summaryrefslogtreecommitdiffstats
path: root/arch/arm64/mm
diff options
context:
space:
mode:
Diffstat (limited to '')
-rw-r--r--arch/arm64/mm/Makefile14
-rw-r--r--arch/arm64/mm/cache.S257
-rw-r--r--arch/arm64/mm/context.c275
-rw-r--r--arch/arm64/mm/copypage.c37
-rw-r--r--arch/arm64/mm/dma-mapping.c903
-rw-r--r--arch/arm64/mm/dump.c413
-rw-r--r--arch/arm64/mm/extable.c18
-rw-r--r--arch/arm64/mm/fault.c914
-rw-r--r--arch/arm64/mm/flush.c106
-rw-r--r--arch/arm64/mm/hugetlbpage.c463
-rw-r--r--arch/arm64/mm/init.c694
-rw-r--r--arch/arm64/mm/ioremap.c113
-rw-r--r--arch/arm64/mm/kasan_init.c244
-rw-r--r--arch/arm64/mm/mmap.c157
-rw-r--r--arch/arm64/mm/mmu.c1041
-rw-r--r--arch/arm64/mm/numa.c470
-rw-r--r--arch/arm64/mm/pageattr.c187
-rw-r--r--arch/arm64/mm/pgd.c65
-rw-r--r--arch/arm64/mm/physaddr.c31
-rw-r--r--arch/arm64/mm/proc.S475
-rw-r--r--arch/arm64/mm/ptdump_debugfs.c21
21 files changed, 6898 insertions, 0 deletions
diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile
new file mode 100644
index 000000000..849c1df3d
--- /dev/null
+++ b/arch/arm64/mm/Makefile
@@ -0,0 +1,14 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-y := dma-mapping.o extable.o fault.o init.o \
+ cache.o copypage.o flush.o \
+ ioremap.o mmap.o pgd.o mmu.o \
+ context.o proc.o pageattr.o
+obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
+obj-$(CONFIG_ARM64_PTDUMP_CORE) += dump.o
+obj-$(CONFIG_ARM64_PTDUMP_DEBUGFS) += ptdump_debugfs.o
+obj-$(CONFIG_NUMA) += numa.o
+obj-$(CONFIG_DEBUG_VIRTUAL) += physaddr.o
+KASAN_SANITIZE_physaddr.o += n
+
+obj-$(CONFIG_KASAN) += kasan_init.o
+KASAN_SANITIZE_kasan_init.o := n
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
new file mode 100644
index 000000000..a194fd0e8
--- /dev/null
+++ b/arch/arm64/mm/cache.S
@@ -0,0 +1,257 @@
+/*
+ * Cache maintenance
+ *
+ * Copyright (C) 2001 Deep Blue Solutions Ltd.
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/errno.h>
+#include <linux/linkage.h>
+#include <linux/init.h>
+#include <asm/assembler.h>
+#include <asm/cpufeature.h>
+#include <asm/alternative.h>
+#include <asm/asm-uaccess.h>
+
+/*
+ * flush_icache_range(start,end)
+ *
+ * Ensure that the I and D caches are coherent within specified region.
+ * This is typically used when code has been written to a memory region,
+ * and will be executed.
+ *
+ * - start - virtual start address of region
+ * - end - virtual end address of region
+ */
+ENTRY(__flush_icache_range)
+ /* FALLTHROUGH */
+
+/*
+ * __flush_cache_user_range(start,end)
+ *
+ * Ensure that the I and D caches are coherent within specified region.
+ * This is typically used when code has been written to a memory region,
+ * and will be executed.
+ *
+ * - start - virtual start address of region
+ * - end - virtual end address of region
+ */
+ENTRY(__flush_cache_user_range)
+ uaccess_ttbr0_enable x2, x3, x4
+alternative_if ARM64_HAS_CACHE_IDC
+ dsb ishst
+ b 7f
+alternative_else_nop_endif
+ dcache_line_size x2, x3
+ sub x3, x2, #1
+ bic x4, x0, x3
+1:
+user_alt 9f, "dc cvau, x4", "dc civac, x4", ARM64_WORKAROUND_CLEAN_CACHE
+ add x4, x4, x2
+ cmp x4, x1
+ b.lo 1b
+ dsb ish
+
+7:
+alternative_if ARM64_HAS_CACHE_DIC
+ isb
+ b 8f
+alternative_else_nop_endif
+ invalidate_icache_by_line x0, x1, x2, x3, 9f
+8: mov x0, #0
+1:
+ uaccess_ttbr0_disable x1, x2
+ ret
+9:
+ mov x0, #-EFAULT
+ b 1b
+ENDPROC(__flush_icache_range)
+ENDPROC(__flush_cache_user_range)
+
+/*
+ * invalidate_icache_range(start,end)
+ *
+ * Ensure that the I cache is invalid within specified region.
