. + */ +static inline struct swap_cluster_info *lock_cluster_or_swap_info( + struct swap_info_struct *si, unsigned long offset) +{ + struct swap_cluster_info *ci; + + /* Try to use fine-grained SSD-style locking if available: */ + ci = lock_cluster(si, offset); + /* Otherwise, fall back to traditional, coarse locking: */ + if (!ci) + spin_lock(&si->lock); + + return ci; +} + +static inline void unlock_cluster_or_swap_info(struct swap_info_struct *si, + struct swap_cluster_info *ci) +{ + if (ci) + unlock_cluster(ci); + else + spin_unlock(&si->lock); +} + +static inline bool cluster_list_empty(struct swap_cluster_list *list) +{ + return cluster_is_null(&list->head); +} + +static inline unsigned int cluster_list_first(struct swap_cluster_list *list) +{ + return cluster_next(&list->head); +} + +static void cluster_list_init(struct swap_cluster_list *list) +{ + cluster_set_null(&list->head); + cluster_set_null(&list->tail); +} + +static void cluster_list_add_tail(struct swap_cluster_list *list, + struct swap_cluster_info *ci, + unsigned int idx) +{ + if (cluster_list_empty(list)) { + cluster_set_next_flag(&list->head, idx, 0); + cluster_set_next_flag(&list->tail, idx, 0); + } else { + struct swap_cluster_info *ci_tail; + unsigned int tail = cluster_next(&list->tail); + + /* + * Nested cluster lock, but both cluster locks are + * only acquired when we held swap_info_struct->lock + */ + ci_tail = ci + tail; + spin_lock_nested(&ci_tail->lock, SINGLE_DEPTH_NESTING); + cluster_set_next(ci_tail, idx); + spin_unlock(&ci_tail->lock); + cluster_set_next_flag(&list->tail, idx, 0); + } +} + +static unsigned int cluster_list_del_first(struct swap_cluster_list *list, + struct swap_cluster_info *ci) +{ + unsigned int idx; + + idx = cluster_next(&list->head); + if (cluster_next(&list->tail) == idx) { + cluster_set_null(&list->head); + cluster_set_null(&list->tail); + } else + cluster_set_next_flag(&list->head, + cluster_next(&ci[idx]), 0); + + return idx; +} + +/* Add a cluster to discard list and schedule it to do discard */ +static void swap_cluster_schedule_discard(struct swap_info_struct *si, + unsigned int idx) +{ + /* + * If scan_swap_map() can't find a free cluster, it will check + * si->swap_map directly. To make sure the discarding cluster isn't + * taken by scan_swap_map(), mark the swap entries bad (occupied). It + * will be cleared after discard + */ + memset(si->swap_map + idx * SWAPFILE_CLUSTER, + SWAP_MAP_BAD, SWAPFILE_CLUSTER); + + cluster_list_add_tail(&si->discard_clusters, si->cluster_info, idx); + + schedule_work(&si->discard_work); +} + +static void __free_cluster(struct swap_info_struct *si, unsigned long idx) +{ + struct swap_cluster_info *ci = si->cluster_info; + + cluster_set_flag(ci + idx, CLUSTER_FLAG_FREE); + cluster_list_add_tail(&si->free_clusters, ci, idx); +} + +/* + * Doing discard actually. After a cluster discard is finished, the cluster + * will be added to free cluster list. caller should hold si->lock. +*/ +static void swap_do_scheduled_discard(struct swap_info_struct *si) +{ + struct swap_cluster_info *info, *ci; + unsigned int idx; + + info = si->cluster_info; + + while (!cluster_list_empty(&si->discard_clusters)) { + idx = cluster_list_del_first(&si->discard_clusters, info); + spin_unlock(&si->lock); + + discard_swap_cluster(si, idx * SWAPFILE_CLUSTER, + SWAPFILE_CLUSTER); + + spin_lock(&si->lock); + ci = lock_cluster(si, idx * SWAPFILE_CLUSTER); + __free_cluster(si, idx); + memset(si->swap_map + idx * SWAPFILE_CLUSTER, + 0, SWAPFILE_CLUSTER); + unlock_cluster(ci); + } +} + +static void swap_discard_work(struct work_struct *work) +{ + struct swap_info_struct *si; + + si = container_of(work, struct swap_info_struct, discard_work); + + spin_lock(&si->lock); + swap_do_scheduled_discard(si); + spin_unlock(&si->lock); +} + +static void alloc_cluster(struct swap_info_struct *si, unsigned long idx) +{ + struct swap_cluster_info *ci = si->cluster_info; + + VM_BUG_ON(cluster_list_first(&si->free_clusters) != idx); + cluster_list_del_first(&si->free_clusters, ci); + cluster_set_count_flag(ci + idx, 0, 0); +} + +static void free_cluster(struct swap_info_struct *si, unsigned long idx) +{ + struct swap_cluster_info *ci = si->cluster_info + idx; + + VM_BUG_ON(cluster_count(ci) != 0); + /* + * If the swap is discardable, prepare discard the cluster + * instead of free it immediately. The cluster will be freed + * after discard. + */ + if ((si->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) == + (SWP_WRITEOK | SWP_PAGE_DISCARD)) { + swap_cluster_schedule_discard(si, idx); + return; + } + + __free_cluster(si, idx); +} + +/* + * The cluster corresponding to page_nr will be used. The cluster will be + * removed from free cluster list and its usage counter will be increased. + */ +static void inc_cluster_info_page(struct swap_info_struct *p, + struct swap_cluster_info *cluster_info, unsigned long page_nr) +{ + unsigned long idx = page_nr / SWAPFILE_CLUSTER; + + if (!cluster_info) + return; + if (cluster_is_free(&cluster_info[idx])) + alloc_cluster(p, idx); + + VM_BUG_ON(cluster_count(&cluster_info[idx]) >= SWAPFILE_CLUSTER); + cluster_set_count(&cluster_info[idx], + cluster_count(&cluster_info[idx]) + 1); +} + +/* + * The cluster corresponding to page_nr decreases one usage. If the usage + * counter becomes 0, which means no page in the cluster is in using, we can + * optionally discard the cluster and add it to free cluster list. + */ +static void dec_cluster_info_page(struct swap_info_struct *p, + struct swap_cluster_info *cluster_info, unsigned long page_nr) +{ + unsigned long idx = page_nr / SWAPFILE_CLUSTER; + + if (!cluster_info) + return; + + VM_BUG_ON(cluster_count(&cluster_info[idx]) == 0); + cluster_set_count(&cluster_info[idx], + cluster_count(&cluster_info[idx]) - 1); + + if (cluster_count(&cluster_info[idx]) == 0) + free_cluster(p, idx); +} + +/* + * It's possible scan_swap_map() uses a free cluster in the middle of free + * cluster list. Avoiding such abuse to avoid list corruption. + */ +static bool +scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si, + unsigned long offset) +{ + struct percpu_cluster *percpu_cluster; + bool conflict; + + offset /= SWAPFILE_CLUSTER; + conflict = !cluster_list_empty(&si->free_clusters) && + offset != cluster_list_first(&si->free_clusters) && + cluster_is_free(&si->cluster_info[offset]); + + if (!conflict) + return false; + + percpu_cluster = this_cpu_ptr(si->percpu_cluster); + cluster_set_null(&percpu_cluster->index); + return true; +} + +/* + * Try to get a swap entry from current cpu's swap entry pool (a cluster). This + * might involve allocating a new cluster for current CPU too. + */ +static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si, + unsigned long *offset, unsigned long *scan_base) +{ + struct percpu_cluster *cluster; + struct swap_cluster_info *ci; + unsigned long tmp, max; + +new_cluster: + cluster = this_cpu_ptr(si->percpu_cluster); + if (cluster_is_null(&cluster->index)) { + if (!cluster_list_empty(&si->free_clusters)) { + cluster->index = si->free_clusters.head; + cluster->next = cluster_next(&cluster->index) * + SWAPFILE_CLUSTER; + } else if (!cluster_list_empty(&si->discard_clusters)) { + /* + * we don't have free cluster but have some clusters in + * discarding, do discard now and reclaim them, then + * reread cluster_next_cpu since we dropped si->lock + */ + swap_do_scheduled_discard(si); + *scan_base = this_cpu_read(*si->cluster_next_cpu); + *offset = *scan_base; + goto new_cluster; + } else + return false; + } + + /* + * Other CPUs can use our cluster if they can't find a free cluster, + * check if there is still free entry in the cluster + */ + tmp = cluster->next; + max = min_t(unsigned long, si->max, + (cluster_next(&cluster->index) + 1) * SWAPFILE_CLUSTER); + if (tmp < max) { + ci = lock_cluster(si, tmp); + while (tmp < max) { + if (!si->swap_map[tmp]) + break; + tmp++; + } + unlock_cluster(ci); + } + if (tmp >= max) { + cluster_set_null(&cluster->index); + goto new_cluster; + } + cluster->next = tmp + 1; + *offset = tmp; + *scan_base = tmp; + return true; +} + +static void __del_from_avail_list(struct swap_info_struct *p) +{ + int nid; + + assert_spin_locked(&p->lock); + for_each_node(nid) + plist_del(&p->avail_lists[nid], &swap_avail_heads[nid]); +} + +static void del_from_avail_list(struct swap_info_struct *p) +{ + spin_lock(&swap_avail_lock); + __del_from_avail_list(p); + spin_unlock(&swap_avail_lock); +} + +static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset, + unsigned int nr_entries) +{ + unsigned int end = offset + nr_entries - 1; + + if (offset == si->lowest_bit) + si->lowest_bit += nr_entries; + if (end == si->highest_bit) + WRITE_ONCE(si->highest_bit, si->highest_bit - nr_entries); + si->inuse_pages += nr_entries; + if (si->inuse_pages == si->pages) { + si->lowest_bit = si->max; + si->highest_bit = 0; + del_from_avail_list(si); + } +} + +static void add_to_avail_list(struct swap_info_struct *p) +{ + int nid; + + spin_lock(&swap_avail_lock); + for_each_node(nid) { + WARN_ON(!plist_node_empty(&p->avail_lists[nid])); + plist_add(&p->avail_lists[nid], &swap_avail_heads[nid]); + } + spin_unlock(&swap_avail_lock); +} + +static void swap_range_free(struct swap_info_struct *si, unsigned long offset, + unsigned int nr_entries) +{ + unsigned long begin = offset; + unsigned long end = offset + nr_entries - 1; + void (*swap_slot_free_notify)(struct block_device *, unsigned long); + + if (offset < si->lowest_bit) + si->lowest_bit = offset; + if (end > si->highest_bit) { + bool was_full = !si->highest_bit; + + WRITE_ONCE(si->highest_bit, end); + if (was_full && (si->flags & SWP_WRITEOK)) + add_to_avail_list(si); + } + atomic_long_add(nr_entries, &nr_swap_pages); + si->inuse_pages -= nr_entries; + if (si->flags & SWP_BLKDEV) + swap_slot_free_notify = + si->bdev->bd_disk->fops->swap_slot_free_notify; + else + swap_slot_free_notify = NULL; + while (offset <= end) { + arch_swap_invalidate_page(si->type, offset); + frontswap_invalidate_page(si->type, offset); + if (swap_slot_free_notify) + swap_slot_free_notify(si->bdev, offset); + offset++; + } + clear_shadow_from_swap_cache(si->type, begin, end); +} + +static void set_cluster_next(struct swap_info_struct *si, unsigned long next) +{ + unsigned long prev; + + if (!(si->flags & SWP_SOLIDSTATE)) { + si->cluster_next = next; + return; + } + + prev = this_cpu_read(*si->cluster_next_cpu); + /* + * Cross the swap address space size aligned trunk, choose + * another trunk randomly to avoid lock contention on swap + * address space if possible. + */ + if ((prev >> SWAP_ADDRESS_SPACE_SHIFT) != + (next >> SWAP_ADDRESS_SPACE_SHIFT)) { + /* No free swap slots available */ + if (si->highest_bit <= si->lowest_bit) + return; + next = si->lowest_bit + + prandom_u32_max(si->highest_bit - si->lowest_bit + 1); + next = ALIGN_DOWN(next, SWAP_ADDRESS_SPACE_PAGES); + next = max_t(unsigned int, next, si->lowest_bit); + } + this_cpu_write(*si->cluster_next_cpu, next); +} + +static int scan_swap_map_slots(struct swap_info_struct *si, + unsigned char usage, int nr, + swp_entry_t slots[]) +{ + struct swap_cluster_info *ci; + unsigned long offset; + unsigned long scan_base; + unsigned long last_in_cluster = 0; + int latency_ration = LATENCY_LIMIT; + int n_ret = 0; + bool scanned_many = false; + + /* + * We try to cluster swap pages by allocating them sequentially + * in swap. Once we've allocated SWAPFILE_CLUSTER pages this + * way, however, we resort to first-free allocation, starting + * a new cluster. This prevents us from scattering swap pages + * all over the entire swap partition, so that we reduce + * overall disk seek times between swap pages. -- sct + * But we do now try to find an empty cluster. -Andrea + * And we let swap pages go all over an SSD partition. Hugh + */ + + si->flags += SWP_SCANNING; + /* + * Use percpu scan base for SSD to reduce lock contention on + * cluster and swap cache. For HDD, sequential access is more + * important. + */ + if (si->flags & SWP_SOLIDSTATE) + scan_base = this_cpu_read(*si->cluster_next_cpu); + else + scan_base = si->cluster_next; + offset = scan_base; + + /* SSD algorithm */ + if (si->cluster_info) { + if (!scan_swap_map_try_ssd_cluster(si, &offset, &scan_base)) + goto scan; + } else if (unlikely(!si->cluster_nr--)) { + if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) { + si->cluster_nr = SWAPFILE_CLUSTER - 1; + goto checks; + } + + spin_unlock(&si->lock); + + /* + * If seek is expensive, start searching for new cluster from + * start of partition, to minimize the span of allocated swap. + * If seek is cheap, that is the SWP_SOLIDSTATE si->cluster_info + * case, just handled by scan_swap_map_try_ssd_cluster() above. + */ + scan_base = offset = si->lowest_bit; + last_in_cluster = offset + SWAPFILE_CLUSTER - 1; + + /* Locate the first empty (unaligned) cluster */ + for (; last_in_cluster <= si->highest_bit; offset++) { + if (si->swap_map[offset]) + last_in_cluster = offset + SWAPFILE_CLUSTER; + else if (offset == last_in_cluster) { + spin_lock(&si->lock); + offset -= SWAPFILE_CLUSTER - 1; + si->cluster_next = offset; + si->cluster_nr = SWAPFILE_CLUSTER - 1; + goto checks; + } + if (unlikely(--latency_ration < 0)) { + cond_resched(); + latency_ration = LATENCY_LIMIT; + } + } + + offset = scan_base; + spin_lock(&si->lock); + si->cluster_nr = SWAPFILE_CLUSTER - 1; + } + +checks: + if (si->cluster_info) { + while (scan_swap_map_ssd_cluster_conflict(si, offset)) { + /* take a break if we already got some slots */ + if (n_ret) + goto done; + if (!scan_swap_map_try_ssd_cluster(si, &offset, + &scan_base)) + goto scan; + } + } + if (!(si->flags & SWP_WRITEOK)) + goto no_page; + if (!si->highest_bit) + goto no_page; + if (offset > si->highest_bit) + scan_base = offset = si->lowest_bit; + + ci = lock_cluster(si, offset); + /* reuse swap entry of cache-only swap if not busy. */ + if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { + int swap_was_freed; + unlock_cluster(ci); + spin_unlock(&si->lock); + swap_was_freed = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY); + spin_lock(&si->lock); + /* entry was freed successfully, try to use this again */ + if (swap_was_freed) + goto checks; + goto scan; /* check next one */ + } + + if (si->swap_map[offset]) { + unlock_cluster(ci); + if (!n_ret) + goto scan; + else + goto done; + } + WRITE_ONCE(si->swap_map[offset], usage); + inc_cluster_info_page(si, si->cluster_info, offset); + unlock_cluster(ci); + + swap_range_alloc(si, offset, 1); + slots[n_ret++] = swp_entry(si->type, offset); + + /* got enough slots or reach max slots? */ + if ((n_ret == nr) || (offset >= si->highest_bit)) + goto done; + + /* search for next available slot */ + + /* time to take a break? */ + if (unlikely(--latency_ration < 0)) { + if (n_ret) + goto done; + spin_unlock(&si->lock); + cond_resched(); + spin_lock(&si->lock); + latency_ration = LATENCY_LIMIT; + } + + /* try to get more slots in cluster */ + if (si->cluster_info) { + if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base)) + goto checks; + } else if (si->cluster_nr && !si->swap_map[++offset]) { + /* non-ssd case, still more slots in cluster? */ + --si->cluster_nr; + goto checks; + } + + /* + * Even if there's no free clusters available (fragmented), + * try to scan a little more quickly with lock held unless we + * have scanned too many slots already. + */ + if (!scanned_many) { + unsigned long scan_limit; + + if (offset < scan_base) + scan_limit = scan_base; + else + scan_limit = si->highest_bit; + for (; offset <= scan_limit && --latency_ration > 0; + offset++) { + if (!si->swap_map[offset]) + goto checks; + } + } + +done: + set_cluster_next(si, offset + 1); + si->flags -= SWP_SCANNING; + return n_ret; + +scan: + spin_unlock(&si->lock); + while (++offset <= READ_ONCE(si->highest_bit)) { + if (data_race(!si->swap_map[offset])) { + spin_lock(&si->lock); + goto checks; + } + if (vm_swap_full() && + READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { + spin_lock(&si->lock); + goto checks; + } + if (unlikely(--latency_ration < 0)) { + cond_resched(); + latency_ration = LATENCY_LIMIT; + scanned_many = true; + } + } + offset = si->lowest_bit; + while (offset < scan_base) { + if (data_race(!si->swap_map[offset])) { + spin_lock(&si->lock); + goto checks; + } + if (vm_swap_full() && + READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { + spin_lock(&si->lock); + goto checks; + } + if (unlikely(--latency_ration < 0)) { + cond_resched(); + latency_ration = LATENCY_LIMIT; + scanned_many = true; + } + offset++; + } + spin_lock(&si->lock); + +no_page: + si->flags -= SWP_SCANNING; + return n_ret; +} + +static int swap_alloc_cluster(struct swap_info_struct *si, swp_entry_t *slot) +{ + unsigned long idx; + struct swap_cluster_info *ci; + unsigned long offset, i; + unsigned char *map; + + /* + * Should not even be attempting cluster allocations when huge + * page swap is disabled. Warn and fail the allocation. + */ + if (!IS_ENABLED(CONFIG_THP_SWAP)) { + VM_WARN_ON_ONCE(1); + return 0; + } + + if (cluster_list_empty(&si->free_clusters)) + return 0; + + idx = cluster_list_first(&si->free_clusters); + offset = idx * SWAPFILE_CLUSTER; + ci = lock_cluster(si, offset); + alloc_cluster(si, idx); + cluster_set_count_flag(ci, SWAPFILE_CLUSTER, CLUSTER_FLAG_HUGE); + + map = si->swap_map + offset; + for (i = 0; i < SWAPFILE_CLUSTER; i++) + map[i] = SWAP_HAS_CACHE; + unlock_cluster(ci); + swap_range_alloc(si, offset, SWAPFILE_CLUSTER); + *slot = swp_entry(si->type, offset); + + return 1; +} + +static void swap_free_cluster(struct swap_info_struct *si, unsigned long idx) +{ + unsigned long offset = idx * SWAPFILE_CLUSTER; + struct swap_cluster_info *ci; + + ci = lock_cluster(si, offset); + memset(si->swap_map + offset, 0, SWAPFILE_CLUSTER); + cluster_set_count_flag(ci, 0, 0); + free_cluster(si, idx); + unlock_cluster(ci); + swap_range_free(si, offset, SWAPFILE_CLUSTER); +} + +static unsigned long scan_swap_map(struct swap_info_struct *si, + unsigned char usage) +{ + swp_entry_t entry; + int n_ret; + + n_ret = scan_swap_map_slots(si, usage, 1, &entry); + + if (n_ret) + return swp_offset(entry); + else + return 0; + +} + +int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size) +{ + unsigned long size = swap_entry_size(entry_size); + struct swap_info_struct *si, *next; + long avail_pgs; + int n_ret = 0; + int node; + + /* Only single cluster request supported */ + WARN_ON_ONCE(n_goal > 1 && size == SWAPFILE_CLUSTER); + + spin_lock(&swap_avail_lock); + + avail_pgs = atomic_long_read(&nr_swap_pages) / size; + if (avail_pgs <= 0) { + spin_unlock(&swap_avail_lock); + goto noswap; + } + + n_goal = min3((long)n_goal, (long)SWAP_BATCH, avail_pgs); + + atomic_long_sub(n_goal * size, &nr_swap_pages); + +start_over: + node = numa_node_id(); + plist_for_each_entry_safe(si, next, &swap_avail_heads[node], avail_lists[node]) { + /* requeue si to after same-priority siblings */ + plist_requeue(&si->avail_lists[node], &swap_avail_heads[node]); + spin_unlock(&swap_avail_lock); + spin_lock(&si->lock); + if (!si->highest_bit || !(si->flags & SWP_WRITEOK)) { + spin_lock(&swap_avail_lock); + if (plist_node_empty(&si->avail_lists[node])) { + spin_unlock(&si->lock); + goto nextsi; + } + WARN(!si->highest_bit, + "swap_info %d in list but !highest_bit\n", + si->type); + WARN(!(si->flags & SWP_WRITEOK), + "swap_info %d in list but !SWP_WRITEOK\n", + si->type); + __del_from_avail_list(si); + spin_unlock(&si->lock); + goto nextsi; + } + if (size == SWAPFILE_CLUSTER) { + if (si->flags & SWP_BLKDEV) + n_ret = swap_alloc_cluster(si, swp_entries); + } else + n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE, + n_goal, swp_entries); + spin_unlock(&si->lock); + if (n_ret || size == SWAPFILE_CLUSTER) + goto check_out; + pr_debug("scan_swap_map of si %d failed to find offset\n", + si->type); + cond_resched(); + + spin_lock(&swap_avail_lock); +nextsi: + /* + * if we got here, it's likely that si was almost full before, + * and since scan_swap_map() can drop the si->lock, multiple + * callers probably all tried to get a page from the same si + * and it filled up before we could get one; or, the si filled + * up between us dropping swap_avail_lock and taking si->lock. + * Since we dropped the swap_avail_lock, the swap_avail_head + * list may have been modified; so if next is still in the + * swap_avail_head list then try it, otherwise start over + * if we have not gotten any slots. + */ + if (plist_node_empty(&next->avail_lists[node])) + goto start_over; + } + + spin_unlock(&swap_avail_lock); + +check_out: + if (n_ret < n_goal) + atomic_long_add((long)(n_goal - n_ret) * size, + &nr_swap_pages); +noswap: + return n_ret; +} + +/* The only caller of this function is now suspend routine */ +swp_entry_t get_swap_page_of_type(int type) +{ + struct swap_info_struct *si = swap_type_to_swap_info(type); + pgoff_t offset; + + if (!si) + goto fail; + + spin_lock(&si->lock); + if (si->flags & SWP_WRITEOK) { + /* This is called for allocating swap entry, not cache */ + offset = scan_swap_map(si, 1); + if (offset) { + atomic_long_dec(&nr_swap_pages); + spin_unlock(&si->lock); + return swp_entry(type, offset); + } + } + spin_unlock(&si->lock); +fail: + return (swp_entry_t) {0}; +} + +static struct swap_info_struct *__swap_info_get(swp_entry_t entry) +{ + struct swap_info_struct *p; + unsigned long offset; + + if (!entry.val) + goto out; + p = swp_swap_info(entry); + if (!p) + goto bad_nofile; + if (data_race(!(p->flags & SWP_USED))) + goto bad_device; + offset = swp_offset(entry); + if (offset >= p->max) + goto bad_offset; + return p; + +bad_offset: + pr_err("swap_info_get: %s%08lx\n", Bad_offset, entry.val); + goto out; +bad_device: + pr_err("swap_info_get: %s%08lx\n", Unused_file, entry.val); + goto out; +bad_nofile: + pr_err("swap_info_get: %s%08lx\n", Bad_file, entry.val); +out: + return NULL; +} + +static struct swap_info_struct *_swap_info_get(swp_entry_t entry) +{ + struct swap_info_struct *p; + + p = __swap_info_get(entry); + if (!p) + goto out; + if (data_race(!p->swap_map[swp_offset(entry)])) + goto bad_free; + return p; + +bad_free: + pr_err("swap_info_get: %s%08lx\n", Unused_offset, entry.val); +out: + return NULL; +} + +static struct swap_info_struct *swap_info_get(swp_entry_t entry) +{ + struct swap_info_struct *p; + + p = _swap_info_get(entry); + if (p) + spin_lock(&p->lock); + return p; +} + +static struct swap_info_struct *swap_info_get_cont(swp_entry_t entry, + struct swap_info_struct *q) +{ + struct swap_info_struct *p; + + p = _swap_info_get(entry); + + if (p != q) { + if (q != NULL) + spin_unlock(&q->lock); + if (p != NULL) + spin_lock(&p->lock); + } + return p; +} + +static unsigned char __swap_entry_free_locked(struct swap_info_struct *p, + unsigned long offset, + unsigned char usage) +{ + unsigned char count; + unsigned char has_cache; + + count = p->swap_map[offset]; + + has_cache = count & SWAP_HAS_CACHE; + count &= ~SWAP_HAS_CACHE; + + if (usage == SWAP_HAS_CACHE) { + VM_BUG_ON(!has_cache); + has_cache = 0; + } else if (count == SWAP_MAP_SHMEM) { + /* + * Or we could insist on shmem.c using a special + * swap_shmem_free() and free_shmem_swap_and_cache()... + */ + count = 0; + } else if ((count & ~COUNT_CONTINUED) <= SWAP_MAP_MAX) { + if (count == COUNT_CONTINUED) { + if (swap_count_continued(p, offset, count)) + count = SWAP_MAP_MAX | COUNT_CONTINUED; + else + count = SWAP_MAP_MAX; + } else + count--; + } + + usage = count | has_cache; + if (usage) + WRITE_ONCE(p->swap_map[offset], usage); + else + WRITE_ONCE(p->swap_map[offset], SWAP_HAS_CACHE); + + return usage; +} + +/* + * Check whether swap entry is valid in the swap device. If so, + * return pointer to swap_info_struct, and keep the swap entry valid + * via preventing the swap device from being swapoff, until + * put_swap_device() is called. Otherwise return NULL. + * + * The entirety of the RCU read critical section must come before the + * return from or after the call to synchronize_rcu() in + * enable_swap_info() or swapoff(). So if "si->flags & SWP_VALID" is + * true, the si->map, si->cluster_info, etc. must be valid in the + * critical section. + * + * Notice that swapoff or swapoff+swapon can still happen before the + * rcu_read_lock() in get_swap_device() or after the rcu_read_unlock() + * in put_swap_device() if there isn't any other way to prevent + * swapoff, such as page lock, page table lock, etc. The caller must + * be prepared for that. For example, the following situation is + * possible. + * + * CPU1 CPU2 + * do_swap_page() + * ... swapoff+swapon + * __read_swap_cache_async() + * swapcache_prepare() + * __swap_duplicate() + * // check swap_map + * // verify PTE not changed + * + * In __swap_duplicate(), the swap_map need to be checked before + * changing partly because the specified swap entry may be for another + * swap device which has been swapoff. And in do_swap_page(), after + * the page is read from the swap device, the PTE is verified not + * changed with the page table locked to check whether the swap device + * has been swapoff or swapoff+swapon. + */ +struct swap_info_struct *get_swap_device(swp_entry_t entry) +{ + struct swap_info_struct *si; + unsigned long offset; + + if (!entry.val) + goto out; + si = swp_swap_info(entry); + if (!si) + goto bad_nofile; + + rcu_read_lock(); + if (data_race(!(si->flags & SWP_VALID))) + goto unlock_out; + offset = swp_offset(entry); + if (offset >= si->max) + goto unlock_out; + + return si; +bad_nofile: + pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); +out: + return NULL; +unlock_out: + rcu_read_unlock(); + return NULL; +} + +static unsigned char __swap_entry_free(struct swap_info_struct *p, + swp_entry_t entry) +{ + struct swap_cluster_info *ci; + unsigned long offset = swp_offset(entry); + unsigned char usage; + + ci = lock_cluster_or_swap_info(p, offset); + usage = __swap_entry_free_locked(p, offset, 1); + unlock_cluster_or_swap_info(p, ci); + if (!usage) + free_swap_slot(entry); + + return usage; +} + +static void swap_entry_free(struct swap_info_struct *p, swp_entry_t entry) +{ + struct swap_cluster_info *ci; + unsigned long offset = swp_offset(entry); + unsigned char count; + + ci = lock_cluster(p, offset); + count = p->swap_map[offset]; + VM_BUG_ON(count != SWAP_HAS_CACHE); + p->swap_map[offset] = 0; + dec_cluster_info_page(p, p->cluster_info, offset); + unlock_cluster(ci); + + mem_cgroup_uncharge_swap(entry, 1); + swap_range_free(p, offset, 1); +} + +/* + * Caller has made sure that the swap device corresponding to entry + * is still around or has not been recycled. + */ +void swap_free(swp_entry_t entry) +{ + struct swap_info_struct *p; + + p = _swap_info_get(entry); + if (p) + __swap_entry_free(p, entry); +} + +/* + * Called after dropping swapcache to decrease refcnt to swap entries. + */ +void put_swap_page(struct page *page, swp_entry_t entry) +{ + unsigned long offset = swp_offset(entry); + unsigned long idx = offset / SWAPFILE_CLUSTER; + struct swap_cluster_info *ci; + struct swap_info_struct *si; + unsigned char *map; + unsigned int i, free_entries = 0; + unsigned char val; + int size = swap_entry_size(thp_nr_pages(page)); + + si = _swap_info_get(entry); + if (!si) + return; + + ci = lock_cluster_or_swap_info(si, offset); + if (size == SWAPFILE_CLUSTER) { + VM_BUG_ON(!cluster_is_huge(ci)); + map = si->swap_map + offset; + for (i = 0; i < SWAPFILE_CLUSTER; i++) { + val = map[i]; + VM_BUG_ON(!(val & SWAP_HAS_CACHE)); + if (val == SWAP_HAS_CACHE) + free_entries++; + } + cluster_clear_huge(ci); + if (free_entries == SWAPFILE_CLUSTER) { + unlock_cluster_or_swap_info(si, ci); + spin_lock(&si->lock); + mem_cgroup_uncharge_swap(entry, SWAPFILE_CLUSTER); + swap_free_cluster(si, idx); + spin_unlock(&si->lock); + return; + } + } + for (i = 0; i < size; i++, entry.val++) { + if (!__swap_entry_free_locked(si, offset + i, SWAP_HAS_CACHE)) { + unlock_cluster_or_swap_info(si, ci); + free_swap_slot(entry); + if (i == size - 1) + return; + lock_cluster_or_swap_info(si, offset); + } + } + unlock_cluster_or_swap_info(si, ci); +} + +#ifdef CONFIG_THP_SWAP +int split_swap_cluster(swp_entry_t entry) +{ + struct swap_info_struct *si; + struct swap_cluster_info *ci; + unsigned long offset = swp_offset(entry); + + si = _swap_info_get(entry); + if (!si) + return -EBUSY; + ci = lock_cluster(si, offset); + cluster_clear_huge(ci); + unlock_cluster(ci); + return 0; +} +#endif + +static int swp_entry_cmp(const void *ent1, const void *ent2) +{ + const swp_entry_t *e1 = ent1, *e2 = ent2; + + return (int)swp_type(*e1) - (int)swp_type(*e2); +} + +void swapcache_free_entries(swp_entry_t *entries, int n) +{ + struct swap_info_struct *p, *prev; + int i; + + if (n <= 0) + return; + + prev = NULL; + p = NULL; + + /* + * Sort swap entries by swap device, so each lock is only taken once. + * nr_swapfiles isn't absolutely correct, but the overhead of sort() is + * so low that it isn't necessary to optimize further. + */ + if (nr_swapfiles > 1) + sort(entries, n, sizeof(entries[0]), swp_entry_cmp, NULL); + for (i = 0; i < n; ++i) { + p = swap_info_get_cont(entries[i], prev); + if (p) + swap_entry_free(p, entries[i]); + prev = p; + } + if (p) + spin_unlock(&p->lock); +} + +/* + * How many references to page are currently swapped out? + * This does not give an exact answer when swap count is continued, + * but does include the high COUNT_CONTINUED flag to allow for that. + */ +int page_swapcount(struct page *page) +{ + int count = 0; + struct swap_info_struct *p; + struct swap_cluster_info *ci; + swp_entry_t entry; + unsigned long offset; + + entry.val = page_private(page); + p = _swap_info_get(entry); + if (p) { + offset = swp_offset(entry); + ci = lock_cluster_or_swap_info(p, offset); + count = swap_count(p->swap_map[offset]); + unlock_cluster_or_swap_info(p, ci); + } + return count; +} + +int __swap_count(swp_entry_t entry) +{ + struct swap_info_struct *si; + pgoff_t offset = swp_offset(entry); + int count = 0; + + si = get_swap_device(entry); + if (si) { + count = swap_count(si->swap_map[offset]); + put_swap_device(si); + } + return count; +} + +static int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry) +{ + int count = 0; + pgoff_t offset = swp_offset(entry); + struct swap_cluster_info *ci; + + ci = lock_cluster_or_swap_info(si, offset); + count = swap_count(si->swap_map[offset]); + unlock_cluster_or_swap_info(si, ci); + return count; +} + +/* + * How many references to @entry are currently swapped out? + * This does not give an exact answer when swap count is continued, + * but does include the high COUNT_CONTINUED flag to allow for that. + */ +int __swp_swapcount(swp_entry_t entry) +{ + int count = 0; + struct swap_info_struct *si; + + si = get_swap_device(entry); + if (si) { + count = swap_swapcount(si, entry); + put_swap_device(si); + } + return count; +} + +/* + * How many references to @entry are currently swapped out? + * This considers COUNT_CONTINUED so it returns exact answer. + */ +int swp_swapcount(swp_entry_t entry) +{ + int count, tmp_count, n; + struct swap_info_struct *p; + struct swap_cluster_info *ci; + struct page *page; + pgoff_t offset; + unsigned char *map; + + p = _swap_info_get(entry); + if (!p) + return 0; + + offset = swp_offset(entry); + + ci = lock_cluster_or_swap_info(p, offset); + + count = swap_count(p->swap_map[offset]); + if (!(count & COUNT_CONTINUED)) + goto out; + + count &= ~COUNT_CONTINUED; + n = SWAP_MAP_MAX + 1; + + page = vmalloc_to_page(p->swap_map + offset); + offset &= ~PAGE_MASK; + VM_BUG_ON(page_private(page) != SWP_CONTINUED); + + do { + page = list_next_entry(page, lru); + map = kmap_atomic(page); + tmp_count = map[offset]; + kunmap_atomic(map); + + count += (tmp_count & ~COUNT_CONTINUED) * n; + n *= (SWAP_CONT_MAX + 1); + } while (tmp_count & COUNT_CONTINUED); +out: + unlock_cluster_or_swap_info(p, ci); + return count; +} + +static bool swap_page_trans_huge_swapped(struct swap_info_struct *si, + swp_entry_t entry) +{ + struct swap_cluster_info *ci; + unsigned char *map = si->swap_map; + unsigned long roffset = swp_offset(entry); + unsigned long offset = round_down(roffset, SWAPFILE_CLUSTER); + int i; + bool ret = false; + + ci = lock_cluster_or_swap_info(si, offset); + if (!ci || !cluster_is_huge(ci)) { + if (swap_count(map[roffset])) + ret = true; + goto unlock_out; + } + for (i = 0; i < SWAPFILE_CLUSTER; i++) { + if (swap_count(map[offset + i])) { + ret = true; + break; + } + } +unlock_out: + unlock_cluster_or_swap_info(si, ci); + return ret; +} + +static bool page_swapped(struct page *page) +{ + swp_entry_t entry; + struct swap_info_struct *si; + + if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!PageTransCompound(page))) + return page_swapcount(page) != 0; + + page = compound_head(page); + entry.val = page_private(page); + si = _swap_info_get(entry); + if (si) + return swap_page_trans_huge_swapped(si, entry); + return false; +} + +static int page_trans_huge_map_swapcount(struct page *page, int *total_mapcount, + int *total_swapcount) +{ + int i, map_swapcount, _total_mapcount, _total_swapcount; + unsigned long offset = 0; + struct swap_info_struct *si; + struct swap_cluster_info *ci = NULL; + unsigned char *map = NULL; + int mapcount, swapcount = 0; + + /* hugetlbfs shouldn't call it */ + VM_BUG_ON_PAGE(PageHuge(page), page); + + if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!PageTransCompound(page))) { + mapcount = page_trans_huge_mapcount(page, total_mapcount); + if (PageSwapCache(page)) + swapcount = page_swapcount(page); + if (total_swapcount) + *total_swapcount = swapcount; + return mapcount + swapcount; + } + + page = compound_head(page); + + _total_mapcount = _total_swapcount = map_swapcount = 0; + if (PageSwapCache(page)) { + swp_entry_t entry; + + entry.val = page_private(page); + si = _swap_info_get(entry); + if (si) { + map = si->swap_map; + offset = swp_offset(entry); + } + } + if (map) + ci = lock_cluster(si, offset); + for (i = 0; i < HPAGE_PMD_NR; i++) { + mapcount = atomic_read(&page[i]._mapcount) + 1; + _total_mapcount += mapcount; + if (map) { + swapcount = swap_count(map[offset + i]); + _total_swapcount += swapcount; + } + map_swapcount = max(map_swapcount, mapcount + swapcount); + } + unlock_cluster(ci); + if (PageDoubleMap(page)) { + map_swapcount -= 1; + _total_mapcount -= HPAGE_PMD_NR; + } + mapcount = compound_mapcount(page); + map_swapcount += mapcount; + _total_mapcount += mapcount; + if (total_mapcount) + *total_mapcount = _total_mapcount; + if (total_swapcount) + *total_swapcount = _total_swapcount; + + return map_swapcount; +} + +/* + * We can write to an anon page without COW if there are no other references + * to it. And as a side-effect, free up its swap: because the old content + * on disk will never be read, and seeking back there to write new content + * later would only waste time away from clustering. + * + * NOTE: total_map_swapcount should not be relied upon by the caller if + * reuse_swap_page() returns false, but it may be always overwritten + * (see the other implementation for CONFIG_SWAP=n). + */ +bool reuse_swap_page(struct page *page, int *total_map_swapcount) +{ + int count, total_mapcount, total_swapcount; + + VM_BUG_ON_PAGE(!PageLocked(page), page); + if (unlikely(PageKsm(page))) + return false; + count = page_trans_huge_map_swapcount(page, &total_mapcount, + &total_swapcount); + if (total_map_swapcount) + *total_map_swapcount = total_mapcount + total_swapcount; + if (count == 1 && PageSwapCache(page) && + (likely(!PageTransCompound(page)) || + /* The remaining swap count will be freed soon */ + total_swapcount == page_swapcount(page))) { + if (!PageWriteback(page)) { + page = compound_head(page); + delete_from_swap_cache(page); + SetPageDirty(page); + } else { + swp_entry_t entry; + struct swap_info_struct *p; + + entry.val = page_private(page); + p = swap_info_get(entry); + if (p->flags & SWP_STABLE_WRITES) { + spin_unlock(&p->lock); + return false; + } + spin_unlock(&p->lock); + } + } + + return count <= 1; +} + +/* + * If swap is getting full, or if there are no more mappings of this page, + * then try_to_free_swap is called to free its swap space. + */ +int try_to_free_swap(struct page *page) +{ + VM_BUG_ON_PAGE(!PageLocked(page), page); + + if (!PageSwapCache(page)) + return 0; + if (PageWriteback(page)) + return 0; + if (page_swapped(page)) + return 0; + + /* + * Once hibernation has begun to create its image of memory, + * there's a danger that one of the calls to try_to_free_swap() + * - most probably a call from __try_to_reclaim_swap() while + * hibernation is allocating its own swap pages for the image, + * but conceivably even a call from memory reclaim - will free + * the swap from a page which has already been recorded in the + * image as a clean swapcache page, and then reuse its swap for + * another page of the image. On waking from hibernation, the + * original page might be freed under memory pressure, then + * later read back in from swap, now with the wrong data. + * + * Hibernation suspends storage while it is writing the image + * to disk so check that here. + */ + if (pm_suspended_storage()) + return 0; + + page = compound_head(page); + delete_from_swap_cache(page); + SetPageDirty(page); + return 1; +} + +/* + * Free the swap entry like above, but also try to + * free the page cache entry if it is the last user. + */ +int free_swap_and_cache(swp_entry_t entry) +{ + struct swap_info_struct *p; + unsigned char count; + + if (non_swap_entry(entry)) + return 1; + + p = _swap_info_get(entry); + if (p) { + count = __swap_entry_free(p, entry); + if (count == SWAP_HAS_CACHE && + !swap_page_trans_huge_swapped(p, entry)) + __try_to_reclaim_swap(p, swp_offset(entry), + TTRS_UNMAPPED | TTRS_FULL); + } + return p != NULL; +} + +#ifdef CONFIG_HIBERNATION +/* + * Find the swap type that corresponds to given device (if any). + * + * @offset - number of the PAGE_SIZE-sized block of the device, starting + * from 0, in which the swap header is expected to be located. + * + * This is needed for the suspend to disk (aka swsusp). + */ +int swap_type_of(dev_t device, sector_t offset) +{ + int type; + + if (!device) + return -1; + + spin_lock(&swap_lock); + for (type = 0; type < nr_swapfiles; type++) { + struct swap_info_struct *sis = swap_info[type]; + + if (!(sis->flags & SWP_WRITEOK)) + continue; + + if (device == sis->bdev->bd_dev) { + struct swap_extent *se = first_se(sis); + + if (se->start_block == offset) { + spin_unlock(&swap_lock); + return type; + } + } + } + spin_unlock(&swap_lock); + return -ENODEV; +} + +int find_first_swap(dev_t *device) +{ + int type; + + spin_lock(&swap_lock); + for (type = 0; type < nr_swapfiles; type++) { + struct swap_info_struct *sis = swap_info[type]; + + if (!(sis->flags & SWP_WRITEOK)) + continue; + *device = sis->bdev->bd_dev; + spin_unlock(&swap_lock); + return type; + } + spin_unlock(&swap_lock); + return -ENODEV; +} + +/* + * Get the (PAGE_SIZE) block corresponding to given offset on the swapdev + * corresponding to given index in swap_info (swap type). + */ +sector_t swapdev_block(int type, pgoff_t offset) +{ + struct block_device *bdev; + struct swap_info_struct *si = swap_type_to_swap_info(type); + + if (!si || !(si->flags & SWP_WRITEOK)) + return 0; + return map_swap_entry(swp_entry(type, offset), &bdev); +} + +/* + * Return either the total number of swap pages of given type, or the number + * of free pages of that type (depending on @free) + * + * This is needed for software suspend + */ +unsigned int count_swap_pages(int type, int free) +{ + unsigned int n = 0; + + spin_lock(&swap_lock); + if ((unsigned int)type < nr_swapfiles) { + struct swap_info_struct *sis = swap_info[type]; + + spin_lock(&sis->lock); + if (sis->flags & SWP_WRITEOK) { + n = sis->pages; + if (free) + n -= sis->inuse_pages; + } + spin_unlock(&sis->lock); + } + spin_unlock(&swap_lock); + return n; +} +#endif /* CONFIG_HIBERNATION */ + +static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte) +{ + return pte_same(pte_swp_clear_flags(pte), swp_pte); +} + +/* + * No need to decide whether this PTE shares the swap entry with others, + * just let do_wp_page work it out if a write is requested later - to + * force COW, vm_page_prot omits write permission from any private vma. + */ +static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, + unsigned long addr, swp_entry_t entry, struct page *page) +{ + struct page *swapcache; + spinlock_t *ptl; + pte_t *pte; + int ret = 1; + + swapcache = page; + page = ksm_might_need_to_copy(page, vma, addr); + if (unlikely(!page)) + return -ENOMEM; + + pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); + if (unlikely(!pte_same_as_swp(*pte, swp_entry_to_pte(entry)))) { + ret = 0; + goto out; + } + + dec_mm_counter(vma->vm_mm, MM_SWAPENTS); + inc_mm_counter(vma->vm_mm, MM_ANONPAGES); + get_page(page); + set_pte_at(vma->vm_mm, addr, pte, + pte_mkold(mk_pte(page, vma->vm_page_prot))); + if (page == swapcache) { + page_add_anon_rmap(page, vma, addr, false); + } else { /* ksm created a completely new copy */ + page_add_new_anon_rmap(page, vma, addr, false); + lru_cache_add_inactive_or_unevictable(page, vma); + } + swap_free(entry); +out: + pte_unmap_unlock(pte, ptl); + if (page != swapcache) { + unlock_page(page); + put_page(page); + } + return ret; +} + +static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, + unsigned long addr, unsigned long end, + unsigned int type, bool frontswap, + unsigned long *fs_pages_to_unuse) +{ + struct page *page; + swp_entry_t entry; + pte_t *pte; + struct swap_info_struct *si; + unsigned long offset; + int ret = 0; + volatile unsigned char *swap_map; + + si = swap_info[type]; + pte = pte_offset_map(pmd, addr); + do { + struct vm_fault vmf; + + if (!is_swap_pte(*pte)) + continue; + + entry = pte_to_swp_entry(*pte); + if (swp_type(entry) != type) + continue; + + offset = swp_offset(entry); + if (frontswap && !frontswap_test(si, offset)) + continue; + + pte_unmap(pte); + swap_map = &si->swap_map[offset]; + page = lookup_swap_cache(entry, vma, addr); + if (!page) { + vmf.vma = vma; + vmf.address = addr; + vmf.pmd = pmd; + page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, + &vmf); + } + if (!page) { + if (*swap_map == 0 || *swap_map == SWAP_MAP_BAD) + goto try_next; + return -ENOMEM; + } + + lock_page(page); + wait_on_page_writeback(page); + ret = unuse_pte(vma, pmd, addr, entry, page); + if (ret < 0) { + unlock_page(page); + put_page(page); + goto out; + } + + try_to_free_swap(page); + unlock_page(page); + put_page(page); + + if (*fs_pages_to_unuse && !--(*fs_pages_to_unuse)) { + ret = FRONTSWAP_PAGES_UNUSED; + goto out; + } +try_next: + pte = pte_offset_map(pmd, addr); + } while (pte++, addr += PAGE_SIZE, addr != end); + pte_unmap(pte - 1); + + ret = 0; +out: + return ret; +} + +static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, + unsigned long addr, unsigned long end, + unsigned int type, bool frontswap, + unsigned long *fs_pages_to_unuse) +{ + pmd_t *pmd; + unsigned long next; + int ret; + + pmd = pmd_offset(pud, addr); + do { + cond_resched(); + next = pmd_addr_end(addr, end); + if (pmd_none_or_trans_huge_or_clear_bad(pmd)) + continue; + ret = unuse_pte_range(vma, pmd, addr, next, type, + frontswap, fs_pages_to_unuse); + if (ret) + return ret; + } while (pmd++, addr = next, addr != end); + return 0; +} + +static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, + unsigned long addr, unsigned long end, + unsigned int type, bool frontswap, + unsigned long *fs_pages_to_unuse) +{ + pud_t *pud; + unsigned long next; + int ret; + + pud = pud_offset(p4d, addr); + do { + next = pud_addr_end(addr, end); + if (pud_none_or_clear_bad(pud)) + continue; + ret = unuse_pmd_range(vma, pud, addr, next, type, + frontswap, fs_pages_to_unuse); + if (ret) + return ret; + } while (pud++, addr = next, addr != end); + return 0; +} + +static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, + unsigned long addr, unsigned long end, + unsigned int type, bool frontswap, + unsigned long *fs_pages_to_unuse) +{ + p4d_t *p4d; + unsigned long next; + int ret; + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(p4d)) + continue; + ret = unuse_pud_range(vma, p4d, addr, next, type, + frontswap, fs_pages_to_unuse); + if (ret) + return ret; + } while (p4d++, addr = next, addr != end); + return 0; +} + +static int unuse_vma(struct vm_area_struct *vma, unsigned int type, + bool frontswap, unsigned long *fs_pages_to_unuse) +{ + pgd_t *pgd; + unsigned long addr, end, next; + int ret; + + addr = vma->vm_start; + end = vma->vm_end; + + pgd = pgd_offset(vma->vm_mm, addr); + do { + next = pgd_addr_end(addr, end); + if (pgd_none_or_clear_bad(pgd)) + continue; + ret = unuse_p4d_range(vma, pgd, addr, next, type, + frontswap, fs_pages_to_unuse); + if (ret) + return ret; + } while (pgd++, addr = next, addr != end); + return 0; +} + +static int unuse_mm(struct mm_struct *mm, unsigned int type, + bool frontswap, unsigned long *fs_pages_to_unuse) +{ + struct vm_area_struct *vma; + int ret = 0; + + mmap_read_lock(mm); + for (vma = mm->mmap; vma; vma = vma->vm_next) { + if (vma->anon_vma) { + ret = unuse_vma(vma, type, frontswap, + fs_pages_to_unuse); + if (ret) + break; + } + cond_resched(); + } + mmap_read_unlock(mm); + return ret; +} + +/* + * Scan swap_map (or frontswap_map if frontswap parameter is true) + * from current position to next entry still in use. Return 0 + * if there are no inuse entries after prev till end of the map. + */ +static unsigned int find_next_to_unuse(struct swap_info_struct *si, + unsigned int prev, bool frontswap) +{ + unsigned int i; + unsigned char count; + + /* + * No need for swap_lock here: we're just looking + * for whether an entry is in use, not modifying it; false + * hits are okay, and sys_swapoff() has already prevented new + * allocations from this area (while holding swap_lock). + */ + for (i = prev + 1; i < si->max; i++) { + count = READ_ONCE(si->swap_map[i]); + if (count && swap_count(count) != SWAP_MAP_BAD) + if (!frontswap || frontswap_test(si, i)) + break; + if ((i % LATENCY_LIMIT) == 0) + cond_resched(); + } + + if (i == si->max) + i = 0; + + return i; +} + +/* + * If the boolean frontswap is true, only unuse pages_to_unuse pages; + * pages_to_unuse==0 means all pages; ignored if frontswap is false + */ +int try_to_unuse(unsigned int type, bool frontswap, + unsigned long pages_to_unuse) +{ + struct mm_struct *prev_mm; + struct mm_struct *mm; + struct list_head *p; + int retval = 0; + struct swap_info_struct *si = swap_info[type]; + struct page *page; + swp_entry_t entry; + unsigned int i; + + if (!READ_ONCE(si->inuse_pages)) + return 0; + + if (!frontswap) + pages_to_unuse = 0; + +retry: + retval = shmem_unuse(type, frontswap, &pages_to_unuse); + if (retval) + goto out; + + prev_mm = &init_mm; + mmget(prev_mm); + + spin_lock(&mmlist_lock); + p = &init_mm.mmlist; + while (READ_ONCE(si->inuse_pages) && + !signal_pending(current) && + (p = p->next) != &init_mm.mmlist) { + + mm = list_entry(p, struct mm_struct, mmlist); + if (!mmget_not_zero(mm)) + continue; + spin_unlock(&mmlist_lock); + mmput(prev_mm); + prev_mm = mm; + retval = unuse_mm(mm, type, frontswap, &pages_to_unuse); + + if (retval) { + mmput(prev_mm); + goto out; + } + + /* + * Make sure that we aren't completely killing + * interactive performance. + */ + cond_resched(); + spin_lock(&mmlist_lock); + } + spin_unlock(&mmlist_lock); + + mmput(prev_mm); + + i = 0; + while (READ_ONCE(si->inuse_pages) && + !signal_pending(current) && + (i = find_next_to_unuse(si, i, frontswap)) != 0) { + + entry = swp_entry(type, i); + page = find_get_page(swap_address_space(entry), i); + if (!page) + continue; + + /* + * It is conceivable that a racing task removed this page from + * swap cache just before we acquired the page lock. The page + * might even be back in swap cache on another swap area. But + * that is okay, try_to_free_swap() only removes stale pages. + */ + lock_page(page); + wait_on_page_writeback(page); + try_to_free_swap(page); + unlock_page(page); + put_page(page); + + /* + * For frontswap, we just need to unuse pages_to_unuse, if + * it was specified. Need not check frontswap again here as + * we already zeroed out pages_to_unuse if not frontswap. + */ + if (pages_to_unuse && --pages_to_unuse == 0) + goto out; + } + + /* + * Lets check again to see if there are still swap entries in the map. + * If yes, we would need to do retry the unuse logic again. + * Under global memory pressure, swap entries can be reinserted back + * into process space after the mmlist loop above passes over them. + * + * Limit the number of retries? No: when mmget_not_zero() above fails, + * that mm is likely to be freeing swap from exit_mmap(), which proceeds + * at its own independent pace; and even shmem_writepage() could have + * been preempted after get_swap_page(), temporarily hiding that swap. + * It's easy and robust (though cpu-intensive) just to keep retrying. + */ + if (READ_ONCE(si->inuse_pages)) { + if (!signal_pending(current)) + goto retry; + retval = -EINTR; + } +out: + return (retval == FRONTSWAP_PAGES_UNUSED) ? 0 : retval; +} + +/* + * After a successful try_to_unuse, if no swap is now in use, we know + * we can empty the mmlist. swap_lock must be held on entry and exit. + * Note that mmlist_lock nests inside swap_lock, and an mm must be + * added to the mmlist just after page_duplicate - before would be racy. + */ +static void drain_mmlist(void) +{ + struct list_head *p, *next; + unsigned int type; + + for (type = 0; type < nr_swapfiles; type++) + if (swap_info[type]->inuse_pages) + return; + spin_lock(&mmlist_lock); + list_for_each_safe(p, next, &init_mm.mmlist) + list_del_init(p); + spin_unlock(&mmlist_lock); +} + +/* + * Use this swapdev's extent info to locate the (PAGE_SIZE) block which + * corresponds to page offset for the specified swap entry. + * Note that the type of this function is sector_t, but it returns page offset + * into the bdev, not sector offset. + */ +static sector_t map_swap_entry(swp_entry_t entry, struct block_device **bdev) +{ + struct swap_info_struct *sis; + struct swap_extent *se; + pgoff_t offset; + + sis = swp_swap_info(entry); + *bdev = sis->bdev; + + offset = swp_offset(entry); + se = offset_to_swap_extent(sis, offset); + return se->start_block + (offset - se->start_page); +} + +/* + * Returns the page offset into bdev for the specified page's swap entry. + */ +sector_t map_swap_page(struct page *page, struct block_device **bdev) +{ + swp_entry_t entry; + entry.val = page_private(page); + return map_swap_entry(entry, bdev); +} + +/* + * Free all of a swapdev's extent information + */ +static void destroy_swap_extents(struct swap_info_struct *sis) +{ + while (!RB_EMPTY_ROOT(&sis->swap_extent_root)) { + struct rb_node *rb = sis->swap_extent_root.rb_node; + struct swap_extent *se = rb_entry(rb, struct swap_extent, rb_node); + + rb_erase(rb, &sis->swap_extent_root); + kfree(se); + } + + if (sis->flags & SWP_ACTIVATED) { + struct file *swap_file = sis->swap_file; + struct address_space *mapping = swap_file->f_mapping; + + sis->flags &= ~SWP_ACTIVATED; + if (mapping->a_ops->swap_deactivate) + mapping->a_ops->swap_deactivate(swap_file); + } +} + +/* + * Add a block range (and the corresponding page range) into this swapdev's + * extent tree. + * + * This function rather assumes that it is called in ascending page order. + */ +int +add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, + unsigned long nr_pages, sector_t start_block) +{ + struct rb_node **link = &sis->swap_extent_root.rb_node, *parent = NULL; + struct swap_extent *se; + struct swap_extent *new_se; + + /* + * place the new node at the right most since the + * function is called in ascending page order. + */ + while (*link) { + parent = *link; + link = &parent->rb_right; + } + + if (parent) { + se = rb_entry(parent, struct swap_extent, rb_node); + BUG_ON(se->start_page + se->nr_pages != start_page); + if (se->start_block + se->nr_pages == start_block) { + /* Merge it */ + se->nr_pages += nr_pages; + return 0; + } + } + + /* No merge, insert a new extent. */ + new_se = kmalloc(sizeof(*se), GFP_KERNEL); + if (new_se == NULL) + return -ENOMEM; + new_se->start_page = start_page; + new_se->nr_pages = nr_pages; + new_se->start_block = start_block; + + rb_link_node(&new_se->rb_node, parent, link); + rb_insert_color(&new_se->rb_node, &sis->swap_extent_root); + return 1; +} +EXPORT_SYMBOL_GPL(add_swap_extent); + +/* + * A `swap extent' is a simple thing which maps a contiguous range of pages + * onto a contiguous range of disk blocks. An ordered list of swap extents + * is built at swapon time and is then used at swap_writepage/swap_readpage + * time for locating where on disk a page belongs. + * + * If the swapfile is an S_ISBLK block device, a single extent is installed. + * This is done so that the main operating code can treat S_ISBLK and S_ISREG + * swap files identically. + * + * Whether the swapdev is an S_ISREG file or an S_ISBLK blockdev, the swap + * extent list operates in PAGE_SIZE disk blocks. Both S_ISREG and S_ISBLK + * swapfiles are handled *identically* after swapon time. + * + * For S_ISREG swapfiles, setup_swap_extents() will walk all the file's blocks + * and will parse them into an ordered extent list, in PAGE_SIZE chunks. If + * some stray blocks are found which do not fall within the PAGE_SIZE alignment + * requirements, they are simply tossed out - we will never use those blocks + * for swapping. + * + * For all swap devices we set S_SWAPFILE across the life of the swapon. This + * prevents users from writing to the swap device, which will corrupt memory. + * + * The amount of disk space which a single swap extent represents varies. + * Typically it is in the 1-4 megabyte range. So we can have hundreds of + * extents in the list. To avoid much list walking, we cache the previous + * search location in `curr_swap_extent', and start new searches from there. + * This is extremely effective. The average number of iterations in + * map_swap_page() has been measured at about 0.3 per page. - akpm. + */ +static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) +{ + struct file *swap_file = sis->swap_file; + struct address_space *mapping = swap_file->f_mapping; + struct inode *inode = mapping->host; + int ret; + + if (S_ISBLK(inode->i_mode)) { + ret = add_swap_extent(sis, 0, sis->max, 0); + *span = sis->pages; + return ret; + } + + if (mapping->a_ops->swap_activate) { + ret = mapping->a_ops->swap_activate(sis, swap_file, span); + if (ret >= 0) + sis->flags |= SWP_ACTIVATED; + if (!ret) { + sis->flags |= SWP_FS_OPS; + ret = add_swap_extent(sis, 0, sis->max, 0); + *span = sis->pages; + } + return ret; + } + + return generic_swapfile_activate(sis, swap_file, span); +} + +static int swap_node(struct swap_info_struct *p) +{ + struct block_device *bdev; + + if (p->bdev) + bdev = p->bdev; + else + bdev = p->swap_file->f_inode->i_sb->s_bdev; + + return bdev ? bdev->bd_disk->node_id : NUMA_NO_NODE; +} + +static void setup_swap_info(struct swap_info_struct *p, int prio, + unsigned char *swap_map, + struct swap_cluster_info *cluster_info) +{ + int i; + + if (prio >= 0) + p->prio = prio; + else + p->prio = --least_priority; + /* + * the plist prio is negated because plist ordering is + * low-to-high, while swap ordering is high-to-low + */ + p->list.prio = -p->prio; + for_each_node(i) { + if (p->prio >= 0) + p->avail_lists[i].prio = -p->prio; + else { + if (swap_node(p) == i) + p->avail_lists[i].prio = 1; + else + p->avail_lists[i].prio = -p->prio; + } + } + p->swap_map = swap_map; + p->cluster_info = cluster_info; +} + +static void _enable_swap_info(struct swap_info_struct *p) +{ + p->flags |= SWP_WRITEOK | SWP_VALID; + atomic_long_add(p->pages, &nr_swap_pages); + total_swap_pages += p->pages; + + assert_spin_locked(&swap_lock); + /* + * both lists are plists, and thus priority ordered. + * swap_active_head needs to be priority ordered for swapoff(), + * which on removal of any swap_info_struct with an auto-assigned + * (i.e. negative) priority increments the auto-assigned priority + * of any lower-priority swap_info_structs. + * swap_avail_head needs to be priority ordered for get_swap_page(), + * which allocates swap pages from the highest available priority + * swap_info_struct. + */ + plist_add(&p->list, &swap_active_head); + add_to_avail_list(p); +} + +static void enable_swap_info(struct swap_info_struct *p, int prio, + unsigned char *swap_map, + struct swap_cluster_info *cluster_info, + unsigned long *frontswap_map) +{ + frontswap_init(p->type, frontswap_map); + spin_lock(&swap_lock); + spin_lock(&p->lock); + setup_swap_info(p, prio, swap_map, cluster_info); + spin_unlock(&p->lock); + spin_unlock(&swap_lock); + /* + * Guarantee swap_map, cluster_info, etc. fields are valid + * between get/put_swap_device() if SWP_VALID bit is set + */ + synchronize_rcu(); + spin_lock(&swap_lock); + spin_lock(&p->lock); + _enable_swap_info(p); + spin_unlock(&p->lock); + spin_unlock(&swap_lock); +} + +static void reinsert_swap_info(struct swap_info_struct *p) +{ + spin_lock(&swap_lock); + spin_lock(&p->lock); + setup_swap_info(p, p->prio, p->swap_map, p->cluster_info); + _enable_swap_info(p); + spin_unlock(&p->lock); + spin_unlock(&swap_lock); +} + +bool has_usable_swap(void) +{ + bool ret = true; + + spin_lock(&swap_lock); + if (plist_head_empty(&swap_active_head)) + ret = false; + spin_unlock(&swap_lock); + return ret; +} + +SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) +{ + struct swap_info_struct *p = NULL; + unsigned char *swap_map; + struct swap_cluster_info *cluster_info; + unsigned long *frontswap_map; + struct file *swap_file, *victim; + struct address_space *mapping; + struct inode *inode; + struct filename *pathname; + int err, found = 0; + unsigned int old_block_size; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + BUG_ON(!current->mm); + + pathname = getname(specialfile); + if (IS_ERR(pathname)) + return PTR_ERR(pathname); + + victim = file_open_name(pathname, O_RDWR|O_LARGEFILE, 0); + err = PTR_ERR(victim); + if (IS_ERR(victim)) + goto out; + + mapping = victim->f_mapping; + spin_lock(&swap_lock); + plist_for_each_entry(p, &swap_active_head, list) { + if (p->flags & SWP_WRITEOK) { + if (p->swap_file->f_mapping == mapping) { + found = 1; + break; + } + } + } + if (!found) { + err = -EINVAL; + spin_unlock(&swap_lock); + goto out_dput; + } + if (!security_vm_enough_memory_mm(current->mm, p->pages)) + vm_unacct_memory(p->pages); + else { + err = -ENOMEM; + spin_unlock(&swap_lock); + goto out_dput; + } + spin_lock(&p->lock); + del_from_avail_list(p); + if (p->prio < 0) { + struct swap_info_struct *si = p; + int nid; + + plist_for_each_entry_continue(si, &swap_active_head, list) { + si->prio++; + si->list.prio--; + for_each_node(nid) { + if (si->avail_lists[nid].prio != 1) + si->avail_lists[nid].prio--; + } + } + least_priority++; + } + plist_del(&p->list, &swap_active_head); + atomic_long_sub(p->pages, &nr_swap_pages); + total_swap_pages -= p->pages; + p->flags &= ~SWP_WRITEOK; + spin_unlock(&p->lock); + spin_unlock(&swap_lock); + + disable_swap_slots_cache_lock(); + + set_current_oom_origin(); + err = try_to_unuse(p->type, false, 0); /* force unuse all pages */ + clear_current_oom_origin(); + + if (err) { + /* re-insert swap space back into swap_list */ + reinsert_swap_info(p); + reenable_swap_slots_cache_unlock(); + goto out_dput; + } + + reenable_swap_slots_cache_unlock(); + + spin_lock(&swap_lock); + spin_lock(&p->lock); + p->flags &= ~SWP_VALID; /* mark swap device as invalid */ + spin_unlock(&p->lock); + spin_unlock(&swap_lock); + /* + * wait for swap operations protected by get/put_swap_device() + * to complete + */ + synchronize_rcu(); + + flush_work(&p->discard_work); + + destroy_swap_extents(p); + if (p->flags & SWP_CONTINUED) + free_swap_count_continuations(p); + + if (!p->bdev || !blk_queue_nonrot(bdev_get_queue(p->bdev))) + atomic_dec(&nr_rotate_swap); + + mutex_lock(&swapon_mutex); + spin_lock(&swap_lock); + spin_lock(&p->lock); + drain_mmlist(); + + /* wait for anyone still in scan_swap_map */ + p->highest_bit = 0; /* cuts scans short */ + while (p->flags >= SWP_SCANNING) { + spin_unlock(&p->lock); + spin_unlock(&swap_lock); + schedule_timeout_uninterruptible(1); + spin_lock(&swap_lock); + spin_lock(&p->lock); + } + + swap_file = p->swap_file; + old_block_size = p->old_block_size; + p->swap_file = NULL; + p->max = 0; + swap_map = p->swap_map; + p->swap_map = NULL; + cluster_info = p->cluster_info; + p->cluster_info = NULL; + frontswap_map = frontswap_map_get(p); + spin_unlock(&p->lock); + spin_unlock(&swap_lock); + arch_swap_invalidate_area(p->type); + frontswap_invalidate_area(p->type); + frontswap_map_set(p, NULL); + mutex_unlock(&swapon_mutex); + free_percpu(p->percpu_cluster); + p->percpu_cluster = NULL; + free_percpu(p->cluster_next_cpu); + p->cluster_next_cpu = NULL; + vfree(swap_map); + kvfree(cluster_info); + kvfree(frontswap_map); + /* Destroy swap account information */ + swap_cgroup_swapoff(p->type); + exit_swap_address_space(p->type); + + inode = mapping->host; + if (S_ISBLK(inode->i_mode)) { + struct block_device *bdev = I_BDEV(inode); + + set_blocksize(bdev, old_block_size); + blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); + } + + inode_lock(inode); + inode->i_flags &= ~S_SWAPFILE; + inode_unlock(inode); + filp_close(swap_file, NULL); + + /* + * Clear the SWP_USED flag after all resources are freed so that swapon + * can reuse this swap_info in alloc_swap_info() safely. It is ok to + * not hold p->lock after we cleared its SWP_WRITEOK. + */ + spin_lock(&swap_lock); + p->flags = 0; + spin_unlock(&swap_lock); + + err = 0; + atomic_inc(&proc_poll_event); + wake_up_interruptible(&proc_poll_wait); + +out_dput: + filp_close(victim, NULL); +out: + putname(pathname); + return err; +} + +#ifdef CONFIG_PROC_FS +static __poll_t swaps_poll(struct file *file, poll_table *wait) +{ + struct seq_file *seq = file->private_data; + + poll_wait(file, &proc_poll_wait, wait); + + if (seq->poll_event != atomic_read(&proc_poll_event)) { + seq->poll_event = atomic_read(&proc_poll_event); + return EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLPRI; + } + + return EPOLLIN | EPOLLRDNORM; +} + +/* iterator */ +static void *swap_start(struct seq_file *swap, loff_t *pos) +{ + struct swap_info_struct *si; + int type; + loff_t l = *pos; + + mutex_lock(&swapon_mutex); + + if (!l) + return SEQ_START_TOKEN; + + for (type = 0; (si = swap_type_to_swap_info(type)); type++) { + if (!(si->flags & SWP_USED) || !si->swap_map) + continue; + if (!--l) + return si; + } + + return NULL; +} + +static void *swap_next(struct seq_file *swap, void *v, loff_t *pos) +{ + struct swap_info_struct *si = v; + int type; + + if (v == SEQ_START_TOKEN) + type = 0; + else + type = si->type + 1; + + ++(*pos); + for (; (si = swap_type_to_swap_info(type)); type++) { + if (!(si->flags & SWP_USED) || !si->swap_map) + continue; + return si; + } + + return NULL; +} + +static void swap_stop(struct seq_file *swap, void *v) +{ + mutex_unlock(&swapon_mutex); +} + +static int swap_show(struct seq_file *swap, void *v) +{ + struct swap_info_struct *si = v; + struct file *file; + int len; + unsigned int bytes, inuse; + + if (si == SEQ_START_TOKEN) { + seq_puts(swap,"Filename\t\t\t\tType\t\tSize\t\tUsed\t\tPriority\n"); + return 0; + } + + bytes = si->pages << (PAGE_SHIFT - 10); + inuse = si->inuse_pages << (PAGE_SHIFT - 10); + + file = si->swap_file; + len = seq_file_path(swap, file, " \t\n\\"); + seq_printf(swap, "%*s%s\t%u\t%s%u\t%s%d\n", + len < 40 ? 40 - len : 1, " ", + S_ISBLK(file_inode(file)->i_mode) ? + "partition" : "file\t", + bytes, bytes < 10000000 ? "\t" : "", + inuse, inuse < 10000000 ? "\t" : "", + si->prio); + return 0; +} + +static const struct seq_operations swaps_op = { + .start = swap_start, + .next = swap_next, + .stop = swap_stop, + .show = swap_show +}; + +static int swaps_open(struct inode *inode, struct file *file) +{ + struct seq_file *seq; + int ret; + + ret = seq_open(file, &swaps_op); + if (ret) + return ret; + + seq = file->private_data; + seq->poll_event = atomic_read(&proc_poll_event); + return 0; +} + +static const struct proc_ops swaps_proc_ops = { + .proc_flags = PROC_ENTRY_PERMANENT, + .proc_open = swaps_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = seq_release, + .proc_poll = swaps_poll, +}; + +static int __init procswaps_init(void) +{ + proc_create("swaps", 0, NULL, &swaps_proc_ops); + return 0; +} +__initcall(procswaps_init); +#endif /* CONFIG_PROC_FS */ + +#ifdef MAX_SWAPFILES_CHECK +static int __init max_swapfiles_check(void) +{ + MAX_SWAPFILES_CHECK(); + return 0; +} +late_initcall(max_swapfiles_check); +#endif + +static struct swap_info_struct *alloc_swap_info(void) +{ + struct swap_info_struct *p; + struct swap_info_struct *defer = NULL; + unsigned int type; + int i; + + p = kvzalloc(struct_size(p, avail_lists, nr_node_ids), GFP_KERNEL); + if (!p) + return ERR_PTR(-ENOMEM); + + spin_lock(&swap_lock); + for (type = 0; type < nr_swapfiles; type++) { + if (!(swap_info[type]->flags & SWP_USED)) + break; + } + if (type >= MAX_SWAPFILES) { + spin_unlock(&swap_lock); + kvfree(p); + return ERR_PTR(-EPERM); + } + if (type >= nr_swapfiles) { + p->type = type; + WRITE_ONCE(swap_info[type], p); + /* + * Write swap_info[type] before nr_swapfiles, in case a + * racing procfs swap_start() or swap_next() is reading them. + * (We never shrink nr_swapfiles, we never free this entry.) + */ + smp_wmb(); + WRITE_ONCE(nr_swapfiles, nr_swapfiles + 1); + } else { + defer = p; + p = swap_info[type]; + /* + * Do not memset this entry: a racing procfs swap_next() + * would be relying on p->type to remain valid. + */ + } + p->swap_extent_root = RB_ROOT; + plist_node_init(&p->list, 0); + for_each_node(i) + plist_node_init(&p->avail_lists[i], 0); + p->flags = SWP_USED; + spin_unlock(&swap_lock); + kvfree(defer); + spin_lock_init(&p->lock); + spin_lock_init(&p->cont_lock); + + return p; +} + +static int claim_swapfile(struct swap_info_struct *p, struct inode *inode) +{ + int error; + + if (S_ISBLK(inode->i_mode)) { + p->bdev = blkdev_get_by_dev(inode->i_rdev, + FMODE_READ | FMODE_WRITE | FMODE_EXCL, p); + if (IS_ERR(p->bdev)) { + error = PTR_ERR(p->bdev); + p->bdev = NULL; + return error; + } + p->old_block_size = block_size(p->bdev); + error = set_blocksize(p->bdev, PAGE_SIZE); + if (error < 0) + return error; + /* + * Zoned block devices contain zones that have a sequential + * write only restriction. Hence zoned block devices are not + * suitable for swapping. Disallow them here. + */ + if (blk_queue_is_zoned(p->bdev->bd_disk->queue)) + return -EINVAL; + p->flags |= SWP_BLKDEV; + } else if (S_ISREG(inode->i_mode)) { + p->bdev = inode->i_sb->s_bdev; + } + + return 0; +} + + +/* + * Find out how many pages are allowed for a single swap device. There + * are two limiting factors: + * 1) the number of bits for the swap offset in the swp_entry_t type, and + * 2) the number of bits in the swap pte, as defined by the different + * architectures. + * + * In order to find the largest possible bit mask, a swap entry with + * swap type 0 and swap offset ~0UL is created, encoded to a swap pte, + * decoded to a swp_entry_t again, and finally the swap offset is + * extracted. + * + * This will mask all the bits from the initial ~0UL mask that can't + * be encoded in either the swp_entry_t or the architecture definition + * of a swap pte. + */ +unsigned long generic_max_swapfile_size(void) +{ + return swp_offset(pte_to_swp_entry( + swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1; +} + +/* Can be overridden by an architecture for additional checks. */ +__weak unsigned long max_swapfile_size(void) +{ + return generic_max_swapfile_size(); +} + +static unsigned long read_swap_header(struct swap_info_struct *p, + union swap_header *swap_header, + struct inode *inode) +{ + int i; + unsigned long maxpages; + unsigned long swapfilepages; + unsigned long last_page; + + if (memcmp("SWAPSPACE2", swap_header->magic.magic, 10)) { + pr_err("Unable to find swap-space signature\n"); + return 0; + } + + /* swap partition endianess hack... */ + if (swab32(swap_header->info.version) == 1) { + swab32s(&swap_header->info.version); + swab32s(&swap_header->info.last_page); + swab32s(&swap_header->info.nr_badpages); + if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) + return 0; + for (i = 0; i < swap_header->info.nr_badpages; i++) + swab32s(&swap_header->info.badpages[i]); + } + /* Check the swap header's sub-version */ + if (swap_header->info.version != 1) { + pr_warn("Unable to handle swap header version %d\n", + swap_header->info.version); + return 0; + } + + p->lowest_bit = 1; + p->cluster_next = 1; + p->cluster_nr = 0; + + maxpages = max_swapfile_size(); + last_page = swap_header->info.last_page; + if (!last_page) { + pr_warn("Empty swap-file\n"); + return 0; + } + if (last_page > maxpages) { + pr_warn("Truncating oversized swap area, only using %luk out of %luk\n", + maxpages << (PAGE_SHIFT - 10), + last_page << (PAGE_SHIFT - 10)); + } + if (maxpages > last_page) { + maxpages = last_page + 1; + /* p->max is an unsigned int: don't overflow it */ + if ((unsigned int)maxpages == 0) + maxpages = UINT_MAX; + } + p->highest_bit = maxpages - 1; + + if (!maxpages) + return 0; + swapfilepages = i_size_read(inode) >> PAGE_SHIFT; + if (swapfilepages && maxpages > swapfilepages) { + pr_warn("Swap area shorter than signature indicates\n"); + return 0; + } + if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode)) + return 0; + if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) + return 0; + + return maxpages; +} + +#define SWAP_CLUSTER_INFO_COLS \ + DIV_ROUND_UP(L1_CACHE_BYTES, sizeof(struct swap_cluster_info)) +#define SWAP_CLUSTER_SPACE_COLS \ + DIV_ROUND_UP(SWAP_ADDRESS_SPACE_PAGES, SWAPFILE_CLUSTER) +#define SWAP_CLUSTER_COLS \ + max_t(unsigned int, SWAP_CLUSTER_INFO_COLS, SWAP_CLUSTER_SPACE_COLS) + +static int setup_swap_map_and_extents(struct swap_info_struct *p, + union swap_header *swap_header, + unsigned char *swap_map, + struct swap_cluster_info *cluster_info, + unsigned long maxpages, + sector_t *span) +{ + unsigned int j, k; + unsigned int nr_good_pages; + int nr_extents; + unsigned long nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); + unsigned long col = p->cluster_next / SWAPFILE_CLUSTER % SWAP_CLUSTER_COLS; + unsigned long i, idx; + + nr_good_pages = maxpages - 1; /* omit header page */ + + cluster_list_init(&p->free_clusters); + cluster_list_init(&p->discard_clusters); + + for (i = 0; i < swap_header->info.nr_badpages; i++) { + unsigned int page_nr = swap_header->info.badpages[i]; + if (page_nr == 0 || page_nr > swap_header->info.last_page) + return -EINVAL; + if (page_nr < maxpages) { + swap_map[page_nr] = SWAP_MAP_BAD; + nr_good_pages--; + /* + * Haven't marked the cluster free yet, no list + * operation involved + */ + inc_cluster_info_page(p, cluster_info, page_nr); + } + } + + /* Haven't marked the cluster free yet, no list operation involved */ + for (i = maxpages; i < round_up(maxpages, SWAPFILE_CLUSTER); i++) + inc_cluster_info_page(p, cluster_info, i); + + if (nr_good_pages) { + swap_map[0] = SWAP_MAP_BAD; + /* + * Not mark the cluster free yet, no list + * operation involved + */ + inc_cluster_info_page(p, cluster_info, 0); + p->max = maxpages; + p->pages = nr_good_pages; + nr_extents = setup_swap_extents(p, span); + if (nr_extents < 0) + return nr_extents; + nr_good_pages = p->pages; + } + if (!nr_good_pages) { + pr_warn("Empty swap-file\n"); + return -EINVAL; + } + + if (!cluster_info) + return nr_extents; + + + /* + * Reduce false cache line sharing between cluster_info and + * sharing same address space. + */ + for (k = 0; k < SWAP_CLUSTER_COLS; k++) { + j = (k + col) % SWAP_CLUSTER_COLS; + for (i = 0; i < DIV_ROUND_UP(nr_clusters, SWAP_CLUSTER_COLS); i++) { + idx = i * SWAP_CLUSTER_COLS + j; + if (idx >= nr_clusters) + continue; + if (cluster_count(&cluster_info[idx])) + continue; + cluster_set_flag(&cluster_info[idx], CLUSTER_FLAG_FREE); + cluster_list_add_tail(&p->free_clusters, cluster_info, + idx); + } + } + return nr_extents; +} + +/* + * Helper to sys_swapon determining if a given swap + * backing device queue supports DISCARD operations. + */ +static bool swap_discardable(struct swap_info_struct *si) +{ + struct request_queue *q = bdev_get_queue(si->bdev); + + if (!q || !blk_queue_discard(q)) + return false; + + return true; +} + +SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) +{ + struct swap_info_struct *p; + struct filename *name; + struct file *swap_file = NULL; + struct address_space *mapping; + int prio; + int error; + union swap_header *swap_header; + int nr_extents; + sector_t span; + unsigned long maxpages; + unsigned char *swap_map = NULL; + struct swap_cluster_info *cluster_info = NULL; + unsigned long *frontswap_map = NULL; + struct page *page = NULL; + struct inode *inode = NULL; + bool inced_nr_rotate_swap = false; + + if (swap_flags & ~SWAP_FLAGS_VALID) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (!swap_avail_heads) + return -ENOMEM; + + p = alloc_swap_info(); + if (IS_ERR(p)) + return PTR_ERR(p); + + INIT_WORK(&p->discard_work, swap_discard_work); + + name = getname(specialfile); + if (IS_ERR(name)) { + error = PTR_ERR(name); + name = NULL; + goto bad_swap; + } + swap_file = file_open_name(name, O_RDWR|O_LARGEFILE, 0); + if (IS_ERR(swap_file)) { + error = PTR_ERR(swap_file); + swap_file = NULL; + goto bad_swap; + } + + p->swap_file = swap_file; + mapping = swap_file->f_mapping; + inode = mapping->host; + + error = claim_swapfile(p, inode); + if (unlikely(error)) + goto bad_swap; + + inode_lock(inode); + if (IS_SWAPFILE(inode)) { + error = -EBUSY; + goto bad_swap_unlock_inode; + } + + /* + * Read the swap header. + */ + if (!mapping->a_ops->readpage) { + error = -EINVAL; + goto bad_swap_unlock_inode; + } + page = read_mapping_page(mapping, 0, swap_file); + if (IS_ERR(page)) { + error = PTR_ERR(page); + goto bad_swap_unlock_inode; + } + swap_header = kmap(page); + + maxpages = read_swap_header(p, swap_header, inode); + if (unlikely(!maxpages)) { + error = -EINVAL; + goto bad_swap_unlock_inode; + } + + /* OK, set up the swap map and apply the bad block list */ + swap_map = vzalloc(maxpages); + if (!swap_map) { + error = -ENOMEM; + goto bad_swap_unlock_inode; + } + + if (p->bdev && blk_queue_stable_writes(p->bdev->bd_disk->queue)) + p->flags |= SWP_STABLE_WRITES; + + if (p->bdev && p->bdev->bd_disk->fops->rw_page) + p->flags |= SWP_SYNCHRONOUS_IO; + + if (p->bdev && blk_queue_nonrot(bdev_get_queue(p->bdev))) { + int cpu; + unsigned long ci, nr_cluster; + + p->flags |= SWP_SOLIDSTATE; + p->cluster_next_cpu = alloc_percpu(unsigned int); + if (!p->cluster_next_cpu) { + error = -ENOMEM; + goto bad_swap_unlock_inode; + } + /* + * select a random position to start with to help wear leveling + * SSD + */ + for_each_possible_cpu(cpu) { + per_cpu(*p->cluster_next_cpu, cpu) = + 1 + prandom_u32_max(p->highest_bit); + } + nr_cluster = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); + + cluster_info = kvcalloc(nr_cluster, sizeof(*cluster_info), + GFP_KERNEL); + if (!cluster_info) { + error = -ENOMEM; + goto bad_swap_unlock_inode; + } + + for (ci = 0; ci < nr_cluster; ci++) + spin_lock_init(&((cluster_info + ci)->lock)); + + p->percpu_cluster = alloc_percpu(struct percpu_cluster); + if (!p->percpu_cluster) { + error = -ENOMEM; + goto bad_swap_unlock_inode; + } + for_each_possible_cpu(cpu) { + struct percpu_cluster *cluster; + cluster = per_cpu_ptr(p->percpu_cluster, cpu); + cluster_set_null(&cluster->index); + } + } else { + atomic_inc(&nr_rotate_swap); + inced_nr_rotate_swap = true; + } + + error = swap_cgroup_swapon(p->type, maxpages); + if (error) + goto bad_swap_unlock_inode; + + nr_extents = setup_swap_map_and_extents(p, swap_header, swap_map, + cluster_info, maxpages, &span); + if (unlikely(nr_extents < 0)) { + error = nr_extents; + goto bad_swap_unlock_inode; + } + /* frontswap enabled? set up bit-per-page map for frontswap */ + if (IS_ENABLED(CONFIG_FRONTSWAP)) + frontswap_map = kvcalloc(BITS_TO_LONGS(maxpages), + sizeof(long), + GFP_KERNEL); + + if (p->bdev &&(swap_flags & SWAP_FLAG_DISCARD) && swap_discardable(p)) { + /* + * When discard is enabled for swap with no particular + * policy flagged, we set all swap discard flags here in + * order to sustain backward compatibility with older + * swapon(8) releases. + */ + p->flags |= (SWP_DISCARDABLE | SWP_AREA_DISCARD | + SWP_PAGE_DISCARD); + + /* + * By flagging sys_swapon, a sysadmin can tell us to + * either do single-time area discards only, or to just + * perform discards for released swap page-clusters. + * Now it's time to adjust the p->flags accordingly. + */ + if (swap_flags & SWAP_FLAG_DISCARD_ONCE) + p->flags &= ~SWP_PAGE_DISCARD; + else if (swap_flags & SWAP_FLAG_DISCARD_PAGES) + p->flags &= ~SWP_AREA_DISCARD; + + /* issue a swapon-time discard if it's still required */ + if (p->flags & SWP_AREA_DISCARD) { + int err = discard_swap(p); + if (unlikely(err)) + pr_err("swapon: discard_swap(%p): %d\n", + p, err); + } + } + + error = init_swap_address_space(p->type, maxpages); + if (error) + goto bad_swap_unlock_inode; + + /* + * Flush any pending IO and dirty mappings before we start using this + * swap device. + */ + inode->i_flags |= S_SWAPFILE; + error = inode_drain_writes(inode); + if (error) { + inode->i_flags &= ~S_SWAPFILE; + goto free_swap_address_space; + } + + mutex_lock(&swapon_mutex); + prio = -1; + if (swap_flags & SWAP_FLAG_PREFER) + prio = + (swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT; + enable_swap_info(p, prio, swap_map, cluster_info, frontswap_map); + + pr_info("Adding %uk swap on %s. Priority:%d extents:%d across:%lluk %s%s%s%s%s\n", + p->pages<<(PAGE_SHIFT-10), name->name, p->prio, + nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10), + (p->flags & SWP_SOLIDSTATE) ? "SS" : "", + (p->flags & SWP_DISCARDABLE) ? "D" : "", + (p->flags & SWP_AREA_DISCARD) ? "s" : "", + (p->flags & SWP_PAGE_DISCARD) ? "c" : "", + (frontswap_map) ? "FS" : ""); + + mutex_unlock(&swapon_mutex); + atomic_inc(&proc_poll_event); + wake_up_interruptible(&proc_poll_wait); + + error = 0; + goto out; +free_swap_address_space: + exit_swap_address_space(p->type); +bad_swap_unlock_inode: + inode_unlock(inode); +bad_swap: + free_percpu(p->percpu_cluster); + p->percpu_cluster = NULL; + free_percpu(p->cluster_next_cpu); + p->cluster_next_cpu = NULL; + if (inode && S_ISBLK(inode->i_mode) && p->bdev) { + set_blocksize(p->bdev, p->old_block_size); + blkdev_put(p->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); + } + inode = NULL; + destroy_swap_extents(p); + swap_cgroup_swapoff(p->type); + spin_lock(&swap_lock); + p->swap_file = NULL; + p->flags = 0; + spin_unlock(&swap_lock); + vfree(swap_map); + kvfree(cluster_info); + kvfree(frontswap_map); + if (inced_nr_rotate_swap) + atomic_dec(&nr_rotate_swap); + if (swap_file) + filp_close(swap_file, NULL); +out: + if (page && !IS_ERR(page)) { + kunmap(page); + put_page(page); + } + if (name) + putname(name); + if (inode) + inode_unlock(inode); + if (!error) + enable_swap_slots_cache(); + return error; +} + +void si_swapinfo(struct sysinfo *val) +{ + unsigned int type; + unsigned long nr_to_be_unused = 0; + + spin_lock(&swap_lock); + for (type = 0; type < nr_swapfiles; type++) { + struct swap_info_struct *si = swap_info[type]; + + if ((si->flags & SWP_USED) && !(si->flags & SWP_WRITEOK)) + nr_to_be_unused += si->inuse_pages; + } + val->freeswap = atomic_long_read(&nr_swap_pages) + nr_to_be_unused; + val->totalswap = total_swap_pages + nr_to_be_unused; + spin_unlock(&swap_lock); +} + +/* + * Verify that a swap entry is valid and increment its swap map count. + * + * Returns error code in following case. + * - success -> 0 + * - swp_entry is invalid -> EINVAL + * - swp_entry is migration entry -> EINVAL + * - swap-cache reference is requested but there is already one. -> EEXIST + * - swap-cache reference is requested but the entry is not used. -> ENOENT + * - swap-mapped reference requested but needs continued swap count. -> ENOMEM + */ +static int __swap_duplicate(swp_entry_t entry, unsigned char usage) +{ + struct swap_info_struct *p; + struct swap_cluster_info *ci; + unsigned long offset; + unsigned char count; + unsigned char has_cache; + int err = -EINVAL; + + p = get_swap_device(entry); + if (!p) + goto out; + + offset = swp_offset(entry); + ci = lock_cluster_or_swap_info(p, offset); + + count = p->swap_map[offset]; + + /* + * swapin_readahead() doesn't check if a swap entry is valid, so the + * swap entry could be SWAP_MAP_BAD. Check here with lock held. + */ + if (unlikely(swap_count(count) == SWAP_MAP_BAD)) { + err = -ENOENT; + goto unlock_out; + } + + has_cache = count & SWAP_HAS_CACHE; + count &= ~SWAP_HAS_CACHE; + err = 0; + + if (usage == SWAP_HAS_CACHE) { + + /* set SWAP_HAS_CACHE if there is no cache and entry is used */ + if (!has_cache && count) + has_cache = SWAP_HAS_CACHE; + else if (has_cache) /* someone else added cache */ + err = -EEXIST; + else /* no users remaining */ + err = -ENOENT; + + } else if (count || has_cache) { + + if ((count & ~COUNT_CONTINUED) < SWAP_MAP_MAX) + count += usage; + else if ((count & ~COUNT_CONTINUED) > SWAP_MAP_MAX) + err = -EINVAL; + else if (swap_count_continued(p, offset, count)) + count = COUNT_CONTINUED; + else + err = -ENOMEM; + } else + err = -ENOENT; /* unused swap entry */ + + WRITE_ONCE(p->swap_map[offset], count | has_cache); + +unlock_out: + unlock_cluster_or_swap_info(p, ci); +out: + if (p) + put_swap_device(p); + return err; +} + +/* + * Help swapoff by noting that swap entry belongs to shmem/tmpfs + * (in which case its reference count is never incremented). + */ +void swap_shmem_alloc(swp_entry_t entry) +{ + __swap_duplicate(entry, SWAP_MAP_SHMEM); +} + +/* + * Increase reference count of swap entry by 1. + * Returns 0 for success, or -ENOMEM if a swap_count_continuation is required + * but could not be atomically allocated. Returns 0, just as if it succeeded, + * if __swap_duplicate() fails for another reason (-EINVAL or -ENOENT), which + * might occur if a page table entry has got corrupted. + */ +int swap_duplicate(swp_entry_t entry) +{ + int err = 0; + + while (!err && __swap_duplicate(entry, 1) == -ENOMEM) + err = add_swap_count_continuation(entry, GFP_ATOMIC); + return err; +} + +/* + * @entry: swap entry for which we allocate swap cache. + * + * Called when allocating swap cache for existing swap entry, + * This can return error codes. Returns 0 at success. + * -EEXIST means there is a swap cache. + * Note: return code is different from swap_duplicate(). + */ +int swapcache_prepare(swp_entry_t entry) +{ + return __swap_duplicate(entry, SWAP_HAS_CACHE); +} + +struct swap_info_struct *swp_swap_info(swp_entry_t entry) +{ + return swap_type_to_swap_info(swp_type(entry)); +} + +struct swap_info_struct *page_swap_info(struct page *page) +{ + swp_entry_t entry = { .val = page_private(page) }; + return swp_swap_info(entry); +} + +/* + * out-of-line __page_file_ methods to avoid include hell. + */ +struct address_space *__page_file_mapping(struct page *page) +{ + return page_swap_info(page)->swap_file->f_mapping; +} +EXPORT_SYMBOL_GPL(__page_file_mapping); + +pgoff_t __page_file_index(struct page *page) +{ + swp_entry_t swap = { .val = page_private(page) }; + return swp_offset(swap); +} +EXPORT_SYMBOL_GPL(__page_file_index); + +/* + * add_swap_count_continuation - called when a swap count is duplicated + * beyond SWAP_MAP_MAX, it allocates a new page and links that to the entry's + * page of the original vmalloc'ed swap_map, to hold the continuation count + * (for that entry and for its neighbouring PAGE_SIZE swap entries). Called + * again when count is duplicated beyond SWAP_MAP_MAX * SWAP_CONT_MAX, etc. + * + * These continuation pages are seldom referenced: the common paths all work + * on the original swap_map, only referring to a continuation page when the + * low "digit" of a count is incremented or decremented through SWAP_MAP_MAX. + * + * add_swap_count_continuation(, GFP_ATOMIC) can be called while holding + * page table locks; if it fails, add_swap_count_continuation(, GFP_KERNEL) + * can be called after dropping locks. + */ +int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) +{ + struct swap_info_struct *si; + struct swap_cluster_info *ci; + struct page *head; + struct page *page; + struct page *list_page; + pgoff_t offset; + unsigned char count; + int ret = 0; + + /* + * When debugging, it's easier to use __GFP_ZERO here; but it's better + * for latency not to zero a page while GFP_ATOMIC and holding locks. + */ + page = alloc_page(gfp_mask | __GFP_HIGHMEM); + + si = get_swap_device(entry); + if (!si) { + /* + * An acceptable race has occurred since the failing + * __swap_duplicate(): the swap device may be swapoff + */ + goto outer; + } + spin_lock(&si->lock); + + offset = swp_offset(entry); + + ci = lock_cluster(si, offset); + + count = si->swap_map[offset] & ~SWAP_HAS_CACHE; + + if ((count & ~COUNT_CONTINUED) != SWAP_MAP_MAX) { + /* + * The higher the swap count, the more likely it is that tasks + * will race to add swap count continuation: we need to avoid + * over-provisioning. + */ + goto out; + } + + if (!page) { + ret = -ENOMEM; + goto out; + } + + /* + * We are fortunate that although vmalloc_to_page uses pte_offset_map, + * no architecture is using highmem pages for kernel page tables: so it + * will not corrupt the GFP_ATOMIC caller's atomic page table kmaps. + */ + head = vmalloc_to_page(si->swap_map + offset); + offset &= ~PAGE_MASK; + + spin_lock(&si->cont_lock); + /* + * Page allocation does not initialize the page's lru field, + * but it does always reset its private field. + */ + if (!page_private(head)) { + BUG_ON(count & COUNT_CONTINUED); + INIT_LIST_HEAD(&head->lru); + set_page_private(head, SWP_CONTINUED); + si->flags |= SWP_CONTINUED; + } + + list_for_each_entry(list_page, &head->lru, lru) { + unsigned char *map; + + /* + * If the previous map said no continuation, but we've found + * a continuation page, free our allocation and use this one. + */ + if (!