+ *
+ * - start - virtual start address of region
+ * - end - virtual end address of region
+ */
+ENTRY(invalidate_icache_range)
+alternative_if ARM64_HAS_CACHE_DIC
+ mov x0, xzr
+ isb
+ ret
+alternative_else_nop_endif
+
+ uaccess_ttbr0_enable x2, x3, x4
+
+ invalidate_icache_by_line x0, x1, x2, x3, 2f
+ mov x0, xzr
+1:
+ uaccess_ttbr0_disable x1, x2
+ ret
+2:
+ mov x0, #-EFAULT
+ b 1b
+ENDPROC(invalidate_icache_range)
+
+/*
+ * __flush_dcache_area(kaddr, size)
+ *
+ * Ensure that any D-cache lines for the interval [kaddr, kaddr+size)
+ * are cleaned and invalidated to the PoC.
+ *
+ * - kaddr - kernel address
+ * - size - size in question
+ */
+ENTRY(__flush_dcache_area)
+ dcache_by_line_op civac, sy, x0, x1, x2, x3
+ ret
+ENDPIPROC(__flush_dcache_area)
+
+/*
+ * __clean_dcache_area_pou(kaddr, size)
+ *
+ * Ensure that any D-cache lines for the interval [kaddr, kaddr+size)
+ * are cleaned to the PoU.
+ *
+ * - kaddr - kernel address
+ * - size - size in question
+ */
+ENTRY(__clean_dcache_area_pou)
+alternative_if ARM64_HAS_CACHE_IDC
+ dsb ishst
+ ret
+alternative_else_nop_endif
+ dcache_by_line_op cvau, ish, x0, x1, x2, x3
+ ret
+ENDPROC(__clean_dcache_area_pou)
+
+/*
+ * __inval_dcache_area(kaddr, size)
+ *
+ * Ensure that any D-cache lines for the interval [kaddr, kaddr+size)
+ * are invalidated. Any partial lines at the ends of the interval are
+ * also cleaned to PoC to prevent data loss.
+ *
+ * - kaddr - kernel address
+ * - size - size in question
+ */
+ENTRY(__inval_dcache_area)
+ /* FALLTHROUGH */
+
+/*
+ * __dma_inv_area(start, size)
+ * - start - virtual start address of region
+ * - size - size in question
+ */
+__dma_inv_area:
+ add x1, x1, x0
+ dcache_line_size x2, x3
+ sub x3, x2, #1
+ tst x1, x3 // end cache line aligned?
+ bic x1, x1, x3
+ b.eq 1f
+ dc civac, x1 // clean & invalidate D / U line
+1: tst x0, x3 // start cache line aligned?
+ bic x0, x0, x3
+ b.eq 2f
+ dc civac, x0 // clean & invalidate D / U line
+ b 3f
+2: dc ivac, x0 // invalidate D / U line
+3: add x0, x0, x2
+ cmp x0, x1
+ b.lo 2b
+ dsb sy
+ ret
+ENDPIPROC(__inval_dcache_area)
+ENDPROC(__dma_inv_area)
+
+/*
+ * __clean_dcache_area_poc(kaddr, size)
+ *
+ * Ensure that any D-cache lines for the interval [kaddr, kaddr+size)
+ * are cleaned to the PoC.
+ *
+ * - kaddr - kernel address
+ * - size - size in question
+ */
+ENTRY(__clean_dcache_area_poc)
+ /* FALLTHROUGH */
+
+/*
+ * __dma_clean_area(start, size)
+ * - start - virtual start address of region
+ * - size - size in question
+ */
+__dma_clean_area:
+ dcache_by_line_op cvac, sy, x0, x1, x2, x3
+ ret
+ENDPIPROC(__clean_dcache_area_poc)
+ENDPROC(__dma_clean_area)
+
+/*
+ * __clean_dcache_area_pop(kaddr, size)
+ *
+ * Ensure that any D-cache lines for the interval [kaddr, kaddr+size)
+ * are cleaned to the PoP.