(count & COUNT_CONTINUED)) + goto out_unlock_cont; + + map = kmap_atomic(list_page) + offset; + count = *map; + kunmap_atomic(map); + + /* + * If this continuation count now has some space in it, + * free our allocation and use this one. + */ + if ((count & ~COUNT_CONTINUED) != SWAP_CONT_MAX) + goto out_unlock_cont; + } + + list_add_tail(&page->lru, &head->lru); + page = NULL; /* now it's attached, don't free it */ +out_unlock_cont: + spin_unlock(&si->cont_lock); +out: + unlock_cluster(ci); + spin_unlock(&si->lock); + put_swap_device(si); +outer: + if (page) + __free_page(page); + return ret; +} + +/* + * swap_count_continued - when the original swap_map count is incremented + * from SWAP_MAP_MAX, check if there is already a continuation page to carry + * into, carry if so, or else fail until a new continuation page is allocated; + * when the original swap_map count is decremented from 0 with continuation, + * borrow from the continuation and report whether it still holds more. + * Called while __swap_duplicate() or swap_entry_free() holds swap or cluster + * lock. + */ +static bool swap_count_continued(struct swap_info_struct *si, + pgoff_t offset, unsigned char count) +{ + struct page *head; + struct page *page; + unsigned char *map; + bool ret; + + head = vmalloc_to_page(si->swap_map + offset); + if (page_private(head) != SWP_CONTINUED) { + BUG_ON(count & COUNT_CONTINUED); + return false; /* need to add count continuation */ + } + + spin_lock(&si->cont_lock); + offset &= ~PAGE_MASK; + page = list_next_entry(head, lru); + map = kmap_atomic(page) + offset; + + if (count == SWAP_MAP_MAX) /* initial increment from swap_map */ + goto init_map; /* jump over SWAP_CONT_MAX checks */ + + if (count == (SWAP_MAP_MAX | COUNT_CONTINUED)) { /* incrementing */ + /* + * Think of how you add 1 to 999 + */ + while (*map == (SWAP_CONT_MAX | COUNT_CONTINUED)) { + kunmap_atomic(map); + page = list_next_entry(page, lru); + BUG_ON(page == head); + map = kmap_atomic(page) + offset; + } + if (*map == SWAP_CONT_MAX) { + kunmap_atomic(map); + page = list_next_entry(page, lru); + if (page == head) { + ret = false; /* add count continuation */ + goto out; + } + map = kmap_atomic(page) + offset; +init_map: *map = 0; /* we didn't zero the page */ + } + *map += 1; + kunmap_atomic(map); + while ((page = list_prev_entry(page, lru)) != head) { + map = kmap_atomic(page) + offset; + *map = COUNT_CONTINUED; + kunmap_atomic(map); + } + ret = true; /* incremented */ + + } else { /* decrementing */ + /* + * Think of how you subtract 1 from 1000 + */ + BUG_ON(count != COUNT_CONTINUED); + while (*map == COUNT_CONTINUED) { + kunmap_atomic(map); + page = list_next_entry(page, lru); + BUG_ON(page == head); + map = kmap_atomic(page) + offset; + } + BUG_ON(*map == 0); + *map -= 1; + if (*map == 0) + count = 0; + kunmap_atomic(map); + while ((page = list_prev_entry(page, lru)) != head) { + map = kmap_atomic(page) + offset; + *map = SWAP_CONT_MAX | count; + count = COUNT_CONTINUED; + kunmap_atomic(map); + } + ret = count == COUNT_CONTINUED; + } +out: + spin_unlock(&si->cont_lock); + return ret; +} + +/* + * free_swap_count_continuations - swapoff free all the continuation pages + * appended to the swap_map, after swap_map is quiesced, before vfree'ing it. + */ +static void free_swap_count_continuations(struct swap_info_struct *si) +{ + pgoff_t offset; + + for (offset = 0; offset < si->max; offset += PAGE_SIZE) { + struct page *head; + head = vmalloc_to_page(si->swap_map + offset); + if (page_private(head)) { + struct page *page, *next; + + list_for_each_entry_safe(page, next, &head->lru, lru) { + list_del(&page->lru); + __free_page(page); + } + } + } +} + +#if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) +void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) +{ + struct swap_info_struct *si, *next; + int nid = page_to_nid(page); + + if (!(gfp_mask & __GFP_IO)) + return; + + if (!blk_cgroup_congested()) + return; + + /* + * We've already scheduled a throttle, avoid taking the global swap + * lock. + */ + if (current->throttle_queue) + return; + + spin_lock(&swap_avail_lock); + plist_for_each_entry_safe(si, next, &swap_avail_heads[nid], + avail_lists[nid]) { + if (si->bdev) { + blkcg_schedule_throttle(bdev_get_queue(si->bdev), true); + break; + } + } + spin_unlock(&swap_avail_lock); +} +#endif + +static int __init swapfile_init(void) +{ + int nid; + + swap_avail_heads = kmalloc_array(nr_node_ids, sizeof(struct plist_head), + GFP_KERNEL); + if (!swap_avail_heads) { + pr_emerg("Not enough memory for swap heads, swap is disabled\n"); + return -ENOMEM; + } + + for_each_node(nid) + plist_head_init(&swap_avail_heads[nid]); + + return 0; +} +subsys_initcall(swapfile_init); diff --git a/mm/truncate.c b/mm/truncate.c new file mode 100644 index 000000000..8914ca4ce --- /dev/null +++ b/mm/truncate.c @@ -0,0 +1,950 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * mm/truncate.c - code for taking down pages from address_spaces + * + * Copyright (C) 2002, Linus Torvalds + * + * 10Sep2002 Andrew Morton + * Initial version. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include /* grr. try_to_release_page, + do_invalidatepage */ +#include +#include +#include +#include "internal.h" + +/* + * Regular page slots are stabilized by the page lock even without the tree + * itself locked. These unlocked entries need verification under the tree + * lock. + */ +static inline void __clear_shadow_entry(struct address_space *mapping, + pgoff_t index, void *entry) +{ + XA_STATE(xas, &mapping->i_pages, index); + + xas_set_update(&xas, workingset_update_node); + if (xas_load(&xas) != entry) + return; + xas_store(&xas, NULL); + mapping->nrexceptional--; +} + +static void clear_shadow_entry(struct address_space *mapping, pgoff_t index, + void *entry) +{ + xa_lock_irq(&mapping->i_pages); + __clear_shadow_entry(mapping, index, entry); + xa_unlock_irq(&mapping->i_pages); +} + +/* + * Unconditionally remove exceptional entries. Usually called from truncate + * path. Note that the pagevec may be altered by this function by removing + * exceptional entries similar to what pagevec_remove_exceptionals does. + */ +static void truncate_exceptional_pvec_entries(struct address_space *mapping, + struct pagevec *pvec, pgoff_t *indices, + pgoff_t end) +{ + int i, j; + bool dax, lock; + + /* Handled by shmem itself */ + if (shmem_mapping(mapping)) + return; + + for (j = 0; j < pagevec_count(pvec); j++) + if (xa_is_value(pvec->pages[j])) + break; + + if (j == pagevec_count(pvec)) + return; + + dax = dax_mapping(mapping); + lock = !dax && indices[j] < end; + if (lock) + xa_lock_irq(&mapping->i_pages); + + for (i = j; i < pagevec_count(pvec); i++) { + struct page *page = pvec->pages[i]; + pgoff_t index = indices[i]; + + if (!xa_is_value(page)) { + pvec->pages[j++] = page; + continue; + } + + if (index >= end) + continue; + + if (unlikely(dax)) { + dax_delete_mapping_entry(mapping, index); + continue; + } + + __clear_shadow_entry(mapping, index, page); + } + + if (lock) + xa_unlock_irq(&mapping->i_pages); + pvec->nr = j; +} + +/* + * Invalidate exceptional entry if easily possible. This handles exceptional + * entries for invalidate_inode_pages(). + */ +static int invalidate_exceptional_entry(struct address_space *mapping, + pgoff_t index, void *entry) +{ + /* Handled by shmem itself, or for DAX we do nothing. */ + if (shmem_mapping(mapping) || dax_mapping(mapping)) + return 1; + clear_shadow_entry(mapping, index, entry); + return 1; +} + +/* + * Invalidate exceptional entry if clean. This handles exceptional entries for + * invalidate_inode_pages2() so for DAX it evicts only clean entries. + */ +static int invalidate_exceptional_entry2(struct address_space *mapping, + pgoff_t index, void *entry) +{ + /* Handled by shmem itself */ + if (shmem_mapping(mapping)) + return 1; + if (dax_mapping(mapping)) + return dax_invalidate_mapping_entry_sync(mapping, index); + clear_shadow_entry(mapping, index, entry); + return 1; +} + +/** + * do_invalidatepage - invalidate part or all of a page + * @page: the page which is affected + * @offset: start of the range to invalidate + * @length: length of the range to invalidate + * + * do_invalidatepage() is called when all or part of the page has become + * invalidated by a truncate operation. + * + * do_invalidatepage() does not have to release all buffers, but it must + * ensure that no dirty buffer is left outside @offset and that no I/O + * is underway against any of the blocks which are outside the truncation + * point. Because the caller is about to free (and possibly reuse) those + * blocks on-disk. + */ +void do_invalidatepage(struct page *page, unsigned int offset, + unsigned int length) +{ + void (*invalidatepage)(struct page *, unsigned int, unsigned int); + + invalidatepage = page->mapping->a_ops->invalidatepage; +#ifdef CONFIG_BLOCK + if (!invalidatepage) + invalidatepage = block_invalidatepage; +#endif + if (invalidatepage) + (*invalidatepage)(page, offset, length); +} + +/* + * If truncate cannot remove the fs-private metadata from the page, the page + * becomes orphaned. It will be left on the LRU and may even be mapped into + * user pagetables if we're racing with filemap_fault(). + * + * We need to bail out if page->mapping is no longer equal to the original + * mapping. This happens a) when the VM reclaimed the page while we waited on + * its lock, b) when a concurrent invalidate_mapping_pages got there first and + * c) when tmpfs swizzles a page between a tmpfs inode and swapper_space. + */ +static void truncate_cleanup_page(struct page *page) +{ + if (page_mapped(page)) + unmap_mapping_page(page); + + if (page_has_private(page)) + do_invalidatepage(page, 0, thp_size(page)); + + /* + * Some filesystems seem to re-dirty the page even after + * the VM has canceled the dirty bit (eg ext3 journaling). + * Hence dirty accounting check is placed after invalidation. + */ + cancel_dirty_page(page); + ClearPageMappedToDisk(page); +} + +/* + * This is for invalidate_mapping_pages(). That function can be called at + * any time, and is not supposed to throw away dirty pages. But pages can + * be marked dirty at any time too, so use remove_mapping which safely + * discards clean, unused pages. + * + * Returns non-zero if the page was successfully invalidated. + */ +static int +invalidate_complete_page(struct address_space *mapping, struct page *page) +{ + int ret; + + if (page->mapping != mapping) + return 0; + + if (page_has_private(page) && !try_to_release_page(page, 0)) + return 0; + + ret = remove_mapping(mapping, page); + + return ret; +} + +int truncate_inode_page(struct address_space *mapping, struct page *page) +{ + VM_BUG_ON_PAGE(PageTail(page), page); + + if (page->mapping != mapping) + return -EIO; + + truncate_cleanup_page(page); + delete_from_page_cache(page); + return 0; +} + +/* + * Used to get rid of pages on hardware memory corruption. + */ +int generic_error_remove_page(struct address_space *mapping, struct page *page) +{ + if (!mapping) + return -EINVAL; + /* + * Only punch for normal data pages for now. + * Handling other types like directories would need more auditing. + */ + if (!S_ISREG(mapping->host->i_mode)) + return -EIO; + return truncate_inode_page(mapping, page); +} +EXPORT_SYMBOL(generic_error_remove_page); + +/* + * Safely invalidate one page from its pagecache mapping. + * It only drops clean, unused pages. The page must be locked. + * + * Returns 1 if the page is successfully invalidated, otherwise 0. + */ +int invalidate_inode_page(struct page *page) +{ + struct address_space *mapping = page_mapping(page); + if (!mapping) + return 0; + if (PageDirty(page) || PageWriteback(page)) + return 0; + if (page_mapped(page)) + return 0; + return invalidate_complete_page(mapping, page); +} + +/** + * truncate_inode_pages_range - truncate range of pages specified by start & end byte offsets + * @mapping: mapping to truncate + * @lstart: offset from which to truncate + * @lend: offset to which to truncate (inclusive) + * + * Truncate the page cache, removing the pages that are between + * specified offsets (and zeroing out partial pages + * if lstart or lend + 1 is not page aligned). + * + * Truncate takes two passes - the first pass is nonblocking. It will not + * block on page locks and it will not block on writeback. The second pass + * will wait. This is to prevent as much IO as possible in the affected region. + * The first pass will remove most pages, so the search cost of the second pass + * is low. + * + * We pass down the cache-hot hint to the page freeing code. Even if the + * mapping is large, it is probably the case that the final pages are the most + * recently touched, and freeing happens in ascending file offset order. + * + * Note that since ->invalidatepage() accepts range to invalidate + * truncate_inode_pages_range is able to handle cases where lend + 1 is not + * page aligned properly. + */ +void truncate_inode_pages_range(struct address_space *mapping, + loff_t lstart, loff_t lend) +{ + pgoff_t start; /* inclusive */ + pgoff_t end; /* exclusive */ + unsigned int partial_start; /* inclusive */ + unsigned int partial_end; /* exclusive */ + struct pagevec pvec; + pgoff_t indices[PAGEVEC_SIZE]; + pgoff_t index; + int i; + + if (mapping->nrpages == 0 && mapping->nrexceptional == 0) + goto out; + + /* Offsets within partial pages */ + partial_start = lstart & (PAGE_SIZE - 1); + partial_end = (lend + 1) & (PAGE_SIZE - 1); + + /* + * 'start' and 'end' always covers the range of pages to be fully + * truncated. Partial pages are covered with 'partial_start' at the + * start of the range and 'partial_end' at the end of the range. + * Note that 'end' is exclusive while 'lend' is inclusive. + */ + start = (lstart + PAGE_SIZE - 1) >> PAGE_SHIFT; + if (lend == -1) + /* + * lend == -1 indicates end-of-file so we have to set 'end' + * to the highest possible pgoff_t and since the type is + * unsigned we're using -1. + */ + end = -1; + else + end = (lend + 1) >> PAGE_SHIFT; + + pagevec_init(&pvec); + index = start; + while (index < end && pagevec_lookup_entries(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE), + indices)) { + /* + * Pagevec array has exceptional entries and we may also fail + * to lock some pages. So we store pages that can be deleted + * in a new pagevec. + */ + struct pagevec locked_pvec; + + pagevec_init(&locked_pvec); + for (i = 0; i < pagevec_count(&pvec); i++) { + struct page *page = pvec.pages[i]; + + /* We rely upon deletion not changing page->index */ + index = indices[i]; + if (index >= end) + break; + + if (xa_is_value(page)) + continue; + + if (!trylock_page(page)) + continue; + WARN_ON(page_to_index(page) != index); + if (PageWriteback(page)) { + unlock_page(page); + continue; + } + if (page->mapping != mapping) { + unlock_page(page); + continue; + } + pagevec_add(&locked_pvec, page); + } + for (i = 0; i < pagevec_count(&locked_pvec); i++) + truncate_cleanup_page(locked_pvec.pages[i]); + delete_from_page_cache_batch(mapping, &locked_pvec); + for (i = 0; i < pagevec_count(&locked_pvec); i++) + unlock_page(locked_pvec.pages[i]); + truncate_exceptional_pvec_entries(mapping, &pvec, indices, end); + pagevec_release(&pvec); + cond_resched(); + index++; + } + if (partial_start) { + struct page *page = find_lock_page(mapping, start - 1); + if (page) { + unsigned int top = PAGE_SIZE; + if (start > end) { + /* Truncation within a single page */ + top = partial_end; + partial_end = 0; + } + wait_on_page_writeback(page); + zero_user_segment(page, partial_start, top); + cleancache_invalidate_page(mapping, page); + if (page_has_private(page)) + do_invalidatepage(page, partial_start, + top - partial_start); + unlock_page(page); + put_page(page); + } + } + if (partial_end) { + struct page *page = find_lock_page(mapping, end); + if (page) { + wait_on_page_writeback(page); + zero_user_segment(page, 0, partial_end); + cleancache_invalidate_page(mapping, page); + if (page_has_private(page)) + do_invalidatepage(page, 0, + partial_end); + unlock_page(page); + put_page(page); + } + } + /* + * If the truncation happened within a single page no pages + * will be released, just zeroed, so we can bail out now. + */ + if (start >= end) + goto out; + + index = start; + for ( ; ; ) { + cond_resched(); + if (!pagevec_lookup_entries(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE), indices)) { + /* If all gone from start onwards, we're done */ + if (index == start) + break; + /* Otherwise restart to make sure all gone */ + index = start; + continue; + } + if (index == start && indices[0] >= end) { + /* All gone out of hole to be punched, we're done */ + pagevec_remove_exceptionals(&pvec); + pagevec_release(&pvec); + break; + } + + for (i = 0; i < pagevec_count(&pvec); i++) { + struct page *page = pvec.pages[i]; + + /* We rely upon deletion not changing page->index */ + index = indices[i]; + if (index >= end) { + /* Restart punch to make sure all gone */ + index = start - 1; + break; + } + + if (xa_is_value(page)) + continue; + + lock_page(page); + WARN_ON(page_to_index(page) != index); + wait_on_page_writeback(page); + truncate_inode_page(mapping, page); + unlock_page(page); + } + truncate_exceptional_pvec_entries(mapping, &pvec, indices, end); + pagevec_release(&pvec); + index++; + } + +out: + cleancache_invalidate_inode(mapping); +} +EXPORT_SYMBOL(truncate_inode_pages_range); + +/** + * truncate_inode_pages - truncate *all* the pages from an offset + * @mapping: mapping to truncate + * @lstart: offset from which to truncate + * + * Called under (and serialised by) inode->i_mutex. + * + * Note: When this function returns, there can be a page in the process of + * deletion (inside __delete_from_page_cache()) in the specified range. Thus + * mapping->nrpages can be non-zero when this function returns even after + * truncation of the whole mapping. + */ +void truncate_inode_pages(struct address_space *mapping, loff_t lstart) +{ + truncate_inode_pages_range(mapping, lstart, (loff_t)-1); +} +EXPORT_SYMBOL(truncate_inode_pages); + +/** + * truncate_inode_pages_final - truncate *all* pages before inode dies + * @mapping: mapping to truncate + * + * Called under (and serialized by) inode->i_mutex. + * + * Filesystems have to use this in the .evict_inode path to inform the + * VM that this is the final truncate and the inode is going away. + */ +void truncate_inode_pages_final(struct address_space *mapping) +{ + unsigned long nrexceptional; + unsigned long nrpages; + + /* + * Page reclaim can not participate in regular inode lifetime + * management (can't call iput()) and thus can race with the + * inode teardown. Tell it when the address space is exiting, + * so that it does not install eviction information after the + * final truncate has begun. + */ + mapping_set_exiting(mapping); + + /* + * When reclaim installs eviction entries, it increases + * nrexceptional first, then decreases nrpages. Make sure we see + * this in the right order or we might miss an entry. + */ + nrpages = mapping->nrpages; + smp_rmb(); + nrexceptional = mapping->nrexceptional; + + if (nrpages || nrexceptional) { + /* + * As truncation uses a lockless tree lookup, cycle + * the tree lock to make sure any ongoing tree + * modification that does not see AS_EXITING is + * completed before starting the final truncate. + */ + xa_lock_irq(&mapping->i_pages); + xa_unlock_irq(&mapping->i_pages); + } + + /* + * Cleancache needs notification even if there are no pages or shadow + * entries. + */ + truncate_inode_pages(mapping, 0); +} +EXPORT_SYMBOL(truncate_inode_pages_final); + +static unsigned long __invalidate_mapping_pages(struct address_space *mapping, + pgoff_t start, pgoff_t end, unsigned long *nr_pagevec) +{ + pgoff_t indices[PAGEVEC_SIZE]; + struct pagevec pvec; + pgoff_t index = start; + unsigned long ret; + unsigned long count = 0; + int i; + + pagevec_init(&pvec); + while (index <= end && pagevec_lookup_entries(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1, + indices)) { + for (i = 0; i < pagevec_count(&pvec); i++) { + struct page *page = pvec.pages[i]; + + /* We rely upon deletion not changing page->index */ + index = indices[i]; + if (index > end) + break; + + if (xa_is_value(page)) { + invalidate_exceptional_entry(mapping, index, + page); + continue; + } + + if (!trylock_page(page)) + continue; + + WARN_ON(page_to_index(page) != index); + + /* Middle of THP: skip */ + if (PageTransTail(page)) { + unlock_page(page); + continue; + } else if (PageTransHuge(page)) { + index += HPAGE_PMD_NR - 1; + i += HPAGE_PMD_NR - 1; + /* + * 'end' is in the middle of THP. Don't + * invalidate the page as the part outside of + * 'end' could be still useful. + */ + if (index > end) { + unlock_page(page); + continue; + } + + /* Take a pin outside pagevec */ + get_page(page); + + /* + * Drop extra pins before trying to invalidate + * the huge page. + */ + pagevec_remove_exceptionals(&pvec); + pagevec_release(&pvec); + } + + ret = invalidate_inode_page(page); + unlock_page(page); + /* + * Invalidation is a hint that the page is no longer + * of interest and try to speed up its reclaim. + */ + if (!ret) { + deactivate_file_page(page); + /* It is likely on the pagevec of a remote CPU */ + if (nr_pagevec) + (*nr_pagevec)++; + } + + if (PageTransHuge(page)) + put_page(page); + count += ret; + } + pagevec_remove_exceptionals(&pvec); + pagevec_release(&pvec); + cond_resched(); + index++; + } + return count; +} + +/** + * invalidate_mapping_pages - Invalidate all the unlocked pages of one inode + * @mapping: the address_space which holds the pages to invalidate + * @start: the offset 'from' which to invalidate + * @end: the offset 'to' which to invalidate (inclusive) + * + * This function only removes the unlocked pages, if you want to + * remove all the pages of one inode, you must call truncate_inode_pages. + * + * invalidate_mapping_pages() will not block on IO activity. It will not + * invalidate pages which are dirty, locked, under writeback or mapped into + * pagetables. + * + * Return: the number of the pages that were invalidated + */ +unsigned long invalidate_mapping_pages(struct address_space *mapping, + pgoff_t start, pgoff_t end) +{ + return __invalidate_mapping_pages(mapping, start, end, NULL); +} +EXPORT_SYMBOL(invalidate_mapping_pages); + +/** + * This helper is similar with the above one, except that it accounts for pages + * that are likely on a pagevec and count them in @nr_pagevec, which will used by + * the caller. + */ +void invalidate_mapping_pagevec(struct address_space *mapping, + pgoff_t start, pgoff_t end, unsigned long *nr_pagevec) +{ + __invalidate_mapping_pages(mapping, start, end, nr_pagevec); +} + +/* + * This is like invalidate_complete_page(), except it ignores the page's + * refcount. We do this because invalidate_inode_pages2() needs stronger + * invalidation guarantees, and cannot afford to leave pages behind because + * shrink_page_list() has a temp ref on them, or because they're transiently + * sitting in the lru_cache_add() pagevecs. + */ +static int +invalidate_complete_page2(struct address_space *mapping, struct page *page) +{ + unsigned long flags; + + if (page->mapping != mapping) + return 0; + + if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL)) + return 0; + + xa_lock_irqsave(&mapping->i_pages, flags); + if (PageDirty(page)) + goto failed; + + BUG_ON(page_has_private(page)); + __delete_from_page_cache(page, NULL); + xa_unlock_irqrestore(&mapping->i_pages, flags); + + if (mapping->a_ops->freepage) + mapping->a_ops->freepage(page); + + put_page(page); /* pagecache ref */ + return 1; +failed: + xa_unlock_irqrestore(&mapping->i_pages, flags); + return 0; +} + +static int do_launder_page(struct address_space *mapping, struct page *page) +{ + if (!PageDirty(page)) + return 0; + if (page->mapping != mapping || mapping->a_ops->launder_page == NULL) + return 0; + return mapping->a_ops->launder_page(page); +} + +/** + * invalidate_inode_pages2_range - remove range of pages from an address_space + * @mapping: the address_space + * @start: the page offset 'from' which to invalidate + * @end: the page offset 'to' which to invalidate (inclusive) + * + * Any pages which are found to be mapped into pagetables are unmapped prior to + * invalidation. + * + * Return: -EBUSY if any pages could not be invalidated. + */ +int invalidate_inode_pages2_range(struct address_space *mapping, + pgoff_t start, pgoff_t end) +{ + pgoff_t indices[PAGEVEC_SIZE]; + struct pagevec pvec; + pgoff_t index; + int i; + int ret = 0; + int ret2 = 0; + int did_range_unmap = 0; + + if (mapping->nrpages == 0 && mapping->nrexceptional == 0) + goto out; + + pagevec_init(&pvec); + index = start; + while (index <= end && pagevec_lookup_entries(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1, + indices)) { + for (i = 0; i < pagevec_count(&pvec); i++) { + struct page *page = pvec.pages[i]; + + /* We rely upon deletion not changing page->index */ + index = indices[i]; + if (index > end) + break; + + if (xa_is_value(page)) { + if (!invalidate_exceptional_entry2(mapping, + index, page)) + ret = -EBUSY; + continue; + } + + if (!did_range_unmap && page_mapped(page)) { + /* + * If page is mapped, before taking its lock, + * zap the rest of the file in one hit. + */ + unmap_mapping_pages(mapping, index, + (1 + end - index), false); + did_range_unmap = 1; + } + + lock_page(page); + WARN_ON(page_to_index(page) != index); + if (page->mapping != mapping) { + unlock_page(page); + continue; + } + wait_on_page_writeback(page); + + if (page_mapped(page)) + unmap_mapping_page(page); + BUG_ON(page_mapped(page)); + + ret2 = do_launder_page(mapping, page); + if (ret2 == 0) { + if (!invalidate_complete_page2(mapping, page)) + ret2 = -EBUSY; + } + if (ret2 < 0) + ret = ret2; + unlock_page(page); + } + pagevec_remove_exceptionals(&pvec); + pagevec_release(&pvec); + cond_resched(); + index++; + } + /* + * For DAX we invalidate page tables after invalidating page cache. We + * could invalidate page tables while invalidating each entry however + * that would be expensive. And doing range unmapping before doesn't + * work as we have no cheap way to find whether page cache entry didn't + * get remapped later. + */ + if (dax_mapping(mapping)) { + unmap_mapping_pages(mapping, start, end - start + 1, false); + } +out: + cleancache_invalidate_inode(mapping); + return ret; +} +EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range); + +/** + * invalidate_inode_pages2 - remove all pages from an address_space + * @mapping: the address_space + * + * Any pages which are found to be mapped into pagetables are unmapped prior to + * invalidation. + * + * Return: -EBUSY if any pages could not be invalidated. + */ +int invalidate_inode_pages2(struct address_space *mapping) +{ + return invalidate_inode_pages2_range(mapping, 0, -1); +} +EXPORT_SYMBOL_GPL(invalidate_inode_pages2); + +/** + * truncate_pagecache - unmap and remove pagecache that has been truncated + * @inode: inode + * @newsize: new file size + * + * inode's new i_size must already be written before truncate_pagecache + * is called. + * + * This function should typically be called before the filesystem + * releases resources associated with the freed range (eg. deallocates + * blocks). This way, pagecache will always stay logically coherent + * with on-disk format, and the filesystem would not have to deal with + * situations such as writepage being called for a page that has already + * had its underlying blocks deallocated. + */ +void truncate_pagecache(struct inode *inode, loff_t newsize) +{ + struct address_space *mapping = inode->i_mapping; + loff_t holebegin = round_up(newsize, PAGE_SIZE); + + /* + * unmap_mapping_range is called twice, first simply for + * efficiency so that truncate_inode_pages does fewer + * single-page unmaps. However after this first call, and + * before truncate_inode_pages finishes, it is possible for + * private pages to be COWed, which remain after + * truncate_inode_pages finishes, hence the second + * unmap_mapping_range call must be made for correctness. + */ + unmap_mapping_range(mapping, holebegin, 0, 1); + truncate_inode_pages(mapping, newsize); + unmap_mapping_range(mapping, holebegin, 0, 1); +} +EXPORT_SYMBOL(truncate_pagecache); + +/** + * truncate_setsize - update inode and pagecache for a new file size + * @inode: inode + * @newsize: new file size + * + * truncate_setsize updates i_size and performs pagecache truncation (if + * necessary) to @newsize. It will be typically be called from the filesystem's + * setattr function when ATTR_SIZE is passed in. + * + * Must be called with a lock serializing truncates and writes (generally + * i_mutex but e.g. xfs uses a different lock) and before all filesystem + * specific block truncation has been performed. + */ +void truncate_setsize(struct inode *inode, loff_t newsize) +{ + loff_t oldsize = inode->i_size; + + i_size_write(inode, newsize); + if (newsize > oldsize) + pagecache_isize_extended(inode, oldsize, newsize); + truncate_pagecache(inode, newsize); +} +EXPORT_SYMBOL(truncate_setsize); + +/** + * pagecache_isize_extended - update pagecache after extension of i_size + * @inode: inode for which i_size was extended + * @from: original inode size + * @to: new inode size + * + * Handle extension of inode size either caused by extending truncate or by + * write starting after current i_size. We mark the page straddling current + * i_size RO so that page_mkwrite() is called on the nearest write access to + * the page. This way filesystem can be sure that page_mkwrite() is called on + * the page before user writes to the page via mmap after the i_size has been + * changed. + * + * The function must be called after i_size is updated so that page fault + * coming after we unlock the page will already see the new i_size. + * The function must be called while we still hold i_mutex - this not only + * makes sure i_size is stable but also that userspace cannot observe new + * i_size value before we are prepared to store mmap writes at new inode size. + */ +void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to) +{ + int bsize = i_blocksize(inode); + loff_t rounded_from; + struct page *page; + pgoff_t index; + + WARN_ON(to > inode->i_size); + + if (from >= to || bsize == PAGE_SIZE) + return; + /* Page straddling @from will not have any hole block created? */ + rounded_from = round_up(from, bsize); + if (to <= rounded_from || !(rounded_from & (PAGE_SIZE - 1))) + return; + + index = from >> PAGE_SHIFT; + page = find_lock_page(inode->i_mapping, index); + /* Page not cached? Nothing to do */ + if (!page) + return; + /* + * See clear_page_dirty_for_io() for details why set_page_dirty() + * is needed. + */ + if (page_mkclean(page)) + set_page_dirty(page); + unlock_page(page); + put_page(page); +} +EXPORT_SYMBOL(pagecache_isize_extended); + +/** + * truncate_pagecache_range - unmap and remove pagecache that is hole-punched + * @inode: inode + * @lstart: offset of beginning of hole + * @lend: offset of last byte of hole + * + * This function should typically be called before the filesystem + * releases resources associated with the freed range (eg. deallocates + * blocks). This way, pagecache will always stay logically coherent + * with on-disk format, and the filesystem would not have to deal with + * situations such as writepage being called for a page that has already + * had its underlying blocks deallocated. + */ +void truncate_pagecache_range(struct inode *inode, loff_t lstart, loff_t lend) +{ + struct address_space *mapping = inode->i_mapping; + loff_t unmap_start = round_up(lstart, PAGE_SIZE); + loff_t unmap_end = round_down(1 + lend, PAGE_SIZE) - 1; + /* + * This rounding is currently just for example: unmap_mapping_range + * expands its hole outwards, whereas we want it to contract the hole + * inwards. However, existing callers of truncate_pagecache_range are + * doing their own page rounding first. Note that unmap_mapping_range + * allows holelen 0 for all, and we allow lend -1 for end of file. + */ + + /* + * Unlike in truncate_pagecache, unmap_mapping_range is called only + * once (before truncating pagecache), and without "even_cows" flag: + * hole-punching should not remove private COWed pages from the hole. + */ + if ((u64)unmap_end > (u64)unmap_start) + unmap_mapping_range(mapping, unmap_start, + 1 + unmap_end - unmap_start, 0); + truncate_inode_pages_range(mapping, lstart, lend); +} +EXPORT_SYMBOL(truncate_pagecache_range); diff --git a/mm/usercopy.c b/mm/usercopy.c new file mode 100644 index 000000000..540968b48 --- /dev/null +++ b/mm/usercopy.c @@ -0,0 +1,312 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * This implements the various checks for CONFIG_HARDENED_USERCOPY*, + * which are designed to protect kernel memory from needless exposure + * and overwrite under many unintended conditions. This code is based + * on PAX_USERCOPY, which is: + * + * Copyright (C) 2001-2016 PaX Team, Bradley Spengler, Open Source + * Security Inc. + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * Checks if a given pointer and length is contained by the current + * stack frame (if possible). + * + * Returns: + * NOT_STACK: not at all on the stack + * GOOD_FRAME: fully within a valid stack frame + * GOOD_STACK: fully on the stack (when can't do frame-checking) + * BAD_STACK: error condition (invalid stack position or bad stack frame) + */ +static noinline int check_stack_object(const void *obj, unsigned long len) +{ + const void * const stack = task_stack_page(current); + const void * const stackend = stack + THREAD_SIZE; + int ret; + + /* Object is not on the stack at all. */ + if (obj + len <= stack || stackend <= obj) + return NOT_STACK; + + /* + * Reject: object partially overlaps the stack (passing the + * check above means at least one end is within the stack, + * so if this check fails, the other end is outside the stack). + */ + if (obj < stack || stackend < obj + len) + return BAD_STACK; + + /* Check if object is safely within a valid frame. */ + ret = arch_within_stack_frames(stack, stackend, obj, len); + if (ret) + return ret; + + return GOOD_STACK; +} + +/* + * If these functions are reached, then CONFIG_HARDENED_USERCOPY has found + * an unexpected state during a copy_from_user() or copy_to_user() call. + * There are several checks being performed on the buffer by the + * __check_object_size() function. Normal stack buffer usage should never + * trip the checks, and kernel text addressing will always trip the check. + * For cache objects, it is checking that only the whitelisted range of + * bytes for a given cache is being accessed (via the cache's usersize and + * useroffset fields). To adjust a cache whitelist, use the usercopy-aware + * kmem_cache_create_usercopy() function to create the cache (and + * carefully audit the whitelist range). + */ +void usercopy_warn(const char *name, const char *detail, bool to_user, + unsigned long offset, unsigned long len) +{ + WARN_ONCE(1, "Bad or missing usercopy whitelist? Kernel memory %s attempt detected %s %s%s%s%s (offset %lu, size %lu)!\n", + to_user ? "exposure" : "overwrite", + to_user ? "from" : "to", + name ? : "unknown?!", + detail ? " '" : "", detail ? : "", detail ? "'" : "", + offset, len); +} + +void __noreturn usercopy_abort(const char *name, const char *detail, + bool to_user, unsigned long offset, + unsigned long len) +{ + pr_emerg("Kernel memory %s attempt detected %s %s%s%s%s (offset %lu, size %lu)!\n", + to_user ? "exposure" : "overwrite", + to_user ? "from" : "to", + name ? : "unknown?!", + detail ? " '" : "", detail ? : "", detail ? "'" : "", + offset, len); + + /* + * For greater effect, it would be nice to do do_group_exit(), + * but BUG() actually hooks all the lock-breaking and per-arch + * Oops code, so that is used here instead. + */ + BUG(); +} + +/* Returns true if any portion of [ptr,ptr+n) over laps with [low,high). */ +static bool overlaps(const unsigned long ptr, unsigned long n, + unsigned long low, unsigned long high) +{ + const unsigned long check_low = ptr; + unsigned long check_high = check_low + n; + + /* Does not overlap if entirely above or entirely below. */ + if (check_low >= high || check_high <= low) + return false; + + return true; +} + +/* Is this address range in the kernel text area? */ +static inline void check_kernel_text_object(const unsigned long ptr, + unsigned long n, bool to_user) +{ + unsigned long textlow = (unsigned long)_stext; + unsigned long texthigh = (unsigned long)_etext; + unsigned long textlow_linear, texthigh_linear; + + if (overlaps(ptr, n, textlow, texthigh)) + usercopy_abort("kernel text", NULL, to_user, ptr - textlow, n); + + /* + * Some architectures have virtual memory mappings with a secondary + * mapping of the kernel text, i.e. there is more than one virtual + * kernel address that points to the kernel image. It is usually + * when there is a separate linear physical memory mapping, in that + * __pa() is not just the reverse of __va(). This can be detected + * and checked: + */ + textlow_linear = (unsigned long)lm_alias(textlow); + /* No different mapping: we're done. */ + if (textlow_linear == textlow) + return; + + /* Check the secondary mapping... */ + texthigh_linear = (unsigned long)lm_alias(texthigh); + if (overlaps(ptr, n, textlow_linear, texthigh_linear)) + usercopy_abort("linear kernel text", NULL, to_user, + ptr - textlow_linear, n); +} + +static inline void check_bogus_address(const unsigned long ptr, unsigned long n, + bool to_user) +{ + /* Reject if object wraps past end of memory. */ + if (ptr + (n - 1) < ptr) + usercopy_abort("wrapped address", NULL, to_user, 0, ptr + n); + + /* Reject if NULL or ZERO-allocation. */ + if (ZERO_OR_NULL_PTR(ptr)) + usercopy_abort("null address", NULL, to_user, ptr, n); +} + +/* Checks for allocs that are marked in some way as spanning multiple pages. */ +static inline void check_page_span(const void *ptr, unsigned long n, + struct page *page, bool to_user) +{ +#ifdef CONFIG_HARDENED_USERCOPY_PAGESPAN + const void *end = ptr + n - 1; + struct page *endpage; + bool is_reserved, is_cma; + + /* + * Sometimes the kernel data regions are not marked Reserved (see + * check below). And sometimes [_sdata,_edata) does not cover + * rodata and/or bss, so check each range explicitly. + */ + + /* Allow reads of kernel rodata region (if not marked as Reserved). */ + if (ptr >= (const void *)__start_rodata && + end <= (const void *)__end_rodata) { + if (!to_user) + usercopy_abort("rodata", NULL, to_user, 0, n); + return; + } + + /* Allow kernel data region (if not marked as Reserved). */ + if (ptr >= (const void *)_sdata && end <= (const void *)_edata) + return; + + /* Allow kernel bss region (if not marked as Reserved). */ + if (ptr >= (const void *)__bss_start && + end <= (const void *)__bss_stop) + return; + + /* Is the object wholly within one base page? */ + if (likely(((unsigned long)ptr & (unsigned long)PAGE_MASK) == + ((unsigned long)end & (unsigned long)PAGE_MASK))) + return; + + /* Allow if fully inside the same compound (__GFP_COMP) page. */ + endpage = virt_to_head_page(end); + if (likely(endpage == page)) + return; + + /* + * Reject if range is entirely either Reserved (i.e. special or + * device memory), or CMA. Otherwise, reject since the object spans + * several independently allocated pages. + */ + is_reserved = PageReserved(page); + is_cma = is_migrate_cma_page(page); + if (!is_reserved && !is_cma) + usercopy_abort("spans multiple pages", NULL, to_user, 0, n); + + for (ptr += PAGE_SIZE; ptr <= end; ptr += PAGE_SIZE) { + page = virt_to_head_page(ptr); + if (is_reserved && !PageReserved(page)) + usercopy_abort("spans Reserved and non-Reserved pages", + NULL, to_user, 0, n); + if (is_cma && !is_migrate_cma_page(page)) + usercopy_abort("spans CMA and non-CMA pages", NULL, + to_user, 0, n); + } +#endif +} + +static inline void check_heap_object(const void *ptr, unsigned long n, + bool to_user) +{ + struct page *page; + + if (!virt_addr_valid(ptr)) + return; + + /* + * When CONFIG_HIGHMEM=y, kmap_to_page() will give either the + * highmem page or fallback to virt_to_page(). The following + * is effectively a highmem-aware virt_to_head_page(). + */ + page = compound_head(kmap_to_page((void *)ptr)); + + if (PageSlab(page)) { + /* Check slab allocator for flags and size. */ + __check_heap_object(ptr, n, page, to_user); + } else { + /* Verify object does not incorrectly span multiple pages. */ + check_page_span(ptr, n, page, to_user); + } +} + +static DEFINE_STATIC_KEY_FALSE_RO(bypass_usercopy_checks); + +/* + * Validates that the given object is: + * - not bogus address + * - fully contained by stack (or stack frame, when available) + * - fully within SLAB object (or object whitelist area, when available) + * - not in kernel text + */ +void __check_object_size(const void *ptr, unsigned long n, bool to_user) +{ + if (static_branch_unlikely(&bypass_usercopy_checks)) + return; + + /* Skip all tests if size is zero. */ + if (!n) + return; + + /* Check for invalid addresses. */ + check_bogus_address((const unsigned long)ptr, n, to_user); + + /* Check for bad stack object. */ + switch (check_stack_object(ptr, n)) { + case NOT_STACK: + /* Object is not touching the current process stack. */ + break; + case GOOD_FRAME: + case GOOD_STACK: + /* + * Object is either in the correct frame (when it + * is possible to check) or just generally on the + * process stack (when frame checking not available). + */ + return; + default: + usercopy_abort("process stack", NULL, to_user, 0, n); + } + + /* Check for bad heap object. */ + check_heap_object(ptr, n, to_user); + + /* Check for object in kernel to avoid text exposure. */ + check_kernel_text_object((const unsigned long)ptr, n, to_user); +} +EXPORT_SYMBOL(__check_object_size); + +static bool enable_checks __initdata = true; + +static int __init parse_hardened_usercopy(char *str) +{ + if (strtobool(str, &enable_checks)) + pr_warn("Invalid option string for hardened_usercopy: '%s'\n", + str); + return 1; +} + +__setup("hardened_usercopy=", parse_hardened_usercopy); + +static int __init set_hardened_usercopy(void) +{ + if (enable_checks == false) + static_branch_enable(&bypass_usercopy_checks); + return 1; +} + +late_initcall(set_hardened_usercopy); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c new file mode 100644 index 000000000..078d95cd3 --- /dev/null +++ b/mm/userfaultfd.c @@ -0,0 +1,694 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * mm/userfaultfd.c + * + * Copyright (C) 2015 Red Hat, Inc. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "internal.h" + +static __always_inline +struct vm_area_struct *find_dst_vma(struct mm_struct *dst_mm, + unsigned long dst_start, + unsigned long len) +{ + /* + * Make sure that the dst range is both valid and fully within a + * single existing vma. + */ + struct vm_area_struct *dst_vma; + + dst_vma = find_vma(dst_mm, dst_start); + if (!dst_vma) + return NULL; + + if (dst_start < dst_vma->vm_start || + dst_start + len > dst_vma->vm_end) + return NULL; + + /* + * Check the vma is registered in uffd, this is required to + * enforce the VM_MAYWRITE check done at uffd registration + * time. + */ + if (!dst_vma->vm_userfaultfd_ctx.ctx) + return NULL; + + return dst_vma; +} + +static int mcopy_atomic_pte(struct mm_struct *dst_mm, + pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + unsigned long src_addr, + struct page **pagep, + bool wp_copy) +{ + pte_t _dst_pte, *dst_pte; + spinlock_t *ptl; + void *page_kaddr; + int ret; + struct page *page; + pgoff_t offset, max_off; + struct inode *inode; + + if (!*pagep) { + ret = -ENOMEM; + page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, dst_vma, dst_addr); + if (!page) + goto out; + + page_kaddr = kmap_atomic(page); + ret = copy_from_user(page_kaddr, + (const void __user *) src_addr, + PAGE_SIZE); + kunmap_atomic(page_kaddr); + + /* fallback to copy_from_user outside mmap_lock */ + if (unlikely(ret)) { + ret = -ENOENT; + *pagep = page; + /* don't free the page */ + goto out; + } + + flush_dcache_page(page); + } else { + page = *pagep; + *pagep = NULL; + } + + /* + * The memory barrier inside __SetPageUptodate makes sure that + * preceding stores to the page contents become visible before + * the set_pte_at() write. + */ + __SetPageUptodate(page); + + ret = -ENOMEM; + if (mem_cgroup_charge(page, dst_mm, GFP_KERNEL)) + goto out_release; + + _dst_pte = pte_mkdirty(mk_pte(page, dst_vma->vm_page_prot)); + if (dst_vma->vm_flags & VM_WRITE) { + if (wp_copy) + _dst_pte = pte_mkuffd_wp(_dst_pte); + else + _dst_pte = pte_mkwrite(_dst_pte); + } + + dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl); + if (dst_vma->vm_file) { + /* the shmem MAP_PRIVATE case requires checking the i_size */ + inode = dst_vma->vm_file->f_inode; + offset = linear_page_index(dst_vma, dst_addr); + max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + ret = -EFAULT; + if (unlikely(offset >= max_off)) + goto out_release_uncharge_unlock; + } + ret = -EEXIST; + if (!pte_none(*dst_pte)) + goto out_release_uncharge_unlock; + + inc_mm_counter(dst_mm, MM_ANONPAGES); + page_add_new_anon_rmap(page, dst_vma, dst_addr, false); + lru_cache_add_inactive_or_unevictable(page, dst_vma); + + set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); + + /* No need to invalidate - it was non-present before */ + update_mmu_cache(dst_vma, dst_addr, dst_pte); + + pte_unmap_unlock(dst_pte, ptl); + ret = 0; +out: + return ret; +out_release_uncharge_unlock: + pte_unmap_unlock(dst_pte, ptl); +out_release: + put_page(page); + goto out; +} + +static int mfill_zeropage_pte(struct mm_struct *dst_mm, + pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr) +{ + pte_t _dst_pte, *dst_pte; + spinlock_t *ptl; + int ret; + pgoff_t offset, max_off; + struct inode *inode; + + _dst_pte = pte_mkspecial(pfn_pte(my_zero_pfn(dst_addr), + dst_vma->vm_page_prot)); + dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl); + if (dst_vma->vm_file) { + /* the shmem MAP_PRIVATE case requires checking the i_size */ + inode = dst_vma->vm_file->f_inode; + offset = linear_page_index(dst_vma, dst_addr); + max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + ret = -EFAULT; + if (unlikely(offset >= max_off)) + goto out_unlock; + } + ret = -EEXIST; + if (!pte_none(*dst_pte)) + goto out_unlock; + set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); + /* No need to invalidate - it was non-present before */ + update_mmu_cache(dst_vma, dst_addr, dst_pte); + ret = 0; +out_unlock: + pte_unmap_unlock(dst_pte, ptl); + return ret; +} + +static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address) +{ + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + + pgd = pgd_offset(mm, address); + p4d = p4d_alloc(mm, pgd, address); + if (!p4d) + return NULL; + pud = pud_alloc(mm, p4d, address); + if (!pud) + return NULL; + /* + * Note that we didn't run this because the pmd was + * missing, the *pmd may be already established and in + * turn it may also be a trans_huge_pmd. + */ + return pmd_alloc(mm, pud, address); +} + +#ifdef CONFIG_HUGETLB_PAGE +/* + * __mcopy_atomic processing for HUGETLB vmas. Note that this routine is + * called with mmap_lock held, it will release mmap_lock before returning. + */ +static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, + struct vm_area_struct *dst_vma, + unsigned long dst_start, + unsigned long src_start, + unsigned long len, + bool zeropage) +{ + int vm_alloc_shared = dst_vma->vm_flags & VM_SHARED; + int vm_shared = dst_vma->vm_flags & VM_SHARED; + ssize_t err; + pte_t *dst_pte; + unsigned long src_addr, dst_addr; + long copied; + struct page *page; + unsigned long vma_hpagesize; + pgoff_t idx; + u32 hash; + struct address_space *mapping; + + /* + * There is no default zero huge page for all huge page sizes as + * supported by hugetlb. A PMD_SIZE huge pages may exist as used + * by THP. Since we can not reliably insert a zero page, this + * feature is not supported. + */ + if (zeropage) { + mmap_read_unlock(dst_mm); + return -EINVAL; + } + + src_addr = src_start; + dst_addr = dst_start; + copied = 0; + page = NULL; + vma_hpagesize = vma_kernel_pagesize(dst_vma); + + /* + * Validate alignment based on huge page size + */ + err = -EINVAL; + if (dst_start & (vma_hpagesize - 1) || len & (vma_hpagesize - 1)) + goto out_unlock; + +retry: + /* + * On routine entry dst_vma is set. If we had to drop mmap_lock and + * retry, dst_vma will be set to NULL and we must lookup again. + */ + if (!dst_vma) { + err = -ENOENT; + dst_vma = find_dst_vma(dst_mm, dst_start, len); + if (!dst_vma || !is_vm_hugetlb_page(dst_vma)) + goto out_unlock; + + err = -EINVAL; + if (vma_hpagesize != vma_kernel_pagesize(dst_vma)) + goto out_unlock; + + vm_shared = dst_vma->vm_flags & VM_SHARED; + } + + /* + * If not shared, ensure the dst_vma has a anon_vma. + */ + err = -ENOMEM; + if (!vm_shared) { + if (unlikely(anon_vma_prepare(dst_vma))) + goto out_unlock; + } + + while (src_addr < src_start + len) { + pte_t dst_pteval; + + BUG_ON(dst_addr >= dst_start + len); + + /* + * Serialize via i_mmap_rwsem and hugetlb_fault_mutex. + * i_mmap_rwsem ensures the dst_pte remains valid even + * in the case of shared pmds. fault mutex prevents + * races with other faulting threads. + */ + mapping = dst_vma->vm_file->f_mapping; + i_mmap_lock_read(mapping); + idx = linear_page_index(dst_vma, dst_addr); + hash = hugetlb_fault_mutex_hash(mapping, idx); + mutex_lock(&hugetlb_fault_mutex_table[hash]); + + err = -ENOMEM; + dst_pte = huge_pte_alloc(dst_mm, dst_addr, vma_hpagesize); + if (!dst_pte) { + mutex_unlock(&hugetlb_fault_mutex_table[hash]); + i_mmap_unlock_read(mapping); + goto out_unlock; + } + + err = -EEXIST; + dst_pteval = huge_ptep_get(dst_pte); + if (!huge_pte_none(dst_pteval)) { + mutex_unlock(&hugetlb_fault_mutex_table[hash]); + i_mmap_unlock_read(mapping); + goto out_unlock; + } + + err = hugetlb_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, + dst_addr, src_addr, &page); + + mutex_unlock(&hugetlb_fault_mutex_table[hash]); + i_mmap_unlock_read(mapping); + vm_alloc_shared = vm_shared; + + cond_resched(); + + if (unlikely(err == -ENOENT)) { + mmap_read_unlock(dst_mm); + BUG_ON(!page); + + err = copy_huge_page_from_user(page, + (const void __user *)src_addr, + vma_hpagesize / PAGE_SIZE, + true); + if (unlikely(err)) { + err = -EFAULT; + goto out; + } + mmap_read_lock(dst_mm); + + dst_vma = NULL; + goto retry; + } else + BUG_ON(page); + + if (!err) { + dst_addr += vma_hpagesize; + src_addr += vma_hpagesize; + copied += vma_hpagesize; + + if (fatal_signal_pending(current)) + err = -EINTR; + } + if (err) + break; + } + +out_unlock: + mmap_read_unlock(dst_mm); +out: + if (page) { + /* + * We encountered an error and are about to free a newly + * allocated huge page. + * + * Reservation handling is very subtle, and is different for + * private and shared mappings. See the routine + * restore_reserve_on_error for details. Unfortunately, we + * can not call restore_reserve_on_error now as it would + * require holding mmap_lock. + * + * If a reservation for the page existed in the reservation + * map of a private mapping, the map was modified to indicate + * the reservation was consumed when the page was allocated. + * We clear the PagePrivate flag now so that the global + * reserve count will not be incremented in free_huge_page. + * The reservation map will still indicate the reservation + * was consumed and possibly prevent later page allocation. + * This is better than leaking a global reservation. If no + * reservation existed, it is still safe to clear PagePrivate + * as no adjustments to reservation counts were made during + * allocation. + * + * The reservation map for shared mappings indicates which + * pages have reservations. When a huge page is allocated + * for an address with a reservation, no change is made to + * the reserve map. In this case PagePrivate will be set + * to indicate that the global reservation count should be + * incremented when the page is freed. This is the desired + * behavior. However, when a huge page is allocated for an + * address without a reservation a reservation entry is added + * to the reservation map, and PagePrivate will not be set. + * When the page is freed, the global reserve count will NOT + * be incremented and it will appear as though we have leaked + * reserved page. In this case, set PagePrivate so that the + * global reserve count will be incremented to match the + * reservation map entry which was created. + * + * Note that vm_alloc_shared is based on the flags of the vma + * for which the page was originally allocated. dst_vma could + * be different or NULL on error. + */ + if (vm_alloc_shared) + SetPagePrivate(page); + else + ClearPagePrivate(page); + put_page(page); + } + BUG_ON(copied < 0); + BUG_ON(err > 0); + BUG_ON(!copied && !err); + return copied ? copied : err; +} +#else /* !CONFIG_HUGETLB_PAGE */ +/* fail at build time if gcc attempts to use this */ +extern ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, + struct vm_area_struct *dst_vma, + unsigned long dst_start, + unsigned long src_start, + unsigned long len, + bool zeropage); +#endif /* CONFIG_HUGETLB_PAGE */ + +static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm, + pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + unsigned long src_addr, + struct page **page, + bool zeropage, + bool wp_copy) +{ + ssize_t err; + + /* + * The normal page fault path for a shmem will invoke the + * fault, fill the hole in the file and COW it right away. The + * result generates plain anonymous memory. So when we are + * asked to fill an hole in a MAP_PRIVATE shmem mapping, we'll + * generate anonymous memory directly without actually filling + * the hole. For the MAP_PRIVATE case the robustness check + * only happens in the pagetable (to verify it's still none) + * and not in the radix tree. + */ + if (!(dst_vma->vm_flags & VM_SHARED)) { + if (!zeropage) + err = mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma, + dst_addr, src_addr, page, + wp_copy); + else + err = mfill_zeropage_pte(dst_mm, dst_pmd, + dst_vma, dst_addr); + } else { + VM_WARN_ON_ONCE(wp_copy); + if (!zeropage) + err = shmem_mcopy_atomic_pte(dst_mm, dst_pmd, + dst_vma, dst_addr, + src_addr, page); + else + err = shmem_mfill_zeropage_pte(dst_mm, dst_pmd, + dst_vma, dst_addr); + } + + return err; +} + +static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm, + unsigned long dst_start, + unsigned long src_start, + unsigned long len, + bool zeropage, + bool *mmap_changing, + __u64 mode) +{ + struct vm_area_struct *dst_vma; + ssize_t err; + pmd_t *dst_pmd; + unsigned long src_addr, dst_addr; + long copied; + struct page *page; + bool wp_copy; + + /* + * Sanitize the command parameters: + */ + BUG_ON(dst_start & ~PAGE_MASK); + BUG_ON(len & ~PAGE_MASK); + + /* Does the address range wrap, or is the span zero-sized? */ + BUG_ON(src_start + len <= src_start); + BUG_ON(dst_start + len <= dst_start); + + src_addr = src_start; + dst_addr = dst_start; + copied = 0; + page = NULL; +retry: + mmap_read_lock(dst_mm); + + /* + * If memory mappings are changing because of non-cooperative + * operation (e.g. mremap) running in parallel, bail out and + * request the user to retry later + */ + err = -EAGAIN; + if (mmap_changing && READ_ONCE(*mmap_changing)) + goto out_unlock; + + /* + * Make sure the vma is not shared, that the dst range is + * both valid and fully within a single existing vma. + */ + err = -ENOENT; + dst_vma = find_dst_vma(dst_mm, dst_start, len); + if (!dst_vma) + goto out_unlock; + + err = -EINVAL; + /* + * shmem_zero_setup is invoked in mmap for MAP_ANONYMOUS|MAP_SHARED but + * it will overwrite vm_ops, so vma_is_anonymous must return false. + */ + if (WARN_ON_ONCE(vma_is_anonymous(dst_vma) && + dst_vma->vm_flags & VM_SHARED)) + goto out_unlock; + + /* + * validate 'mode' now that we know the dst_vma: don't allow + * a wrprotect copy if the userfaultfd didn't register as WP. + */ + wp_copy = mode & UFFDIO_COPY_MODE_WP; + if (wp_copy && !(dst_vma->vm_flags & VM_UFFD_WP)) + goto out_unlock; + + /* + * If this is a HUGETLB vma, pass off to appropriate routine + */ + if (is_vm_hugetlb_page(dst_vma)) + return __mcopy_atomic_hugetlb(dst_mm, dst_vma, dst_start, + src_start, len, zeropage); + + if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma)) + goto out_unlock; + + /* + * Ensure the dst_vma has a anon_vma or this page + * would get a NULL anon_vma when moved in the + * dst_vma. + */ + err = -ENOMEM; + if (!(dst_vma->vm_flags & VM_SHARED) && + unlikely(anon_vma_prepare(dst_vma))) + goto out_unlock; + + while (src_addr < src_start + len) { + pmd_t dst_pmdval; + + BUG_ON(dst_addr >= dst_start + len); + + dst_pmd = mm_alloc_pmd(dst_mm, dst_addr); + if (unlikely(!dst_pmd)) { + err = -ENOMEM; + break; + } + + dst_pmdval = pmd_read_atomic(dst_pmd); + /* + * If the dst_pmd is mapped as THP don't + * override it and just be strict. + */ + if (unlikely(pmd_trans_huge(dst_pmdval))) { + err = -EEXIST; + break; + } + if (unlikely(pmd_none(dst_pmdval)) && + unlikely(__pte_alloc(dst_mm, dst_pmd))) { + err = -ENOMEM; + break; + } + /* If an huge pmd materialized from under us fail */ + if (unlikely(pmd_trans_huge(*dst_pmd))) { + err = -EFAULT; + break; + } + + BUG_ON(pmd_none(*dst_pmd)); + BUG_ON(pmd_trans_huge(*dst_pmd)); + + err = mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, + src_addr, &page, zeropage, wp_copy); + cond_resched(); + + if (unlikely(err == -ENOENT)) { + void *page_kaddr; + + mmap_read_unlock(dst_mm); + BUG_ON(!page); + + page_kaddr = kmap(page); + err = copy_from_user(page_kaddr, + (const void __user *) src_addr, + PAGE_SIZE); + kunmap(page); + if (unlikely(err)) { + err = -EFAULT; + goto out; + } + flush_dcache_page(page); + goto retry; + } else + BUG_ON(page); + + if (!err) { + dst_addr += PAGE_SIZE; + src_addr += PAGE_SIZE; + copied += PAGE_SIZE; + + if (fatal_signal_pending(current)) + err = -EINTR; + } + if (err) + break; + } + +out_unlock: + mmap_read_unlock(dst_mm); +out: + if (page) + put_page(page); + BUG_ON(copied < 0); + BUG_ON(err > 0); + BUG_ON(!copied && !err); + return copied ? copied : err; +} + +ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start, + unsigned long src_start, unsigned long len, + bool *mmap_changing, __u64 mode) +{ + return __mcopy_atomic(dst_mm, dst_start, src_start, len, false, + mmap_changing, mode); +} + +ssize_t mfill_zeropage(struct mm_struct *dst_mm, unsigned long start, + unsigned long len, bool *mmap_changing) +{ + return __mcopy_atomic(dst_mm, start, 0, len, true, mmap_changing, 0); +} + +int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, + unsigned long len, bool enable_wp, bool *mmap_changing) +{ + struct vm_area_struct *dst_vma; + pgprot_t newprot; + int err; + + /* + * Sanitize the command parameters: + */ + BUG_ON(start & ~PAGE_MASK); + BUG_ON(len & ~PAGE_MASK); + + /* Does the address range wrap, or is the span zero-sized? */ + BUG_ON(start + len <= start); + + mmap_read_lock(dst_mm); + + /* + * If memory mappings are changing because of non-cooperative + * operation (e.g. mremap) running in parallel, bail out and + * request the user to retry later + */ + err = -EAGAIN; + if (mmap_changing && READ_ONCE(*mmap_changing)) + goto out_unlock; + + err = -ENOENT; + dst_vma = find_dst_vma(dst_mm, start, len); + /* + * Make sure the vma is not shared, that the dst range is + * both valid and fully within a single existing vma. + */ + if (!dst_vma || (dst_vma->vm_flags & VM_SHARED)) + goto out_unlock; + if (!userfaultfd_wp(dst_vma)) + goto out_unlock; + if (!vma_is_anonymous(dst_vma)) + goto out_unlock; + + if (enable_wp) + newprot = vm_get_page_prot(dst_vma->vm_flags & ~(VM_WRITE)); + else + newprot = vm_get_page_prot(dst_vma->vm_flags); + + change_protection(dst_vma, start, start + len, newprot, + enable_wp ? MM_CP_UFFD_WP : MM_CP_UFFD_WP_RESOLVE); + + err = 0; +out_unlock: + mmap_read_unlock(dst_mm); + return err; +} diff --git a/mm/util.c b/mm/util.c new file mode 100644 index 000000000..25bfda774 --- /dev/null +++ b/mm/util.c @@ -0,0 +1,1025 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "internal.h" + +/** + * kfree_const - conditionally free memory + * @x: pointer to the memory + * + * Function calls kfree only if @x is not in .rodata section. + */ +void kfree_const(const void *x) +{ + if (!is_kernel_rodata((unsigned long)x)) + kfree(x); +} +EXPORT_SYMBOL(kfree_const); + +/** + * kstrdup - allocate space for and copy an existing string + * @s: the string to duplicate + * @gfp: the GFP mask used in the kmalloc() call when allocating memory + * + * Return: newly allocated copy of @s or %NULL in case of error + */ +char *kstrdup(const char *s, gfp_t gfp) +{ + size_t len; + char *buf; + + if (!s) + return NULL; + + len = strlen(s) + 1; + buf = kmalloc_track_caller(len, gfp); + if (buf) + memcpy(buf, s, len); + return buf; +} +EXPORT_SYMBOL(kstrdup); + +/** + * kstrdup_const - conditionally duplicate an existing const string + * @s: the string to duplicate + * @gfp: the GFP mask used in the kmalloc() call when allocating memory + * + * Note: Strings allocated by kstrdup_const should be freed by kfree_const and + * must not be passed to krealloc(). + * + * Return: source string if it is in .rodata section otherwise + * fallback to kstrdup. + */ +const char *kstrdup_const(const char *s, gfp_t gfp) +{ + if (is_kernel_rodata((unsigned long)s)) + return s; + + return kstrdup(s, gfp); +} +EXPORT_SYMBOL(kstrdup_const); + +/** + * kstrndup - allocate space for and copy an existing string + * @s: the string to duplicate + * @max: read at most @max chars from @s + * @gfp: the GFP mask used in the kmalloc() call when allocating memory + * + * Note: Use kmemdup_nul() instead if the size is known exactly. + * + * Return: newly allocated copy of @s or %NULL in case of error + */ +char *kstrndup(const char *s, size_t max, gfp_t gfp) +{ + size_t len; + char *buf; + + if (!s) + return NULL; + + len = strnlen(s, max); + buf = kmalloc_track_caller(len+1, gfp); + if (buf) { + memcpy(buf, s, len); + buf[len] = '\0'; + } + return buf; +} +EXPORT_SYMBOL(kstrndup); + +/** + * kmemdup - duplicate region of memory + * + * @src: memory region to duplicate + * @len: memory region length + * @gfp: GFP mask to use + * + * Return: newly allocated copy of @src or %NULL in case of error + */ +void *kmemdup(const void *src, size_t len, gfp_t gfp) +{ + void *p; + + p = kmalloc_track_caller(len, gfp); + if (p) + memcpy(p, src, len); + return p; +} +EXPORT_SYMBOL(kmemdup); + +/** + * kmemdup_nul - Create a NUL-terminated string from unterminated data + * @s: The data to stringify + * @len: The size of the data + * @gfp: the GFP mask used in the kmalloc() call when allocating memory + * + * Return: newly allocated copy of @s with NUL-termination or %NULL in + * case of error + */ +char *kmemdup_nul(const char *s, size_t len, gfp_t gfp) +{ + char *buf; + + if (!s) + return NULL; + + buf = kmalloc_track_caller(len + 1, gfp); + if (buf) { + memcpy(buf, s, len); + buf[len] = '\0'; + } + return buf; +} +EXPORT_SYMBOL(kmemdup_nul); + +/** + * memdup_user - duplicate memory region from user space + * + * @src: source address in user space + * @len: number of bytes to copy + * + * Return: an ERR_PTR() on failure. Result is physically + * contiguous, to be freed by kfree(). + */ +void *memdup_user(const void __user *src, size_t len) +{ + void *p; + + p = kmalloc_track_caller(len, GFP_USER | __GFP_NOWARN); + if (!p) + return ERR_PTR(-ENOMEM); + + if (copy_from_user(p, src, len)) { + kfree(p); + return ERR_PTR(-EFAULT); + } + + return p; +} +EXPORT_SYMBOL(memdup_user); + +/** + * vmemdup_user - duplicate memory region from user space + * + * @src: source address in user space + * @len: number of bytes to copy + * + * Return: an ERR_PTR() on failure. Result may be not + * physically contiguous. Use kvfree() to free. + */ +void *vmemdup_user(const void __user *src, size_t len) +{ + void *p; + + p = kvmalloc(len, GFP_USER); + if (!p) + return ERR_PTR(-ENOMEM); + + if (copy_from_user(p, src, len)) { + kvfree(p); + return ERR_PTR(-EFAULT); + } + + return p; +} +EXPORT_SYMBOL(vmemdup_user); + +/** + * strndup_user - duplicate an existing string from user space + * @s: The string to duplicate + * @n: Maximum number of bytes to copy, including the trailing NUL. + * + * Return: newly allocated copy of @s or an ERR_PTR() in case of error + */ +char *strndup_user(const char __user *s, long n) +{ + char *p; + long length; + + length = strnlen_user(s, n); + + if (!length) + return ERR_PTR(-EFAULT); + + if (length > n) + return ERR_PTR(-EINVAL); + + p = memdup_user(s, length); + + if (IS_ERR(p)) + return p; + + p[length - 1] = '\0'; + + return p; +} +EXPORT_SYMBOL(strndup_user); + +/** + * memdup_user_nul - duplicate memory region from user space and NUL-terminate + * + * @src: source address in user space + * @len: number of bytes to copy + * + * Return: an ERR_PTR() on failure. + */ +void *memdup_user_nul(const void __user *src, size_t len) +{ + char *p; + + /* + * Always use GFP_KERNEL, since copy_from_user() can sleep and + * cause pagefault, which makes it pointless to use GFP_NOFS + * or GFP_ATOMIC. + */ + p = kmalloc_track_caller(len + 1, GFP_KERNEL); + if (!p) + return ERR_PTR(-ENOMEM); + + if (copy_from_user(p, src, len)) { + kfree(p); + return ERR_PTR(-EFAULT); + } + p[len] = '\0'; + + return p; +} +EXPORT_SYMBOL(memdup_user_nul); + +void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma, + struct vm_area_struct *prev) +{ + struct vm_area_struct *next; + + vma->vm_prev = prev; + if (prev) { + next = prev->vm_next; + prev->vm_next = vma; + } else { + next = mm->mmap; + mm->mmap = vma; + } + vma->vm_next = next; + if (next) + next->vm_prev = vma; +} + +void __vma_unlink_list(struct mm_struct *mm, struct vm_area_struct *vma) +{ + struct vm_area_struct *prev, *next; + + next = vma->vm_next; + prev = vma->vm_prev; + if (prev) + prev->vm_next = next; + else + mm->mmap = next; + if (next) + next->vm_prev = prev; +} + +/* Check if the vma is being used as a stack by this task */ +int vma_is_stack_for_current(struct vm_area_struct *vma) +{ + struct task_struct * __maybe_unused t = current; + + return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t)); +} + +#ifndef STACK_RND_MASK +#define STACK_RND_MASK (0x7ff >> (PAGE_SHIFT - 12)) /* 8MB of VA */ +#endif + +unsigned long randomize_stack_top(unsigned long stack_top) +{ + unsigned long random_variable = 0; + + if (current->flags & PF_RANDOMIZE) { + random_variable = get_random_long(); + random_variable &= STACK_RND_MASK; + random_variable <<= PAGE_SHIFT; + } +#ifdef CONFIG_STACK_GROWSUP + return PAGE_ALIGN(stack_top) + random_variable; +#else + return PAGE_ALIGN(stack_top) - random_variable; +#endif +} + +/** + * randomize_page - Generate a random, page aligned address + * @start: The smallest acceptable address the caller will take. + * @range: The size of the area, starting at @start, within which the + * random address must fall. + * + * If @start + @range would overflow, @range is capped. + * + * NOTE: Historical use of randomize_range, which this replaces, presumed that + * @start was already page aligned. We now align it regardless. + * + * Return: A page aligned address within [start, start + range). On error, + * @start is returned. + */ +unsigned long randomize_page(unsigned long start, unsigned long range) +{ + if (!PAGE_ALIGNED(start)) { + range -= PAGE_ALIGN(start) - start; + start = PAGE_ALIGN(start); + } + + if (start > ULONG_MAX - range) + range = ULONG_MAX - start; + + range >>= PAGE_SHIFT; + + if (range == 0) + return start; + + return start + (get_random_long() % range << PAGE_SHIFT); +} + +#ifdef CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT +unsigned long arch_randomize_brk(struct mm_struct *mm) +{ + /* Is the current task 32bit ? */ + if (!IS_ENABLED(CONFIG_64BIT) || is_compat_task()) + return randomize_page(mm->brk, SZ_32M); + + return randomize_page(mm->brk, SZ_1G); +} + +unsigned long arch_mmap_rnd(void) +{ + unsigned long rnd; + +#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS + if (is_compat_task()) + rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1); + else +#endif /* CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS */ + rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); + + return rnd << PAGE_SHIFT; +} + +static int mmap_is_legacy(struct rlimit *rlim_stack) +{ + if (current->personality & ADDR_COMPAT_LAYOUT) + return 1; + + if (rlim_stack->rlim_cur == RLIM_INFINITY) + return 1; + + return sysctl_legacy_va_layout; +} + +/* + * Leave enough space between the mmap area and the stack to honour ulimit in + * the face of randomisation. + */ +#define MIN_GAP (SZ_128M) +#define MAX_GAP (STACK_TOP / 6 * 5) + +static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack) +{ + unsigned long gap = rlim_stack->rlim_cur; + unsigned long pad = stack_guard_gap; + + /* Account for stack randomization if necessary */ + if (current->flags & PF_RANDOMIZE) + pad += (STACK_RND_MASK << PAGE_SHIFT); + + /* Values close to RLIM_INFINITY can overflow. */ + if (gap + pad > gap) + gap += pad; + + if (gap < MIN_GAP) + gap = MIN_GAP; + else if (gap > MAX_GAP) + gap = MAX_GAP; + + return PAGE_ALIGN(STACK_TOP - gap - rnd); +} + +void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) +{ + unsigned long random_factor = 0UL; + + if (current->flags & PF_RANDOMIZE) + random_factor = arch_mmap_rnd(); + + if (mmap_is_legacy(rlim_stack)) { + mm->mmap_base = TASK_UNMAPPED_BASE + random_factor; + mm->get_unmapped_area = arch_get_unmapped_area; + } else { + mm->mmap_base = mmap_base(random_factor, rlim_stack); + mm->get_unmapped_area = arch_get_unmapped_area_topdown; + } +} +#elif defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT) +void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) +{ + mm->mmap_base = TASK_UNMAPPED_BASE; + mm->get_unmapped_area = arch_get_unmapped_area; +} +#endif + +/** + * __account_locked_vm - account locked pages to an mm's locked_vm + * @mm: mm to account against + * @pages: number of pages to account + * @inc: %true if @pages should be considered positive, %false if not + * @task: task used to check RLIMIT_MEMLOCK + * @bypass_rlim: %true if checking RLIMIT_MEMLOCK should be skipped + * + * Assumes @task and @mm are valid (i.e. at least one reference on each), and + * that mmap_lock is held as writer. + * + * Return: + * * 0 on success + * * -ENOMEM if RLIMIT_MEMLOCK would be exceeded. + */ +int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, + struct task_struct *task, bool bypass_rlim) +{ + unsigned long locked_vm, limit; + int ret = 0; + + mmap_assert_write_locked(mm); + + locked_vm = mm->locked_vm; + if (inc) { + if (!bypass_rlim) { + limit = task_rlimit(task, RLIMIT_MEMLOCK) >> PAGE_SHIFT; + if (locked_vm + pages > limit) + ret = -ENOMEM; + } + if (!ret) + mm->locked_vm = locked_vm + pages; + } else { + WARN_ON_ONCE(pages > locked_vm); + mm->locked_vm = locked_vm - pages; + } + + pr_debug("%s: [%d] caller %ps %c%lu %lu/%lu%s\n", __func__, task->pid, + (void *)_RET_IP_, (inc) ? '+' : '-', pages << PAGE_SHIFT, + locked_vm << PAGE_SHIFT, task_rlimit(task, RLIMIT_MEMLOCK), + ret ? " - exceeded" : ""); + + return ret; +} +EXPORT_SYMBOL_GPL(__account_locked_vm); + +/** + * account_locked_vm - account locked pages to an mm's locked_vm + * @mm: mm to account against, may be NULL + * @pages: number of pages to account + * @inc: %true if @pages should be considered positive, %false if not + * + * Assumes a non-NULL @mm is valid (i.e. at least one reference on it). + * + * Return: + * * 0 on success, or if mm is NULL + * * -ENOMEM if RLIMIT_MEMLOCK would be exceeded. + */ +int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc) +{ + int ret; + + if (pages == 0 || !mm) + return 0; + + mmap_write_lock(mm); + ret = __account_locked_vm(mm, pages, inc, current, + capable(CAP_IPC_LOCK)); + mmap_write_unlock(mm); + + return ret; +} +EXPORT_SYMBOL_GPL(account_locked_vm); + +unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr, + unsigned long len, unsigned long prot, + unsigned long flag, unsigned long pgoff) +{ + unsigned long ret; + struct mm_struct *mm = current->mm; + unsigned long populate; + LIST_HEAD(uf); + + ret = security_mmap_file(file, prot, flag); + if (!ret) { + if (mmap_write_lock_killable(mm)) + return -EINTR; + ret = do_mmap(file, addr, len, prot, flag, pgoff, &populate, + &uf); + mmap_write_unlock(mm); + userfaultfd_unmap_complete(mm, &uf); + if (populate) + mm_populate(ret, populate); + } + return ret; +} + +unsigned long vm_mmap(struct file *file, unsigned long addr, + unsigned long len, unsigned long prot, + unsigned long flag, unsigned long offset) +{ + if (unlikely(offset + PAGE_ALIGN(len) < offset)) + return -EINVAL; + if (unlikely(offset_in_page(offset))) + return -EINVAL; + + return vm_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT); +} +EXPORT_SYMBOL(vm_mmap); + +/** + * kvmalloc_node - attempt to allocate physically contiguous memory, but upon + * failure, fall back to non-contiguous (vmalloc) allocation. + * @size: size of the request. + * @flags: gfp mask for the allocation - must be compatible (superset) with GFP_KERNEL. + * @node: numa node to allocate from + * + * Uses kmalloc to get the memory but if the allocation fails then falls back + * to the vmalloc allocator. Use kvfree for freeing the memory. + * + * Reclaim modifiers - __GFP_NORETRY and __GFP_NOFAIL are not supported. + * __GFP_RETRY_MAYFAIL is supported, and it should be used only if kmalloc is + * preferable to the vmalloc fallback, due to visible performance drawbacks. + * + * Please note that any use of gfp flags outside of GFP_KERNEL is careful to not + * fall back to vmalloc. + * + * Return: pointer to the allocated memory of %NULL in case of failure + */ +void *kvmalloc_node(size_t size, gfp_t flags, int node) +{ + gfp_t kmalloc_flags = flags; + void *ret; + + /* + * vmalloc uses GFP_KERNEL for some internal allocations (e.g page tables) + * so the given set of flags has to be compatible. + */ + if ((flags & GFP_KERNEL) != GFP_KERNEL) + return kmalloc_node(size, flags, node); + + /* + * We want to attempt a large physically contiguous block first because + * it is less likely to fragment multiple larger blocks and therefore + * contribute to a long term fragmentation less than vmalloc fallback. + * However make sure that larger requests are not too disruptive - no + * OOM killer and no allocation failure warnings as we have a fallback. + */ + if (size > PAGE_SIZE) { + kmalloc_flags |= __GFP_NOWARN; + + if (!(kmalloc_flags & __GFP_RETRY_MAYFAIL)) + kmalloc_flags |= __GFP_NORETRY; + } + + ret = kmalloc_node(size, kmalloc_flags, node); + + /* + * It doesn't really make sense to fallback to vmalloc for sub page + * requests + */ + if (ret || size <= PAGE_SIZE) + return ret; + + /* Don't even allow crazy sizes */ + if (unlikely(size > INT_MAX)) { + WARN_ON_ONCE(!(flags & __GFP_NOWARN)); + return NULL; + } + + return __vmalloc_node(size, 1, flags, node, + __builtin_return_address(0)); +} +EXPORT_SYMBOL(kvmalloc_node); + +/** + * kvfree() - Free memory. + * @addr: Pointer to allocated memory. + * + * kvfree frees memory allocated by any of vmalloc(), kmalloc() or kvmalloc(). + * It is slightly more efficient to use kfree() or vfree() if you are certain + * that you know which one to use. + * + * Context: Either preemptible task context or not-NMI interrupt. + */ +void kvfree(const void *addr) +{ + if (is_vmalloc_addr(addr)) + vfree(addr); + else + kfree(addr); +} +EXPORT_SYMBOL(kvfree); + +/** + * kvfree_sensitive - Free a data object containing sensitive information. + * @addr: address of the data object to be freed. + * @len: length of the data object. + * + * Use the special memzero_explicit() function to clear the content of a + * kvmalloc'ed object containing sensitive data to make sure that the + * compiler won't optimize out the data clearing. + */ +void kvfree_sensitive(const void *addr, size_t len) +{ + if (likely(!ZERO_OR_NULL_PTR(addr))) { + memzero_explicit((void *)addr, len); + kvfree(addr); + } +} +EXPORT_SYMBOL(kvfree_sensitive); + +void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags) +{ + void *newp; + + if (oldsize >= newsize) + return (void *)p; + newp = kvmalloc(newsize, flags); + if (!newp) + return NULL; + memcpy(newp, p, oldsize); + kvfree(p); + return newp; +} +EXPORT_SYMBOL(kvrealloc); + +static inline void *__page_rmapping(struct page *page) +{ + unsigned long mapping; + + mapping = (unsigned long)page->mapping; + mapping &= ~PAGE_MAPPING_FLAGS; + + return (void *)mapping; +} + +/* Neutral page->mapping pointer to address_space or anon_vma or other */ +void *page_rmapping(struct page *page) +{ + page = compound_head(page); + return __page_rmapping(page); +} + +/* + * Return true if this page is mapped into pagetables. + * For compound page it returns true if any subpage of compound page is mapped. + */ +bool page_mapped(struct page *page) +{ + int i; + + if (likely(!PageCompound(page))) + return atomic_read(&page->_mapcount) >= 0; + page = compound_head(page); + if (atomic_read(compound_mapcount_ptr(page)) >= 0) + return true; + if (PageHuge(page)) + return false; + for (i = 0; i < compound_nr(page); i++) { + if (atomic_read(&page[i]._mapcount) >= 0) + return true; + } + return false; +} +EXPORT_SYMBOL(page_mapped); + +struct anon_vma *page_anon_vma(struct page *page) +{ + unsigned long mapping; + + page = compound_head(page); + mapping = (unsigned long)page->mapping; + if ((mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) + return NULL; + return __page_rmapping(page); +} + +struct address_space *page_mapping(struct page *page) +{ + struct address_space *mapping; + + page = compound_head(page); + + /* This happens if someone calls flush_dcache_page on slab page */ + if (unlikely(PageSlab(page))) + return NULL; + + if (unlikely(PageSwapCache(page))) { + swp_entry_t entry; + + entry.val = page_private(page); + return swap_address_space(entry); + } + + mapping = page->mapping; + if ((unsigned long)mapping & PAGE_MAPPING_ANON) + return NULL; + + return (void *)((unsigned long)mapping & ~PAGE_MAPPING_FLAGS); +} +EXPORT_SYMBOL(page_mapping); + +/* + * For file cache pages, return the address_space, otherwise return NULL + */ +struct address_space *page_mapping_file(struct page *page) +{ + if (unlikely(PageSwapCache(page))) + return NULL; + return page_mapping(page); +} + +/* Slow path of page_mapcount() for compound pages */ +int __page_mapcount(struct page *page) +{ + int ret; + + ret = atomic_read(&page->_mapcount) + 1; + /* + * For file THP page->_mapcount contains total number of mapping + * of the page: no need to look into compound_mapcount. + */ + if (!PageAnon(page) && !PageHuge(page)) + return ret; + page = compound_head(page); + ret += atomic_read(compound_mapcount_ptr(page)) + 1; + if (PageDoubleMap(page)) + ret--; + return ret; +} +EXPORT_SYMBOL_GPL(__page_mapcount); + +int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS; +int sysctl_overcommit_ratio __read_mostly = 50; +unsigned long sysctl_overcommit_kbytes __read_mostly; +int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT; +unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */ +unsigned long sysctl_admin_reserve_kbytes __read_mostly = 1UL << 13; /* 8MB */ + +int overcommit_ratio_handler(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret; + + ret = proc_dointvec(table, write, buffer, lenp, ppos); + if (ret == 0 && write) + sysctl_overcommit_kbytes = 0; + return ret; +} + +static void sync_overcommit_as(struct work_struct *dummy) +{ + percpu_counter_sync(&vm_committed_as); +} + +int overcommit_policy_handler(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos) +{ + struct ctl_table t; + int new_policy = -1; + int ret; + + /* + * The deviation of sync_overcommit_as could be big with loose policy + * like OVERCOMMIT_ALWAYS/OVERCOMMIT_GUESS. When changing policy to + * strict OVERCOMMIT_NEVER, we need to reduce the deviation to comply + * with the strict "NEVER", and to avoid possible race condtion (even + * though user usually won't too frequently do the switching to policy + * OVERCOMMIT_NEVER), the switch is done in the following order: + * 1. changing the batch + * 2. sync percpu count on each CPU + * 3. switch the policy + */ + if (write) { + t = *table; + t.data = &new_policy; + ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); + if (ret || new_policy == -1) + return ret; + + mm_compute_batch(new_policy); + if (new_policy == OVERCOMMIT_NEVER) + schedule_on_each_cpu(sync_overcommit_as); + sysctl_overcommit_memory = new_policy; + } else { + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + } + + return ret; +} + +int overcommit_kbytes_handler(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret; + + ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); + if (ret == 0 && write) + sysctl_overcommit_ratio = 0; + return ret; +} + +/* + * Committed memory limit enforced when OVERCOMMIT_NEVER policy is used + */ +unsigned long vm_commit_limit(void) +{ + unsigned long allowed; + + if (sysctl_overcommit_kbytes) + allowed = sysctl_overcommit_kbytes >> (PAGE_SHIFT - 10); + else + allowed = ((totalram_pages() - hugetlb_total_pages()) + * sysctl_overcommit_ratio / 100); + allowed += total_swap_pages; + + return allowed; +} + +/* + * Make sure vm_committed_as in one cacheline and not cacheline shared with + * other variables. It can be updated by several CPUs frequently. + */ +struct percpu_counter vm_committed_as ____cacheline_aligned_in_smp; + +/* + * The global memory commitment made in the system can be a metric + * that can be used to drive ballooning decisions when Linux is hosted + * as a guest. On Hyper-V, the host implements a policy engine for dynamically + * balancing memory across competing virtual machines that are hosted. + * Several metrics drive this policy engine including the guest reported + * memory commitment. + * + * The time cost of this is very low for small platforms, and for big + * platform like a 2S/36C/72T Skylake server, in worst case where + * vm_committed_as's spinlock is under severe contention, the time cost + * could be about 30~40 microseconds. + */ +unsigned long vm_memory_committed(void) +{ + return percpu_counter_sum_positive(&vm_committed_as); +} +EXPORT_SYMBOL_GPL(vm_memory_committed); + +/* + * Check that a process has enough memory to allocate a new virtual + * mapping. 