+ *
+ * - kaddr - kernel address
+ * - size - size in question
+ */
+ENTRY(__clean_dcache_area_pop)
+ alternative_if_not ARM64_HAS_DCPOP
+ b __clean_dcache_area_poc
+ alternative_else_nop_endif
+ dcache_by_line_op cvap, sy, x0, x1, x2, x3
+ ret
+ENDPIPROC(__clean_dcache_area_pop)
+
+/*
+ * __dma_flush_area(start, size)
+ *
+ * clean & invalidate D / U line
+ *
+ * - start - virtual start address of region
+ * - size - size in question
+ */
+ENTRY(__dma_flush_area)
+ dcache_by_line_op civac, sy, x0, x1, x2, x3
+ ret
+ENDPIPROC(__dma_flush_area)
+
+/*
+ * __dma_map_area(start, size, dir)
+ * - start - kernel virtual start address
+ * - size - size of region
+ * - dir - DMA direction
+ */
+ENTRY(__dma_map_area)
+ cmp w2, #DMA_FROM_DEVICE
+ b.eq __dma_inv_area
+ b __dma_clean_area
+ENDPIPROC(__dma_map_area)
+
+/*
+ * __dma_unmap_area(start, size, dir)
+ * - start - kernel virtual start address
+ * - size - size of region
+ * - dir - DMA direction
+ */
+ENTRY(__dma_unmap_area)
+ cmp w2, #DMA_TO_DEVICE
+ b.ne __dma_inv_area
+ ret
+ENDPIPROC(__dma_unmap_area)
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
new file mode 100644
index 000000000..c127f94da
--- /dev/null
+++ b/arch/arm64/mm/context.c
@@ -0,0 +1,275 @@
+/*
+ * Based on arch/arm/mm/context.c
+ *
+ * Copyright (C) 2002-2003 Deep Blue Solutions Ltd, all rights reserved.
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/bitops.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+
+#include <asm/cpufeature.h>
+#include <asm/mmu_context.h>
+#include <asm/smp.h>
+#include <asm/tlbflush.h>
+
+static u32 asid_bits;
+static DEFINE_RAW_SPINLOCK(cpu_asid_lock);
+
+static atomic64_t asid_generation;
+static unsigned long *asid_map;
+
+static DEFINE_PER_CPU(atomic64_t, active_asids);
+static DEFINE_PER_CPU(u64, reserved_asids);
+static cpumask_t tlb_flush_pending;
+
+#define ASID_MASK (~GENMASK(asid_bits - 1, 0))
+#define ASID_FIRST_VERSION (1UL << asid_bits)
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+#define NUM_USER_ASIDS (ASID_FIRST_VERSION >> 1)
+#define asid2idx(asid) (((asid) & ~ASID_MASK) >> 1)
+#define idx2asid(idx) (((idx) << 1) & ~ASID_MASK)
+#else
+#define NUM_USER_ASIDS (ASID_FIRST_VERSION)
+#define asid2idx(asid) ((asid) & ~ASID_MASK)
+#define idx2asid(idx) asid2idx(idx)
+#endif
+
+/* Get the ASIDBits supported by the current CPU */
+static u32 get_cpu_asid_bits(void)
+{
+ u32 asid;
+ int fld = cpuid_feature_extract_unsigned_field(read_cpuid(ID_AA64MMFR0_EL1),
+ ID_AA64MMFR0_ASID_SHIFT);
+
+ switch (fld) {
+ default:
+ pr_warn("CPU%d: Unknown ASID size (%d); assuming 8-bit\n",
+ smp_processor_id(), fld);
+ /* Fallthrough */
+ case 0:
+ asid = 8;
+ break;
+ case 2:
+ asid = 16;
+ }
+
+ return asid;
+}
+
+/* Check if the current cpu's ASIDBits is compatible with asid_bits */
+void verify_cpu_asid_bits(void)
+{
+ u32 asid = get_cpu_asid_bits();
+
+ if (asid < asid_bits) {
+ /*
+ * We cannot decrease the ASID size at runtime, so panic if we support
+ * fewer ASID bits than the boot CPU.