0 means there is enough memory for the allocation to + * succeed and -ENOMEM implies there is not. + * + * We currently support three overcommit policies, which are set via the + * vm.overcommit_memory sysctl. See Documentation/vm/overcommit-accounting.rst + * + * Strict overcommit modes added 2002 Feb 26 by Alan Cox. + * Additional code 2002 Jul 20 by Robert Love. + * + * cap_sys_admin is 1 if the process has admin privileges, 0 otherwise. + * + * Note this is a helper function intended to be used by LSMs which + * wish to use this logic. + */ +int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) +{ + long allowed; + + vm_acct_memory(pages); + + /* + * Sometimes we want to use more memory than we have + */ + if (sysctl_overcommit_memory == OVERCOMMIT_ALWAYS) + return 0; + + if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) { + if (pages > totalram_pages() + total_swap_pages) + goto error; + return 0; + } + + allowed = vm_commit_limit(); + /* + * Reserve some for root + */ + if (!cap_sys_admin) + allowed -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10); + + /* + * Don't let a single process grow so big a user can't recover + */ + if (mm) { + long reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10); + + allowed -= min_t(long, mm->total_vm / 32, reserve); + } + + if (percpu_counter_read_positive(&vm_committed_as) < allowed) + return 0; +error: + vm_unacct_memory(pages); + + return -ENOMEM; +} + +/** + * get_cmdline() - copy the cmdline value to a buffer. + * @task: the task whose cmdline value to copy. + * @buffer: the buffer to copy to. + * @buflen: the length of the buffer. Larger cmdline values are truncated + * to this length. + * + * Return: the size of the cmdline field copied. Note that the copy does + * not guarantee an ending NULL byte. + */ +int get_cmdline(struct task_struct *task, char *buffer, int buflen) +{ + int res = 0; + unsigned int len; + struct mm_struct *mm = get_task_mm(task); + unsigned long arg_start, arg_end, env_start, env_end; + if (!mm) + goto out; + if (!mm->arg_end) + goto out_mm; /* Shh! No looking before we're done */ + + spin_lock(&mm->arg_lock); + arg_start = mm->arg_start; + arg_end = mm->arg_end; + env_start = mm->env_start; + env_end = mm->env_end; + spin_unlock(&mm->arg_lock); + + len = arg_end - arg_start; + + if (len > buflen) + len = buflen; + + res = access_process_vm(task, arg_start, buffer, len, FOLL_FORCE); + + /* + * If the nul at the end of args has been overwritten, then + * assume application is using setproctitle(3). + */ + if (res > 0 && buffer[res-1] != '\0' && len < buflen) { + len = strnlen(buffer, res); + if (len < res) { + res = len; + } else { + len = env_end - env_start; + if (len > buflen - res) + len = buflen - res; + res += access_process_vm(task, env_start, + buffer+res, len, + FOLL_FORCE); + res = strnlen(buffer, res); + } + } +out_mm: + mmput(mm); +out: + return res; +} + +int __weak memcmp_pages(struct page *page1, struct page *page2) +{ + char *addr1, *addr2; + int ret; + + addr1 = kmap_atomic(page1); + addr2 = kmap_atomic(page2); + ret = memcmp(addr1, addr2, PAGE_SIZE); + kunmap_atomic(addr2); + kunmap_atomic(addr1); + return ret; +} diff --git a/mm/vmacache.c b/mm/vmacache.c new file mode 100644 index 000000000..01a6e6688 --- /dev/null +++ b/mm/vmacache.c @@ -0,0 +1,117 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2014 Davidlohr Bueso. + */ +#include +#include +#include +#include + +/* + * Hash based on the pmd of addr if configured with MMU, which provides a good + * hit rate for workloads with spatial locality. Otherwise, use pages. + */ +#ifdef CONFIG_MMU +#define VMACACHE_SHIFT PMD_SHIFT +#else +#define VMACACHE_SHIFT PAGE_SHIFT +#endif +#define VMACACHE_HASH(addr) ((addr >> VMACACHE_SHIFT) & VMACACHE_MASK) + +/* + * This task may be accessing a foreign mm via (for example) + * get_user_pages()->find_vma(). The vmacache is task-local and this + * task's vmacache pertains to a different mm (ie, its own). There is + * nothing we can do here. + * + * Also handle the case where a kernel thread has adopted this mm via + * kthread_use_mm(). That kernel thread's vmacache is not applicable to this mm. + */ +static inline bool vmacache_valid_mm(struct mm_struct *mm) +{ + return current->mm == mm && !(current->flags & PF_KTHREAD); +} + +void vmacache_update(unsigned long addr, struct vm_area_struct *newvma) +{ + if (vmacache_valid_mm(newvma->vm_mm)) + current->vmacache.vmas[VMACACHE_HASH(addr)] = newvma; +} + +static bool vmacache_valid(struct mm_struct *mm) +{ + struct task_struct *curr; + + if (!vmacache_valid_mm(mm)) + return false; + + curr = current; + if (mm->vmacache_seqnum != curr->vmacache.seqnum) { + /* + * First attempt will always be invalid, initialize + * the new cache for this task here. + */ + curr->vmacache.seqnum = mm->vmacache_seqnum; + vmacache_flush(curr); + return false; + } + return true; +} + +struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr) +{ + int idx = VMACACHE_HASH(addr); + int i; + + count_vm_vmacache_event(VMACACHE_FIND_CALLS); + + if (!vmacache_valid(mm)) + return NULL; + + for (i = 0; i < VMACACHE_SIZE; i++) { + struct vm_area_struct *vma = current->vmacache.vmas[idx]; + + if (vma) { +#ifdef CONFIG_DEBUG_VM_VMACACHE + if (WARN_ON_ONCE(vma->vm_mm != mm)) + break; +#endif + if (vma->vm_start <= addr && vma->vm_end > addr) { + count_vm_vmacache_event(VMACACHE_FIND_HITS); + return vma; + } + } + if (++idx == VMACACHE_SIZE) + idx = 0; + } + + return NULL; +} + +#ifndef CONFIG_MMU +struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm, + unsigned long start, + unsigned long end) +{ + int idx = VMACACHE_HASH(start); + int i; + + count_vm_vmacache_event(VMACACHE_FIND_CALLS); + + if (!vmacache_valid(mm)) + return NULL; + + for (i = 0; i < VMACACHE_SIZE; i++) { + struct vm_area_struct *vma = current->vmacache.vmas[idx]; + + if (vma && vma->vm_start == start && vma->vm_end == end) { + count_vm_vmacache_event(VMACACHE_FIND_HITS); + return vma; + } + if (++idx == VMACACHE_SIZE) + idx = 0; + } + + return NULL; +} +#endif diff --git a/mm/vmalloc.c b/mm/vmalloc.c new file mode 100644 index 000000000..d6a4794fa --- /dev/null +++ b/mm/vmalloc.c @@ -0,0 +1,3589 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 1993 Linus Torvalds + * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 + * SMP-safe vmalloc/vfree/ioremap, Tigran Aivazian , May 2000 + * Major rework to support vmap/vunmap, Christoph Hellwig, SGI, August 2002 + * Numa awareness, Christoph Lameter, SGI, June 2005 + * Improving global KVA allocator, Uladzislau Rezki, Sony, May 2019 + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +#include "internal.h" +#include "pgalloc-track.h" + +bool is_vmalloc_addr(const void *x) +{ + unsigned long addr = (unsigned long)x; + + return addr >= VMALLOC_START && addr < VMALLOC_END; +} +EXPORT_SYMBOL(is_vmalloc_addr); + +struct vfree_deferred { + struct llist_head list; + struct work_struct wq; +}; +static DEFINE_PER_CPU(struct vfree_deferred, vfree_deferred); + +static void __vunmap(const void *, int); + +static void free_work(struct work_struct *w) +{ + struct vfree_deferred *p = container_of(w, struct vfree_deferred, wq); + struct llist_node *t, *llnode; + + llist_for_each_safe(llnode, t, llist_del_all(&p->list)) + __vunmap((void *)llnode, 1); +} + +/*** Page table manipulation functions ***/ + +static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, + pgtbl_mod_mask *mask) +{ + pte_t *pte; + + pte = pte_offset_kernel(pmd, addr); + do { + pte_t ptent = ptep_get_and_clear(&init_mm, addr, pte); + WARN_ON(!pte_none(ptent) && !pte_present(ptent)); + } while (pte++, addr += PAGE_SIZE, addr != end); + *mask |= PGTBL_PTE_MODIFIED; +} + +static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, + pgtbl_mod_mask *mask) +{ + pmd_t *pmd; + unsigned long next; + int cleared; + + pmd = pmd_offset(pud, addr); + do { + next = pmd_addr_end(addr, end); + + cleared = pmd_clear_huge(pmd); + if (cleared || pmd_bad(*pmd)) + *mask |= PGTBL_PMD_MODIFIED; + + if (cleared) + continue; + if (pmd_none_or_clear_bad(pmd)) + continue; + vunmap_pte_range(pmd, addr, next, mask); + + cond_resched(); + } while (pmd++, addr = next, addr != end); +} + +static void vunmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, + pgtbl_mod_mask *mask) +{ + pud_t *pud; + unsigned long next; + int cleared; + + pud = pud_offset(p4d, addr); + do { + next = pud_addr_end(addr, end); + + cleared = pud_clear_huge(pud); + if (cleared || pud_bad(*pud)) + *mask |= PGTBL_PUD_MODIFIED; + + if (cleared) + continue; + if (pud_none_or_clear_bad(pud)) + continue; + vunmap_pmd_range(pud, addr, next, mask); + } while (pud++, addr = next, addr != end); +} + +static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, + pgtbl_mod_mask *mask) +{ + p4d_t *p4d; + unsigned long next; + int cleared; + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + + cleared = p4d_clear_huge(p4d); + if (cleared || p4d_bad(*p4d)) + *mask |= PGTBL_P4D_MODIFIED; + + if (cleared) + continue; + if (p4d_none_or_clear_bad(p4d)) + continue; + vunmap_pud_range(p4d, addr, next, mask); + } while (p4d++, addr = next, addr != end); +} + +/** + * unmap_kernel_range_noflush - unmap kernel VM area + * @start: start of the VM area to unmap + * @size: size of the VM area to unmap + * + * Unmap PFN_UP(@size) pages at @addr. The VM area @addr and @size specify + * should have been allocated using get_vm_area() and its friends. + * + * NOTE: + * This function does NOT do any cache flushing. The caller is responsible + * for calling flush_cache_vunmap() on to-be-mapped areas before calling this + * function and flush_tlb_kernel_range() after. + */ +void unmap_kernel_range_noflush(unsigned long start, unsigned long size) +{ + unsigned long end = start + size; + unsigned long next; + pgd_t *pgd; + unsigned long addr = start; + pgtbl_mod_mask mask = 0; + + BUG_ON(addr >= end); + pgd = pgd_offset_k(addr); + do { + next = pgd_addr_end(addr, end); + if (pgd_bad(*pgd)) + mask |= PGTBL_PGD_MODIFIED; + if (pgd_none_or_clear_bad(pgd)) + continue; + vunmap_p4d_range(pgd, addr, next, &mask); + } while (pgd++, addr = next, addr != end); + + if (mask & ARCH_PAGE_TABLE_SYNC_MASK) + arch_sync_kernel_mappings(start, end); +} + +static int vmap_pte_range(pmd_t *pmd, unsigned long addr, + unsigned long end, pgprot_t prot, struct page **pages, int *nr, + pgtbl_mod_mask *mask) +{ + pte_t *pte; + + /* + * nr is a running index into the array which helps higher level + * callers keep track of where we're up to. + */ + + pte = pte_alloc_kernel_track(pmd, addr, mask); + if (!pte) + return -ENOMEM; + do { + struct page *page = pages[*nr]; + + if (WARN_ON(!pte_none(*pte))) + return -EBUSY; + if (WARN_ON(!page)) + return -ENOMEM; + set_pte_at(&init_mm, addr, pte, mk_pte(page, prot)); + (*nr)++; + } while (pte++, addr += PAGE_SIZE, addr != end); + *mask |= PGTBL_PTE_MODIFIED; + return 0; +} + +static int vmap_pmd_range(pud_t *pud, unsigned long addr, + unsigned long end, pgprot_t prot, struct page **pages, int *nr, + pgtbl_mod_mask *mask) +{ + pmd_t *pmd; + unsigned long next; + + pmd = pmd_alloc_track(&init_mm, pud, addr, mask); + if (!pmd) + return -ENOMEM; + do { + next = pmd_addr_end(addr, end); + if (vmap_pte_range(pmd, addr, next, prot, pages, nr, mask)) + return -ENOMEM; + } while (pmd++, addr = next, addr != end); + return 0; +} + +static int vmap_pud_range(p4d_t *p4d, unsigned long addr, + unsigned long end, pgprot_t prot, struct page **pages, int *nr, + pgtbl_mod_mask *mask) +{ + pud_t *pud; + unsigned long next; + + pud = pud_alloc_track(&init_mm, p4d, addr, mask); + if (!pud) + return -ENOMEM; + do { + next = pud_addr_end(addr, end); + if (vmap_pmd_range(pud, addr, next, prot, pages, nr, mask)) + return -ENOMEM; + } while (pud++, addr = next, addr != end); + return 0; +} + +static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, + unsigned long end, pgprot_t prot, struct page **pages, int *nr, + pgtbl_mod_mask *mask) +{ + p4d_t *p4d; + unsigned long next; + + p4d = p4d_alloc_track(&init_mm, pgd, addr, mask); + if (!p4d) + return -ENOMEM; + do { + next = p4d_addr_end(addr, end); + if (vmap_pud_range(p4d, addr, next, prot, pages, nr, mask)) + return -ENOMEM; + } while (p4d++, addr = next, addr != end); + return 0; +} + +/** + * map_kernel_range_noflush - map kernel VM area with the specified pages + * @addr: start of the VM area to map + * @size: size of the VM area to map + * @prot: page protection flags to use + * @pages: pages to map + * + * Map PFN_UP(@size) pages at @addr. The VM area @addr and @size specify should + * have been allocated using get_vm_area() and its friends. + * + * NOTE: + * This function does NOT do any cache flushing. The caller is responsible for + * calling flush_cache_vmap() on to-be-mapped areas before calling this + * function. + * + * RETURNS: + * 0 on success, -errno on failure. + */ +int map_kernel_range_noflush(unsigned long addr, unsigned long size, + pgprot_t prot, struct page **pages) +{ + unsigned long start = addr; + unsigned long end = addr + size; + unsigned long next; + pgd_t *pgd; + int err = 0; + int nr = 0; + pgtbl_mod_mask mask = 0; + + BUG_ON(addr >= end); + pgd = pgd_offset_k(addr); + do { + next = pgd_addr_end(addr, end); + if (pgd_bad(*pgd)) + mask |= PGTBL_PGD_MODIFIED; + err = vmap_p4d_range(pgd, addr, next, prot, pages, &nr, &mask); + if (err) + return err; + } while (pgd++, addr = next, addr != end); + + if (mask & ARCH_PAGE_TABLE_SYNC_MASK) + arch_sync_kernel_mappings(start, end); + + return 0; +} + +int map_kernel_range(unsigned long start, unsigned long size, pgprot_t prot, + struct page **pages) +{ + int ret; + + ret = map_kernel_range_noflush(start, size, prot, pages); + flush_cache_vmap(start, start + size); + return ret; +} + +int is_vmalloc_or_module_addr(const void *x) +{ + /* + * ARM, x86-64 and sparc64 put modules in a special place, + * and fall back on vmalloc() if that fails. Others + * just put it in the vmalloc space. + */ +#if defined(CONFIG_MODULES) && defined(MODULES_VADDR) + unsigned long addr = (unsigned long)x; + if (addr >= MODULES_VADDR && addr < MODULES_END) + return 1; +#endif + return is_vmalloc_addr(x); +} + +/* + * Walk a vmap address to the struct page it maps. + */ +struct page *vmalloc_to_page(const void *vmalloc_addr) +{ + unsigned long addr = (unsigned long) vmalloc_addr; + struct page *page = NULL; + pgd_t *pgd = pgd_offset_k(addr); + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *ptep, pte; + + /* + * XXX we might need to change this if we add VIRTUAL_BUG_ON for + * architectures that do not vmalloc module space + */ + VIRTUAL_BUG_ON(!is_vmalloc_or_module_addr(vmalloc_addr)); + + if (pgd_none(*pgd)) + return NULL; + p4d = p4d_offset(pgd, addr); + if (p4d_none(*p4d)) + return NULL; + pud = pud_offset(p4d, addr); + + /* + * Don't dereference bad PUD or PMD (below) entries. This will also + * identify huge mappings, which we may encounter on architectures + * that define CONFIG_HAVE_ARCH_HUGE_VMAP=y. Such regions will be + * identified as vmalloc addresses by is_vmalloc_addr(), but are + * not [unambiguously] associated with a struct page, so there is + * no correct value to return for them. + */ + WARN_ON_ONCE(pud_bad(*pud)); + if (pud_none(*pud) || pud_bad(*pud)) + return NULL; + pmd = pmd_offset(pud, addr); + WARN_ON_ONCE(pmd_bad(*pmd)); + if (pmd_none(*pmd) || pmd_bad(*pmd)) + return NULL; + + ptep = pte_offset_map(pmd, addr); + pte = *ptep; + if (pte_present(pte)) + page = pte_page(pte); + pte_unmap(ptep); + return page; +} +EXPORT_SYMBOL(vmalloc_to_page); + +/* + * Map a vmalloc()-space virtual address to the physical page frame number. + */ +unsigned long vmalloc_to_pfn(const void *vmalloc_addr) +{ + return page_to_pfn(vmalloc_to_page(vmalloc_addr)); +} +EXPORT_SYMBOL(vmalloc_to_pfn); + + +/*** Global kva allocator ***/ + +#define DEBUG_AUGMENT_PROPAGATE_CHECK 0 +#define DEBUG_AUGMENT_LOWEST_MATCH_CHECK 0 + + +static DEFINE_SPINLOCK(vmap_area_lock); +static DEFINE_SPINLOCK(free_vmap_area_lock); +/* Export for kexec only */ +LIST_HEAD(vmap_area_list); +static LLIST_HEAD(vmap_purge_list); +static struct rb_root vmap_area_root = RB_ROOT; +static bool vmap_initialized __read_mostly; + +/* + * This kmem_cache is used for vmap_area objects. Instead of + * allocating from slab we reuse an object from this cache to + * make things faster. Especially in "no edge" splitting of + * free block. + */ +static struct kmem_cache *vmap_area_cachep; + +/* + * This linked list is used in pair with free_vmap_area_root. + * It gives O(1) access to prev/next to perform fast coalescing. + */ +static LIST_HEAD(free_vmap_area_list); + +/* + * This augment red-black tree represents the free vmap space. + * All vmap_area objects in this tree are sorted by va->va_start + * address. It is used for allocation and merging when a vmap + * object is released. + * + * Each vmap_area node contains a maximum available free block + * of its sub-tree, right or left. Therefore it is possible to + * find a lowest match of free area. + */ +static struct rb_root free_vmap_area_root = RB_ROOT; + +/* + * Preload a CPU with one object for "no edge" split case. The + * aim is to get rid of allocations from the atomic context, thus + * to use more permissive allocation masks. + */ +static DEFINE_PER_CPU(struct vmap_area *, ne_fit_preload_node); + +static __always_inline unsigned long +va_size(struct vmap_area *va) +{ + return (va->va_end - va->va_start); +} + +static __always_inline unsigned long +get_subtree_max_size(struct rb_node *node) +{ + struct vmap_area *va; + + va = rb_entry_safe(node, struct vmap_area, rb_node); + return va ? va->subtree_max_size : 0; +} + +/* + * Gets called when remove the node and rotate. + */ +static __always_inline unsigned long +compute_subtree_max_size(struct vmap_area *va) +{ + return max3(va_size(va), + get_subtree_max_size(va->rb_node.rb_left), + get_subtree_max_size(va->rb_node.rb_right)); +} + +RB_DECLARE_CALLBACKS_MAX(static, free_vmap_area_rb_augment_cb, + struct vmap_area, rb_node, unsigned long, subtree_max_size, va_size) + +static void purge_vmap_area_lazy(void); +static BLOCKING_NOTIFIER_HEAD(vmap_notify_list); +static unsigned long lazy_max_pages(void); + +static atomic_long_t nr_vmalloc_pages; + +unsigned long vmalloc_nr_pages(void) +{ + return atomic_long_read(&nr_vmalloc_pages); +} + +static struct vmap_area *__find_vmap_area(unsigned long addr) +{ + struct rb_node *n = vmap_area_root.rb_node; + + while (n) { + struct vmap_area *va; + + va = rb_entry(n, struct vmap_area, rb_node); + if (addr < va->va_start) + n = n->rb_left; + else if (addr >= va->va_end) + n = n->rb_right; + else + return va; + } + + return NULL; +} + +/* + * This function returns back addresses of parent node + * and its left or right link for further processing. + * + * Otherwise NULL is returned. In that case all further + * steps regarding inserting of conflicting overlap range + * have to be declined and actually considered as a bug. + */ +static __always_inline struct rb_node ** +find_va_links(struct vmap_area *va, + struct rb_root *root, struct rb_node *from, + struct rb_node **parent) +{ + struct vmap_area *tmp_va; + struct rb_node **link; + + if (root) { + link = &root->rb_node; + if (unlikely(!*link)) { + *parent = NULL; + return link; + } + } else { + link = &from; + } + + /* + * Go to the bottom of the tree. When we hit the last point + * we end up with parent rb_node and correct direction, i name + * it link, where the new va->rb_node will be attached to. + */ + do { + tmp_va = rb_entry(*link, struct vmap_area, rb_node); + + /* + * During the traversal we also do some sanity check. + * Trigger the BUG() if there are sides(left/right) + * or full overlaps. + */ + if (va->va_start < tmp_va->va_end && + va->va_end <= tmp_va->va_start) + link = &(*link)->rb_left; + else if (va->va_end > tmp_va->va_start && + va->va_start >= tmp_va->va_end) + link = &(*link)->rb_right; + else { + WARN(1, "vmalloc bug: 0x%lx-0x%lx overlaps with 0x%lx-0x%lx\n", + va->va_start, va->va_end, tmp_va->va_start, tmp_va->va_end); + + return NULL; + } + } while (*link); + + *parent = &tmp_va->rb_node; + return link; +} + +static __always_inline struct list_head * +get_va_next_sibling(struct rb_node *parent, struct rb_node **link) +{ + struct list_head *list; + + if (unlikely(!parent)) + /* + * The red-black tree where we try to find VA neighbors + * before merging or inserting is empty, i.e. it means + * there is no free vmap space. Normally it does not + * happen but we handle this case anyway. + */ + return NULL; + + list = &rb_entry(parent, struct vmap_area, rb_node)->list; + return (&parent->rb_right == link ? list->next : list); +} + +static __always_inline void +link_va(struct vmap_area *va, struct rb_root *root, + struct rb_node *parent, struct rb_node **link, struct list_head *head) +{ + /* + * VA is still not in the list, but we can + * identify its future previous list_head node. + */ + if (likely(parent)) { + head = &rb_entry(parent, struct vmap_area, rb_node)->list; + if (&parent->rb_right != link) + head = head->prev; + } + + /* Insert to the rb-tree */ + rb_link_node(&va->rb_node, parent, link); + if (root == &free_vmap_area_root) { + /* + * Some explanation here. Just perform simple insertion + * to the tree. We do not set va->subtree_max_size to + * its current size before calling rb_insert_augmented(). + * It is because of we populate the tree from the bottom + * to parent levels when the node _is_ in the tree. + * + * Therefore we set subtree_max_size to zero after insertion, + * to let __augment_tree_propagate_from() puts everything to + * the correct order later on. + */ + rb_insert_augmented(&va->rb_node, + root, &free_vmap_area_rb_augment_cb); + va->subtree_max_size = 0; + } else { + rb_insert_color(&va->rb_node, root); + } + + /* Address-sort this list */ + list_add(&va->list, head); +} + +static __always_inline void +unlink_va(struct vmap_area *va, struct rb_root *root) +{ + if (WARN_ON(RB_EMPTY_NODE(&va->rb_node))) + return; + + if (root == &free_vmap_area_root) + rb_erase_augmented(&va->rb_node, + root, &free_vmap_area_rb_augment_cb); + else + rb_erase(&va->rb_node, root); + + list_del(&va->list); + RB_CLEAR_NODE(&va->rb_node); +} + +#if DEBUG_AUGMENT_PROPAGATE_CHECK +static void +augment_tree_propagate_check(void) +{ + struct vmap_area *va; + unsigned long computed_size; + + list_for_each_entry(va, &free_vmap_area_list, list) { + computed_size = compute_subtree_max_size(va); + if (computed_size != va->subtree_max_size) + pr_emerg("tree is corrupted: %lu, %lu\n", + va_size(va), va->subtree_max_size); + } +} +#endif + +/* + * This function populates subtree_max_size from bottom to upper + * levels starting from VA point. The propagation must be done + * when VA size is modified by changing its va_start/va_end. Or + * in case of newly inserting of VA to the tree. + * + * It means that __augment_tree_propagate_from() must be called: + * - After VA has been inserted to the tree(free path); + * - After VA has been shrunk(allocation path); + * - After VA has been increased(merging path). + * + * Please note that, it does not mean that upper parent nodes + * and their subtree_max_size are recalculated all the time up + * to the root node. + * + * 4--8 + * /\ + * / \ + * / \ + * 2--2 8--8 + * + * For example if we modify the node 4, shrinking it to 2, then + * no any modification is required. If we shrink the node 2 to 1 + * its subtree_max_size is updated only, and set to 1. If we shrink + * the node 8 to 6, then its subtree_max_size is set to 6 and parent + * node becomes 4--6. + */ +static __always_inline void +augment_tree_propagate_from(struct vmap_area *va) +{ + /* + * Populate the tree from bottom towards the root until + * the calculated maximum available size of checked node + * is equal to its current one. + */ + free_vmap_area_rb_augment_cb_propagate(&va->rb_node, NULL); + +#if DEBUG_AUGMENT_PROPAGATE_CHECK + augment_tree_propagate_check(); +#endif +} + +static void +insert_vmap_area(struct vmap_area *va, + struct rb_root *root, struct list_head *head) +{ + struct rb_node **link; + struct rb_node *parent; + + link = find_va_links(va, root, NULL, &parent); + if (link) + link_va(va, root, parent, link, head); +} + +static void +insert_vmap_area_augment(struct vmap_area *va, + struct rb_node *from, struct rb_root *root, + struct list_head *head) +{ + struct rb_node **link; + struct rb_node *parent; + + if (from) + link = find_va_links(va, NULL, from, &parent); + else + link = find_va_links(va, root, NULL, &parent); + + if (link) { + link_va(va, root, parent, link, head); + augment_tree_propagate_from(va); + } +} + +/* + * Merge de-allocated chunk of VA memory with previous + * and next free blocks. If coalesce is not done a new + * free area is inserted. If VA has been merged, it is + * freed. + * + * Please note, it can return NULL in case of overlap + * ranges, followed by WARN() report. Despite it is a + * buggy behaviour, a system can be alive and keep + * ongoing. + */ +static __always_inline struct vmap_area * +merge_or_add_vmap_area(struct vmap_area *va, + struct rb_root *root, struct list_head *head) +{ + struct vmap_area *sibling; + struct list_head *next; + struct rb_node **link; + struct rb_node *parent; + bool merged = false; + + /* + * Find a place in the tree where VA potentially will be + * inserted, unless it is merged with its sibling/siblings. + */ + link = find_va_links(va, root, NULL, &parent); + if (!link) + return NULL; + + /* + * Get next node of VA to check if merging can be done. + */ + next = get_va_next_sibling(parent, link); + if (unlikely(next == NULL)) + goto insert; + + /* + * start end + * | | + * |<------VA------>|<-----Next----->| + * | | + * start end + */ + if (next != head) { + sibling = list_entry(next, struct vmap_area, list); + if (sibling->va_start == va->va_end) { + sibling->va_start = va->va_start; + + /* Free vmap_area object. */ + kmem_cache_free(vmap_area_cachep, va); + + /* Point to the new merged area. */ + va = sibling; + merged = true; + } + } + + /* + * start end + * | | + * |<-----Prev----->|<------VA------>| + * | | + * start end + */ + if (next->prev != head) { + sibling = list_entry(next->prev, struct vmap_area, list); + if (sibling->va_end == va->va_start) { + /* + * If both neighbors are coalesced, it is important + * to unlink the "next" node first, followed by merging + * with "previous" one. Otherwise the tree might not be + * fully populated if a sibling's augmented value is + * "normalized" because of rotation operations. + */ + if (merged) + unlink_va(va, root); + + sibling->va_end = va->va_end; + + /* Free vmap_area object. */ + kmem_cache_free(vmap_area_cachep, va); + + /* Point to the new merged area. */ + va = sibling; + merged = true; + } + } + +insert: + if (!merged) + link_va(va, root, parent, link, head); + + /* + * Last step is to check and update the tree. + */ + augment_tree_propagate_from(va); + return va; +} + +static __always_inline bool +is_within_this_va(struct vmap_area *va, unsigned long size, + unsigned long align, unsigned long vstart) +{ + unsigned long nva_start_addr; + + if (va->va_start > vstart) + nva_start_addr = ALIGN(va->va_start, align); + else + nva_start_addr = ALIGN(vstart, align); + + /* Can be overflowed due to big size or alignment. */ + if (nva_start_addr + size < nva_start_addr || + nva_start_addr < vstart) + return false; + + return (nva_start_addr + size <= va->va_end); +} + +/* + * Find the first free block(lowest start address) in the tree, + * that will accomplish the request corresponding to passing + * parameters. + */ +static __always_inline struct vmap_area * +find_vmap_lowest_match(unsigned long size, + unsigned long align, unsigned long vstart) +{ + struct vmap_area *va; + struct rb_node *node; + unsigned long length; + + /* Start from the root. */ + node = free_vmap_area_root.rb_node; + + /* Adjust the search size for alignment overhead. */ + length = size + align - 1; + + while (node) { + va = rb_entry(node, struct vmap_area, rb_node); + + if (get_subtree_max_size(node->rb_left) >= length && + vstart < va->va_start) { + node = node->rb_left; + } else { + if (is_within_this_va(va, size, align, vstart)) + return va; + + /* + * Does not make sense to go deeper towards the right + * sub-tree if it does not have a free block that is + * equal or bigger to the requested search length. + */ + if (get_subtree_max_size(node->rb_right) >= length) { + node = node->rb_right; + continue; + } + + /* + * OK. We roll back and find the first right sub-tree, + * that will satisfy the search criteria. It can happen + * only once due to "vstart" restriction. + */ + while ((node = rb_parent(node))) { + va = rb_entry(node, struct vmap_area, rb_node); + if (is_within_this_va(va, size, align, vstart)) + return va; + + if (get_subtree_max_size(node->rb_right) >= length && + vstart <= va->va_start) { + node = node->rb_right; + break; + } + } + } + } + + return NULL; +} + +#if DEBUG_AUGMENT_LOWEST_MATCH_CHECK +#include + +static struct vmap_area * +find_vmap_lowest_linear_match(unsigned long size, + unsigned long align, unsigned long vstart) +{ + struct vmap_area *va; + + list_for_each_entry(va, &free_vmap_area_list, list) { + if (!is_within_this_va(va, size, align, vstart)) + continue; + + return va; + } + + return NULL; +} + +static void +find_vmap_lowest_match_check(unsigned long size) +{ + struct vmap_area *va_1, *va_2; + unsigned long vstart; + unsigned int rnd; + + get_random_bytes(&rnd, sizeof(rnd)); + vstart = VMALLOC_START + rnd; + + va_1 = find_vmap_lowest_match(size, 1, vstart); + va_2 = find_vmap_lowest_linear_match(size, 1, vstart); + + if (va_1 != va_2) + pr_emerg("not lowest: t: 0x%p, l: 0x%p, v: 0x%lx\n", + va_1, va_2, vstart); +} +#endif + +enum fit_type { + NOTHING_FIT = 0, + FL_FIT_TYPE = 1, /* full fit */ + LE_FIT_TYPE = 2, /* left edge fit */ + RE_FIT_TYPE = 3, /* right edge fit */ + NE_FIT_TYPE = 4 /* no edge fit */ +}; + +static __always_inline enum fit_type +classify_va_fit_type(struct vmap_area *va, + unsigned long nva_start_addr, unsigned long size) +{ + enum fit_type type; + + /* Check if it is within VA. */ + if (nva_start_addr < va->va_start || + nva_start_addr + size > va->va_end) + return NOTHING_FIT; + + /* Now classify. */ + if (va->va_start == nva_start_addr) { + if (va->va_end == nva_start_addr + size) + type = FL_FIT_TYPE; + else + type = LE_FIT_TYPE; + } else if (va->va_end == nva_start_addr + size) { + type = RE_FIT_TYPE; + } else { + type = NE_FIT_TYPE; + } + + return type; +} + +static __always_inline int +adjust_va_to_fit_type(struct vmap_area *va, + unsigned long nva_start_addr, unsigned long size, + enum fit_type type) +{ + struct vmap_area *lva = NULL; + + if (type == FL_FIT_TYPE) { + /* + * No need to split VA, it fully fits. + * + * | | + * V NVA V + * |---------------| + */ + unlink_va(va, &free_vmap_area_root); + kmem_cache_free(vmap_area_cachep, va); + } else if (type == LE_FIT_TYPE) { + /* + * Split left edge of fit VA. + * + * | | + * V NVA V R + * |-------|-------| + */ + va->va_start += size; + } else if (type == RE_FIT_TYPE) { + /* + * Split right edge of fit VA. + * + * | | + * L V NVA V + * |-------|-------| + */ + va->va_end = nva_start_addr; + } else if (type == NE_FIT_TYPE) { + /* + * Split no edge of fit VA. + * + * | | + * L V NVA V R + * |---|-------|---| + */ + lva = __this_cpu_xchg(ne_fit_preload_node, NULL); + if (unlikely(!lva)) { + /* + * For percpu allocator we do not do any pre-allocation + * and leave it as it is. The reason is it most likely + * never ends up with NE_FIT_TYPE splitting. In case of + * percpu allocations offsets and sizes are aligned to + * fixed align request, i.e. RE_FIT_TYPE and FL_FIT_TYPE + * are its main fitting cases. + * + * There are a few exceptions though, as an example it is + * a first allocation (early boot up) when we have "one" + * big free space that has to be split. + * + * Also we can hit this path in case of regular "vmap" + * allocations, if "this" current CPU was not preloaded. + * See the comment in alloc_vmap_area() why. If so, then + * GFP_NOWAIT is used instead to get an extra object for + * split purpose. That is rare and most time does not + * occur. + * + * What happens if an allocation gets failed. Basically, + * an "overflow" path is triggered to purge lazily freed + * areas to free some memory, then, the "retry" path is + * triggered to repeat one more time. See more details + * in alloc_vmap_area() function. + */ + lva = kmem_cache_alloc(vmap_area_cachep, GFP_NOWAIT); + if (!lva) + return -1; + } + + /* + * Build the remainder. + */ + lva->va_start = va->va_start; + lva->va_end = nva_start_addr; + + /* + * Shrink this VA to remaining size. + */ + va->va_start = nva_start_addr + size; + } else { + return -1; + } + + if (type != FL_FIT_TYPE) { + augment_tree_propagate_from(va); + + if (lva) /* type == NE_FIT_TYPE */ + insert_vmap_area_augment(lva, &va->rb_node, + &free_vmap_area_root, &free_vmap_area_list); + } + + return 0; +} + +/* + * Returns a start address of the newly allocated area, if success. + * Otherwise a vend is returned that indicates failure. + */ +static __always_inline unsigned long +__alloc_vmap_area(unsigned long size, unsigned long align, + unsigned long vstart, unsigned long vend) +{ + unsigned long nva_start_addr; + struct vmap_area *va; + enum fit_type type; + int ret; + + va = find_vmap_lowest_match(size, align, vstart); + if (unlikely(!va)) + return vend; + + if (va->va_start > vstart) + nva_start_addr = ALIGN(va->va_start, align); + else + nva_start_addr = ALIGN(vstart, align); + + /* Check the "vend" restriction. */ + if (nva_start_addr + size > vend) + return vend; + + /* Classify what we have found. */ + type = classify_va_fit_type(va, nva_start_addr, size); + if (WARN_ON_ONCE(type == NOTHING_FIT)) + return vend; + + /* Update the free vmap_area. */ + ret = adjust_va_to_fit_type(va, nva_start_addr, size, type); + if (ret) + return vend; + +#if DEBUG_AUGMENT_LOWEST_MATCH_CHECK + find_vmap_lowest_match_check(size); +#endif + + return nva_start_addr; +} + +/* + * Free a region of KVA allocated by alloc_vmap_area + */ +static void free_vmap_area(struct vmap_area *va) +{ + /* + * Remove from the busy tree/list. + */ + spin_lock(&vmap_area_lock); + unlink_va(va, &vmap_area_root); + spin_unlock(&vmap_area_lock); + + /* + * Insert/Merge it back to the free tree/list. + */ + spin_lock(&free_vmap_area_lock); + merge_or_add_vmap_area(va, &free_vmap_area_root, &free_vmap_area_list); + spin_unlock(&free_vmap_area_lock); +} + +/* + * Allocate a region of KVA of the specified size and alignment, within the + * vstart and vend. + */ +static struct vmap_area *alloc_vmap_area(unsigned long size, + unsigned long align, + unsigned long vstart, unsigned long vend, + int node, gfp_t gfp_mask) +{ + struct vmap_area *va, *pva; + unsigned long addr; + int purged = 0; + int ret; + + BUG_ON(!size); + BUG_ON(offset_in_page(size)); + BUG_ON(!is_power_of_2(align)); + + if (unlikely(!vmap_initialized)) + return ERR_PTR(-EBUSY); + + might_sleep(); + gfp_mask = gfp_mask & GFP_RECLAIM_MASK; + + va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node); + if (unlikely(!va)) + return ERR_PTR(-ENOMEM); + + /* + * Only scan the relevant parts containing pointers to other objects + * to avoid false negatives. + */ + kmemleak_scan_area(&va->rb_node, SIZE_MAX, gfp_mask); + +retry: + /* + * Preload this CPU with one extra vmap_area object. It is used + * when fit type of free area is NE_FIT_TYPE. Please note, it + * does not guarantee that an allocation occurs on a CPU that + * is preloaded, instead we minimize the case when it is not. + * It can happen because of cpu migration, because there is a + * race until the below spinlock is taken. + * + * The preload is done in non-atomic context, thus it allows us + * to use more permissive allocation masks to be more stable under + * low memory condition and high memory pressure. In rare case, + * if not preloaded, GFP_NOWAIT is used. + * + * Set "pva" to NULL here, because of "retry" path. + */ + pva = NULL; + + if (!this_cpu_read(ne_fit_preload_node)) + /* + * Even if it fails we do not really care about that. + * Just proceed as it is. If needed "overflow" path + * will refill the cache we allocate from. + */ + pva = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node); + + spin_lock(&free_vmap_area_lock); + + if (pva && __this_cpu_cmpxchg(ne_fit_preload_node, NULL, pva)) + kmem_cache_free(vmap_area_cachep, pva); + + /* + * If an allocation fails, the "vend" address is + * returned. Therefore trigger the overflow path. + */ + addr = __alloc_vmap_area(size, align, vstart, vend); + spin_unlock(&free_vmap_area_lock); + + if (unlikely(addr == vend)) + goto overflow; + + va->va_start = addr; + va->va_end = addr + size; + va->vm = NULL; + + + spin_lock(&vmap_area_lock); + insert_vmap_area(va, &vmap_area_root, &vmap_area_list); + spin_unlock(&vmap_area_lock); + + BUG_ON(!IS_ALIGNED(va->va_start, align)); + BUG_ON(va->va_start < vstart); + BUG_ON(va->va_end > vend); + + ret = kasan_populate_vmalloc(addr, size); + if (ret) { + free_vmap_area(va); + return ERR_PTR(ret); + } + + return va; + +overflow: + if (!purged) { + purge_vmap_area_lazy(); + purged = 1; + goto retry; + } + + if (gfpflags_allow_blocking(gfp_mask)) { + unsigned long freed = 0; + blocking_notifier_call_chain(&vmap_notify_list, 0, &freed); + if (freed > 0) { + purged = 0; + goto retry; + } + } + + if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit()) + pr_warn("vmap allocation for size %lu failed: use vmalloc= to increase size\n", + size); + + kmem_cache_free(vmap_area_cachep, va); + return ERR_PTR(-EBUSY); +} + +int register_vmap_purge_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&vmap_notify_list, nb); +} +EXPORT_SYMBOL_GPL(register_vmap_purge_notifier); + +int unregister_vmap_purge_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&vmap_notify_list, nb); +} +EXPORT_SYMBOL_GPL(unregister_vmap_purge_notifier); + +/* + * lazy_max_pages is the maximum amount of virtual address space we gather up + * before attempting to purge with a TLB flush. + * + * There is a tradeoff here: a larger number will cover more kernel page tables + * and take slightly longer to purge, but it will linearly reduce the number of + * global TLB flushes that must be performed. It would seem natural to scale + * this number up linearly with the number of CPUs (because vmapping activity + * could also scale linearly with the number of CPUs), however it is likely + * that in practice, workloads might be constrained in other ways that mean + * vmap activity will not scale linearly with CPUs. Also, I want to be + * conservative and not introduce a big latency on huge systems, so go with + * a less aggressive log scale. It will still be an improvement over the old + * code, and it will be simple to change the scale factor if we find that it + * becomes a problem on bigger systems. + */ +static unsigned long lazy_max_pages(void) +{ + unsigned int log; + + log = fls(num_online_cpus()); + + return log * (32UL * 1024 * 1024 / PAGE_SIZE); +} + +static atomic_long_t vmap_lazy_nr = ATOMIC_LONG_INIT(0); + +/* + * Serialize vmap purging. There is no actual criticial section protected + * by this look, but we want to avoid concurrent calls for performance + * reasons and to make the pcpu_get_vm_areas more deterministic. + */ +static DEFINE_MUTEX(vmap_purge_lock); + +/* for per-CPU blocks */ +static void purge_fragmented_blocks_allcpus(void); + +/* + * called before a call to iounmap() if the caller wants vm_area_struct's + * immediately freed. + */ +void set_iounmap_nonlazy(void) +{ + atomic_long_set(&vmap_lazy_nr, lazy_max_pages()+1); +} + +/* + * Purges all lazily-freed vmap areas. + */ +static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end) +{ + unsigned long resched_threshold; + struct llist_node *valist; + struct vmap_area *va; + struct vmap_area *n_va; + + lockdep_assert_held(&vmap_purge_lock); + + valist = llist_del_all(&vmap_purge_list); + if (unlikely(valist == NULL)) + return false; + + /* + * TODO: to calculate a flush range without looping. + * The list can be up to lazy_max_pages() elements. + */ + llist_for_each_entry(va, valist, purge_list) { + if (va->va_start < start) + start = va->va_start; + if (va->va_end > end) + end = va->va_end; + } + + flush_tlb_kernel_range(start, end); + resched_threshold = lazy_max_pages() << 1; + + spin_lock(&free_vmap_area_lock); + llist_for_each_entry_safe(va, n_va, valist, purge_list) { + unsigned long nr = (va->va_end - va->va_start) >> PAGE_SHIFT; + unsigned long orig_start = va->va_start; + unsigned long orig_end = va->va_end; + + /* + * Finally insert or merge lazily-freed area. It is + * detached and there is no need to "unlink" it from + * anything. + */ + va = merge_or_add_vmap_area(va, &free_vmap_area_root, + &free_vmap_area_list); + + if (!va) + continue; + + if (is_vmalloc_or_module_addr((void *)orig_start)) + kasan_release_vmalloc(orig_start, orig_end, + va->va_start, va->va_end); + + atomic_long_sub(nr, &vmap_lazy_nr); + + if (atomic_long_read(&vmap_lazy_nr) < resched_threshold) + cond_resched_lock(&free_vmap_area_lock); + } + spin_unlock(&free_vmap_area_lock); + return true; +} + +/* + * Kick off a purge of the outstanding lazy areas. Don't bother if somebody + * is already purging. + */ +static void try_purge_vmap_area_lazy(void) +{ + if (mutex_trylock(&vmap_purge_lock)) { + __purge_vmap_area_lazy(ULONG_MAX, 0); + mutex_unlock(&vmap_purge_lock); + } +} + +/* + * Kick off a purge of the outstanding lazy areas. + */ +static void purge_vmap_area_lazy(void) +{ + mutex_lock(&vmap_purge_lock); + purge_fragmented_blocks_allcpus(); + __purge_vmap_area_lazy(ULONG_MAX, 0); + mutex_unlock(&vmap_purge_lock); +} + +/* + * Free a vmap area, caller ensuring that the area has been unmapped + * and flush_cache_vunmap had been called for the correct range + * previously. + */ +static void free_vmap_area_noflush(struct vmap_area *va) +{ + unsigned long nr_lazy; + + spin_lock(&vmap_area_lock); + unlink_va(va, &vmap_area_root); + spin_unlock(&vmap_area_lock); + + nr_lazy = atomic_long_add_return((va->va_end - va->va_start) >> + PAGE_SHIFT, &vmap_lazy_nr); + + /* After this point, we may free va at any time */ + llist_add(&va->purge_list, &vmap_purge_list); + + if (unlikely(nr_lazy > lazy_max_pages())) + try_purge_vmap_area_lazy(); +} + +/* + * Free and unmap a vmap area + */ +static void free_unmap_vmap_area(struct vmap_area *va) +{ + flush_cache_vunmap(va->va_start, va->va_end); + unmap_kernel_range_noflush(va->va_start, va->va_end - va->va_start); + if (debug_pagealloc_enabled_static()) + flush_tlb_kernel_range(va->va_start, va->va_end); + + free_vmap_area_noflush(va); +} + +static struct vmap_area *find_vmap_area(unsigned long addr) +{ + struct vmap_area *va; + + spin_lock(&vmap_area_lock); + va = __find_vmap_area(addr); + spin_unlock(&vmap_area_lock); + + return va; +} + +/*** Per cpu kva allocator ***/ + +/* + * vmap space is limited especially on 32 bit architectures. Ensure there is + * room for at least 16 percpu vmap blocks per CPU. + */ +/* + * If we had a constant VMALLOC_START and VMALLOC_END, we'd like to be able + * to #define VMALLOC_SPACE (VMALLOC_END-VMALLOC_START). Guess + * instead (we just need a rough idea) + */ +#if BITS_PER_LONG == 32 +#define VMALLOC_SPACE (128UL*1024*1024) +#else +#define VMALLOC_SPACE (128UL*1024*1024*1024) +#endif + +#define VMALLOC_PAGES (VMALLOC_SPACE / PAGE_SIZE) +#define VMAP_MAX_ALLOC BITS_PER_LONG /* 256K with 4K pages */ +#define VMAP_BBMAP_BITS_MAX 1024 /* 4MB with 4K pages */ +#define VMAP_BBMAP_BITS_MIN (VMAP_MAX_ALLOC*2) +#define VMAP_MIN(x, y) ((x) < (y) ? (x) : (y)) /* can't use min() */ +#define VMAP_MAX(x, y) ((x) > (y) ? (x) : (y)) /* can't use max() */ +#define VMAP_BBMAP_BITS \ + VMAP_MIN(VMAP_BBMAP_BITS_MAX, \ + VMAP_MAX(VMAP_BBMAP_BITS_MIN, \ + VMALLOC_PAGES / roundup_pow_of_two(NR_CPUS) / 16)) + +#define VMAP_BLOCK_SIZE (VMAP_BBMAP_BITS * PAGE_SIZE) + +struct vmap_block_queue { + spinlock_t lock; + struct list_head free; +}; + +struct vmap_block { + spinlock_t lock; + struct vmap_area *va; + unsigned long free, dirty; + unsigned long dirty_min, dirty_max; /*< dirty range */ + struct list_head free_list; + struct rcu_head rcu_head; + struct list_head purge; +}; + +/* Queue of free and dirty vmap blocks, for allocation and flushing purposes */ +static DEFINE_PER_CPU(struct vmap_block_queue, vmap_block_queue); + +/* + * XArray of vmap blocks, indexed by address, to quickly find a vmap block + * in the free path. Could get rid of this if we change the API to return a + * "cookie" from alloc, to be passed to free. But no big deal yet. + */ +static DEFINE_XARRAY(vmap_blocks); + +/* + * We should probably have a fallback mechanism to allocate virtual memory + * out of partially filled vmap blocks. However vmap block sizing should be + * fairly reasonable according to the vmalloc size, so it shouldn't be a + * big problem. + */ + +static unsigned long addr_to_vb_idx(unsigned long addr) +{ + addr -= VMALLOC_START & ~(VMAP_BLOCK_SIZE-1); + addr /= VMAP_BLOCK_SIZE; + return addr; +} + +static void *vmap_block_vaddr(unsigned long va_start, unsigned long pages_off) +{ + unsigned long addr; + + addr = va_start + (pages_off << PAGE_SHIFT); + BUG_ON(addr_to_vb_idx(addr) != addr_to_vb_idx(va_start)); + return (void *)addr; +} + +/** + * new_vmap_block - allocates new vmap_block and occupies 2^order pages in this + * block. Of course pages number can't exceed VMAP_BBMAP_BITS + * @order: how many 2^order pages should be occupied in newly allocated block + * @gfp_mask: flags for the page level allocator + * + * Return: virtual address in a newly allocated block or ERR_PTR(-errno) + */ +static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) +{ + struct vmap_block_queue *vbq; + struct vmap_block *vb; + struct vmap_area *va; + unsigned long vb_idx; + int node, err; + void *vaddr; + + node = numa_node_id(); + + vb = kmalloc_node(sizeof(struct vmap_block), + gfp_mask & GFP_RECLAIM_MASK, node); + if (unlikely(!vb)) + return ERR_PTR(-ENOMEM); + + va = alloc_vmap_area(VMAP_BLOCK_SIZE, VMAP_BLOCK_SIZE, + VMALLOC_START, VMALLOC_END, + node, gfp_mask); + if (IS_ERR(va)) { + kfree(vb); + return ERR_CAST(va); + } + + vaddr = vmap_block_vaddr(va->va_start, 0); + spin_lock_init(&vb->lock); + vb->va = va; + /* At least something should be left free */ + BUG_ON(VMAP_BBMAP_BITS <= (1UL << order)); + vb->free = VMAP_BBMAP_BITS - (1UL << order); + vb->dirty = 0; + vb->dirty_min = VMAP_BBMAP_BITS; + vb->dirty_max = 0; + INIT_LIST_HEAD(&vb->free_list); + + vb_idx = addr_to_vb_idx(va->va_start); + err = xa_insert(&vmap_blocks, vb_idx, vb, gfp_mask); + if (err) { + kfree(vb); + free_vmap_area(va); + return ERR_PTR(err); + } + + vbq = &get_cpu_var(vmap_block_queue); + spin_lock(&vbq->lock); + list_add_tail_rcu(&vb->free_list, &vbq->free); + spin_unlock(&vbq->lock); + put_cpu_var(vmap_block_queue); + + return vaddr; +} + +static void free_vmap_block(struct vmap_block *vb) +{ + struct vmap_block *tmp; + + tmp = xa_erase(&vmap_blocks, addr_to_vb_idx(vb->va->va_start)); + BUG_ON(tmp != vb); + + free_vmap_area_noflush(vb->va); + kfree_rcu(vb, rcu_head); +} + +static void purge_fragmented_blocks(int cpu) +{ + LIST_HEAD(purge); + struct vmap_block *vb; + struct vmap_block *n_vb; + struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu); + + rcu_read_lock(); + list_for_each_entry_rcu(vb, &vbq->free, free_list) { + + if (!(vb->free + vb->dirty == VMAP_BBMAP_BITS && vb->dirty != VMAP_BBMAP_BITS)) + continue; + + spin_lock(&vb->lock); + if (vb->free + vb->dirty == VMAP_BBMAP_BITS && vb->dirty != VMAP_BBMAP_BITS) { + vb->free = 0; /* prevent further allocs after releasing lock */ + vb->dirty = VMAP_BBMAP_BITS; /* prevent purging it again */ + vb->dirty_min = 0; + vb->dirty_max = VMAP_BBMAP_BITS; + spin_lock(&vbq->lock); + list_del_rcu(&vb->free_list); + spin_unlock(&vbq->lock); + spin_unlock(&vb->lock); + list_add_tail(&vb->purge, &purge); + } else + spin_unlock(&vb->lock); + } + rcu_read_unlock(); + + list_for_each_entry_safe(vb, n_vb, &purge, purge) { + list_del(&vb->purge); + free_vmap_block(vb); + } +} + +static void purge_fragmented_blocks_allcpus(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + purge_fragmented_blocks(cpu); +} + +static void *vb_alloc(unsigned long size, gfp_t gfp_mask) +{ + struct vmap_block_queue *vbq; + struct vmap_block *vb; + void *vaddr = NULL; + unsigned int order; + + BUG_ON(offset_in_page(size)); + BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); + if (WARN_ON(size == 0)) { + /* + * Allocating 0 bytes isn't what caller wants since + * get_order(0) returns funny result. Just warn and terminate + * early. + */ + return NULL; + } + order = get_order(size); + + rcu_read_lock(); + vbq = &get_cpu_var(vmap_block_queue); + list_for_each_entry_rcu(vb, &vbq->free, free_list) { + unsigned long pages_off; + + spin_lock(&vb->lock); + if (vb->free < (1UL << order)) { + spin_unlock(&vb->lock); + continue; + } + + pages_off = VMAP_BBMAP_BITS - vb->free; + vaddr = vmap_block_vaddr(vb->va->va_start, pages_off); + vb->free -= 1UL << order; + if (vb->free == 0) { + spin_lock(&vbq->lock); + list_del_rcu(&vb->free_list); + spin_unlock(&vbq->lock); + } + + spin_unlock(&vb->lock); + break; + } + + put_cpu_var(vmap_block_queue); + rcu_read_unlock(); + + /* Allocate new block if nothing was found */ + if (!vaddr) + vaddr = new_vmap_block(order, gfp_mask); + + return vaddr; +} + +static void vb_free(unsigned long addr, unsigned long size) +{ + unsigned long offset; + unsigned int order; + struct vmap_block *vb; + + BUG_ON(offset_in_page(size)); + BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); + + flush_cache_vunmap(addr, addr + size); + + order = get_order(size); + offset = (addr & (VMAP_BLOCK_SIZE - 1)) >> PAGE_SHIFT; + vb = xa_load(&vmap_blocks, addr_to_vb_idx(addr)); + + unmap_kernel_range_noflush(addr, size); + + if (debug_pagealloc_enabled_static()) + flush_tlb_kernel_range(addr, addr + size); + + spin_lock(&vb->lock); + + /* Expand dirty range */ + vb->dirty_min = min(vb->dirty_min, offset); + vb->dirty_max = max(vb->dirty_max, offset + (1UL << order)); + + vb->dirty += 1UL << order; + if (vb->dirty == VMAP_BBMAP_BITS) { + BUG_ON(vb->free); + spin_unlock(&vb->lock); + free_vmap_block(vb); + } else + spin_unlock(&vb->lock); +} + +static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush) +{ + int cpu; + + if (unlikely(!vmap_initialized)) + return; + + might_sleep(); + + for_each_possible_cpu(cpu) { + struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu); + struct vmap_block *vb; + + rcu_read_lock(); + list_for_each_entry_rcu(vb, &vbq->free, free_list) { + spin_lock(&vb->lock); + if (vb->dirty) { + unsigned long va_start = vb->va->va_start; + unsigned long s, e; + + s = va_start + (vb->dirty_min << PAGE_SHIFT); + e = va_start + (vb->dirty_max << PAGE_SHIFT); + + start = min(s, start); + end = max(e, end); + + flush = 1; + } + spin_unlock(&vb->lock); + } + rcu_read_unlock(); + } + + mutex_lock(&vmap_purge_lock); + purge_fragmented_blocks_allcpus(); + if (!__purge_vmap_area_lazy(start, end) && flush) + flush_tlb_kernel_range(start, end); + mutex_unlock(&vmap_purge_lock); +} + +/** + * vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer + * + * The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily + * to amortize TLB flushing overheads. What this means is that any page you + * have now, may, in a former life, have been mapped into kernel virtual + * address by the vmap layer and so there might be some CPUs with TLB entries + * still referencing that page (additional to the regular 1:1 kernel mapping). + * + * vm_unmap_aliases flushes all such lazy mappings. After it returns, we can + * be sure that none of the pages we have control over will have any aliases + * from the vmap layer. + */ +void vm_unmap_aliases(void) +{ + unsigned long start = ULONG_MAX, end = 0; + int flush = 0; + + _vm_unmap_aliases(start, end, flush); +} +EXPORT_SYMBOL_GPL(vm_unmap_aliases); + +/** + * vm_unmap_ram - unmap linear kernel address space set up by vm_map_ram + * @mem: the pointer returned by vm_map_ram + * @count: the count passed to that vm_map_ram call (cannot unmap partial) + */ +void vm_unmap_ram(const void *mem, unsigned int count) +{ + unsigned long size = (unsigned long)count << PAGE_SHIFT; + unsigned long addr = (unsigned long)mem; + struct vmap_area *va; + + might_sleep(); + BUG_ON(!addr); + BUG_ON(addr < VMALLOC_START); + BUG_ON(addr > VMALLOC_END); + BUG_ON(!PAGE_ALIGNED(addr)); + + kasan_poison_vmalloc(mem, size); + + if (likely(count <= VMAP_MAX_ALLOC)) { + debug_check_no_locks_freed(mem, size); + vb_free(addr, size); + return; + } + + va = find_vmap_area(addr); + BUG_ON(!va); + debug_check_no_locks_freed((void *)va->va_start, + (va->va_end - va->va_start)); + free_unmap_vmap_area(va); +} +EXPORT_SYMBOL(vm_unmap_ram); + +/** + * vm_map_ram - map pages linearly into kernel virtual address (vmalloc space) + * @pages: an array of pointers to the pages to be mapped + * @count: number of pages + * @node: prefer to allocate data structures on this node + * + * If you use this function for less than VMAP_MAX_ALLOC pages, it could be + * faster than vmap so it's good. But if you mix long-life and short-life + * objects with vm_map_ram(), it could consume lots of address space through + * fragmentation (especially on a 32bit machine). You could see failures in + * the end. Please use this function for short-lived objects. + * + * Returns: a pointer to the address that has been mapped, or %NULL on failure + */ +void *vm_map_ram(struct page **pages, unsigned int count, int node) +{ + unsigned long size = (unsigned long)count << PAGE_SHIFT; + unsigned long addr; + void *mem; + + if (likely(count <= VMAP_MAX_ALLOC)) { + mem = vb_alloc(size, GFP_KERNEL); + if (IS_ERR(mem)) + return NULL; + addr = (unsigned long)mem; + } else { + struct vmap_area *va; + va = alloc_vmap_area(size, PAGE_SIZE, + VMALLOC_START, VMALLOC_END, node, GFP_KERNEL); + if (IS_ERR(va)) + return NULL; + + addr = va->va_start; + mem = (void *)addr; + } + + kasan_unpoison_vmalloc(mem, size); + + if (map_kernel_range(addr, size, PAGE_KERNEL, pages) < 0) { + vm_unmap_ram(mem, count); + return NULL; + } + return mem; +} +EXPORT_SYMBOL(vm_map_ram); + +static struct vm_struct *vmlist __initdata; + +/** + * vm_area_add_early - add vmap area early during boot + * @vm: vm_struct to add + * + * This function is used to add fixed kernel vm area to vmlist before + * vmalloc_init() is called. @vm->addr, @vm->size, and @vm->flags + * should contain proper values and the other fields should be zero. + * + * DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING. + */ +void __init vm_area_add_early(struct vm_struct *vm) +{ + struct vm_struct *tmp, **p; + + BUG_ON(vmap_initialized); + for (p = &vmlist; (tmp = *p) != NULL; p = &tmp->next) { + if (tmp->addr >= vm->addr) { + BUG_ON(tmp->addr < vm->addr + vm->size); + break; + } else + BUG_ON(tmp->addr + tmp->size > vm->addr); + } + vm->next = *p; + *p = vm; +} + +/** + * vm_area_register_early - register vmap area early during boot + * @vm: vm_struct to register + * @align: requested alignment + * + * This function is used to register kernel vm area before + * vmalloc_init() is called. @vm->size and @vm->flags should contain + * proper values on entry and other fields should be zero. On return, + * vm->addr contains the allocated address. + * + * DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING. + */ +void __init vm_area_register_early(struct vm_struct *vm, size_t align) +{ + static size_t vm_init_off __initdata; + unsigned long addr; + + addr = ALIGN(VMALLOC_START + vm_init_off, align); + vm_init_off = PFN_ALIGN(addr + vm->size) - VMALLOC_START; + + vm->addr = (void *)addr; + + vm_area_add_early(vm); +} + +static void vmap_init_free_space(void) +{ + unsigned long vmap_start = 1; + const unsigned long vmap_end = ULONG_MAX; + struct vmap_area *busy, *free; + + /* + * B F B B B F + * -|-----|.....|-----|-----|-----|.....|- + * | The KVA space | + * |<--------------------------------->| + */ + list_for_each_entry(busy, &vmap_area_list, list) { + if (busy->va_start - vmap_start > 0) { + free = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); + if (!WARN_ON_ONCE(!free)) { + free->va_start = vmap_start; + free->va_end = busy->va_start; + + insert_vmap_area_augment(free, NULL, + &free_vmap_area_root, + &free_vmap_area_list); + } + } + + vmap_start = busy->va_end; + } + + if (vmap_end - vmap_start > 0) { + free = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); + if (!WARN_ON_ONCE(!free)) { + free->va_start = vmap_start; + free->va_end = vmap_end; + + insert_vmap_area_augment(free, NULL, + &free_vmap_area_root, + &free_vmap_area_list); + } + } +} + +void __init vmalloc_init(void) +{ + struct vmap_area *va; + struct vm_struct *tmp; + int i; + + /* + * Create the cache for vmap_area objects. + */ + vmap_area_cachep = KMEM_CACHE(vmap_area, SLAB_PANIC); + + for_each_possible_cpu(i) { + struct vmap_block_queue *vbq; + struct vfree_deferred *p; + + vbq = &per_cpu(vmap_block_queue, i); + spin_lock_init(&vbq->lock); + INIT_LIST_HEAD(&vbq->free); + p = &per_cpu(vfree_deferred, i); + init_llist_head(&p->list); + INIT_WORK(&p->wq, free_work); + } + + /* Import existing vmlist entries. */ + for (tmp = vmlist; tmp; tmp = tmp->next) { + va = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); + if (WARN_ON_ONCE(!va)) + continue; + + va->va_start = (unsigned long)tmp->addr; + va->va_end = va->va_start + tmp->size; + va->vm = tmp; + insert_vmap_area(va, &vmap_area_root, &vmap_area_list); + } + + /* + * Now we can initialize a free vmap space. + */ + vmap_init_free_space(); + vmap_initialized = true; +} + +/** + * unmap_kernel_range - unmap kernel VM area and flush cache and TLB + * @addr: start of the VM area to unmap + * @size: size of the VM area to unmap + * + * Similar to unmap_kernel_range_noflush() but flushes vcache before + * the unmapping and tlb after. + */ +void unmap_kernel_range(unsigned long addr, unsigned long size) +{ + unsigned long end = addr + size; + + flush_cache_vunmap(addr, end); + unmap_kernel_range_noflush(addr, size); + flush_tlb_kernel_range(addr, end); +} + +static inline void setup_vmalloc_vm_locked(struct vm_struct *vm, + struct vmap_area *va, unsigned long flags, const void *caller) +{ + vm->flags = flags; + vm->addr = (void *)va->va_start; + vm->size = va->va_end - va->va_start; + vm->caller = caller; + va->vm = vm; +} + +static void setup_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, + unsigned long flags, const void *caller) +{ + spin_lock(&vmap_area_lock); + setup_vmalloc_vm_locked(vm, va, flags, caller); + spin_unlock(&vmap_area_lock); +} + +static void clear_vm_uninitialized_flag(struct vm_struct *vm) +{ + /* + * Before removing VM_UNINITIALIZED, + * we should make sure that vm has proper values. + * Pair with smp_rmb() in show_numa_info(). + */ + smp_wmb(); + vm->flags &= ~VM_UNINITIALIZED; +} + +static struct vm_struct *__get_vm_area_node(unsigned long size, + unsigned long align, unsigned long flags, unsigned long start, + unsigned long end, int node, gfp_t gfp_mask, const void *caller) +{ + struct vmap_area *va; + struct vm_struct *area; + unsigned long requested_size = size; + + BUG_ON(in_interrupt()); + size = PAGE_ALIGN(size); + if (unlikely(!size)) + return NULL; + + if (flags & VM_IOREMAP) + align = 1ul << clamp_t(int, get_count_order_long(size), + PAGE_SHIFT, IOREMAP_MAX_ORDER); + + area = kzalloc_node(sizeof(*area), gfp_mask & GFP_RECLAIM_MASK, node); + if (unlikely(!area)) + return NULL; + + if (!(flags & VM_NO_GUARD)) + size += PAGE_SIZE; + + va = alloc_vmap_area(size, align, start, end, node, gfp_mask); + if (IS_ERR(va)) { + kfree(area); + return NULL; + } + + kasan_unpoison_vmalloc((void *)va->va_start, requested_size); + + setup_vmalloc_vm(area, va, flags, caller); + + return area; +} + +struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, + unsigned long start, unsigned long end, + const void *caller) +{ + return __get_vm_area_node(size, 1, flags, start, end, NUMA_NO_NODE, + GFP_KERNEL, caller); +} + +/** + * get_vm_area - reserve a contiguous kernel virtual area + * @size: size of the area + * @flags: %VM_IOREMAP for I/O mappings or VM_ALLOC + * + * Search an area of @size in the kernel virtual mapping area, + * and reserved it for out purposes. Returns the area descriptor + * on success or %NULL on failure. + * + * Return: the area descriptor on success or %NULL on failure. + */ +struct vm_struct *get_vm_area(unsigned long size, unsigned long flags) +{ + return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END, + NUMA_NO_NODE, GFP_KERNEL, + __builtin_return_address(0)); +} + +struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags, + const void *caller) +{ + return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END, + NUMA_NO_NODE, GFP_KERNEL, caller); +} + +/** + * find_vm_area - find a continuous kernel virtual area + * @addr: base address + * + * Search for the kernel VM area starting at @addr, and return it. + * It is up to the caller to do all required locking to keep the returned + * pointer valid. + * + * Return: the area descriptor on success or %NULL on failure. + */ +struct vm_struct *find_vm_area(const void *addr) +{ + struct vmap_area *va; + + va = find_vmap_area((unsigned long)addr); + if (!va) + return NULL; + + return va->vm; +} + +/** + * remove_vm_area - find and remove a continuous kernel virtual area + * @addr: base address + * + * Search for the kernel VM area starting at @addr, and remove it. + * This function returns the found VM area, but using it is NOT safe + * on SMP machines, except for its size or flags. + * + * Return: the area descriptor on success or %NULL on failure. + */ +struct vm_struct *remove_vm_area(const void *addr) +{ + struct vmap_area *va; + + might_sleep(); + + spin_lock(&vmap_area_lock); + va = __find_vmap_area((unsigned long)addr); + if (va && va->vm) { + struct vm_struct *vm = va->vm; + + va->vm = NULL; + spin_unlock(&vmap_area_lock); + + kasan_free_shadow(vm); + free_unmap_vmap_area(va); + + return vm; + } + + spin_unlock(&vmap_area_lock); + return NULL; +} + +static inline void set_area_direct_map(const struct vm_struct *area, + int (*set_direct_map)(struct page *page)) +{ + int i; + + for (i = 0; i < area->nr_pages; i++) + if (page_address(area->pages[i])) + set_direct_map(area->pages[i]); +} + +/* Handle removing and resetting vm mappings related to the vm_struct. */ +static void vm_remove_mappings(struct vm_struct *area, int deallocate_pages) +{ + unsigned long start = ULONG_MAX, end = 0; + int flush_reset = area->flags & VM_FLUSH_RESET_PERMS; + int flush_dmap = 0; + int i; + + remove_vm_area(area->addr); + + /* If this is not VM_FLUSH_RESET_PERMS memory, no need for the below. */ + if (!flush_reset) + return; + + /* + * If not deallocating pages, just do the flush of the VM area and + * return. + */ + if (!deallocate_pages) { + vm_unmap_aliases(); + return; + } + + /* + * If execution gets here, flush the vm mapping and reset the direct + * map. Find the start and end range of the direct mappings to make sure + * the vm_unmap_aliases() flush includes the direct map. + */ + for (i = 0; i < area->nr_pages; i++) { + unsigned long addr = (unsigned long)page_address(area->pages[i]); + if (addr) { + start = min(addr, start); + end = max(addr + PAGE_SIZE, end); + flush_dmap = 1; + } + } + + /* + * Set direct map to something invalid so that it won't be cached if + * there are any accesses after the TLB flush, then flush the TLB and + * reset the direct map permissions to the default. + */ + set_area_direct_map(area, set_direct_map_invalid_noflush); + _vm_unmap_aliases(start, end, flush_dmap); + set_area_direct_map(area, set_direct_map_default_noflush); +} + +static void __vunmap(const void *addr, int deallocate_pages) +{ + struct vm_struct *area; + + if (!addr) + return; + + if (WARN(!PAGE_ALIGNED(addr), "Trying to vfree() bad address (%p)\n", + addr)) + return; + + area = find_vm_area(addr); + if (unlikely(!area)) { + WARN(1, KERN_ERR "Trying to vfree() nonexistent vm area (%p)\n", + addr); + return; + } + + debug_check_no_locks_freed(area->addr, get_vm_area_size(area)); + debug_check_no_obj_freed(area->addr, get_vm_area_size(area)); + + kasan_poison_vmalloc(area->addr, get_vm_area_size(area)); + + vm_remove_mappings(area, deallocate_pages); + + if (deallocate_pages) { + int i; + + for (i = 0; i < area->nr_pages; i++) { + struct page *page = area->pages[i]; + + BUG_ON(!page); + __free_pages(page, 0); + } + atomic_long_sub(area->nr_pages, &nr_vmalloc_pages); + + kvfree(area->pages); + } + + kfree(area); + return; +} + +static inline void __vfree_deferred(const void *addr) +{ + /* + * Use raw_cpu_ptr() because this can be called from preemptible + * context. Preemption is absolutely fine here, because the llist_add() + * implementation is lockless, so it works even if we are adding to + * another cpu's list. schedule_work() should be fine with this too. + */ + struct vfree_deferred *p = raw_cpu_ptr(&vfree_deferred); + + if (llist_add((struct llist_node *)addr, &p->list)) + schedule_work(&p->wq); +} + +/** + * vfree_atomic - release memory allocated by vmalloc() + * @addr: memory base address + * + * This one is just like vfree() but can be called in any atomic context + * except NMIs. + */ +void vfree_atomic(const void *addr) +{ + BUG_ON(in_nmi()); + + kmemleak_free(addr); + + if (!addr) + return; + __vfree_deferred(addr); +} + +static void __vfree(const void *addr) +{ + if (unlikely(in_interrupt())) + __vfree_deferred(addr); + else + __vunmap(addr, 1); +} + +/** + * vfree - Release memory allocated by vmalloc() + * @addr: Memory base address + * + * Free the virtually continuous memory area starting at @addr, as obtained + * from one of the vmalloc() family of APIs. This will usually also free the + * physical memory underlying the virtual allocation, but that memory is + * reference counted, so it will not be freed until the last user goes away. + * + * If @addr is NULL, no operation is performed. + * + * Context: + * May sleep if called *not* from interrupt context. + * Must not be called in NMI context (strictly speaking, it could be + * if we have CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG, but making the calling + * conventions for vfree() arch-depenedent would be a really bad idea). + */ +void vfree(const void *addr) +{ + BUG_ON(in_nmi()); + + kmemleak_free(addr); + + might_sleep_if(!in_interrupt()); + + if (!addr) + return; + + __vfree(addr); +} +EXPORT_SYMBOL(vfree); + +/** + * vunmap - release virtual mapping obtained by vmap() + * @addr: memory base address + * + * Free the virtually contiguous memory area starting at @addr, + * which was created from the page array passed to vmap(). + * + * Must not be called in interrupt context. + */ +void vunmap(const void *addr) +{ + BUG_ON(in_interrupt()); + might_sleep(); + if (addr) + __vunmap(addr, 0); +} +EXPORT_SYMBOL(vunmap); + +/** + * vmap - map an array of pages into virtually contiguous space + * @pages: array of page pointers + * @count: number of pages to map + * @flags: vm_area->flags + * @prot: page protection for the mapping + * + * Maps @count pages from @pages into contiguous kernel virtual space. + * If @flags contains %VM_MAP_PUT_PAGES the ownership of the pages array itself + * (which must be kmalloc or vmalloc memory) and one reference per pages in it + * are transferred from the caller to vmap(), and will be freed / dropped when + * vfree() is called on the return value. + * + * Return: the address of the area or %NULL on failure + */ +void *vmap(struct page **pages, unsigned int count, + unsigned long flags, pgprot_t prot) +{ + struct vm_struct *area; + unsigned long size; /* In bytes */ + + might_sleep(); + + if (count > totalram_pages()) + return NULL; + + size = (unsigned long)count << PAGE_SHIFT; + area = get_vm_area_caller(size, flags, __builtin_return_address(0)); + if (!area) + return NULL; + + if (map_kernel_range((unsigned long)area->addr, size, pgprot_nx(prot), + pages) < 0) { + vunmap(area->addr); + return NULL; + } + + if (flags & VM_MAP_PUT_PAGES) { + area->pages = pages; + area->nr_pages = count; + } + return area->addr; +} +EXPORT_SYMBOL(vmap); + +#ifdef CONFIG_VMAP_PFN +struct vmap_pfn_data { + unsigned long *pfns; + pgprot_t prot; + unsigned int idx; +}; + +static int vmap_pfn_apply(pte_t *pte, unsigned long addr, void *private) +{ + struct vmap_pfn_data *data = private; + + if (WARN_ON_ONCE(pfn_valid(data->pfns[data->idx]))) + return -EINVAL; + *pte = pte_mkspecial(pfn_pte(data->pfns[data->idx++], data->prot)); + return 0; +} + +/** + * vmap_pfn - map an array of PFNs into virtually contiguous space + * @pfns: array of PFNs + * @count: number of pages to map + * @prot: page protection for the mapping + * + * Maps @count PFNs from @pfns into contiguous kernel virtual space and returns + * the start address of the mapping. + */ +void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot) +{ + struct vmap_pfn_data data = { .pfns = pfns, .prot = pgprot_nx(prot) }; + struct vm_struct *area; + + area = get_vm_area_caller(count * PAGE_SIZE, VM_IOREMAP, + __builtin_return_address(0)); + if (!area) + return NULL; + if (apply_to_page_range(&init_mm, (unsigned long)area->addr, + count * PAGE_SIZE, vmap_pfn_apply, &data)) { + free_vm_area(area); + return NULL; + } + + flush_cache_vmap((unsigned long)area->addr, + (unsigned long)area->addr + count * PAGE_SIZE); + + return area->addr; +} +EXPORT_SYMBOL_GPL(vmap_pfn); +#endif /* CONFIG_VMAP_PFN */ + +static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, + pgprot_t prot, int node) +{ + const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO; + unsigned int nr_pages = get_vm_area_size(area) >> PAGE_SHIFT; + unsigned int array_size = nr_pages * sizeof(struct page *), i; + struct page **pages; + + gfp_mask |= __GFP_NOWARN; + if (!(gfp_mask & (GFP_DMA | GFP_DMA32))) + gfp_mask |= __GFP_HIGHMEM; + + /* Please note that the recursion is strictly bounded. */ + if (array_size > PAGE_SIZE) { + pages = __vmalloc_node(array_size, 1, nested_gfp, node, + area->caller); + } else { + pages = kmalloc_node(array_size, nested_gfp, node); + } + + if (!pages) { + remove_vm_area(area->addr); + kfree(area); + return NULL; + } + + area->pages = pages; + area->nr_pages = nr_pages; + + for (i = 0; i < area->nr_pages; i++) { + struct page *page; + + if (node == NUMA_NO_NODE) + page = alloc_page(gfp_mask); + else + page = alloc_pages_node(node, gfp_mask, 0); + + if (unlikely(!page)) { + /* Successfully allocated i pages, free them in __vfree() */ + area->nr_pages = i; + atomic_long_add(area->nr_pages, &nr_vmalloc_pages); + goto fail; + } + area->pages[i] = page; + if (gfpflags_allow_blocking(gfp_mask)) + cond_resched(); + } + atomic_long_add(area->nr_pages, &nr_vmalloc_pages); + + if (map_kernel_range((unsigned long)area->addr, get_vm_area_size(area), + prot, pages) < 0) + goto fail; + + return area->addr; + +fail: + warn_alloc(gfp_mask, NULL, + "vmalloc: allocation failure, allocated %ld of %ld bytes", + (area->nr_pages*PAGE_SIZE), area->size); + __vfree(area->addr); + return NULL; +} + +/** + * __vmalloc_node_range - allocate virtually contiguous memory + * @size: allocation size + * @align: desired alignment + * @start: vm area range start + * @end: vm area range end + * @gfp_mask: flags for the page level allocator + * @prot: protection mask for the allocated pages + * @vm_flags: additional vm area flags (e.g. %VM_NO_GUARD) + * @node: node to use for allocation or NUMA_NO_NODE + * @caller: caller's return address + * + * Allocate enough pages to cover @size from the page level + * allocator with @gfp_mask flags. Map them into contiguous + * kernel virtual space, using a pagetable protection of @prot. + * + * Return: the address of the area or %NULL on failure + */ +void *__vmalloc_node_range(unsigned long size, unsigned long align, + unsigned long start, unsigned long end, gfp_t gfp_mask, + pgprot_t prot, unsigned long vm_flags, int node, + const void *caller) +{ + struct vm_struct *area; + void *addr; + unsigned long real_size = size; + + size = PAGE_ALIGN(size); + if (!size || (size >> PAGE_SHIFT) > totalram_pages()) + goto fail; + + area = __get_vm_area_node(real_size, align, VM_ALLOC | VM_UNINITIALIZED | + vm_flags, start, end, node, gfp_mask, caller); + if (!area) + goto fail; + + addr = __vmalloc_area_node(area, gfp_mask, prot, node); + if (!addr) + return NULL; + + /* + * In this function, newly allocated vm_struct has VM_UNINITIALIZED + * flag. It means that vm_struct is not fully initialized. + * Now, it is fully initialized, so remove this flag here. + */ + clear_vm_uninitialized_flag(area); + + kmemleak_vmalloc(area, size, gfp_mask); + + return addr; + +fail: + warn_alloc(gfp_mask, NULL, + "vmalloc: allocation failure: %lu bytes", real_size); + return NULL; +} + +/** + * __vmalloc_node - allocate virtually contiguous memory + * @size: allocation size + * @align: desired alignment + * @gfp_mask: flags for the page level allocator + * @node: node to use for allocation or NUMA_NO_NODE + * @caller: caller's return address + * + * Allocate enough pages to cover @size from the page level allocator with + * @gfp_mask flags. Map them into contiguous kernel virtual space. + * + * Reclaim modifiers in @gfp_mask - __GFP_NORETRY, __GFP_RETRY_MAYFAIL + * and __GFP_NOFAIL are not supported + * + * Any use of gfp flags outside of GFP_KERNEL should be consulted + * with mm people. + * + * Return: pointer to the allocated memory or %NULL on error + */ +void *__vmalloc_node(unsigned long size, unsigned long align, + gfp_t gfp_mask, int node, const void *caller) +{ + return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END, + gfp_mask, PAGE_KERNEL, 0, node, caller); +} +/* + * This is only for performance analysis of vmalloc and stress purpose. + * It is required by vmalloc test module, therefore do not use it other + * than that. + */ +#ifdef CONFIG_TEST_VMALLOC_MODULE +EXPORT_SYMBOL_GPL(__vmalloc_node); +#endif + +void *__vmalloc(unsigned long size, gfp_t gfp_mask) +{ + return __vmalloc_node(size, 1, gfp_mask, NUMA_NO_NODE, + __builtin_return_address(0)); +} +EXPORT_SYMBOL(__vmalloc); + +/** + * vmalloc - allocate virtually contiguous memory + * @size: allocation size + * + * Allocate enough pages to cover @size from the page level + * allocator and map them into contiguous kernel virtual space. + * + * For tight control over page level allocator and protection flags + * use __vmalloc() instead. + * + * Return: pointer to the allocated memory or %NULL on error + */ +void *vmalloc(unsigned long size) +{ + return __vmalloc_node(size, 1, GFP_KERNEL, NUMA_NO_NODE, + __builtin_return_address(0)); +} +EXPORT_SYMBOL(vmalloc); + +/** + * vzalloc - allocate virtually contiguous memory with zero fill + * @size: allocation size + * + * Allocate enough pages to cover @size from the page level + * allocator and map them into contiguous kernel virtual space. + * The memory allocated is set to zero. + * + * For tight control over page level allocator and protection flags + * use __vmalloc() instead. + * + * Return: pointer to the allocated memory or %NULL on error + */ +void *vzalloc(unsigned long size) +{ + return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_ZERO, NUMA_NO_NODE, + __builtin_return_address(0)); +} +EXPORT_SYMBOL(vzalloc); + +/** + * vmalloc_user - allocate zeroed virtually contiguous memory for userspace + * @size: allocation size + * + * The resulting memory area is zeroed so it can be mapped to userspace + * without leaking data. + * + * Return: pointer to the allocated memory or %NULL on error + */ +void *vmalloc_user(unsigned long size) +{ + return __vmalloc_node_range(size, SHMLBA, VMALLOC_START, VMALLOC_END, + GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL, + VM_USERMAP, NUMA_NO_NODE, + __builtin_return_address(0)); +} +EXPORT_SYMBOL(vmalloc_user); + +/** + * vmalloc_node - allocate memory on a specific node + * @size: allocation size + * @node: numa node + * + * Allocate enough pages to cover @size from the page level + * allocator and map them into contiguous kernel virtual space. + * + * For tight control over page level allocator and protection flags + * use __vmalloc() instead. + * + * Return: pointer to the allocated memory or %NULL on error + */ +void *vmalloc_node(unsigned long size, int node) +{ + return __vmalloc_node(size, 1, GFP_KERNEL, node, + __builtin_return_address(0)); +} +EXPORT_SYMBOL(vmalloc_node); + +/** + * vzalloc_node - allocate memory on a specific node with zero fill + * @size: allocation size + * @node: numa node + * + * Allocate enough pages to cover @size from the page level + * allocator and map them into contiguous kernel virtual space. + * The memory allocated is set to zero. + * + * Return: pointer to the allocated memory or %NULL on error + */ +void *vzalloc_node(unsigned long size, int node) +{ + return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_ZERO, node, + __builtin_return_address(0)); +} +EXPORT_SYMBOL(vzalloc_node); + +#if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32) +#define GFP_VMALLOC32 (GFP_DMA32 | GFP_KERNEL) +#elif defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA) +#define GFP_VMALLOC32 (GFP_DMA | GFP_KERNEL) +#else +/* + * 64b systems should always have either DMA or DMA32 zones. For others + * GFP_DMA32 should do the right thing and use the normal zone. + */ +#define GFP_VMALLOC32 GFP_DMA32 | GFP_KERNEL +#endif + +/** + * vmalloc_32 - allocate virtually contiguous memory (32bit addressable) + * @size: allocation size + * + * Allocate enough 32bit PA addressable pages to cover @size from the + * page level allocator and map them into contiguous kernel virtual space. + * + * Return: pointer to the allocated memory or %NULL on error + */ +void *vmalloc_32(unsigned long size) +{ + return __vmalloc_node(size, 1, GFP_VMALLOC32, NUMA_NO_NODE, + __builtin_return_address(0)); +} +EXPORT_SYMBOL(vmalloc_32); + +/** + * vmalloc_32_user - allocate zeroed virtually contiguous 32bit memory + * @size: allocation size + * + * The resulting memory area is 32bit addressable and zeroed so it can be + * mapped to userspace without leaking data. + * + * Return: pointer to the allocated memory or %NULL on error + */ +void *vmalloc_32_user(unsigned long size) +{ + return __vmalloc_node_range(size, SHMLBA, VMALLOC_START, VMALLOC_END, + GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL, + VM_USERMAP, NUMA_NO_NODE, + __builtin_return_address(0)); +} +EXPORT_SYMBOL(vmalloc_32_user); + +/* + * small helper routine , copy contents to buf from addr. + * If the page is not present, fill zero. + */ + +static int aligned_vread(char *buf, char *addr, unsigned long count) +{ + struct page *p; + int copied = 0; + + while (count) { + unsigned long offset, length; + + offset = offset_in_page(addr); + length = PAGE_SIZE - offset; + if (length > count) + length = count; + p = vmalloc_to_page(addr); + /* + * To do safe access to this _mapped_ area, we need + * lock. But adding lock here means that we need to add + * overhead of vmalloc()/vfree() calles for this _debug_ + * interface, rarely used. Instead of that, we'll use + * kmap() and get small overhead in this access function. + */ + if (p) { + /* + * we can expect USER0 is not used (see vread/vwrite's + * function description) + */ + void *map = kmap_atomic(p); + memcpy(buf, map + offset, length); + kunmap_atomic(map); + } else + memset(buf, 0, length); + + addr += length; + buf += length; + copied += length; + count -= length; + } + return copied; +} + +static int aligned_vwrite(char *buf, char *addr, unsigned long count) +{ + struct page *p; + int copied = 0; + + while (count) { + unsigned long offset, length; + + offset = offset_in_page(addr); + length = PAGE_SIZE - offset; + if (length > count) + length = count; + p = vmalloc_to_page(addr); + /* + * To do safe access to this _mapped_ area, we need + * lock. But adding lock here means that we need to add + * overhead of vmalloc()/vfree() calles for this _debug_ + * interface, rarely used. Instead of that, we'll use + * kmap() and get small overhead in this access function. + */ + if (p) { + /* + * we can expect USER0 is not used (see vread/vwrite's + * function description) + */ + void *map = kmap_atomic(p); + memcpy(map + offset, buf, length); + kunmap_atomic(map); + } + addr += length; + buf += length; + copied += length; + count -= length; + } + return copied; +} + +/** + * vread() - read vmalloc area in a safe way. + * @buf: buffer for reading data + * @addr: vm address. + * @count: number of bytes to be read. + * + * This function checks that addr is a valid vmalloc'ed area, and + * copy data from that area to a given buffer. If the given memory range + * of [addr...addr+count) includes some valid address, data is copied to + * proper area of @buf. If there are memory holes, they'll be zero-filled. + * IOREMAP area is treated as memory hole and no copy is done. + * + * If [addr...addr+count) doesn't includes any intersects with alive + * vm_struct area, returns 0. @buf should be kernel's buffer. + * + * Note: In usual ops, vread() is never necessary because the caller + * should know vmalloc() area is valid and can use memcpy(). + * This is for routines which have to access vmalloc area without + * any information, as /dev/kmem. + * + * Return: number of bytes for which addr and buf should be increased + * (same number as @count) or %0 if [addr...addr+count) doesn't + * include any intersection with valid vmalloc area + */ +long vread(char *buf, char *addr, unsigned long count) +{ + struct vmap_area *va; + struct vm_struct *vm; + char *vaddr, *buf_start = buf; + unsigned long buflen = count; + unsigned long n; + + /* Don't allow overflow */ + if ((unsigned long) addr + count < count) + count = -(unsigned long) addr; + + spin_lock(&vmap_area_lock); + list_for_each_entry(va, &vmap_area_list, list) { + if (!count) + break; + + if (!va->vm) + continue; + + vm = va->vm; + vaddr = (char *) vm->addr; + if (addr >= vaddr + get_vm_area_size(vm)) + continue; + while (addr < vaddr) { + if (count == 0) + goto finished; + *buf = '\0'; + buf++; + addr++; + count--; + } + n = vaddr + get_vm_area_size(vm) - addr; + if (n > count) + n = count; + if (!