+ */
+ pr_crit("CPU%d: smaller ASID size(%u) than boot CPU (%u)\n",
+ smp_processor_id(), asid, asid_bits);
+ cpu_panic_kernel();
+ }
+}
+
+static void flush_context(unsigned int cpu)
+{
+ int i;
+ u64 asid;
+
+ /* Update the list of reserved ASIDs and the ASID bitmap. */
+ bitmap_clear(asid_map, 0, NUM_USER_ASIDS);
+
+ for_each_possible_cpu(i) {
+ asid = atomic64_xchg_relaxed(&per_cpu(active_asids, i), 0);
+ /*
+ * If this CPU has already been through a
+ * rollover, but hasn't run another task in
+ * the meantime, we must preserve its reserved
+ * ASID, as this is the only trace we have of
+ * the process it is still running.
+ */
+ if (asid == 0)
+ asid = per_cpu(reserved_asids, i);
+ __set_bit(asid2idx(asid), asid_map);
+ per_cpu(reserved_asids, i) = asid;
+ }
+
+ /*
+ * Queue a TLB invalidation for each CPU to perform on next
+ * context-switch
+ */
+ cpumask_setall(&tlb_flush_pending);
+}
+
+static bool check_update_reserved_asid(u64 asid, u64 newasid)
+{
+ int cpu;
+ bool hit = false;
+
+ /*
+ * Iterate over the set of reserved ASIDs looking for a match.
+ * If we find one, then we can update our mm to use newasid
+ * (i.e. the same ASID in the current generation) but we can't
+ * exit the loop early, since we need to ensure that all copies
+ * of the old ASID are updated to reflect the mm. Failure to do
+ * so could result in us missing the reserved ASID in a future
+ * generation.
+ */
+ for_each_possible_cpu(cpu) {
+ if (per_cpu(reserved_asids, cpu) == asid) {
+ hit = true;
+ per_cpu(reserved_asids, cpu) = newasid;
+ }
+ }
+
+ return hit;
+}
+
+static u64 new_context(struct mm_struct *mm, unsigned int cpu)
+{
+ static u32 cur_idx = 1;
+ u64 asid = atomic64_read(&mm->context.id);
+ u64 generation = atomic64_read(&asid_generation);
+
+ if (asid != 0) {
+ u64 newasid = generation | (asid & ~ASID_MASK);
+
+ /*
+ * If our current ASID was active during a rollover, we
+ * can continue to use it and this was just a false alarm.
+ */
+ if (check_update_reserved_asid(asid, newasid))
+ return newasid;
+
+ /*
+ * We had a valid ASID in a previous life, so try to re-use
+ * it if possible.
+ */
+ if (!__test_and_set_bit(asid2idx(asid), asid_map))
+ return newasid;
+ }
+
+ /*
+ * Allocate a free ASID. If we can't find one, take a note of the
+ * currently active ASIDs and mark the TLBs as requiring flushes. We
+ * always count from ASID #2 (index 1), as we use ASID #0 when setting
+ * a reserved TTBR0 for the init_mm and we allocate ASIDs in even/odd
+ * pairs.
+ */
+ asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, cur_idx);
+ if (asid != NUM_USER_ASIDS)
+ goto set_asid;
+
+ /* We're out of ASIDs, so increment the global generation count */
+ generation = atomic64_add_return_relaxed(ASID_FIRST_VERSION,
+ &asid_generation);
+ flush_context(cpu);
+
+ /* We have more ASIDs than CPUs, so this will always succeed */
+ asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1);
+
+set_asid:
+ __set_bit(asid, asid_map);
+ cur_idx = asid;
+ return idx2asid(asid) | generation;
+}
+
+void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
+{
+ unsigned long flags;
+ u64 asid, old_active_asid;
+
+ asid = atomic64_read(&mm->context.id);
+
+ /*
+ * The memory ordering here is subtle.
+ * If our active_asids is non-zero and the ASID matches the current
+ * generation, then we update the active_asids entry with a relaxed
+ * cmpxchg. Racing with a concurrent rollover means that either:
+ *
+ * - We get a zero back from the cmpxchg and end up waiting on the
+ * lock. Taking the lock synchronises with the rollover and so
+ * we are forced to see the updated generation.
+ *
+ * - We get a valid ASID back from the cmpxchg, which means the
+ * relaxed xchg in flush_context will treat us as reserved
+ * because atomic RmWs are totally ordered for a given location.
+ */
+ old_active_asid = atomic64_read(&per_cpu(active_asids, cpu));
+ if (old_active_asid &&
+ !((asid ^ atomic64_read(&asid_generation)) >> asid_bits) &&
+ atomic64_cmpxchg_relaxed(&per_cpu(active_asids, cpu),
+ old_active_asid, asid))
+ goto switch_mm_fastpath;
+
+ raw_spin_lock_irqsave(&cpu_asid_lock, flags);
+ /* Check that our ASID belongs to the current generation. */
+ asid = atomic64_read(&mm->context.id);
+ if ((asid ^ atomic64_read(&asid_generation)) >> asid_bits) {
+ asid = new_context(mm, cpu);
+ atomic64_set(&mm->context.id, asid);
+ }
+
+ if (cpumask_test_and_clear_cpu(cpu, &tlb_flush_pending))
+ local_flush_tlb_all();
+
+ atomic64_set(&per_cpu(active_asids, cpu), asid);
+ raw_spin_unlock_irqrestore(&cpu_asid_lock, flags);
+
+switch_mm_fastpath:
+
+ arm64_apply_bp_hardening();
+
+ /*
+ * Defer TTBR0_EL1 setting for user threads to uaccess_enable() when
+ * emulating PAN.
+ */
+ if (!system_uses_ttbr0_pan())
+ cpu_switch_mm(mm->pgd, mm);
+}
+
+/* Errata workaround post TTBRx_EL1 update. */
+asmlinkage void post_ttbr_update_workaround(void)
+{
+ asm(ALTERNATIVE("nop; nop; nop",
+ "ic iallu; dsb nsh; isb",
+ ARM64_WORKAROUND_CAVIUM_27456,
+ CONFIG_CAVIUM_ERRATUM_27456));
+}
+
+static int asids_init(void)
+{
+ asid_bits = get_cpu_asid_bits();
+ /*
+ * Expect allocation after rollover to fail if we don't have at least
+ * one more ASID than CPUs. ASID #0 is reserved for init_mm.
+ */
+ WARN_ON(NUM_USER_ASIDS - 1 <= num_possible_cpus());
+ atomic64_set(&asid_generation, ASID_FIRST_VERSION);
+ asid_map = kcalloc(BITS_TO_LONGS(NUM_USER_ASIDS), sizeof(*asid_map),
+ GFP_KERNEL);
+ if (!asid_map)
+ panic("Failed to allocate bitmap for %lu ASIDs\n",
+ NUM_USER_ASIDS);
+
+ pr_info("ASID allocator initialised with %lu entries\n", NUM_USER_ASIDS);
+ return 0;
+}
+early_initcall(asids_init);
diff --git a/arch/arm64/mm/copypage.c b/arch/arm64/mm/copypage.c
new file mode 100644
index 000000000..22e4cb4d6
--- /dev/null
+++ b/arch/arm64/mm/copypage.c
@@ -0,0 +1,37 @@
+/*
+ * Based on arch/arm/mm/copypage.c
+ *
+ * Copyright (C) 2002 Deep Blue Solutions Ltd, All Rights Reserved.