(vm->flags & VM_IOREMAP)) + aligned_vread(buf, addr, n); + else /* IOREMAP area is treated as memory hole */ + memset(buf, 0, n); + buf += n; + addr += n; + count -= n; + } +finished: + spin_unlock(&vmap_area_lock); + + if (buf == buf_start) + return 0; + /* zero-fill memory holes */ + if (buf != buf_start + buflen) + memset(buf, 0, buflen - (buf - buf_start)); + + return buflen; +} + +/** + * vwrite() - write vmalloc area in a safe way. + * @buf: buffer for source data + * @addr: vm address. + * @count: number of bytes to be read. + * + * This function checks that addr is a valid vmalloc'ed area, and + * copy data from a buffer to the given addr. If specified range of + * [addr...addr+count) includes some valid address, data is copied from + * proper area of @buf. If there are memory holes, no copy to hole. + * IOREMAP area is treated as memory hole and no copy is done. + * + * If [addr...addr+count) doesn't includes any intersects with alive + * vm_struct area, returns 0. @buf should be kernel's buffer. + * + * Note: In usual ops, vwrite() is never necessary because the caller + * should know vmalloc() area is valid and can use memcpy(). + * This is for routines which have to access vmalloc area without + * any information, as /dev/kmem. + * + * Return: number of bytes for which addr and buf should be + * increased (same number as @count) or %0 if [addr...addr+count) + * doesn't include any intersection with valid vmalloc area + */ +long vwrite(char *buf, char *addr, unsigned long count) +{ + struct vmap_area *va; + struct vm_struct *vm; + char *vaddr; + unsigned long n, buflen; + int copied = 0; + + /* Don't allow overflow */ + if ((unsigned long) addr + count < count) + count = -(unsigned long) addr; + buflen = count; + + spin_lock(&vmap_area_lock); + list_for_each_entry(va, &vmap_area_list, list) { + if (!count) + break; + + if (!va->vm) + continue; + + vm = va->vm; + vaddr = (char *) vm->addr; + if (addr >= vaddr + get_vm_area_size(vm)) + continue; + while (addr < vaddr) { + if (count == 0) + goto finished; + buf++; + addr++; + count--; + } + n = vaddr + get_vm_area_size(vm) - addr; + if (n > count) + n = count; + if (!(vm->flags & VM_IOREMAP)) { + aligned_vwrite(buf, addr, n); + copied++; + } + buf += n; + addr += n; + count -= n; + } +finished: + spin_unlock(&vmap_area_lock); + if (!copied) + return 0; + return buflen; +} + +/** + * remap_vmalloc_range_partial - map vmalloc pages to userspace + * @vma: vma to cover + * @uaddr: target user address to start at + * @kaddr: virtual address of vmalloc kernel memory + * @pgoff: offset from @kaddr to start at + * @size: size of map area + * + * Returns: 0 for success, -Exxx on failure + * + * This function checks that @kaddr is a valid vmalloc'ed area, + * and that it is big enough to cover the range starting at + * @uaddr in @vma. Will return failure if that criteria isn't + * met. + * + * Similar to remap_pfn_range() (see mm/memory.c) + */ +int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr, + void *kaddr, unsigned long pgoff, + unsigned long size) +{ + struct vm_struct *area; + unsigned long off; + unsigned long end_index; + + if (check_shl_overflow(pgoff, PAGE_SHIFT, &off)) + return -EINVAL; + + size = PAGE_ALIGN(size); + + if (!PAGE_ALIGNED(uaddr) || !PAGE_ALIGNED(kaddr)) + return -EINVAL; + + area = find_vm_area(kaddr); + if (!area) + return -EINVAL; + + if (!(area->flags & (VM_USERMAP | VM_DMA_COHERENT))) + return -EINVAL; + + if (check_add_overflow(size, off, &end_index) || + end_index > get_vm_area_size(area)) + return -EINVAL; + kaddr += off; + + do { + struct page *page = vmalloc_to_page(kaddr); + int ret; + + ret = vm_insert_page(vma, uaddr, page); + if (ret) + return ret; + + uaddr += PAGE_SIZE; + kaddr += PAGE_SIZE; + size -= PAGE_SIZE; + } while (size > 0); + + vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + + return 0; +} +EXPORT_SYMBOL(remap_vmalloc_range_partial); + +/** + * remap_vmalloc_range - map vmalloc pages to userspace + * @vma: vma to cover (map full range of vma) + * @addr: vmalloc memory + * @pgoff: number of pages into addr before first page to map + * + * Returns: 0 for success, -Exxx on failure + * + * This function checks that addr is a valid vmalloc'ed area, and + * that it is big enough to cover the vma. Will return failure if + * that criteria isn't met. + * + * Similar to remap_pfn_range() (see mm/memory.c) + */ +int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, + unsigned long pgoff) +{ + return remap_vmalloc_range_partial(vma, vma->vm_start, + addr, pgoff, + vma->vm_end - vma->vm_start); +} +EXPORT_SYMBOL(remap_vmalloc_range); + +void free_vm_area(struct vm_struct *area) +{ + struct vm_struct *ret; + ret = remove_vm_area(area->addr); + BUG_ON(ret != area); + kfree(area); +} +EXPORT_SYMBOL_GPL(free_vm_area); + +#ifdef CONFIG_SMP +static struct vmap_area *node_to_va(struct rb_node *n) +{ + return rb_entry_safe(n, struct vmap_area, rb_node); +} + +/** + * pvm_find_va_enclose_addr - find the vmap_area @addr belongs to + * @addr: target address + * + * Returns: vmap_area if it is found. If there is no such area + * the first highest(reverse order) vmap_area is returned + * i.e. va->va_start < addr && va->va_end < addr or NULL + * if there are no any areas before @addr. + */ +static struct vmap_area * +pvm_find_va_enclose_addr(unsigned long addr) +{ + struct vmap_area *va, *tmp; + struct rb_node *n; + + n = free_vmap_area_root.rb_node; + va = NULL; + + while (n) { + tmp = rb_entry(n, struct vmap_area, rb_node); + if (tmp->va_start <= addr) { + va = tmp; + if (tmp->va_end >= addr) + break; + + n = n->rb_right; + } else { + n = n->rb_left; + } + } + + return va; +} + +/** + * pvm_determine_end_from_reverse - find the highest aligned address + * of free block below VMALLOC_END + * @va: + * in - the VA we start the search(reverse order); + * out - the VA with the highest aligned end address. + * + * Returns: determined end address within vmap_area + */ +static unsigned long +pvm_determine_end_from_reverse(struct vmap_area **va, unsigned long align) +{ + unsigned long vmalloc_end = VMALLOC_END & ~(align - 1); + unsigned long addr; + + if (likely(*va)) { + list_for_each_entry_from_reverse((*va), + &free_vmap_area_list, list) { + addr = min((*va)->va_end & ~(align - 1), vmalloc_end); + if ((*va)->va_start < addr) + return addr; + } + } + + return 0; +} + +/** + * pcpu_get_vm_areas - allocate vmalloc areas for percpu allocator + * @offsets: array containing offset of each area + * @sizes: array containing size of each area + * @nr_vms: the number of areas to allocate + * @align: alignment, all entries in @offsets and @sizes must be aligned to this + * + * Returns: kmalloc'd vm_struct pointer array pointing to allocated + * vm_structs on success, %NULL on failure + * + * Percpu allocator wants to use congruent vm areas so that it can + * maintain the offsets among percpu areas. This function allocates + * congruent vmalloc areas for it with GFP_KERNEL. These areas tend to + * be scattered pretty far, distance between two areas easily going up + * to gigabytes. To avoid interacting with regular vmallocs, these + * areas are allocated from top. + * + * Despite its complicated look, this allocator is rather simple. It + * does everything top-down and scans free blocks from the end looking + * for matching base. While scanning, if any of the areas do not fit the + * base address is pulled down to fit the area. Scanning is repeated till + * all the areas fit and then all necessary data structures are inserted + * and the result is returned. + */ +struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, + const size_t *sizes, int nr_vms, + size_t align) +{ + const unsigned long vmalloc_start = ALIGN(VMALLOC_START, align); + const unsigned long vmalloc_end = VMALLOC_END & ~(align - 1); + struct vmap_area **vas, *va; + struct vm_struct **vms; + int area, area2, last_area, term_area; + unsigned long base, start, size, end, last_end, orig_start, orig_end; + bool purged = false; + enum fit_type type; + + /* verify parameters and allocate data structures */ + BUG_ON(offset_in_page(align) || !is_power_of_2(align)); + for (last_area = 0, area = 0; area < nr_vms; area++) { + start = offsets[area]; + end = start + sizes[area]; + + /* is everything aligned properly? */ + BUG_ON(!IS_ALIGNED(offsets[area], align)); + BUG_ON(!IS_ALIGNED(sizes[area], align)); + + /* detect the area with the highest address */ + if (start > offsets[last_area]) + last_area = area; + + for (area2 = area + 1; area2 < nr_vms; area2++) { + unsigned long start2 = offsets[area2]; + unsigned long end2 = start2 + sizes[area2]; + + BUG_ON(start2 < end && start < end2); + } + } + last_end = offsets[last_area] + sizes[last_area]; + + if (vmalloc_end - vmalloc_start < last_end) { + WARN_ON(true); + return NULL; + } + + vms = kcalloc(nr_vms, sizeof(vms[0]), GFP_KERNEL); + vas = kcalloc(nr_vms, sizeof(vas[0]), GFP_KERNEL); + if (!vas || !vms) + goto err_free2; + + for (area = 0; area < nr_vms; area++) { + vas[area] = kmem_cache_zalloc(vmap_area_cachep, GFP_KERNEL); + vms[area] = kzalloc(sizeof(struct vm_struct), GFP_KERNEL); + if (!vas[area] || !vms[area]) + goto err_free; + } +retry: + spin_lock(&free_vmap_area_lock); + + /* start scanning - we scan from the top, begin with the last area */ + area = term_area = last_area; + start = offsets[area]; + end = start + sizes[area]; + + va = pvm_find_va_enclose_addr(vmalloc_end); + base = pvm_determine_end_from_reverse(&va, align) - end; + + while (true) { + /* + * base might have underflowed, add last_end before + * comparing. + */ + if (base + last_end < vmalloc_start + last_end) + goto overflow; + + /* + * Fitting base has not been found. + */ + if (va == NULL) + goto overflow; + + /* + * If required width exceeds current VA block, move + * base downwards and then recheck. + */ + if (base + end > va->va_end) { + base = pvm_determine_end_from_reverse(&va, align) - end; + term_area = area; + continue; + } + + /* + * If this VA does not fit, move base downwards and recheck. + */ + if (base + start < va->va_start) { + va = node_to_va(rb_prev(&va->rb_node)); + base = pvm_determine_end_from_reverse(&va, align) - end; + term_area = area; + continue; + } + + /* + * This area fits, move on to the previous one. If + * the previous one is the terminal one, we're done. + */ + area = (area + nr_vms - 1) % nr_vms; + if (area == term_area) + break; + + start = offsets[area]; + end = start + sizes[area]; + va = pvm_find_va_enclose_addr(base + end); + } + + /* we've found a fitting base, insert all va's */ + for (area = 0; area < nr_vms; area++) { + int ret; + + start = base + offsets[area]; + size = sizes[area]; + + va = pvm_find_va_enclose_addr(start); + if (WARN_ON_ONCE(va == NULL)) + /* It is a BUG(), but trigger recovery instead. */ + goto recovery; + + type = classify_va_fit_type(va, start, size); + if (WARN_ON_ONCE(type == NOTHING_FIT)) + /* It is a BUG(), but trigger recovery instead. */ + goto recovery; + + ret = adjust_va_to_fit_type(va, start, size, type); + if (unlikely(ret)) + goto recovery; + + /* Allocated area. */ + va = vas[area]; + va->va_start = start; + va->va_end = start + size; + } + + spin_unlock(&free_vmap_area_lock); + + /* populate the kasan shadow space */ + for (area = 0; area < nr_vms; area++) { + if (kasan_populate_vmalloc(vas[area]->va_start, sizes[area])) + goto err_free_shadow; + + kasan_unpoison_vmalloc((void *)vas[area]->va_start, + sizes[area]); + } + + /* insert all vm's */ + spin_lock(&vmap_area_lock); + for (area = 0; area < nr_vms; area++) { + insert_vmap_area(vas[area], &vmap_area_root, &vmap_area_list); + + setup_vmalloc_vm_locked(vms[area], vas[area], VM_ALLOC, + pcpu_get_vm_areas); + } + spin_unlock(&vmap_area_lock); + + kfree(vas); + return vms; + +recovery: + /* + * Remove previously allocated areas. There is no + * need in removing these areas from the busy tree, + * because they are inserted only on the final step + * and when pcpu_get_vm_areas() is success. + */ + while (area--) { + orig_start = vas[area]->va_start; + orig_end = vas[area]->va_end; + va = merge_or_add_vmap_area(vas[area], &free_vmap_area_root, + &free_vmap_area_list); + if (va) + kasan_release_vmalloc(orig_start, orig_end, + va->va_start, va->va_end); + vas[area] = NULL; + } + +overflow: + spin_unlock(&free_vmap_area_lock); + if (!purged) { + purge_vmap_area_lazy(); + purged = true; + + /* Before "retry", check if we recover. */ + for (area = 0; area < nr_vms; area++) { + if (vas[area]) + continue; + + vas[area] = kmem_cache_zalloc( + vmap_area_cachep, GFP_KERNEL); + if (!vas[area]) + goto err_free; + } + + goto retry; + } + +err_free: + for (area = 0; area < nr_vms; area++) { + if (vas[area]) + kmem_cache_free(vmap_area_cachep, vas[area]); + + kfree(vms[area]); + } +err_free2: + kfree(vas); + kfree(vms); + return NULL; + +err_free_shadow: + spin_lock(&free_vmap_area_lock); + /* + * We release all the vmalloc shadows, even the ones for regions that + * hadn't been successfully added. This relies on kasan_release_vmalloc + * being able to tolerate this case. + */ + for (area = 0; area < nr_vms; area++) { + orig_start = vas[area]->va_start; + orig_end = vas[area]->va_end; + va = merge_or_add_vmap_area(vas[area], &free_vmap_area_root, + &free_vmap_area_list); + if (va) + kasan_release_vmalloc(orig_start, orig_end, + va->va_start, va->va_end); + vas[area] = NULL; + kfree(vms[area]); + } + spin_unlock(&free_vmap_area_lock); + kfree(vas); + kfree(vms); + return NULL; +} + +/** + * pcpu_free_vm_areas - free vmalloc areas for percpu allocator + * @vms: vm_struct pointer array returned by pcpu_get_vm_areas() + * @nr_vms: the number of allocated areas + * + * Free vm_structs and the array allocated by pcpu_get_vm_areas(). + */ +void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) +{ + int i; + + for (i = 0; i < nr_vms; i++) + free_vm_area(vms[i]); + kfree(vms); +} +#endif /* CONFIG_SMP */ + +#ifdef CONFIG_PROC_FS +static void *s_start(struct seq_file *m, loff_t *pos) + __acquires(&vmap_purge_lock) + __acquires(&vmap_area_lock) +{ + mutex_lock(&vmap_purge_lock); + spin_lock(&vmap_area_lock); + + return seq_list_start(&vmap_area_list, *pos); +} + +static void *s_next(struct seq_file *m, void *p, loff_t *pos) +{ + return seq_list_next(p, &vmap_area_list, pos); +} + +static void s_stop(struct seq_file *m, void *p) + __releases(&vmap_area_lock) + __releases(&vmap_purge_lock) +{ + spin_unlock(&vmap_area_lock); + mutex_unlock(&vmap_purge_lock); +} + +static void show_numa_info(struct seq_file *m, struct vm_struct *v) +{ + if (IS_ENABLED(CONFIG_NUMA)) { + unsigned int nr, *counters = m->private; + + if (!counters) + return; + + if (v->flags & VM_UNINITIALIZED) + return; + /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ + smp_rmb(); + + memset(counters, 0, nr_node_ids * sizeof(unsigned int)); + + for (nr = 0; nr < v->nr_pages; nr++) + counters[page_to_nid(v->pages[nr])]++; + + for_each_node_state(nr, N_HIGH_MEMORY) + if (counters[nr]) + seq_printf(m, " N%u=%u", nr, counters[nr]); + } +} + +static void show_purge_info(struct seq_file *m) +{ + struct llist_node *head; + struct vmap_area *va; + + head = READ_ONCE(vmap_purge_list.first); + if (head == NULL) + return; + + llist_for_each_entry(va, head, purge_list) { + seq_printf(m, "0x%pK-0x%pK %7ld unpurged vm_area\n", + (void *)va->va_start, (void *)va->va_end, + va->va_end - va->va_start); + } +} + +static int s_show(struct seq_file *m, void *p) +{ + struct vmap_area *va; + struct vm_struct *v; + + va = list_entry(p, struct vmap_area, list); + + /* + * s_show can encounter race with remove_vm_area, !vm on behalf + * of vmap area is being tear down or vm_map_ram allocation. + */ + if (!va->vm) { + seq_printf(m, "0x%pK-0x%pK %7ld vm_map_ram\n", + (void *)va->va_start, (void *)va->va_end, + va->va_end - va->va_start); + + return 0; + } + + v = va->vm; + + seq_printf(m, "0x%pK-0x%pK %7ld", + v->addr, v->addr + v->size, v->size); + + if (v->caller) + seq_printf(m, " %pS", v->caller); + + if (v->nr_pages) + seq_printf(m, " pages=%d", v->nr_pages); + + if (v->phys_addr) + seq_printf(m, " phys=%pa", &v->phys_addr); + + if (v->flags & VM_IOREMAP) + seq_puts(m, " ioremap"); + + if (v->flags & VM_ALLOC) + seq_puts(m, " vmalloc"); + + if (v->flags & VM_MAP) + seq_puts(m, " vmap"); + + if (v->flags & VM_USERMAP) + seq_puts(m, " user"); + + if (v->flags & VM_DMA_COHERENT) + seq_puts(m, " dma-coherent"); + + if (is_vmalloc_addr(v->pages)) + seq_puts(m, " vpages"); + + show_numa_info(m, v); + seq_putc(m, '\n'); + + /* + * As a final step, dump "unpurged" areas. Note, + * that entire "/proc/vmallocinfo" output will not + * be address sorted, because the purge list is not + * sorted. + */ + if (list_is_last(&va->list, &vmap_area_list)) + show_purge_info(m); + + return 0; +} + +static const struct seq_operations vmalloc_op = { + .start = s_start, + .next = s_next, + .stop = s_stop, + .show = s_show, +}; + +static int __init proc_vmalloc_init(void) +{ + if (IS_ENABLED(CONFIG_NUMA)) + proc_create_seq_private("vmallocinfo", 0400, NULL, + &vmalloc_op, + nr_node_ids * sizeof(unsigned int), NULL); + else + proc_create_seq("vmallocinfo", 0400, NULL, &vmalloc_op); + return 0; +} +module_init(proc_vmalloc_init); + +#endif diff --git a/mm/vmpressure.c b/mm/vmpressure.c new file mode 100644 index 000000000..d69019fc3 --- /dev/null +++ b/mm/vmpressure.c @@ -0,0 +1,469 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Linux VM pressure + * + * Copyright 2012 Linaro Ltd. + * Anton Vorontsov + * + * Based on ideas from Andrew Morton, David Rientjes, KOSAKI Motohiro, + * Leonid Moiseichuk, Mel Gorman, Minchan Kim and Pekka Enberg. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * The window size (vmpressure_win) is the number of scanned pages before + * we try to analyze scanned/reclaimed ratio. So the window is used as a + * rate-limit tunable for the "low" level notification, and also for + * averaging the ratio for medium/critical levels. Using small window + * sizes can cause lot of false positives, but too big window size will + * delay the notifications. + * + * As the vmscan reclaimer logic works with chunks which are multiple of + * SWAP_CLUSTER_MAX, it makes sense to use it for the window size as well. + * + * TODO: Make the window size depend on machine size, as we do for vmstat + * thresholds. Currently we set it to 512 pages (2MB for 4KB pages). + */ +static const unsigned long vmpressure_win = SWAP_CLUSTER_MAX * 16; + +/* + * These thresholds are used when we account memory pressure through + * scanned/reclaimed ratio. The current values were chosen empirically. In + * essence, they are percents: the higher the value, the more number + * unsuccessful reclaims there were. + */ +static const unsigned int vmpressure_level_med = 60; +static const unsigned int vmpressure_level_critical = 95; + +/* + * When there are too little pages left to scan, vmpressure() may miss the + * critical pressure as number of pages will be less than "window size". + * However, in that case the vmscan priority will raise fast as the + * reclaimer will try to scan LRUs more deeply. + * + * The vmscan logic considers these special priorities: + * + * prio == DEF_PRIORITY (12): reclaimer starts with that value + * prio <= DEF_PRIORITY - 2 : kswapd becomes somewhat overwhelmed + * prio == 0 : close to OOM, kernel scans every page in an lru + * + * Any value in this range is acceptable for this tunable (i.e. from 12 to + * 0). Current value for the vmpressure_level_critical_prio is chosen + * empirically, but the number, in essence, means that we consider + * critical level when scanning depth is ~10% of the lru size (vmscan + * scans 'lru_size >> prio' pages, so it is actually 12.5%, or one + * eights). + */ +static const unsigned int vmpressure_level_critical_prio = ilog2(100 / 10); + +static struct vmpressure *work_to_vmpressure(struct work_struct *work) +{ + return container_of(work, struct vmpressure, work); +} + +static struct vmpressure *vmpressure_parent(struct vmpressure *vmpr) +{ + struct cgroup_subsys_state *css = vmpressure_to_css(vmpr); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + + memcg = parent_mem_cgroup(memcg); + if (!memcg) + return NULL; + return memcg_to_vmpressure(memcg); +} + +enum vmpressure_levels { + VMPRESSURE_LOW = 0, + VMPRESSURE_MEDIUM, + VMPRESSURE_CRITICAL, + VMPRESSURE_NUM_LEVELS, +}; + +enum vmpressure_modes { + VMPRESSURE_NO_PASSTHROUGH = 0, + VMPRESSURE_HIERARCHY, + VMPRESSURE_LOCAL, + VMPRESSURE_NUM_MODES, +}; + +static const char * const vmpressure_str_levels[] = { + [VMPRESSURE_LOW] = "low", + [VMPRESSURE_MEDIUM] = "medium", + [VMPRESSURE_CRITICAL] = "critical", +}; + +static const char * const vmpressure_str_modes[] = { + [VMPRESSURE_NO_PASSTHROUGH] = "default", + [VMPRESSURE_HIERARCHY] = "hierarchy", + [VMPRESSURE_LOCAL] = "local", +}; + +static enum vmpressure_levels vmpressure_level(unsigned long pressure) +{ + if (pressure >= vmpressure_level_critical) + return VMPRESSURE_CRITICAL; + else if (pressure >= vmpressure_level_med) + return VMPRESSURE_MEDIUM; + return VMPRESSURE_LOW; +} + +static enum vmpressure_levels vmpressure_calc_level(unsigned long scanned, + unsigned long reclaimed) +{ + unsigned long scale = scanned + reclaimed; + unsigned long pressure = 0; + + /* + * reclaimed can be greater than scanned for things such as reclaimed + * slab pages. shrink_node() just adds reclaimed pages without a + * related increment to scanned pages. + */ + if (reclaimed >= scanned) + goto out; + /* + * We calculate the ratio (in percents) of how many pages were + * scanned vs. reclaimed in a given time frame (window). Note that + * time is in VM reclaimer's "ticks", i.e. number of pages + * scanned. This makes it possible to set desired reaction time + * and serves as a ratelimit. + */ + pressure = scale - (reclaimed * scale / scanned); + pressure = pressure * 100 / scale; + +out: + pr_debug("%s: %3lu (s: %lu r: %lu)\n", __func__, pressure, + scanned, reclaimed); + + return vmpressure_level(pressure); +} + +struct vmpressure_event { + struct eventfd_ctx *efd; + enum vmpressure_levels level; + enum vmpressure_modes mode; + struct list_head node; +}; + +static bool vmpressure_event(struct vmpressure *vmpr, + const enum vmpressure_levels level, + bool ancestor, bool signalled) +{ + struct vmpressure_event *ev; + bool ret = false; + + mutex_lock(&vmpr->events_lock); + list_for_each_entry(ev, &vmpr->events, node) { + if (ancestor && ev->mode == VMPRESSURE_LOCAL) + continue; + if (signalled && ev->mode == VMPRESSURE_NO_PASSTHROUGH) + continue; + if (level < ev->level) + continue; + eventfd_signal(ev->efd, 1); + ret = true; + } + mutex_unlock(&vmpr->events_lock); + + return ret; +} + +static void vmpressure_work_fn(struct work_struct *work) +{ + struct vmpressure *vmpr = work_to_vmpressure(work); + unsigned long scanned; + unsigned long reclaimed; + enum vmpressure_levels level; + bool ancestor = false; + bool signalled = false; + + spin_lock(&vmpr->sr_lock); + /* + * Several contexts might be calling vmpressure(), so it is + * possible that the work was rescheduled again before the old + * work context cleared the counters. In that case we will run + * just after the old work returns, but then scanned might be zero + * here. No need for any locks here since we don't care if + * vmpr->reclaimed is in sync. + */ + scanned = vmpr->tree_scanned; + if (!scanned) { + spin_unlock(&vmpr->sr_lock); + return; + } + + reclaimed = vmpr->tree_reclaimed; + vmpr->tree_scanned = 0; + vmpr->tree_reclaimed = 0; + spin_unlock(&vmpr->sr_lock); + + level = vmpressure_calc_level(scanned, reclaimed); + + do { + if (vmpressure_event(vmpr, level, ancestor, signalled)) + signalled = true; + ancestor = true; + } while ((vmpr = vmpressure_parent(vmpr))); +} + +/** + * vmpressure() - Account memory pressure through scanned/reclaimed ratio + * @gfp: reclaimer's gfp mask + * @memcg: cgroup memory controller handle + * @tree: legacy subtree mode + * @scanned: number of pages scanned + * @reclaimed: number of pages reclaimed + * + * This function should be called from the vmscan reclaim path to account + * "instantaneous" memory pressure (scanned/reclaimed ratio). The raw + * pressure index is then further refined and averaged over time. + * + * If @tree is set, vmpressure is in traditional userspace reporting + * mode: @memcg is considered the pressure root and userspace is + * notified of the entire subtree's reclaim efficiency. + * + * If @tree is not set, reclaim efficiency is recorded for @memcg, and + * only in-kernel users are notified. + * + * This function does not return any value. + */ +void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree, + unsigned long scanned, unsigned long reclaimed) +{ + struct vmpressure *vmpr = memcg_to_vmpressure(memcg); + + /* + * Here we only want to account pressure that userland is able to + * help us with. For example, suppose that DMA zone is under + * pressure; if we notify userland about that kind of pressure, + * then it will be mostly a waste as it will trigger unnecessary + * freeing of memory by userland (since userland is more likely to + * have HIGHMEM/MOVABLE pages instead of the DMA fallback). That + * is why we include only movable, highmem and FS/IO pages. + * Indirect reclaim (kswapd) sets sc->gfp_mask to GFP_KERNEL, so + * we account it too. + */ + if (!(gfp & (__GFP_HIGHMEM | __GFP_MOVABLE | __GFP_IO | __GFP_FS))) + return; + + /* + * If we got here with no pages scanned, then that is an indicator + * that reclaimer was unable to find any shrinkable LRUs at the + * current scanning depth. But it does not mean that we should + * report the critical pressure, yet. If the scanning priority + * (scanning depth) goes too high (deep), we will be notified + * through vmpressure_prio(). But so far, keep calm. + */ + if (!scanned) + return; + + if (tree) { + spin_lock(&vmpr->sr_lock); + scanned = vmpr->tree_scanned += scanned; + vmpr->tree_reclaimed += reclaimed; + spin_unlock(&vmpr->sr_lock); + + if (scanned < vmpressure_win) + return; + schedule_work(&vmpr->work); + } else { + enum vmpressure_levels level; + + /* For now, no users for root-level efficiency */ + if (!memcg || mem_cgroup_is_root(memcg)) + return; + + spin_lock(&vmpr->sr_lock); + scanned = vmpr->scanned += scanned; + reclaimed = vmpr->reclaimed += reclaimed; + if (scanned < vmpressure_win) { + spin_unlock(&vmpr->sr_lock); + return; + } + vmpr->scanned = vmpr->reclaimed = 0; + spin_unlock(&vmpr->sr_lock); + + level = vmpressure_calc_level(scanned, reclaimed); + + if (level > VMPRESSURE_LOW) { + /* + * Let the socket buffer allocator know that + * we are having trouble reclaiming LRU pages. + * + * For hysteresis keep the pressure state + * asserted for a second in which subsequent + * pressure events can occur. + */ + memcg->socket_pressure = jiffies + HZ; + } + } +} + +/** + * vmpressure_prio() - Account memory pressure through reclaimer priority level + * @gfp: reclaimer's gfp mask + * @memcg: cgroup memory controller handle + * @prio: reclaimer's priority + * + * This function should be called from the reclaim path every time when + * the vmscan's reclaiming priority (scanning depth) changes. + * + * This function does not return any value. + */ +void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio) +{ + /* + * We only use prio for accounting critical level. For more info + * see comment for vmpressure_level_critical_prio variable above. + */ + if (prio > vmpressure_level_critical_prio) + return; + + /* + * OK, the prio is below the threshold, updating vmpressure + * information before shrinker dives into long shrinking of long + * range vmscan. Passing scanned = vmpressure_win, reclaimed = 0 + * to the vmpressure() basically means that we signal 'critical' + * level. + */ + vmpressure(gfp, memcg, true, vmpressure_win, 0); +} + +#define MAX_VMPRESSURE_ARGS_LEN (strlen("critical") + strlen("hierarchy") + 2) + +/** + * vmpressure_register_event() - Bind vmpressure notifications to an eventfd + * @memcg: memcg that is interested in vmpressure notifications + * @eventfd: eventfd context to link notifications with + * @args: event arguments (pressure level threshold, optional mode) + * + * This function associates eventfd context with the vmpressure + * infrastructure, so that the notifications will be delivered to the + * @eventfd. The @args parameter is a comma-delimited string that denotes a + * pressure level threshold (one of vmpressure_str_levels, i.e. "low", "medium", + * or "critical") and an optional mode (one of vmpressure_str_modes, i.e. + * "hierarchy" or "local"). + * + * To be used as memcg event method. + * + * Return: 0 on success, -ENOMEM on memory failure or -EINVAL if @args could + * not be parsed. + */ +int vmpressure_register_event(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd, const char *args) +{ + struct vmpressure *vmpr = memcg_to_vmpressure(memcg); + struct vmpressure_event *ev; + enum vmpressure_modes mode = VMPRESSURE_NO_PASSTHROUGH; + enum vmpressure_levels level; + char *spec, *spec_orig; + char *token; + int ret = 0; + + spec_orig = spec = kstrndup(args, MAX_VMPRESSURE_ARGS_LEN, GFP_KERNEL); + if (!spec) + return -ENOMEM; + + /* Find required level */ + token = strsep(&spec, ","); + ret = match_string(vmpressure_str_levels, VMPRESSURE_NUM_LEVELS, token); + if (ret < 0) + goto out; + level = ret; + + /* Find optional mode */ + token = strsep(&spec, ","); + if (token) { + ret = match_string(vmpressure_str_modes, VMPRESSURE_NUM_MODES, token); + if (ret < 0) + goto out; + mode = ret; + } + + ev = kzalloc(sizeof(*ev), GFP_KERNEL); + if (!ev) { + ret = -ENOMEM; + goto out; + } + + ev->efd = eventfd; + ev->level = level; + ev->mode = mode; + + mutex_lock(&vmpr->events_lock); + list_add(&ev->node, &vmpr->events); + mutex_unlock(&vmpr->events_lock); + ret = 0; +out: + kfree(spec_orig); + return ret; +} + +/** + * vmpressure_unregister_event() - Unbind eventfd from vmpressure + * @memcg: memcg handle + * @eventfd: eventfd context that was used to link vmpressure with the @cg + * + * This function does internal manipulations to detach the @eventfd from + * the vmpressure notifications, and then frees internal resources + * associated with the @eventfd (but the @eventfd itself is not freed). + * + * To be used as memcg event method. + */ +void vmpressure_unregister_event(struct mem_cgroup *memcg, + struct eventfd_ctx *eventfd) +{ + struct vmpressure *vmpr = memcg_to_vmpressure(memcg); + struct vmpressure_event *ev; + + mutex_lock(&vmpr->events_lock); + list_for_each_entry(ev, &vmpr->events, node) { + if (ev->efd != eventfd) + continue; + list_del(&ev->node); + kfree(ev); + break; + } + mutex_unlock(&vmpr->events_lock); +} + +/** + * vmpressure_init() - Initialize vmpressure control structure + * @vmpr: Structure to be initialized + * + * This function should be called on every allocated vmpressure structure + * before any usage. + */ +void vmpressure_init(struct vmpressure *vmpr) +{ + spin_lock_init(&vmpr->sr_lock); + mutex_init(&vmpr->events_lock); + INIT_LIST_HEAD(&vmpr->events); + INIT_WORK(&vmpr->work, vmpressure_work_fn); +} + +/** + * vmpressure_cleanup() - shuts down vmpressure control structure + * @vmpr: Structure to be cleaned up + * + * This function should be called before the structure in which it is + * embedded is cleaned up. + */ +void vmpressure_cleanup(struct vmpressure *vmpr) +{ + /* + * Make sure there is no pending work before eventfd infrastructure + * goes away. + */ + flush_work(&vmpr->work); +} diff --git a/mm/vmscan.c b/mm/vmscan.c new file mode 100644 index 000000000..51ccd80e7 --- /dev/null +++ b/mm/vmscan.c @@ -0,0 +1,4322 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/mm/vmscan.c + * + * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds + * + * Swap reorganised 29.12.95, Stephen Tweedie. + * kswapd added: 7.1.96 sct + * Removed kswapd_ctl limits, and swap out as many pages as needed + * to bring the system back to freepages.high: 2.4.97, Rik van Riel. + * Zone aware kswapd started 02/00, Kanoj Sarcar (kanoj@sgi.com). + * Multiqueue VM started 5.8.00, Rik van Riel. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include /* for try_to_release_page(), + buffer_heads_over_limit */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include +#include + +#include "internal.h" + +#define CREATE_TRACE_POINTS +#include + +struct scan_control { + /* How many pages shrink_list() should reclaim */ + unsigned long nr_to_reclaim; + + /* + * Nodemask of nodes allowed by the caller. If NULL, all nodes + * are scanned. + */ + nodemask_t *nodemask; + + /* + * The memory cgroup that hit its limit and as a result is the + * primary target of this reclaim invocation. + */ + struct mem_cgroup *target_mem_cgroup; + + /* + * Scan pressure balancing between anon and file LRUs + */ + unsigned long anon_cost; + unsigned long file_cost; + + /* Can active pages be deactivated as part of reclaim? */ +#define DEACTIVATE_ANON 1 +#define DEACTIVATE_FILE 2 + unsigned int may_deactivate:2; + unsigned int force_deactivate:1; + unsigned int skipped_deactivate:1; + + /* Writepage batching in laptop mode; RECLAIM_WRITE */ + unsigned int may_writepage:1; + + /* Can mapped pages be reclaimed? */ + unsigned int may_unmap:1; + + /* Can pages be swapped as part of reclaim? */ + unsigned int may_swap:1; + + /* + * Cgroup memory below memory.low is protected as long as we + * don't threaten to OOM. If any cgroup is reclaimed at + * reduced force or passed over entirely due to its memory.low + * setting (memcg_low_skipped), and nothing is reclaimed as a + * result, then go back for one more cycle that reclaims the protected + * memory (memcg_low_reclaim) to avert OOM. + */ + unsigned int memcg_low_reclaim:1; + unsigned int memcg_low_skipped:1; + + unsigned int hibernation_mode:1; + + /* One of the zones is ready for compaction */ + unsigned int compaction_ready:1; + + /* There is easily reclaimable cold cache in the current node */ + unsigned int cache_trim_mode:1; + + /* The file pages on the current node are dangerously low */ + unsigned int file_is_tiny:1; + + /* Allocation order */ + s8 order; + + /* Scan (total_size >> priority) pages at once */ + s8 priority; + + /* The highest zone to isolate pages for reclaim from */ + s8 reclaim_idx; + + /* This context's GFP mask */ + gfp_t gfp_mask; + + /* Incremented by the number of inactive pages that were scanned */ + unsigned long nr_scanned; + + /* Number of pages freed so far during a call to shrink_zones() */ + unsigned long nr_reclaimed; + + struct { + unsigned int dirty; + unsigned int unqueued_dirty; + unsigned int congested; + unsigned int writeback; + unsigned int immediate; + unsigned int file_taken; + unsigned int taken; + } nr; + + /* for recording the reclaimed slab by now */ + struct reclaim_state reclaim_state; +}; + +#ifdef ARCH_HAS_PREFETCHW +#define prefetchw_prev_lru_page(_page, _base, _field) \ + do { \ + if ((_page)->lru.prev != _base) { \ + struct page *prev; \ + \ + prev = lru_to_page(&(_page->lru)); \ + prefetchw(&prev->_field); \ + } \ + } while (0) +#else +#define prefetchw_prev_lru_page(_page, _base, _field) do { } while (0) +#endif + +/* + * From 0 .. 200. Higher means more swappy. + */ +int vm_swappiness = 60; + +static void set_task_reclaim_state(struct task_struct *task, + struct reclaim_state *rs) +{ + /* Check for an overwrite */ + WARN_ON_ONCE(rs && task->reclaim_state); + + /* Check for the nulling of an already-nulled member */ + WARN_ON_ONCE(!rs && !task->reclaim_state); + + task->reclaim_state = rs; +} + +static LIST_HEAD(shrinker_list); +static DECLARE_RWSEM(shrinker_rwsem); + +#ifdef CONFIG_MEMCG +/* + * We allow subsystems to populate their shrinker-related + * LRU lists before register_shrinker_prepared() is called + * for the shrinker, since we don't want to impose + * restrictions on their internal registration order. + * In this case shrink_slab_memcg() may find corresponding + * bit is set in the shrinkers map. + * + * This value is used by the function to detect registering + * shrinkers and to skip do_shrink_slab() calls for them. + */ +#define SHRINKER_REGISTERING ((struct shrinker *)~0UL) + +static DEFINE_IDR(shrinker_idr); +static int shrinker_nr_max; + +static int prealloc_memcg_shrinker(struct shrinker *shrinker) +{ + int id, ret = -ENOMEM; + + down_write(&shrinker_rwsem); + /* This may call shrinker, so it must use down_read_trylock() */ + id = idr_alloc(&shrinker_idr, SHRINKER_REGISTERING, 0, 0, GFP_KERNEL); + if (id < 0) + goto unlock; + + if (id >= shrinker_nr_max) { + if (memcg_expand_shrinker_maps(id)) { + idr_remove(&shrinker_idr, id); + goto unlock; + } + + shrinker_nr_max = id + 1; + } + shrinker->id = id; + ret = 0; +unlock: + up_write(&shrinker_rwsem); + return ret; +} + +static void unregister_memcg_shrinker(struct shrinker *shrinker) +{ + int id = shrinker->id; + + BUG_ON(id < 0); + + down_write(&shrinker_rwsem); + idr_remove(&shrinker_idr, id); + up_write(&shrinker_rwsem); +} + +static bool cgroup_reclaim(struct scan_control *sc) +{ + return sc->target_mem_cgroup; +} + +/** + * writeback_throttling_sane - is the usual dirty throttling mechanism available? + * @sc: scan_control in question + * + * The normal page dirty throttling mechanism in balance_dirty_pages() is + * completely broken with the legacy memcg and direct stalling in + * shrink_page_list() is used for throttling instead, which lacks all the + * niceties such as fairness, adaptive pausing, bandwidth proportional + * allocation and configurability. + * + * This function tests whether the vmscan currently in progress can assume + * that the normal dirty throttling mechanism is operational. + */ +static bool writeback_throttling_sane(struct scan_control *sc) +{ + if (!cgroup_reclaim(sc)) + return true; +#ifdef CONFIG_CGROUP_WRITEBACK + if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) + return true; +#endif + return false; +} +#else +static int prealloc_memcg_shrinker(struct shrinker *shrinker) +{ + return 0; +} + +static void unregister_memcg_shrinker(struct shrinker *shrinker) +{ +} + +static bool cgroup_reclaim(struct scan_control *sc) +{ + return false; +} + +static bool writeback_throttling_sane(struct scan_control *sc) +{ + return true; +} +#endif + +/* + * This misses isolated pages which are not accounted for to save counters. + * As the data only determines if reclaim or compaction continues, it is + * not expected that isolated pages will be a dominating factor. + */ +unsigned long zone_reclaimable_pages(struct zone *zone) +{ + unsigned long nr; + + nr = zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_FILE) + + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_FILE); + if (get_nr_swap_pages() > 0) + nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) + + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON); + + return nr; +} + +/** + * lruvec_lru_size - Returns the number of pages on the given LRU list. + * @lruvec: lru vector + * @lru: lru to use + * @zone_idx: zones to consider (use MAX_NR_ZONES for the whole LRU list) + */ +unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) +{ + unsigned long size = 0; + int zid; + + for (zid = 0; zid <= zone_idx && zid < MAX_NR_ZONES; zid++) { + struct zone *zone = &lruvec_pgdat(lruvec)->node_zones[zid]; + + if (!managed_zone(zone)) + continue; + + if (!mem_cgroup_disabled()) + size += mem_cgroup_get_zone_lru_size(lruvec, lru, zid); + else + size += zone_page_state(zone, NR_ZONE_LRU_BASE + lru); + } + return size; +} + +/* + * Add a shrinker callback to be called from the vm. + */ +int prealloc_shrinker(struct shrinker *shrinker) +{ + unsigned int size = sizeof(*shrinker->nr_deferred); + + if (shrinker->flags & SHRINKER_NUMA_AWARE) + size *= nr_node_ids; + + shrinker->nr_deferred = kzalloc(size, GFP_KERNEL); + if (!shrinker->nr_deferred) + return -ENOMEM; + + if (shrinker->flags & SHRINKER_MEMCG_AWARE) { + if (prealloc_memcg_shrinker(shrinker)) + goto free_deferred; + } + + return 0; + +free_deferred: + kfree(shrinker->nr_deferred); + shrinker->nr_deferred = NULL; + return -ENOMEM; +} + +void free_prealloced_shrinker(struct shrinker *shrinker) +{ + if (!shrinker->nr_deferred) + return; + + if (shrinker->flags & SHRINKER_MEMCG_AWARE) + unregister_memcg_shrinker(shrinker); + + kfree(shrinker->nr_deferred); + shrinker->nr_deferred = NULL; +} + +void register_shrinker_prepared(struct shrinker *shrinker) +{ + down_write(&shrinker_rwsem); + list_add_tail(&shrinker->list, &shrinker_list); +#ifdef CONFIG_MEMCG + if (shrinker->flags & SHRINKER_MEMCG_AWARE) + idr_replace(&shrinker_idr, shrinker, shrinker->id); +#endif + up_write(&shrinker_rwsem); +} + +int register_shrinker(struct shrinker *shrinker) +{ + int err = prealloc_shrinker(shrinker); + + if (err) + return err; + register_shrinker_prepared(shrinker); + return 0; +} +EXPORT_SYMBOL(register_shrinker); + +/* + * Remove one + */ +void unregister_shrinker(struct shrinker *shrinker) +{ + if (!shrinker->nr_deferred) + return; + if (shrinker->flags & SHRINKER_MEMCG_AWARE) + unregister_memcg_shrinker(shrinker); + down_write(&shrinker_rwsem); + list_del(&shrinker->list); + up_write(&shrinker_rwsem); + kfree(shrinker->nr_deferred); + shrinker->nr_deferred = NULL; +} +EXPORT_SYMBOL(unregister_shrinker); + +#define SHRINK_BATCH 128 + +static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, + struct shrinker *shrinker, int priority) +{ + unsigned long freed = 0; + unsigned long long delta; + long total_scan; + long freeable; + long nr; + long new_nr; + int nid = shrinkctl->nid; + long batch_size = shrinker->batch ? shrinker->batch + : SHRINK_BATCH; + long scanned = 0, next_deferred; + + if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) + nid = 0; + + freeable = shrinker->count_objects(shrinker, shrinkctl); + if (freeable == 0 || freeable == SHRINK_EMPTY) + return freeable; + + /* + * copy the current shrinker scan count into a local variable + * and zero it so that other concurrent shrinker invocations + * don't also do this scanning work. + */ + nr = atomic_long_xchg(&shrinker->nr_deferred[nid], 0); + + total_scan = nr; + if (shrinker->seeks) { + delta = freeable >> priority; + delta *= 4; + do_div(delta, shrinker->seeks); + } else { + /* + * These objects don't require any IO to create. Trim + * them aggressively under memory pressure to keep + * them from causing refetches in the IO caches. + */ + delta = freeable / 2; + } + + total_scan += delta; + if (total_scan < 0) { + pr_err("shrink_slab: %pS negative objects to delete nr=%ld\n", + shrinker->scan_objects, total_scan); + total_scan = freeable; + next_deferred = nr; + } else + next_deferred = total_scan; + + /* + * We need to avoid excessive windup on filesystem shrinkers + * due to large numbers of GFP_NOFS allocations causing the + * shrinkers to return -1 all the time. This results in a large + * nr being built up so when a shrink that can do some work + * comes along it empties the entire cache due to nr >>> + * freeable. This is bad for sustaining a working set in + * memory. + * + * Hence only allow the shrinker to scan the entire cache when + * a large delta change is calculated directly. + */ + if (delta < freeable / 4) + total_scan = min(total_scan, freeable / 2); + + /* + * Avoid risking looping forever due to too large nr value: + * never try to free more than twice the estimate number of + * freeable entries. + */ + if (total_scan > freeable * 2) + total_scan = freeable * 2; + + trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, + freeable, delta, total_scan, priority); + + /* + * Normally, we should not scan less than batch_size objects in one + * pass to avoid too frequent shrinker calls, but if the slab has less + * than batch_size objects in total and we are really tight on memory, + * we will try to reclaim all available objects, otherwise we can end + * up failing allocations although there are plenty of reclaimable + * objects spread over several slabs with usage less than the + * batch_size. + * + * We detect the "tight on memory" situations by looking at the total + * number of objects we want to scan (total_scan). If it is greater + * than the total number of objects on slab (freeable), we must be + * scanning at high prio and therefore should try to reclaim as much as + * possible. + */ + while (total_scan >= batch_size || + total_scan >= freeable) { + unsigned long ret; + unsigned long nr_to_scan = min(batch_size, total_scan); + + shrinkctl->nr_to_scan = nr_to_scan; + shrinkctl->nr_scanned = nr_to_scan; + ret = shrinker->scan_objects(shrinker, shrinkctl); + if (ret == SHRINK_STOP) + break; + freed += ret; + + count_vm_events(SLABS_SCANNED, shrinkctl->nr_scanned); + total_scan -= shrinkctl->nr_scanned; + scanned += shrinkctl->nr_scanned; + + cond_resched(); + } + + if (next_deferred >= scanned) + next_deferred -= scanned; + else + next_deferred = 0; + /* + * move the unused scan count back into the shrinker in a + * manner that handles concurrent updates. If we exhausted the + * scan, there is no need to do an update. + */ + if (next_deferred > 0) + new_nr = atomic_long_add_return(next_deferred, + &shrinker->nr_deferred[nid]); + else + new_nr = atomic_long_read(&shrinker->nr_deferred[nid]); + + trace_mm_shrink_slab_end(shrinker, nid, freed, nr, new_nr, total_scan); + return freed; +} + +#ifdef CONFIG_MEMCG +static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, + struct mem_cgroup *memcg, int priority) +{ + struct memcg_shrinker_map *map; + unsigned long ret, freed = 0; + int i; + + if (!mem_cgroup_online(memcg)) + return 0; + + if (!down_read_trylock(&shrinker_rwsem)) + return 0; + + map = rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_map, + true); + if (unlikely(!map)) + goto unlock; + + for_each_set_bit(i, map->map, shrinker_nr_max) { + struct shrink_control sc = { + .gfp_mask = gfp_mask, + .nid = nid, + .memcg = memcg, + }; + struct shrinker *shrinker; + + shrinker = idr_find(&shrinker_idr, i); + if (unlikely(!shrinker || shrinker == SHRINKER_REGISTERING)) { + if (!shrinker) + clear_bit(i, map->map); + continue; + } + + /* Call non-slab shrinkers even though kmem is disabled */ + if (!memcg_kmem_enabled() && + !(shrinker->flags & SHRINKER_NONSLAB)) + continue; + + ret = do_shrink_slab(&sc, shrinker, priority); + if (ret == SHRINK_EMPTY) { + clear_bit(i, map->map); + /* + * After the shrinker reported that it had no objects to + * free, but before we cleared the corresponding bit in + * the memcg shrinker map, a new object might have been + * added. To make sure, we have the bit set in this + * case, we invoke the shrinker one more time and reset + * the bit if it reports that it is not empty anymore. + * The memory barrier here pairs with the barrier in + * memcg_set_shrinker_bit(): + * + * list_lru_add() shrink_slab_memcg() + * list_add_tail() clear_bit() + * + * set_bit() do_shrink_slab() + */ + smp_mb__after_atomic(); + ret = do_shrink_slab(&sc, shrinker, priority); + if (ret == SHRINK_EMPTY) + ret = 0; + else + memcg_set_shrinker_bit(memcg, nid, i); + } + freed += ret; + + if (rwsem_is_contended(&shrinker_rwsem)) { + freed = freed ? : 1; + break; + } + } +unlock: + up_read(&shrinker_rwsem); + return freed; +} +#else /* CONFIG_MEMCG */ +static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, + struct mem_cgroup *memcg, int priority) +{ + return 0; +} +#endif /* CONFIG_MEMCG */ + +/** + * shrink_slab - shrink slab caches + * @gfp_mask: allocation context + * @nid: node whose slab caches to target + * @memcg: memory cgroup whose slab caches to target + * @priority: the reclaim priority + * + * Call the shrink functions to age shrinkable caches. + * + * @nid is passed along to shrinkers with SHRINKER_NUMA_AWARE set, + * unaware shrinkers will receive a node id of 0 instead. + * + * @memcg specifies the memory cgroup to target. Unaware shrinkers + * are called only if it is the root cgroup. + * + * @priority is sc->priority, we take the number of objects and >> by priority + * in order to get the scan target. + * + * Returns the number of reclaimed slab objects. + */ +static unsigned long shrink_slab(gfp_t gfp_mask, int nid, + struct mem_cgroup *memcg, + int priority) +{ + unsigned long ret, freed = 0; + struct shrinker *shrinker; + + /* + * The root memcg might be allocated even though memcg is disabled + * via "cgroup_disable=memory" boot parameter. This could make + * mem_cgroup_is_root() return false, then just run memcg slab + * shrink, but skip global shrink. This may result in premature + * oom. + */ + if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg)) + return shrink_slab_memcg(gfp_mask, nid, memcg, priority); + + if (!down_read_trylock(&shrinker_rwsem)) + goto out; + + list_for_each_entry(shrinker, &shrinker_list, list) { + struct shrink_control sc = { + .gfp_mask = gfp_mask, + .nid = nid, + .memcg = memcg, + }; + + ret = do_shrink_slab(&sc, shrinker, priority); + if (ret == SHRINK_EMPTY) + ret = 0; + freed += ret; + /* + * Bail out if someone want to register a new shrinker to + * prevent the registration from being stalled for long periods + * by parallel ongoing shrinking. + */ + if (rwsem_is_contended(&shrinker_rwsem)) { + freed = freed ? : 1; + break; + } + } + + up_read(&shrinker_rwsem); +out: + cond_resched(); + return freed; +} + +void drop_slab_node(int nid) +{ + unsigned long freed; + + do { + struct mem_cgroup *memcg = NULL; + + if (fatal_signal_pending(current)) + return; + + freed = 0; + memcg = mem_cgroup_iter(NULL, NULL, NULL); + do { + freed += shrink_slab(GFP_KERNEL, nid, memcg, 0); + } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); + } while (freed > 10); +} + +void drop_slab(void) +{ + int nid; + + for_each_online_node(nid) + drop_slab_node(nid); +} + +static inline int is_page_cache_freeable(struct page *page) +{ + /* + * A freeable page cache page is referenced only by the caller + * that isolated the page, the page cache and optional buffer + * heads at page->private. + */ + int page_cache_pins = thp_nr_pages(page); + return page_count(page) - page_has_private(page) == 1 + page_cache_pins; +} + +static int may_write_to_inode(struct inode *inode) +{ + if (current->flags & PF_SWAPWRITE) + return 1; + if (!inode_write_congested(inode)) + return 1; + if (inode_to_bdi(inode) == current->backing_dev_info) + return 1; + return 0; +} + +/* + * We detected a synchronous write error writing a page out. Probably + * -ENOSPC. We need to propagate that into the address_space for a subsequent + * fsync(), msync() or close(). + * + * The tricky part is that after writepage we cannot touch the mapping: nothing + * prevents it from being freed up. But we have a ref on the page and once + * that page is locked, the mapping is pinned. + * + * We're allowed to run sleeping lock_page() here because we know the caller has + * __GFP_FS. + */ +static void handle_write_error(struct address_space *mapping, + struct page *page, int error) +{ + lock_page(page); + if (page_mapping(page) == mapping) + mapping_set_error(mapping, error); + unlock_page(page); +} + +/* possible outcome of pageout() */ +typedef enum { + /* failed to write page out, page is locked */ + PAGE_KEEP, + /* move page to the active list, page is locked */ + PAGE_ACTIVATE, + /* page has been sent to the disk successfully, page is unlocked */ + PAGE_SUCCESS, + /* page is clean and locked */ + PAGE_CLEAN, +} pageout_t; + +/* + * pageout is called by shrink_page_list() for each dirty page. + * Calls ->writepage(). + */ +static pageout_t pageout(struct page *page, struct address_space *mapping) +{ + /* + * If the page is dirty, only perform writeback if that write + * will be non-blocking. To prevent this allocation from being + * stalled by pagecache activity. But note that there may be + * stalls if we need to run get_block(). We could test + * PagePrivate for that. + * + * If this process is currently in __generic_file_write_iter() against + * this page's queue, we can perform writeback even if that + * will block. + * + * If the page is swapcache, write it back even if that would + * block, for some throttling. This happens by accident, because + * swap_backing_dev_info is bust: it doesn't reflect the + * congestion state of the swapdevs. Easy to fix, if needed. + */ + if (!is_page_cache_freeable(page)) + return PAGE_KEEP; + if (!mapping) { + /* + * Some data journaling orphaned pages can have + * page->mapping == NULL while being dirty with clean buffers. + */ + if (page_has_private(page)) { + if (try_to_free_buffers(page)) { + ClearPageDirty(page); + pr_info("%s: orphaned page\n", __func__); + return PAGE_CLEAN; + } + } + return PAGE_KEEP; + } + if (mapping->a_ops->writepage == NULL) + return PAGE_ACTIVATE; + if (!may_write_to_inode(mapping->host)) + return PAGE_KEEP; + + if (clear_page_dirty_for_io(page)) { + int res; + struct writeback_control wbc = { + .sync_mode = WB_SYNC_NONE, + .nr_to_write = SWAP_CLUSTER_MAX, + .range_start = 0, + .range_end = LLONG_MAX, + .for_reclaim = 1, + }; + + SetPageReclaim(page); + res = mapping->a_ops->writepage(page, &wbc); + if (res < 0) + handle_write_error(mapping, page, res); + if (res == AOP_WRITEPAGE_ACTIVATE) { + ClearPageReclaim(page); + return PAGE_ACTIVATE; + } + + if (!PageWriteback(page)) { + /* synchronous write or broken a_ops? */ + ClearPageReclaim(page); + } + trace_mm_vmscan_writepage(page); + inc_node_page_state(page, NR_VMSCAN_WRITE); + return PAGE_SUCCESS; + } + + return PAGE_CLEAN; +} + +/* + * Same as remove_mapping, but if the page is removed from the mapping, it + * gets returned with a refcount of 0. + */ +static int __remove_mapping(struct address_space *mapping, struct page *page, + bool reclaimed, struct mem_cgroup *target_memcg) +{ + unsigned long flags; + int refcount; + void *shadow = NULL; + + BUG_ON(!PageLocked(page)); + BUG_ON(mapping != page_mapping(page)); + + xa_lock_irqsave(&mapping->i_pages, flags); + /* + * The non racy check for a busy page. + * + * Must be careful with the order of the tests. When someone has + * a ref to the page, it may be possible that they dirty it then + * drop the reference. So if PageDirty is tested before page_count + * here, then the following race may occur: + * + * get_user_pages(&page); + * [user mapping goes away] + * write_to(page); + * !PageDirty(page) [good] + * SetPageDirty(page); + * put_page(page); + * !page_count(page) [good, discard it] + * + * [oops, our write_to data is lost] + * + * Reversing the order of the tests ensures such a situation cannot + * escape unnoticed. The smp_rmb is needed to ensure the page->flags + * load is not satisfied before that of page->_refcount. + * + * Note that if SetPageDirty is always performed via set_page_dirty, + * and thus under the i_pages lock, then this ordering is not required. + */ + refcount = 1 + compound_nr(page); + if (!page_ref_freeze(page, refcount)) + goto cannot_free; + /* note: atomic_cmpxchg in page_ref_freeze provides the smp_rmb */ + if (unlikely(PageDirty(page))) { + page_ref_unfreeze(page, refcount); + goto cannot_free; + } + + if (PageSwapCache(page)) { + swp_entry_t swap = { .val = page_private(page) }; + mem_cgroup_swapout(page, swap); + if (reclaimed && !mapping_exiting(mapping)) + shadow = workingset_eviction(page, target_memcg); + __delete_from_swap_cache(page, swap, shadow); + xa_unlock_irqrestore(&mapping->i_pages, flags); + put_swap_page(page, swap); + } else { + void (*freepage)(struct page *); + + freepage = mapping->a_ops->freepage; + /* + * Remember a shadow entry for reclaimed file cache in + * order to detect refaults, thus thrashing, later on. + * + * But don't store shadows in an address space that is + * already exiting. This is not just an optimization, + * inode reclaim needs to empty out the radix tree or + * the nodes are lost. Don't plant shadows behind its + * back. + * + * We also don't store shadows for DAX mappings because the + * only page cache pages found in these are zero pages + * covering holes, and because we don't want to mix DAX + * exceptional entries and shadow exceptional entries in the + * same address_space. + */ + if (reclaimed && page_is_file_lru(page) && + !mapping_exiting(mapping) && !dax_mapping(mapping)) + shadow = workingset_eviction(page, target_memcg); + __delete_from_page_cache(page, shadow); + xa_unlock_irqrestore(&mapping->i_pages, flags); + + if (freepage != NULL) + freepage(page); + } + + return 1; + +cannot_free: + xa_unlock_irqrestore(&mapping->i_pages, flags); + return 0; +} + +/* + * Attempt to detach a locked page from its ->mapping. If it is dirty or if + * someone else has a ref on the page, abort and return 0. If it was + * successfully detached, return 1. Assumes the caller has a single ref on + * this page. + */ +int remove_mapping(struct address_space *mapping, struct page *page) +{ + if (__remove_mapping(mapping, page, false, NULL)) { + /* + * Unfreezing the refcount with 1 rather than 2 effectively + * drops the pagecache ref for us without requiring another + * atomic operation. + */ + page_ref_unfreeze(page, 1); + return 1; + } + return 0; +} + +/** + * putback_lru_page - put previously isolated page onto appropriate LRU list + * @page: page to be put back to appropriate lru list + * + * Add previously isolated @page to appropriate LRU list. + * Page may still be unevictable for other reasons. + * + * lru_lock must not be held, interrupts must be enabled. + */ +void putback_lru_page(struct page *page) +{ + lru_cache_add(page); + put_page(page); /* drop ref from isolate */ +} + +enum page_references { + PAGEREF_RECLAIM, + PAGEREF_RECLAIM_CLEAN, + PAGEREF_KEEP, + PAGEREF_ACTIVATE, +}; + +static enum page_references page_check_references(struct page *page, + struct scan_control *sc) +{ + int referenced_ptes, referenced_page; + unsigned long vm_flags; + + referenced_ptes = page_referenced(page, 1, sc->target_mem_cgroup, + &vm_flags); + referenced_page = TestClearPageReferenced(page); + + /* + * Mlock lost the isolation race with us. Let try_to_unmap() + * move the page to the unevictable list. + */ + if (vm_flags & VM_LOCKED) + return PAGEREF_RECLAIM; + + if (referenced_ptes) { + /* + * All mapped pages start out with page table + * references from the instantiating fault, so we need + * to look twice if a mapped file page is used more + * than once. + * + * Mark it and spare it for another trip around the + * inactive list. Another page table reference will + * lead to its activation. + * + * Note: the mark is set for activated pages as well + * so that recently deactivated but used pages are + * quickly recovered. + */ + SetPageReferenced(page); + + if (referenced_page || referenced_ptes > 1) + return PAGEREF_ACTIVATE; + + /* + * Activate file-backed executable pages after first usage. + */ + if ((vm_flags & VM_EXEC) && !PageSwapBacked(page)) + return PAGEREF_ACTIVATE; + + return PAGEREF_KEEP; + } + + /* Reclaim if clean, defer dirty pages to writeback */ + if (referenced_page && !PageSwapBacked(page)) + return PAGEREF_RECLAIM_CLEAN; + + return PAGEREF_RECLAIM; +} + +/* Check if a page is dirty or under writeback */ +static void page_check_dirty_writeback(struct page *page, + bool *dirty, bool *writeback) +{ + struct address_space *mapping; + + /* + * Anonymous pages are not handled by flushers and must be written + * from reclaim context. Do not stall reclaim based on them + */ + if (!page_is_file_lru(page) || + (PageAnon(page) && !PageSwapBacked(page))) { + *dirty = false; + *writeback = false; + return; + } + + /* By default assume that the page flags are accurate */ + *dirty = PageDirty(page); + *writeback = PageWriteback(page); + + /* Verify dirty/writeback state if the filesystem supports it */ + if (!page_has_private(page)) + return; + + mapping = page_mapping(page); + if (mapping && mapping->a_ops->is_dirty_writeback) + mapping->a_ops->is_dirty_writeback(page, dirty, writeback); +} + +/* + * shrink_page_list() returns the number of reclaimed pages + */ +static unsigned int shrink_page_list(struct list_head *page_list, + struct pglist_data *pgdat, + struct scan_control *sc, + struct reclaim_stat *stat, + bool ignore_references) +{ + LIST_HEAD(ret_pages); + LIST_HEAD(free_pages); + unsigned int nr_reclaimed = 0; + unsigned int pgactivate = 0; + + memset(stat, 0, sizeof(*stat)); + cond_resched(); + + while (!list_empty(page_list)) { + struct address_space *mapping; + struct page *page; + enum page_references references = PAGEREF_RECLAIM; + bool dirty, writeback, may_enter_fs; + unsigned int nr_pages; + + cond_resched(); + + page = lru_to_page(page_list); + list_del(&page->lru); + + if (!trylock_page(page)) + goto keep; + + VM_BUG_ON_PAGE(PageActive(page), page); + + nr_pages = compound_nr(page); + + /* Account the number of base pages even though THP */ + sc->nr_scanned += nr_pages; + + if (unlikely(!page_evictable(page))) + goto activate_locked; + + if (!sc->may_unmap && page_mapped(page)) + goto keep_locked; + + may_enter_fs = (sc->gfp_mask & __GFP_FS) || + (PageSwapCache(page) && (sc->gfp_mask & __GFP_IO)); + + /* + * The number of dirty pages determines if a node is marked + * reclaim_congested which affects wait_iff_congested. kswapd + * will stall and start writing pages if the tail of the LRU + * is all dirty unqueued pages. + */ + page_check_dirty_writeback(page, &dirty, &writeback); + if (dirty || writeback) + stat->nr_dirty++; + + if (dirty && !writeback) + stat->nr_unqueued_dirty++; + + /* + * Treat this page as congested if the underlying BDI is or if + * pages are cycling through the LRU so quickly that the + * pages marked for immediate reclaim are making it to the + * end of the LRU a second time. + */ + mapping = page_mapping(page); + if (((dirty || writeback) && mapping && + inode_write_congested(mapping->host)) || + (writeback && PageReclaim(page))) + stat->nr_congested++; + + /* + * If a page at the tail of the LRU is under writeback, there + * are three cases to consider. + * + * 1) If reclaim is encountering an excessive number of pages + * under writeback and this page is both under writeback and + * PageReclaim then it indicates that pages are being queued + * for IO but are being recycled through the LRU before the + * IO can complete. Waiting on the page itself risks an + * indefinite stall if it is impossible to writeback the + * page due to IO error or disconnected storage so instead + * note that the LRU is being scanned too quickly and the + * caller can stall after page list has been processed. + * + * 2) Global or new memcg reclaim encounters a page that is + * not marked for immediate reclaim, or the caller does not + * have __GFP_FS (or __GFP_IO if it's simply going to swap, + * not to fs). In this case mark the page for immediate + * reclaim and continue scanning. + * + * Require may_enter_fs because we would wait on fs, which + * may not have submitted IO yet. And the loop driver might + * enter reclaim, and deadlock if it waits on a page for + * which it is needed to do the write (loop masks off + * __GFP_IO|__GFP_FS for this reason); but more thought + * would probably show more reasons. + * + * 3) Legacy memcg encounters a page that is already marked + * PageReclaim. memcg does not have any dirty pages + * throttling so we could easily OOM just because too many + * pages are in writeback and there is nothing else to + * reclaim. Wait for the writeback to complete. + * + * In cases 1) and 2) we activate the pages to get them out of + * the way while we continue scanning for clean pages on the + * inactive list and refilling from the active list. The + * observation here is that waiting for disk writes is more + * expensive than potentially causing reloads down the line. + * Since they're marked for immediate reclaim, they won't put + * memory pressure on the cache working set any longer than it + * takes to write them to disk. + */ + if (PageWriteback(page)) { + /* Case 1 above */ + if (current_is_kswapd() && + PageReclaim(page) && + test_bit(PGDAT_WRITEBACK, &pgdat->flags)) { + stat->nr_immediate++; + goto activate_locked; + + /* Case 2 above */ + } else if (writeback_throttling_sane(sc) || + !PageReclaim(page) || !may_enter_fs) { + /* + * This is slightly racy - end_page_writeback() + * might have just cleared PageReclaim, then + * setting PageReclaim here end up interpreted + * as PageReadahead - but that does not matter + * enough to care. What we do want is for this + * page to have PageReclaim set next time memcg + * reclaim reaches the tests above, so it will + * then wait_on_page_writeback() to avoid OOM; + * and it's also appropriate in global reclaim. + */ + SetPageReclaim(page); + stat->nr_writeback++; + goto activate_locked; + + /* Case 3 above */ + } else { + unlock_page(page); + wait_on_page_writeback(page); + /* then go back and try same page again */ + list_add_tail(&page->lru, page_list); + continue; + } + } + + if (!ignore_references) + references = page_check_references(page, sc); + + switch (references) { + case PAGEREF_ACTIVATE: + goto activate_locked; + case PAGEREF_KEEP: + stat->nr_ref_keep += nr_pages; + goto keep_locked; + case PAGEREF_RECLAIM: + case PAGEREF_RECLAIM_CLEAN: + ; /* try to reclaim the page below */ + } + + /* + * Anonymous process memory has backing store? + * Try to allocate it some swap space here. + * Lazyfree page could be freed directly + */ + if (PageAnon(page) && PageSwapBacked(page)) { + if (!PageSwapCache(page)) { + if (!(sc->gfp_mask & __GFP_IO)) + goto keep_locked; + if (page_maybe_dma_pinned(page)) + goto keep_locked; + if (PageTransHuge(page)) { + /* cannot split THP, skip it */ + if (!can_split_huge_page(page, NULL)) + goto activate_locked; + /* + * Split pages without a PMD map right + * away. Chances are some or all of the + * tail pages can be freed without IO. + */ + if (!compound_mapcount(page) && + split_huge_page_to_list(page, + page_list)) + goto activate_locked; + } + if (!add_to_swap(page)) { + if (!PageTransHuge(page)) + goto activate_locked_split; + /* Fallback to swap normal pages */ + if (split_huge_page_to_list(page, + page_list)) + goto activate_locked; +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + count_vm_event(THP_SWPOUT_FALLBACK); +#endif + if (!add_to_swap(page)) + goto activate_locked_split; + } + + may_enter_fs = true; + + /* Adding to swap updated mapping */ + mapping = page_mapping(page); + } + } else if (unlikely(PageTransHuge(page))) { + /* Split file THP */ + if (split_huge_page_to_list(page, page_list)) + goto keep_locked; + } + + /* + * THP may get split above, need minus tail pages and update + * nr_pages to avoid accounting tail pages twice. + * + * The tail pages that are added into swap cache successfully + * reach here. + */ + if ((nr_pages > 1) && !PageTransHuge(page)) { + sc->nr_scanned -= (nr_pages - 1); + nr_pages = 1; + } + + /* + * The page is mapped into the page tables of one or more + * processes. Try to unmap it here. + */ + if (page_mapped(page)) { + enum ttu_flags flags = TTU_BATCH_FLUSH; + bool was_swapbacked = PageSwapBacked(page); + + if (unlikely(PageTransHuge(page))) + flags |= TTU_SPLIT_HUGE_PMD; + + if (!try_to_unmap(page, flags)) { + stat->nr_unmap_fail += nr_pages; + if (!was_swapbacked && PageSwapBacked(page)) + stat->nr_lazyfree_fail += nr_pages; + goto activate_locked; + } + } + + if (PageDirty(page)) { + /* + * Only kswapd can writeback filesystem pages + * to avoid risk of stack overflow. But avoid + * injecting inefficient single-page IO into + * flusher writeback as much as possible: only + * write pages when we've encountered many + * dirty pages, and when we've already scanned + * the rest of the LRU for clean pages and see + * the same dirty pages again (PageReclaim). + */ + if (page_is_file_lru(page) && + (!current_is_kswapd() || !PageReclaim(page) || + !test_bit(PGDAT_DIRTY, &pgdat->flags))) { + /* + * Immediately reclaim when written back. + * Similar in principal to deactivate_page() + * except we already have the page isolated + * and know it's dirty + */ + inc_node_page_state(page, NR_VMSCAN_IMMEDIATE); + SetPageReclaim(page); + + goto activate_locked; + } + + if (references == PAGEREF_RECLAIM_CLEAN) + goto keep_locked; + if (!may_enter_fs) + goto keep_locked; + if (!sc->may_writepage) + goto keep_locked; + + /* + * Page is dirty. Flush the TLB if a writable entry + * potentially exists to avoid CPU writes after IO + * starts and then write it out here. + */ + try_to_unmap_flush_dirty(); + switch (pageout(page, mapping)) { + case PAGE_KEEP: + goto keep_locked; + case PAGE_ACTIVATE: + goto activate_locked; + case PAGE_SUCCESS: + stat->nr_pageout += thp_nr_pages(page); + + if (PageWriteback(page)) + goto keep; + if (PageDirty(page)) + goto keep; + + /* + * A synchronous write - probably a ramdisk. Go + * ahead and try to reclaim the page. + */ + if (!trylock_page(page)) + goto keep; + if (PageDirty(page) || PageWriteback(page)) + goto keep_locked; + mapping = page_mapping(page); + case PAGE_CLEAN: + ; /* try to free the page below */ + } + } + + /* + * If the page has buffers, try to free the buffer mappings + * associated with this page. If we succeed we try to free + * the page as well. + * + * We do this even if the page is PageDirty(). + * try_to_release_page() does not perform I/O, but it is + * possible for a page to have PageDirty set, but it is actually + * clean (all its buffers are clean). This happens if the + * buffers were written out directly, with submit_bh(). ext3 + * will do this, as well as the blockdev mapping. + * try_to_release_page() will discover that cleanness and will + * drop the buffers and mark the page clean - it can be freed. + * + * Rarely, pages can have buffers and no ->mapping. These are + * the pages which were not successfully invalidated in + * truncate_complete_page(). We try to drop those buffers here + * and if that worked, and the page is no longer mapped into + * process address space (page_count == 1) it can be freed. + * Otherwise, leave the page on the LRU so it is swappable. + */ + if (page_has_private(page)) { + if (!try_to_release_page(page, sc->gfp_mask)) + goto activate_locked; + if (!mapping && page_count(page) == 1) { + unlock_page(page); + if (put_page_testzero(page)) + goto free_it; + else { + /* + * rare race with speculative reference. + * the speculative reference will free + * this page shortly, so we may + * increment nr_reclaimed here (and + * leave it off the LRU). + */ + nr_reclaimed++; + continue; + } + } + } + + if (PageAnon(page) && !PageSwapBacked(page)) { + /* follow __remove_mapping for reference */ + if (!page_ref_freeze(page, 1)) + goto keep_locked; + if (PageDirty(page)) { + page_ref_unfreeze(page, 1); + goto keep_locked; + } + + count_vm_event(PGLAZYFREED); + count_memcg_page_event(page, PGLAZYFREED); + } else if (!mapping || !__remove_mapping(mapping, page, true, + sc->target_mem_cgroup)) + goto keep_locked; + + unlock_page(page); +free_it: + /* + * THP may get swapped out in a whole, need account + * all base pages. + */ + nr_reclaimed += nr_pages; + + /* + * Is there need to periodically free_page_list? It would + * appear not as the counts should be low + */ + if (unlikely(PageTransHuge(page))) + destroy_compound_page(page); + else + list_add(&page->lru, &free_pages); + continue; + +activate_locked_split: + /* + * The tail pages that are failed to add into swap cache + * reach here. Fixup nr_scanned and nr_pages. + */ + if (nr_pages > 1) { + sc->nr_scanned -= (nr_pages - 1); + nr_pages = 1; + } +activate_locked: + /* Not a candidate for swapping, so reclaim swap space. */ + if (PageSwapCache(page) && (mem_cgroup_swap_full(page) || + PageMlocked(page))) + try_to_free_swap(page); + VM_BUG_ON_PAGE(PageActive(page), page); + if (!PageMlocked(page)) { + int type = page_is_file_lru(page); + SetPageActive(page); + stat->nr_activate[type] += nr_pages; + count_memcg_page_event(page, PGACTIVATE); + } +keep_locked: + unlock_page(page); +keep: + list_add(&page->lru, &ret_pages); + VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page); + } + + pgactivate = stat->nr_activate[0] + stat->nr_activate[1]; + + mem_cgroup_uncharge_list(&free_pages); + try_to_unmap_flush(); + free_unref_page_list(&free_pages); + + list_splice(&ret_pages, page_list); + count_vm_events(PGACTIVATE, pgactivate); + + return nr_reclaimed; +} + +unsigned int reclaim_clean_pages_from_list(struct zone *zone, + struct list_head *page_list) +{ + struct scan_control sc = { + .gfp_mask = GFP_KERNEL, + .priority = DEF_PRIORITY, + .may_unmap = 1, + }; + struct reclaim_stat stat; + unsigned int nr_reclaimed; + struct page *page, *next; + LIST_HEAD(clean_pages); + + list_for_each_entry_safe(page, next, page_list, lru) { + if (page_is_file_lru(page) && !PageDirty(page) && + !__PageMovable(page) && !PageUnevictable(page)) { + ClearPageActive(page); + list_move(&page->lru, &clean_pages); + } + } + + nr_reclaimed = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc, + &stat, true); + list_splice(&clean_pages, page_list); + mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, + -(long)nr_reclaimed); + /* + * Since lazyfree pages are isolated from file LRU from the beginning, + * they will rotate back to anonymous LRU in the end if it failed to + * discard so isolated count will be mismatched. + * Compensate the isolated count for both LRU lists. + */ + mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON, + stat.nr_lazyfree_fail); + mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, + -(long)stat.nr_lazyfree_fail); + return nr_reclaimed; +} + +/* + * Attempt to remove the specified page from its LRU. Only take this page + * if it is of the appropriate PageActive status. Pages which are being + * freed elsewhere are also ignored. + * + * page: page to consider + * mode: one of the LRU isolation modes defined above + * + * returns 0 on success, -ve errno on failure. + */ +int __isolate_lru_page(struct page *page, isolate_mode_t mode) +{ + int ret = -EINVAL; + + /* Only take pages on the LRU. */ + if (!PageLRU(page)) + return ret; + + /* Compaction should not handle unevictable pages but CMA can do so */ + if (PageUnevictable(page) && !(mode & ISOLATE_UNEVICTABLE)) + return ret; + + ret = -EBUSY; + + /* + * To minimise LRU disruption, the caller can indicate that it only + * wants to isolate pages it will be able to operate on without + * blocking - clean pages for the most part. + * + * ISOLATE_ASYNC_MIGRATE is used to indicate that it only wants to pages + * that it is possible to migrate without blocking + */ + if (mode & ISOLATE_ASYNC_MIGRATE) { + /* All the caller can do on PageWriteback is block */ + if (PageWriteback(page)) + return ret; + + if (PageDirty(page)) { + struct address_space *mapping; + bool migrate_dirty; + + /* + * Only pages without mappings or that have a + * ->migratepage callback are possible to migrate + * without blocking. However, we can be racing with + * truncation so it's necessary to lock the page + * to stabilise the mapping as truncation holds + * the page lock until after the page is removed + * from the page cache. + */ + if (!trylock_page(page)) + return ret; + + mapping = page_mapping(page); + migrate_dirty = !mapping || mapping->a_ops->migratepage; + unlock_page(page); + if (!migrate_dirty) + return ret; + } + } + + if ((mode & ISOLATE_UNMAPPED) && page_mapped(page)) + return ret; + + if (likely(get_page_unless_zero(page))) { + /* + * Be careful not to clear PageLRU until after we're + * sure the page is not being freed elsewhere -- the + * page release code relies on it. + */ + ClearPageLRU(page); + ret = 0; + } + + return ret; +} + + +/* + * Update LRU sizes after isolating pages. The LRU size updates must + * be complete before mem_cgroup_update_lru_size due to a sanity check. + */ +static __always_inline void update_lru_sizes(struct lruvec *lruvec, + enum lru_list lru, unsigned long *nr_zone_taken) +{ + int zid; + + for (zid = 0; zid < MAX_NR_ZONES; zid++) { + if (!nr_zone_taken[zid]) + continue; + + update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]); + } + +} + +/** + * pgdat->lru_lock is heavily contended. Some of the functions that + * shrink the lists perform better by taking out a batch of pages + * and working on them outside the LRU lock. + * + * For pagecache intensive workloads, this function is the hottest + * spot in the kernel (apart from copy_*_user functions). + * + * Appropriate locks must be held before calling this function. + * + * @nr_to_scan: The number of eligible pages to look through on the list. + * @lruvec: The LRU vector to pull pages from. + * @dst: The temp list to put pages on to. + * @nr_scanned: The number of pages that were scanned. + * @sc: The scan_control struct for this reclaim session + * @lru: LRU list id for isolating + * + * returns how many pages were moved onto *@dst. + */ +static unsigned long isolate_lru_pages(unsigned long nr_to_scan, + struct lruvec *lruvec, struct list_head *dst, + unsigned long *nr_scanned, struct scan_control *sc, + enum lru_list lru) +{ + struct list_head *src = &lruvec->lists[lru]; + unsigned long nr_taken = 0; + unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 }; + unsigned long nr_skipped[MAX_NR_ZONES] = { 0, }; + unsigned long skipped = 0; + unsigned long scan, total_scan, nr_pages; + LIST_HEAD(pages_skipped); + isolate_mode_t mode = (sc->may_unmap ? 0 : ISOLATE_UNMAPPED); + + total_scan = 0; + scan = 0; + while (scan < nr_to_scan && !list_empty(src)) { + struct page *page; + + page = lru_to_page(src); + prefetchw_prev_lru_page(page, src, flags); + + VM_BUG_ON_PAGE(!PageLRU(page), page); + + nr_pages = compound_nr(page); + total_scan += nr_pages; + + if (page_zonenum(page) > sc->reclaim_idx) { + list_move(&page->lru, &pages_skipped); + nr_skipped[page_zonenum(page)] += nr_pages; + continue; + } + + /* + * Do not count skipped pages because that makes the function + * return with no isolated pages if the LRU mostly contains + * ineligible pages. This causes the VM to not reclaim any + * pages, triggering a premature OOM. + * + * Account all tail pages of THP. This would not cause + * premature OOM since __isolate_lru_page() returns -EBUSY + * only when the page is being freed somewhere else. + */ + scan += nr_pages; + switch (__isolate_lru_page(page, mode)) { + case 0: + nr_taken += nr_pages; + nr_zone_taken[page_zonenum(page)] += nr_pages; + list_move(&page->lru, dst); + break; + + case -EBUSY: + /* else it is being freed elsewhere */ + list_move(&page->lru, src); + continue; + + default: + BUG(); + } + } + + /* + * Splice any skipped pages to the start of the LRU list. Note that + * this disrupts the LRU order when reclaiming for lower zones but + * we cannot splice to the tail. If we did then the SWAP_CLUSTER_MAX + * scanning would soon rescan the same pages to skip and put the + * system at risk of premature OOM. + */ + if (!list_empty(&pages_skipped)) { + int zid; + + list_splice(&pages_skipped, src); + for (zid = 0; zid < MAX_NR_ZONES; zid++) { + if (!nr_skipped[zid]) + continue; + + __count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]); + skipped += nr_skipped[zid]; + } + } + *nr_scanned = total_scan; + trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, + total_scan, skipped, nr_taken, mode, lru); + update_lru_sizes(lruvec, lru, nr_zone_taken); + return nr_taken; +} + +/** + * isolate_lru_page - tries to isolate a page from its LRU list + * @page: page to isolate from its LRU list + * + * Isolates a @page from an LRU list, clears PageLRU and adjusts the + * vmstat statistic corresponding to whatever LRU list the page was on. + * + * Returns 0 if the page was removed from an LRU list. + * Returns -EBUSY if the page was not on an LRU list. + * + * The returned page will have PageLRU() cleared. If it was found on + * the active list, it will have PageActive set. If it was found on + * the unevictable list, it will have the PageUnevictable bit set. That flag + * may need to be cleared by the caller before letting the page go. + * + * The vmstat statistic corresponding to the list on which the page was + * found will be decremented. + * + * Restrictions: + * + * (1) Must be called with an elevated refcount on the page. This is a + * fundamental difference from isolate_lru_pages (which is called + * without a stable reference). + * (2) the lru_lock must not be held. + * (3) interrupts must be enabled. + */ +int isolate_lru_page(struct page *page) +{ + int ret = -EBUSY; + + VM_BUG_ON_PAGE(!page_count(page), page); + WARN_RATELIMIT(PageTail(page), "trying to isolate tail page"); + + if (PageLRU(page)) { + pg_data_t *pgdat = page_pgdat(page); + struct lruvec *lruvec; + + spin_lock_irq(&pgdat->lru_lock); + lruvec = mem_cgroup_page_lruvec(page, pgdat); + if (PageLRU(page)) { + int lru = page_lru(page); + get_page(page); + ClearPageLRU(page); + del_page_from_lru_list(page, lruvec, lru); + ret = 0; + } + spin_unlock_irq(&pgdat->lru_lock); + } + return ret; +} + +/* + * A direct reclaimer may isolate SWAP_CLUSTER_MAX pages from the LRU list and + * then get rescheduled. When there are massive number of tasks doing page + * allocation, such sleeping direct reclaimers may keep piling up on each CPU, + * the LRU list will go small and be scanned faster than necessary, leading to + * unnecessary swapping, thrashing and OOM. + */ +static int too_many_isolated(struct pglist_data *pgdat, int file, + struct scan_control *sc) +{ + unsigned long inactive, isolated; + + if (current_is_kswapd()) + return 0; + + if (!writeback_throttling_sane(sc)) + return 0; + + if (file) { + inactive = node_page_state(pgdat, NR_INACTIVE_FILE); + isolated = node_page_state(pgdat, NR_ISOLATED_FILE); + } else { + inactive = node_page_state(pgdat, NR_INACTIVE_ANON); + isolated = node_page_state(pgdat, NR_ISOLATED_ANON); + } + + /* + * GFP_NOIO/GFP_NOFS callers are allowed to isolate more pages, so they + * won't get blocked by normal direct-reclaimers, forming a circular + * deadlock. + */ + if ((sc->gfp_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS)) + inactive >>= 3; + + return isolated > inactive; +} + +/* + * This moves pages from @list to corresponding LRU list. + * + * We move them the other way if the page is referenced by one or more + * processes, from rmap. + * + * If the pages are mostly unmapped, the processing is fast and it is + * appropriate to hold zone_lru_lock across the whole operation. But if + * the pages are mapped, the processing is slow (page_referenced()) so we + * should drop zone_lru_lock around each page. It's impossible to balance + * this, so instead we remove the pages from the LRU while processing them. + * It is safe to rely on PG_active against the non-LRU pages in here because + * nobody will play with that bit on a non-LRU page. + * + * The downside is that we have to touch page->_refcount against each page. + * But we had to alter page->flags anyway. + * + * Returns the number of pages moved to the given lruvec. + */ + +static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec, + struct list_head *list) +{ + struct pglist_data *pgdat = lruvec_pgdat(lruvec); + int nr_pages, nr_moved = 0; + LIST_HEAD(pages_to_free); + struct page *page; + enum lru_list lru; + + while (!list_empty(list)) { + page = lru_to_page(list); + VM_BUG_ON_PAGE(PageLRU(page), page); + if (unlikely(!page_evictable(page))) { + list_del(&page->lru); + spin_unlock_irq(&pgdat->lru_lock); + putback_lru_page(page); + spin_lock_irq(&pgdat->lru_lock); + continue; + } + lruvec = mem_cgroup_page_lruvec(page, pgdat); + + SetPageLRU(page); + lru = page_lru(page); + + nr_pages = thp_nr_pages(page); + update_lru_size(lruvec, lru, page_zonenum(page), nr_pages); + list_move(&page->lru, &lruvec->lists[lru]); + + if (put_page_testzero(page)) { + __ClearPageLRU(page); + __ClearPageActive(page); + del_page_from_lru_list(page, lruvec, lru); + + if (unlikely(PageCompound(page))) { + spin_unlock_irq(&pgdat->lru_lock); + destroy_compound_page(page); + spin_lock_irq(&pgdat->lru_lock); + } else + list_add(&page->lru, &pages_to_free); + } else { + nr_moved += nr_pages; + if (PageActive(page)) + workingset_age_nonresident(lruvec, nr_pages); + } + } + + /* + * To save our caller's stack, now use input list for pages to free. + */ + list_splice(&pages_to_free, list); + + return nr_moved; +} + +/* + * If a kernel thread (such as nfsd for loop-back mounts) services + * a backing device by writing to the page cache it sets PF_LOCAL_THROTTLE. + * In that case we should only throttle if the backing device it is + * writing to is congested. In other cases it is safe to throttle. + */ +static int current_may_throttle(void) +{ + return !