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/mm.h>
+
+#include <asm/page.h>
+#include <asm/cacheflush.h>
+
+void __cpu_copy_user_page(void *kto, const void *kfrom, unsigned long vaddr)
+{
+ struct page *page = virt_to_page(kto);
+ copy_page(kto, kfrom);
+ flush_dcache_page(page);
+}
+EXPORT_SYMBOL_GPL(__cpu_copy_user_page);
+
+void __cpu_clear_user_page(void *kaddr, unsigned long vaddr)
+{
+ clear_page(kaddr);
+}
+EXPORT_SYMBOL_GPL(__cpu_clear_user_page);
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
new file mode 100644
index 000000000..d3a5bb16f
--- /dev/null
+++ b/arch/arm64/mm/dma-mapping.c
@@ -0,0 +1,903 @@
+/*
+ * SWIOTLB-based DMA API implementation
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/gfp.h>
+#include <linux/acpi.h>
+#include <linux/bootmem.h>
+#include <linux/cache.h>
+#include <linux/export.h>
+#include <linux/slab.h>
+#include <linux/genalloc.h>
+#include <linux/dma-direct.h>
+#include <linux/dma-contiguous.h>
+#include <linux/vmalloc.h>
+#include <linux/swiotlb.h>
+#include <linux/pci.h>
+
+#include <asm/cacheflush.h>
+
+static int swiotlb __ro_after_init;
+
+static pgprot_t __get_dma_pgprot(unsigned long attrs, pgprot_t prot,
+ bool coherent)
+{
+ if (!coherent || (attrs & DMA_ATTR_WRITE_COMBINE))
+ return pgprot_writecombine(prot);
+ return prot;
+}
+
+static struct gen_pool *atomic_pool __ro_after_init;
+
+#define DEFAULT_DMA_COHERENT_POOL_SIZE SZ_256K
+static size_t atomic_pool_size __initdata = DEFAULT_DMA_COHERENT_POOL_SIZE;
+
+static int __init early_coherent_pool(char *p)
+{
+ atomic_pool_size = memparse(p, &p);
+ return 0;
+}
+early_param("coherent_pool", early_coherent_pool);
+
+static void *__alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags)
+{
+ unsigned long val;
+ void *ptr = NULL;
+
+ if (!atomic_pool) {
+ WARN(1, "coherent pool not initialised!\n");
+ return NULL;
+ }
+
+ val = gen_pool_alloc(atomic_pool, size);
+ if (val) {
+ phys_addr_t phys = gen_pool_virt_to_phys(atomic_pool, val);
+
+ *ret_page = phys_to_page(phys);
+ ptr = (void *)val;
+ memset(ptr, 0, size);
+ }
+
+ return ptr;
+}
+
+static bool __in_atomic_pool(void *start, size_t size)
+{
+ return addr_in_gen_pool(atomic_pool, (unsigned long)start, size);
+}
+
+static int __free_from_pool(void *start, size_t size)
+{
+ if (!__in_atomic_pool(start, size))
+ return 0;
+
+ gen_pool_free(atomic_pool, (unsigned long)start, size);
+
+ return 1;
+}
+
+static void *__dma_alloc(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t flags,
+ unsigned long attrs)
+{
+ struct page *page;
+ void *ptr, *coherent_ptr;
+ bool coherent = is_device_dma_coherent(dev);
+ pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, false);
+
+ size = PAGE_ALIGN(size);
+
+ if (!coherent && !gfpflags_allow_blocking(flags)) {
+ struct page *page = NULL;
+ void *addr = __alloc_from_pool(size, &page, flags);
+
+ if (addr)
+ *dma_handle = phys_to_dma(dev, page_to_phys(page));
+
+ return addr;
+ }
+
+ ptr = swiotlb_alloc(dev, size, dma_handle, flags, attrs);
+ if (!ptr)
+ goto no_mem;
+
+ /* no need for non-cacheable mapping if coherent */
+ if (coherent)
+ return ptr;
+
+ /* remove any dirty cache lines on the kernel alias */
+ __dma_flush_area(ptr, size);
+
+ /* create a coherent mapping */
+ page = virt_to_page(ptr);
+ coherent_ptr = dma_common_contiguous_remap(page, size, VM_USERMAP,
+ prot, __builtin_return_address(0));
+ if (!coherent_ptr)
+ goto no_map;
+
+ return coherent_ptr;
+
+no_map:
+ swiotlb_free(dev, size, ptr, *dma_handle, attrs);
+no_mem:
+ return NULL;
+}
+
+static void __dma_free(struct device *dev, size_t size,
+ void *vaddr, dma_addr_t dma_handle,
+ unsigned long attrs)
+{
+ void *swiotlb_addr = phys_to_virt(dma_to_phys(dev, dma_handle));
+
+ size = PAGE_ALIGN(size);
+
+ if (!is_device_dma_coherent(dev)) {
+ if (__free_from_pool(vaddr, size))
+ return;
+ vunmap(vaddr);
+ }
+ swiotlb_free(dev, size, swiotlb_addr, dma_handle, attrs);
+}
+
+static dma_addr_t __swiotlb_map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t size,
+ enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ dma_addr_t dev_addr;
+
+ dev_addr = swiotlb_map_page(dev, page, offset, size, dir, attrs);
+ if (!is_device_dma_coherent(dev) &&
+ (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
+ __dma_map_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
+
+ return dev_addr;
+}
+
+
+static void __swiotlb_unmap_page(struct device *dev, dma_addr_t dev_addr,
+ size_t size, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ if (!is_device_dma_coherent(dev) &&
+ (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
+ __dma_unmap_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
+ swiotlb_unmap_page(dev, dev_addr, size, dir, attrs);
+}
+
+static int __swiotlb_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
+ int nelems, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ struct scatterlist *sg;
+ int i, ret;
+
+ ret = swiotlb_map_sg_attrs(dev, sgl, nelems, dir, attrs);
+ if (!is_device_dma_coherent(dev) &&
+ (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
+ for_each_sg(sgl, sg, ret, i)
+ __dma_map_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
+ sg->length, dir);
+
+ return ret;
+}
+
+static void __swiotlb_unmap_sg_attrs(struct device *dev,
+ struct scatterlist *sgl, int nelems,
+ enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ struct scatterlist *sg;
+ int i;
+
+ if (!is_device_dma_coherent(dev) &&
+ (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
+ for_each_sg(sgl, sg, nelems, i)
+ __dma_unmap_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
+ sg->length, dir);
+ swiotlb_unmap_sg_attrs(dev, sgl, nelems, dir, attrs);
+}
+
+static void __swiotlb_sync_single_for_cpu(struct device *dev,
+ dma_addr_t dev_addr, size_t size,
+ enum dma_data_direction dir)
+{
+ if (!is_device_dma_coherent(dev))
+ __dma_unmap_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
+ swiotlb_sync_single_for_cpu(dev, dev_addr, size, dir);
+}
+
+static void __swiotlb_sync_single_for_device(struct device *dev,
+ dma_addr_t dev_addr, size_t size,
+ enum dma_data_direction dir)
+{
+ swiotlb_sync_single_for_device(dev, dev_addr, size, dir);
+ if (!is_device_dma_coherent(dev))
+ __dma_map_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
+}
+
+static void __swiotlb_sync_sg_for_cpu(struct device *dev,
+ struct scatterlist *sgl, int nelems,
+ enum dma_data_direction dir)
+{
+ struct scatterlist *sg;
+ int i;
+
+ if (!is_device_dma_coherent(dev))
+ for_each_sg(sgl, sg, nelems, i)
+ __dma_unmap_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
+ sg->length, dir);
+ swiotlb_sync_sg_for_cpu(dev, sgl, nelems, dir);
+}
+
+static void __swiotlb_sync_sg_for_device(struct device *dev,
+ struct scatterlist *sgl, int nelems,
+ enum dma_data_direction dir)
+{
+ struct scatterlist *sg;
+ int i;
+
+ swiotlb_sync_sg_for_device(dev, sgl, nelems, dir);
+ if (!is_device_dma_coherent(dev))
+ for_each_sg(sgl, sg, nelems, i)
+ __dma_map_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
+ sg->length, dir);
+}
+
+static int __swiotlb_mmap_pfn(struct vm_area_struct *vma,
+ unsigned long pfn, size_t size)
+{
+ int ret = -ENXIO;
+ unsigned long nr_vma_pages = vma_pages(vma);
+ unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
+ unsigned long off = vma->vm_pgoff;
+
+ if (off < nr_pages && nr_vma_pages <= (nr_pages - off)) {
+ ret = remap_pfn_range(vma, vma->vm_start,
+ pfn + off,
+ vma->vm_end - vma->vm_start,
+ vma->vm_page_prot);
+ }
+
+ return ret;
+}