(current->flags & PF_LOCAL_THROTTLE) || + current->backing_dev_info == NULL || + bdi_write_congested(current->backing_dev_info); +} + +/* + * shrink_inactive_list() is a helper for shrink_node(). It returns the number + * of reclaimed pages + */ +static noinline_for_stack unsigned long +shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, + struct scan_control *sc, enum lru_list lru) +{ + LIST_HEAD(page_list); + unsigned long nr_scanned; + unsigned int nr_reclaimed = 0; + unsigned long nr_taken; + struct reclaim_stat stat; + bool file = is_file_lru(lru); + enum vm_event_item item; + struct pglist_data *pgdat = lruvec_pgdat(lruvec); + bool stalled = false; + + while (unlikely(too_many_isolated(pgdat, file, sc))) { + if (stalled) + return 0; + + /* wait a bit for the reclaimer. */ + msleep(100); + stalled = true; + + /* We are about to die and free our memory. Return now. */ + if (fatal_signal_pending(current)) + return SWAP_CLUSTER_MAX; + } + + lru_add_drain(); + + spin_lock_irq(&pgdat->lru_lock); + + nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &page_list, + &nr_scanned, sc, lru); + + __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); + item = current_is_kswapd() ? PGSCAN_KSWAPD : PGSCAN_DIRECT; + if (!cgroup_reclaim(sc)) + __count_vm_events(item, nr_scanned); + __count_memcg_events(lruvec_memcg(lruvec), item, nr_scanned); + __count_vm_events(PGSCAN_ANON + file, nr_scanned); + + spin_unlock_irq(&pgdat->lru_lock); + + if (nr_taken == 0) + return 0; + + nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, &stat, false); + + spin_lock_irq(&pgdat->lru_lock); + + move_pages_to_lru(lruvec, &page_list); + + __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); + lru_note_cost(lruvec, file, stat.nr_pageout); + item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT; + if (!cgroup_reclaim(sc)) + __count_vm_events(item, nr_reclaimed); + __count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed); + __count_vm_events(PGSTEAL_ANON + file, nr_reclaimed); + + spin_unlock_irq(&pgdat->lru_lock); + + mem_cgroup_uncharge_list(&page_list); + free_unref_page_list(&page_list); + + /* + * If dirty pages are scanned that are not queued for IO, it + * implies that flushers are not doing their job. This can + * happen when memory pressure pushes dirty pages to the end of + * the LRU before the dirty limits are breached and the dirty + * data has expired. It can also happen when the proportion of + * dirty pages grows not through writes but through memory + * pressure reclaiming all the clean cache. And in some cases, + * the flushers simply cannot keep up with the allocation + * rate. Nudge the flusher threads in case they are asleep. + */ + if (stat.nr_unqueued_dirty == nr_taken) + wakeup_flusher_threads(WB_REASON_VMSCAN); + + sc->nr.dirty += stat.nr_dirty; + sc->nr.congested += stat.nr_congested; + sc->nr.unqueued_dirty += stat.nr_unqueued_dirty; + sc->nr.writeback += stat.nr_writeback; + sc->nr.immediate += stat.nr_immediate; + sc->nr.taken += nr_taken; + if (file) + sc->nr.file_taken += nr_taken; + + trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id, + nr_scanned, nr_reclaimed, &stat, sc->priority, file); + return nr_reclaimed; +} + +static void shrink_active_list(unsigned long nr_to_scan, + struct lruvec *lruvec, + struct scan_control *sc, + enum lru_list lru) +{ + unsigned long nr_taken; + unsigned long nr_scanned; + unsigned long vm_flags; + LIST_HEAD(l_hold); /* The pages which were snipped off */ + LIST_HEAD(l_active); + LIST_HEAD(l_inactive); + struct page *page; + unsigned nr_deactivate, nr_activate; + unsigned nr_rotated = 0; + int file = is_file_lru(lru); + struct pglist_data *pgdat = lruvec_pgdat(lruvec); + + lru_add_drain(); + + spin_lock_irq(&pgdat->lru_lock); + + nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &l_hold, + &nr_scanned, sc, lru); + + __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); + + if (!cgroup_reclaim(sc)) + __count_vm_events(PGREFILL, nr_scanned); + __count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned); + + spin_unlock_irq(&pgdat->lru_lock); + + while (!list_empty(&l_hold)) { + cond_resched(); + page = lru_to_page(&l_hold); + list_del(&page->lru); + + if (unlikely(!page_evictable(page))) { + putback_lru_page(page); + continue; + } + + if (unlikely(buffer_heads_over_limit)) { + if (page_has_private(page) && trylock_page(page)) { + if (page_has_private(page)) + try_to_release_page(page, 0); + unlock_page(page); + } + } + + if (page_referenced(page, 0, sc->target_mem_cgroup, + &vm_flags)) { + /* + * Identify referenced, file-backed active pages and + * give them one more trip around the active list. So + * that executable code get better chances to stay in + * memory under moderate memory pressure. Anon pages + * are not likely to be evicted by use-once streaming + * IO, plus JVM can create lots of anon VM_EXEC pages, + * so we ignore them here. + */ + if ((vm_flags & VM_EXEC) && page_is_file_lru(page)) { + nr_rotated += thp_nr_pages(page); + list_add(&page->lru, &l_active); + continue; + } + } + + ClearPageActive(page); /* we are de-activating */ + SetPageWorkingset(page); + list_add(&page->lru, &l_inactive); + } + + /* + * Move pages back to the lru list. + */ + spin_lock_irq(&pgdat->lru_lock); + + nr_activate = move_pages_to_lru(lruvec, &l_active); + nr_deactivate = move_pages_to_lru(lruvec, &l_inactive); + /* Keep all free pages in l_active list */ + list_splice(&l_inactive, &l_active); + + __count_vm_events(PGDEACTIVATE, nr_deactivate); + __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_deactivate); + + __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); + spin_unlock_irq(&pgdat->lru_lock); + + mem_cgroup_uncharge_list(&l_active); + free_unref_page_list(&l_active); + trace_mm_vmscan_lru_shrink_active(pgdat->node_id, nr_taken, nr_activate, + nr_deactivate, nr_rotated, sc->priority, file); +} + +unsigned long reclaim_pages(struct list_head *page_list) +{ + int nid = NUMA_NO_NODE; + unsigned int nr_reclaimed = 0; + LIST_HEAD(node_page_list); + struct reclaim_stat dummy_stat; + struct page *page; + struct scan_control sc = { + .gfp_mask = GFP_KERNEL, + .priority = DEF_PRIORITY, + .may_writepage = 1, + .may_unmap = 1, + .may_swap = 1, + }; + + while (!list_empty(page_list)) { + page = lru_to_page(page_list); + if (nid == NUMA_NO_NODE) { + nid = page_to_nid(page); + INIT_LIST_HEAD(&node_page_list); + } + + if (nid == page_to_nid(page)) { + ClearPageActive(page); + list_move(&page->lru, &node_page_list); + continue; + } + + nr_reclaimed += shrink_page_list(&node_page_list, + NODE_DATA(nid), + &sc, &dummy_stat, false); + while (!list_empty(&node_page_list)) { + page = lru_to_page(&node_page_list); + list_del(&page->lru); + putback_lru_page(page); + } + + nid = NUMA_NO_NODE; + } + + if (!list_empty(&node_page_list)) { + nr_reclaimed += shrink_page_list(&node_page_list, + NODE_DATA(nid), + &sc, &dummy_stat, false); + while (!list_empty(&node_page_list)) { + page = lru_to_page(&node_page_list); + list_del(&page->lru); + putback_lru_page(page); + } + } + + return nr_reclaimed; +} + +static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, + struct lruvec *lruvec, struct scan_control *sc) +{ + if (is_active_lru(lru)) { + if (sc->may_deactivate & (1 << is_file_lru(lru))) + shrink_active_list(nr_to_scan, lruvec, sc, lru); + else + sc->skipped_deactivate = 1; + return 0; + } + + return shrink_inactive_list(nr_to_scan, lruvec, sc, lru); +} + +/* + * The inactive anon list should be small enough that the VM never has + * to do too much work. + * + * The inactive file list should be small enough to leave most memory + * to the established workingset on the scan-resistant active list, + * but large enough to avoid thrashing the aggregate readahead window. + * + * Both inactive lists should also be large enough that each inactive + * page has a chance to be referenced again before it is reclaimed. + * + * If that fails and refaulting is observed, the inactive list grows. + * + * The inactive_ratio is the target ratio of ACTIVE to INACTIVE pages + * on this LRU, maintained by the pageout code. An inactive_ratio + * of 3 means 3:1 or 25% of the pages are kept on the inactive list. + * + * total target max + * memory ratio inactive + * ------------------------------------- + * 10MB 1 5MB + * 100MB 1 50MB + * 1GB 3 250MB + * 10GB 10 0.9GB + * 100GB 31 3GB + * 1TB 101 10GB + * 10TB 320 32GB + */ +static bool inactive_is_low(struct lruvec *lruvec, enum lru_list inactive_lru) +{ + enum lru_list active_lru = inactive_lru + LRU_ACTIVE; + unsigned long inactive, active; + unsigned long inactive_ratio; + unsigned long gb; + + inactive = lruvec_page_state(lruvec, NR_LRU_BASE + inactive_lru); + active = lruvec_page_state(lruvec, NR_LRU_BASE + active_lru); + + gb = (inactive + active) >> (30 - PAGE_SHIFT); + if (gb) + inactive_ratio = int_sqrt(10 * gb); + else + inactive_ratio = 1; + + return inactive * inactive_ratio < active; +} + +enum scan_balance { + SCAN_EQUAL, + SCAN_FRACT, + SCAN_ANON, + SCAN_FILE, +}; + +/* + * Determine how aggressively the anon and file LRU lists should be + * scanned. The relative value of each set of LRU lists is determined + * by looking at the fraction of the pages scanned we did rotate back + * onto the active list instead of evict. + * + * nr[0] = anon inactive pages to scan; nr[1] = anon active pages to scan + * nr[2] = file inactive pages to scan; nr[3] = file active pages to scan + */ +static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, + unsigned long *nr) +{ + struct mem_cgroup *memcg = lruvec_memcg(lruvec); + unsigned long anon_cost, file_cost, total_cost; + int swappiness = mem_cgroup_swappiness(memcg); + u64 fraction[ANON_AND_FILE]; + u64 denominator = 0; /* gcc */ + enum scan_balance scan_balance; + unsigned long ap, fp; + enum lru_list lru; + + /* If we have no swap space, do not bother scanning anon pages. */ + if (!sc->may_swap || mem_cgroup_get_nr_swap_pages(memcg) <= 0) { + scan_balance = SCAN_FILE; + goto out; + } + + /* + * Global reclaim will swap to prevent OOM even with no + * swappiness, but memcg users want to use this knob to + * disable swapping for individual groups completely when + * using the memory controller's swap limit feature would be + * too expensive. + */ + if (cgroup_reclaim(sc) && !swappiness) { + scan_balance = SCAN_FILE; + goto out; + } + + /* + * Do not apply any pressure balancing cleverness when the + * system is close to OOM, scan both anon and file equally + * (unless the swappiness setting disagrees with swapping). + */ + if (!sc->priority && swappiness) { + scan_balance = SCAN_EQUAL; + goto out; + } + + /* + * If the system is almost out of file pages, force-scan anon. + */ + if (sc->file_is_tiny) { + scan_balance = SCAN_ANON; + goto out; + } + + /* + * If there is enough inactive page cache, we do not reclaim + * anything from the anonymous working right now. + */ + if (sc->cache_trim_mode) { + scan_balance = SCAN_FILE; + goto out; + } + + scan_balance = SCAN_FRACT; + /* + * Calculate the pressure balance between anon and file pages. + * + * The amount of pressure we put on each LRU is inversely + * proportional to the cost of reclaiming each list, as + * determined by the share of pages that are refaulting, times + * the relative IO cost of bringing back a swapped out + * anonymous page vs reloading a filesystem page (swappiness). + * + * Although we limit that influence to ensure no list gets + * left behind completely: at least a third of the pressure is + * applied, before swappiness. + * + * With swappiness at 100, anon and file have equal IO cost. + */ + total_cost = sc->anon_cost + sc->file_cost; + anon_cost = total_cost + sc->anon_cost; + file_cost = total_cost + sc->file_cost; + total_cost = anon_cost + file_cost; + + ap = swappiness * (total_cost + 1); + ap /= anon_cost + 1; + + fp = (200 - swappiness) * (total_cost + 1); + fp /= file_cost + 1; + + fraction[0] = ap; + fraction[1] = fp; + denominator = ap + fp; +out: + for_each_evictable_lru(lru) { + int file = is_file_lru(lru); + unsigned long lruvec_size; + unsigned long low, min; + unsigned long scan; + + lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx); + mem_cgroup_protection(sc->target_mem_cgroup, memcg, + &min, &low); + + if (min || low) { + /* + * Scale a cgroup's reclaim pressure by proportioning + * its current usage to its memory.low or memory.min + * setting. + * + * This is important, as otherwise scanning aggression + * becomes extremely binary -- from nothing as we + * approach the memory protection threshold, to totally + * nominal as we exceed it. This results in requiring + * setting extremely liberal protection thresholds. It + * also means we simply get no protection at all if we + * set it too low, which is not ideal. + * + * If there is any protection in place, we reduce scan + * pressure by how much of the total memory used is + * within protection thresholds. + * + * There is one special case: in the first reclaim pass, + * we skip over all groups that are within their low + * protection. If that fails to reclaim enough pages to + * satisfy the reclaim goal, we come back and override + * the best-effort low protection. However, we still + * ideally want to honor how well-behaved groups are in + * that case instead of simply punishing them all + * equally. As such, we reclaim them based on how much + * memory they are using, reducing the scan pressure + * again by how much of the total memory used is under + * hard protection. + */ + unsigned long cgroup_size = mem_cgroup_size(memcg); + unsigned long protection; + + /* memory.low scaling, make sure we retry before OOM */ + if (!sc->memcg_low_reclaim && low > min) { + protection = low; + sc->memcg_low_skipped = 1; + } else { + protection = min; + } + + /* Avoid TOCTOU with earlier protection check */ + cgroup_size = max(cgroup_size, protection); + + scan = lruvec_size - lruvec_size * protection / + (cgroup_size + 1); + + /* + * Minimally target SWAP_CLUSTER_MAX pages to keep + * reclaim moving forwards, avoiding decrementing + * sc->priority further than desirable. + */ + scan = max(scan, SWAP_CLUSTER_MAX); + } else { + scan = lruvec_size; + } + + scan >>= sc->priority; + + /* + * If the cgroup's already been deleted, make sure to + * scrape out the remaining cache. + */ + if (!scan && !mem_cgroup_online(memcg)) + scan = min(lruvec_size, SWAP_CLUSTER_MAX); + + switch (scan_balance) { + case SCAN_EQUAL: + /* Scan lists relative to size */ + break; + case SCAN_FRACT: + /* + * Scan types proportional to swappiness and + * their relative recent reclaim efficiency. + * Make sure we don't miss the last page on + * the offlined memory cgroups because of a + * round-off error. + */ + scan = mem_cgroup_online(memcg) ? + div64_u64(scan * fraction[file], denominator) : + DIV64_U64_ROUND_UP(scan * fraction[file], + denominator); + break; + case SCAN_FILE: + case SCAN_ANON: + /* Scan one type exclusively */ + if ((scan_balance == SCAN_FILE) != file) + scan = 0; + break; + default: + /* Look ma, no brain */ + BUG(); + } + + nr[lru] = scan; + } +} + +static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) +{ + unsigned long nr[NR_LRU_LISTS]; + unsigned long targets[NR_LRU_LISTS]; + unsigned long nr_to_scan; + enum lru_list lru; + unsigned long nr_reclaimed = 0; + unsigned long nr_to_reclaim = sc->nr_to_reclaim; + bool proportional_reclaim; + struct blk_plug plug; + + get_scan_count(lruvec, sc, nr); + + /* Record the original scan target for proportional adjustments later */ + memcpy(targets, nr, sizeof(nr)); + + /* + * Global reclaiming within direct reclaim at DEF_PRIORITY is a normal + * event that can occur when there is little memory pressure e.g. + * multiple streaming readers/writers. Hence, we do not abort scanning + * when the requested number of pages are reclaimed when scanning at + * DEF_PRIORITY on the assumption that the fact we are direct + * reclaiming implies that kswapd is not keeping up and it is best to + * do a batch of work at once. For memcg reclaim one check is made to + * abort proportional reclaim if either the file or anon lru has already + * dropped to zero at the first pass. + */ + proportional_reclaim = (!cgroup_reclaim(sc) && !current_is_kswapd() && + sc->priority == DEF_PRIORITY); + + blk_start_plug(&plug); + while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || + nr[LRU_INACTIVE_FILE]) { + unsigned long nr_anon, nr_file, percentage; + unsigned long nr_scanned; + + for_each_evictable_lru(lru) { + if (nr[lru]) { + nr_to_scan = min(nr[lru], SWAP_CLUSTER_MAX); + nr[lru] -= nr_to_scan; + + nr_reclaimed += shrink_list(lru, nr_to_scan, + lruvec, sc); + } + } + + cond_resched(); + + if (nr_reclaimed < nr_to_reclaim || proportional_reclaim) + continue; + + /* + * For kswapd and memcg, reclaim at least the number of pages + * requested. Ensure that the anon and file LRUs are scanned + * proportionally what was requested by get_scan_count(). We + * stop reclaiming one LRU and reduce the amount scanning + * proportional to the original scan target. + */ + nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE]; + nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON]; + + /* + * It's just vindictive to attack the larger once the smaller + * has gone to zero. And given the way we stop scanning the + * smaller below, this makes sure that we only make one nudge + * towards proportionality once we've got nr_to_reclaim. + */ + if (!nr_file || !nr_anon) + break; + + if (nr_file > nr_anon) { + unsigned long scan_target = targets[LRU_INACTIVE_ANON] + + targets[LRU_ACTIVE_ANON] + 1; + lru = LRU_BASE; + percentage = nr_anon * 100 / scan_target; + } else { + unsigned long scan_target = targets[LRU_INACTIVE_FILE] + + targets[LRU_ACTIVE_FILE] + 1; + lru = LRU_FILE; + percentage = nr_file * 100 / scan_target; + } + + /* Stop scanning the smaller of the LRU */ + nr[lru] = 0; + nr[lru + LRU_ACTIVE] = 0; + + /* + * Recalculate the other LRU scan count based on its original + * scan target and the percentage scanning already complete + */ + lru = (lru == LRU_FILE) ? LRU_BASE : LRU_FILE; + nr_scanned = targets[lru] - nr[lru]; + nr[lru] = targets[lru] * (100 - percentage) / 100; + nr[lru] -= min(nr[lru], nr_scanned); + + lru += LRU_ACTIVE; + nr_scanned = targets[lru] - nr[lru]; + nr[lru] = targets[lru] * (100 - percentage) / 100; + nr[lru] -= min(nr[lru], nr_scanned); + } + blk_finish_plug(&plug); + sc->nr_reclaimed += nr_reclaimed; + + /* + * Even if we did not try to evict anon pages at all, we want to + * rebalance the anon lru active/inactive ratio. + */ + if (total_swap_pages && inactive_is_low(lruvec, LRU_INACTIVE_ANON)) + shrink_active_list(SWAP_CLUSTER_MAX, lruvec, + sc, LRU_ACTIVE_ANON); +} + +/* Use reclaim/compaction for costly allocs or under memory pressure */ +static bool in_reclaim_compaction(struct scan_control *sc) +{ + if (IS_ENABLED(CONFIG_COMPACTION) && sc->order && + (sc->order > PAGE_ALLOC_COSTLY_ORDER || + sc->priority < DEF_PRIORITY - 2)) + return true; + + return false; +} + +/* + * Reclaim/compaction is used for high-order allocation requests. It reclaims + * order-0 pages before compacting the zone. should_continue_reclaim() returns + * true if more pages should be reclaimed such that when the page allocator + * calls try_to_compact_pages() that it will have enough free pages to succeed. + * It will give up earlier than that if there is difficulty reclaiming pages. + */ +static inline bool should_continue_reclaim(struct pglist_data *pgdat, + unsigned long nr_reclaimed, + struct scan_control *sc) +{ + unsigned long pages_for_compaction; + unsigned long inactive_lru_pages; + int z; + + /* If not in reclaim/compaction mode, stop */ + if (!in_reclaim_compaction(sc)) + return false; + + /* + * Stop if we failed to reclaim any pages from the last SWAP_CLUSTER_MAX + * number of pages that were scanned. This will return to the caller + * with the risk reclaim/compaction and the resulting allocation attempt + * fails. In the past we have tried harder for __GFP_RETRY_MAYFAIL + * allocations through requiring that the full LRU list has been scanned + * first, by assuming that zero delta of sc->nr_scanned means full LRU + * scan, but that approximation was wrong, and there were corner cases + * where always a non-zero amount of pages were scanned. + */ + if (!nr_reclaimed) + return false; + + /* If compaction would go ahead or the allocation would succeed, stop */ + for (z = 0; z <= sc->reclaim_idx; z++) { + struct zone *zone = &pgdat->node_zones[z]; + if (!managed_zone(zone)) + continue; + + switch (compaction_suitable(zone, sc->order, 0, sc->reclaim_idx)) { + case COMPACT_SUCCESS: + case COMPACT_CONTINUE: + return false; + default: + /* check next zone */ + ; + } + } + + /* + * If we have not reclaimed enough pages for compaction and the + * inactive lists are large enough, continue reclaiming + */ + pages_for_compaction = compact_gap(sc->order); + inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE); + if (get_nr_swap_pages() > 0) + inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON); + + return inactive_lru_pages > pages_for_compaction; +} + +static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc) +{ + struct mem_cgroup *target_memcg = sc->target_mem_cgroup; + struct mem_cgroup *memcg; + + memcg = mem_cgroup_iter(target_memcg, NULL, NULL); + do { + struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); + unsigned long reclaimed; + unsigned long scanned; + + /* + * This loop can become CPU-bound when target memcgs + * aren't eligible for reclaim - either because they + * don't have any reclaimable pages, or because their + * memory is explicitly protected. Avoid soft lockups. + */ + cond_resched(); + + mem_cgroup_calculate_protection(target_memcg, memcg); + + if (mem_cgroup_below_min(memcg)) { + /* + * Hard protection. + * If there is no reclaimable memory, OOM. + */ + continue; + } else if (mem_cgroup_below_low(memcg)) { + /* + * Soft protection. + * Respect the protection only as long as + * there is an unprotected supply + * of reclaimable memory from other cgroups. + */ + if (!sc->memcg_low_reclaim) { + sc->memcg_low_skipped = 1; + continue; + } + memcg_memory_event(memcg, MEMCG_LOW); + } + + reclaimed = sc->nr_reclaimed; + scanned = sc->nr_scanned; + + shrink_lruvec(lruvec, sc); + + shrink_slab(sc->gfp_mask, pgdat->node_id, memcg, + sc->priority); + + /* Record the group's reclaim efficiency */ + vmpressure(sc->gfp_mask, memcg, false, + sc->nr_scanned - scanned, + sc->nr_reclaimed - reclaimed); + + } while ((memcg = mem_cgroup_iter(target_memcg, memcg, NULL))); +} + +static void shrink_node(pg_data_t *pgdat, struct scan_control *sc) +{ + struct reclaim_state *reclaim_state = current->reclaim_state; + unsigned long nr_reclaimed, nr_scanned; + struct lruvec *target_lruvec; + bool reclaimable = false; + unsigned long file; + + target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat); + +again: + memset(&sc->nr, 0, sizeof(sc->nr)); + + nr_reclaimed = sc->nr_reclaimed; + nr_scanned = sc->nr_scanned; + + /* + * Determine the scan balance between anon and file LRUs. + */ + spin_lock_irq(&pgdat->lru_lock); + sc->anon_cost = target_lruvec->anon_cost; + sc->file_cost = target_lruvec->file_cost; + spin_unlock_irq(&pgdat->lru_lock); + + /* + * Target desirable inactive:active list ratios for the anon + * and file LRU lists. + */ + if (!sc->force_deactivate) { + unsigned long refaults; + + refaults = lruvec_page_state(target_lruvec, + WORKINGSET_ACTIVATE_ANON); + if (refaults != target_lruvec->refaults[0] || + inactive_is_low(target_lruvec, LRU_INACTIVE_ANON)) + sc->may_deactivate |= DEACTIVATE_ANON; + else + sc->may_deactivate &= ~DEACTIVATE_ANON; + + /* + * When refaults are being observed, it means a new + * workingset is being established. Deactivate to get + * rid of any stale active pages quickly. + */ + refaults = lruvec_page_state(target_lruvec, + WORKINGSET_ACTIVATE_FILE); + if (refaults != target_lruvec->refaults[1] || + inactive_is_low(target_lruvec, LRU_INACTIVE_FILE)) + sc->may_deactivate |= DEACTIVATE_FILE; + else + sc->may_deactivate &= ~DEACTIVATE_FILE; + } else + sc->may_deactivate = DEACTIVATE_ANON | DEACTIVATE_FILE; + + /* + * If we have plenty of inactive file pages that aren't + * thrashing, try to reclaim those first before touching + * anonymous pages. + */ + file = lruvec_page_state(target_lruvec, NR_INACTIVE_FILE); + if (file >> sc->priority && !(sc->may_deactivate & DEACTIVATE_FILE)) + sc->cache_trim_mode = 1; + else + sc->cache_trim_mode = 0; + + /* + * Prevent the reclaimer from falling into the cache trap: as + * cache pages start out inactive, every cache fault will tip + * the scan balance towards the file LRU. And as the file LRU + * shrinks, so does the window for rotation from references. + * This means we have a runaway feedback loop where a tiny + * thrashing file LRU becomes infinitely more attractive than + * anon pages. Try to detect this based on file LRU size. + */ + if (!cgroup_reclaim(sc)) { + unsigned long total_high_wmark = 0; + unsigned long free, anon; + int z; + + free = sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES); + file = node_page_state(pgdat, NR_ACTIVE_FILE) + + node_page_state(pgdat, NR_INACTIVE_FILE); + + for (z = 0; z < MAX_NR_ZONES; z++) { + struct zone *zone = &pgdat->node_zones[z]; + if (!managed_zone(zone)) + continue; + + total_high_wmark += high_wmark_pages(zone); + } + + /* + * Consider anon: if that's low too, this isn't a + * runaway file reclaim problem, but rather just + * extreme pressure. Reclaim as per usual then. + */ + anon = node_page_state(pgdat, NR_INACTIVE_ANON); + + sc->file_is_tiny = + file + free <= total_high_wmark && + !(sc->may_deactivate & DEACTIVATE_ANON) && + anon >> sc->priority; + } + + shrink_node_memcgs(pgdat, sc); + + if (reclaim_state) { + sc->nr_reclaimed += reclaim_state->reclaimed_slab; + reclaim_state->reclaimed_slab = 0; + } + + /* Record the subtree's reclaim efficiency */ + vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true, + sc->nr_scanned - nr_scanned, + sc->nr_reclaimed - nr_reclaimed); + + if (sc->nr_reclaimed - nr_reclaimed) + reclaimable = true; + + if (current_is_kswapd()) { + /* + * If reclaim is isolating dirty pages under writeback, + * it implies that the long-lived page allocation rate + * is exceeding the page laundering rate. Either the + * global limits are not being effective at throttling + * processes due to the page distribution throughout + * zones or there is heavy usage of a slow backing + * device. The only option is to throttle from reclaim + * context which is not ideal as there is no guarantee + * the dirtying process is throttled in the same way + * balance_dirty_pages() manages. + * + * Once a node is flagged PGDAT_WRITEBACK, kswapd will + * count the number of pages under pages flagged for + * immediate reclaim and stall if any are encountered + * in the nr_immediate check below. + */ + if (sc->nr.writeback && sc->nr.writeback == sc->nr.taken) + set_bit(PGDAT_WRITEBACK, &pgdat->flags); + + /* Allow kswapd to start writing pages during reclaim.*/ + if (sc->nr.unqueued_dirty == sc->nr.file_taken) + set_bit(PGDAT_DIRTY, &pgdat->flags); + + /* + * If kswapd scans pages marked for immediate + * reclaim and under writeback (nr_immediate), it + * implies that pages are cycling through the LRU + * faster than they are written so also forcibly stall. + */ + if (sc->nr.immediate) + congestion_wait(BLK_RW_ASYNC, HZ/10); + } + + /* + * Tag a node/memcg as congested if all the dirty pages + * scanned were backed by a congested BDI and + * wait_iff_congested will stall. + * + * Legacy memcg will stall in page writeback so avoid forcibly + * stalling in wait_iff_congested(). + */ + if ((current_is_kswapd() || + (cgroup_reclaim(sc) && writeback_throttling_sane(sc))) && + sc->nr.dirty && sc->nr.dirty == sc->nr.congested) + set_bit(LRUVEC_CONGESTED, &target_lruvec->flags); + + /* + * Stall direct reclaim for IO completions if underlying BDIs + * and node is congested. Allow kswapd to continue until it + * starts encountering unqueued dirty pages or cycling through + * the LRU too quickly. + */ + if (!current_is_kswapd() && current_may_throttle() && + !sc->hibernation_mode && + test_bit(LRUVEC_CONGESTED, &target_lruvec->flags)) + wait_iff_congested(BLK_RW_ASYNC, HZ/10); + + if (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed, + sc)) + goto again; + + /* + * Kswapd gives up on balancing particular nodes after too + * many failures to reclaim anything from them and goes to + * sleep. On reclaim progress, reset the failure counter. A + * successful direct reclaim run will revive a dormant kswapd. + */ + if (reclaimable) + pgdat->kswapd_failures = 0; +} + +/* + * Returns true if compaction should go ahead for a costly-order request, or + * the allocation would already succeed without compaction. Return false if we + * should reclaim first. + */ +static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) +{ + unsigned long watermark; + enum compact_result suitable; + + suitable = compaction_suitable(zone, sc->order, 0, sc->reclaim_idx); + if (suitable == COMPACT_SUCCESS) + /* Allocation should succeed already. Don't reclaim. */ + return true; + if (suitable == COMPACT_SKIPPED) + /* Compaction cannot yet proceed. Do reclaim. */ + return false; + + /* + * Compaction is already possible, but it takes time to run and there + * are potentially other callers using the pages just freed. So proceed + * with reclaim to make a buffer of free pages available to give + * compaction a reasonable chance of completing and allocating the page. + * Note that we won't actually reclaim the whole buffer in one attempt + * as the target watermark in should_continue_reclaim() is lower. But if + * we are already above the high+gap watermark, don't reclaim at all. + */ + watermark = high_wmark_pages(zone) + compact_gap(sc->order); + + return zone_watermark_ok_safe(zone, 0, watermark, sc->reclaim_idx); +} + +/* + * This is the direct reclaim path, for page-allocating processes. We only + * try to reclaim pages from zones which will satisfy the caller's allocation + * request. + * + * If a zone is deemed to be full of pinned pages then just give it a light + * scan then give up on it. + */ +static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) +{ + struct zoneref *z; + struct zone *zone; + unsigned long nr_soft_reclaimed; + unsigned long nr_soft_scanned; + gfp_t orig_mask; + pg_data_t *last_pgdat = NULL; + + /* + * If the number of buffer_heads in the machine exceeds the maximum + * allowed level, force direct reclaim to scan the highmem zone as + * highmem pages could be pinning lowmem pages storing buffer_heads + */ + orig_mask = sc->gfp_mask; + if (buffer_heads_over_limit) { + sc->gfp_mask |= __GFP_HIGHMEM; + sc->reclaim_idx = gfp_zone(sc->gfp_mask); + } + + for_each_zone_zonelist_nodemask(zone, z, zonelist, + sc->reclaim_idx, sc->nodemask) { + /* + * Take care memory controller reclaiming has small influence + * to global LRU. + */ + if (!cgroup_reclaim(sc)) { + if (!cpuset_zone_allowed(zone, + GFP_KERNEL | __GFP_HARDWALL)) + continue; + + /* + * If we already have plenty of memory free for + * compaction in this zone, don't free any more. + * Even though compaction is invoked for any + * non-zero order, only frequent costly order + * reclamation is disruptive enough to become a + * noticeable problem, like transparent huge + * page allocations. + */ + if (IS_ENABLED(CONFIG_COMPACTION) && + sc->order > PAGE_ALLOC_COSTLY_ORDER && + compaction_ready(zone, sc)) { + sc->compaction_ready = true; + continue; + } + + /* + * Shrink each node in the zonelist once. If the + * zonelist is ordered by zone (not the default) then a + * node may be shrunk multiple times but in that case + * the user prefers lower zones being preserved. + */ + if (zone->zone_pgdat == last_pgdat) + continue; + + /* + * This steals pages from memory cgroups over softlimit + * and returns the number of reclaimed pages and + * scanned pages. This works for global memory pressure + * and balancing, not for a memcg's limit. + */ + nr_soft_scanned = 0; + nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone->zone_pgdat, + sc->order, sc->gfp_mask, + &nr_soft_scanned); + sc->nr_reclaimed += nr_soft_reclaimed; + sc->nr_scanned += nr_soft_scanned; + /* need some check for avoid more shrink_zone() */ + } + + /* See comment about same check for global reclaim above */ + if (zone->zone_pgdat == last_pgdat) + continue; + last_pgdat = zone->zone_pgdat; + shrink_node(zone->zone_pgdat, sc); + } + + /* + * Restore to original mask to avoid the impact on the caller if we + * promoted it to __GFP_HIGHMEM. + */ + sc->gfp_mask = orig_mask; +} + +static void snapshot_refaults(struct mem_cgroup *target_memcg, pg_data_t *pgdat) +{ + struct lruvec *target_lruvec; + unsigned long refaults; + + target_lruvec = mem_cgroup_lruvec(target_memcg, pgdat); + refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON); + target_lruvec->refaults[0] = refaults; + refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_FILE); + target_lruvec->refaults[1] = refaults; +} + +/* + * This is the main entry point to direct page reclaim. + * + * If a full scan of the inactive list fails to free enough memory then we + * are "out of memory" and something needs to be killed. + * + * If the caller is !__GFP_FS then the probability of a failure is reasonably + * high - the zone may be full of dirty or under-writeback pages, which this + * caller can't do much about. We kick the writeback threads and take explicit + * naps in the hope that some of these pages can be written. But if the + * allocating task holds filesystem locks which prevent writeout this might not + * work, and the allocation attempt will fail. + * + * returns: 0, if no pages reclaimed + * else, the number of pages reclaimed + */ +static unsigned long do_try_to_free_pages(struct zonelist *zonelist, + struct scan_control *sc) +{ + int initial_priority = sc->priority; + pg_data_t *last_pgdat; + struct zoneref *z; + struct zone *zone; +retry: + delayacct_freepages_start(); + + if (!cgroup_reclaim(sc)) + __count_zid_vm_events(ALLOCSTALL, sc->reclaim_idx, 1); + + do { + vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup, + sc->priority); + sc->nr_scanned = 0; + shrink_zones(zonelist, sc); + + if (sc->nr_reclaimed >= sc->nr_to_reclaim) + break; + + if (sc->compaction_ready) + break; + + /* + * If we're getting trouble reclaiming, start doing + * writepage even in laptop mode. + */ + if (sc->priority < DEF_PRIORITY - 2) + sc->may_writepage = 1; + } while (--sc->priority >= 0); + + last_pgdat = NULL; + for_each_zone_zonelist_nodemask(zone, z, zonelist, sc->reclaim_idx, + sc->nodemask) { + if (zone->zone_pgdat == last_pgdat) + continue; + last_pgdat = zone->zone_pgdat; + + snapshot_refaults(sc->target_mem_cgroup, zone->zone_pgdat); + + if (cgroup_reclaim(sc)) { + struct lruvec *lruvec; + + lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, + zone->zone_pgdat); + clear_bit(LRUVEC_CONGESTED, &lruvec->flags); + } + } + + delayacct_freepages_end(); + + if (sc->nr_reclaimed) + return sc->nr_reclaimed; + + /* Aborted reclaim to try compaction? don't OOM, then */ + if (sc->compaction_ready) + return 1; + + /* + * We make inactive:active ratio decisions based on the node's + * composition of memory, but a restrictive reclaim_idx or a + * memory.low cgroup setting can exempt large amounts of + * memory from reclaim. Neither of which are very common, so + * instead of doing costly eligibility calculations of the + * entire cgroup subtree up front, we assume the estimates are + * good, and retry with forcible deactivation if that fails. + */ + if (sc->skipped_deactivate) { + sc->priority = initial_priority; + sc->force_deactivate = 1; + sc->skipped_deactivate = 0; + goto retry; + } + + /* Untapped cgroup reserves? Don't OOM, retry. */ + if (sc->memcg_low_skipped) { + sc->priority = initial_priority; + sc->force_deactivate = 0; + sc->memcg_low_reclaim = 1; + sc->memcg_low_skipped = 0; + goto retry; + } + + return 0; +} + +static bool allow_direct_reclaim(pg_data_t *pgdat) +{ + struct zone *zone; + unsigned long pfmemalloc_reserve = 0; + unsigned long free_pages = 0; + int i; + bool wmark_ok; + + if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) + return true; + + for (i = 0; i <= ZONE_NORMAL; i++) { + zone = &pgdat->node_zones[i]; + if (!managed_zone(zone)) + continue; + + if (!zone_reclaimable_pages(zone)) + continue; + + pfmemalloc_reserve += min_wmark_pages(zone); + free_pages += zone_page_state(zone, NR_FREE_PAGES); + } + + /* If there are no reserves (unexpected config) then do not throttle */ + if (!pfmemalloc_reserve) + return true; + + wmark_ok = free_pages > pfmemalloc_reserve / 2; + + /* kswapd must be awake if processes are being throttled */ + if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) { + if (READ_ONCE(pgdat->kswapd_highest_zoneidx) > ZONE_NORMAL) + WRITE_ONCE(pgdat->kswapd_highest_zoneidx, ZONE_NORMAL); + + wake_up_interruptible(&pgdat->kswapd_wait); + } + + return wmark_ok; +} + +/* + * Throttle direct reclaimers if backing storage is backed by the network + * and the PFMEMALLOC reserve for the preferred node is getting dangerously + * depleted. kswapd will continue to make progress and wake the processes + * when the low watermark is reached. + * + * Returns true if a fatal signal was delivered during throttling. If this + * happens, the page allocator should not consider triggering the OOM killer. + */ +static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist, + nodemask_t *nodemask) +{ + struct zoneref *z; + struct zone *zone; + pg_data_t *pgdat = NULL; + + /* + * Kernel threads should not be throttled as they may be indirectly + * responsible for cleaning pages necessary for reclaim to make forward + * progress. kjournald for example may enter direct reclaim while + * committing a transaction where throttling it could forcing other + * processes to block on log_wait_commit(). + */ + if (current->flags & PF_KTHREAD) + goto out; + + /* + * If a fatal signal is pending, this process should not throttle. + * It should return quickly so it can exit and free its memory + */ + if (fatal_signal_pending(current)) + goto out; + + /* + * Check if the pfmemalloc reserves are ok by finding the first node + * with a usable ZONE_NORMAL or lower zone. The expectation is that + * GFP_KERNEL will be required for allocating network buffers when + * swapping over the network so ZONE_HIGHMEM is unusable. + * + * Throttling is based on the first usable node and throttled processes + * wait on a queue until kswapd makes progress and wakes them. There + * is an affinity then between processes waking up and where reclaim + * progress has been made assuming the process wakes on the same node. + * More importantly, processes running on remote nodes will not compete + * for remote pfmemalloc reserves and processes on different nodes + * should make reasonable progress. + */ + for_each_zone_zonelist_nodemask(zone, z, zonelist, + gfp_zone(gfp_mask), nodemask) { + if (zone_idx(zone) > ZONE_NORMAL) + continue; + + /* Throttle based on the first usable node */ + pgdat = zone->zone_pgdat; + if (allow_direct_reclaim(pgdat)) + goto out; + break; + } + + /* If no zone was usable by the allocation flags then do not throttle */ + if (!pgdat) + goto out; + + /* Account for the throttling */ + count_vm_event(PGSCAN_DIRECT_THROTTLE); + + /* + * If the caller cannot enter the filesystem, it's possible that it + * is due to the caller holding an FS lock or performing a journal + * transaction in the case of a filesystem like ext[3|4]. In this case, + * it is not safe to block on pfmemalloc_wait as kswapd could be + * blocked waiting on the same lock. Instead, throttle for up to a + * second before continuing. + */ + if (!(gfp_mask & __GFP_FS)) { + wait_event_interruptible_timeout(pgdat->pfmemalloc_wait, + allow_direct_reclaim(pgdat), HZ); + + goto check_pending; + } + + /* Throttle until kswapd wakes the process */ + wait_event_killable(zone->zone_pgdat->pfmemalloc_wait, + allow_direct_reclaim(pgdat)); + +check_pending: + if (fatal_signal_pending(current)) + return true; + +out: + return false; +} + +unsigned long try_to_free_pages(struct zonelist *zonelist, int order, + gfp_t gfp_mask, nodemask_t *nodemask) +{ + unsigned long nr_reclaimed; + struct scan_control sc = { + .nr_to_reclaim = SWAP_CLUSTER_MAX, + .gfp_mask = current_gfp_context(gfp_mask), + .reclaim_idx = gfp_zone(gfp_mask), + .order = order, + .nodemask = nodemask, + .priority = DEF_PRIORITY, + .may_writepage = !laptop_mode, + .may_unmap = 1, + .may_swap = 1, + }; + + /* + * scan_control uses s8 fields for order, priority, and reclaim_idx. + * Confirm they are large enough for max values. + */ + BUILD_BUG_ON(MAX_ORDER > S8_MAX); + BUILD_BUG_ON(DEF_PRIORITY > S8_MAX); + BUILD_BUG_ON(MAX_NR_ZONES > S8_MAX); + + /* + * Do not enter reclaim if fatal signal was delivered while throttled. + * 1 is returned so that the page allocator does not OOM kill at this + * point. + */ + if (throttle_direct_reclaim(sc.gfp_mask, zonelist, nodemask)) + return 1; + + set_task_reclaim_state(current, &sc.reclaim_state); + trace_mm_vmscan_direct_reclaim_begin(order, sc.gfp_mask); + + nr_reclaimed = do_try_to_free_pages(zonelist, &sc); + + trace_mm_vmscan_direct_reclaim_end(nr_reclaimed); + set_task_reclaim_state(current, NULL); + + return nr_reclaimed; +} + +#ifdef CONFIG_MEMCG + +/* Only used by soft limit reclaim. Do not reuse for anything else. */ +unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, + gfp_t gfp_mask, bool noswap, + pg_data_t *pgdat, + unsigned long *nr_scanned) +{ + struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); + struct scan_control sc = { + .nr_to_reclaim = SWAP_CLUSTER_MAX, + .target_mem_cgroup = memcg, + .may_writepage = !laptop_mode, + .may_unmap = 1, + .reclaim_idx = MAX_NR_ZONES - 1, + .may_swap = !noswap, + }; + + WARN_ON_ONCE(!current->reclaim_state); + + sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | + (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK); + + trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.order, + sc.gfp_mask); + + /* + * NOTE: Although we can get the priority field, using it + * here is not a good idea, since it limits the pages we can scan. + * if we don't reclaim here, the shrink_node from balance_pgdat + * will pick up pages from other mem cgroup's as well. We hack + * the priority and make it zero. + */ + shrink_lruvec(lruvec, &sc); + + trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed); + + *nr_scanned = sc.nr_scanned; + + return sc.nr_reclaimed; +} + +unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, + unsigned long nr_pages, + gfp_t gfp_mask, + bool may_swap) +{ + unsigned long nr_reclaimed; + unsigned int noreclaim_flag; + struct scan_control sc = { + .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), + .gfp_mask = (current_gfp_context(gfp_mask) & GFP_RECLAIM_MASK) | + (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK), + .reclaim_idx = MAX_NR_ZONES - 1, + .target_mem_cgroup = memcg, + .priority = DEF_PRIORITY, + .may_writepage = !laptop_mode, + .may_unmap = 1, + .may_swap = may_swap, + }; + /* + * Traverse the ZONELIST_FALLBACK zonelist of the current node to put + * equal pressure on all the nodes. This is based on the assumption that + * the reclaim does not bail out early. + */ + struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); + + set_task_reclaim_state(current, &sc.reclaim_state); + trace_mm_vmscan_memcg_reclaim_begin(0, sc.gfp_mask); + noreclaim_flag = memalloc_noreclaim_save(); + + nr_reclaimed = do_try_to_free_pages(zonelist, &sc); + + memalloc_noreclaim_restore(noreclaim_flag); + trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed); + set_task_reclaim_state(current, NULL); + + return nr_reclaimed; +} +#endif + +static void age_active_anon(struct pglist_data *pgdat, + struct scan_control *sc) +{ + struct mem_cgroup *memcg; + struct lruvec *lruvec; + + if (!total_swap_pages) + return; + + lruvec = mem_cgroup_lruvec(NULL, pgdat); + if (!inactive_is_low(lruvec, LRU_INACTIVE_ANON)) + return; + + memcg = mem_cgroup_iter(NULL, NULL, NULL); + do { + lruvec = mem_cgroup_lruvec(memcg, pgdat); + shrink_active_list(SWAP_CLUSTER_MAX, lruvec, + sc, LRU_ACTIVE_ANON); + memcg = mem_cgroup_iter(NULL, memcg, NULL); + } while (memcg); +} + +static bool pgdat_watermark_boosted(pg_data_t *pgdat, int highest_zoneidx) +{ + int i; + struct zone *zone; + + /* + * Check for watermark boosts top-down as the higher zones + * are more likely to be boosted. Both watermarks and boosts + * should not be checked at the same time as reclaim would + * start prematurely when there is no boosting and a lower + * zone is balanced. + */ + for (i = highest_zoneidx; i >= 0; i--) { + zone = pgdat->node_zones + i; + if (!managed_zone(zone)) + continue; + + if (zone->watermark_boost) + return true; + } + + return false; +} + +/* + * Returns true if there is an eligible zone balanced for the request order + * and highest_zoneidx + */ +static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx) +{ + int i; + unsigned long mark = -1; + struct zone *zone; + + /* + * Check watermarks bottom-up as lower zones are more likely to + * meet watermarks. + */ + for (i = 0; i <= highest_zoneidx; i++) { + zone = pgdat->node_zones + i; + + if (!managed_zone(zone)) + continue; + + mark = high_wmark_pages(zone); + if (zone_watermark_ok_safe(zone, order, mark, highest_zoneidx)) + return true; + } + + /* + * If a node has no populated zone within highest_zoneidx, it does not + * need balancing by definition. This can happen if a zone-restricted + * allocation tries to wake a remote kswapd. + */ + if (mark == -1) + return true; + + return false; +} + +/* Clear pgdat state for congested, dirty or under writeback. */ +static void clear_pgdat_congested(pg_data_t *pgdat) +{ + struct lruvec *lruvec = mem_cgroup_lruvec(NULL, pgdat); + + clear_bit(LRUVEC_CONGESTED, &lruvec->flags); + clear_bit(PGDAT_DIRTY, &pgdat->flags); + clear_bit(PGDAT_WRITEBACK, &pgdat->flags); +} + +/* + * Prepare kswapd for sleeping. This verifies that there are no processes + * waiting in throttle_direct_reclaim() and that watermarks have been met. + * + * Returns true if kswapd is ready to sleep + */ +static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, + int highest_zoneidx) +{ + /* + * The throttled processes are normally woken up in balance_pgdat() as + * soon as allow_direct_reclaim() is true. But there is a potential + * race between when kswapd checks the watermarks and a process gets + * throttled. There is also a potential race if processes get + * throttled, kswapd wakes, a large process exits thereby balancing the + * zones, which causes kswapd to exit balance_pgdat() before reaching + * the wake up checks. If kswapd is going to sleep, no process should + * be sleeping on pfmemalloc_wait, so wake them now if necessary. If + * the wake up is premature, processes will wake kswapd and get + * throttled again. The difference from wake ups in balance_pgdat() is + * that here we are under prepare_to_wait(). + */ + if (waitqueue_active(&pgdat->pfmemalloc_wait)) + wake_up_all(&pgdat->pfmemalloc_wait); + + /* Hopeless node, leave it to direct reclaim */ + if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) + return true; + + if (pgdat_balanced(pgdat, order, highest_zoneidx)) { + clear_pgdat_congested(pgdat); + return true; + } + + return false; +} + +/* + * kswapd shrinks a node of pages that are at or below the highest usable + * zone that is currently unbalanced. + * + * Returns true if kswapd scanned at least the requested number of pages to + * reclaim or if the lack of progress was due to pages under writeback. + * This is used to determine if the scanning priority needs to be raised. + */ +static bool kswapd_shrink_node(pg_data_t *pgdat, + struct scan_control *sc) +{ + struct zone *zone; + int z; + + /* Reclaim a number of pages proportional to the number of zones */ + sc->nr_to_reclaim = 0; + for (z = 0; z <= sc->reclaim_idx; z++) { + zone = pgdat->node_zones + z; + if (!managed_zone(zone)) + continue; + + sc->nr_to_reclaim += max(high_wmark_pages(zone), SWAP_CLUSTER_MAX); + } + + /* + * Historically care was taken to put equal pressure on all zones but + * now pressure is applied based on node LRU order. + */ + shrink_node(pgdat, sc); + + /* + * Fragmentation may mean that the system cannot be rebalanced for + * high-order allocations. If twice the allocation size has been + * reclaimed then recheck watermarks only at order-0 to prevent + * excessive reclaim. Assume that a process requested a high-order + * can direct reclaim/compact. + */ + if (sc->order && sc->nr_reclaimed >= compact_gap(sc->order)) + sc->order = 0; + + return sc->nr_scanned >= sc->nr_to_reclaim; +} + +/* + * For kswapd, balance_pgdat() will reclaim pages across a node from zones + * that are eligible for use by the caller until at least one zone is + * balanced. + * + * Returns the order kswapd finished reclaiming at. + * + * kswapd scans the zones in the highmem->normal->dma direction. It skips + * zones which have free_pages > high_wmark_pages(zone), but once a zone is + * found to have free_pages <= high_wmark_pages(zone), any page in that zone + * or lower is eligible for reclaim until at least one usable zone is + * balanced. + */ +static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx) +{ + int i; + unsigned long nr_soft_reclaimed; + unsigned long nr_soft_scanned; + unsigned long pflags; + unsigned long nr_boost_reclaim; + unsigned long zone_boosts[MAX_NR_ZONES] = { 0, }; + bool boosted; + struct zone *zone; + struct scan_control sc = { + .gfp_mask = GFP_KERNEL, + .order = order, + .may_unmap = 1, + }; + + set_task_reclaim_state(current, &sc.reclaim_state); + psi_memstall_enter(&pflags); + __fs_reclaim_acquire(); + + count_vm_event(PAGEOUTRUN); + + /* + * Account for the reclaim boost. Note that the zone boost is left in + * place so that parallel allocations that are near the watermark will + * stall or direct reclaim until kswapd is finished. + */ + nr_boost_reclaim = 0; + for (i = 0; i <= highest_zoneidx; i++) { + zone = pgdat->node_zones + i; + if (!managed_zone(zone)) + continue; + + nr_boost_reclaim += zone->watermark_boost; + zone_boosts[i] = zone->watermark_boost; + } + boosted = nr_boost_reclaim; + +restart: + sc.priority = DEF_PRIORITY; + do { + unsigned long nr_reclaimed = sc.nr_reclaimed; + bool raise_priority = true; + bool balanced; + bool ret; + + sc.reclaim_idx = highest_zoneidx; + + /* + * If the number of buffer_heads exceeds the maximum allowed + * then consider reclaiming from all zones. This has a dual + * purpose -- on 64-bit systems it is expected that + * buffer_heads are stripped during active rotation. On 32-bit + * systems, highmem pages can pin lowmem memory and shrinking + * buffers can relieve lowmem pressure. Reclaim may still not + * go ahead if all eligible zones for the original allocation + * request are balanced to avoid excessive reclaim from kswapd. + */ + if (buffer_heads_over_limit) { + for (i = MAX_NR_ZONES - 1; i >= 0; i--) { + zone = pgdat->node_zones + i; + if (!managed_zone(zone)) + continue; + + sc.reclaim_idx = i; + break; + } + } + + /* + * If the pgdat is imbalanced then ignore boosting and preserve + * the watermarks for a later time and restart. Note that the + * zone watermarks will be still reset at the end of balancing + * on the grounds that the normal reclaim should be enough to + * re-evaluate if boosting is required when kswapd next wakes. + */ + balanced = pgdat_balanced(pgdat, sc.order, highest_zoneidx); + if (!balanced && nr_boost_reclaim) { + nr_boost_reclaim = 0; + goto restart; + } + + /* + * If boosting is not active then only reclaim if there are no + * eligible zones. Note that sc.reclaim_idx is not used as + * buffer_heads_over_limit may have adjusted it. + */ + if (!nr_boost_reclaim && balanced) + goto out; + + /* Limit the priority of boosting to avoid reclaim writeback */ + if (nr_boost_reclaim && sc.priority == DEF_PRIORITY - 2) + raise_priority = false; + + /* + * Do not writeback or swap pages for boosted reclaim. The + * intent is to relieve pressure not issue sub-optimal IO + * from reclaim context. If no pages are reclaimed, the + * reclaim will be aborted. + */ + sc.may_writepage = !laptop_mode && !nr_boost_reclaim; + sc.may_swap = !nr_boost_reclaim; + + /* + * Do some background aging of the anon list, to give + * pages a chance to be referenced before reclaiming. All + * pages are rotated regardless of classzone as this is + * about consistent aging. + */ + age_active_anon(pgdat, &sc); + + /* + * If we're getting trouble reclaiming, start doing writepage + * even in laptop mode. + */ + if (sc.priority < DEF_PRIORITY - 2) + sc.may_writepage = 1; + + /* Call soft limit reclaim before calling shrink_node. */ + sc.nr_scanned = 0; + nr_soft_scanned = 0; + nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(pgdat, sc.order, + sc.gfp_mask, &nr_soft_scanned); + sc.nr_reclaimed += nr_soft_reclaimed; + + /* + * There should be no need to raise the scanning priority if + * enough pages are already being scanned that that high + * watermark would be met at 100% efficiency. + */ + if (kswapd_shrink_node(pgdat, &sc)) + raise_priority = false; + + /* + * If the low watermark is met there is no need for processes + * to be throttled on pfmemalloc_wait as they should not be + * able to safely make forward progress. Wake them + */ + if (waitqueue_active(&pgdat->pfmemalloc_wait) && + allow_direct_reclaim(pgdat)) + wake_up_all(&pgdat->pfmemalloc_wait); + + /* Check if kswapd should be suspending */ + __fs_reclaim_release(); + ret = try_to_freeze(); + __fs_reclaim_acquire(); + if (ret || kthread_should_stop()) + break; + + /* + * Raise priority if scanning rate is too low or there was no + * progress in reclaiming pages + */ + nr_reclaimed = sc.nr_reclaimed - nr_reclaimed; + nr_boost_reclaim -= min(nr_boost_reclaim, nr_reclaimed); + + /* + * If reclaim made no progress for a boost, stop reclaim as + * IO cannot be queued and it could be an infinite loop in + * extreme circumstances. + */ + if (nr_boost_reclaim && !nr_reclaimed) + break; + + if (raise_priority || !nr_reclaimed) + sc.priority--; + } while (sc.priority >= 1); + + if (!sc.nr_reclaimed) + pgdat->kswapd_failures++; + +out: + /* If reclaim was boosted, account for the reclaim done in this pass */ + if (boosted) { + unsigned long flags; + + for (i = 0; i <= highest_zoneidx; i++) { + if (!zone_boosts[i]) + continue; + + /* Increments are under the zone lock */ + zone = pgdat->node_zones + i; + spin_lock_irqsave(&zone->lock, flags); + zone->watermark_boost -= min(zone->watermark_boost, zone_boosts[i]); + spin_unlock_irqrestore(&zone->lock, flags); + } + + /* + * As there is now likely space, wakeup kcompact to defragment + * pageblocks. + */ + wakeup_kcompactd(pgdat, pageblock_order, highest_zoneidx); + } + + snapshot_refaults(NULL, pgdat); + __fs_reclaim_release(); + psi_memstall_leave(&pflags); + set_task_reclaim_state(current, NULL); + + /* + * Return the order kswapd stopped reclaiming at as + * prepare_kswapd_sleep() takes it into account. If another caller + * entered the allocator slow path while kswapd was awake, order will + * remain at the higher level. + */ + return sc.order; +} + +/* + * The pgdat->kswapd_highest_zoneidx is used to pass the highest zone index to + * be reclaimed by kswapd from the waker. If the value is MAX_NR_ZONES which is + * not a valid index then either kswapd runs for first time or kswapd couldn't + * sleep after previous reclaim attempt (node is still unbalanced). In that + * case return the zone index of the previous kswapd reclaim cycle. + */ +static enum zone_type kswapd_highest_zoneidx(pg_data_t *pgdat, + enum zone_type prev_highest_zoneidx) +{ + enum zone_type curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx); + + return curr_idx == MAX_NR_ZONES ? prev_highest_zoneidx : curr_idx; +} + +static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order, + unsigned int highest_zoneidx) +{ + long remaining = 0; + DEFINE_WAIT(wait); + + if (freezing(current) || kthread_should_stop()) + return; + + prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); + + /* + * Try to sleep for a short interval. Note that kcompactd will only be + * woken if it is possible to sleep for a short interval. This is + * deliberate on the assumption that if reclaim cannot keep an + * eligible zone balanced that it's also unlikely that compaction will + * succeed. + */ + if (prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) { + /* + * Compaction records what page blocks it recently failed to + * isolate pages from and skips them in the future scanning. + * When kswapd is going to sleep, it is reasonable to assume + * that pages and compaction may succeed so reset the cache. + */ + reset_isolation_suitable(pgdat); + + /* + * We have freed the memory, now we should compact it to make + * allocation of the requested order possible. + */ + wakeup_kcompactd(pgdat, alloc_order, highest_zoneidx); + + remaining = schedule_timeout(HZ/10); + + /* + * If woken prematurely then reset kswapd_highest_zoneidx and + * order. The values will either be from a wakeup request or + * the previous request that slept prematurely. + */ + if (remaining) { + WRITE_ONCE(pgdat->kswapd_highest_zoneidx, + kswapd_highest_zoneidx(pgdat, + highest_zoneidx)); + + if (READ_ONCE(pgdat->kswapd_order) < reclaim_order) + WRITE_ONCE(pgdat->kswapd_order, reclaim_order); + } + + finish_wait(&pgdat->kswapd_wait, &wait); + prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); + } + + /* + * After a short sleep, check if it was a premature sleep. If not, then + * go fully to sleep until explicitly woken up. + */ + if (!remaining && + prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) { + trace_mm_vmscan_kswapd_sleep(pgdat->node_id); + + /* + * vmstat counters are not perfectly accurate and the estimated + * value for counters such as NR_FREE_PAGES can deviate from the + * true value by nr_online_cpus * threshold. To avoid the zone + * watermarks being breached while under pressure, we reduce the + * per-cpu vmstat threshold while kswapd is awake and restore + * them before going back to sleep. + */ + set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold); + + if (!kthread_should_stop()) + schedule(); + + set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold); + } else { + if (remaining) + count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY); + else + count_vm_event(KSWAPD_HIGH_WMARK_HIT_QUICKLY); + } + finish_wait(&pgdat->kswapd_wait, &wait); +} + +/* + * The background pageout daemon, started as a kernel thread + * from the init process. + * + * This basically trickles out pages so that we have _some_ + * free memory available even if there is no other activity + * that frees anything up. This is needed for things like routing + * etc, where we otherwise might have all activity going on in + * asynchronous contexts that cannot page things out. + * + * If there are applications that are active memory-allocators + * (most normal use), this basically shouldn't matter. + */ +static int kswapd(void *p) +{ + unsigned int alloc_order, reclaim_order; + unsigned int highest_zoneidx = MAX_NR_ZONES - 1; + pg_data_t *pgdat = (pg_data_t*)p; + struct task_struct *tsk = current; + const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id); + + if (!cpumask_empty(cpumask)) + set_cpus_allowed_ptr(tsk, cpumask); + + /* + * Tell the memory management that we're a "memory allocator", + * and that if we need more memory we should get access to it + * regardless (see "__alloc_pages()"). "kswapd" should + * never get caught in the normal page freeing logic. + * + * (Kswapd normally doesn't need memory anyway, but sometimes + * you need a small amount of memory in order to be able to + * page out something else, and this flag essentially protects + * us from recursively trying to free more memory as we're + * trying to free the first piece of memory in the first place). + */ + tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD; + set_freezable(); + + WRITE_ONCE(pgdat->kswapd_order, 0); + WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); + for ( ; ; ) { + bool ret; + + alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order); + highest_zoneidx = kswapd_highest_zoneidx(pgdat, + highest_zoneidx); + +kswapd_try_sleep: + kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order, + highest_zoneidx); + + /* Read the new order and highest_zoneidx */ + alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order); + highest_zoneidx = kswapd_highest_zoneidx(pgdat, + highest_zoneidx); + WRITE_ONCE(pgdat->kswapd_order, 0); + WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); + + ret = try_to_freeze(); + if (kthread_should_stop()) + break; + + /* + * We can speed up thawing tasks if we don't call balance_pgdat + * after returning from the refrigerator + */ + if (ret) + continue; + + /* + * Reclaim begins at the requested order but if a high-order + * reclaim fails then kswapd falls back to reclaiming for + * order-0. If that happens, kswapd will consider sleeping + * for the order it finished reclaiming at (reclaim_order) + * but kcompactd is woken to compact for the original + * request (alloc_order). + */ + trace_mm_vmscan_kswapd_wake(pgdat->node_id, highest_zoneidx, + alloc_order); + reclaim_order = balance_pgdat(pgdat, alloc_order, + highest_zoneidx); + if (reclaim_order < alloc_order) + goto kswapd_try_sleep; + } + + tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD); + + return 0; +} + +/* + * A zone is low on free memory or too fragmented for high-order memory. If + * kswapd should reclaim (direct reclaim is deferred), wake it up for the zone's + * pgdat. It will wake up kcompactd after reclaiming memory. If kswapd reclaim + * has failed or is not needed, still wake up kcompactd if only compaction is + * needed. + */ +void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order, + enum zone_type highest_zoneidx) +{ + pg_data_t *pgdat; + enum zone_type curr_idx; + + if (!managed_zone(zone)) + return; + + if (!cpuset_zone_allowed(zone, gfp_flags)) + return; + + pgdat = zone->zone_pgdat; + curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx); + + if (curr_idx == MAX_NR_ZONES || curr_idx < highest_zoneidx) + WRITE_ONCE(pgdat->kswapd_highest_zoneidx, highest_zoneidx); + + if (READ_ONCE(pgdat->kswapd_order) < order) + WRITE_ONCE(pgdat->kswapd_order, order); + + if (!waitqueue_active(&pgdat->kswapd_wait)) + return; + + /* Hopeless node, leave it to direct reclaim if possible */ + if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES || + (pgdat_balanced(pgdat, order, highest_zoneidx) && + !pgdat_watermark_boosted(pgdat, highest_zoneidx))) { + /* + * There may be plenty of free memory available, but it's too + * fragmented for high-order allocations. Wake up kcompactd + * and rely on compaction_suitable() to determine if it's + * needed. If it fails, it will defer subsequent attempts to + * ratelimit its work. + */ + if (!(gfp_flags & __GFP_DIRECT_RECLAIM)) + wakeup_kcompactd(pgdat, order, highest_zoneidx); + return; + } + + trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, highest_zoneidx, order, + gfp_flags); + wake_up_interruptible(&pgdat->kswapd_wait); +} + +#ifdef CONFIG_HIBERNATION +/* + * Try to free `nr_to_reclaim' of memory, system-wide, and return the number of + * freed pages. + * + * Rather than trying to age LRUs the aim is to preserve the overall + * LRU order by reclaiming preferentially + * inactive > active > active referenced > active mapped + */ +unsigned long shrink_all_memory(unsigned long nr_to_reclaim) +{ + struct scan_control sc = { + .nr_to_reclaim = nr_to_reclaim, + .gfp_mask = GFP_HIGHUSER_MOVABLE, + .reclaim_idx = MAX_NR_ZONES - 1, + .priority = DEF_PRIORITY, + .may_writepage = 1, + .may_unmap = 1, + .may_swap = 1, + .hibernation_mode = 1, + }; + struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); + unsigned long nr_reclaimed; + unsigned int noreclaim_flag; + + fs_reclaim_acquire(sc.gfp_mask); + noreclaim_flag = memalloc_noreclaim_save(); + set_task_reclaim_state(current, &sc.reclaim_state); + + nr_reclaimed = do_try_to_free_pages(zonelist, &sc); + + set_task_reclaim_state(current, NULL); + memalloc_noreclaim_restore(noreclaim_flag); + fs_reclaim_release(sc.gfp_mask); + + return nr_reclaimed; +} +#endif /* CONFIG_HIBERNATION */ + +/* + * This kswapd start function will be called by init and node-hot-add. + * On node-hot-add, kswapd will moved to proper cpus if cpus are hot-added. + */ +int kswapd_run(int nid) +{ + pg_data_t *pgdat = NODE_DATA(nid); + int ret = 0; + + if (pgdat->kswapd) + return 0; + + pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid); + if (IS_ERR(pgdat->kswapd)) { + /* failure at boot is fatal */ + BUG_ON(system_state < SYSTEM_RUNNING); + pr_err("Failed to start kswapd on node %d\n", nid); + ret = PTR_ERR(pgdat->kswapd); + pgdat->kswapd = NULL; + } + return ret; +} + +/* + * Called by memory hotplug when all memory in a node is offlined. Caller must + * hold mem_hotplug_begin/end(). + */ +void kswapd_stop(int nid) +{ + struct task_struct *kswapd = NODE_DATA(nid)->kswapd; + + if (kswapd) { + kthread_stop(kswapd); + NODE_DATA(nid)->kswapd = NULL; + } +} + +static int __init kswapd_init(void) +{ + int nid; + + swap_setup(); + for_each_node_state(nid, N_MEMORY) + kswapd_run(nid); + return 0; +} + +module_init(kswapd_init) + +#ifdef CONFIG_NUMA +/* + * Node reclaim mode + * + * If non-zero call node_reclaim when the number of free pages falls below + * the watermarks. + */ +int node_reclaim_mode __read_mostly; + +/* + * These bit locations are exposed in the vm.zone_reclaim_mode sysctl + * ABI. New bits are OK, but existing bits can never change. + */ +#define RECLAIM_ZONE (1<<0) /* Run shrink_inactive_list on the zone */ +#define RECLAIM_WRITE (1<<1) /* Writeout pages during reclaim */ +#define RECLAIM_UNMAP (1<<2) /* Unmap pages during reclaim */ + +/* + * Priority for NODE_RECLAIM. This determines the fraction of pages + * of a node considered for each zone_reclaim. 4 scans 1/16th of + * a zone. + */ +#define NODE_RECLAIM_PRIORITY 4 + +/* + * Percentage of pages in a zone that must be unmapped for node_reclaim to + * occur. + */ +int sysctl_min_unmapped_ratio = 1; + +/* + * If the number of slab pages in a zone grows beyond this percentage then + * slab reclaim needs to occur. + */ +int sysctl_min_slab_ratio = 5; + +static inline unsigned long node_unmapped_file_pages(struct pglist_data *pgdat) +{ + unsigned long file_mapped = node_page_state(pgdat, NR_FILE_MAPPED); + unsigned long file_lru = node_page_state(pgdat, NR_INACTIVE_FILE) + + node_page_state(pgdat, NR_ACTIVE_FILE); + + /* + * It's possible for there to be more file mapped pages than + * accounted for by the pages on the file LRU lists because + * tmpfs pages accounted for as ANON can also be FILE_MAPPED + */ + return (file_lru > file_mapped) ? (file_lru - file_mapped) : 0; +} + +/* Work out how many page cache pages we can reclaim in this reclaim_mode */ +static unsigned long node_pagecache_reclaimable(struct pglist_data *pgdat) +{ + unsigned long nr_pagecache_reclaimable; + unsigned long delta = 0; + + /* + * If RECLAIM_UNMAP is set, then all file pages are considered + * potentially reclaimable. Otherwise, we have to worry about + * pages like swapcache and node_unmapped_file_pages() provides + * a better estimate + */ + if (node_reclaim_mode & RECLAIM_UNMAP) + nr_pagecache_reclaimable = node_page_state(pgdat, NR_FILE_PAGES); + else + nr_pagecache_reclaimable = node_unmapped_file_pages(pgdat); + + /* If we can't clean pages, remove dirty pages from consideration */ + if (!(node_reclaim_mode & RECLAIM_WRITE)) + delta += node_page_state(pgdat, NR_FILE_DIRTY); + + /* Watch for any possible underflows due to delta */ + if (unlikely(delta > nr_pagecache_reclaimable)) + delta = nr_pagecache_reclaimable; + + return nr_pagecache_reclaimable - delta; +} + +/* + * Try to free up some pages from this node through reclaim. + */ +static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) +{ + /* Minimum pages needed in order to stay on node */ + const unsigned long nr_pages = 1 << order; + struct task_struct *p = current; + unsigned int noreclaim_flag; + struct scan_control sc = { + .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), + .gfp_mask = current_gfp_context(gfp_mask), + .order = order, + .priority = NODE_RECLAIM_PRIORITY, + .may_writepage = !!(node_reclaim_mode & RECLAIM_WRITE), + .may_unmap = !!(node_reclaim_mode & RECLAIM_UNMAP), + .may_swap = 1, + .reclaim_idx = gfp_zone(gfp_mask), + }; + + trace_mm_vmscan_node_reclaim_begin(pgdat->node_id, order, + sc.gfp_mask); + + cond_resched(); + fs_reclaim_acquire(sc.gfp_mask); + /* + * We need to be able to allocate from the reserves for RECLAIM_UNMAP + * and we also need to be able to write out pages for RECLAIM_WRITE + * and RECLAIM_UNMAP. + */ + noreclaim_flag = memalloc_noreclaim_save(); + p->flags |= PF_SWAPWRITE; + set_task_reclaim_state(p, &sc.reclaim_state); + + if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages) { + /* + * Free memory by calling shrink node with increasing + * priorities until we have enough memory freed. + */ + do { + shrink_node(pgdat, &sc); + } while (sc.nr_reclaimed < nr_pages && --sc.priority >= 0); + } + + set_task_reclaim_state(p, NULL); + current->flags &= ~PF_SWAPWRITE; + memalloc_noreclaim_restore(noreclaim_flag); + fs_reclaim_release(sc.gfp_mask); + + trace_mm_vmscan_node_reclaim_end(sc.nr_reclaimed); + + return sc.nr_reclaimed >= nr_pages; +} + +int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) +{ + int ret; + + /* + * Node reclaim reclaims unmapped file backed pages and + * slab pages if we are over the defined limits. + * + * A small portion of unmapped file backed pages is needed for + * file I/O otherwise pages read by file I/O will be immediately + * thrown out if the node is overallocated. So we do not reclaim + * if less than a specified percentage of the node is used by + * unmapped file backed pages. + */ + if (node_pagecache_reclaimable(pgdat) <= pgdat->min_unmapped_pages && + node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) <= + pgdat->min_slab_pages) + return NODE_RECLAIM_FULL; + + /* + * Do not scan if the allocation should not be delayed. + */ + if (!gfpflags_allow_blocking(gfp_mask) || (current->flags & PF_MEMALLOC)) + return NODE_RECLAIM_NOSCAN; + + /* + * Only run node reclaim on the local node or on nodes that do not + * have associated processors. This will favor the local processor + * over remote processors and spread off node memory allocations + * as wide as possible. + */ + if (node_state(pgdat->node_id, N_CPU) && pgdat->node_id != numa_node_id()) + return NODE_RECLAIM_NOSCAN; + + if (test_and_set_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags)) + return NODE_RECLAIM_NOSCAN; + + ret = __node_reclaim(pgdat, gfp_mask, order); + clear_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags); + + if (!ret) + count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED); + + return ret; +} +#endif + +/** + * check_move_unevictable_pages - check pages for evictability and move to + * appropriate zone lru list + * @pvec: pagevec with lru pages to check + * + * Checks pages for evictability, if an evictable page is in the unevictable + * lru list, moves it to the appropriate evictable lru list. This function + * should be only used for lru pages. + */ +void check_move_unevictable_pages(struct pagevec *pvec) +{ + struct lruvec *lruvec; + struct pglist_data *pgdat = NULL; + int pgscanned = 0; + int pgrescued = 0; + int i; + + for (i = 0; i < pvec->nr; i++) { + struct page *page = pvec->pages[i]; + struct pglist_data *pagepgdat = page_pgdat(page); + int nr_pages; + + if (PageTransTail(page)) + continue; + + nr_pages = thp_nr_pages(page); + pgscanned += nr_pages; + + if (pagepgdat != pgdat) { + if (pgdat) + spin_unlock_irq(&pgdat->lru_lock); + pgdat = pagepgdat; + spin_lock_irq(&pgdat->lru_lock); + } + lruvec = mem_cgroup_page_lruvec(page, pgdat); + + if (!PageLRU(page) || !PageUnevictable(page)) + continue; + + if (page_evictable(page)) { + enum lru_list lru = page_lru_base_type(page); + + VM_BUG_ON_PAGE(PageActive(page), page); + ClearPageUnevictable(page); + del_page_from_lru_list(page, lruvec, LRU_UNEVICTABLE); + add_page_to_lru_list(page, lruvec, lru); + pgrescued += nr_pages; + } + } + + if (pgdat) { + __count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued); + __count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned); + spin_unlock_irq(&pgdat->lru_lock); + } +} +EXPORT_SYMBOL_GPL(check_move_unevictable_pages); diff --git a/mm/vmstat.c b/mm/vmstat.c new file mode 100644 index 000000000..e292e63af --- /dev/null +++ b/mm/vmstat.c @@ -0,0 +1,2182 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/mm/vmstat.c + * + * Manages VM statistics + * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds + * + * zoned VM statistics + * Copyright (C) 2006 Silicon Graphics, Inc., + * Christoph Lameter + * Copyright (C) 2008-2014 Christoph Lameter + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "internal.h" + +#define NUMA_STATS_THRESHOLD (U16_MAX - 2) + +#ifdef CONFIG_NUMA +int sysctl_vm_numa_stat = ENABLE_NUMA_STAT; + +/* zero numa counters within a zone */ +static void zero_zone_numa_counters(struct zone *zone) +{ + int item, cpu; + + for (item = 0; item < NR_VM_NUMA_STAT_ITEMS; item++) { + atomic_long_set(&zone->vm_numa_stat[item], 0); + for_each_online_cpu(cpu) + per_cpu_ptr(zone->pageset, cpu)->vm_numa_stat_diff[item] + = 0; + } +} + +/* zero numa counters of all the populated zones */ +static void zero_zones_numa_counters(void) +{ + struct zone *zone; + + for_each_populated_zone(zone) + zero_zone_numa_counters(zone); +} + +/* zero global numa counters */ +static void zero_global_numa_counters(void) +{ + int item; + + for (item = 0; item < NR_VM_NUMA_STAT_ITEMS; item++) + atomic_long_set(&vm_numa_stat[item], 0); +} + +static void invalid_numa_statistics(void) +{ + zero_zones_numa_counters(); + zero_global_numa_counters(); +} + +static DEFINE_MUTEX(vm_numa_stat_lock); + +int sysctl_vm_numa_stat_handler(struct ctl_table *table, int write, + void *buffer, size_t *length, loff_t *ppos) +{ + int ret, oldval; + + mutex_lock(&vm_numa_stat_lock); + if (write) + oldval = sysctl_vm_numa_stat; + ret = proc_dointvec_minmax(table, write, buffer, length, ppos); + if (ret || !write) + goto out; + + if (oldval == sysctl_vm_numa_stat) + goto out; + else if (sysctl_vm_numa_stat == ENABLE_NUMA_STAT) { + static_branch_enable(&vm_numa_stat_key); + pr_info("enable numa statistics\n"); + } else { + static_branch_disable(&vm_numa_stat_key); + invalid_numa_statistics(); + pr_info("disable numa statistics, and clear numa counters\n"); + } + +out: + mutex_unlock(&vm_numa_stat_lock); + return ret; +} +#endif + +#ifdef CONFIG_VM_EVENT_COUNTERS +DEFINE_PER_CPU(struct vm_event_state, vm_event_states) = {{0}}; +EXPORT_PER_CPU_SYMBOL(vm_event_states); + +static void sum_vm_events(unsigned long *ret) +{ + int cpu; + int i; + + memset(ret, 0, NR_VM_EVENT_ITEMS * sizeof(unsigned long)); + + for_each_online_cpu(cpu) { + struct vm_event_state *this = &per_cpu(vm_event_states, cpu); + + for (i = 0; i < NR_VM_EVENT_ITEMS; i++) + ret[i] += this->event[i]; + } +} + +/* + * Accumulate the vm event counters across all CPUs. + * The result is unavoidably approximate - it can change + * during and after execution of this function. +*/ +void all_vm_events(unsigned long *ret) +{ + get_online_cpus(); + sum_vm_events(ret); + put_online_cpus(); +} +EXPORT_SYMBOL_GPL(all_vm_events); + +/* + * Fold the foreign cpu events into our own. + * + * This is adding to the events on one processor + * but keeps the global counts constant. + */ +void vm_events_fold_cpu(int cpu) +{ + struct vm_event_state *fold_state = &per_cpu(vm_event_states, cpu); + int i; + + for (i = 0; i < NR_VM_EVENT_ITEMS; i++) { + count_vm_events(i, fold_state->event[i]); + fold_state->event[i] = 0; + } +} + +#endif /* CONFIG_VM_EVENT_COUNTERS */ + +/* + * Manage combined zone based / global counters + * + * vm_stat contains the global counters + */ +atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp; +atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS] __cacheline_aligned_in_smp; +atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS] __cacheline_aligned_in_smp; +EXPORT_SYMBOL(vm_zone_stat); +EXPORT_SYMBOL(vm_numa_stat); +EXPORT_SYMBOL(vm_node_stat); + +#ifdef CONFIG_SMP + +int calculate_pressure_threshold(struct zone *zone) +{ + int threshold; + int watermark_distance; + + /* + * As vmstats are not up to date, there is drift between the estimated + * and real values. For high thresholds and a high number of CPUs, it + * is possible for the min watermark to be breached while the estimated + * value looks fine. The pressure threshold is a reduced value such + * that even the maximum amount of drift will not accidentally breach + * the min watermark + */ + watermark_distance = low_wmark_pages(zone) - min_wmark_pages(zone); + threshold = max(1, (int)(watermark_distance / num_online_cpus())); + + /* + * Maximum threshold is 125 + */ + threshold = min(125, threshold); + + return threshold; +} + +int calculate_normal_threshold(struct zone *zone) +{ + int threshold; + int mem; /* memory in 128 MB units */ + + /* + * The threshold scales with the number of processors and the amount + * of memory per zone. More memory means that we can defer updates for + * longer, more processors could lead to more contention. + * fls() is used to have a cheap way of logarithmic scaling. + * + * Some sample thresholds: + * + * Threshold Processors (fls) Zonesize fls(mem+1) + * ------------------------------------------------------------------ + * 8 1 1 0.9-1 GB 4 + * 16 2 2 0.9-1 GB 4 + * 20 2 2 1-2 GB 5 + * 24 2 2 2-4 GB 6 + * 28 2 2 4-8 GB 7 + * 32 2 2 8-16 GB 8 + * 4 2 2 <128M 1 + * 30 4 3 2-4 GB 5 + * 48 4 3 8-16 GB 8 + * 32 8 4 1-2 GB 4 + * 32 8 4 0.9-1GB 4 + * 10 16 5 <128M 1 + * 40 16 5 900M 4 + * 70 64 7 2-4 GB 5 + * 84 64 7 4-8 GB 6 + * 108 512 9 4-8 GB 6 + * 125 1024 10 8-16 GB 8 + * 125 1024 10 16-32 GB 9 + */ + + mem = zone_managed_pages(zone) >> (27 - PAGE_SHIFT); + + threshold = 2 * fls(num_online_cpus()) * (1 + fls(mem)); + + /* + * Maximum threshold is 125 + */ + threshold = min(125, threshold); + + return threshold; +} + +/* + * Refresh the thresholds for each zone. + */ +void refresh_zone_stat_thresholds(void) +{ + struct pglist_data *pgdat; + struct zone *zone; + int cpu; + int threshold; + + /* Zero current pgdat thresholds */ + for_each_online_pgdat(pgdat) { + for_each_online_cpu(cpu) { + per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold = 0; + } + } + + for_each_populated_zone(zone) { + struct pglist_data *pgdat = zone->zone_pgdat; + unsigned long max_drift, tolerate_drift; + + threshold = calculate_normal_threshold(zone); + + for_each_online_cpu(cpu) { + int pgdat_threshold; + + per_cpu_ptr(zone->pageset, cpu)->stat_threshold + = threshold; + + /* Base nodestat threshold on the largest populated zone. */ + pgdat_threshold = per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold; + per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold + = max(threshold, pgdat_threshold); + } + + /* + * Only set percpu_drift_mark if there is a danger that + * NR_FREE_PAGES reports the low watermark is ok when in fact + * the min watermark could be breached by an allocation + */ + tolerate_drift = low_wmark_pages(zone) - min_wmark_pages(zone); + max_drift = num_online_cpus() * threshold; + if (max_drift > tolerate_drift) + zone->percpu_drift_mark = high_wmark_pages(zone) + + max_drift; + } +} + +void set_pgdat_percpu_threshold(pg_data_t *pgdat, + int (*calculate_pressure)(struct zone *)) +{ + struct zone *zone; + int cpu; + int threshold; + int i; + + for (i = 0; i < pgdat->nr_zones; i++) { + zone = &pgdat->node_zones[i]; + if (!zone->percpu_drift_mark) + continue; + + threshold = (*calculate_pressure)(zone); + for_each_online_cpu(cpu) + per_cpu_ptr(zone->pageset, cpu)->stat_threshold + = threshold; + } +} + +/* + * For use when we know that interrupts are disabled, + * or when we know that preemption is disabled and that + * particular counter cannot be updated from interrupt context. + */ +void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, + long delta) +{ + struct per_cpu_pageset __percpu *pcp = zone->pageset; + s8 __percpu *p = pcp->vm_stat_diff + item; + long x; + long t; + + x = delta + __this_cpu_read(*p); + + t = __this_cpu_read(pcp->stat_threshold); + + if (unlikely(abs(x) > t)) { + zone_page_state_add(x, zone, item); + x = 0; + } + __this_cpu_write(*p, x); +} +EXPORT_SYMBOL(__mod_zone_page_state); + +void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, + long delta) +{ + struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats; + s8 __percpu *p = pcp->vm_node_stat_diff + item; + long x; + long t; + + if (vmstat_item_in_bytes(item)) { + VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1)); + delta >>= PAGE_SHIFT; + } + + x = delta + __this_cpu_read(*p); + + t = __this_cpu_read(pcp->stat_threshold); + + if (unlikely(abs(x) > t)) { + node_page_state_add(x, pgdat, item); + x = 0; + } + __this_cpu_write(*p, x); +} +EXPORT_SYMBOL(__mod_node_page_state); + +/* + * Optimized increment and decrement functions. + * + * These are only for a single page and therefore can take a struct page * + * argument instead of struct zone *. This allows the inclusion of the code + * generated for page_zone(page) into the optimized functions. + * + * No overflow check is necessary and therefore the differential can be + * incremented or decremented in place which may allow the compilers to + * generate better code. + * The increment or decrement is known and therefore one boundary check can + * be omitted. + * + * NOTE: These functions are very performance sensitive. Change only + * with care. + * + * Some processors have inc/dec instructions that are atomic vs an interrupt. + * However, the code must first determine the differential location in a zone + * based on the processor number and then inc/dec the counter. There is no + * guarantee without disabling preemption that the processor will not change + * in between and therefore the atomicity vs. interrupt cannot be exploited + * in a useful way here. + */ +void __inc_zone_state(struct zone *zone, enum zone_stat_item item) +{ + struct per_cpu_pageset __percpu *pcp = zone->pageset; + s8 __percpu *p = pcp->vm_stat_diff + item; + s8 v, t; + + v = __this_cpu_inc_return(*p); + t = __this_cpu_read(pcp->stat_threshold); + if (unlikely(v > t)) { + s8 overstep = t >> 1; + + zone_page_state_add(v + overstep, zone, item); + __this_cpu_write(*p, -overstep); + } +} + +void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) +{ + struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats; + s8 __percpu *p = pcp->vm_node_stat_diff + item; + s8 v, t; + + VM_WARN_ON_ONCE(vmstat_item_in_bytes(item)); + + v = __this_cpu_inc_return(*p); + t = __this_cpu_read(pcp->stat_threshold); + if (unlikely(v > t)) { + s8 overstep = t >> 1; + + node_page_state_add(v + overstep, pgdat, item); + __this_cpu_write(*p, -overstep); + } +} + +void __inc_zone_page_state(struct page *page, enum zone_stat_item item) +{ + __inc_zone_state(page_zone(page), item); +} +EXPORT_SYMBOL(__inc_zone_page_state); + +void __inc_node_page_state(struct page *page, enum node_stat_item item) +{ + __inc_node_state(page_pgdat(page), item); +} +EXPORT_SYMBOL(__inc_node_page_state); + +void __dec_zone_state(struct zone *zone, enum zone_stat_item item) +{ + struct per_cpu_pageset __percpu *pcp = zone->pageset; + s8 __percpu *p = pcp->vm_stat_diff + item; + s8 v, t; + + v = __this_cpu_dec_return(*p); + t = __this_cpu_read(pcp->stat_threshold); + if (unlikely(v < - t)) { + s8 overstep = t >> 1; + + zone_page_state_add(v - overstep, zone, item); + __this_cpu_write(*p, overstep); + } +} + +void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item) +{ + struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats; + s8 __percpu *p = pcp->vm_node_stat_diff + item; + s8 v, t; + + VM_WARN_ON_ONCE(vmstat_item_in_bytes(item)); + + v = __this_cpu_dec_return(*p); + t = __this_cpu_read(pcp->stat_threshold); + if (unlikely(v < - t)) { + s8 overstep = t >> 1; + + node_page_state_add(v - overstep, pgdat, item); + __this_cpu_write(*p, overstep); + } +} + +void __dec_zone_page_state(struct page *page, enum zone_stat_item item) +{ + __dec_zone_state(page_zone(page), item); +} +EXPORT_SYMBOL(__dec_zone_page_state); + +void __dec_node_page_state(struct page *page, enum node_stat_item item) +{ + __dec_node_state(page_pgdat(page), item); +} +EXPORT_SYMBOL(__dec_node_page_state); + +#ifdef CONFIG_HAVE_CMPXCHG_LOCAL +/* + * If we have cmpxchg_local support then we do not need to incur the overhead + * that comes with local_irq_save/restore if we use this_cpu_cmpxchg. + * + * mod_state() modifies the zone counter state through atomic per cpu + * operations. + * + * Overstep mode specifies how overstep should handled: + * 0 No overstepping + * 1 Overstepping half of threshold + * -1 Overstepping minus half of threshold +*/ +static inline void mod_zone_state(struct zone *zone, + enum zone_stat_item item, long delta, int overstep_mode) +{ + struct per_cpu_pageset __percpu *pcp = zone->pageset; + s8 __percpu *p = pcp->vm_stat_diff + item; + long o, n, t, z; + + do { + z = 0; /* overflow to zone counters */ + + /* + * The fetching of the stat_threshold is racy. We may apply + * a counter threshold to the wrong the cpu if we get + * rescheduled while executing here. However, the next + * counter update will apply the threshold again and + * therefore bring the counter under the threshold again. + * + * Most of the time the thresholds are the same anyways + * for all cpus in a zone. + */ + t = this_cpu_read(pcp->stat_threshold); + + o = this_cpu_read(*p); + n = delta + o; + + if (abs(n) > t) { + int os = overstep_mode * (t >> 1) ; + + /* Overflow must be added to zone counters */ + z = n + os; + n = -os; + } + } while (this_cpu_cmpxchg(*p, o, n) != o); + + if (z) + zone_page_state_add(z, zone, item); +} + +void mod_zone_page_state(struct zone *zone, enum zone_stat_item item, + long delta) +{ + mod_zone_state(zone, item, delta, 0); +} +EXPORT_SYMBOL(mod_zone_page_state); + +void inc_zone_page_state(struct page *page, enum zone_stat_item item) +{ + mod_zone_state(page_zone(page), item, 1, 1); +} +EXPORT_SYMBOL(inc_zone_page_state); + +void dec_zone_page_state(struct page *page, enum zone_stat_item item) +{ + mod_zone_state(page_zone(page), item, -1, -1); +} +EXPORT_SYMBOL(dec_zone_page_state); + +static inline void mod_node_state(struct pglist_data *pgdat, + enum node_stat_item item, int delta, int overstep_mode) +{ + struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats; + s8 __percpu *p = pcp->vm_node_stat_diff + item; + long o, n, t, z; + + if (vmstat_item_in_bytes(item)) { + VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1)); + delta >>= PAGE_SHIFT; + } + + do { + z = 0; /* overflow to node counters */ + + /* + * The fetching of the stat_threshold is racy. We may apply + * a counter threshold to the wrong the cpu if we get + * rescheduled while executing here. However, the next + * counter update will apply the threshold again and + * therefore bring the counter under the threshold again. + * + * Most of the time the thresholds are the same anyways + * for all cpus in a node. + */ + t = this_cpu_read(pcp->stat_threshold); + + o = this_cpu_read(*p); + n = delta + o; + + if (abs(n) > t) { + int os = overstep_mode * (t >> 1) ; + + /* Overflow must be added to node counters */ + z = n + os; + n = -os; + } + } while (this_cpu_cmpxchg(*p, o, n) != o); + + if (z) + node_page_state_add(z, pgdat, item); +} + +void mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, + long delta) +{ + mod_node_state(pgdat, item, delta, 0); +} +EXPORT_SYMBOL(mod_node_page_state); + +void inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) +{ + mod_node_state(pgdat, item, 1, 1); +} + +void inc_node_page_state(struct page *page, enum node_stat_item item) +{ + mod_node_state(page_pgdat(page), item, 1, 1); +} +EXPORT_SYMBOL(inc_node_page_state); + +void dec_node_page_state(struct page *page, enum node_stat_item item) +{ + mod_node_state(page_pgdat(page), item, -1, -1); +} +EXPORT_SYMBOL(dec_node_page_state); +#else +/* + * Use interrupt disable to serialize counter updates + */ +void mod_zone_page_state(struct zone *zone, enum zone_stat_item item, + long delta) +{ + unsigned long flags; + + local_irq_save(flags); + __mod_zone_page_state(zone, item, delta); + local_irq_restore(flags); +} +EXPORT_SYMBOL(mod_zone_page_state); + +void inc_zone_page_state(struct page *page, enum zone_stat_item item) +{ + unsigned long flags; + struct zone *zone; + + zone = page_zone(page); + local_irq_save(flags); + __inc_zone_state(zone, item); + local_irq_restore(flags); +} +EXPORT_SYMBOL(inc_zone_page_state); + +void dec_zone_page_state(struct page *page, enum zone_stat_item item) +{ + unsigned long flags; + + local_irq_save(flags); + __dec_zone_page_state(page, item); + local_irq_restore(flags); +} +EXPORT_SYMBOL(dec_zone_page_state); + +void inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) +{ + unsigned long flags; + + local_irq_save(flags); + __inc_node_state(pgdat, item); + local_irq_restore(flags); +} +EXPORT_SYMBOL(inc_node_state); + +void mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, + long delta) +{ + unsigned long flags; + + local_irq_save(flags); + __mod_node_page_state(pgdat, item, delta); + local_irq_restore(flags); +} +EXPORT_SYMBOL(mod_node_page_state); + +void inc_node_page_state(struct page *page, enum node_stat_item item) +{ + unsigned long flags; + struct pglist_data *pgdat; + + pgdat = page_pgdat(page); + local_irq_save(flags); + __inc_node_state(pgdat, item); + local_irq_restore(flags); +} +EXPORT_SYMBOL(inc_node_page_state); + +void dec_node_page_state(struct page *page, enum node_stat_item item) +{ + unsigned long flags; + + local_irq_save(flags); + __dec_node_page_state(page, item); + local_irq_restore(flags); +} +EXPORT_SYMBOL(dec_node_page_state); +#endif + +/* + * Fold a differential into the global counters. + * Returns the number of counters updated. + */ +#ifdef CONFIG_NUMA +static int fold_diff(int *zone_diff, int *numa_diff, int *node_diff) +{ + int i; + int changes = 0; + + for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) + if (zone_diff[i]) { + atomic_long_add(zone_diff[i], &vm_zone_stat[i]); + changes++; + } + + for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) + if (numa_diff[i]) { + atomic_long_add(numa_diff[i], &vm_numa_stat[i]); + changes++; + } + + for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) + if (node_diff[i]) { + atomic_long_add(node_diff[i], &vm_node_stat[i]); + changes++; + } + return changes; +} +#else +static int fold_diff(int *zone_diff, int *node_diff) +{ + int i; + int changes = 0; + + for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) + if (zone_diff[i]) { + atomic_long_add(zone_diff[i], &vm_zone_stat[i]); + changes++; + } + + for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) + if (node_diff[i]) { + atomic_long_add(node_diff[i], &vm_node_stat[i]); + changes++; + } + return changes; +} +#endif /* CONFIG_NUMA */ + +/* + * Update the zone counters for the current cpu. + * + * Note that refresh_cpu_vm_stats strives to only access + * node local memory. The per cpu pagesets on remote zones are placed + * in the memory local to the processor using that pageset. So the + * loop over all zones will access a series of cachelines local to + * the processor. + * + * The call to zone_page_state_add updates the cachelines with the + * statistics in the remote zone struct as well as the global cachelines + * with the global counters. These could cause remote node cache line + * bouncing and will have to be only done when necessary. + * + * The function returns the number of global counters updated. + */ +static int refresh_cpu_vm_stats(bool do_pagesets) +{ + struct pglist_data *pgdat; + struct zone *zone; + int i; + int global_zone_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, }; +#ifdef CONFIG_NUMA + int global_numa_diff[NR_VM_NUMA_STAT_ITEMS] = { 0, }; +#endif + int global_node_diff[NR_VM_NODE_STAT_ITEMS] = { 0, }; + int changes = 0; + + for_each_populated_zone(zone) { + struct per_cpu_pageset __percpu *p = zone->pageset; + + for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) { + int v; + + v = this_cpu_xchg(p->vm_stat_diff[i], 0); + if (v) { + + atomic_long_add(v, &zone->vm_stat[i]); + global_zone_diff[i] += v; +#ifdef CONFIG_NUMA + /* 3 seconds idle till flush */ + __this_cpu_write(p->expire, 3); +#endif + } + } +#ifdef CONFIG_NUMA + for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) { + int v; + + v = this_cpu_xchg(p->vm_numa_stat_diff[i], 0); + if (v) { + + atomic_long_add(v, &zone->vm_numa_stat[i]); + global_numa_diff[i] += v; + __this_cpu_write(p->expire, 3); + } + } + + if (do_pagesets) { + cond_resched(); + /* + * Deal with draining the remote pageset of this + * processor + * + * Check if there are pages remaining in this pageset + * if not then there is nothing to expire. + */ + if (!__this_cpu_read(p->expire) || + !__this_cpu_read(p->pcp.count)) + continue; + + /* + * We never drain zones local to this processor. + */ + if (zone_to_nid(zone) == numa_node_id()) { + __this_cpu_write(p->expire, 0); + continue; + } + + if (__this_cpu_dec_return(p->expire)) + continue; + + if (__this_cpu_read(p->pcp.count)) { + drain_zone_pages(zone, this_cpu_ptr(&p->pcp)); + changes++; + } + } +#endif + } + + for_each_online_pgdat(pgdat) { + struct per_cpu_nodestat __percpu *p = pgdat->per_cpu_nodestats; + + for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) { + int v; + + v = this_cpu_xchg(p->vm_node_stat_diff[i], 0); + if (v) { + atomic_long_add(v, &pgdat->vm_stat[i]); + global_node_diff[i] += v; + } + } + } + +#ifdef CONFIG_NUMA + changes += fold_diff(global_zone_diff, global_numa_diff, + global_node_diff); +#else + changes += fold_diff(global_zone_diff, global_node_diff); +#endif + return changes; +} + +/* + * Fold the data for an offline cpu into the global array. + * There cannot be any access by the offline cpu and therefore + * synchronization is simplified. + */ +void cpu_vm_stats_fold(int cpu) +{ + struct pglist_data *pgdat; + struct zone *zone; + int i; + int global_zone_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, }; +#ifdef CONFIG_NUMA + int global_numa_diff[NR_VM_NUMA_STAT_ITEMS] = { 0, }; +#endif + int global_node_diff[NR_VM_NODE_STAT_ITEMS] = { 0, }; + + for_each_populated_zone(zone) { + struct per_cpu_pageset *p; + + p = per_cpu_ptr(zone->pageset, cpu); + + for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) + if (p->vm_stat_diff[i]) { + int v; + + v = p->vm_stat_diff[i]; + p->vm_stat_diff[i] = 0; + atomic_long_add(v, &zone->vm_stat[i]); + global_zone_diff[i] += v; + } + +#ifdef CONFIG_NUMA + for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) + if (p->vm_numa_stat_diff[i]) { + int v; + + v = p->vm_numa_stat_diff[i]; + p->vm_numa_stat_diff[i] = 0; + atomic_long_add(v, &zone->vm_numa_stat[i]); + global_numa_diff[i] += v; + } +#endif + } + + for_each_online_pgdat(pgdat) { + struct per_cpu_nodestat *p; + + p = per_cpu_ptr(pgdat->per_cpu_nodestats, cpu); + + for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) + if (p->vm_node_stat_diff[i]) { + int v; + + v = p->vm_node_stat_diff[i]; + p->vm_node_stat_diff[i] = 0; + atomic_long_add(v, &pgdat->vm_stat[i]); + global_node_diff[i] += v; + } + } + +#ifdef CONFIG_NUMA + fold_diff(global_zone_diff, global_numa_diff, global_node_diff); +#else + fold_diff(global_zone_diff, global_node_diff); +#endif +} + +/* + * this is only called if !populated_zone(zone), which implies no other users of + * pset->vm_stat_diff[] exsist. + */ +void drain_zonestat(struct zone *zone, struct per_cpu_pageset *pset) +{ + int i; + + for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) + if (pset->vm_stat_diff[i]) { + int v = pset->vm_stat_diff[i]; + pset->vm_stat_diff[i] = 0; + atomic_long_add(v, &zone->vm_stat[i]); + atomic_long_add(v, &vm_zone_stat[i]); + } + +#ifdef CONFIG_NUMA + for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) + if (pset->vm_numa_stat_diff[i]) { + int v = pset->vm_numa_stat_diff[i]; + + pset->vm_numa_stat_diff[i] = 0; + atomic_long_add(v, &zone->vm_numa_stat[i]); + atomic_long_add(v, &vm_numa_stat[i]); + } +#endif +} +#endif + +#ifdef CONFIG_NUMA +void __inc_numa_state(struct zone *zone, + enum numa_stat_item item) +{ + struct per_cpu_pageset __percpu *pcp = zone->pageset; + u16 __percpu *p = pcp->vm_numa_stat_diff + item; + u16 v; + + v = __this_cpu_inc_return(*p); + + if (unlikely(v > NUMA_STATS_THRESHOLD)) { + zone_numa_state_add(v, zone, item); + __this_cpu_write(*p, 0); + } +} + +/* + * Determine the per node value of a stat item. This function + * is called frequently in a NUMA machine, so try to be as + * frugal as possible. + */ +unsigned long sum_zone_node_page_state(int node, + enum zone_stat_item item) +{ + struct zone *zones = NODE_DATA(node)->node_zones; + int i; + unsigned long count = 0; + + for (i = 0; i < MAX_NR_ZONES; i++) + count += zone_page_state(zones + i, item); + + return count; +} + +/* + * Determine the per node value of a numa stat item. To avoid deviation, + * the per cpu stat number in vm_numa_stat_diff[] is also included. + */ +unsigned long sum_zone_numa_state(int node, + enum numa_stat_item item) +{ + struct zone *zones = NODE_DATA(node)->node_zones; + int i; + unsigned long count = 0; + + for (i = 0; i < MAX_NR_ZONES; i++) + count += zone_numa_state_snapshot(zones + i, item); + + return count; +} + +/* + * Determine the per node value of a stat item. + */ +unsigned long node_page_state_pages(struct pglist_data *pgdat, + enum node_stat_item item) +{ + long x = atomic_long_read(&pgdat->vm_stat[item]); +#ifdef CONFIG_SMP + if (x < 0) + x = 0; +#endif + return x; +} + +unsigned long node_page_state(struct pglist_data *pgdat, + enum node_stat_item item) +{ + VM_WARN_ON_ONCE(vmstat_item_in_bytes(item)); + + return node_page_state_pages(pgdat, item); +} +#endif + +#ifdef CONFIG_COMPACTION + +struct contig_page_info { + unsigned long free_pages; + unsigned long free_blocks_total; + unsigned long free_blocks_suitable; +}; + +/* + * Calculate the number of free pages in a zone, how many contiguous + * pages are free and how many are large enough to satisfy an allocation of + * the target size. Note that this function makes no attempt to estimate + * how many suitable free blocks there *might* be if MOVABLE pages were + * migrated. Calculating that is possible, but expensive and can be + * figured out from userspace + */ +static void fill_contig_page_info(struct zone *zone, + unsigned int suitable_order, + struct contig_page_info *info) +{ + unsigned int order; + + info->free_pages = 0; + info->free_blocks_total = 0; + info->free_blocks_suitable = 0; + + for (order = 0; order < MAX_ORDER; order++) { + unsigned long blocks; + + /* Count number of free blocks */ + blocks = zone->free_area[order].nr_free; + info->free_blocks_total += blocks; + + /* Count free base pages */ + info->free_pages += blocks << order; + + /* Count the suitable free blocks */ + if (order >= suitable_order) + info->free_blocks_suitable += blocks << + (order - suitable_order); + } +} + +/* + * A fragmentation index only makes sense if an allocation of a requested + * size would fail. If that is true, the fragmentation index indicates + * whether external fragmentation or a lack of memory was the problem. + * The value can be used to determine if page reclaim or compaction + * should be used + */ +static int __fragmentation_index(unsigned int order, struct contig_page_info *info) +{ + unsigned long requested = 1UL << order; + + if (WARN_ON_ONCE(order >= MAX_ORDER)) + return 0; + + if (!info->free_blocks_total) + return 0; + + /* Fragmentation index only makes sense when a request would fail */ + if (info->free_blocks_suitable) + return -1000; + + /* + * Index is between 0 and 1 so return within 3 decimal places + * + * 0 => allocation would fail due to lack of memory + * 1 => allocation would fail due to fragmentation + */ + return 1000 - div_u64( (1000+(div_u64(info->free_pages * 1000ULL, requested))), info->free_blocks_total); +} + +/* + * Calculates external fragmentation within a zone wrt the given order. + * It is defined as the percentage of pages found in blocks of size + * less than 1 << order. It returns values in range [0, 100]. + */ +unsigned int extfrag_for_order(struct zone *zone, unsigned int order) +{ + struct contig_page_info info; + + fill_contig_page_info(zone, order, &info); + if (info.free_pages == 0) + return 0; + + return div_u64((info.free_pages - + (info.free_blocks_suitable << order)) * 100, + info.free_pages); +} + +/* Same as __fragmentation index but allocs contig_page_info on stack */ +int fragmentation_index(struct zone *zone, unsigned int order) +{ + struct contig_page_info info; + + fill_contig_page_info(zone, order, &info); + return __fragmentation_index(order, &info); +} +#endif + +#if defined(CONFIG_PROC_FS) || defined(CONFIG_SYSFS) || \ + defined(CONFIG_NUMA) || defined(CONFIG_MEMCG) +#ifdef CONFIG_ZONE_DMA +#define TEXT_FOR_DMA(xx) xx "_dma", +#else +#define TEXT_FOR_DMA(xx) +#endif + +#ifdef CONFIG_ZONE_DMA32 +#define TEXT_FOR_DMA32(xx) xx "_dma32", +#else +#define TEXT_FOR_DMA32(xx) +#endif + +#ifdef CONFIG_HIGHMEM +#define TEXT_FOR_HIGHMEM(xx) xx "_high", +#else +#define TEXT_FOR_HIGHMEM(xx) +#endif + +#define TEXTS_FOR_ZONES(xx) TEXT_FOR_DMA(xx) TEXT_FOR_DMA32(xx) xx "_normal", \ + TEXT_FOR_HIGHMEM(xx) xx "_movable", + +const char * const vmstat_text[] = { + /* enum zone_stat_item counters */ + "nr_free_pages", + "nr_zone_inactive_anon", + "nr_zone_active_anon", + "nr_zone_inactive_file", + "nr_zone_active_file", + "nr_zone_unevictable", + "nr_zone_write_pending", + "nr_mlock", + "nr_page_table_pages", + "nr_bounce", +#if IS_ENABLED(CONFIG_ZSMALLOC) + "nr_zspages", +#endif + "nr_free_cma", + + /* enum numa_stat_item counters */ +#ifdef CONFIG_NUMA + "numa_hit", + "numa_miss", + "numa_foreign", + "numa_interleave", + "numa_local", + "numa_other", +#endif + + /* enum node_stat_item counters */ + "nr_inactive_anon", + "nr_active_anon", + "nr_inactive_file", + "nr_active_file", + "nr_unevictable", + "nr_slab_reclaimable", + "nr_slab_unreclaimable", + "nr_isolated_anon", + "nr_isolated_file", + "workingset_nodes", + "workingset_refault_anon", + "workingset_refault_file", + "workingset_activate_anon", + "workingset_activate_file", + "workingset_restore_anon", + "workingset_restore_file", + "workingset_nodereclaim", + "nr_anon_pages", + "nr_mapped", + "nr_file_pages", + "nr_dirty", + "nr_writeback", + "nr_writeback_temp", + "nr_shmem", + "nr_shmem_hugepages", + "nr_shmem_pmdmapped", + "nr_file_hugepages", + "nr_file_pmdmapped", + "nr_anon_transparent_hugepages", + "nr_vmscan_write", + "nr_vmscan_immediate_reclaim", + "nr_dirtied", + "nr_written", + "nr_kernel_misc_reclaimable", + "nr_foll_pin_acquired", + "nr_foll_pin_released", + "nr_kernel_stack", +#if IS_ENABLED(CONFIG_SHADOW_CALL_STACK) + "nr_shadow_call_stack", +#endif + + /* enum writeback_stat_item counters */ + "nr_dirty_threshold", + "nr_dirty_background_threshold", + +#if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) + /* enum vm_event_item counters */ + "pgpgin", + "pgpgout", + "pswpin", + "pswpout", + + TEXTS_FOR_ZONES("pgalloc") + TEXTS_FOR_ZONES("allocstall") + TEXTS_FOR_ZONES("pgskip") + + "pgfree", + "pgactivate", + "pgdeactivate", + "pglazyfree", + + "pgfault", + "pgmajfault", + "pglazyfreed", + + "pgrefill", + "pgreuse", + "pgsteal_kswapd", + "pgsteal_direct", + "pgscan_kswapd", + "pgscan_direct", + "pgscan_direct_throttle", + "pgscan_anon", + "pgscan_file", + "pgsteal_anon", + "pgsteal_file", + +#ifdef CONFIG_NUMA + "zone_reclaim_failed", +#endif + "pginodesteal", + "slabs_scanned", + "kswapd_inodesteal", + "kswapd_low_wmark_hit_quickly", + "kswapd_high_wmark_hit_quickly", + "pageoutrun", + + "pgrotated", + + "drop_pagecache", + "drop_slab", + "oom_kill", + +#ifdef CONFIG_NUMA_BALANCING + "numa_pte_updates", + "numa_huge_pte_updates", + "numa_hint_faults", + "numa_hint_faults_local", + "numa_pages_migrated", +#endif +#ifdef CONFIG_MIGRATION + "pgmigrate_success", + "pgmigrate_fail", + "thp_migration_success", + "thp_migration_fail", + "thp_migration_split", +#endif +#ifdef CONFIG_COMPACTION + "compact_migrate_scanned", + "compact_free_scanned", + "compact_isolated", + "compact_stall", + "compact_fail", + "compact_success", + "compact_daemon_wake", + "compact_daemon_migrate_scanned", + "compact_daemon_free_scanned", +#endif + +#ifdef CONFIG_HUGETLB_PAGE + "htlb_buddy_alloc_success", + "htlb_buddy_alloc_fail", +#endif + "unevictable_pgs_culled", + "unevictable_pgs_scanned", + "unevictable_pgs_rescued", + "unevictable_pgs_mlocked", + "unevictable_pgs_munlocked", + "unevictable_pgs_cleared", + "unevictable_pgs_stranded", + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + "thp_fault_alloc", + "thp_fault_fallback", + "thp_fault_fallback_charge", + "thp_collapse_alloc", + "thp_collapse_alloc_failed", + "thp_file_alloc", + "thp_file_fallback", + "thp_file_fallback_charge", + "thp_file_mapped", + "thp_split_page", + "thp_split_page_failed", + "thp_deferred_split_page", + "thp_split_pmd", +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD + "thp_split_pud", +#endif + "thp_zero_page_alloc", + "thp_zero_page_alloc_failed", + "thp_swpout", + "thp_swpout_fallback", +#endif +#ifdef CONFIG_MEMORY_BALLOON + "balloon_inflate", + "balloon_deflate", +#ifdef CONFIG_BALLOON_COMPACTION + "balloon_migrate", +#endif +#endif /* CONFIG_MEMORY_BALLOON */ +#ifdef CONFIG_DEBUG_TLBFLUSH + "nr_tlb_remote_flush", + "nr_tlb_remote_flush_received", + "nr_tlb_local_flush_all", + "nr_tlb_local_flush_one", +#endif /* CONFIG_DEBUG_TLBFLUSH */ + +#ifdef CONFIG_DEBUG_VM_VMACACHE + "vmacache_find_calls", + "vmacache_find_hits", +#endif +#ifdef CONFIG_SWAP + "swap_ra", + "swap_ra_hit", +#endif +#endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */ +}; +#endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA || CONFIG_MEMCG */ + +#if (defined(CONFIG_DEBUG_FS) && defined(CONFIG_COMPACTION)) || \ + defined(CONFIG_PROC_FS) +static void *frag_start(struct seq_file *m, loff_t *pos) +{ + pg_data_t *pgdat; + loff_t node = *pos; + + for (pgdat = first_online_pgdat(); + pgdat && node; + pgdat = next_online_pgdat(pgdat)) + --node; + + return pgdat; +} + +static void *frag_next(struct seq_file *m, void *arg, loff_t *pos) +{ + pg_data_t *pgdat = (pg_data_t *)arg; + + (*pos)++; + return next_online_pgdat(pgdat); +} + +static void frag_stop(struct seq_file *m, void *arg) +{ +} + +/* + * Walk zones in a node and print using a callback. + * If @assert_populated is true, only use callback for zones that are populated. + */ +static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat, + bool assert_populated, bool nolock, + void (*print)(struct seq_file *m, pg_data_t *, struct zone *)) +{ + struct zone *zone; + struct zone *node_zones = pgdat->node_zones; + unsigned long flags; + + for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) { + if (assert_populated && !populated_zone(zone)) + continue; + + if (!nolock) + spin_lock_irqsave(&zone->lock, flags); + print(m, pgdat, zone); + if (!nolock) + spin_unlock_irqrestore(&zone->lock, flags); + } +} +#endif + +#ifdef CONFIG_PROC_FS +static void frag_show_print(struct seq_file *m, pg_data_t *pgdat, + struct zone *zone) +{ + int order; + + seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name); + for (order = 0; order < MAX_ORDER; ++order) + seq_printf(m, "%6lu ", zone->free_area[order].nr_free); + seq_putc(m, '\n'); +} + +/* + * This walks the free areas for each zone. + */ +static int frag_show(struct seq_file *m, void *arg) +{ + pg_data_t *pgdat = (pg_data_t *)arg; + walk_zones_in_node(m, pgdat, true, false, frag_show_print); + return 0; +} + +static void pagetypeinfo_showfree_print(struct seq_file *m, + pg_data_t *pgdat, struct zone *zone) +{ + int order, mtype; + + for (mtype = 0; mtype < MIGRATE_TYPES; mtype++) { + seq_printf(m, "Node %4d, zone %8s, type %12s ", + pgdat->node_id, + zone->name, + migratetype_names[mtype]); + for (order = 0; order < MAX_ORDER; ++order) { + unsigned long freecount = 0; + struct free_area *area; + struct list_head *curr; + bool overflow = false; + + area = &(zone->free_area[order]); + + list_for_each(curr, &area->free_list[mtype]) { + /* + * Cap the free_list iteration because it might + * be really large and we are under a spinlock + * so a long time spent here could trigger a + * hard lockup detector. Anyway this is a + * debugging tool so knowing there is a handful + * of pages of this order should be more than + * sufficient. + */ + if (++freecount >= 100000) { + overflow = true; + break; + } + } + seq_printf(m, "%s%6lu ", overflow ? ">" : "", freecount); + spin_unlock_irq(&zone->lock); + cond_resched(); + spin_lock_irq(&zone->lock); + } + seq_putc(m, '\n'); + } +} + +/* Print out the free pages at each order for each migatetype */ +static int pagetypeinfo_showfree(struct seq_file *m, void *arg) +{ + int order; + pg_data_t *pgdat = (pg_data_t *)arg; + + /* Print header */ + seq_printf(m, "%-43s ", "Free pages count per migrate type at order"); + for (order = 0; order < MAX_ORDER; ++order) + seq_printf(m, "%6d ", order); + seq_putc(m, '\n'); + + walk_zones_in_node(m, pgdat, true, false, pagetypeinfo_showfree_print); + + return 0; +} + +static void pagetypeinfo_showblockcount_print(struct seq_file *m, + pg_data_t *pgdat, struct zone *zone) +{ + int mtype; + unsigned long pfn; + unsigned long start_pfn = zone->zone_start_pfn; + unsigned long end_pfn = zone_end_pfn(zone); + unsigned long count[MIGRATE_TYPES] = { 0, }; + + for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) { + struct page *page; + + page = pfn_to_online_page(pfn); + if (!page) + continue; + + if (page_zone(page) != zone) + continue; + + mtype = get_pageblock_migratetype(page); + + if (mtype < MIGRATE_TYPES) + count[mtype]++; + } + + /* Print counts */ + seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name); + for (mtype = 0; mtype < MIGRATE_TYPES; mtype++) + seq_printf(m, "%12lu ", count[mtype]); + seq_putc(m, '\n'); +} + +/* Print out the number of pageblocks for each migratetype */ +static int pagetypeinfo_showblockcount(struct seq_file *m, void *arg) +{ + int mtype; + pg_data_t *pgdat = (pg_data_t *)arg; + + seq_printf(m, "\n%-23s", "Number of blocks type "); + for (mtype = 0; mtype < MIGRATE_TYPES; mtype++) + seq_printf(m, "%12s ", migratetype_names[mtype]); + seq_putc(m, '\n'); + walk_zones_in_node(m, pgdat, true, false, + pagetypeinfo_showblockcount_print); + + return 0; +} + +/* + * Print out the number of pageblocks for each migratetype that contain pages + * of other types. This gives an indication of how well fallbacks are being + * contained by rmqueue_fallback(). It requires information from PAGE_OWNER + * to determine what is going on + */ +static void pagetypeinfo_showmixedcount(struct seq_file *m, pg_data_t *pgdat) +{ +#ifdef CONFIG_PAGE_OWNER + int mtype; + + if (!static_branch_unlikely(&page_owner_inited)) + return; + + drain_all_pages(NULL); + + seq_printf(m, "\n%-23s", "Number of mixed blocks "); + for (mtype = 0; mtype < MIGRATE_TYPES; mtype++) + seq_printf(m, "%12s ", migratetype_names[mtype]); + seq_putc(m, '\n'); + + walk_zones_in_node(m, pgdat, true, true, + pagetypeinfo_showmixedcount_print); +#endif /* CONFIG_PAGE_OWNER */ +} + +/* + * This prints out statistics in relation to grouping pages by mobility. + * It is expensive to collect so do not constantly read the file. + */ +static int pagetypeinfo_show(struct seq_file *m, void *arg) +{ + pg_data_t *pgdat = (pg_data_t *)arg; + + /* check memoryless node */ + if (!node_state(pgdat->node_id, N_MEMORY)) + return 0; + + seq_printf(m, "Page block order: %d\n", pageblock_order); + seq_printf(m, "Pages per block: %lu\n", pageblock_nr_pages); + seq_putc(m, '\n'); + pagetypeinfo_showfree(m, pgdat); + pagetypeinfo_showblockcount(m, pgdat); + pagetypeinfo_showmixedcount(m, pgdat); + + return 0; +} + +static const struct seq_operations fragmentation_op = { + .start = frag_start, + .next = frag_next, + .stop = frag_stop, + .show = frag_show, +}; + +static const struct seq_operations pagetypeinfo_op = { + .start = frag_start, + .next = frag_next, + .stop = frag_stop, + .show = pagetypeinfo_show, +}; + +static bool is_zone_first_populated(pg_data_t *pgdat, struct zone *zone) +{ + int zid; + + for (zid = 0; zid < MAX_NR_ZONES; zid++) { + struct zone *compare = &pgdat->node_zones[zid]; + + if (populated_zone(compare)) + return zone == compare; + } + + return false; +} + +static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, + struct zone *zone) +{ + int i; + seq_printf(m, "Node %d, zone %8s", pgdat->node_id, zone->name); + if (is_zone_first_populated(pgdat, zone)) { + seq_printf(m, "\n per-node stats"); + for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) { + seq_printf(m, "\n %-12s %lu", node_stat_name(i), + node_page_state_pages(pgdat, i)); + } + } + seq_printf(m, + "\n pages free %lu" + "\n min %lu" + "\n low %lu" + "\n high %lu" + "\n spanned %lu" + "\n present %lu" + "\n managed %lu", + zone_page_state(zone, NR_FREE_PAGES), + min_wmark_pages(zone), + low_wmark_pages(zone), + high_wmark_pages(zone), + zone->spanned_pages, + zone->present_pages, + zone_managed_pages(zone)); + + seq_printf(m, + "\n protection: (%ld", + zone->lowmem_reserve[0]); + for (i = 1; i < ARRAY_SIZE(zone->lowmem_reserve); i++) + seq_printf(m, ", %ld", zone->lowmem_reserve[i]); + seq_putc(m, ')'); + + /* If unpopulated, no other information is useful */ + if (!populated_zone(zone)) { + seq_putc(m, '\n'); + return; + } + + for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) + seq_printf(m, "\n %-12s %lu", zone_stat_name(i), + zone_page_state(zone, i)); + +#ifdef CONFIG_NUMA + for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) + seq_printf(m, "\n %-12s %lu", numa_stat_name(i), + zone_numa_state_snapshot(zone, i)); +#endif + + seq_printf(m, "\n pagesets"); + for_each_online_cpu(i) { + struct per_cpu_pageset *pageset; + + pageset = per_cpu_ptr(zone->pageset, i); + seq_printf(m, + "\n cpu: %i" + "\n count: %i" + "\n high: %i" + "\n batch: %i", + i, + pageset->pcp.count, + pageset->pcp.high, + pageset->pcp.batch); +#ifdef CONFIG_SMP + seq_printf(m, "\n vm stats threshold: %d", + pageset->stat_threshold); +#endif + } + seq_printf(m, + "\n node_unreclaimable: %u" + "\n start_pfn: %lu", + pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES, + zone->zone_start_pfn); + seq_putc(m, '\n'); +} + +/* + * Output information about zones in @pgdat. All zones are printed regardless + * of whether they are populated or not: lowmem_reserve_ratio operates on the + * set of all zones and userspace would not be aware of such zones if they are + * suppressed here (zoneinfo displays the effect of lowmem_reserve_ratio). + */ +static int zoneinfo_show(struct seq_file *m, void *arg) +{ + pg_data_t *pgdat = (pg_data_t *)arg; + walk_zones_in_node(m, pgdat, false, false, zoneinfo_show_print); + return 0; +} + +static const struct seq_operations zoneinfo_op = { + .start = frag_start, /* iterate over all zones. The same as in + * fragmentation. */ + .next = frag_next, + .stop = frag_stop, + .show = zoneinfo_show, +}; + +#define NR_VMSTAT_ITEMS (NR_VM_ZONE_STAT_ITEMS + \ + NR_VM_NUMA_STAT_ITEMS + \ + NR_VM_NODE_STAT_ITEMS + \ + NR_VM_WRITEBACK_STAT_ITEMS + \ + (IS_ENABLED(CONFIG_VM_EVENT_COUNTERS) ? \ + NR_VM_EVENT_ITEMS : 0)) + +static void *vmstat_start(struct seq_file *m, loff_t *pos) +{ + unsigned long *v; + int i; + + if (*pos >= NR_VMSTAT_ITEMS) + return NULL; + + BUILD_BUG_ON(ARRAY_SIZE(vmstat_text) < NR_VMSTAT_ITEMS); + v = kmalloc_array(NR_VMSTAT_ITEMS, sizeof(unsigned long), GFP_KERNEL); + m->private = v; + if (!v) + return ERR_PTR(-ENOMEM); + for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) + v[i] = global_zone_page_state(i); + v += NR_VM_ZONE_STAT_ITEMS; + +#ifdef CONFIG_NUMA + for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) + v[i] = global_numa_state(i); + v += NR_VM_NUMA_STAT_ITEMS; +#endif + + for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) + v[i] = global_node_page_state_pages(i); + v += NR_VM_NODE_STAT_ITEMS; + + global_dirty_limits(v + NR_DIRTY_BG_THRESHOLD, + v + NR_DIRTY_THRESHOLD); + v += NR_VM_WRITEBACK_STAT_ITEMS; + +#ifdef CONFIG_VM_EVENT_COUNTERS + all_vm_events(v); + v[PGPGIN] /= 2; /* sectors -> kbytes */ + v[PGPGOUT] /= 2; +#endif + return (unsigned long *)m->private + *pos; +} + +static void *vmstat_next(struct seq_file *m, void *arg, loff_t *pos) +{ + (*pos)++; + if (*pos >= NR_VMSTAT_ITEMS) + return NULL; + return (unsigned long *)m->private + *pos; +} + +static int vmstat_show(struct seq_file *m, void *arg) +{ + unsigned long *l = arg; + unsigned long off = l - (unsigned long *)m->private; + + seq_puts(m, vmstat_text[off]); + seq_put_decimal_ull(m, " ", *l); + seq_putc(m, '\n'); + + if (off == NR_VMSTAT_ITEMS - 1) { + /* + * We've come to the end - add any deprecated counters to avoid + * breaking userspace which might depend on them being present. + */ + seq_puts(m, "nr_unstable 0\n"); + } + return 0; +} + +static void vmstat_stop(struct seq_file *m, void *arg) +{ + kfree(m->private); + m->private = NULL; +} + +static const struct seq_operations vmstat_op = { + .start = vmstat_start, + .next = vmstat_next, + .stop = vmstat_stop, + .show = vmstat_show, +}; +#endif /* CONFIG_PROC_FS */ + +#ifdef CONFIG_SMP +static DEFINE_PER_CPU(struct delayed_work, vmstat_work); +int sysctl_stat_interval __read_mostly = HZ; + +#ifdef CONFIG_PROC_FS +static void refresh_vm_stats(struct work_struct *work) +{ + refresh_cpu_vm_stats(true); +} + +int vmstat_refresh(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + long val; + int err; + int i; + + /* + * The regular update, every sysctl_stat_interval, may come later + * than expected: leaving a significant amount in per_cpu buckets. + * This is particularly misleading when checking a quantity of HUGE + * pages, immediately after running a test. /proc/sys/vm/stat_refresh, + * which can equally be echo'ed to or cat'ted from (by root), + * can be used to update the stats just before reading them. + * + * Oh, and since global_zone_page_state() etc. are so careful to hide + * transiently negative values, report an error here if any of + * the stats is negative, so we know to go looking for imbalance. + */ + err = schedule_on_each_cpu(refresh_vm_stats); + if (err) + return err; + for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) { + val = atomic_long_read(&vm_zone_stat[i]); + if (val < 0) { + pr_warn("%s: %s %ld\n", + __func__, zone_stat_name(i), val); + err = -EINVAL; + } + } +#ifdef CONFIG_NUMA + for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) { + val = atomic_long_read(&vm_numa_stat[i]); + if (val < 0) { + pr_warn("%s: %s %ld\n", + __func__, numa_stat_name(i), val); + err = -EINVAL; + } + } +#endif + if (err) + return err; + if (write) + *ppos += *lenp; + else + *lenp = 0; + return 0; +} +#endif /* CONFIG_PROC_FS */ + +static void vmstat_update(struct work_struct *w) +{ + if (refresh_cpu_vm_stats(true)) { + /* + * Counters were updated so we expect more updates + * to occur in the future. Keep on running the + * update worker thread. + */ + queue_delayed_work_on(smp_processor_id(), mm_percpu_wq, + this_cpu_ptr(&vmstat_work), + round_jiffies_relative(sysctl_stat_interval)); + } +} + +/* + * Switch off vmstat processing and then fold all the remaining differentials + * until the diffs stay at zero. The function is used by NOHZ and can only be + * invoked when tick processing is not active. + */ +/* + * Check if the diffs for a certain cpu indicate that + * an update is needed. + */ +static bool need_update(int cpu) +{ + struct zone *zone; + + for_each_populated_zone(zone) { + struct per_cpu_pageset *p = per_cpu_ptr(zone->pageset, cpu); + + BUILD_BUG_ON(sizeof(p->vm_stat_diff[0]) != 1); +#ifdef CONFIG_NUMA + BUILD_BUG_ON(sizeof(p->vm_numa_stat_diff[0]) != 2); +#endif + + /* + * The fast way of checking if there are any vmstat diffs. + */ + if (memchr_inv(p->vm_stat_diff, 0, NR_VM_ZONE_STAT_ITEMS * + sizeof(p->vm_stat_diff[0]))) + return true; +#ifdef CONFIG_NUMA + if (memchr_inv(p->vm_numa_stat_diff, 0, NR_VM_NUMA_STAT_ITEMS * + sizeof(p->vm_numa_stat_diff[0]))) + return true; +#endif + } + return false; +} + +/* + * Switch off vmstat processing and then fold all the remaining differentials + * until the diffs stay at zero. The function is used by NOHZ and can only be + * invoked when tick processing is not active. + */ +void quiet_vmstat(void) +{ + if (system_state != SYSTEM_RUNNING) + return; + + if (!delayed_work_pending(this_cpu_ptr(&vmstat_work))) + return; + + if (!need_update(smp_processor_id())) + return; + + /* + * Just refresh counters and do not care about the pending delayed + * vmstat_update. It doesn't fire that often to matter and canceling + * it would be too expensive from this path. + * vmstat_shepherd will take care about that for us. + */ + refresh_cpu_vm_stats(false); +} + +/* + * Shepherd worker thread that checks the + * differentials of processors that have their worker + * threads for vm statistics updates disabled because of + * inactivity. + */ +static void vmstat_shepherd(struct work_struct *w); + +static DECLARE_DEFERRABLE_WORK(shepherd, vmstat_shepherd); + +static void vmstat_shepherd(struct work_struct *w) +{ + int cpu; + + get_online_cpus(); + /* Check processors whose vmstat worker threads have been disabled */ + for_each_online_cpu(cpu) { + struct delayed_work *dw = &per_cpu(vmstat_work, cpu); + + if (!delayed_work_pending(dw) && need_update(cpu)) + queue_delayed_work_on(cpu, mm_percpu_wq, dw, 0); + } + put_online_cpus(); + + schedule_delayed_work(&shepherd, + round_jiffies_relative(sysctl_stat_interval)); +} + +static void __init start_shepherd_timer(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + INIT_DEFERRABLE_WORK(per_cpu_ptr(&vmstat_work, cpu), + vmstat_update); + + schedule_delayed_work(&shepherd, + round_jiffies_relative(sysctl_stat_interval)); +} + +static void __init init_cpu_node_state(void) +{ + int node; + + for_each_online_node(node) { + if (cpumask_weight(cpumask_of_node(node)) > 0) + node_set_state(node, N_CPU); + } +} + +static int vmstat_cpu_online(unsigned int cpu) +{ + refresh_zone_stat_thresholds(); + node_set_state(cpu_to_node(cpu), N_CPU); + return 0; +} + +static int vmstat_cpu_down_prep(unsigned int cpu) +{ + cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu)); + return 0; +} + +static int vmstat_cpu_dead(unsigned int cpu) +{ + const struct cpumask *node_cpus; + int node; + + node = cpu_to_node(cpu); + + refresh_zone_stat_thresholds(); + node_cpus = cpumask_of_node(node); + if (cpumask_weight(node_cpus) > 0) + return 0; + + node_clear_state(node, N_CPU); + return 0; +} + +#endif + +struct workqueue_struct *mm_percpu_wq; + +void __init init_mm_internals(void) +{ + int ret __maybe_unused; + + mm_percpu_wq = alloc_workqueue("mm_percpu_wq", WQ_MEM_RECLAIM, 0); + +#ifdef CONFIG_SMP + ret = cpuhp_setup_state_nocalls(CPUHP_MM_VMSTAT_DEAD, "mm/vmstat:dead", + NULL, vmstat_cpu_dead); + if (ret < 0) + pr_err("vmstat: failed to register 'dead' hotplug state\n"); + + ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "mm/vmstat:online", + vmstat_cpu_online, + vmstat_cpu_down_prep); + if (ret < 0) + pr_err("vmstat: failed to register 'online' hotplug state\n"); + + get_online_cpus(); + init_cpu_node_state(); + put_online_cpus(); + + start_shepherd_timer(); +#endif +#ifdef CONFIG_PROC_FS + proc_create_seq("buddyinfo", 0444, NULL, &fragmentation_op); + proc_create_seq("pagetypeinfo", 0400, NULL, &pagetypeinfo_op); + proc_create_seq("vmstat", 0444, NULL, &vmstat_op); + proc_create_seq("zoneinfo", 0444, NULL, &zoneinfo_op); +#endif +} + +#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_COMPACTION) + +/* + * Return an index indicating how much of the available free memory is + * unusable for an allocation of the requested size. + */ +static int unusable_free_index(unsigned int order, + struct contig_page_info *info) +{ + /* No free memory is interpreted as all free memory is unusable */ + if (info->free_pages == 0) + return 1000; + + /* + * Index should be a value between 0 and 1. Return a value to 3 + * decimal places. + * + * 0 => no fragmentation + * 1 => high fragmentation + */ + return div_u64((info->free_pages - (info->free_blocks_suitable << order)) * 1000ULL, info->free_pages); + +} + +static void unusable_show_print(struct seq_file *m, + pg_data_t *pgdat, struct zone *zone) +{ + unsigned int order; + int index; + struct contig_page_info info; + + seq_printf(m, "Node %d, zone %8s ", + pgdat->node_id, + zone->name); + for (order = 0; order < MAX_ORDER; ++order) { + fill_contig_page_info(zone, order, &info); + index = unusable_free_index(order, &info); + seq_printf(m, "%d.%03d ", index / 1000, index % 1000); + } + + seq_putc(m, '\n'); +} + +/* + * Display unusable free space index + * + * The unusable free space index measures how much of the available free + * memory cannot be used to satisfy an allocation of a given size and is a + * value between 0 and 1. The higher the value, the more of free memory is + * unusable and by implication, the worse the external fragmentation is. This + * can be expressed as a percentage by multiplying by 100. + */ +static int unusable_show(struct seq_file *m, void *arg) +{ + pg_data_t *pgdat = (pg_data_t *)arg; + + /* check memoryless node */ + if (!node_state(pgdat->node_id, N_MEMORY)) + return 0; + + walk_zones_in_node(m, pgdat, true, false, unusable_show_print); + + return 0; +} + +static const struct seq_operations unusable_sops = { + .start = frag_start, + .next = frag_next, + .stop = frag_stop, + .show = unusable_show, +}; + +DEFINE_SEQ_ATTRIBUTE(unusable); + +static void extfrag_show_print(struct seq_file *m, + pg_data_t *pgdat, struct zone *zone) +{ + unsigned int order; + int index; + + /* Alloc on stack as interrupts are disabled for zone walk */ + struct contig_page_info info; + + seq_printf(m, "Node %d, zone %8s ", + pgdat->node_id, + zone->name); + for (order = 0; order < MAX_ORDER; ++order) { + fill_contig_page_info(zone, order, &info); + index = __fragmentation_index(order, &info); + seq_printf(m, "%d.%03d ", index / 1000, index % 1000); + } + + seq_putc(m, '\n'); +} + +/* + * Display fragmentation index for orders that allocations would fail for + */ +static int extfrag_show(struct seq_file *m, void *arg) +{ + pg_data_t *pgdat = (pg_data_t *)arg; + + walk_zones_in_node(m, pgdat, true, false, extfrag_show_print); + + return 0; +} + +static const struct seq_operations extfrag_sops = { + .start = frag_start, + .next = frag_next, + .stop = frag_stop, + .show = extfrag_show, +}; + +DEFINE_SEQ_ATTRIBUTE(extfrag); + +static int __init extfrag_debug_init(void) +{ + struct dentry *extfrag_debug_root; + + extfrag_debug_root = debugfs_create_dir("extfrag", NULL); + + debugfs_create_file("unusable_index", 0444, extfrag_debug_root, NULL, + &unusable_fops); + + debugfs_create_file("extfrag_index", 0444, extfrag_debug_root, NULL, + &extfrag_fops); + + return 0; +} + +module_init(extfrag_debug_init); +#endif diff --git a/mm/workingset.c b/mm/workingset.c new file mode 100644 index 000000000..975a4d2dd --- /dev/null +++ b/mm/workingset.c @@ -0,0 +1,629 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Workingset detection + * + * Copyright (C) 2013 Red Hat, Inc., Johannes Weiner + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * Double CLOCK lists + * + * Per node, two clock lists are maintained for file pages: the + * inactive and the active list. Freshly faulted pages start out at + * the head of the inactive list and page reclaim scans pages from the + * tail. Pages that are accessed multiple times on the inactive list + * are promoted to the active list, to protect them from reclaim, + * whereas active pages are demoted to the inactive list when the + * active list grows too big. + * + * fault ------------------------+ + * | + * +--------------+ | +-------------+ + * reclaim <- | inactive | <-+-- demotion | active | <--+ + * +--------------+ +-------------+ | + * | | + * +-------------- promotion ------------------+ + * + * + * Access frequency and refault distance + * + * A workload is thrashing when its pages are frequently used but they + * are evicted from the inactive list every time before another access + * would have promoted them to the active list. + * + * In cases where the average access distance between thrashing pages + * is bigger than the size of memory there is nothing that can be + * done - the thrashing set could never fit into memory under any + * circumstance. + * + * However, the average access distance could be bigger than the + * inactive list, yet smaller than the size of memory. In this case, + * the set could fit into memory if it weren't for the currently + * active pages - which may be used more, hopefully less frequently: + * + * +-memory available to cache-+ + * | | + * +-inactive------+-active----+ + * a b | c d e f g h i | J K L M N | + * +---------------+-----------+ + * + * It is prohibitively expensive to accurately track access frequency + * of pages. But a reasonable approximation can be made to measure + * thrashing on the inactive list, after which refaulting pages can be + * activated optimistically to compete with the existing active pages. + * + * Approximating inactive page access frequency - Observations: + * + * 1. When a page is accessed for the first time, it is added to the + * head of the inactive list, slides every existing inactive page + * towards the tail by one slot, and pushes the current tail page + * out of memory. + * + * 2. When a page is accessed for the second time, it is promoted to + * the active list, shrinking the inactive list by one slot. This + * also slides all inactive pages that were faulted into the cache + * more recently than the activated page towards the tail of the + * inactive list. + * + * Thus: + * + * 1. The sum of evictions and activations between any two points in + * time indicate the minimum number of inactive pages accessed in + * between. + * + * 2. Moving one inactive page N page slots towards the tail of the + * list requires at least N inactive page accesses. + * + * Combining these: + * + * 1. When a page is finally evicted from memory, the number of + * inactive pages accessed while the page was in cache is at least + * the number of page slots on the inactive list. + * + * 2. In addition, measuring the sum of evictions and activations (E) + * at the time of a page's eviction, and comparing it to another + * reading (R) at the time the page faults back into memory tells + * the minimum number of accesses while the page was not cached. + * This is called the refault distance. + * + * Because the first access of the page was the fault and the second + * access the refault, we combine the in-cache distance with the + * out-of-cache distance to get the complete minimum access distance + * of this page: + * + * NR_inactive + (R - E) + * + * And knowing the minimum access distance of a page, we can easily + * tell if the page would be able to stay in cache assuming all page + * slots in the cache were available: + * + * NR_inactive + (R - E) <= NR_inactive + NR_active + * + * which can be further simplified to + * + * (R - E) <= NR_active + * + * Put into words, the refault distance (out-of-cache) can be seen as + * a deficit in inactive list space (in-cache). If the inactive list + * had (R - E) more page slots, the page would not have been evicted + * in between accesses, but activated instead. And on a full system, + * the only thing eating into inactive list space is active pages. + * + * + * Refaulting inactive pages + * + * All that is known about the active list is that the pages have been + * accessed more than once in the past. This means that at any given + * time there is actually a good chance that pages on the active list + * are no longer in active use. + * + * So when a refault distance of (R - E) is observed and there are at + * least (R - E) active pages, the refaulting page is activated + * optimistically in the hope that (R - E) active pages are actually + * used less frequently than the refaulting page - or even not used at + * all anymore. + * + * That means if inactive cache is refaulting with a suitable refault + * distance, we assume the cache workingset is transitioning and put + * pressure on the current active list. + * + * If this is wrong and demotion kicks in, the pages which are truly + * used more frequently will be reactivated while the less frequently + * used once will be evicted from memory. + * + * But if this is right, the stale pages will be pushed out of memory + * and the used pages get to stay in cache. + * + * Refaulting active pages + * + * If on the other hand the refaulting pages have recently been + * deactivated, it means that the active list is no longer protecting + * actively used cache from reclaim. The cache is NOT transitioning to + * a different workingset; the existing workingset is thrashing in the + * space allocated to the page cache. + * + * + * Implementation + * + * For each node's LRU lists, a counter for inactive evictions and + * activations is maintained (node->nonresident_age). + * + * On eviction, a snapshot of this counter (along with some bits to + * identify the node) is stored in the now empty page cache + * slot of the evicted page. This is called a shadow entry. + * + * On cache misses for which there are shadow entries, an eligible + * refault distance will immediately activate the refaulting page. + */ + +#define EVICTION_SHIFT ((BITS_PER_LONG - BITS_PER_XA_VALUE) + \ + 1 + NODES_SHIFT + MEM_CGROUP_ID_SHIFT) +#define EVICTION_MASK (~0UL >> EVICTION_SHIFT) + +/* + * Eviction timestamps need to be able to cover the full range of + * actionable refaults. However, bits are tight in the xarray + * entry, and after storing the identifier for the lruvec there might + * not be enough left to represent every single actionable refault. In + * that case, we have to sacrifice granularity for distance, and group + * evictions into coarser buckets by shaving off lower timestamp bits. + */ +static unsigned int bucket_order __read_mostly; + +static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction, + bool workingset) +{ + eviction >>= bucket_order; + eviction &= EVICTION_MASK; + eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid; + eviction = (eviction << NODES_SHIFT) | pgdat->node_id; + eviction = (eviction << 1) | workingset; + + return xa_mk_value(eviction); +} + +static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, + unsigned long *evictionp, bool *workingsetp) +{ + unsigned long entry = xa_to_value(shadow); + int memcgid, nid; + bool workingset; + + workingset = entry & 1; + entry >>= 1; + nid = entry & ((1UL << NODES_SHIFT) - 1); + entry >>= NODES_SHIFT; + memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1); + entry >>= MEM_CGROUP_ID_SHIFT; + + *memcgidp = memcgid; + *pgdat = NODE_DATA(nid); + *evictionp = entry << bucket_order; + *workingsetp = workingset; +} + +/** + * workingset_age_nonresident - age non-resident entries as LRU ages + * @lruvec: the lruvec that was aged + * @nr_pages: the number of pages to count + * + * As in-memory pages are aged, non-resident pages need to be aged as + * well, in order for the refault distances later on to be comparable + * to the in-memory dimensions. This function allows reclaim and LRU + * operations to drive the non-resident aging along in parallel. + */ +void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages) +{ + /* + * Reclaiming a cgroup means reclaiming all its children in a + * round-robin fashion. That means that each cgroup has an LRU + * order that is composed of the LRU orders of its child + * cgroups; and every page has an LRU position not just in the + * cgroup that owns it, but in all of that group's ancestors. + * + * So when the physical inactive list of a leaf cgroup ages, + * the virtual inactive lists of all its parents, including + * the root cgroup's, age as well. + */ + do { + atomic_long_add(nr_pages, &lruvec->nonresident_age); + } while ((lruvec = parent_lruvec(lruvec))); +} + +/** + * workingset_eviction - note the eviction of a page from memory + * @target_memcg: the cgroup that is causing the reclaim + * @page: the page being evicted + * + * Returns a shadow entry to be stored in @page->mapping->i_pages in place + * of the evicted @page so that a later refault can be detected. + */ +void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg) +{ + struct pglist_data *pgdat = page_pgdat(page); + unsigned long eviction; + struct lruvec *lruvec; + int memcgid; + + /* Page is fully exclusive and pins page->mem_cgroup */ + VM_BUG_ON_PAGE(PageLRU(page), page); + VM_BUG_ON_PAGE(page_count(page), page); + VM_BUG_ON_PAGE(!PageLocked(page), page); + + lruvec = mem_cgroup_lruvec(target_memcg, pgdat); + workingset_age_nonresident(lruvec, thp_nr_pages(page)); + /* XXX: target_memcg can be NULL, go through lruvec */ + memcgid = mem_cgroup_id(lruvec_memcg(lruvec)); + eviction = atomic_long_read(&lruvec->nonresident_age); + return pack_shadow(memcgid, pgdat, eviction, PageWorkingset(page)); +} + +/** + * workingset_refault - evaluate the refault of a previously evicted page + * @page: the freshly allocated replacement page + * @shadow: shadow entry of the evicted page + * + * Calculates and evaluates the refault distance of the previously + * evicted page in the context of the node and the memcg whose memory + * pressure caused the eviction. + */ +void workingset_refault(struct page *page, void *shadow) +{ + bool file = page_is_file_lru(page); + struct mem_cgroup *eviction_memcg; + struct lruvec *eviction_lruvec; + unsigned long refault_distance; + unsigned long workingset_size; + struct pglist_data *pgdat; + struct mem_cgroup *memcg; + unsigned long eviction; + struct lruvec *lruvec; + unsigned long refault; + bool workingset; + int memcgid; + + unpack_shadow(shadow, &memcgid, &pgdat, &eviction, &workingset); + + rcu_read_lock(); + /* + * Look up the memcg associated with the stored ID. It might + * have been deleted since the page's eviction. + * + * Note that in rare events the ID could have been recycled + * for a new cgroup that refaults a shared page. This is + * impossible to tell from the available data. However, this + * should be a rare and limited disturbance, and activations + * are always speculative anyway. Ultimately, it's the aging + * algorithm's job to shake out the minimum access frequency + * for the active cache. + * + * XXX: On !CONFIG_MEMCG, this will always return NULL; it + * would be better if the root_mem_cgroup existed in all + * configurations instead. + */ + eviction_memcg = mem_cgroup_from_id(memcgid); + if (!mem_cgroup_disabled() && !eviction_memcg) + goto out; + eviction_lruvec = mem_cgroup_lruvec(eviction_memcg, pgdat); + refault = atomic_long_read(&eviction_lruvec->nonresident_age); + + /* + * Calculate the refault distance + * + * The unsigned subtraction here gives an accurate distance + * across nonresident_age overflows in most cases. There is a + * special case: usually, shadow entries have a short lifetime + * and are either refaulted or reclaimed along with the inode + * before they get too old. But it is not impossible for the + * nonresident_age to lap a shadow entry in the field, which + * can then result in a false small refault distance, leading + * to a false activation should this old entry actually + * refault again. However, earlier kernels used to deactivate + * unconditionally with *every* reclaim invocation for the + * longest time, so the occasional inappropriate activation + * leading to pressure on the active list is not a problem. + */ + refault_distance = (refault - eviction) & EVICTION_MASK; + + /* + * The activation decision for this page is made at the level + * where the eviction occurred, as that is where the LRU order + * during page reclaim is being determined. + * + * However, the cgroup that will own the page is the one that + * is actually experiencing the refault event. + */ + memcg = page_memcg(page); + lruvec = mem_cgroup_lruvec(memcg, pgdat); + + inc_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file); + + /* + * Compare the distance to the existing workingset size. We + * don't activate pages that couldn't stay resident even if + * all the memory was available to the workingset. Whether + * workingset competition needs to consider anon or not depends + * on having swap. + */ + workingset_size = lruvec_page_state(eviction_lruvec, NR_ACTIVE_FILE); + if (!file) { + workingset_size += lruvec_page_state(eviction_lruvec, + NR_INACTIVE_FILE); + } + if (mem_cgroup_get_nr_swap_pages(memcg) > 0) { + workingset_size += lruvec_page_state(eviction_lruvec, + NR_ACTIVE_ANON); + if (file) { + workingset_size += lruvec_page_state(eviction_lruvec, + NR_INACTIVE_ANON); + } + } + if (refault_distance > workingset_size) + goto out; + + SetPageActive(page); + workingset_age_nonresident(lruvec, thp_nr_pages(page)); + inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + file); + + /* Page was active prior to eviction */ + if (workingset) { + SetPageWorkingset(page); + /* XXX: Move to lru_cache_add() when it supports new vs putback */ + spin_lock_irq(&page_pgdat(page)->lru_lock); + lru_note_cost_page(page); + spin_unlock_irq(&page_pgdat(page)->lru_lock); + inc_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + file); + } +out: + rcu_read_unlock(); +} + +/** + * workingset_activation - note a page activation + * @page: page that is being activated + */ +void workingset_activation(struct page *page) +{ + struct mem_cgroup *memcg; + struct lruvec *lruvec; + + rcu_read_lock(); + /* + * Filter non-memcg pages here, e.g. unmap can call + * mark_page_accessed() on VDSO pages. + * + * XXX: See workingset_refault() - this should return + * root_mem_cgroup even for !CONFIG_MEMCG. + */ + memcg = page_memcg_rcu(page); + if (!mem_cgroup_disabled() && !memcg) + goto out; + lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page)); + workingset_age_nonresident(lruvec, thp_nr_pages(page)); +out: + rcu_read_unlock(); +} + +/* + * Shadow entries reflect the share of the working set that does not + * fit into memory, so their number depends on the access pattern of + * the workload. In most cases, they will refault or get reclaimed + * along with the inode, but a (malicious) workload that streams + * through files with a total size several times that of available + * memory, while preventing the inodes from being reclaimed, can + * create excessive amounts of shadow nodes. To keep a lid on this, + * track shadow nodes and reclaim them when they grow way past the + * point where they would still be useful. + */ + +static struct list_lru shadow_nodes; + +void workingset_update_node(struct xa_node *node) +{ + /* + * Track non-empty nodes that contain only shadow entries; + * unlink those that contain pages or are being freed. + * + * Avoid acquiring the list_lru lock when the nodes are + * already where they should be. The list_empty() test is safe + * as node->private_list is protected by the i_pages lock. + */ + VM_WARN_ON_ONCE(!irqs_disabled()); /* For __inc_lruvec_page_state */ + + if (node->count && node->count == node->nr_values) { + if (list_empty(&node->private_list)) { + list_lru_add(&shadow_nodes, &node->private_list); + __inc_lruvec_slab_state(node, WORKINGSET_NODES); + } + } else { + if (!list_empty(&node->private_list)) { + list_lru_del(&shadow_nodes, &node->private_list); + __dec_lruvec_slab_state(node, WORKINGSET_NODES); + } + } +} + +static unsigned long count_shadow_nodes(struct shrinker *shrinker, + struct shrink_control *sc) +{ + unsigned long max_nodes; + unsigned long nodes; + unsigned long pages; + + nodes = list_lru_shrink_count(&shadow_nodes, sc); + + /* + * Approximate a reasonable limit for the nodes + * containing shadow entries. We don't need to keep more + * shadow entries than possible pages on the active list, + * since refault distances bigger than that are dismissed. + * + * The size of the active list converges toward 100% of + * overall page cache as memory grows, with only a tiny + * inactive list. Assume the total cache size for that. + * + * Nodes might be sparsely populated, with only one shadow + * entry in the extreme case. Obviously, we cannot keep one + * node for every eligible shadow entry, so compromise on a + * worst-case density of 1/8th. Below that, not all eligible + * refaults can be detected anymore. + * + * On 64-bit with 7 xa_nodes per page and 64 slots + * each, this will reclaim shadow entries when they consume + * ~1.8% of available memory: + * + * PAGE_SIZE / xa_nodes / node_entries * 8 / PAGE_SIZE + */ +#ifdef CONFIG_MEMCG + if (sc->memcg) { + struct lruvec *lruvec; + int i; + + lruvec = mem_cgroup_lruvec(sc->memcg, NODE_DATA(sc->nid)); + for (pages = 0, i = 0; i < NR_LRU_LISTS; i++) + pages += lruvec_page_state_local(lruvec, + NR_LRU_BASE + i); + pages += lruvec_page_state_local( + lruvec, NR_SLAB_RECLAIMABLE_B) >> PAGE_SHIFT; + pages += lruvec_page_state_local( + lruvec, NR_SLAB_UNRECLAIMABLE_B) >> PAGE_SHIFT; + } else +#endif + pages = node_present_pages(sc->nid); + + max_nodes = pages >> (XA_CHUNK_SHIFT - 3); + + if (!nodes) + return SHRINK_EMPTY; + + if (nodes <= max_nodes) + return 0; + return nodes - max_nodes; +} + +static enum lru_status shadow_lru_isolate(struct list_head *item, + struct list_lru_one *lru, + spinlock_t *lru_lock, + void *arg) __must_hold(lru_lock) +{ + struct xa_node *node = container_of(item, struct xa_node, private_list); + struct address_space *mapping; + int ret; + + /* + * Page cache insertions and deletions synchronously maintain + * the shadow node LRU under the i_pages lock and the + * lru_lock. Because the page cache tree is emptied before + * the inode can be destroyed, holding the lru_lock pins any + * address_space that has nodes on the LRU. + * + * We can then safely transition to the i_pages lock to + * pin only the address_space of the particular node we want + * to reclaim, take the node off-LRU, and drop the lru_lock. + */ + + mapping = container_of(node->array, struct address_space, i_pages); + + /* Coming from the list, invert the lock order */ + if (!xa_trylock(&mapping->i_pages)) { + spin_unlock_irq(lru_lock); + ret = LRU_RETRY; + goto out; + } + + list_lru_isolate(lru, item); + __dec_lruvec_slab_state(node, WORKINGSET_NODES); + + spin_unlock(lru_lock); + + /* + * The nodes should only contain one or more shadow entries, + * no pages, so we expect to be able to remove them all and + * delete and free the empty node afterwards. + */ + if (WARN_ON_ONCE(!node->nr_values)) + goto out_invalid; + if (WARN_ON_ONCE(node->count != node->nr_values)) + goto out_invalid; + mapping->nrexceptional -= node->nr_values; + xa_delete_node(node, workingset_update_node); + __inc_lruvec_slab_state(node, WORKINGSET_NODERECLAIM); + +out_invalid: + xa_unlock_irq(&mapping->i_pages); + ret = LRU_REMOVED_RETRY; +out: + cond_resched(); + spin_lock_irq(lru_lock); + return ret; +} + +static unsigned long scan_shadow_nodes(struct shrinker *shrinker, + struct shrink_control *sc) +{ + /* list_lru lock nests inside the IRQ-safe i_pages lock */ + return list_lru_shrink_walk_irq(&shadow_nodes, sc, shadow_lru_isolate, + NULL); +} + +static struct shrinker workingset_shadow_shrinker = { + .count_objects = count_shadow_nodes, + .scan_objects = scan_shadow_nodes, + .seeks = 0, /* ->count reports only fully expendable nodes */ + .flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE, +}; + +/* + * Our list_lru->lock is IRQ-safe as it nests inside the IRQ-safe + * i_pages lock. + */ +static struct lock_class_key shadow_nodes_key; + +static int __init workingset_init(void) +{ + unsigned int timestamp_bits; + unsigned int max_order; + int ret; + + BUILD_BUG_ON(BITS_PER_LONG < EVICTION_SHIFT); + /* + * Calculate the eviction bucket size to cover the longest + * actionable refault distance, which is currently half of + * memory (totalram_pages/2). However, memory hotplug may add + * some more pages at runtime, so keep working with up to + * double the initial memory by using totalram_pages as-is. + */ + timestamp_bits = BITS_PER_LONG - EVICTION_SHIFT; + max_order = fls_long(totalram_pages() - 1); + if (max_order > timestamp_bits) + bucket_order = max_order - timestamp_bits; + pr_info("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n", + timestamp_bits, max_order, bucket_order); + + ret = prealloc_shrinker(&workingset_shadow_shrinker); + if (ret) + goto err; + ret = __list_lru_init(&shadow_nodes, true, &shadow_nodes_key, + &workingset_shadow_shrinker); + if (ret) + goto err_list_lru; + register_shrinker_prepared(&workingset_shadow_shrinker); + return 0; +err_list_lru: + free_prealloced_shrinker(&workingset_shadow_shrinker); +err: + return ret; +} +module_init(workingset_init); diff --git a/mm/z3fold.c b/mm/z3fold.c new file mode 100644 index 000000000..912ac9a64 --- /dev/null +++ b/mm/z3fold.c @@ -0,0 +1,1832 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * z3fold.c + * + * Author: Vitaly Wool + * Copyright (C) 2016, Sony Mobile Communications Inc. + * + * This implementation is based on zbud written by Seth Jennings. + * + * z3fold is an special purpose allocator for storing compressed pages. It + * can store up to three compressed pages per page which improves the + * compression ratio of zbud while retaining its main concepts (e. g. always + * storing an integral number of objects per page) and simplicity. + * It still has simple and deterministic reclaim properties that make it + * preferable to a higher density approach (with no requirement on integral + * number of object per page) when reclaim is used. + * + * As in zbud, pages are divided into "chunks". The size of the chunks is + * fixed at compile time and is determined by NCHUNKS_ORDER below. + * + * z3fold doesn't export any API and is meant to be used via zpool API. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * NCHUNKS_ORDER determines the internal allocation granularity, effectively + * adjusting internal fragmentation. It also determines the number of + * freelists maintained in each pool. NCHUNKS_ORDER of 6 means that the + * allocation granularity will be in chunks of size PAGE_SIZE/64. Some chunks + * in the beginning of an allocated page are occupied by z3fold header, so + * NCHUNKS will be calculated to 63 (or 62 in case CONFIG_DEBUG_SPINLOCK=y), + * which shows the max number of free chunks in z3fold page, also there will + * be 63, or 62, respectively, freelists per pool. + */ +#define NCHUNKS_ORDER 6 + +#define CHUNK_SHIFT (PAGE_SHIFT - NCHUNKS_ORDER) +#define CHUNK_SIZE (1 << CHUNK_SHIFT) +#define ZHDR_SIZE_ALIGNED round_up(sizeof(struct z3fold_header), CHUNK_SIZE) +#define ZHDR_CHUNKS (ZHDR_SIZE_ALIGNED >> CHUNK_SHIFT) +#define TOTAL_CHUNKS (PAGE_SIZE >> CHUNK_SHIFT) +#define NCHUNKS ((PAGE_SIZE - ZHDR_SIZE_ALIGNED) >> CHUNK_SHIFT) + +#define BUDDY_MASK (0x3) +#define BUDDY_SHIFT 2 +#define SLOTS_ALIGN (0x40) + +/***************** + * Structures +*****************/ +struct z3fold_pool; +struct z3fold_ops { + int (*evict)(struct z3fold_pool *pool, unsigned long handle); +}; + +enum buddy { + HEADLESS = 0, + FIRST, + MIDDLE, + LAST, + BUDDIES_MAX = LAST +}; + +struct z3fold_buddy_slots { + /* + * we are using BUDDY_MASK in handle_to_buddy etc. so there should + * be enough slots to hold all possible variants + */ + unsigned long slot[BUDDY_MASK + 1]; + unsigned long pool; /* back link */ + rwlock_t lock; +}; +#define HANDLE_FLAG_MASK (0x03) + +/* + * struct z3fold_header - z3fold page metadata occupying first chunks of each + * z3fold page, except for HEADLESS pages + * @buddy: links the z3fold page into the relevant list in the + * pool + * @page_lock: per-page lock + * @refcount: reference count for the z3fold page + * @work: work_struct for page layout optimization + * @slots: pointer to the structure holding buddy slots + * @pool: pointer to the containing pool + * @cpu: CPU which this page "belongs" to + * @first_chunks: the size of the first buddy in chunks, 0 if free + * @middle_chunks: the size of the middle buddy in chunks, 0 if free + * @last_chunks: the size of the last buddy in chunks, 0 if free + * @first_num: the starting number (for the first handle) + * @mapped_count: the number of objects currently mapped + */ +struct z3fold_header { + struct list_head buddy; + spinlock_t page_lock; + struct kref refcount; + struct work_struct work; + struct z3fold_buddy_slots *slots; + struct z3fold_pool *pool; + short cpu; + unsigned short first_chunks; + unsigned short middle_chunks; + unsigned short last_chunks; + unsigned short start_middle; + unsigned short first_num:2; + unsigned short mapped_count:2; + unsigned short foreign_handles:2; +}; + +/** + * struct z3fold_pool - stores metadata for each z3fold pool + * @name: pool name + * @lock: protects pool unbuddied/lru lists + * @stale_lock: protects pool stale page list + * @unbuddied: per-cpu array of lists tracking z3fold pages that contain 2- + * buddies; the list each z3fold page is added to depends on + * the size of its free region. + * @lru: list tracking the z3fold pages in LRU order by most recently + * added buddy. + * @stale: list of pages marked for freeing + * @pages_nr: number of z3fold pages in the pool. + * @c_handle: cache for z3fold_buddy_slots allocation + * @ops: pointer to a structure of user defined operations specified at + * pool creation time. + * @compact_wq: workqueue for page layout background optimization + * @release_wq: workqueue for safe page release + * @work: work_struct for safe page release + * @inode: inode for z3fold pseudo filesystem + * + * This structure is allocated at pool creation time and maintains metadata + * pertaining to a particular z3fold pool. + */ +struct z3fold_pool { + const char *name; + spinlock_t lock; + spinlock_t stale_lock; + struct list_head *unbuddied; + struct list_head lru; + struct list_head stale; + atomic64_t pages_nr; + struct kmem_cache *c_handle; + const struct z3fold_ops *ops; + struct zpool *zpool; + const struct zpool_ops *zpool_ops; + struct workqueue_struct *compact_wq; + struct workqueue_struct *release_wq; + struct work_struct work; + struct inode *inode; +}; + +/* + * Internal z3fold page flags + */ +enum z3fold_page_flags { + PAGE_HEADLESS = 0, + MIDDLE_CHUNK_MAPPED, + NEEDS_COMPACTING, + PAGE_STALE, + PAGE_CLAIMED, /* by either reclaim or free */ +}; + +/* + * handle flags, go under HANDLE_FLAG_MASK + */ +enum z3fold_handle_flags { + HANDLES_NOFREE = 0, +}; + +/* + * Forward declarations + */ +static struct z3fold_header *__z3fold_alloc(struct z3fold_pool *, size_t, bool); +static void compact_page_work(struct work_struct *w); + +/***************** + * Helpers +*****************/ + +/* Converts an allocation size in bytes to size in z3fold chunks */ +static int size_to_chunks(size_t size) +{ + return (size + CHUNK_SIZE - 1) >> CHUNK_SHIFT; +} + +#define for_each_unbuddied_list(_iter, _begin) \ + for ((_iter) = (_begin); (_iter) < NCHUNKS; (_iter)++) + +static inline struct z3fold_buddy_slots *alloc_slots(struct z3fold_pool *pool, + gfp_t gfp) +{ + struct z3fold_buddy_slots *slots; + + slots = kmem_cache_zalloc(pool->c_handle, + (gfp & ~(__GFP_HIGHMEM | __GFP_MOVABLE))); + + if (slots) { + /* It will be freed separately in free_handle(). */ + kmemleak_not_leak(slots); + slots->pool = (unsigned long)pool; + rwlock_init(&slots->lock); + } + + return slots; +} + +static inline struct z3fold_pool *slots_to_pool(struct z3fold_buddy_slots *s) +{ + return (struct z3fold_pool *)(s->pool & ~HANDLE_FLAG_MASK); +} + +static inline struct z3fold_buddy_slots *handle_to_slots(unsigned long handle) +{ + return (struct z3fold_buddy_slots *)(handle & ~(SLOTS_ALIGN - 1)); +} + +/* Lock a z3fold page */ +static inline void z3fold_page_lock(struct z3fold_header *zhdr) +{ + spin_lock(&zhdr->page_lock); +} + +/* Try to lock a z3fold page */ +static inline int z3fold_page_trylock(struct z3fold_header *zhdr) +{ + return spin_trylock(&zhdr->page_lock); +} + +/* Unlock a z3fold page */ +static inline void z3fold_page_unlock(struct z3fold_header *zhdr) +{ + spin_unlock(&zhdr->page_lock); +} + + +static inline struct z3fold_header *__get_z3fold_header(unsigned long handle, + bool lock) +{ + struct z3fold_buddy_slots *slots; + struct z3fold_header *zhdr; + int locked = 0; + + if (!(handle & (1 << PAGE_HEADLESS))) { + slots = handle_to_slots(handle); + do { + unsigned long addr; + + read_lock(&slots->lock); + addr = *(unsigned long *)handle; + zhdr = (struct z3fold_header *)(addr & PAGE_MASK); + if (lock) + locked = z3fold_page_trylock(zhdr); + read_unlock(&slots->lock); + if (locked) + break; + cpu_relax(); + } while (lock); + } else { + zhdr = (struct z3fold_header *)(handle & PAGE_MASK); + } + + return zhdr; +} + +/* Returns the z3fold page where a given handle is stored */ +static inline struct z3fold_header *handle_to_z3fold_header(unsigned long h) +{ + return __get_z3fold_header(h, false); +} + +/* return locked z3fold page if it's not headless */ +static inline struct z3fold_header *get_z3fold_header(unsigned long h) +{ + return __get_z3fold_header(h, true); +} + +static inline void put_z3fold_header(struct z3fold_header *zhdr) +{ + struct page *page = virt_to_page(zhdr); + + if (!test_bit(PAGE_HEADLESS, &page->private)) + z3fold_page_unlock(zhdr); +} + +static inline void free_handle(unsigned long handle, struct z3fold_header *zhdr) +{ + struct z3fold_buddy_slots *slots; + int i; + bool is_free; + + if (handle & (1 << PAGE_HEADLESS)) + return; + + if (WARN_ON(*(unsigned long *)handle == 0)) + return; + + slots = handle_to_slots(handle); + write_lock(&slots->lock); + *(unsigned long *)handle = 0; + + if (test_bit(HANDLES_NOFREE, &slots->pool)) { + write_unlock(&slots->lock); + return; /* simple case, nothing else to do */ + } + + if (zhdr->slots != slots) + zhdr->foreign_handles--; + + is_free = true; + for (i = 0; i <= BUDDY_MASK; i++) { + if (slots->slot[i]) { + is_free = false; + break; + } + } + write_unlock(&slots->lock); + + if (is_free) { + struct z3fold_pool *pool = slots_to_pool(slots); + + if (zhdr->slots == slots) + zhdr->slots = NULL; + kmem_cache_free(pool->c_handle, slots); + } +} + +static int z3fold_init_fs_context(struct fs_context *fc) +{ + return init_pseudo(fc, Z3FOLD_MAGIC) ? 0 : -ENOMEM; +} + +static struct file_system_type z3fold_fs = { + .name = "z3fold", + .init_fs_context = z3fold_init_fs_context, + .kill_sb = kill_anon_super, +}; + +static struct vfsmount *z3fold_mnt; +static int z3fold_mount(void) +{ + int ret = 0; + + z3fold_mnt = kern_mount(&z3fold_fs); + if (IS_ERR(z3fold_mnt)) + ret = PTR_ERR(z3fold_mnt); + + return ret; +} + +static void z3fold_unmount(void) +{ + kern_unmount(z3fold_mnt); +} + +static const struct address_space_operations z3fold_aops; +static int z3fold_register_migration(struct z3fold_pool *pool) +{ + pool->inode = alloc_anon_inode(z3fold_mnt->mnt_sb); + if (IS_ERR(pool->inode)) { + pool->inode = NULL; + return 1; + } + + pool->inode->i_mapping->private_data = pool; + pool->inode->i_mapping->a_ops = &z3fold_aops; + return 0; +} + +static void z3fold_unregister_migration(struct z3fold_pool *pool) +{ + if (pool->inode) + iput(pool->inode); + } + +/* Initializes the z3fold header of a newly allocated z3fold page */ +static struct z3fold_header *init_z3fold_page(struct page *page, bool headless, + struct z3fold_pool *pool, gfp_t gfp) +{ + struct z3fold_header *zhdr = page_address(page); + struct z3fold_buddy_slots *slots; + + INIT_LIST_HEAD(&page->lru); + clear_bit(PAGE_HEADLESS, &page->private); + clear_bit(MIDDLE_CHUNK_MAPPED, &page->private); + clear_bit(NEEDS_COMPACTING, &page->private); + clear_bit(PAGE_STALE, &page->private); + clear_bit(PAGE_CLAIMED, &page->private); + if (headless) + return zhdr; + + slots = alloc_slots(pool, gfp); + if (!slots) + return NULL; + + spin_lock_init(&zhdr->page_lock); + kref_init(&zhdr->refcount); + zhdr->first_chunks = 0; + zhdr->middle_chunks = 0; + zhdr->last_chunks = 0; + zhdr->first_num = 0; + zhdr->start_middle = 0; + zhdr->cpu = -1; + zhdr->foreign_handles = 0; + zhdr->mapped_count = 0; + zhdr->slots = slots; + zhdr->pool = pool; + INIT_LIST_HEAD(&zhdr->buddy); + INIT_WORK(&zhdr->work, compact_page_work); + return zhdr; +} + +/* Resets the struct page fields and frees the page */ +static void free_z3fold_page(struct page *page, bool headless) +{ + if (!headless) { + lock_page(page); + __ClearPageMovable(page); + unlock_page(page); + } + ClearPagePrivate(page); + __free_page(page); +} + +/* Helper function to build the index */ +static inline int __idx(struct z3fold_header *zhdr, enum buddy bud) +{ + return (bud + zhdr->first_num) & BUDDY_MASK; +} + +/* + * Encodes the handle of a particular buddy within a z3fold page + * Pool lock should be held as this function accesses first_num + */ +static unsigned long __encode_handle(struct z3fold_header *zhdr, + struct z3fold_buddy_slots *slots, + enum buddy bud) +{ + unsigned long h = (unsigned long)zhdr; + int idx = 0; + + /* + * For a headless page, its handle is its pointer with the extra + * PAGE_HEADLESS bit set + */ + if (bud == HEADLESS) + return h | (1 << PAGE_HEADLESS); + + /* otherwise, return pointer to encoded handle */ + idx = __idx(zhdr, bud); + h += idx; + if (bud == LAST) + h |= (zhdr->last_chunks << BUDDY_SHIFT); + + write_lock(&slots->lock); + slots->slot[idx] = h; + write_unlock(&slots->lock); + return (unsigned long)&slots->slot[idx]; +} + +static unsigned long encode_handle(struct z3fold_header *zhdr, enum buddy bud) +{ + return __encode_handle(zhdr, zhdr->slots, bud); +} + +/* only for LAST bud, returns zero otherwise */ +static unsigned short handle_to_chunks(unsigned long handle) +{ + struct z3fold_buddy_slots *slots = handle_to_slots(handle); + unsigned long addr; + + read_lock(&slots->lock); + addr = *(unsigned long *)handle; + read_unlock(&slots->lock); + return (addr & ~PAGE_MASK) >> BUDDY_SHIFT; +} + +/* + * (handle & BUDDY_MASK) < zhdr->first_num is possible in encode_handle + * but that doesn't matter. because the masking will result in the + * correct buddy number. + */ +static enum buddy handle_to_buddy(unsigned long handle) +{ + struct z3fold_header *zhdr; + struct z3fold_buddy_slots *slots = handle_to_slots(handle); + unsigned long addr; + + read_lock(&slots->lock); + WARN_ON(handle & (1 << PAGE_HEADLESS)); + addr = *(unsigned long *)handle; + read_unlock(&slots->lock); + zhdr = (struct z3fold_header *)(addr & PAGE_MASK); + return (addr - zhdr->first_num) & BUDDY_MASK; +} + +static inline struct z3fold_pool *zhdr_to_pool(struct z3fold_header *zhdr) +{ + return zhdr->pool; +} + +static void __release_z3fold_page(struct z3fold_header *zhdr, bool locked) +{ + struct page *page = virt_to_page(zhdr); + struct z3fold_pool *pool = zhdr_to_pool(zhdr); + + WARN_ON(!list_empty(&zhdr->buddy)); + set_bit(PAGE_STALE, &page->private); + clear_bit(NEEDS_COMPACTING, &page->private); + spin_lock(&pool->lock); + if (!list_empty(&page->lru)) + list_del_init(&page->lru); + spin_unlock(&pool->lock); + + if (locked) + z3fold_page_unlock(zhdr); + + spin_lock(&pool->stale_lock); + list_add(&zhdr->buddy, &pool->stale); + queue_work(pool->release_wq, &pool->work); + spin_unlock(&pool->stale_lock); +} + +static void __attribute__((__unused__)) + release_z3fold_page(struct kref *ref) +{ + struct z3fold_header *zhdr = container_of(ref, struct z3fold_header, + refcount); + __release_z3fold_page(zhdr, false); +} + +static void release_z3fold_page_locked(struct kref *ref) +{ + struct z3fold_header *zhdr = container_of(ref, struct z3fold_header, + refcount); + WARN_ON(z3fold_page_trylock(zhdr)); + __release_z3fold_page(zhdr, true); +} + +static void release_z3fold_page_locked_list(struct kref *ref) +{ + struct z3fold_header *zhdr = container_of(ref, struct z3fold_header, + refcount); + struct z3fold_pool *pool = zhdr_to_pool(zhdr); + + spin_lock(&pool->lock); + list_del_init(&zhdr->buddy); + spin_unlock(&pool->lock); + + WARN_ON(z3fold_page_trylock(zhdr)); + __release_z3fold_page(zhdr, true); +} + +static void free_pages_work(struct work_struct *w) +{ + struct z3fold_pool *pool = container_of(w, struct z3fold_pool, work); + + spin_lock(&pool->stale_lock); + while (!list_empty(&pool->stale)) { + struct z3fold_header *zhdr = list_first_entry(&pool->stale, + struct z3fold_header, buddy); + struct page *page = virt_to_page(zhdr); + + list_del(&zhdr->buddy); + if (WARN_ON(!test_bit(PAGE_STALE, &page->private))) + continue; + spin_unlock(&pool->stale_lock); + cancel_work_sync(&zhdr->work); + free_z3fold_page(page, false); + cond_resched(); + spin_lock(&pool->stale_lock); + } + spin_unlock(&pool->stale_lock); +} + +/* + * Returns the number of free chunks in a z3fold page. + * NB: can't be used with HEADLESS pages. + */ +static int num_free_chunks(struct z3fold_header *zhdr) +{ + int nfree; + /* + * If there is a middle object, pick up the bigger free space + * either before or after it. Otherwise just subtract the number + * of chunks occupied by the first and the last objects. + */ + if (zhdr->middle_chunks != 0) { + int nfree_before = zhdr->first_chunks ? + 0 : zhdr->start_middle - ZHDR_CHUNKS; + int nfree_after = zhdr->last_chunks ? + 0 : TOTAL_CHUNKS - + (zhdr->start_middle + zhdr->middle_chunks); + nfree = max(nfree_before, nfree_after); + } else + nfree = NCHUNKS - zhdr->first_chunks - zhdr->last_chunks; + return nfree; +} + +/* Add to the appropriate unbuddied list */ +static inline void add_to_unbuddied(struct z3fold_pool *pool, + struct z3fold_header *zhdr) +{ + if (zhdr->first_chunks == 0 || zhdr->last_chunks == 0 || + zhdr->middle_chunks == 0) { + struct list_head *unbuddied = get_cpu_ptr(pool->unbuddied); + + int freechunks = num_free_chunks(zhdr); + spin_lock(&pool->lock); + list_add(&zhdr->buddy, &unbuddied[freechunks]); + spin_unlock(&pool->lock); + zhdr->cpu = smp_processor_id(); + put_cpu_ptr(pool->unbuddied); + } +} + +static inline enum buddy get_free_buddy(struct z3fold_header *zhdr, int chunks) +{ + enum buddy bud = HEADLESS; + + if (zhdr->middle_chunks) { + if (!zhdr->first_chunks && + chunks <= zhdr->start_middle - ZHDR_CHUNKS) + bud = FIRST; + else if (!zhdr->last_chunks) + bud = LAST; + } else { + if (!zhdr->first_chunks) + bud = FIRST; + else if (!zhdr->last_chunks) + bud = LAST; + else + bud = MIDDLE; + } + + return bud; +} + +static inline void *mchunk_memmove(struct z3fold_header *zhdr, + unsigned short dst_chunk) +{ + void *beg = zhdr; + return memmove(beg + (dst_chunk << CHUNK_SHIFT), + beg + (zhdr->start_middle << CHUNK_SHIFT), + zhdr->middle_chunks << CHUNK_SHIFT); +} + +static inline bool buddy_single(struct z3fold_header *zhdr) +{ + return !((zhdr->first_chunks && zhdr->middle_chunks) || + (zhdr->first_chunks && zhdr->last_chunks) || + (zhdr->middle_chunks && zhdr->last_chunks)); +} + +static struct z3fold_header *compact_single_buddy(struct z3fold_header *zhdr) +{ + struct z3fold_pool *pool = zhdr_to_pool(zhdr); + void *p = zhdr; + unsigned long old_handle = 0; + size_t sz = 0; + struct z3fold_header *new_zhdr = NULL; + int first_idx = __idx(zhdr, FIRST); + int middle_idx = __idx(zhdr, MIDDLE); + int last_idx = __idx(zhdr, LAST); + unsigned short *moved_chunks = NULL; + + /* + * No need to protect slots here -- all the slots are "local" and + * the page lock is already taken + */ + if (zhdr->first_chunks && zhdr->slots->slot[first_idx]) { + p += ZHDR_SIZE_ALIGNED; + sz = zhdr->first_chunks << CHUNK_SHIFT; + old_handle = (unsigned long)&zhdr->slots->slot[first_idx]; + moved_chunks = &zhdr->first_chunks; + } else if (zhdr->middle_chunks && zhdr->slots->slot[middle_idx]) { + p += zhdr->start_middle << CHUNK_SHIFT; + sz = zhdr->middle_chunks << CHUNK_SHIFT; + old_handle = (unsigned long)&zhdr->slots->slot[middle_idx]; + moved_chunks = &zhdr->middle_chunks; + } else if (zhdr->last_chunks && zhdr->slots->slot[last_idx]) { + p += PAGE_SIZE - (zhdr->last_chunks << CHUNK_SHIFT); + sz = zhdr->last_chunks << CHUNK_SHIFT; + old_handle = (unsigned long)&zhdr->slots->slot[last_idx]; + moved_chunks = &zhdr->last_chunks; + } + + if (sz > 0) { + enum buddy new_bud = HEADLESS; + short chunks = size_to_chunks(sz); + void *q; + + new_zhdr = __z3fold_alloc(pool, sz, false); + if (!new_zhdr) + return NULL; + + if (WARN_ON(new_zhdr == zhdr)) + goto out_fail; + + new_bud = get_free_buddy(new_zhdr, chunks); + q = new_zhdr; + switch (new_bud) { + case FIRST: + new_zhdr->first_chunks = chunks; + q += ZHDR_SIZE_ALIGNED; + break; + case MIDDLE: + new_zhdr->middle_chunks = chunks; + new_zhdr->start_middle = + new_zhdr->first_chunks + ZHDR_CHUNKS; + q += new_zhdr->start_middle << CHUNK_SHIFT; + break; + case LAST: + new_zhdr->last_chunks = chunks; + q += PAGE_SIZE - (new_zhdr->last_chunks << CHUNK_SHIFT); + break; + default: + goto out_fail; + } + new_zhdr->foreign_handles++; + memcpy(q, p, sz); + write_lock(&zhdr->slots->lock); + *(unsigned long *)old_handle = (unsigned long)new_zhdr + + __idx(new_zhdr, new_bud); + if (new_bud == LAST) + *(unsigned long *)old_handle |= + (new_zhdr->last_chunks << BUDDY_SHIFT); + write_unlock(&zhdr->slots->lock); + add_to_unbuddied(pool, new_zhdr); + z3fold_page_unlock(new_zhdr); + + *moved_chunks = 0; + } + + return new_zhdr; + +out_fail: + if (new_zhdr) { + if (kref_put(&new_zhdr->refcount, release_z3fold_page_locked)) + atomic64_dec(&pool->pages_nr); + else { + add_to_unbuddied(pool, new_zhdr); + z3fold_page_unlock(new_zhdr); + } + } + return NULL; + +} + +#define BIG_CHUNK_GAP 3 +/* Has to be called with lock held */ +static int z3fold_compact_page(struct z3fold_header *zhdr) +{ + struct page *page = virt_to_page(zhdr); + + if (test_bit(MIDDLE_CHUNK_MAPPED, &page->private)) + return 0; /* can't move middle chunk, it's used */ + + if (unlikely(PageIsolated(page))) + return 0; + + if (zhdr->middle_chunks == 0) + return 0; /* nothing to compact */ + + if (zhdr->first_chunks == 0 && zhdr->last_chunks == 0) { + /* move to the beginning */ + mchunk_memmove(zhdr, ZHDR_CHUNKS); + zhdr->first_chunks = zhdr->middle_chunks; + zhdr->middle_chunks = 0; + zhdr->start_middle = 0; + zhdr->first_num++; + return 1; + } + + /* + * moving data is expensive, so let's only do that if + * there's substantial gain (at least BIG_CHUNK_GAP chunks) + */ + if (zhdr->first_chunks != 0 && zhdr->last_chunks == 0 && + zhdr->start_middle - (zhdr->first_chunks + ZHDR_CHUNKS) >= + BIG_CHUNK_GAP) { + mchunk_memmove(zhdr, zhdr->first_chunks + ZHDR_CHUNKS); + zhdr->start_middle = zhdr->first_chunks + ZHDR_CHUNKS; + return 1; + } else if (zhdr->last_chunks != 0 && zhdr->first_chunks == 0 && + TOTAL_CHUNKS - (zhdr->last_chunks + zhdr->start_middle + + zhdr->middle_chunks) >= + BIG_CHUNK_GAP) { + unsigned short new_start = TOTAL_CHUNKS - zhdr->last_chunks - + zhdr->middle_chunks; + mchunk_memmove(zhdr, new_start); + zhdr->start_middle = new_start; + return 1; + } + + return 0; +} + +static void do_compact_page(struct z3fold_header *zhdr, bool locked) +{ + struct z3fold_pool *pool = zhdr_to_pool(zhdr); + struct page *page; + + page = virt_to_page(zhdr); + if (locked) + WARN_ON(z3fold_page_trylock(zhdr)); + else + z3fold_page_lock(zhdr); + if (WARN_ON(!test_and_clear_bit(NEEDS_COMPACTING, &page->private))) { + z3fold_page_unlock(zhdr); + return; + } + spin_lock(&pool->lock); + list_del_init(&zhdr->buddy); + spin_unlock(&pool->lock); + + if (kref_put(&zhdr->refcount, release_z3fold_page_locked)) { + atomic64_dec(&pool->pages_nr); + return; + } + + if (test_bit(PAGE_STALE, &page->private) || + test_and_set_bit(PAGE_CLAIMED, &page->private)) { + z3fold_page_unlock(zhdr); + return; + } + + if (!zhdr->foreign_handles && buddy_single(zhdr) && + zhdr->mapped_count == 0 && compact_single_buddy(zhdr)) { + if (kref_put(&zhdr->refcount, release_z3fold_page_locked)) + atomic64_dec(&pool->pages_nr); + else { + clear_bit(PAGE_CLAIMED, &page->private); + z3fold_page_unlock(zhdr); + } + return; + } + + z3fold_compact_page(zhdr); + add_to_unbuddied(pool, zhdr); + clear_bit(PAGE_CLAIMED, &page->private); + z3fold_page_unlock(zhdr); +} + +static void compact_page_work(struct work_struct *w) +{ + struct z3fold_header *zhdr = container_of(w, struct z3fold_header, + work); + + do_compact_page(zhdr, false); +} + +/* returns _locked_ z3fold page header or NULL */ +static inline struct z3fold_header *__z3fold_alloc(struct z3fold_pool *pool, + size_t size, bool can_sleep) +{ + struct z3fold_header *zhdr = NULL; + struct page *page; + struct list_head *unbuddied; + int chunks = size_to_chunks(size), i; + +lookup: + /* First, try to find an unbuddied z3fold page. */ + unbuddied = get_cpu_ptr(pool->unbuddied); + for_each_unbuddied_list(i, chunks) { + struct list_head *l = &unbuddied[i]; + + zhdr = list_first_entry_or_null(READ_ONCE(l), + struct z3fold_header, buddy); + + if (!zhdr) + continue; + + /* Re-check under lock. */ + spin_lock(&pool->lock); + l = &unbuddied[i]; + if (unlikely(zhdr != list_first_entry(READ_ONCE(l), + struct z3fold_header, buddy)) || + !z3fold_page_trylock(zhdr)) { + spin_unlock(&pool->lock); + zhdr = NULL; + put_cpu_ptr(pool->unbuddied); + if (can_sleep) + cond_resched(); + goto lookup; + } + list_del_init(&zhdr->buddy); + zhdr->cpu = -1; + spin_unlock(&pool->lock); + + page = virt_to_page(zhdr); + if (test_bit(NEEDS_COMPACTING, &page->private) || + test_bit(PAGE_CLAIMED, &page->private)) { + z3fold_page_unlock(zhdr); + zhdr = NULL; + put_cpu_ptr(pool->unbuddied); + if (can_sleep) + cond_resched(); + goto lookup; + } + + /* + * this page could not be removed from its unbuddied + * list while pool lock was held, and then we've taken + * page lock so kref_put could not be called before + * we got here, so it's safe to just call kref_get() + */ + kref_get(&zhdr->refcount); + break; + } + put_cpu_ptr(pool->unbuddied); + + if (!zhdr) { + int cpu; + + /* look for _exact_ match on other cpus' lists */ + for_each_online_cpu(cpu) { + struct list_head *l; + + unbuddied = per_cpu_ptr(pool->unbuddied, cpu); + spin_lock(&pool->lock); + l = &unbuddied[chunks]; + + zhdr = list_first_entry_or_null(READ_ONCE(l), + struct z3fold_header, buddy); + + if (!zhdr || !z3fold_page_trylock(zhdr)) { + spin_unlock(&pool->lock); + zhdr = NULL; + continue; + } + list_del_init(&zhdr->buddy); + zhdr->cpu = -1; + spin_unlock(&pool->lock); + + page = virt_to_page(zhdr); + if (test_bit(NEEDS_COMPACTING, &page->private) || + test_bit(PAGE_CLAIMED, &page->private)) { + z3fold_page_unlock(zhdr); + zhdr = NULL; + if (can_sleep) + cond_resched(); + continue; + } + kref_get(&zhdr->refcount); + break; + } + } + + if (zhdr && !zhdr->slots) + zhdr->slots = alloc_slots(pool, + can_sleep ? GFP_NOIO : GFP_ATOMIC); + return zhdr; +} + +/* + * API Functions + */ + +/** + * z3fold_create_pool() - create a new z3fold pool + * @name: pool name + * @gfp: gfp flags when allocating the z3fold pool structure + * @ops: user-defined operations for the z3fold pool + * + * Return: pointer to the new z3fold pool or NULL if the metadata allocation + * failed. + */ +static struct z3fold_pool *z3fold_create_pool(const char *name, gfp_t gfp, + const struct z3fold_ops *ops) +{ + struct z3fold_pool *pool = NULL; + int i, cpu; + + pool = kzalloc(sizeof(struct z3fold_pool), gfp); + if (!pool) + goto out; + pool->c_handle = kmem_cache_create("z3fold_handle", + sizeof(struct z3fold_buddy_slots), + SLOTS_ALIGN, 0, NULL); + if (!pool->c_handle) + goto out_c; + spin_lock_init(&pool->lock); + spin_lock_init(&pool->stale_lock); + pool->unbuddied = __alloc_percpu(sizeof(struct list_head)*NCHUNKS, 2); + if (!pool->unbuddied) + goto out_pool; + for_each_possible_cpu(cpu) { + struct list_head *unbuddied = + per_cpu_ptr(pool->unbuddied, cpu); + for_each_unbuddied_list(i, 0) + INIT_LIST_HEAD(&unbuddied[i]); + } + INIT_LIST_HEAD(&pool->lru); + INIT_LIST_HEAD(&pool->stale); + atomic64_set(&pool->pages_nr, 0); + pool->name = name; + pool->compact_wq = create_singlethread_workqueue(pool->name); + if (!pool->compact_wq) + goto out_unbuddied; + pool->release_wq = create_singlethread_workqueue(pool->name); + if (!pool->release_wq) + goto out_wq; + if (z3fold_register_migration(pool)) + goto out_rwq; + INIT_WORK(&pool->work, free_pages_work); + pool->ops = ops; + return pool; + +out_rwq: + destroy_workqueue(pool->release_wq); +out_wq: + destroy_workqueue(pool->compact_wq); +out_unbuddied: + free_percpu(pool->unbuddied); +out_pool: + kmem_cache_destroy(pool->c_handle); +out_c: + kfree(pool); +out: + return NULL; +} + +/** + * z3fold_destroy_pool() - destroys an existing z3fold pool + * @pool: the z3fold pool to be destroyed + * + * The pool should be emptied before this function is called. + */ +static void z3fold_destroy_pool(struct z3fold_pool *pool) +{ + kmem_cache_destroy(pool->c_handle); + + /* + * We need to destroy pool->compact_wq before pool->release_wq, + * as any pending work on pool->compact_wq will call + * queue_work(pool->release_wq, &pool->work). + * + * There are still outstanding pages until both workqueues are drained, + * so we cannot unregister migration until then. + */ + + destroy_workqueue(pool->compact_wq); + destroy_workqueue(pool->release_wq); + z3fold_unregister_migration(pool); + free_percpu(pool->unbuddied); + kfree(pool); +} + +/** + * z3fold_alloc() - allocates a region of a given size + * @pool: z3fold pool from which to allocate + * @size: size in bytes of the desired allocation + * @gfp: gfp flags used if the pool needs to grow + * @handle: handle of the new allocation + * + * This function will attempt to find a free region in the pool large enough to + * satisfy the allocation request. A search of the unbuddied lists is + * performed first. If no suitable free region is found, then a new page is + * allocated and added to the pool to satisfy the request. + * + * gfp should not set __GFP_HIGHMEM as highmem pages cannot be used + * as z3fold pool pages. + * + * Return: 0 if success and handle is set, otherwise -EINVAL if the size or + * gfp arguments are invalid or -ENOMEM if the pool was unable to allocate + * a new page. + */ +static int z3fold_alloc(struct z3fold_pool *pool, size_t size, gfp_t gfp, + unsigned long *handle) +{ + int chunks = size_to_chunks(size); + struct z3fold_header *zhdr = NULL; + struct page *page = NULL; + enum buddy bud; + bool can_sleep = gfpflags_allow_blocking(gfp); + + if (!size) + return -EINVAL; + + if (size > PAGE_SIZE) + return -ENOSPC; + + if (size > PAGE_SIZE - ZHDR_SIZE_ALIGNED - CHUNK_SIZE) + bud = HEADLESS; + else { +retry: + zhdr = __z3fold_alloc(pool, size, can_sleep); + if (zhdr) { + bud = get_free_buddy(zhdr, chunks); + if (bud == HEADLESS) { + if (kref_put(&zhdr->refcount, + release_z3fold_page_locked)) + atomic64_dec(&pool->pages_nr); + else + z3fold_page_unlock(zhdr); + pr_err("No free chunks in unbuddied\n"); + WARN_ON(1); + goto retry; + } + page = virt_to_page(zhdr); + goto found; + } + bud = FIRST; + } + + page = NULL; + if (can_sleep) { + spin_lock(&pool->stale_lock); + zhdr = list_first_entry_or_null(&pool->stale, + struct z3fold_header, buddy); + /* + * Before allocating a page, let's see if we can take one from + * the stale pages list. cancel_work_sync() can sleep so we + * limit this case to the contexts where we can sleep + */ + if (zhdr) { + list_del(&zhdr->buddy); + spin_unlock(&pool->stale_lock); + cancel_work_sync(&zhdr->work); + page = virt_to_page(zhdr); + } else { + spin_unlock(&pool->stale_lock); + } + } + if (!page) + page = alloc_page(gfp); + + if (!page) + return -ENOMEM; + + zhdr = init_z3fold_page(page, bud == HEADLESS, pool, gfp); + if (!zhdr) { + __free_page(page); + return -ENOMEM; + } + atomic64_inc(&pool->pages_nr); + + if (bud == HEADLESS) { + set_bit(PAGE_HEADLESS, &page->private); + goto headless; + } + if (can_sleep) { + lock_page(page); + __SetPageMovable(page, pool->inode->i_mapping); + unlock_page(page); + } else { + if (trylock_page(page)) { + __SetPageMovable(page, pool->inode->i_mapping); + unlock_page(page); + } + } + z3fold_page_lock(zhdr); + +found: + if (bud == FIRST) + zhdr->first_chunks = chunks; + else if (bud == LAST) + zhdr->last_chunks = chunks; + else { + zhdr->middle_chunks = chunks; + zhdr->start_middle = zhdr->first_chunks + ZHDR_CHUNKS; + } + add_to_unbuddied(pool, zhdr); + +headless: + spin_lock(&pool->lock); + /* Add/move z3fold page to beginning of LRU */ + if (!list_empty(&page->lru)) + list_del(&page->lru); + + list_add(&page->lru, &pool->lru); + + *handle = encode_handle(zhdr, bud); + spin_unlock(&pool->lock); + if (bud != HEADLESS) + z3fold_page_unlock(zhdr); + + return 0; +} + +/** + * z3fold_free() - frees the allocation associated with the given handle + * @pool: pool in which the allocation resided + * @handle: handle associated with the allocation returned by z3fold_alloc() + * + * In the case that the z3fold page in which the allocation resides is under + * reclaim, as indicated by the PG_reclaim flag being set, this function + * only sets the first|last_chunks to 0. The page is actually freed + * once both buddies are evicted (see z3fold_reclaim_page() below). + */ +static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) +{ + struct z3fold_header *zhdr; + struct page *page; + enum buddy bud; + bool page_claimed; + + zhdr = get_z3fold_header(handle); + page = virt_to_page(zhdr); + page_claimed = test_and_set_bit(PAGE_CLAIMED, &page->private); + + if (test_bit(PAGE_HEADLESS, &page->private)) { + /* if a headless page is under reclaim, just leave. + * NB: we use test_and_set_bit for a reason: if the bit + * has not been set before, we release this page + * immediately so we don't care about its value any more. + */ + if (!page_claimed) { + spin_lock(&pool->lock); + list_del(&page->lru); + spin_unlock(&pool->lock); + put_z3fold_header(zhdr); + free_z3fold_page(page, true); + atomic64_dec(&pool->pages_nr); + } + return; + } + + /* Non-headless case */ + bud = handle_to_buddy(handle); + + switch (bud) { + case FIRST: + zhdr->first_chunks = 0; + break; + case MIDDLE: + zhdr->middle_chunks = 0; + break; + case LAST: + zhdr->last_chunks = 0; + break; + default: + pr_err("%s: unknown bud %d\n", __func__, bud); + WARN_ON(1); + put_z3fold_header(zhdr); + return; + } + + if (!page_claimed) + free_handle(handle, zhdr); + if (kref_put(&zhdr->refcount, release_z3fold_page_locked_list)) { + atomic64_dec(&pool->pages_nr); + return; + } + if (page_claimed) { + /* the page has not been claimed by us */ + z3fold_page_unlock(zhdr); + return; + } + if (test_and_set_bit(NEEDS_COMPACTING, &page->private)) { + put_z3fold_header(zhdr); + clear_bit(PAGE_CLAIMED, &page->private); + return; + } + if (zhdr->cpu < 0 || !cpu_online(zhdr->cpu)) { + spin_lock(&pool->lock); + list_del_init(&zhdr->buddy); + spin_unlock(&pool->lock); + zhdr->cpu = -1; + kref_get(&zhdr->refcount); + clear_bit(PAGE_CLAIMED, &page->private); + do_compact_page(zhdr, true); + return; + } + kref_get(&zhdr->refcount); + clear_bit(PAGE_CLAIMED, &page->private); + queue_work_on(zhdr->cpu, pool->compact_wq, &zhdr->work); + put_z3fold_header(zhdr); +} + +/** + * z3fold_reclaim_page() - evicts allocations from a pool page and frees it + * @pool: pool from which a page will attempt to be evicted + * @retries: number of pages on the LRU list for which eviction will + * be attempted before failing + * + * z3fold reclaim is different from normal system reclaim in that it is done + * from the bottom, up. This is because only the bottom layer, z3fold, has + * information on how the allocations are organized within each z3fold page. + * This has the potential to create interesting locking situations between + * z3fold and the user, however. + * + * To avoid these, this is how z3fold_reclaim_page() should be called: + * + * The user detects a page should be reclaimed and calls z3fold_reclaim_page(). + * z3fold_reclaim_page() will remove a z3fold page from the pool LRU list and + * call the user-defined eviction handler with the pool and handle as + * arguments. + * + * If the handle can not be evicted, the eviction handler should return + * non-zero. z3fold_reclaim_page() will add the z3fold page back to the + * appropriate list and try the next z3fold page on the LRU up to + * a user defined number of retries. + * + * If the handle is successfully evicted, the eviction handler should + * return 0 _and_ should have called z3fold_free() on the handle. z3fold_free() + * contains logic to delay freeing the page if the page is under reclaim, + * as indicated by the setting of the PG_reclaim flag on the underlying page. + * + * If all buddies in the z3fold page are successfully evicted, then the + * z3fold page can be freed. + * + * Returns: 0 if page is successfully freed, otherwise -EINVAL if there are + * no pages to evict or an eviction handler is not registered, -EAGAIN if + * the retry limit was hit. + */ +static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries) +{ + int i, ret = -1; + struct z3fold_header *zhdr = NULL; + struct page *page = NULL; + struct list_head *pos; + unsigned long first_handle = 0, middle_handle = 0, last_handle = 0; + struct z3fold_buddy_slots slots __attribute__((aligned(SLOTS_ALIGN))); + + rwlock_init(&slots.lock); + slots.pool = (unsigned long)pool | (1 << HANDLES_NOFREE); + + spin_lock(&pool->lock); + if (!pool->ops || !pool->ops->evict || retries == 0) { + spin_unlock(&pool->lock); + return -EINVAL; + } + for (i = 0; i < retries; i++) { + if (list_empty(&pool->lru)) { + spin_unlock(&pool->lock); + return -EINVAL; + } + list_for_each_prev(pos, &pool->lru) { + page = list_entry(pos, struct page, lru); + + zhdr = page_address(page); + if (test_bit(PAGE_HEADLESS, &page->private)) { + /* + * For non-headless pages, we wait to do this + * until we have the page lock to avoid racing + * with __z3fold_alloc(). Headless pages don't + * have a lock (and __z3fold_alloc() will never + * see them), but we still need to test and set + * PAGE_CLAIMED to avoid racing with + * z3fold_free(), so just do it now before + * leaving the loop. + */ + if (test_and_set_bit(PAGE_CLAIMED, &page->private)) + continue; + + break; + } + + if (kref_get_unless_zero(&zhdr->refcount) == 0) { + zhdr = NULL; + break; + } + if (!z3fold_page_trylock(zhdr)) { + if (kref_put(&zhdr->refcount, + release_z3fold_page)) + atomic64_dec(&pool->pages_nr); + zhdr = NULL; + continue; /* can't evict at this point */ + } + + /* test_and_set_bit is of course atomic, but we still + * need to do it under page lock, otherwise checking + * that bit in __z3fold_alloc wouldn't make sense + */ + if (zhdr->foreign_handles || + test_and_set_bit(PAGE_CLAIMED, &page->private)) { + if (kref_put(&zhdr->refcount, + release_z3fold_page_locked)) + atomic64_dec(&pool->pages_nr); + else + z3fold_page_unlock(zhdr); + zhdr = NULL; + continue; /* can't evict such page */ + } + list_del_init(&zhdr->buddy); + zhdr->cpu = -1; + break; + } + + if (!zhdr) + break; + + list_del_init(&page->lru); + spin_unlock(&pool->lock); + + if (!test_bit(PAGE_HEADLESS, &page->private)) { + /* + * We need encode the handles before unlocking, and + * use our local slots structure because z3fold_free + * can zero out zhdr->slots and we can't do much + * about that + */ + first_handle = 0; + last_handle = 0; + middle_handle = 0; + memset(slots.slot, 0, sizeof(slots.slot)); + if (zhdr->first_chunks) + first_handle = __encode_handle(zhdr, &slots, + FIRST); + if (zhdr->middle_chunks) + middle_handle = __encode_handle(zhdr, &slots, + MIDDLE); + if (zhdr->last_chunks) + last_handle = __encode_handle(zhdr, &slots, + LAST); + /* + * it's safe to unlock here because we hold a + * reference to this page + */ + z3fold_page_unlock(zhdr); + } else { + first_handle = encode_handle(zhdr, HEADLESS); + last_handle = middle_handle = 0; + } + /* Issue the eviction callback(s) */ + if (middle_handle) { + ret = pool->ops->evict(pool, middle_handle); + if (ret) + goto next; + } + if (first_handle) { + ret = pool->ops->evict(pool, first_handle); + if (ret) + goto next; + } + if (last_handle) { + ret = pool->ops->evict(pool, last_handle); + if (ret) + goto next; + } +next: + if (test_bit(PAGE_HEADLESS, &page->private)) { + if (ret == 0) { + free_z3fold_page(page, true); + atomic64_dec(&pool->pages_nr); + return 0; + } + spin_lock(&pool->lock); + list_add(&page->lru, &pool->lru); + spin_unlock(&pool->lock); + clear_bit(PAGE_CLAIMED, &page->private); + } else { + struct z3fold_buddy_slots *slots = zhdr->slots; + z3fold_page_lock(zhdr); + if (kref_put(&zhdr->refcount, + release_z3fold_page_locked)) { + kmem_cache_free(pool->c_handle, slots); + atomic64_dec(&pool->pages_nr); + return 0; + } + /* + * if we are here, the page is still not completely + * free. Take the global pool lock then to be able + * to add it back to the lru list + */ + spin_lock(&pool->lock); + list_add(&page->lru, &pool->lru); + spin_unlock(&pool->lock); + z3fold_page_unlock(zhdr); + clear_bit(PAGE_CLAIMED, &page->private); + } + + /* We started off locked to we need to lock the pool back */ + spin_lock(&pool->lock); + } + spin_unlock(&pool->lock); + return -EAGAIN; +} + +/** + * z3fold_map() - maps the allocation associated with the given handle + * @pool: pool in which the allocation resides + * @handle: handle associated with the allocation to be mapped + * + * Extracts the buddy number from handle and constructs the pointer to the + * correct starting chunk within the page. + * + * Returns: a pointer to the mapped allocation + */ +static void *z3fold_map(struct z3fold_pool *pool, unsigned long handle) +{ + struct z3fold_header *zhdr; + struct page *page; + void *addr; + enum buddy buddy; + + zhdr = get_z3fold_header(handle); + addr = zhdr; + page = virt_to_page(zhdr); + + if (test_bit(PAGE_HEADLESS, &page->private)) + goto out; + + buddy = handle_to_buddy(handle); + switch (buddy) { + case FIRST: + addr += ZHDR_SIZE_ALIGNED; + break; + case MIDDLE: + addr += zhdr->start_middle << CHUNK_SHIFT; + set_bit(MIDDLE_CHUNK_MAPPED, &page->private); + break; + case LAST: + addr += PAGE_SIZE - (handle_to_chunks(handle) << CHUNK_SHIFT); + break; + default: + pr_err("unknown buddy id %d\n", buddy); + WARN_ON(1); + addr = NULL; + break; + } + + if (addr) + zhdr->mapped_count++; +out: + put_z3fold_header(zhdr); + return addr; +} + +/** + * z3fold_unmap() - unmaps the allocation associated with the given handle + * @pool: pool in which the allocation resides + * @handle: handle associated with the allocation to be unmapped + */ +static void z3fold_unmap(struct z3fold_pool *pool, unsigned long handle) +{ + struct z3fold_header *zhdr; + struct page *page; + enum buddy buddy; + + zhdr = get_z3fold_header(handle); + page = virt_to_page(zhdr); + + if (test_bit(PAGE_HEADLESS, &page->private)) + return; + + buddy = handle_to_buddy(handle); + if (buddy == MIDDLE) + clear_bit(MIDDLE_CHUNK_MAPPED, &page->private); + zhdr->mapped_count--; + put_z3fold_header(zhdr); +} + +/** + * z3fold_get_pool_size() - gets the z3fold pool size in pages + * @pool: pool whose size is being queried + * + * Returns: size in pages of the given pool. + */ +static u64 z3fold_get_pool_size(struct z3fold_pool *pool) +{ + return atomic64_read(&pool->pages_nr); +} + +static bool z3fold_page_isolate(struct page *page, isolate_mode_t mode) +{ + struct z3fold_header *zhdr; + struct z3fold_pool *pool; + + VM_BUG_ON_PAGE(!PageMovable(page), page); + VM_BUG_ON_PAGE(PageIsolated(page), page); + + if (test_bit(PAGE_HEADLESS, &page->private)) + return false; + + zhdr = page_address(page); + z3fold_page_lock(zhdr); + if (test_bit(NEEDS_COMPACTING, &page->private) || + test_bit(PAGE_STALE, &page->private)) + goto out; + + if (zhdr->mapped_count != 0 || zhdr->foreign_handles != 0) + goto out; + + if (test_and_set_bit(PAGE_CLAIMED, &page->private)) + goto out; + pool = zhdr_to_pool(zhdr); + spin_lock(&pool->lock); + if (!list_empty(&zhdr->buddy)) + list_del_init(&zhdr->buddy); + if (!list_empty(&page->lru)) + list_del_init(&page->lru); + spin_unlock(&pool->lock); + + kref_get(&zhdr->refcount); + z3fold_page_unlock(zhdr); + return true; + +out: + z3fold_page_unlock(zhdr); + return false; +} + +static int z3fold_page_migrate(struct address_space *mapping, struct page *newpage, + struct page *page, enum migrate_mode mode) +{ + struct z3fold_header *zhdr, *new_zhdr; + struct z3fold_pool *pool; + struct address_space *new_mapping; + + VM_BUG_ON_PAGE(!PageMovable(page), page); + VM_BUG_ON_PAGE(!PageIsolated(page), page); + VM_BUG_ON_PAGE(!test_bit(PAGE_CLAIMED, &page->private), page); + VM_BUG_ON_PAGE(!PageLocked(newpage), newpage); + + zhdr = page_address(page); + pool = zhdr_to_pool(zhdr); + + if (!z3fold_page_trylock(zhdr)) + return -EAGAIN; + if (zhdr->mapped_count != 0 || zhdr->foreign_handles != 0) { + z3fold_page_unlock(zhdr); + clear_bit(PAGE_CLAIMED, &page->private); + return -EBUSY; + } + if (work_pending(&zhdr->work)) { + z3fold_page_unlock(zhdr); + return -EAGAIN; + } + new_zhdr = page_address(newpage); + memcpy(new_zhdr, zhdr, PAGE_SIZE); + newpage->private = page->private; + page->private = 0; + z3fold_page_unlock(zhdr); + spin_lock_init(&new_zhdr->page_lock); + INIT_WORK(&new_zhdr->work, compact_page_work); + /* + * z3fold_page_isolate() ensures that new_zhdr->buddy is empty, + * so we only have to reinitialize it. + */ + INIT_LIST_HEAD(&new_zhdr->buddy); + new_mapping = page_mapping(page); + __ClearPageMovable(page); + ClearPagePrivate(page); + + get_page(newpage); + z3fold_page_lock(new_zhdr); + if (new_zhdr->first_chunks) + encode_handle(new_zhdr, FIRST); + if (new_zhdr->last_chunks) + encode_handle(new_zhdr, LAST); + if (new_zhdr->middle_chunks) + encode_handle(new_zhdr, MIDDLE); + set_bit(NEEDS_COMPACTING, &newpage->private); + new_zhdr->cpu = smp_processor_id(); + spin_lock(&pool->lock); + list_add(&newpage->lru, &pool->lru); + spin_unlock(&pool->lock); + __SetPageMovable(newpage, new_mapping); + z3fold_page_unlock(new_zhdr); + + queue_work_on(new_zhdr->cpu, pool->compact_wq, &new_zhdr->work); + + page_mapcount_reset(page); + clear_bit(PAGE_CLAIMED, &page->private); + put_page(page); + return 0; +} + +static void z3fold_page_putback(struct page *page) +{ + struct z3fold_header *zhdr; + struct z3fold_pool *pool; + + zhdr = page_address(page); + pool = zhdr_to_pool(zhdr); + + z3fold_page_lock(zhdr); + if (!list_empty(&zhdr->buddy)) + list_del_init(&zhdr->buddy); + INIT_LIST_HEAD(&page->lru); + if (kref_put(&zhdr->refcount, release_z3fold_page_locked)) { + atomic64_dec(&pool->pages_nr); + return; + } + spin_lock(&pool->lock); + list_add(&page->lru, &pool->lru); + spin_unlock(&pool->lock); + clear_bit(PAGE_CLAIMED, &page->private); + z3fold_page_unlock(zhdr); +} + +static const struct address_space_operations z3fold_aops = { + .isolate_page = z3fold_page_isolate, + .migratepage = z3fold_page_migrate, + .putback_page = z3fold_page_putback, +}; + +/***************** + * zpool + ****************/ + +static int z3fold_zpool_evict(struct z3fold_pool *pool, unsigned long handle) +{ + if (pool->zpool && pool->zpool_ops && pool->zpool_ops->evict) + return pool->zpool_ops->evict(pool->zpool, handle); + else + return -ENOENT; +} + +static const struct z3fold_ops z3fold_zpool_ops = { + .evict = z3fold_zpool_evict +}; + +static void *z3fold_zpool_create(const char *name, gfp_t gfp, + const struct zpool_ops *zpool_ops, + struct zpool *zpool) +{ + struct z3fold_pool *pool; + + pool = z3fold_create_pool(name, gfp, + zpool_ops ? &z3fold_zpool_ops : NULL); + if (pool) { + pool->zpool = zpool; + pool->zpool_ops = zpool_ops; + } + return pool; +} + +static void z3fold_zpool_destroy(void *pool) +{ + z3fold_destroy_pool(pool); +} + +static int z3fold_zpool_malloc(void *pool, size_t size, gfp_t gfp, + unsigned long *handle) +{ + return z3fold_alloc(pool, size, gfp, handle); +} +static void z3fold_zpool_free(void *pool, unsigned long handle) +{ + z3fold_free(pool, handle); +} + +static int z3fold_zpool_shrink(void *pool, unsigned int pages, + unsigned int *reclaimed) +{ + unsigned int total = 0; + int ret = -EINVAL; + + while (total < pages) { + ret = z3fold_reclaim_page(pool, 8); + if (ret < 0) + break; + total++; + } + + if (reclaimed) + *reclaimed = total; + + return ret; +} + +static void *z3fold_zpool_map(void *pool, unsigned long handle, + enum zpool_mapmode mm) +{ + return z3fold_map(pool, handle); +} +static void z3fold_zpool_unmap(void *pool, unsigned long handle) +{ + z3fold_unmap(pool, handle); +} + +static u64 z3fold_zpool_total_size(void *pool) +{ + return z3fold_get_pool_size(pool) * PAGE_SIZE; +} + +static struct zpool_driver z3fold_zpool_driver = { + .type = "z3fold", + .owner = THIS_MODULE, + .create = z3fold_zpool_create, + .destroy = z3fold_zpool_destroy, + .malloc = z3fold_zpool_malloc, + .free = z3fold_zpool_free, + .shrink = z3fold_zpool_shrink, + .map = z3fold_zpool_map, + .unmap = z3fold_zpool_unmap, + .total_size = z3fold_zpool_total_size, +}; + +MODULE_ALIAS("zpool-z3fold"); + +static int __init init_z3fold(void) +{ + int ret; + + /* Make sure the z3fold header is not larger than the page size */ + BUILD_BUG_ON(ZHDR_SIZE_ALIGNED > PAGE_SIZE); + ret = z3fold_mount(); + if (ret) + return ret; + + zpool_register_driver(&z3fold_zpool_driver); + + return 0; +} + +static void __exit exit_z3fold(void) +{ + z3fold_unmount(); + zpool_unregister_driver(&z3fold_zpool_driver); +} + +module_init(init_z3fold); +module_exit(exit_z3fold); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Vitaly Wool "); +MODULE_DESCRIPTION("3-Fold Allocator for Compressed Pages"); diff --git a/mm/zbud.c b/mm/zbud.c new file mode 100644 index 000000000..c49966ece --- /dev/null +++ b/mm/zbud.c @@ -0,0 +1,636 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * zbud.c + * + * Copyright (C) 2013, Seth Jennings, IBM + * + * Concepts based on zcache internal zbud allocator by Dan Magenheimer. + * + * zbud is an special purpose allocator for storing compressed pages. Contrary + * to what its name may suggest, zbud is not a buddy allocator, but rather an + * allocator that "buddies" two compressed pages together in a single memory + * page. + * + * While this design limits storage density, it has simple and deterministic + * reclaim properties that make it preferable to a higher density approach when + * reclaim will be used. + * + * zbud works by storing compressed pages, or "zpages", together in pairs in a + * single memory page called a "zbud page". The first buddy is "left + * justified" at the beginning of the zbud page, and the last buddy is "right + * justified" at the end of the zbud page. The benefit is that if either + * buddy is freed, the freed buddy space, coalesced with whatever slack space + * that existed between the buddies, results in the largest possible free region + * within the zbud page. + * + * zbud also provides an attractive lower bound on density. The ratio of zpages + * to zbud pages can not be less than 1. This ensures that zbud can never "do + * harm" by using more pages to store zpages than the uncompressed zpages would + * have used on their own. + * + * zbud pages are divided into "chunks". The size of the chunks is fixed at + * compile time and determined by NCHUNKS_ORDER below. Dividing zbud pages + * into chunks allows organizing unbuddied zbud pages into a manageable number + * of unbuddied lists according to the number of free chunks available in the + * zbud page. + * + * The zbud API differs from that of conventional allocators in that the + * allocation function, zbud_alloc(), returns an opaque handle to the user, + * not a dereferenceable pointer. The user must map the handle using + * zbud_map() in order to get a usable pointer by which to access the + * allocation data and unmap the handle with zbud_unmap() when operations + * on the allocation data are complete. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/***************** + * Structures +*****************/ +/* + * NCHUNKS_ORDER determines the internal allocation granularity, effectively + * adjusting internal fragmentation. It also determines the number of + * freelists maintained in each pool. NCHUNKS_ORDER of 6 means that the + * allocation granularity will be in chunks of size PAGE_SIZE/64. As one chunk + * in allocated page is occupied by zbud header, NCHUNKS will be calculated to + * 63 which shows the max number of free chunks in zbud page, also there will be + * 63 freelists per pool. + */ +#define NCHUNKS_ORDER 6 + +#define CHUNK_SHIFT (PAGE_SHIFT - NCHUNKS_ORDER) +#define CHUNK_SIZE (1 << CHUNK_SHIFT) +#define ZHDR_SIZE_ALIGNED CHUNK_SIZE +#define NCHUNKS ((PAGE_SIZE - ZHDR_SIZE_ALIGNED) >> CHUNK_SHIFT) + +/** + * struct zbud_pool - stores metadata for each zbud pool + * @lock: protects all pool fields and first|last_chunk fields of any + * zbud page in the pool + * @unbuddied: array of lists tracking zbud pages that only contain one buddy; + * the lists each zbud page is added to depends on the size of + * its free region. + * @buddied: list tracking the zbud pages that contain two buddies; + * these zbud pages are full + * @lru: list tracking the zbud pages in LRU order by most recently + * added buddy. + * @pages_nr: number of zbud pages in the pool. + * @ops: pointer to a structure of user defined operations specified at + * pool creation time. + * + * This structure is allocated at pool creation time and maintains metadata + * pertaining to a particular zbud pool. + */ +struct zbud_pool { + spinlock_t lock; + struct list_head unbuddied[NCHUNKS]; + struct list_head buddied; + struct list_head lru; + u64 pages_nr; + const struct zbud_ops *ops; +#ifdef CONFIG_ZPOOL + struct zpool *zpool; + const struct zpool_ops *zpool_ops; +#endif +}; + +/* + * struct zbud_header - zbud page metadata occupying the first chunk of each + * zbud page. + * @buddy: links the zbud page into the unbuddied/buddied lists in the pool + * @lru: links the zbud page into the lru list in the pool + * @first_chunks: the size of the first buddy in chunks, 0 if free + * @last_chunks: the size of the last buddy in chunks, 0 if free + */ +struct zbud_header { + struct list_head buddy; + struct list_head lru; + unsigned int first_chunks; + unsigned int last_chunks; + bool under_reclaim; +}; + +/***************** + * zpool + ****************/ + +#ifdef CONFIG_ZPOOL + +static int zbud_zpool_evict(struct zbud_pool *pool, unsigned long handle) +{ + if (pool->zpool && pool->zpool_ops && pool->zpool_ops->evict) + return pool->zpool_ops->evict(pool->zpool, handle); + else + return -ENOENT; +} + +static const struct zbud_ops zbud_zpool_ops = { + .evict = zbud_zpool_evict +}; + +static void *zbud_zpool_create(const char *name, gfp_t gfp, + const struct zpool_ops *zpool_ops, + struct zpool *zpool) +{ + struct zbud_pool *pool; + + pool = zbud_create_pool(gfp, zpool_ops ? &zbud_zpool_ops : NULL); + if (pool) { + pool->zpool = zpool; + pool->zpool_ops = zpool_ops; + } + return pool; +} + +static void zbud_zpool_destroy(void *pool) +{ + zbud_destroy_pool(pool); +} + +static int zbud_zpool_malloc(void *pool, size_t size, gfp_t gfp, + unsigned long *handle) +{ + return zbud_alloc(pool, size, gfp, handle); +} +static void zbud_zpool_free(void *pool, unsigned long handle) +{ + zbud_free(pool, handle); +} + +static int zbud_zpool_shrink(void *pool, unsigned int pages, + unsigned int *reclaimed) +{ + unsigned int total = 0; + int ret = -EINVAL; + + while (total < pages) { + ret = zbud_reclaim_page(pool, 8); + if (ret < 0) + break; + total++; + } + + if (reclaimed) + *reclaimed = total; + + return ret; +} + +static void *zbud_zpool_map(void *pool, unsigned long handle, + enum zpool_mapmode mm) +{ + return zbud_map(pool, handle); +} +static void zbud_zpool_unmap(void *pool, unsigned long handle) +{ + zbud_unmap(pool, handle); +} + +static u64 zbud_zpool_total_size(void *pool) +{ + return zbud_get_pool_size(pool) * PAGE_SIZE; +} + +static struct zpool_driver zbud_zpool_driver = { + .type = "zbud", + .owner = THIS_MODULE, + .create = zbud_zpool_create, + .destroy = zbud_zpool_destroy, + .malloc = zbud_zpool_malloc, + .free = zbud_zpool_free, + .shrink = zbud_zpool_shrink, + .map = zbud_zpool_map, + .unmap = zbud_zpool_unmap, + .total_size = zbud_zpool_total_size, +}; + +MODULE_ALIAS("zpool-zbud"); +#endif /* CONFIG_ZPOOL */ + +/***************** + * Helpers +*****************/ +/* Just to make the code easier to read */ +enum buddy { + FIRST, + LAST +}; + +/* Converts an allocation size in bytes to size in zbud chunks */ +static int size_to_chunks(size_t size) +{ + return (size + CHUNK_SIZE - 1) >> CHUNK_SHIFT; +} + +#define for_each_unbuddied_list(_iter, _begin) \ + for ((_iter) = (_begin); (_iter) < NCHUNKS; (_iter)++) + +/* Initializes the zbud header of a newly allocated zbud page */ +static struct zbud_header *init_zbud_page(struct page *page) +{ + struct zbud_header *zhdr = page_address(page); + zhdr->first_chunks = 0; + zhdr->last_chunks = 0; + INIT_LIST_HEAD(&zhdr->buddy); + INIT_LIST_HEAD(&zhdr->lru); + zhdr->under_reclaim = false; + return zhdr; +} + +/* Resets the struct page fields and frees the page */ +static void free_zbud_page(struct zbud_header *zhdr) +{ + __free_page(virt_to_page(zhdr)); +} + +/* + * Encodes the handle of a particular buddy within a zbud page + * Pool lock should be held as this function accesses first|last_chunks + */ +static unsigned long encode_handle(struct zbud_header *zhdr, enum buddy bud) +{ + unsigned long handle; + + /* + * For now, the encoded handle is actually just the pointer to the data + * but this might not always be the case. A little information hiding. + * Add CHUNK_SIZE to the handle if it is the first allocation to jump + * over the zbud header in the first chunk. + */ + handle = (unsigned long)zhdr; + if (bud == FIRST) + /* skip over zbud header */ + handle += ZHDR_SIZE_ALIGNED; + else /* bud == LAST */ + handle += PAGE_SIZE - (zhdr->last_chunks << CHUNK_SHIFT); + return handle; +} + +/* Returns the zbud page where a given handle is stored */ +static struct zbud_header *handle_to_zbud_header(unsigned long handle) +{ + return (struct zbud_header *)(handle & PAGE_MASK); +} + +/* Returns the number of free chunks in a zbud page */ +static int num_free_chunks(struct zbud_header *zhdr) +{ + /* + * Rather than branch for different situations, just use the fact that + * free buddies have a length of zero to simplify everything. + */ + return NCHUNKS - zhdr->first_chunks - zhdr->last_chunks; +} + +/***************** + * API Functions +*****************/ +/** + * zbud_create_pool() - create a new zbud pool + * @gfp: gfp flags when allocating the zbud pool structure + * @ops: user-defined operations for the zbud pool + * + * Return: pointer to the new zbud pool or NULL if the metadata allocation + * failed. + */ +struct zbud_pool *zbud_create_pool(gfp_t gfp, const struct zbud_ops *ops) +{ + struct zbud_pool *pool; + int i; + + pool = kzalloc(sizeof(struct zbud_pool), gfp); + if (!pool) + return NULL; + spin_lock_init(&pool->lock); + for_each_unbuddied_list(i, 0) + INIT_LIST_HEAD(&pool->unbuddied[i]); + INIT_LIST_HEAD(&pool->buddied); + INIT_LIST_HEAD(&pool->lru); + pool->pages_nr = 0; + pool->ops = ops; + return pool; +} + +/** + * zbud_destroy_pool() - destroys an existing zbud pool + * @pool: the zbud pool to be destroyed + * + * The pool should be emptied before this function is called. + */ +void zbud_destroy_pool(struct zbud_pool *pool) +{ + kfree(pool); +} + +/** + * zbud_alloc() - allocates a region of a given size + * @pool: zbud pool from which to allocate + * @size: size in bytes of the desired allocation + * @gfp: gfp flags used if the pool needs to grow + * @handle: handle of the new allocation + * + * This function will attempt to find a free region in the pool large enough to + * satisfy the allocation request. A search of the unbuddied lists is + * performed first. If no suitable free region is found, then a new page is + * allocated and added to the pool to satisfy the request. + * + * gfp should not set __GFP_HIGHMEM as highmem pages cannot be used + * as zbud pool pages. + * + * Return: 0 if success and handle is set, otherwise -EINVAL if the size or + * gfp arguments are invalid or -ENOMEM if the pool was unable to allocate + * a new page. + */ +int zbud_alloc(struct zbud_pool *pool, size_t size, gfp_t gfp, + unsigned long *handle) +{ + int chunks, i, freechunks; + struct zbud_header *zhdr = NULL; + enum buddy bud; + struct page *page; + + if (!size || (gfp & __GFP_HIGHMEM)) + return -EINVAL; + if (size > PAGE_SIZE - ZHDR_SIZE_ALIGNED - CHUNK_SIZE) + return -ENOSPC; + chunks = size_to_chunks(size); + spin_lock(&pool->lock); + + /* First, try to find an unbuddied zbud page. */ + for_each_unbuddied_list(i, chunks) { + if (!list_empty(&pool->unbuddied[i])) { + zhdr = list_first_entry(&pool->unbuddied[i], + struct zbud_header, buddy); + list_del(&zhdr->buddy); + if (zhdr->first_chunks == 0) + bud = FIRST; + else + bud = LAST; + goto found; + } + } + + /* Couldn't find unbuddied zbud page, create new one */ + spin_unlock(&pool->lock); + page = alloc_page(gfp); + if (!page) + return -ENOMEM; + spin_lock(&pool->lock); + pool->pages_nr++; + zhdr = init_zbud_page(page); + bud = FIRST; + +found: + if (bud == FIRST) + zhdr->first_chunks = chunks; + else + zhdr->last_chunks = chunks; + + if (zhdr->first_chunks == 0 || zhdr->last_chunks == 0) { + /* Add to unbuddied list */ + freechunks = num_free_chunks(zhdr); + list_add(&zhdr->buddy, &pool->unbuddied[freechunks]); + } else { + /* Add to buddied list */ + list_add(&zhdr->buddy, &pool->buddied); + } + + /* Add/move zbud page to beginning of LRU */ + if (!list_empty(&zhdr->lru)) + list_del(&zhdr->lru); + list_add(&zhdr->lru, &pool->lru); + + *handle = encode_handle(zhdr, bud); + spin_unlock(&pool->lock); + + return 0; +} + +/** + * zbud_free() - frees the allocation associated with the given handle + * @pool: pool in which the allocation resided + * @handle: handle associated with the allocation returned by zbud_alloc() + * + * In the case that the zbud page in which the allocation resides is under + * reclaim, as indicated by the PG_reclaim flag being set, this function + * only sets the first|last_chunks to 0. The page is actually freed + * once both buddies are evicted (see zbud_reclaim_page() below). + */ +void zbud_free(struct zbud_pool *pool, unsigned long handle) +{ + struct zbud_header *zhdr; + int freechunks; + + spin_lock(&pool->lock); + zhdr = handle_to_zbud_header(handle); + + /* If first buddy, handle will be page aligned */ + if ((handle - ZHDR_SIZE_ALIGNED) & ~PAGE_MASK) + zhdr->last_chunks = 0; + else + zhdr->first_chunks = 0; + + if (zhdr->under_reclaim) { + /* zbud page is under reclaim, reclaim will free */ + spin_unlock(&pool->lock); + return; + } + + /* Remove from existing buddy list */ + list_del(&zhdr->buddy); + + if (zhdr->first_chunks == 0 && zhdr->last_chunks == 0) { + /* zbud page is empty, free */ + list_del(&zhdr->lru); + free_zbud_page(zhdr); + pool->pages_nr--; + } else { + /* Add to unbuddied list */ + freechunks = num_free_chunks(zhdr); + list_add(&zhdr->buddy, &pool->unbuddied[freechunks]); + } + + spin_unlock(&pool->lock); +} + +/** + * zbud_reclaim_page() - evicts allocations from a pool page and frees it + * @pool: pool from which a page will attempt to be evicted + * @retries: number of pages on the LRU list for which eviction will + * be attempted before failing + * + * zbud reclaim is different from normal system reclaim in that the reclaim is + * done from the bottom, up. This is because only the bottom layer, zbud, has + * information on how the allocations are organized within each zbud page. This + * has the potential to create interesting locking situations between zbud and + * the user, however. + * + * To avoid these, this is how zbud_reclaim_page() should be called: + * + * The user detects a page should be reclaimed and calls zbud_reclaim_page(). + * zbud_reclaim_page() will remove a zbud page from the pool LRU list and call + * the user-defined eviction handler with the pool and handle as arguments. + * + * If the handle can not be evicted, the eviction handler should return + * non-zero. zbud_reclaim_page() will add the zbud page back to the + * appropriate list and try the next zbud page on the LRU up to + * a user defined number of retries. + * + * If the handle is successfully evicted, the eviction handler should + * return 0 _and_ should have called zbud_free() on the handle. zbud_free() + * contains logic to delay freeing the page if the page is under reclaim, + * as indicated by the setting of the PG_reclaim flag on the underlying page. + * + * If all buddies in the zbud page are successfully evicted, then the + * zbud page can be freed. + * + * Returns: 0 if page is successfully freed, otherwise -EINVAL if there are + * no pages to evict or an eviction handler is not registered, -EAGAIN if + * the retry limit was hit. + */ +int zbud_reclaim_page(struct zbud_pool *pool, unsigned int retries) +{ + int i, ret, freechunks; + struct zbud_header *zhdr; + unsigned long first_handle = 0, last_handle = 0; + + spin_lock(&pool->lock); + if (!pool->ops || !pool->ops->evict || list_empty(&pool->lru) || + retries == 0) { + spin_unlock(&pool->lock); + return -EINVAL; + } + for (i = 0; i < retries; i++) { + zhdr = list_last_entry(&pool->lru, struct zbud_header, lru); + list_del(&zhdr->lru); + list_del(&zhdr->buddy); + /* Protect zbud page against free */ + zhdr->under_reclaim = true; + /* + * We need encode the handles before unlocking, since we can + * race with free that will set (first|last)_chunks to 0 + */ + first_handle = 0; + last_handle = 0; + if (zhdr->first_chunks) + first_handle = encode_handle(zhdr, FIRST); + if (zhdr->last_chunks) + last_handle = encode_handle(zhdr, LAST); + spin_unlock(&pool->lock); + + /* Issue the eviction callback(s) */ + if (first_handle) { + ret = pool->ops->evict(pool, first_handle); + if (ret) + goto next; + } + if (last_handle) { + ret = pool->ops->evict(pool, last_handle); + if (ret) + goto next; + } +next: + spin_lock(&pool->lock); + zhdr->under_reclaim = false; + if (zhdr->first_chunks == 0 && zhdr->last_chunks == 0) { + /* + * Both buddies are now free, free the zbud page and + * return success. + */ + free_zbud_page(zhdr); + pool->pages_nr--; + spin_unlock(&pool->lock); + return 0; + } else if (zhdr->first_chunks == 0 || + zhdr->last_chunks == 0) { + /* add to unbuddied list */ + freechunks = num_free_chunks(zhdr); + list_add(&zhdr->buddy, &pool->unbuddied[freechunks]); + } else { + /* add to buddied list */ + list_add(&zhdr->buddy, &pool->buddied); + } + + /* add to beginning of LRU */ + list_add(&zhdr->lru, &pool->lru); + } + spin_unlock(&pool->lock); + return -EAGAIN; +} + +/** + * zbud_map() - maps the allocation associated with the given handle + * @pool: pool in which the allocation resides + * @handle: handle associated with the allocation to be mapped + * + * While trivial for zbud, the mapping functions for others allocators + * implementing this allocation API could have more complex information encoded + * in the handle and could create temporary mappings to make the data + * accessible to the user. + * + * Returns: a pointer to the mapped allocation + */ +void *zbud_map(struct zbud_pool *pool, unsigned long handle) +{ + return (void *)(handle); +} + +/** + * zbud_unmap() - maps the allocation associated with the given handle + * @pool: pool in which the allocation resides + * @handle: handle associated with the allocation to be unmapped + */ +void zbud_unmap(struct zbud_pool *pool, unsigned long handle) +{ +} + +/** + * zbud_get_pool_size() - gets the zbud pool size in pages + * @pool: pool whose size is being queried + * + * Returns: size in pages of the given pool. The pool lock need not be + * taken to access pages_nr. + */ +u64 zbud_get_pool_size(struct zbud_pool *pool) +{ + return pool->pages_nr; +} + +static int __init init_zbud(void) +{ + /* Make sure the zbud header will fit in one chunk */ + BUILD_BUG_ON(sizeof(struct zbud_header) > ZHDR_SIZE_ALIGNED); + pr_info("loaded\n"); + +#ifdef CONFIG_ZPOOL + zpool_register_driver(&zbud_zpool_driver); +#endif + + return 0; +} + +static void __exit exit_zbud(void) +{ +#ifdef CONFIG_ZPOOL + zpool_unregister_driver(&zbud_zpool_driver); +#endif + + pr_info("unloaded\n"); +} + +module_init(init_zbud); +module_exit(exit_zbud); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Seth Jennings "); +MODULE_DESCRIPTION("Buddy Allocator for Compressed Pages"); diff --git a/mm/zpool.c b/mm/zpool.c new file mode 100644 index 000000000..3744a2d1a --- /dev/null +++ b/mm/zpool.c @@ -0,0 +1,398 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * zpool memory storage api + * + * Copyright (C) 2014 Dan Streetman + * + * This is a common frontend for memory storage pool implementations. + * Typically, this is used to store compressed memory. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include + +struct zpool { + struct zpool_driver *driver; + void *pool; + const struct zpool_ops *ops; + bool evictable; + + struct list_head list; +}; + +static LIST_HEAD(drivers_head); +static DEFINE_SPINLOCK(drivers_lock); + +static LIST_HEAD(pools_head); +static DEFINE_SPINLOCK(pools_lock); + +/** + * zpool_register_driver() - register a zpool implementation. + * @driver: driver to register + */ +void zpool_register_driver(struct zpool_driver *driver) +{ + spin_lock(&drivers_lock); + atomic_set(&driver->refcount, 0); + list_add(&driver->list, &drivers_head); + spin_unlock(&drivers_lock); +} +EXPORT_SYMBOL(zpool_register_driver); + +/** + * zpool_unregister_driver() - unregister a zpool implementation. + * @driver: driver to unregister. + * + * Module usage counting is used to prevent using a driver + * while/after unloading, so if this is called from module + * exit function, this should never fail; if called from + * other than the module exit function, and this returns + * failure, the driver is in use and must remain available. + */ +int zpool_unregister_driver(struct zpool_driver *driver) +{ + int ret = 0, refcount; + + spin_lock(&drivers_lock); + refcount = atomic_read(&driver->refcount); + WARN_ON(refcount < 0); + if (refcount > 0) + ret = -EBUSY; + else + list_del(&driver->list); + spin_unlock(&drivers_lock); + + return ret; +} +EXPORT_SYMBOL(zpool_unregister_driver); + +/* this assumes @type is null-terminated. */ +static struct zpool_driver *zpool_get_driver(const char *type) +{ + struct zpool_driver *driver; + + spin_lock(&drivers_lock); + list_for_each_entry(driver, &drivers_head, list) { + if (!strcmp(driver->type, type)) { + bool got = try_module_get(driver->owner); + + if (got) + atomic_inc(&driver->refcount); + spin_unlock(&drivers_lock); + return got ? driver : NULL; + } + } + + spin_unlock(&drivers_lock); + return NULL; +} + +static void zpool_put_driver(struct zpool_driver *driver) +{ + atomic_dec(&driver->refcount); + module_put(driver->owner); +} + +/** + * zpool_has_pool() - Check if the pool driver is available + * @type: The type of the zpool to check (e.g. zbud, zsmalloc) + * + * This checks if the @type pool driver is available. This will try to load + * the requested module, if needed, but there is no guarantee the module will + * still be loaded and available immediately after calling. If this returns + * true, the caller should assume the pool is available, but must be prepared + * to handle the @zpool_create_pool() returning failure. However if this + * returns false, the caller should assume the requested pool type is not + * available; either the requested pool type module does not exist, or could + * not be loaded, and calling @zpool_create_pool() with the pool type will + * fail. + * + * The @type string must be null-terminated. + * + * Returns: true if @type pool is available, false if not + */ +bool zpool_has_pool(char *type) +{ + struct zpool_driver *driver = zpool_get_driver(type); + + if (!driver) { + request_module("zpool-%s", type); + driver = zpool_get_driver(type); + } + + if (!driver) + return false; + + zpool_put_driver(driver); + return true; +} +EXPORT_SYMBOL(zpool_has_pool); + +/** + * zpool_create_pool() - Create a new zpool + * @type: The type of the zpool to create (e.g. zbud, zsmalloc) + * @name: The name of the zpool (e.g. zram0, zswap) + * @gfp: The GFP flags to use when allocating the pool. + * @ops: The optional ops callback. + * + * This creates a new zpool of the specified type. The gfp flags will be + * used when allocating memory, if the implementation supports it. If the + * ops param is NULL, then the created zpool will not be evictable. + * + * Implementations must guarantee this to be thread-safe. + * + * The @type and @name strings must be null-terminated. + * + * Returns: New zpool on success, NULL on failure. + */ +struct zpool *zpool_create_pool(const char *type, const char *name, gfp_t gfp, + const struct zpool_ops *ops) +{ + struct zpool_driver *driver; + struct zpool *zpool; + + pr_debug("creating pool type %s\n", type); + + driver = zpool_get_driver(type); + + if (!driver) { + request_module("zpool-%s", type); + driver = zpool_get_driver(type); + } + + if (!driver) { + pr_err("no driver for type %s\n", type); + return NULL; + } + + zpool = kmalloc(sizeof(*zpool), gfp); + if (!zpool) { + pr_err("couldn't create zpool - out of memory\n"); + zpool_put_driver(driver); + return NULL; + } + + zpool->driver = driver; + zpool->pool = driver->create(name, gfp, ops, zpool); + zpool->ops = ops; + zpool->evictable = driver->shrink && ops && ops->evict; + + if (!zpool->pool) { + pr_err("couldn't create %s pool\n", type); + zpool_put_driver(driver); + kfree(zpool); + return NULL; + } + + pr_debug("created pool type %s\n", type); + + spin_lock(&pools_lock); + list_add(&zpool->list, &pools_head); + spin_unlock(&pools_lock); + + return zpool; +} + +/** + * zpool_destroy_pool() - Destroy a zpool + * @zpool: The zpool to destroy. + * + * Implementations must guarantee this to be thread-safe, + * however only when destroying different pools. The same + * pool should only be destroyed once, and should not be used + * after it is destroyed. + * + * This destroys an existing zpool. The zpool should not be in use. + */ +void zpool_destroy_pool(struct zpool *zpool) +{ + pr_debug("destroying pool type %s\n", zpool->driver->type); + + spin_lock(&pools_lock); + list_del(&zpool->list); + spin_unlock(&pools_lock); + zpool->driver->destroy(zpool->pool); + zpool_put_driver(zpool->driver); + kfree(zpool); +} + +/** + * zpool_get_type() - Get the type of the zpool + * @zpool: The zpool to check + * + * This returns the type of the pool. + * + * Implementations must guarantee this to be thread-safe. + * + * Returns: The type of zpool. + */ +const char *zpool_get_type(struct zpool *zpool) +{ + return zpool->driver->type; +} + +/** + * zpool_malloc_support_movable() - Check if the zpool supports + * allocating movable memory + * @zpool: The zpool to check + * + * This returns if the zpool supports allocating movable memory. + * + * Implementations must guarantee this to be thread-safe. + * + * Returns: true if the zpool supports allocating movable memory, false if not + */ +bool zpool_malloc_support_movable(struct zpool *zpool) +{ + return zpool->driver->malloc_support_movable; +} + +/** + * zpool_malloc() - Allocate memory + * @zpool: The zpool to allocate from. + * @size: The amount of memory to allocate. + * @gfp: The GFP flags to use when allocating memory. + * @handle: Pointer to the handle to set + * + * This allocates the requested amount of memory from the pool. + * The gfp flags will be used when allocating memory, if the + * implementation supports it. The provided @handle will be + * set to the allocated object handle. + * + * Implementations must guarantee this to be thread-safe. + * + * Returns: 0 on success, negative value on error. + */ +int zpool_malloc(struct zpool *zpool, size_t size, gfp_t gfp, + unsigned long *handle) +{ + return zpool->driver->malloc(zpool->pool, size, gfp, handle); +} + +/** + * zpool_free() - Free previously allocated memory + * @zpool: The zpool that allocated the memory. + * @handle: The handle to the memory to free. + * + * This frees previously allocated memory. This does not guarantee + * that the pool will actually free memory, only that the memory + * in the pool will become available for use by the pool. + * + * Implementations must guarantee this to be thread-safe, + * however only when freeing different handles. The same + * handle should only be freed once, and should not be used + * after freeing. + */ +void zpool_free(struct zpool *zpool, unsigned long handle) +{ + zpool->driver->free(zpool->pool, handle); +} + +/** + * zpool_shrink() - Shrink the pool size + * @zpool: The zpool to shrink. + * @pages: The number of pages to shrink the pool. + * @reclaimed: The number of pages successfully evicted. + * + * This attempts to shrink the actual memory size of the pool + * by evicting currently used handle(s). If the pool was + * created with no zpool_ops, or the evict call fails for any + * of the handles, this will fail. If non-NULL, the @reclaimed + * parameter will be set to the number of pages reclaimed, + * which may be more than the number of pages requested. + * + * Implementations must guarantee this to be thread-safe. + * + * Returns: 0 on success, negative value on error/failure. + */ +int zpool_shrink(struct zpool *zpool, unsigned int pages, + unsigned int *reclaimed) +{ + return zpool->driver->shrink ? + zpool->driver->shrink(zpool->pool, pages, reclaimed) : -EINVAL; +} + +/** + * zpool_map_handle() - Map a previously allocated handle into memory + * @zpool: The zpool that the handle was allocated from + * @handle: The handle to map + * @mapmode: How the memory should be mapped + * + * This maps a previously allocated handle into memory. The @mapmode + * param indicates to the implementation how the memory will be + * used, i.e. read-only, write-only, read-write. If the + * implementation does not support it, the memory will be treated + * as read-write. + * + * This may hold locks, disable interrupts, and/or preemption, + * and the zpool_unmap_handle() must be called to undo those + * actions. The code that uses the mapped handle should complete + * its operatons on the mapped handle memory quickly and unmap + * as soon as possible. As the implementation may use per-cpu + * data, multiple handles should not be mapped concurrently on + * any cpu. + * + * Returns: A pointer to the handle's mapped memory area. + */ +void *zpool_map_handle(struct zpool *zpool, unsigned long handle, + enum zpool_mapmode mapmode) +{ + return zpool->driver->map(zpool->pool, handle, mapmode); +} + +/** + * zpool_unmap_handle() - Unmap a previously mapped handle + * @zpool: The zpool that the handle was allocated from + * @handle: The handle to unmap + * + * This unmaps a previously mapped handle. Any locks or other + * actions that the implementation took in zpool_map_handle() + * will be undone here. The memory area returned from + * zpool_map_handle() should no longer be used after this. + */ +void zpool_unmap_handle(struct zpool *zpool, unsigned long handle) +{ + zpool->driver->unmap(zpool->pool, handle); +} + +/** + * zpool_get_total_size() - The total size of the pool + * @zpool: The zpool to check + * + * This returns the total size in bytes of the pool. + * + * Returns: Total size of the zpool in bytes. + */ +u64 zpool_get_total_size(struct zpool *zpool) +{ + return zpool->driver->total_size(zpool->pool); +} + +/** + * zpool_evictable() - Test if zpool is potentially evictable + * @zpool: The zpool to test + * + * Zpool is only potentially evictable when it's created with struct + * zpool_ops.evict and its driver implements struct zpool_driver.shrink. + * + * However, it doesn't necessarily mean driver will use zpool_ops.evict + * in its implementation of zpool_driver.shrink. It could do internal + * defragmentation instead. + * + * Returns: true if potentially evictable; false otherwise. + */ +bool zpool_evictable(struct zpool *zpool) +{ + return zpool->evictable; +} + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Dan Streetman "); +MODULE_DESCRIPTION("Common API for compressed memory storage"); diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c new file mode 100644 index 000000000..c18dc8e61 --- /dev/null +++ b/mm/zsmalloc.c @@ -0,0 +1,2581 @@ +/* + * zsmalloc memory allocator + * + * Copyright (C) 2011 Nitin Gupta + * Copyright (C) 2012, 2013 Minchan Kim + * + * This code is released using a dual license strategy: BSD/GPL + * You can choose the license that better fits your requirements. + * + * Released under the terms of 3-clause BSD License + * Released under the terms of GNU General Public License Version 2.0 + */ + +/* + * Following is how we use various fields and flags of underlying + * struct page(s) to form a zspage. + * + * Usage of struct page fields: + * page->private: points to zspage + * page->freelist(index): links together all component pages of a zspage + * For the huge page, this is always 0, so we use this field + * to store handle. + * page->units: first object offset in a subpage of zspage + * + * Usage of struct page flags: + * PG_private: identifies the first component page + * PG_owner_priv_1: identifies the huge component page + * + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define ZSPAGE_MAGIC 0x58 + +/* + * This must be power of 2 and greater than of equal to sizeof(link_free). + * These two conditions ensure that any 'struct link_free' itself doesn't + * span more than 1 page which avoids complex case of mapping 2 pages simply + * to restore link_free pointer values. + */ +#define ZS_ALIGN 8 + +/* + * A single 'zspage' is composed of up to 2^N discontiguous 0-order (single) + * pages. ZS_MAX_ZSPAGE_ORDER defines upper limit on N. + */ +#define ZS_MAX_ZSPAGE_ORDER 2 +#define ZS_MAX_PAGES_PER_ZSPAGE (_AC(1, UL) << ZS_MAX_ZSPAGE_ORDER) + +#define ZS_HANDLE_SIZE (sizeof(unsigned long)) + +/* + * Object location (, ) is encoded as + * a single (unsigned long) handle value. + * + * Note that object index starts from 0. + * + * This is made more complicated by various memory models and PAE. + */ + +#ifndef MAX_POSSIBLE_PHYSMEM_BITS +#ifdef MAX_PHYSMEM_BITS +#define MAX_POSSIBLE_PHYSMEM_BITS MAX_PHYSMEM_BITS +#else +/* + * If this definition of MAX_PHYSMEM_BITS is used, OBJ_INDEX_BITS will just + * be PAGE_SHIFT + */ +#define MAX_POSSIBLE_PHYSMEM_BITS BITS_PER_LONG +#endif +#endif + +#define _PFN_BITS (MAX_POSSIBLE_PHYSMEM_BITS - PAGE_SHIFT) + +/* + * Memory for allocating for handle keeps object position by + * encoding and the encoded value has a room + * in least bit(ie, look at obj_to_location). + * We use the bit to synchronize between object access by + * user and migration. + */ +#define HANDLE_PIN_BIT 0 + +/* + * Head in allocated object should have OBJ_ALLOCATED_TAG + * to identify the object was allocated or not. + * It's okay to add the status bit in the least bit because + * header keeps handle which is 4byte-aligned address so we + * have room for two bit at least. + */ +#define OBJ_ALLOCATED_TAG 1 +#define OBJ_TAG_BITS 1 +#define OBJ_INDEX_BITS (BITS_PER_LONG - _PFN_BITS - OBJ_TAG_BITS) +#define OBJ_INDEX_MASK ((_AC(1, UL) << OBJ_INDEX_BITS) - 1) + +#define FULLNESS_BITS 2 +#define CLASS_BITS 8 +#define ISOLATED_BITS 3 +#define MAGIC_VAL_BITS 8 + +#define MAX(a, b) ((a) >= (b) ? (a) : (b)) +/* ZS_MIN_ALLOC_SIZE must be multiple of ZS_ALIGN */ +#define ZS_MIN_ALLOC_SIZE \ + MAX(32, (ZS_MAX_PAGES_PER_ZSPAGE << PAGE_SHIFT >> OBJ_INDEX_BITS)) +/* each chunk includes extra space to keep handle */ +#define ZS_MAX_ALLOC_SIZE PAGE_SIZE + +/* + * On systems with 4K page size, this gives 255 size classes! There is a + * trader-off here: + * - Large number of size classes is potentially wasteful as free page are + * spread across these classes + * - Small number of size classes causes large internal fragmentation + * - Probably its better to use specific size classes (empirically + * determined). NOTE: all those class sizes must be set as multiple of + * ZS_ALIGN to make sure link_free itself never has to span 2 pages. + * + * ZS_MIN_ALLOC_SIZE and ZS_SIZE_CLASS_DELTA must be multiple of ZS_ALIGN + * (reason above) + */ +#define ZS_SIZE_CLASS_DELTA (PAGE_SIZE >> CLASS_BITS) +#define ZS_SIZE_CLASSES (DIV_ROUND_UP(ZS_MAX_ALLOC_SIZE - ZS_MIN_ALLOC_SIZE, \ + ZS_SIZE_CLASS_DELTA) + 1) + +enum fullness_group { + ZS_EMPTY, + ZS_ALMOST_EMPTY, + ZS_ALMOST_FULL, + ZS_FULL, + NR_ZS_FULLNESS, +}; + +enum zs_stat_type { + CLASS_EMPTY, + CLASS_ALMOST_EMPTY, + CLASS_ALMOST_FULL, + CLASS_FULL, + OBJ_ALLOCATED, + OBJ_USED, + NR_ZS_STAT_TYPE, +}; + +struct zs_size_stat { + unsigned long objs[NR_ZS_STAT_TYPE]; +}; + +#ifdef CONFIG_ZSMALLOC_STAT +static struct dentry *zs_stat_root; +#endif + +#ifdef CONFIG_COMPACTION +static struct vfsmount *zsmalloc_mnt; +#endif + +/* + * We assign a page to ZS_ALMOST_EMPTY fullness group when: + * n <= N / f, where + * n = number of allocated objects + * N = total number of objects zspage can store + * f = fullness_threshold_frac + * + * Similarly, we assign zspage to: + * ZS_ALMOST_FULL when n > N / f + * ZS_EMPTY when n == 0 + * ZS_FULL when n == N + * + * (see: fix_fullness_group()) + */ +static const int fullness_threshold_frac = 4; +static size_t huge_class_size; + +struct size_class { + spinlock_t lock; + struct list_head fullness_list[NR_ZS_FULLNESS]; + /* + * Size of objects stored in this class. Must be multiple + * of ZS_ALIGN. + */ + int size; + int objs_per_zspage; + /* Number of PAGE_SIZE sized pages to combine to form a 'zspage' */ + int pages_per_zspage; + + unsigned int index; + struct zs_size_stat stats; +}; + +/* huge object: pages_per_zspage == 1 && maxobj_per_zspage == 1 */ +static void SetPageHugeObject(struct page *page) +{ + SetPageOwnerPriv1(page); +} + +static void ClearPageHugeObject(struct page *page) +{ + ClearPageOwnerPriv1(page); +} + +static int PageHugeObject(struct page *page) +{ + return PageOwnerPriv1(page); +} + +/* + * Placed within free objects to form a singly linked list. + * For every zspage, zspage->freeobj gives head of this list. + * + * This must be power of 2 and less than or equal to ZS_ALIGN + */ +struct link_free { + union { + /* + * Free object index; + * It's valid for non-allocated object + */ + unsigned long next; + /* + * Handle of allocated object. + */ + unsigned long handle; + }; +}; + +struct zs_pool { + const char *name; + + struct size_class *size_class[ZS_SIZE_CLASSES]; + struct kmem_cache *handle_cachep; + struct kmem_cache *zspage_cachep; + + atomic_long_t pages_allocated; + + struct zs_pool_stats stats; + + /* Compact classes */ + struct shrinker shrinker; + +#ifdef CONFIG_ZSMALLOC_STAT + struct dentry *stat_dentry; +#endif +#ifdef CONFIG_COMPACTION + struct inode *inode; + struct work_struct free_work; + /* A wait queue for when migration races with async_free_zspage() */ + struct wait_queue_head migration_wait; + atomic_long_t isolated_pages; + bool destroying; +#endif +}; + +struct zspage { + struct { + unsigned int fullness:FULLNESS_BITS; + unsigned int class:CLASS_BITS + 1; + unsigned int isolated:ISOLATED_BITS; + unsigned int magic:MAGIC_VAL_BITS; + }; + unsigned int inuse; + unsigned int freeobj; + struct page *first_page; + struct list_head list; /* fullness list */ +#ifdef CONFIG_COMPACTION + rwlock_t lock; +#endif +}; + +struct mapping_area { + char *vm_buf; /* copy buffer for objects that span pages */ + char *vm_addr; /* address of kmap_atomic()'ed pages */ + enum zs_mapmode vm_mm; /* mapping mode */ +}; + +#ifdef CONFIG_COMPACTION +static int zs_register_migration(struct zs_pool *pool); +static void zs_unregister_migration(struct zs_pool *pool); +static void migrate_lock_init(struct zspage *zspage); +static void migrate_read_lock(struct zspage *zspage); +static void migrate_read_unlock(struct zspage *zspage); +static void kick_deferred_free(struct zs_pool *pool); +static void init_deferred_free(struct zs_pool *pool); +static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage); +#else +static int zsmalloc_mount(void) { return 0; } +static void zsmalloc_unmount(void) {} +static int zs_register_migration(struct zs_pool *pool) { return 0; } +static void zs_unregister_migration(struct zs_pool *pool) {} +static void migrate_lock_init(struct zspage *zspage) {} +static void migrate_read_lock(struct zspage *zspage) {} +static void migrate_read_unlock(struct zspage *zspage) {} +static void kick_deferred_free(struct zs_pool *pool) {} +static void init_deferred_free(struct zs_pool *pool) {} +static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage) {} +#endif + +static int create_cache(struct zs_pool *pool) +{ + pool->handle_cachep = kmem_cache_create("zs_handle", ZS_HANDLE_SIZE, + 0, 0, NULL); + if (!pool->handle_cachep) + return 1; + + pool->zspage_cachep = kmem_cache_create("zspage", sizeof(struct zspage), + 0, 0, NULL); + if (!pool->zspage_cachep) { + kmem_cache_destroy(pool->handle_cachep); + pool->handle_cachep = NULL; + return 1; + } + + return 0; +} + +static void destroy_cache(struct zs_pool *pool) +{ + kmem_cache_destroy(pool->handle_cachep); + kmem_cache_destroy(pool->zspage_cachep); +} + +static unsigned long cache_alloc_handle(struct zs_pool *pool, gfp_t gfp) +{ + return (unsigned long)kmem_cache_alloc(pool->handle_cachep, + gfp & ~(__GFP_HIGHMEM|__GFP_MOVABLE)); +} + +static void cache_free_handle(struct zs_pool *pool, unsigned long handle) +{ + kmem_cache_free(pool->handle_cachep, (void *)handle); +} + +static struct zspage *cache_alloc_zspage(struct zs_pool *pool, gfp_t flags) +{ + return kmem_cache_alloc(pool->zspage_cachep, + flags & ~(__GFP_HIGHMEM|__GFP_MOVABLE)); +} + +static void cache_free_zspage(struct zs_pool *pool, struct zspage *zspage) +{ + kmem_cache_free(pool->zspage_cachep, zspage); +} + +static void record_obj(unsigned long handle, unsigned long obj) +{ + /* + * lsb of @obj represents handle lock while other bits + * represent object value the handle is pointing so + * updating shouldn't do store tearing. + */ + WRITE_ONCE(*(unsigned long *)handle, obj); +} + +/* zpool driver */ + +#ifdef CONFIG_ZPOOL + +static void *zs_zpool_create(const char *name, gfp_t gfp, + const struct zpool_ops *zpool_ops, + struct zpool *zpool) +{ + /* + * Ignore global gfp flags: zs_malloc() may be invoked from + * different contexts and its caller must provide a valid + * gfp mask. + */ + return zs_create_pool(name); +} + +static void zs_zpool_destroy(void *pool) +{ + zs_destroy_pool(pool); +} + +static int zs_zpool_malloc(void *pool, size_t size, gfp_t gfp, + unsigned long *handle) +{ + *handle = zs_malloc(pool, size, gfp); + return *handle ? 0 : -1; +} +static void zs_zpool_free(void *pool, unsigned long handle) +{ + zs_free(pool, handle); +} + +static void *zs_zpool_map(void *pool, unsigned long handle, + enum zpool_mapmode mm) +{ + enum zs_mapmode zs_mm; + + switch (mm) { + case ZPOOL_MM_RO: + zs_mm = ZS_MM_RO; + break; + case ZPOOL_MM_WO: + zs_mm = ZS_MM_WO; + break; + case ZPOOL_MM_RW: + default: + zs_mm = ZS_MM_RW; + break; + } + + return zs_map_object(pool, handle, zs_mm); +} +static void zs_zpool_unmap(void *pool, unsigned long handle) +{ + zs_unmap_object(pool, handle); +} + +static u64 zs_zpool_total_size(void *pool) +{ + return zs_get_total_pages(pool) << PAGE_SHIFT; +} + +static struct zpool_driver zs_zpool_driver = { + .type = "zsmalloc", + .owner = THIS_MODULE, + .create = zs_zpool_create, + .destroy = zs_zpool_destroy, + .malloc_support_movable = true, + .malloc = zs_zpool_malloc, + .free = zs_zpool_free, + .map = zs_zpool_map, + .unmap = zs_zpool_unmap, + .total_size = zs_zpool_total_size, +}; + +MODULE_ALIAS("zpool-zsmalloc"); +#endif /* CONFIG_ZPOOL */ + +/* per-cpu VM mapping areas for zspage accesses that cross page boundaries */ +static DEFINE_PER_CPU(struct mapping_area, zs_map_area); + +static bool is_zspage_isolated(struct zspage *zspage) +{ + return zspage->isolated; +} + +static __maybe_unused int is_first_page(struct page *page) +{ + return PagePrivate(page); +} + +/* Protected by class->lock */ +static inline int get_zspage_inuse(struct zspage *zspage) +{ + return zspage->inuse; +} + + +static inline void mod_zspage_inuse(struct zspage *zspage, int val) +{ + zspage->inuse += val; +} + +static inline struct page *get_first_page(struct zspage *zspage) +{ + struct page *first_page = zspage->first_page; + + VM_BUG_ON_PAGE(!is_first_page(first_page), first_page); + return first_page; +} + +static inline int get_first_obj_offset(struct page *page) +{ + return page->units; +} + +static inline void set_first_obj_offset(struct page *page, int offset) +{ + page->units = offset; +} + +static inline unsigned int get_freeobj(struct zspage *zspage) +{ + return zspage->freeobj; +} + +static inline void set_freeobj(struct zspage *zspage, unsigned int obj) +{ + zspage->freeobj = obj; +} + +static void get_zspage_mapping(struct zspage *zspage, + unsigned int *class_idx, + enum fullness_group *fullness) +{ + BUG_ON(zspage->magic != ZSPAGE_MAGIC); + + *fullness = zspage->fullness; + *class_idx = zspage->class; +} + +static void set_zspage_mapping(struct zspage *zspage, + unsigned int class_idx, + enum fullness_group fullness) +{ + zspage->class = class_idx; + zspage->fullness = fullness; +} + +/* + * zsmalloc divides the pool into various size classes where each + * class maintains a list of zspages where each zspage is divided + * into equal sized chunks. Each allocation falls into one of these + * classes depending on its size. This function returns index of the + * size class which has chunk size big enough to hold the give size. + */ +static int get_size_class_index(int size) +{ + int idx = 0; + + if (likely(size > ZS_MIN_ALLOC_SIZE)) + idx = DIV_ROUND_UP(size - ZS_MIN_ALLOC_SIZE, + ZS_SIZE_CLASS_DELTA); + + return min_t(int, ZS_SIZE_CLASSES - 1, idx); +} + +/* type can be of enum type zs_stat_type or fullness_group */ +static inline void zs_stat_inc(struct size_class *class, + int type, unsigned long cnt) +{ + class->stats.objs[type] += cnt; +} + +/* type can be of enum type zs_stat_type or fullness_group */ +static inline void zs_stat_dec(struct size_class *class, + int type, unsigned long cnt) +{ + class->stats.objs[type] -= cnt; +} + +/* type can be of enum type zs_stat_type or fullness_group */ +static inline unsigned long zs_stat_get(struct size_class *class, + int type) +{ + return class->stats.objs[type]; +} + +#ifdef CONFIG_ZSMALLOC_STAT + +static void __init zs_stat_init(void) +{ + if (!debugfs_initialized()) { + pr_warn("debugfs not available, stat dir not created\n"); + return; + } + + zs_stat_root = debugfs_create_dir("zsmalloc", NULL); +} + +static void __exit zs_stat_exit(void) +{ + debugfs_remove_recursive(zs_stat_root); +} + +static unsigned long zs_can_compact(struct size_class *class); + +static int zs_stats_size_show(struct seq_file *s, void *v) +{ + int i; + struct zs_pool *pool = s->private; + struct size_class *class; + int objs_per_zspage; + unsigned long class_almost_full, class_almost_empty; + unsigned long obj_allocated, obj_used, pages_used, freeable; + unsigned long total_class_almost_full = 0, total_class_almost_empty = 0; + unsigned long total_objs = 0, total_used_objs = 0, total_pages = 0; + unsigned long total_freeable = 0; + + seq_printf(s, " %5s %5s %11s %12s %13s %10s %10s %16s %8s\n", + "class", "size", "almost_full", "almost_empty", + "obj_allocated", "obj_used", "pages_used", + "pages_per_zspage", "freeable"); + + for (i = 0; i < ZS_SIZE_CLASSES; i++) { + class = pool->size_class[i]; + + if (class->index != i) + continue; + + spin_lock(&class->lock); + class_almost_full = zs_stat_get(class, CLASS_ALMOST_FULL); + class_almost_empty = zs_stat_get(class, CLASS_ALMOST_EMPTY); + obj_allocated = zs_stat_get(class, OBJ_ALLOCATED); + obj_used = zs_stat_get(class, OBJ_USED); + freeable = zs_can_compact(class); + spin_unlock(&class->lock); + + objs_per_zspage = class->objs_per_zspage; + pages_used = obj_allocated / objs_per_zspage * + class->pages_per_zspage; + + seq_printf(s, " %5u %5u %11lu %12lu %13lu" + " %10lu %10lu %16d %8lu\n", + i, class->size, class_almost_full, class_almost_empty, + obj_allocated, obj_used, pages_used, + class->pages_per_zspage, freeable); + + total_class_almost_full += class_almost_full; + total_class_almost_empty += class_almost_empty; + total_objs += obj_allocated; + total_used_objs += obj_used; + total_pages += pages_used; + total_freeable += freeable; + } + + seq_puts(s, "\n"); + seq_printf(s, " %5s %5s %11lu %12lu %13lu %10lu %10lu %16s %8lu\n", + "Total", "", total_class_almost_full, + total_class_almost_empty, total_objs, + total_used_objs, total_pages, "", total_freeable); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(zs_stats_size); + +static void zs_pool_stat_create(struct zs_pool *pool, const char *name) +{ + if (!zs_stat_root) { + pr_warn("no root stat dir, not creating <%s> stat dir\n", name); + return; + } + + pool->stat_dentry = debugfs_create_dir(name, zs_stat_root); + + debugfs_create_file("classes", S_IFREG | 0444, pool->stat_dentry, pool, + &zs_stats_size_fops); +} + +static void zs_pool_stat_destroy(struct zs_pool *pool) +{ + debugfs_remove_recursive(pool->stat_dentry); +} + +#else /* CONFIG_ZSMALLOC_STAT */ +static void __init zs_stat_init(void) +{ +} + +static void __exit zs_stat_exit(void) +{ +} + +static inline void zs_pool_stat_create(struct zs_pool *pool, const char *name) +{ +} + +static inline void zs_pool_stat_destroy(struct zs_pool *pool) +{ +} +#endif + + +/* + * For each size class, zspages are divided into different groups + * depending on how "full" they are. This was done so that we could + * easily find empty or nearly empty zspages when we try to shrink + * the pool (not yet implemented). This function returns fullness + * status of the given page. + */ +static enum fullness_group get_fullness_group(struct size_class *class, + struct zspage *zspage) +{ + int inuse, objs_per_zspage; + enum fullness_group fg; + + inuse = get_zspage_inuse(zspage); + objs_per_zspage = class->objs_per_zspage; + + if (inuse == 0) + fg = ZS_EMPTY; + else if (inuse == objs_per_zspage) + fg = ZS_FULL; + else if (inuse <= 3 * objs_per_zspage / fullness_threshold_frac) + fg = ZS_ALMOST_EMPTY; + else + fg = ZS_ALMOST_FULL; + + return fg; +} + +/* + * Each size class maintains various freelists and zspages are assigned + * to one of these freelists based on the number of live objects they + * have. This functions inserts the given zspage into the freelist + * identified by . + */ +static void insert_zspage(struct size_class *class, + struct zspage *zspage, + enum fullness_group fullness) +{ + struct zspage *head; + + zs_stat_inc(class, fullness, 1); + head = list_first_entry_or_null(&class->fullness_list[fullness], + struct zspage, list); + /* + * We want to see more ZS_FULL pages and less almost empty/full. + * Put pages with higher ->inuse first. + */ + if (head) { + if (get_zspage_inuse(zspage) < get_zspage_inuse(head)) { + list_add(&zspage->list, &head->list); + return; + } + } + list_add(&zspage->list, &class->fullness_list[fullness]); +} + +/* + * This function removes the given zspage from the freelist identified + * by . + */ +static void remove_zspage(struct size_class *class, + struct zspage *zspage, + enum fullness_group fullness) +{ + VM_BUG_ON(list_empty(&class->fullness_list[fullness])); + VM_BUG_ON(is_zspage_isolated(zspage)); + + list_del_init(&zspage->list); + zs_stat_dec(class, fullness, 1); +} + +/* + * Each size class maintains zspages in different fullness groups depending + * on the number of live objects they contain. When allocating or freeing + * objects, the fullness status of the page can change, say, from ALMOST_FULL + * to ALMOST_EMPTY when freeing an object. This function checks if such + * a status change has occurred for the given page and accordingly moves the + * page from the freelist of the old fullness group to that of the new + * fullness group. + */ +static enum fullness_group fix_fullness_group(struct size_class *class, + struct zspage *zspage) +{ + int class_idx; + enum fullness_group currfg, newfg; + + get_zspage_mapping(zspage, &class_idx, &currfg); + newfg = get_fullness_group(class, zspage); + if (newfg == currfg) + goto out; + + if (!is_zspage_isolated(zspage)) { + remove_zspage(class, zspage, currfg); + insert_zspage(class, zspage, newfg); + } + + set_zspage_mapping(zspage, class_idx, newfg); + +out: + return newfg; +} + +/* + * We have to decide on how many pages to link together + * to form a zspage for each size class. This is important + * to reduce wastage due to unusable space left at end of + * each zspage which is given as: + * wastage = Zp % class_size + * usage = Zp - wastage + * where Zp = zspage size = k * PAGE_SIZE where k = 1, 2, ... + * + * For example, for size class of 3/8 * PAGE_SIZE, we should + * link together 3 PAGE_SIZE sized pages to form a zspage + * since then we can perfectly fit in 8 such objects. + */ +static int get_pages_per_zspage(int class_size) +{ + int i, max_usedpc = 0; + /* zspage order which gives maximum used size per KB */ + int max_usedpc_order = 1; + + for (i = 1; i <= ZS_MAX_PAGES_PER_ZSPAGE; i++) { + int zspage_size; + int waste, usedpc; + + zspage_size = i * PAGE_SIZE; + waste = zspage_size % class_size; + usedpc = (zspage_size - waste) * 100 / zspage_size; + + if (usedpc > max_usedpc) { + max_usedpc = usedpc; + max_usedpc_order = i; + } + } + + return max_usedpc_order; +} + +static struct zspage *get_zspage(struct page *page) +{ + struct zspage *zspage = (struct zspage *)page->private; + + BUG_ON(zspage->magic != ZSPAGE_MAGIC); + return zspage; +} + +static struct page *get_next_page(struct page *page) +{ + if (unlikely(PageHugeObject(page))) + return NULL; + + return page->freelist; +} + +/** + * obj_to_location - get (, ) from encoded object value + * @obj: the encoded object value + * @page: page object resides in zspage + * @obj_idx: object index + */ +static void obj_to_location(unsigned long obj, struct page **page, + unsigned int *obj_idx) +{ + obj >>= OBJ_TAG_BITS; + *page = pfn_to_page(obj >> OBJ_INDEX_BITS); + *obj_idx = (obj & OBJ_INDEX_MASK); +} + +/** + * location_to_obj - get obj value encoded from (, ) + * @page: page object resides in zspage + * @obj_idx: object index + */ +static unsigned long location_to_obj(struct page *page, unsigned int obj_idx) +{ + unsigned long obj; + + obj = page_to_pfn(page) << OBJ_INDEX_BITS; + obj |= obj_idx & OBJ_INDEX_MASK; + obj <<= OBJ_TAG_BITS; + + return obj; +} + +static unsigned long handle_to_obj(unsigned long handle) +{ + return *(unsigned long *)handle; +} + +static unsigned long obj_to_head(struct page *page, void *obj) +{ + if (unlikely(PageHugeObject(page))) { + VM_BUG_ON_PAGE(!is_first_page(page), page); + return page->index; + } else + return *(unsigned long *)obj; +} + +static inline int testpin_tag(unsigned long handle) +{ + return bit_spin_is_locked(HANDLE_PIN_BIT, (unsigned long *)handle); +} + +static inline int trypin_tag(unsigned long handle) +{ + return bit_spin_trylock(HANDLE_PIN_BIT, (unsigned long *)handle); +} + +static void pin_tag(unsigned long handle) __acquires(bitlock) +{ + bit_spin_lock(HANDLE_PIN_BIT, (unsigned long *)handle); +} + +static void unpin_tag(unsigned long handle) __releases(bitlock) +{ + bit_spin_unlock(HANDLE_PIN_BIT, (unsigned long *)handle); +} + +static void reset_page(struct page *page) +{ + __ClearPageMovable(page); + ClearPagePrivate(page); + set_page_private(page, 0); + page_mapcount_reset(page); + ClearPageHugeObject(page); + page->freelist = NULL; +} + +static int trylock_zspage(struct zspage *zspage) +{ + struct page *cursor, *fail; + + for (cursor = get_first_page(zspage); cursor != NULL; cursor = + get_next_page(cursor)) { + if (!trylock_page(cursor)) { + fail = cursor; + goto unlock; + } + } + + return 1; +unlock: + for (cursor = get_first_page(zspage); cursor != fail; cursor = + get_next_page(cursor)) + unlock_page(cursor); + + return 0; +} + +static void __free_zspage(struct zs_pool *pool, struct size_class *class, + struct zspage *zspage) +{ + struct page *page, *next; + enum fullness_group fg; + unsigned int class_idx; + + get_zspage_mapping(zspage, &class_idx, &fg); + + assert_spin_locked(&class->lock); + + VM_BUG_ON(get_zspage_inuse(zspage)); + VM_BUG_ON(fg != ZS_EMPTY); + + next = page = get_first_page(zspage); + do { + VM_BUG_ON_PAGE(!PageLocked(page), page); + next = get_next_page(page); + reset_page(page); + unlock_page(page); + dec_zone_page_state(page, NR_ZSPAGES); + put_page(page); + page = next; + } while (page != NULL); + + cache_free_zspage(pool, zspage); + + zs_stat_dec(class, OBJ_ALLOCATED, class->objs_per_zspage); + atomic_long_sub(class->pages_per_zspage, + &pool->pages_allocated); +} + +static void free_zspage(struct zs_pool *pool, struct size_class *class, + struct zspage *zspage) +{ + VM_BUG_ON(get_zspage_inuse(zspage)); + VM_BUG_ON(list_empty(&zspage->list)); + + if (!trylock_zspage(zspage)) { + kick_deferred_free(pool); + return; + } + + remove_zspage(class, zspage, ZS_EMPTY); + __free_zspage(pool, class, zspage); +} + +/* Initialize a newly allocated zspage */ +static void init_zspage(struct size_class *class, struct zspage *zspage) +{ + unsigned int freeobj = 1; + unsigned long off = 0; + struct page *page = get_first_page(zspage); + + while (page) { + struct page *next_page; + struct link_free *link; + void *vaddr; + + set_first_obj_offset(page, off); + + vaddr = kmap_atomic(page); + link = (struct link_free *)vaddr + off / sizeof(*link); + + while ((off += class->size) < PAGE_SIZE) { + link->next = freeobj++ << OBJ_TAG_BITS; + link += class->size / sizeof(*link); + } + + /* + * We now come to the last (full or partial) object on this + * page, which must point to the first object on the next + * page (if present) + */ + next_page = get_next_page(page); + if (next_page) { + link->next = freeobj++ << OBJ_TAG_BITS; + } else { + /* + * Reset OBJ_TAG_BITS bit to last link to tell + * whether it's allocated object or not. + */ + link->next = -1UL << OBJ_TAG_BITS; + } + kunmap_atomic(vaddr); + page = next_page; + off %= PAGE_SIZE; + } + + set_freeobj(zspage, 0); +} + +static void create_page_chain(struct size_class *class, struct zspage *zspage, + struct page *pages[]) +{ + int i; + struct page *page; + struct page *prev_page = NULL; + int nr_pages = class->pages_per_zspage; + + /* + * Allocate individual pages and link them together as: + * 1. all pages are linked together using page->freelist + * 2. each sub-page point to zspage using page->private + * + * we set PG_private to identify the first page (i.e. no other sub-page + * has this flag set). + */ + for (i = 0; i < nr_pages; i++) { + page = pages[i]; + set_page_private(page, (unsigned long)zspage); + page->freelist = NULL; + if (i == 0) { + zspage->first_page = page; + SetPagePrivate(page); + if (unlikely(class->objs_per_zspage == 1 && + class->pages_per_zspage == 1)) + SetPageHugeObject(page); + } else { + prev_page->freelist = page; + } + prev_page = page; + } +} + +/* + * Allocate a zspage for the given size class + */ +static struct zspage *alloc_zspage(struct zs_pool *pool, + struct size_class *class, + gfp_t gfp) +{ + int i; + struct page *pages[ZS_MAX_PAGES_PER_ZSPAGE]; + struct zspage *zspage = cache_alloc_zspage(pool, gfp); + + if (!zspage) + return NULL; + + memset(zspage, 0, sizeof(struct zspage)); + zspage->magic = ZSPAGE_MAGIC; + migrate_lock_init(zspage); + + for (i = 0; i < class->pages_per_zspage; i++) { + struct page *page; + + page = alloc_page(gfp); + if (!page) { + while (--i >= 0) { + dec_zone_page_state(pages[i], NR_ZSPAGES); + __free_page(pages[i]); + } + cache_free_zspage(pool, zspage); + return NULL; + } + + inc_zone_page_state(page, NR_ZSPAGES); + pages[i] = page; + } + + create_page_chain(class, zspage, pages); + init_zspage(class, zspage); + + return zspage; +} + +static struct zspage *find_get_zspage(struct size_class *class) +{ + int i; + struct zspage *zspage; + + for (i = ZS_ALMOST_FULL; i >= ZS_EMPTY; i--) { + zspage = list_first_entry_or_null(&class->fullness_list[i], + struct zspage, list); + if (zspage) + break; + } + + return zspage; +} + +static inline int __zs_cpu_up(struct mapping_area *area) +{ + /* + * Make sure we don't leak memory if a cpu UP notification + * and zs_init() race and both call zs_cpu_up() on the same cpu + */ + if (area->vm_buf) + return 0; + area->vm_buf = kmalloc(ZS_MAX_ALLOC_SIZE, GFP_KERNEL); + if (!area->vm_buf) + return -ENOMEM; + return 0; +} + +static inline void __zs_cpu_down(struct mapping_area *area) +{ + kfree(area->vm_buf); + area->vm_buf = NULL; +} + +static void *__zs_map_object(struct mapping_area *area, + struct page *pages[2], int off, int size) +{ + int sizes[2]; + void *addr; + char *buf = area->vm_buf; + + /* disable page faults to match kmap_atomic() return conditions */ + pagefault_disable(); + + /* no read fastpath */ + if (area->vm_mm == ZS_MM_WO) + goto out; + + sizes[0] = PAGE_SIZE - off; + sizes[1] = size - sizes[0]; + + /* copy object to per-cpu buffer */ + addr = kmap_atomic(pages[0]); + memcpy(buf, addr + off, sizes[0]); + kunmap_atomic(addr); + addr = kmap_atomic(pages[1]); + memcpy(buf + sizes[0], addr, sizes[1]); + kunmap_atomic(addr); +out: + return area->vm_buf; +} + +static void __zs_unmap_object(struct mapping_area *area, + struct page *pages[2], int off, int size) +{ + int sizes[2]; + void *addr; + char *buf; + + /* no write fastpath */ + if (area->vm_mm == ZS_MM_RO) + goto out; + + buf = area->vm_buf; + buf = buf + ZS_HANDLE_SIZE; + size -= ZS_HANDLE_SIZE; + off += ZS_HANDLE_SIZE; + + sizes[0] = PAGE_SIZE - off; + sizes[1] = size - sizes[0]; + + /* copy per-cpu buffer to object */ + addr = kmap_atomic(pages[0]); + memcpy(addr + off, buf, sizes[0]); + kunmap_atomic(addr); + addr = kmap_atomic(pages[1]); + memcpy(addr, buf + sizes[0], sizes[1]); + kunmap_atomic(addr); + +out: + /* enable page faults to match kunmap_atomic() return conditions */ + pagefault_enable(); +} + +static int zs_cpu_prepare(unsigned int cpu) +{ + struct mapping_area *area; + + area = &per_cpu(zs_map_area, cpu); + return __zs_cpu_up(area); +} + +static int zs_cpu_dead(unsigned int cpu) +{ + struct mapping_area *area; + + area = &per_cpu(zs_map_area, cpu); + __zs_cpu_down(area); + return 0; +} + +static bool can_merge(struct size_class *prev, int pages_per_zspage, + int objs_per_zspage) +{ + if (prev->pages_per_zspage == pages_per_zspage && + prev->objs_per_zspage == objs_per_zspage) + return true; + + return false; +} + +static bool zspage_full(struct size_class *class, struct zspage *zspage) +{ + return get_zspage_inuse(zspage) == class->objs_per_zspage; +} + +unsigned long zs_get_total_pages(struct zs_pool *pool) +{ + return atomic_long_read(&pool->pages_allocated); +} +EXPORT_SYMBOL_GPL(zs_get_total_pages); + +/** + * zs_map_object - get address of allocated object from handle. + * @pool: pool from which the object was allocated + * @handle: handle returned from zs_malloc + * @mm: maping mode to use + * + * Before using an object allocated from zs_malloc, it must be mapped using + * this function. When done with the object, it must be unmapped using + * zs_unmap_object. + * + * Only one object can be mapped per cpu at a time. There is no protection + * against nested mappings. + * + * This function returns with preemption and page faults disabled. + */ +void *zs_map_object(struct zs_pool *pool, unsigned long handle, + enum zs_mapmode mm) +{ + struct zspage *zspage; + struct page *page; + unsigned long obj, off; + unsigned int obj_idx; + + unsigned int class_idx; + enum fullness_group fg; + struct size_class *class; + struct mapping_area *area; + struct page *pages[2]; + void *ret; + + /* + * Because we use per-cpu mapping areas shared among the + * pools/users, we can't allow mapping in interrupt context + * because it can corrupt another users mappings. + */ + BUG_ON(in_interrupt()); + + /* From now on, migration cannot move the object */ + pin_tag(handle); + + obj = handle_to_obj(handle); + obj_to_location(obj, &page, &obj_idx); + zspage = get_zspage(page); + + /* migration cannot move any subpage in this zspage */ + migrate_read_lock(zspage); + + get_zspage_mapping(zspage, &class_idx, &fg); + class = pool->size_class[class_idx]; + off = (class->size * obj_idx) & ~PAGE_MASK; + + area = &get_cpu_var(zs_map_area); + area->vm_mm = mm; + if (off + class->size <= PAGE_SIZE) { + /* this object is contained entirely within a page */ + area->vm_addr = kmap_atomic(page); + ret = area->vm_addr + off; + goto out; + } + + /* this object spans two pages */ + pages[0] = page; + pages[1] = get_next_page(page); + BUG_ON(!pages[1]); + + ret = __zs_map_object(area, pages, off, class->size); +out: + if (likely(!PageHugeObject(page))) + ret += ZS_HANDLE_SIZE; + + return ret; +} +EXPORT_SYMBOL_GPL(zs_map_object); + +void zs_unmap_object(struct zs_pool *pool, unsigned long handle) +{ + struct zspage *zspage; + struct page *page; + unsigned long obj, off; + unsigned int obj_idx; + + unsigned int class_idx; + enum fullness_group fg; + struct size_class *class; + struct mapping_area *area; + + obj = handle_to_obj(handle); + obj_to_location(obj, &page, &obj_idx); + zspage = get_zspage(page); + get_zspage_mapping(zspage, &class_idx, &fg); + class = pool->size_class[class_idx]; + off = (class->size * obj_idx) & ~PAGE_MASK; + + area = this_cpu_ptr(&zs_map_area); + if (off + class->size <= PAGE_SIZE) + kunmap_atomic(area->vm_addr); + else { + struct page *pages[2]; + + pages[0] = page; + pages[1] = get_next_page(page); + BUG_ON(!pages[1]); + + __zs_unmap_object(area, pages, off, class->size); + } + put_cpu_var(zs_map_area); + + migrate_read_unlock(zspage); + unpin_tag(handle); +} +EXPORT_SYMBOL_GPL(zs_unmap_object); + +/** + * zs_huge_class_size() - Returns the size (in bytes) of the first huge + * zsmalloc &size_class. + * @pool: zsmalloc pool to use + * + * The function returns the size of the first huge class - any object of equal + * or bigger size will be stored in zspage consisting of a single physical + * page. + * + * Context: Any context. + * + * Return: the size (in bytes) of the first huge zsmalloc &size_class. + */ +size_t zs_huge_class_size(struct zs_pool *pool) +{ + return huge_class_size; +} +EXPORT_SYMBOL_GPL(zs_huge_class_size); + +static unsigned long obj_malloc(struct size_class *class, + struct zspage *zspage, unsigned long handle) +{ + int i, nr_page, offset; + unsigned long obj; + struct link_free *link; + + struct page *m_page; + unsigned long m_offset; + void *vaddr; + + handle |= OBJ_ALLOCATED_TAG; + obj = get_freeobj(zspage); + + offset = obj * class->size; + nr_page = offset >> PAGE_SHIFT; + m_offset = offset & ~PAGE_MASK; + m_page = get_first_page(zspage); + + for (i = 0; i < nr_page; i++) + m_page = get_next_page(m_page); + + vaddr = kmap_atomic(m_page); + link = (struct link_free *)vaddr + m_offset / sizeof(*link); + set_freeobj(zspage, link->next >> OBJ_TAG_BITS); + if (likely(!PageHugeObject(m_page))) + /* record handle in the header of allocated chunk */ + link->handle = handle; + else + /* record handle to page->index */ + zspage->first_page->index = handle; + + kunmap_atomic(vaddr); + mod_zspage_inuse(zspage, 1); + zs_stat_inc(class, OBJ_USED, 1); + + obj = location_to_obj(m_page, obj); + + return obj; +} + + +/** + * zs_malloc - Allocate block of given size from pool. + * @pool: pool to allocate from + * @size: size of block to allocate + * @gfp: gfp flags when allocating object + * + * On success, handle to the allocated object is returned, + * otherwise 0. + * Allocation requests with size > ZS_MAX_ALLOC_SIZE will fail. + */ +unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) +{ + unsigned long handle, obj; + struct size_class *class; + enum fullness_group newfg; + struct zspage *zspage; + + if (unlikely(!size || size > ZS_MAX_ALLOC_SIZE)) + return 0; + + handle = cache_alloc_handle(pool, gfp); + if (!handle) + return 0; + + /* extra space in chunk to keep the handle */ + size += ZS_HANDLE_SIZE; + class = pool->size_class[get_size_class_index(size)]; + + spin_lock(&class->lock); + zspage = find_get_zspage(class); + if (likely(zspage)) { + obj = obj_malloc(class, zspage, handle); + /* Now move the zspage to another fullness group, if required */ + fix_fullness_group(class, zspage); + record_obj(handle, obj); + spin_unlock(&class->lock); + + return handle; + } + + spin_unlock(&class->lock); + + zspage = alloc_zspage(pool, class, gfp); + if (!zspage) { + cache_free_handle(pool, handle); + return 0; + } + + spin_lock(&class->lock); + obj = obj_malloc(class, zspage, handle); + newfg = get_fullness_group(class, zspage); + insert_zspage(class, zspage, newfg); + set_zspage_mapping(zspage, class->index, newfg); + record_obj(handle, obj); + atomic_long_add(class->pages_per_zspage, + &pool->pages_allocated); + zs_stat_inc(class, OBJ_ALLOCATED, class->objs_per_zspage); + + /* We completely set up zspage so mark them as movable */ + SetZsPageMovable(pool, zspage); + spin_unlock(&class->lock); + + return handle; +} +EXPORT_SYMBOL_GPL(zs_malloc); + +static void obj_free(struct size_class *class, unsigned long obj) +{ + struct link_free *link; + struct zspage *zspage; + struct page *f_page; + unsigned long f_offset; + unsigned int f_objidx; + void *vaddr; + + obj &= ~OBJ_ALLOCATED_TAG; + obj_to_location(obj, &f_page, &f_objidx); + f_offset = (class->size * f_objidx) & ~PAGE_MASK; + zspage = get_zspage(f_page); + + vaddr = kmap_atomic(f_page); + + /* Insert this object in containing zspage's freelist */ + link = (struct link_free *)(vaddr + f_offset); + link->next = get_freeobj(zspage) << OBJ_TAG_BITS; + kunmap_atomic(vaddr); + set_freeobj(zspage, f_objidx); + mod_zspage_inuse(zspage, -1); + zs_stat_dec(class, OBJ_USED, 1); +} + +void zs_free(struct zs_pool *pool, unsigned long handle) +{ + struct zspage *zspage; + struct page *f_page; + unsigned long obj; + unsigned int f_objidx; + int class_idx; + struct size_class *class; + enum fullness_group fullness; + bool isolated; + + if (unlikely(!handle)) + return; + + pin_tag(handle); + obj = handle_to_obj(handle); + obj_to_location(obj, &f_page, &f_objidx); + zspage = get_zspage(f_page); + + migrate_read_lock(zspage); + + get_zspage_mapping(zspage, &class_idx, &fullness); + class = pool->size_class[class_idx]; + + spin_lock(&class->lock); + obj_free(class, obj); + fullness = fix_fullness_group(class, zspage); + if (fullness != ZS_EMPTY) { + migrate_read_unlock(zspage); + goto out; + } + + isolated = is_zspage_isolated(zspage); + migrate_read_unlock(zspage); + /* If zspage is isolated, zs_page_putback will free the zspage */ + if (likely(!isolated)) + free_zspage(pool, class, zspage); +out: + + spin_unlock(&class->lock); + unpin_tag(handle); + cache_free_handle(pool, handle); +} +EXPORT_SYMBOL_GPL(zs_free); + +static void zs_object_copy(struct size_class *class, unsigned long dst, + unsigned long src) +{ + struct page *s_page, *d_page; + unsigned int s_objidx, d_objidx; + unsigned long s_off, d_off; + void *s_addr, *d_addr; + int s_size, d_size, size; + int written = 0; + + s_size = d_size = class->size; + + obj_to_location(src, &s_page, &s_objidx); + obj_to_location(dst, &d_page, &d_objidx); + + s_off = (class->size * s_objidx) & ~PAGE_MASK; + d_off = (class->size * d_objidx) & ~PAGE_MASK; + + if (s_off + class->size > PAGE_SIZE) + s_size = PAGE_SIZE - s_off; + + if (d_off + class->size > PAGE_SIZE) + d_size = PAGE_SIZE - d_off; + + s_addr = kmap_atomic(s_page); + d_addr = kmap_atomic(d_page); + + while (1) { + size = min(s_size, d_size); + memcpy(d_addr + d_off, s_addr + s_off, size); + written += size; + + if (written == class->size) + break; + + s_off += size; + s_size -= size; + d_off += size; + d_size -= size; + + if (s_off >= PAGE_SIZE) { + kunmap_atomic(d_addr); + kunmap_atomic(s_addr); + s_page = get_next_page(s_page); + s_addr = kmap_atomic(s_page); + d_addr = kmap_atomic(d_page); + s_size = class->size - written; + s_off = 0; + } + + if (d_off >= PAGE_SIZE) { + kunmap_atomic(d_addr); + d_page = get_next_page(d_page); + d_addr = kmap_atomic(d_page); + d_size = class->size - written; + d_off = 0; + } + } + + kunmap_atomic(d_addr); + kunmap_atomic(s_addr); +} + +/* + * Find alloced object in zspage from index object and + * return handle. + */ +static unsigned long find_alloced_obj(struct size_class *class, + struct page *page, int *obj_idx) +{ + unsigned long head; + int offset = 0; + int index = *obj_idx; + unsigned long handle = 0; + void *addr = kmap_atomic(page); + + offset = get_first_obj_offset(page); + offset += class->size * index; + + while (offset < PAGE_SIZE) { + head = obj_to_head(page, addr + offset); + if (head & OBJ_ALLOCATED_TAG) { + handle = head & ~OBJ_ALLOCATED_TAG; + if (trypin_tag(handle)) + break; + handle = 0; + } + + offset += class->size; + index++; + } + + kunmap_atomic(addr); + + *obj_idx = index; + + return handle; +} + +struct zs_compact_control { + /* Source spage for migration which could be a subpage of zspage */ + struct page *s_page; + /* Destination page for migration which should be a first page + * of zspage. */ + struct page *d_page; + /* Starting object index within @s_page which used for live object + * in the subpage. */ + int obj_idx; +}; + +static int migrate_zspage(struct zs_pool *pool, struct size_class *class, + struct zs_compact_control *cc) +{ + unsigned long used_obj, free_obj; + unsigned long handle; + struct page *s_page = cc->s_page; + struct page *d_page = cc->d_page; + int obj_idx = cc->obj_idx; + int ret = 0; + + while (1) { + handle = find_alloced_obj(class, s_page, &obj_idx); + if (!handle) { + s_page = get_next_page(s_page); + if (!s_page) + break; + obj_idx = 0; + continue; + } + + /* Stop if there is no more space */ + if (zspage_full(class, get_zspage(d_page))) { + unpin_tag(handle); + ret = -ENOMEM; + break; + } + + used_obj = handle_to_obj(handle); + free_obj = obj_malloc(class, get_zspage(d_page), handle); + zs_object_copy(class, free_obj, used_obj); + obj_idx++; + /* + * record_obj updates handle's value to free_obj and it will + * invalidate lock bit(ie, HANDLE_PIN_BIT) of handle, which + * breaks synchronization using pin_tag(e,g, zs_free) so + * let's keep the lock bit. + */ + free_obj |= BIT(HANDLE_PIN_BIT); + record_obj(handle, free_obj); + unpin_tag(handle); + obj_free(class, used_obj); + } + + /* Remember last position in this iteration */ + cc->s_page = s_page; + cc->obj_idx = obj_idx; + + return ret; +} + +static struct zspage *isolate_zspage(struct size_class *class, bool source) +{ + int i; + struct zspage *zspage; + enum fullness_group fg[2] = {ZS_ALMOST_EMPTY, ZS_ALMOST_FULL}; + + if (!source) { + fg[0] = ZS_ALMOST_FULL; + fg[1] = ZS_ALMOST_EMPTY; + } + + for (i = 0; i < 2; i++) { + zspage = list_first_entry_or_null(&class->fullness_list[fg[i]], + struct zspage, list); + if (zspage) { + VM_BUG_ON(is_zspage_isolated(zspage)); + remove_zspage(class, zspage, fg[i]); + return zspage; + } + } + + return zspage; +} + +/* + * putback_zspage - add @zspage into right class's fullness list + * @class: destination class + * @zspage: target page + * + * Return @zspage's fullness_group + */ +static enum fullness_group putback_zspage(struct size_class *class, + struct zspage *zspage) +{ + enum fullness_group fullness; + + VM_BUG_ON(is_zspage_isolated(zspage)); + + fullness = get_fullness_group(class, zspage); + insert_zspage(class, zspage, fullness); + set_zspage_mapping(zspage, class->index, fullness); + + return fullness; +} + +#ifdef CONFIG_COMPACTION +/* + * To prevent zspage destroy during migration, zspage freeing should + * hold locks of all pages in the zspage. + */ +static void lock_zspage(struct zspage *zspage) +{ + struct page *curr_page, *page; + + /* + * Pages we haven't locked yet can be migrated off the list while we're + * trying to lock them, so we need to be careful and only attempt to + * lock each page under migrate_read_lock(). Otherwise, the page we lock + * may no longer belong to the zspage. This means that we may wait for + * the wrong page to unlock, so we must take a reference to the page + * prior to waiting for it to unlock outside migrate_read_lock(). + */ + while (1) { + migrate_read_lock(zspage); + page = get_first_page(zspage); + if (trylock_page(page)) + break; + get_page(page); + migrate_read_unlock(zspage); + wait_on_page_locked(page); + put_page(page); + } + + curr_page = page; + while ((page = get_next_page(curr_page))) { + if (trylock_page(page)) { + curr_page = page; + } else { + get_page(page); + migrate_read_unlock(zspage); + wait_on_page_locked(page); + put_page(page); + migrate_read_lock(zspage); + } + } + migrate_read_unlock(zspage); +} + +static int zs_init_fs_context(struct fs_context *fc) +{ + return init_pseudo(fc, ZSMALLOC_MAGIC) ? 0 : -ENOMEM; +} + +static struct file_system_type zsmalloc_fs = { + .name = "zsmalloc", + .init_fs_context = zs_init_fs_context, + .kill_sb = kill_anon_super, +}; + +static int zsmalloc_mount(void) +{ + int ret = 0; + + zsmalloc_mnt = kern_mount(&zsmalloc_fs); + if (IS_ERR(zsmalloc_mnt)) + ret = PTR_ERR(zsmalloc_mnt); + + return ret; +} + +static void zsmalloc_unmount(void) +{ + kern_unmount(zsmalloc_mnt); +} + +static void migrate_lock_init(struct zspage *zspage) +{ + rwlock_init(&zspage->lock); +} + +static void migrate_read_lock(struct zspage *zspage) __acquires(&zspage->lock) +{ + read_lock(&zspage->lock); +} + +static void migrate_read_unlock(struct zspage *zspage) __releases(&zspage->lock) +{ + read_unlock(&zspage->lock); +} + +static void migrate_write_lock(struct zspage *zspage) +{ + write_lock(&zspage->lock); +} + +static void migrate_write_unlock(struct zspage *zspage) +{ + write_unlock(&zspage->lock); +} + +/* Number of isolated subpage for *page migration* in this zspage */ +static void inc_zspage_isolation(struct zspage *zspage) +{ + zspage->isolated++; +} + +static void dec_zspage_isolation(struct zspage *zspage) +{ + zspage->isolated--; +} + +static void putback_zspage_deferred(struct zs_pool *pool, + struct size_class *class, + struct zspage *zspage) +{ + enum fullness_group fg; + + fg = putback_zspage(class, zspage); + if (fg == ZS_EMPTY) + schedule_work(&pool->free_work); + +} + +static inline void zs_pool_dec_isolated(struct zs_pool *pool) +{ + VM_BUG_ON(atomic_long_read(&pool->isolated_pages) <= 0); + atomic_long_dec(&pool->isolated_pages); + /* + * Checking pool->destroying must happen after atomic_long_dec() + * for pool->isolated_pages above. Paired with the smp_mb() in + * zs_unregister_migration(). + */ + smp_mb__after_atomic(); + if (atomic_long_read(&pool->isolated_pages) == 0 && pool->destroying) + wake_up_all(&pool->migration_wait); +} + +static void replace_sub_page(struct size_class *class, struct zspage *zspage, + struct page *newpage, struct page *oldpage) +{ + struct page *page; + struct page *pages[ZS_MAX_PAGES_PER_ZSPAGE] = {NULL, }; + int idx = 0; + + page = get_first_page(zspage); + do { + if (page == oldpage) + pages[idx] = newpage; + else + pages[idx] = page; + idx++; + } while ((page = get_next_page(page)) != NULL); + + create_page_chain(class, zspage, pages); + set_first_obj_offset(newpage, get_first_obj_offset(oldpage)); + if (unlikely(PageHugeObject(oldpage))) + newpage->index = oldpage->index; + __SetPageMovable(newpage, page_mapping(oldpage)); +} + +static bool zs_page_isolate(struct page *page, isolate_mode_t mode) +{ + struct zs_pool *pool; + struct size_class *class; + int class_idx; + enum fullness_group fullness; + struct zspage *zspage; + struct address_space *mapping; + + /* + * Page is locked so zspage couldn't be destroyed. For detail, look at + * lock_zspage in free_zspage. + */ + VM_BUG_ON_PAGE(!PageMovable(page), page); + VM_BUG_ON_PAGE(PageIsolated(page), page); + + zspage = get_zspage(page); + + /* + * Without class lock, fullness could be stale while class_idx is okay + * because class_idx is constant unless page is freed so we should get + * fullness again under class lock. + */ + get_zspage_mapping(zspage, &class_idx, &fullness); + mapping = page_mapping(page); + pool = mapping->private_data; + class = pool->size_class[class_idx]; + + spin_lock(&class->lock); + if (get_zspage_inuse(zspage) == 0) { + spin_unlock(&class->lock); + return false; + } + + /* zspage is isolated for object migration */ + if (list_empty(&zspage->list) && !is_zspage_isolated(zspage)) { + spin_unlock(&class->lock); + return false; + } + + /* + * If this is first time isolation for the zspage, isolate zspage from + * size_class to prevent further object allocation from the zspage. + */ + if (!list_empty(&zspage->list) && !is_zspage_isolated(zspage)) { + get_zspage_mapping(zspage, &class_idx, &fullness); + atomic_long_inc(&pool->isolated_pages); + remove_zspage(class, zspage, fullness); + } + + inc_zspage_isolation(zspage); + spin_unlock(&class->lock); + + return true; +} + +static int zs_page_migrate(struct address_space *mapping, struct page *newpage, + struct page *page, enum migrate_mode mode) +{ + struct zs_pool *pool; + struct size_class *class; + int class_idx; + enum fullness_group fullness; + struct zspage *zspage; + struct page *dummy; + void *s_addr, *d_addr, *addr; + int offset, pos; + unsigned long handle, head; + unsigned long old_obj, new_obj; + unsigned int obj_idx; + int ret = -EAGAIN; + + /* + * We cannot support the _NO_COPY case here, because copy needs to + * happen under the zs lock, which does not work with + * MIGRATE_SYNC_NO_COPY workflow. + */ + if (mode == MIGRATE_SYNC_NO_COPY) + return -EINVAL; + + VM_BUG_ON_PAGE(!PageMovable(page), page); + VM_BUG_ON_PAGE(!PageIsolated(page), page); + + zspage = get_zspage(page); + + /* Concurrent compactor cannot migrate any subpage in zspage */ + migrate_write_lock(zspage); + get_zspage_mapping(zspage, &class_idx, &fullness); + pool = mapping->private_data; + class = pool->size_class[class_idx]; + offset = get_first_obj_offset(page); + + spin_lock(&class->lock); + if (!get_zspage_inuse(zspage)) { + /* + * Set "offset" to end of the page so that every loops + * skips unnecessary object scanning. + */ + offset = PAGE_SIZE; + } + + pos = offset; + s_addr = kmap_atomic(page); + while (pos < PAGE_SIZE) { + head = obj_to_head(page, s_addr + pos); + if (head & OBJ_ALLOCATED_TAG) { + handle = head & ~OBJ_ALLOCATED_TAG; + if (!trypin_tag(handle)) + goto unpin_objects; + } + pos += class->size; + } + + /* + * Here, any user cannot access all objects in the zspage so let's move. + */ + d_addr = kmap_atomic(newpage); + memcpy(d_addr, s_addr, PAGE_SIZE); + kunmap_atomic(d_addr); + + for (addr = s_addr + offset; addr < s_addr + pos; + addr += class->size) { + head = obj_to_head(page, addr); + if (head & OBJ_ALLOCATED_TAG) { + handle = head & ~OBJ_ALLOCATED_TAG; + if (!testpin_tag(handle)) + BUG(); + + old_obj = handle_to_obj(handle); + obj_to_location(old_obj, &dummy, &obj_idx); + new_obj = (unsigned long)location_to_obj(newpage, + obj_idx); + new_obj |= BIT(HANDLE_PIN_BIT); + record_obj(handle, new_obj); + } + } + + replace_sub_page(class, zspage, newpage, page); + get_page(newpage); + + dec_zspage_isolation(zspage); + + /* + * Page migration is done so let's putback isolated zspage to + * the list if @page is final isolated subpage in the zspage. + */ + if (!is_zspage_isolated(zspage)) { + /* + * We cannot race with zs_destroy_pool() here because we wait + * for isolation to hit zero before we start destroying. + * Also, we ensure that everyone can see pool->destroying before + * we start waiting. + */ + putback_zspage_deferred(pool, class, zspage); + zs_pool_dec_isolated(pool); + } + + if (page_zone(newpage) != page_zone(page)) { + dec_zone_page_state(page, NR_ZSPAGES); + inc_zone_page_state(newpage, NR_ZSPAGES); + } + + reset_page(page); + put_page(page); + page = newpage; + + ret = MIGRATEPAGE_SUCCESS; +unpin_objects: + for (addr = s_addr + offset; addr < s_addr + pos; + addr += class->size) { + head = obj_to_head(page, addr); + if (head & OBJ_ALLOCATED_TAG) { + handle = head & ~OBJ_ALLOCATED_TAG; + if (!testpin_tag(handle)) + BUG(); + unpin_tag(handle); + } + } + kunmap_atomic(s_addr); + spin_unlock(&class->lock); + migrate_write_unlock(zspage); + + return ret; +} + +static void zs_page_putback(struct page *page) +{ + struct zs_pool *pool; + struct size_class *class; + int class_idx; + enum fullness_group fg; + struct address_space *mapping; + struct zspage *zspage; + + VM_BUG_ON_PAGE(!PageMovable(page), page); + VM_BUG_ON_PAGE(!PageIsolated(page), page); + + zspage = get_zspage(page); + get_zspage_mapping(zspage, &class_idx, &fg); + mapping = page_mapping(page); + pool = mapping->private_data; + class = pool->size_class[class_idx]; + + spin_lock(&class->lock); + dec_zspage_isolation(zspage); + if (!is_zspage_isolated(zspage)) { + /* + * Due to page_lock, we cannot free zspage immediately + * so let's defer. + */ + putback_zspage_deferred(pool, class, zspage); + zs_pool_dec_isolated(pool); + } + spin_unlock(&class->lock); +} + +static const struct address_space_operations zsmalloc_aops = { + .isolate_page = zs_page_isolate, + .migratepage = zs_page_migrate, + .putback_page = zs_page_putback, +}; + +static int zs_register_migration(struct zs_pool *pool) +{ + pool->inode = alloc_anon_inode(zsmalloc_mnt->mnt_sb); + if (IS_ERR(pool->inode)) { + pool->inode = NULL; + return 1; + } + + pool->inode->i_mapping->private_data = pool; + pool->inode->i_mapping->a_ops = &zsmalloc_aops; + return 0; +} + +static bool pool_isolated_are_drained(struct zs_pool *pool) +{ + return atomic_long_read(&pool->isolated_pages) == 0; +} + +/* Function for resolving migration */ +static void wait_for_isolated_drain(struct zs_pool *pool) +{ + + /* + * We're in the process of destroying the pool, so there are no + * active allocations. zs_page_isolate() fails for completely free + * zspages, so we need only wait for the zs_pool's isolated + * count to hit zero. + */ + wait_event(pool->migration_wait, + pool_isolated_are_drained(pool)); +} + +static void zs_unregister_migration(struct zs_pool *pool) +{ + pool->destroying = true; + /* + * We need a memory barrier here to ensure global visibility of + * pool->destroying. Thus pool->isolated pages will either be 0 in which + * case we don't care, or it will be > 0 and pool->destroying will + * ensure that we wake up once isolation hits 0. + */ + smp_mb(); + wait_for_isolated_drain(pool); /* This can block */ + flush_work(&pool->free_work); + iput(pool->inode); +} + +/* + * Caller should hold page_lock of all pages in the zspage + * In here, we cannot use zspage meta data. + */ +static void async_free_zspage(struct work_struct *work) +{ + int i; + struct size_class *class; + unsigned int class_idx; + enum fullness_group fullness; + struct zspage *zspage, *tmp; + LIST_HEAD(free_pages); + struct zs_pool *pool = container_of(work, struct zs_pool, + free_work); + + for (i = 0; i < ZS_SIZE_CLASSES; i++) { + class = pool->size_class[i]; + if (class->index != i) + continue; + + spin_lock(&class->lock); + list_splice_init(&class->fullness_list[ZS_EMPTY], &free_pages); + spin_unlock(&class->lock); + } + + + list_for_each_entry_safe(zspage, tmp, &free_pages, list) { + list_del(&zspage->list); + lock_zspage(zspage); + + get_zspage_mapping(zspage, &class_idx, &fullness); + VM_BUG_ON(fullness != ZS_EMPTY); + class = pool->size_class[class_idx]; + spin_lock(&class->lock); + __free_zspage(pool, pool->size_class[class_idx], zspage); + spin_unlock(&class->lock); + } +}; + +static void kick_deferred_free(struct zs_pool *pool) +{ + schedule_work(&pool->free_work); +} + +static void init_deferred_free(struct zs_pool *pool) +{ + INIT_WORK(&pool->free_work, async_free_zspage); +} + +static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage) +{ + struct page *page = get_first_page(zspage); + + do { + WARN_ON(!trylock_page(page)); + __SetPageMovable(page, pool->inode->i_mapping); + unlock_page(page); + } while ((page = get_next_page(page)) != NULL); +} +#endif + +/* + * + * Based on the number of unused allocated objects calculate + * and return the number of pages that we can free. + */ +static unsigned long zs_can_compact(struct size_class *class) +{ + unsigned long obj_wasted; + unsigned long obj_allocated = zs_stat_get(class, OBJ_ALLOCATED); + unsigned long obj_used = zs_stat_get(class, OBJ_USED); + + if (obj_allocated <= obj_used) + return 0; + + obj_wasted = obj_allocated - obj_used; + obj_wasted /= class->objs_per_zspage; + + return obj_wasted * class->pages_per_zspage; +} + +static unsigned long __zs_compact(struct zs_pool *pool, + struct size_class *class) +{ + struct zs_compact_control cc; + struct zspage *src_zspage; + struct zspage *dst_zspage = NULL; + unsigned long pages_freed = 0; + + spin_lock(&class->lock); + while ((src_zspage = isolate_zspage(class, true))) { + + if (!zs_can_compact(class)) + break; + + cc.obj_idx = 0; + cc.s_page = get_first_page(src_zspage); + + while ((dst_zspage = isolate_zspage(class, false))) { + cc.d_page = get_first_page(dst_zspage); + /* + * If there is no more space in dst_page, resched + * and see if anyone had allocated another zspage. + */ + if (!migrate_zspage(pool, class, &cc)) + break; + + putback_zspage(class, dst_zspage); + } + + /* Stop if we couldn't find slot */ + if (dst_zspage == NULL) + break; + + putback_zspage(class, dst_zspage); + if (putback_zspage(class, src_zspage) == ZS_EMPTY) { + free_zspage(pool, class, src_zspage); + pages_freed += class->pages_per_zspage; + } + spin_unlock(&class->lock); + cond_resched(); + spin_lock(&class->lock); + } + + if (src_zspage) + putback_zspage(class, src_zspage); + + spin_unlock(&class->lock); + + return pages_freed; +} + +unsigned long zs_compact(struct zs_pool *pool) +{ + int i; + struct size_class *class; + unsigned long pages_freed = 0; + + for (i = ZS_SIZE_CLASSES - 1; i >= 0; i--) { + class = pool->size_class[i]; + if (!class) + continue; + if (class->index != i) + continue; + pages_freed += __zs_compact(pool, class); + } + atomic_long_add(pages_freed, &pool->stats.pages_compacted); + + return pages_freed; +} +EXPORT_SYMBOL_GPL(zs_compact); + +void zs_pool_stats(struct zs_pool *pool, struct zs_pool_stats *stats) +{ + memcpy(stats, &pool->stats, sizeof(struct zs_pool_stats)); +} +EXPORT_SYMBOL_GPL(zs_pool_stats); + +static unsigned long zs_shrinker_scan(struct shrinker *shrinker, + struct shrink_control *sc) +{ + unsigned long pages_freed; + struct zs_pool *pool = container_of(shrinker, struct zs_pool, + shrinker); + + /* + * Compact classes and calculate compaction delta. + * Can run concurrently with a manually triggered + * (by user) compaction. + */ + pages_freed = zs_compact(pool); + + return pages_freed ? pages_freed : SHRINK_STOP; +} + +static unsigned long zs_shrinker_count(struct shrinker *shrinker, + struct shrink_control *sc) +{ + int i; + struct size_class *class; + unsigned long pages_to_free = 0; + struct zs_pool *pool = container_of(shrinker, struct zs_pool, + shrinker); + + for (i = ZS_SIZE_CLASSES - 1; i >= 0; i--) { + class = pool->size_class[i]; + if (!class) + continue; + if (class->index != i) + continue; + + pages_to_free += zs_can_compact(class); + } + + return pages_to_free; +} + +static void zs_unregister_shrinker(struct zs_pool *pool) +{ + unregister_shrinker(&pool->shrinker); +} + +static int zs_register_shrinker(struct zs_pool *pool) +{ + pool->shrinker.scan_objects = zs_shrinker_scan; + pool->shrinker.count_objects = zs_shrinker_count; + pool->shrinker.batch = 0; + pool->shrinker.seeks = DEFAULT_SEEKS; + + return register_shrinker(&pool->shrinker); +} + +/** + * zs_create_pool - Creates an allocation pool to work from. + * @name: pool name to be created + * + * This function must be called before anything when using + * the zsmalloc allocator. + * + * On success, a pointer to the newly created pool is returned, + * otherwise NULL. + */ +struct zs_pool *zs_create_pool(const char *name) +{ + int i; + struct zs_pool *pool; + struct size_class *prev_class = NULL; + + pool = kzalloc(sizeof(*pool), GFP_KERNEL); + if (!pool) + return NULL; + + init_deferred_free(pool); + + pool->name = kstrdup(name, GFP_KERNEL); + if (!pool->name) + goto err; + +#ifdef CONFIG_COMPACTION + init_waitqueue_head(&pool->migration_wait); +#endif + + if (create_cache(pool)) + goto err; + + /* + * Iterate reversely, because, size of size_class that we want to use + * for merging should be larger or equal to current size. + */ + for (i = ZS_SIZE_CLASSES - 1; i >= 0; i--) { + int size; + int pages_per_zspage; + int objs_per_zspage; + struct size_class *class; + int fullness = 0; + + size = ZS_MIN_ALLOC_SIZE + i * ZS_SIZE_CLASS_DELTA; + if (size > ZS_MAX_ALLOC_SIZE) + size = ZS_MAX_ALLOC_SIZE; + pages_per_zspage = get_pages_per_zspage(size); + objs_per_zspage = pages_per_zspage * PAGE_SIZE / size; + + /* + * We iterate from biggest down to smallest classes, + * so huge_class_size holds the size of the first huge + * class. Any object bigger than or equal to that will + * endup in the huge class. + */ + if (pages_per_zspage != 1 && objs_per_zspage != 1 && + !huge_class_size) { + huge_class_size = size; + /* + * The object uses ZS_HANDLE_SIZE bytes to store the + * handle. We need to subtract it, because zs_malloc() + * unconditionally adds handle size before it performs + * size class search - so object may be smaller than + * huge class size, yet it still can end up in the huge + * class because it grows by ZS_HANDLE_SIZE extra bytes + * right before class lookup. + */ + huge_class_size -= (ZS_HANDLE_SIZE - 1); + } + + /* + * size_class is used for normal zsmalloc operation such + * as alloc/free for that size. Although it is natural that we + * have one size_class for each size, there is a chance that we + * can get more memory utilization if we use one size_class for + * many different sizes whose size_class have same + * characteristics. So, we makes size_class point to + * previous size_class if possible. + */ + if (prev_class) { + if (can_merge(prev_class, pages_per_zspage, objs_per_zspage)) { + pool->size_class[i] = prev_class; + continue; + } + } + + class = kzalloc(sizeof(struct size_class), GFP_KERNEL); + if (!class) + goto err; + + class->size = size; + class->index = i; + class->pages_per_zspage = pages_per_zspage; + class->objs_per_zspage = objs_per_zspage; + spin_lock_init(&class->lock); + pool->size_class[i] = class; + for (fullness = ZS_EMPTY; fullness < NR_ZS_FULLNESS; + fullness++) + INIT_LIST_HEAD(&class->fullness_list[fullness]); + + prev_class = class; + } + + /* debug only, don't abort if it fails */ + zs_pool_stat_create(pool, name); + + if (zs_register_migration(pool)) + goto err; + + /* + * Not critical since shrinker is only used to trigger internal + * defragmentation of the pool which is pretty optional thing. If + * registration fails we still can use the pool normally and user can + * trigger compaction manually. Thus, ignore return code. + */ + zs_register_shrinker(pool); + + return pool; + +err: + zs_destroy_pool(pool); + return NULL; +} +EXPORT_SYMBOL_GPL(zs_create_pool); + +void zs_destroy_pool(struct zs_pool *pool) +{ + int i; + + zs_unregister_shrinker(pool); + zs_unregister_migration(pool); + zs_pool_stat_destroy(pool); + + for (i = 0; i < ZS_SIZE_CLASSES; i++) { + int fg; + struct size_class *class = pool->size_class[i]; + + if (!class) + continue; + + if (class->index != i) + continue; + + for (fg = ZS_EMPTY; fg < NR_ZS_FULLNESS; fg++) { + if (!list_empty(&class->fullness_list[fg])) { + pr_info("Freeing non-empty class with size %db, fullness group %d\n", + class->size, fg); + } + } + kfree(class); + } + + destroy_cache(pool); + kfree(pool->name); + kfree(pool); +} +EXPORT_SYMBOL_GPL(zs_destroy_pool); + +static int __init zs_init(void) +{ + int ret; + + ret = zsmalloc_mount(); + if (ret) + goto out; + + ret = cpuhp_setup_state(CPUHP_MM_ZS_PREPARE, "mm/zsmalloc:prepare", + zs_cpu_prepare, zs_cpu_dead); + if (ret) + goto hp_setup_fail; + +#ifdef CONFIG_ZPOOL + zpool_register_driver(&zs_zpool_driver); +#endif + + zs_stat_init(); + + return 0; + +hp_setup_fail: + zsmalloc_unmount(); +out: + return ret; +} + +static void __exit zs_exit(void) +{ +#ifdef CONFIG_ZPOOL + zpool_unregister_driver(&zs_zpool_driver); +#endif + zsmalloc_unmount(); + cpuhp_remove_state(CPUHP_MM_ZS_PREPARE); + + zs_stat_exit(); +} + +module_init(zs_init); +module_exit(zs_exit); + +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_AUTHOR("Nitin Gupta "); diff --git a/mm/zswap.c b/mm/zswap.c new file mode 100644 index 000000000..fbb782924 --- /dev/null +++ b/mm/zswap.c @@ -0,0 +1,1379 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * zswap.c - zswap driver file + * + * zswap is a backend for frontswap that takes pages that are in the process + * of being swapped out and attempts to compress and store them in a + * RAM-based memory pool. This can result in a significant I/O reduction on + * the swap device and, in the case where decompressing from RAM is faster + * than reading from the swap device, can also improve workload performance. + * + * Copyright (C) 2012 Seth Jennings +*/ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include + +/********************************* +* statistics +**********************************/ +/* Total bytes used by the compressed storage */ +static u64 zswap_pool_total_size; +/* The number of compressed pages currently stored in zswap */ +static atomic_t zswap_stored_pages = ATOMIC_INIT(0); +/* The number of same-value filled pages currently stored in zswap */ +static atomic_t zswap_same_filled_pages = ATOMIC_INIT(0); + +/* + * The statistics below are not protected from concurrent access for + * performance reasons so they may not be a 100% accurate. However, + * they do provide useful information on roughly how many times a + * certain event is occurring. +*/ + +/* Pool limit was hit (see zswap_max_pool_percent) */ +static u64 zswap_pool_limit_hit; +/* Pages written back when pool limit was reached */ +static u64 zswap_written_back_pages; +/* Store failed due to a reclaim failure after pool limit was reached */ +static u64 zswap_reject_reclaim_fail; +/* Compressed page was too big for the allocator to (optimally) store */ +static u64 zswap_reject_compress_poor; +/* Store failed because underlying allocator could not get memory */ +static u64 zswap_reject_alloc_fail; +/* Store failed because the entry metadata could not be allocated (rare) */ +static u64 zswap_reject_kmemcache_fail; +/* Duplicate store was encountered (rare) */ +static u64 zswap_duplicate_entry; + +/* Shrinker work queue */ +static struct workqueue_struct *shrink_wq; +/* Pool limit was hit, we need to calm down */ +static bool zswap_pool_reached_full; + +/********************************* +* tunables +**********************************/ + +#define ZSWAP_PARAM_UNSET "" + +/* Enable/disable zswap */ +static bool zswap_enabled = IS_ENABLED(CONFIG_ZSWAP_DEFAULT_ON); +static int zswap_enabled_param_set(const char *, + const struct kernel_param *); +static struct kernel_param_ops zswap_enabled_param_ops = { + .set = zswap_enabled_param_set, + .get = param_get_bool, +}; +module_param_cb(enabled, &zswap_enabled_param_ops, &zswap_enabled, 0644); + +/* Crypto compressor to use */ +static char *zswap_compressor = CONFIG_ZSWAP_COMPRESSOR_DEFAULT; +static int zswap_compressor_param_set(const char *, + const struct kernel_param *); +static struct kernel_param_ops zswap_compressor_param_ops = { + .set = zswap_compressor_param_set, + .get = param_get_charp, + .free = param_free_charp, +}; +module_param_cb(compressor, &zswap_compressor_param_ops, + &zswap_compressor, 0644); + +/* Compressed storage zpool to use */ +static char *zswap_zpool_type = CONFIG_ZSWAP_ZPOOL_DEFAULT; +static int zswap_zpool_param_set(const char *, const struct kernel_param *); +static struct kernel_param_ops zswap_zpool_param_ops = { + .set = zswap_zpool_param_set, + .get = param_get_charp, + .free = param_free_charp, +}; +module_param_cb(zpool, &zswap_zpool_param_ops, &zswap_zpool_type, 0644); + +/* The maximum percentage of memory that the compressed pool can occupy */ +static unsigned int zswap_max_pool_percent = 20; +module_param_named(max_pool_percent, zswap_max_pool_percent, uint, 0644); + +/* The threshold for accepting new pages after the max_pool_percent was hit */ +static unsigned int zswap_accept_thr_percent = 90; /* of max pool size */ +module_param_named(accept_threshold_percent, zswap_accept_thr_percent, + uint, 0644); + +/* Enable/disable handling same-value filled pages (enabled by default) */ +static bool zswap_same_filled_pages_enabled = true; +module_param_named(same_filled_pages_enabled, zswap_same_filled_pages_enabled, + bool, 0644); + +/********************************* +* data structures +**********************************/ + +struct zswap_pool { + struct zpool *zpool; + struct crypto_comp * __percpu *tfm; + struct kref kref; + struct list_head list; + struct work_struct release_work; + struct work_struct shrink_work; + struct hlist_node node; + char tfm_name[CRYPTO_MAX_ALG_NAME]; +}; + +/* + * struct zswap_entry + * + * This structure contains the metadata for tracking a single compressed + * page within zswap. + * + * rbnode - links the entry into red-black tree for the appropriate swap type + * offset - the swap offset for the entry. Index into the red-black tree. + * refcount - the number of outstanding reference to the entry. This is needed + * to protect against premature freeing of the entry by code + * concurrent calls to load, invalidate, and writeback. The lock + * for the zswap_tree structure that contains the entry must + * be held while changing the refcount. Since the lock must + * be held, there is no reason to also make refcount atomic. + * length - the length in bytes of the compressed page data. Needed during + * decompression. For a same value filled page length is 0. + * pool - the zswap_pool the entry's data is in + * handle - zpool allocation handle that stores the compressed page data + * value - value of the same-value filled pages which have same content + */ +struct zswap_entry { + struct rb_node rbnode; + pgoff_t offset; + int refcount; + unsigned int length; + struct zswap_pool *pool; + union { + unsigned long handle; + unsigned long value; + }; +}; + +struct zswap_header { + swp_entry_t swpentry; +}; + +/* + * The tree lock in the zswap_tree struct protects a few things: + * - the rbtree + * - the refcount field of each entry in the tree + */ +struct zswap_tree { + struct rb_root rbroot; + spinlock_t lock; +}; + +static struct zswap_tree *zswap_trees[MAX_SWAPFILES]; + +/* RCU-protected iteration */ +static LIST_HEAD(zswap_pools); +/* protects zswap_pools list modification */ +static DEFINE_SPINLOCK(zswap_pools_lock); +/* pool counter to provide unique names to zpool */ +static atomic_t zswap_pools_count = ATOMIC_INIT(0); + +/* used by param callback function */ +static bool zswap_init_started; + +/* fatal error during init */ +static bool zswap_init_failed; + +/* init completed, but couldn't create the initial pool */ +static bool zswap_has_pool; + +/********************************* +* helpers and fwd declarations +**********************************/ + +#define zswap_pool_debug(msg, p) \ + pr_debug("%s pool %s/%s\n", msg, (p)->tfm_name, \ + zpool_get_type((p)->zpool)) + +static int zswap_writeback_entry(struct zpool *pool, unsigned long handle); +static int zswap_pool_get(struct zswap_pool *pool); +static void zswap_pool_put(struct zswap_pool *pool); + +static const struct zpool_ops zswap_zpool_ops = { + .evict = zswap_writeback_entry +}; + +static bool zswap_is_full(void) +{ + return totalram_pages() * zswap_max_pool_percent / 100 < + DIV_ROUND_UP(zswap_pool_total_size, PAGE_SIZE); +} + +static bool zswap_can_accept(void) +{ + return totalram_pages() * zswap_accept_thr_percent / 100 * + zswap_max_pool_percent / 100 > + DIV_ROUND_UP(zswap_pool_total_size, PAGE_SIZE); +} + +static void zswap_update_total_size(void) +{ + struct zswap_pool *pool; + u64 total = 0; + + rcu_read_lock(); + + list_for_each_entry_rcu(pool, &zswap_pools, list) + total += zpool_get_total_size(pool->zpool); + + rcu_read_unlock(); + + zswap_pool_total_size = total; +} + +/********************************* +* zswap entry functions +**********************************/ +static struct kmem_cache *zswap_entry_cache; + +static int __init zswap_entry_cache_create(void) +{ + zswap_entry_cache = KMEM_CACHE(zswap_entry, 0); + return zswap_entry_cache == NULL; +} + +static void __init zswap_entry_cache_destroy(void) +{ + kmem_cache_destroy(zswap_entry_cache); +} + +static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp) +{ + struct zswap_entry *entry; + entry = kmem_cache_alloc(zswap_entry_cache, gfp); + if (!entry) + return NULL; + entry->refcount = 1; + RB_CLEAR_NODE(&entry->rbnode); + return entry; +} + +static void zswap_entry_cache_free(struct zswap_entry *entry) +{ + kmem_cache_free(zswap_entry_cache, entry); +} + +/********************************* +* rbtree functions +**********************************/ +static struct zswap_entry *zswap_rb_search(struct rb_root *root, pgoff_t offset) +{ + struct rb_node *node = root->rb_node; + struct zswap_entry *entry; + + while (node) { + entry = rb_entry(node, struct zswap_entry, rbnode); + if (entry->offset > offset) + node = node->rb_left; + else if (entry->offset < offset) + node = node->rb_right; + else + return entry; + } + return NULL; +} + +/* + * In the case that a entry with the same offset is found, a pointer to + * the existing entry is stored in dupentry and the function returns -EEXIST + */ +static int zswap_rb_insert(struct rb_root *root, struct zswap_entry *entry, + struct zswap_entry **dupentry) +{ + struct rb_node **link = &root->rb_node, *parent = NULL; + struct zswap_entry *myentry; + + while (*link) { + parent = *link; + myentry = rb_entry(parent, struct zswap_entry, rbnode); + if (myentry->offset > entry->offset) + link = &(*link)->rb_left; + else if (myentry->offset < entry->offset) + link = &(*link)->rb_right; + else { + *dupentry = myentry; + return -EEXIST; + } + } + rb_link_node(&entry->rbnode, parent, link); + rb_insert_color(&entry->rbnode, root); + return 0; +} + +static void zswap_rb_erase(struct rb_root *root, struct zswap_entry *entry) +{ + if (!RB_EMPTY_NODE(&entry->rbnode)) { + rb_erase(&entry->rbnode, root); + RB_CLEAR_NODE(&entry->rbnode); + } +} + +/* + * Carries out the common pattern of freeing and entry's zpool allocation, + * freeing the entry itself, and decrementing the number of stored pages. + */ +static void zswap_free_entry(struct zswap_entry *entry) +{ + if (!entry->length) + atomic_dec(&zswap_same_filled_pages); + else { + zpool_free(entry->pool->zpool, entry->handle); + zswap_pool_put(entry->pool); + } + zswap_entry_cache_free(entry); + atomic_dec(&zswap_stored_pages); + zswap_update_total_size(); +} + +/* caller must hold the tree lock */ +static void zswap_entry_get(struct zswap_entry *entry) +{ + entry->refcount++; +} + +/* caller must hold the tree lock +* remove from the tree and free it, if nobody reference the entry +*/ +static void zswap_entry_put(struct zswap_tree *tree, + struct zswap_entry *entry) +{ + int refcount = --entry->refcount; + + BUG_ON(refcount < 0); + if (refcount == 0) { + zswap_rb_erase(&tree->rbroot, entry); + zswap_free_entry(entry); + } +} + +/* caller must hold the tree lock */ +static struct zswap_entry *zswap_entry_find_get(struct rb_root *root, + pgoff_t offset) +{ + struct zswap_entry *entry; + + entry = zswap_rb_search(root, offset); + if (entry) + zswap_entry_get(entry); + + return entry; +} + +/********************************* +* per-cpu code +**********************************/ +static DEFINE_PER_CPU(u8 *, zswap_dstmem); + +static int zswap_dstmem_prepare(unsigned int cpu) +{ + u8 *dst; + + dst = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu)); + if (!dst) + return -ENOMEM; + + per_cpu(zswap_dstmem, cpu) = dst; + return 0; +} + +static int zswap_dstmem_dead(unsigned int cpu) +{ + u8 *dst; + + dst = per_cpu(zswap_dstmem, cpu); + kfree(dst); + per_cpu(zswap_dstmem, cpu) = NULL; + + return 0; +} + +static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) +{ + struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node); + struct crypto_comp *tfm; + + if (WARN_ON(*per_cpu_ptr(pool->tfm, cpu))) + return 0; + + tfm = crypto_alloc_comp(pool->tfm_name, 0, 0); + if (IS_ERR_OR_NULL(tfm)) { + pr_err("could not alloc crypto comp %s : %ld\n", + pool->tfm_name, PTR_ERR(tfm)); + return -ENOMEM; + } + *per_cpu_ptr(pool->tfm, cpu) = tfm; + return 0; +} + +static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node) +{ + struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node); + struct crypto_comp *tfm; + + tfm = *per_cpu_ptr(pool->tfm, cpu); + if (!IS_ERR_OR_NULL(tfm)) + crypto_free_comp(tfm); + *per_cpu_ptr(pool->tfm, cpu) = NULL; + return 0; +} + +/********************************* +* pool functions +**********************************/ + +static struct zswap_pool *__zswap_pool_current(void) +{ + struct zswap_pool *pool; + + pool = list_first_or_null_rcu(&zswap_pools, typeof(*pool), list); + WARN_ONCE(!pool && zswap_has_pool, + "%s: no page storage pool!\n", __func__); + + return pool; +} + +static struct zswap_pool *zswap_pool_current(void) +{ + assert_spin_locked(&zswap_pools_lock); + + return __zswap_pool_current(); +} + +static struct zswap_pool *zswap_pool_current_get(void) +{ + struct zswap_pool *pool; + + rcu_read_lock(); + + pool = __zswap_pool_current(); + if (!zswap_pool_get(pool)) + pool = NULL; + + rcu_read_unlock(); + + return pool; +} + +static struct zswap_pool *zswap_pool_last_get(void) +{ + struct zswap_pool *pool, *last = NULL; + + rcu_read_lock(); + + list_for_each_entry_rcu(pool, &zswap_pools, list) + last = pool; + WARN_ONCE(!last && zswap_has_pool, + "%s: no page storage pool!\n", __func__); + if (!zswap_pool_get(last)) + last = NULL; + + rcu_read_unlock(); + + return last; +} + +/* type and compressor must be null-terminated */ +static struct zswap_pool *zswap_pool_find_get(char *type, char *compressor) +{ + struct zswap_pool *pool; + + assert_spin_locked(&zswap_pools_lock); + + list_for_each_entry_rcu(pool, &zswap_pools, list) { + if (strcmp(pool->tfm_name, compressor)) + continue; + if (strcmp(zpool_get_type(pool->zpool), type)) + continue; + /* if we can't get it, it's about to be destroyed */ + if (!zswap_pool_get(pool)) + continue; + return pool; + } + + return NULL; +} + +static void shrink_worker(struct work_struct *w) +{ + struct zswap_pool *pool = container_of(w, typeof(*pool), + shrink_work); + + if (zpool_shrink(pool->zpool, 1, NULL)) + zswap_reject_reclaim_fail++; + zswap_pool_put(pool); +} + +static struct zswap_pool *zswap_pool_create(char *type, char *compressor) +{ + struct zswap_pool *pool; + char name[38]; /* 'zswap' + 32 char (max) num + \0 */ + gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM; + int ret; + + if (!zswap_has_pool) { + /* if either are unset, pool initialization failed, and we + * need both params to be set correctly before trying to + * create a pool. + */ + if (!strcmp(type, ZSWAP_PARAM_UNSET)) + return NULL; + if (!strcmp(compressor, ZSWAP_PARAM_UNSET)) + return NULL; + } + + pool = kzalloc(sizeof(*pool), GFP_KERNEL); + if (!pool) + return NULL; + + /* unique name for each pool specifically required by zsmalloc */ + snprintf(name, 38, "zswap%x", atomic_inc_return(&zswap_pools_count)); + + pool->zpool = zpool_create_pool(type, name, gfp, &zswap_zpool_ops); + if (!pool->zpool) { + pr_err("%s zpool not available\n", type); + goto error; + } + pr_debug("using %s zpool\n", zpool_get_type(pool->zpool)); + + strlcpy(pool->tfm_name, compressor, sizeof(pool->tfm_name)); + pool->tfm = alloc_percpu(struct crypto_comp *); + if (!pool->tfm) { + pr_err("percpu alloc failed\n"); + goto error; + } + + ret = cpuhp_state_add_instance(CPUHP_MM_ZSWP_POOL_PREPARE, + &pool->node); + if (ret) + goto error; + pr_debug("using %s compressor\n", pool->tfm_name); + + /* being the current pool takes 1 ref; this func expects the + * caller to always add the new pool as the current pool + */ + kref_init(&pool->kref); + INIT_LIST_HEAD(&pool->list); + INIT_WORK(&pool->shrink_work, shrink_worker); + + zswap_pool_debug("created", pool); + + return pool; + +error: + free_percpu(pool->tfm); + if (pool->zpool) + zpool_destroy_pool(pool->zpool); + kfree(pool); + return NULL; +} + +static __init struct zswap_pool *__zswap_pool_create_fallback(void) +{ + bool has_comp, has_zpool; + + has_comp = crypto_has_comp(zswap_compressor, 0, 0); + if (!has_comp && strcmp(zswap_compressor, + CONFIG_ZSWAP_COMPRESSOR_DEFAULT)) { + pr_err("compressor %s not available, using default %s\n", + zswap_compressor, CONFIG_ZSWAP_COMPRESSOR_DEFAULT); + param_free_charp(&zswap_compressor); + zswap_compressor = CONFIG_ZSWAP_COMPRESSOR_DEFAULT; + has_comp = crypto_has_comp(zswap_compressor, 0, 0); + } + if (!has_comp) { + pr_err("default compressor %s not available\n", + zswap_compressor); + param_free_charp(&zswap_compressor); + zswap_compressor = ZSWAP_PARAM_UNSET; + } + + has_zpool = zpool_has_pool(zswap_zpool_type); + if (!has_zpool && strcmp(zswap_zpool_type, + CONFIG_ZSWAP_ZPOOL_DEFAULT)) { + pr_err("zpool %s not available, using default %s\n", + zswap_zpool_type, CONFIG_ZSWAP_ZPOOL_DEFAULT); + param_free_charp(&zswap_zpool_type); + zswap_zpool_type = CONFIG_ZSWAP_ZPOOL_DEFAULT; + has_zpool = zpool_has_pool(zswap_zpool_type); + } + if (!has_zpool) { + pr_err("default zpool %s not available\n", + zswap_zpool_type); + param_free_charp(&zswap_zpool_type); + zswap_zpool_type = ZSWAP_PARAM_UNSET; + } + + if (!has_comp || !has_zpool) + return NULL; + + return zswap_pool_create(zswap_zpool_type, zswap_compressor); +} + +static void zswap_pool_destroy(struct zswap_pool *pool) +{ + zswap_pool_debug("destroying", pool); + + cpuhp_state_remove_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node); + free_percpu(pool->tfm); + zpool_destroy_pool(pool->zpool); + kfree(pool); +} + +static int __must_check zswap_pool_get(struct zswap_pool *pool) +{ + if (!pool) + return 0; + + return kref_get_unless_zero(&pool->kref); +} + +static void __zswap_pool_release(struct work_struct *work) +{ + struct zswap_pool *pool = container_of(work, typeof(*pool), + release_work); + + synchronize_rcu(); + + /* nobody should have been able to get a kref... */ + WARN_ON(kref_get_unless_zero(&pool->kref)); + + /* pool is now off zswap_pools list and has no references. */ + zswap_pool_destroy(pool); +} + +static void __zswap_pool_empty(struct kref *kref) +{ + struct zswap_pool *pool; + + pool = container_of(kref, typeof(*pool), kref); + + spin_lock(&zswap_pools_lock); + + WARN_ON(pool == zswap_pool_current()); + + list_del_rcu(&pool->list); + + INIT_WORK(&pool->release_work, __zswap_pool_release); + schedule_work(&pool->release_work); + + spin_unlock(&zswap_pools_lock); +} + +static void zswap_pool_put(struct zswap_pool *pool) +{ + kref_put(&pool->kref, __zswap_pool_empty); +} + +/********************************* +* param callbacks +**********************************/ + +/* val must be a null-terminated string */ +static int __zswap_param_set(const char *val, const struct kernel_param *kp, + char *type, char *compressor) +{ + struct zswap_pool *pool, *put_pool = NULL; + char *s = strstrip((char *)val); + int ret; + + if (zswap_init_failed) { + pr_err("can't set param, initialization failed\n"); + return -ENODEV; + } + + /* no change required */ + if (!strcmp(s, *(char **)kp->arg) && zswap_has_pool) + return 0; + + /* if this is load-time (pre-init) param setting, + * don't create a pool; that's done during init. + */ + if (!zswap_init_started) + return param_set_charp(s, kp); + + if (!type) { + if (!zpool_has_pool(s)) { + pr_err("zpool %s not available\n", s); + return -ENOENT; + } + type = s; + } else if (!compressor) { + if (!crypto_has_comp(s, 0, 0)) { + pr_err("compressor %s not available\n", s); + return -ENOENT; + } + compressor = s; + } else { + WARN_ON(1); + return -EINVAL; + } + + spin_lock(&zswap_pools_lock); + + pool = zswap_pool_find_get(type, compressor); + if (pool) { + zswap_pool_debug("using existing", pool); + WARN_ON(pool == zswap_pool_current()); + list_del_rcu(&pool->list); + } + + spin_unlock(&zswap_pools_lock); + + if (!pool) + pool = zswap_pool_create(type, compressor); + + if (pool) + ret = param_set_charp(s, kp); + else + ret = -EINVAL; + + spin_lock(&zswap_pools_lock); + + if (!ret) { + put_pool = zswap_pool_current(); + list_add_rcu(&pool->list, &zswap_pools); + zswap_has_pool = true; + } else if (pool) { + /* add the possibly pre-existing pool to the end of the pools + * list; if it's new (and empty) then it'll be removed and + * destroyed by the put after we drop the lock + */ + list_add_tail_rcu(&pool->list, &zswap_pools); + put_pool = pool; + } + + spin_unlock(&zswap_pools_lock); + + if (!zswap_has_pool && !pool) { + /* if initial pool creation failed, and this pool creation also + * failed, maybe both compressor and zpool params were bad. + * Allow changing this param, so pool creation will succeed + * when the other param is changed. We already verified this + * param is ok in the zpool_has_pool() or crypto_has_comp() + * checks above. + */ + ret = param_set_charp(s, kp); + } + + /* drop the ref from either the old current pool, + * or the new pool we failed to add + */ + if (put_pool) + zswap_pool_put(put_pool); + + return ret; +} + +static int zswap_compressor_param_set(const char *val, + const struct kernel_param *kp) +{ + return __zswap_param_set(val, kp, zswap_zpool_type, NULL); +} + +static int zswap_zpool_param_set(const char *val, + const struct kernel_param *kp) +{ + return __zswap_param_set(val, kp, NULL, zswap_compressor); +} + +static int zswap_enabled_param_set(const char *val, + const struct kernel_param *kp) +{ + if (zswap_init_failed) { + pr_err("can't enable, initialization failed\n"); + return -ENODEV; + } + if (!zswap_has_pool && zswap_init_started) { + pr_err("can't enable, no pool configured\n"); + return -ENODEV; + } + + return param_set_bool(val, kp); +} + +/********************************* +* writeback code +**********************************/ +/* return enum for zswap_get_swap_cache_page */ +enum zswap_get_swap_ret { + ZSWAP_SWAPCACHE_NEW, + ZSWAP_SWAPCACHE_EXIST, + ZSWAP_SWAPCACHE_FAIL, +}; + +/* + * zswap_get_swap_cache_page + * + * This is an adaption of read_swap_cache_async() + * + * This function tries to find a page with the given swap entry + * in the swapper_space address space (the swap cache). If the page + * is found, it is returned in retpage. Otherwise, a page is allocated, + * added to the swap cache, and returned in retpage. + * + * If success, the swap cache page is returned in retpage + * Returns ZSWAP_SWAPCACHE_EXIST if page was already in the swap cache + * Returns ZSWAP_SWAPCACHE_NEW if the new page needs to be populated, + * the new page is added to swapcache and locked + * Returns ZSWAP_SWAPCACHE_FAIL on error + */ +static int zswap_get_swap_cache_page(swp_entry_t entry, + struct page **retpage) +{ + bool page_was_allocated; + + *retpage = __read_swap_cache_async(entry, GFP_KERNEL, + NULL, 0, &page_was_allocated); + if (page_was_allocated) + return ZSWAP_SWAPCACHE_NEW; + if (!*retpage) + return ZSWAP_SWAPCACHE_FAIL; + return ZSWAP_SWAPCACHE_EXIST; +} + +/* + * Attempts to free an entry by adding a page to the swap cache, + * decompressing the entry data into the page, and issuing a + * bio write to write the page back to the swap device. + * + * This can be thought of as a "resumed writeback" of the page + * to the swap device. We are basically resuming the same swap + * writeback path that was intercepted with the frontswap_store() + * in the first place. After the page has been decompressed into + * the swap cache, the compressed version stored by zswap can be + * freed. + */ +static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) +{ + struct zswap_header *zhdr; + swp_entry_t swpentry; + struct zswap_tree *tree; + pgoff_t offset; + struct zswap_entry *entry; + struct page *page; + struct crypto_comp *tfm; + u8 *src, *dst; + unsigned int dlen; + int ret; + struct writeback_control wbc = { + .sync_mode = WB_SYNC_NONE, + }; + + /* extract swpentry from data */ + zhdr = zpool_map_handle(pool, handle, ZPOOL_MM_RO); + swpentry = zhdr->swpentry; /* here */ + tree = zswap_trees[swp_type(swpentry)]; + offset = swp_offset(swpentry); + + /* find and ref zswap entry */ + spin_lock(&tree->lock); + entry = zswap_entry_find_get(&tree->rbroot, offset); + if (!entry) { + /* entry was invalidated */ + spin_unlock(&tree->lock); + zpool_unmap_handle(pool, handle); + return 0; + } + spin_unlock(&tree->lock); + BUG_ON(offset != entry->offset); + + /* try to allocate swap cache page */ + switch (zswap_get_swap_cache_page(swpentry, &page)) { + case ZSWAP_SWAPCACHE_FAIL: /* no memory or invalidate happened */ + ret = -ENOMEM; + goto fail; + + case ZSWAP_SWAPCACHE_EXIST: + /* page is already in the swap cache, ignore for now */ + put_page(page); + ret = -EEXIST; + goto fail; + + case ZSWAP_SWAPCACHE_NEW: /* page is locked */ + /* decompress */ + dlen = PAGE_SIZE; + src = (u8 *)zhdr + sizeof(struct zswap_header); + dst = kmap_atomic(page); + tfm = *get_cpu_ptr(entry->pool->tfm); + ret = crypto_comp_decompress(tfm, src, entry->length, + dst, &dlen); + put_cpu_ptr(entry->pool->tfm); + kunmap_atomic(dst); + BUG_ON(ret); + BUG_ON(dlen != PAGE_SIZE); + + /* page is up to date */ + SetPageUptodate(page); + } + + /* move it to the tail of the inactive list after end_writeback */ + SetPageReclaim(page); + + /* start writeback */ + __swap_writepage(page, &wbc, end_swap_bio_write); + put_page(page); + zswap_written_back_pages++; + + spin_lock(&tree->lock); + /* drop local reference */ + zswap_entry_put(tree, entry); + + /* + * There are two possible situations for entry here: + * (1) refcount is 1(normal case), entry is valid and on the tree + * (2) refcount is 0, entry is freed and not on the tree + * because invalidate happened during writeback + * search the tree and free the entry if find entry + */ + if (entry == zswap_rb_search(&tree->rbroot, offset)) + zswap_entry_put(tree, entry); + spin_unlock(&tree->lock); + + goto end; + + /* + * if we get here due to ZSWAP_SWAPCACHE_EXIST + * a load may happening concurrently + * it is safe and okay to not free the entry + * if we free the entry in the following put + * it it either okay to return !0 + */ +fail: + spin_lock(&tree->lock); + zswap_entry_put(tree, entry); + spin_unlock(&tree->lock); + +end: + zpool_unmap_handle(pool, handle); + return ret; +} + +static int zswap_is_page_same_filled(void *ptr, unsigned long *value) +{ + unsigned int pos; + unsigned long *page; + + page = (unsigned long *)ptr; + for (pos = 1; pos < PAGE_SIZE / sizeof(*page); pos++) { + if (page[pos] != page[0]) + return 0; + } + *value = page[0]; + return 1; +} + +static void zswap_fill_page(void *ptr, unsigned long value) +{ + unsigned long *page; + + page = (unsigned long *)ptr; + memset_l(page, value, PAGE_SIZE / sizeof(unsigned long)); +} + +/********************************* +* frontswap hooks +**********************************/ +/* attempts to compress and store an single page */ +static int zswap_frontswap_store(unsigned type, pgoff_t offset, + struct page *page) +{ + struct zswap_tree *tree = zswap_trees[type]; + struct zswap_entry *entry, *dupentry; + struct crypto_comp *tfm; + int ret; + unsigned int hlen, dlen = PAGE_SIZE; + unsigned long handle, value; + char *buf; + u8 *src, *dst; + struct zswap_header zhdr = { .swpentry = swp_entry(type, offset) }; + gfp_t gfp; + + /* THP isn't supported */ + if (PageTransHuge(page)) { + ret = -EINVAL; + goto reject; + } + + if (!zswap_enabled || !tree) { + ret = -ENODEV; + goto reject; + } + + /* reclaim space if needed */ + if (zswap_is_full()) { + struct zswap_pool *pool; + + zswap_pool_limit_hit++; + zswap_pool_reached_full = true; + pool = zswap_pool_last_get(); + if (pool) + queue_work(shrink_wq, &pool->shrink_work); + ret = -ENOMEM; + goto reject; + } + + if (zswap_pool_reached_full) { + if (!zswap_can_accept()) { + ret = -ENOMEM; + goto reject; + } else + zswap_pool_reached_full = false; + } + + /* allocate entry */ + entry = zswap_entry_cache_alloc(GFP_KERNEL); + if (!entry) { + zswap_reject_kmemcache_fail++; + ret = -ENOMEM; + goto reject; + } + + if (zswap_same_filled_pages_enabled) { + src = kmap_atomic(page); + if (zswap_is_page_same_filled(src, &value)) { + kunmap_atomic(src); + entry->offset = offset; + entry->length = 0; + entry->value = value; + atomic_inc(&zswap_same_filled_pages); + goto insert_entry; + } + kunmap_atomic(src); + } + + /* if entry is successfully added, it keeps the reference */ + entry->pool = zswap_pool_current_get(); + if (!entry->pool) { + ret = -EINVAL; + goto freepage; + } + + /* compress */ + dst = get_cpu_var(zswap_dstmem); + tfm = *get_cpu_ptr(entry->pool->tfm); + src = kmap_atomic(page); + ret = crypto_comp_compress(tfm, src, PAGE_SIZE, dst, &dlen); + kunmap_atomic(src); + put_cpu_ptr(entry->pool->tfm); + if (ret) { + ret = -EINVAL; + goto put_dstmem; + } + + /* store */ + hlen = zpool_evictable(entry->pool->zpool) ? sizeof(zhdr) : 0; + gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM; + if (zpool_malloc_support_movable(entry->pool->zpool)) + gfp |= __GFP_HIGHMEM | __GFP_MOVABLE; + ret = zpool_malloc(entry->pool->zpool, hlen + dlen, gfp, &handle); + if (ret == -ENOSPC) { + zswap_reject_compress_poor++; + goto put_dstmem; + } + if (ret) { + zswap_reject_alloc_fail++; + goto put_dstmem; + } + buf = zpool_map_handle(entry->pool->zpool, handle, ZPOOL_MM_RW); + memcpy(buf, &zhdr, hlen); + memcpy(buf + hlen, dst, dlen); + zpool_unmap_handle(entry->pool->zpool, handle); + put_cpu_var(zswap_dstmem); + + /* populate entry */ + entry->offset = offset; + entry->handle = handle; + entry->length = dlen; + +insert_entry: + /* map */ + spin_lock(&tree->lock); + do { + ret = zswap_rb_insert(&tree->rbroot, entry, &dupentry); + if (ret == -EEXIST) { + zswap_duplicate_entry++; + /* remove from rbtree */ + zswap_rb_erase(&tree->rbroot, dupentry); + zswap_entry_put(tree, dupentry); + } + } while (ret == -EEXIST); + spin_unlock(&tree->lock); + + /* update stats */ + atomic_inc(&zswap_stored_pages); + zswap_update_total_size(); + + return 0; + +put_dstmem: + put_cpu_var(zswap_dstmem); + zswap_pool_put(entry->pool); +freepage: + zswap_entry_cache_free(entry); +reject: + return ret; +} + +/* + * returns 0 if the page was successfully decompressed + * return -1 on entry not found or error +*/ +static int zswap_frontswap_load(unsigned type, pgoff_t offset, + struct page *page) +{ + struct zswap_tree *tree = zswap_trees[type]; + struct zswap_entry *entry; + struct crypto_comp *tfm; + u8 *src, *dst; + unsigned int dlen; + int ret; + + /* find */ + spin_lock(&tree->lock); + entry = zswap_entry_find_get(&tree->rbroot, offset); + if (!entry) { + /* entry was written back */ + spin_unlock(&tree->lock); + return -1; + } + spin_unlock(&tree->lock); + + if (!entry->length) { + dst = kmap_atomic(page); + zswap_fill_page(dst, entry->value); + kunmap_atomic(dst); + goto freeentry; + } + + /* decompress */ + dlen = PAGE_SIZE; + src = zpool_map_handle(entry->pool->zpool, entry->handle, ZPOOL_MM_RO); + if (zpool_evictable(entry->pool->zpool)) + src += sizeof(struct zswap_header); + dst = kmap_atomic(page); + tfm = *get_cpu_ptr(entry->pool->tfm); + ret = crypto_comp_decompress(tfm, src, entry->length, dst, &dlen); + put_cpu_ptr(entry->pool->tfm); + kunmap_atomic(dst); + zpool_unmap_handle(entry->pool->zpool, entry->handle); + BUG_ON(ret); + +freeentry: + spin_lock(&tree->lock); + zswap_entry_put(tree, entry); + spin_unlock(&tree->lock); + + return 0; +} + +/* frees an entry in zswap */ +static void zswap_frontswap_invalidate_page(unsigned type, pgoff_t offset) +{ + struct zswap_tree *tree = zswap_trees[type]; + struct zswap_entry *entry; + + /* find */ + spin_lock(&tree->lock); + entry = zswap_rb_search(&tree->rbroot, offset); + if (!entry) { + /* entry was written back */ + spin_unlock(&tree->lock); + return; + } + + /* remove from rbtree */ + zswap_rb_erase(&tree->rbroot, entry); + + /* drop the initial reference from entry creation */ + zswap_entry_put(tree, entry); + + spin_unlock(&tree->lock); +} + +/* frees all zswap entries for the given swap type */ +static void zswap_frontswap_invalidate_area(unsigned type) +{ + struct zswap_tree *tree = zswap_trees[type]; + struct zswap_entry *entry, *n; + + if (!tree) + return; + + /* walk the tree and free everything */ + spin_lock(&tree->lock); + rbtree_postorder_for_each_entry_safe(entry, n, &tree->rbroot, rbnode) + zswap_free_entry(entry); + tree->rbroot = RB_ROOT; + spin_unlock(&tree->lock); + kfree(tree); + zswap_trees[type] = NULL; +} + +static void zswap_frontswap_init(unsigned type) +{ + struct zswap_tree *tree; + + tree = kzalloc(sizeof(*tree), GFP_KERNEL); + if (!tree) { + pr_err("alloc failed, zswap disabled for swap type %d\n", type); + return; + } + + tree->rbroot = RB_ROOT; + spin_lock_init(&tree->lock); + zswap_trees[type] = tree; +} + +static struct frontswap_ops zswap_frontswap_ops = { + .store = zswap_frontswap_store, + .load = zswap_frontswap_load, + .invalidate_page = zswap_frontswap_invalidate_page, + .invalidate_area = zswap_frontswap_invalidate_area, + .init = zswap_frontswap_init +}; + +/********************************* +* debugfs functions +**********************************/ +#ifdef CONFIG_DEBUG_FS +#include + +static struct dentry *zswap_debugfs_root; + +static int __init zswap_debugfs_init(void) +{ + if (!debugfs_initialized()) + return -ENODEV; + + zswap_debugfs_root = debugfs_create_dir("zswap", NULL); + + debugfs_create_u64("pool_limit_hit", 0444, + zswap_debugfs_root, &zswap_pool_limit_hit); + debugfs_create_u64("reject_reclaim_fail", 0444, + zswap_debugfs_root, &zswap_reject_reclaim_fail); + debugfs_create_u64("reject_alloc_fail", 0444, + zswap_debugfs_root, &zswap_reject_alloc_fail); + debugfs_create_u64("reject_kmemcache_fail", 0444, + zswap_debugfs_root, &zswap_reject_kmemcache_fail); + debugfs_create_u64("reject_compress_poor", 0444, + zswap_debugfs_root, &zswap_reject_compress_poor); + debugfs_create_u64("written_back_pages", 0444, + zswap_debugfs_root, &zswap_written_back_pages); + debugfs_create_u64("duplicate_entry", 0444, + zswap_debugfs_root, &zswap_duplicate_entry); + debugfs_create_u64("pool_total_size", 0444, + zswap_debugfs_root, &zswap_pool_total_size); + debugfs_create_atomic_t("stored_pages", 0444, + zswap_debugfs_root, &zswap_stored_pages); + debugfs_create_atomic_t("same_filled_pages", 0444, + zswap_debugfs_root, &zswap_same_filled_pages); + + return 0; +} + +static void __exit zswap_debugfs_exit(void) +{ + debugfs_remove_recursive(zswap_debugfs_root); +} +#else +static int __init zswap_debugfs_init(void) +{ + return 0; +} + +static void __exit zswap_debugfs_exit(void) { } +#endif + +/********************************* +* module init and exit +**********************************/ +static int __init init_zswap(void) +{ + struct zswap_pool *pool; + int ret; + + zswap_init_started = true; + + if (zswap_entry_cache_create()) { + pr_err("entry cache creation failed\n"); + goto cache_fail; + } + + ret = cpuhp_setup_state(CPUHP_MM_ZSWP_MEM_PREPARE, "mm/zswap:prepare", + zswap_dstmem_prepare, zswap_dstmem_dead); + if (ret) { + pr_err("dstmem alloc failed\n"); + goto dstmem_fail; + } + + ret = cpuhp_setup_state_multi(CPUHP_MM_ZSWP_POOL_PREPARE, + "mm/zswap_pool:prepare", + zswap_cpu_comp_prepare, + zswap_cpu_comp_dead); + if (ret) + goto hp_fail; + + pool = __zswap_pool_create_fallback(); + if (pool) { + pr_info("loaded using pool %s/%s\n", pool->tfm_name, + zpool_get_type(pool->zpool)); + list_add(&pool->list, &zswap_pools); + zswap_has_pool = true; + } else { + pr_err("pool creation failed\n"); + zswap_enabled = false; + } + + shrink_wq = create_workqueue("zswap-shrink"); + if (!shrink_wq) + goto fallback_fail; + + frontswap_register_ops(&zswap_frontswap_ops); + if (zswap_debugfs_init()) + pr_warn("debugfs initialization failed\n"); + return 0; + +fallback_fail: + if (pool) + zswap_pool_destroy(pool); +hp_fail: + cpuhp_remove_state(CPUHP_MM_ZSWP_MEM_PREPARE); +dstmem_fail: + zswap_entry_cache_destroy(); +cache_fail: + /* if built-in, we aren't unloaded on failure; don't allow use */ + zswap_init_failed = true; + zswap_enabled = false; + return -ENOMEM; +} +/* must be late so crypto has time to come up */ +late_initcall(init_zswap); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Seth Jennings "); +MODULE_DESCRIPTION("Compressed cache for swap pages"); -- cgit v1.2.3