+
+static int __swiotlb_mmap(struct device *dev,
+ struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size,
+ unsigned long attrs)
+{
+ int ret;
+ unsigned long pfn = dma_to_phys(dev, dma_addr) >> PAGE_SHIFT;
+
+ vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot,
+ is_device_dma_coherent(dev));
+
+ if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
+ return ret;
+
+ return __swiotlb_mmap_pfn(vma, pfn, size);
+}
+
+static int __swiotlb_get_sgtable_page(struct sg_table *sgt,
+ struct page *page, size_t size)
+{
+ int ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
+
+ if (!ret)
+ sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
+
+ return ret;
+}
+
+static int __swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt,
+ void *cpu_addr, dma_addr_t handle, size_t size,
+ unsigned long attrs)
+{
+ struct page *page = phys_to_page(dma_to_phys(dev, handle));
+
+ return __swiotlb_get_sgtable_page(sgt, page, size);
+}
+
+static int __swiotlb_dma_supported(struct device *hwdev, u64 mask)
+{
+ if (swiotlb)
+ return swiotlb_dma_supported(hwdev, mask);
+ return 1;
+}
+
+static int __swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t addr)
+{
+ if (swiotlb)
+ return swiotlb_dma_mapping_error(hwdev, addr);
+ return 0;
+}
+
+static const struct dma_map_ops arm64_swiotlb_dma_ops = {
+ .alloc = __dma_alloc,
+ .free = __dma_free,
+ .mmap = __swiotlb_mmap,
+ .get_sgtable = __swiotlb_get_sgtable,
+ .map_page = __swiotlb_map_page,
+ .unmap_page = __swiotlb_unmap_page,
+ .map_sg = __swiotlb_map_sg_attrs,
+ .unmap_sg = __swiotlb_unmap_sg_attrs,
+ .sync_single_for_cpu = __swiotlb_sync_single_for_cpu,
+ .sync_single_for_device = __swiotlb_sync_single_for_device,
+ .sync_sg_for_cpu = __swiotlb_sync_sg_for_cpu,
+ .sync_sg_for_device = __swiotlb_sync_sg_for_device,
+ .dma_supported = __swiotlb_dma_supported,
+ .mapping_error = __swiotlb_dma_mapping_error,
+};
+
+static int __init atomic_pool_init(void)
+{
+ pgprot_t prot = __pgprot(PROT_NORMAL_NC);
+ unsigned long nr_pages = atomic_pool_size >> PAGE_SHIFT;
+ struct page *page;
+ void *addr;
+ unsigned int pool_size_order = get_order(atomic_pool_size);
+
+ if (dev_get_cma_area(NULL))
+ page = dma_alloc_from_contiguous(NULL, nr_pages,
+ pool_size_order, false);
+ else
+ page = alloc_pages(GFP_DMA32, pool_size_order);
+
+ if (page) {
+ int ret;
+ void *page_addr = page_address(page);
+
+ memset(page_addr, 0, atomic_pool_size);
+ __dma_flush_area(page_addr, atomic_pool_size);
+
+ atomic_pool = gen_pool_create(PAGE_SHIFT, -1);
+ if (!atomic_pool)
+ goto free_page;
+
+ addr = dma_common_contiguous_remap(page, atomic_pool_size,
+ VM_USERMAP, prot, atomic_pool_init);
+
+ if (!addr)
+ goto destroy_genpool;
+
+ ret = gen_pool_add_virt(atomic_pool, (unsigned long)addr,
+ page_to_phys(page),
+ atomic_pool_size, -1);
+ if (ret)
+ goto remove_mapping;
+
+ gen_pool_set_algo(atomic_pool,
+ gen_pool_first_fit_order_align,
+ NULL);
+
+ pr_info("DMA: preallocated %zu KiB pool for atomic allocations\n",
+ atomic_pool_size / 1024);
+ return 0;
+ }
+ goto out;
+
+remove_mapping:
+ dma_common_free_remap(addr, atomic_pool_size, VM_USERMAP);
+destroy_genpool:
+ gen_pool_destroy(atomic_pool);
+ atomic_pool = NULL;
+free_page:
+ if (!dma_release_from_contiguous(NULL, page, nr_pages))
+ __free_pages(page, pool_size_order);
+out:
+ pr_err("DMA: failed to allocate %zu KiB pool for atomic coherent allocation\n",
+ atomic_pool_size / 1024);
+ return -ENOMEM;
+}
+
+/********************************************
+ * The following APIs are for dummy DMA ops *
+ ********************************************/
+
+static void *__dummy_alloc(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t flags,
+ unsigned long attrs)
+{
+ return NULL;
+}
+
+static void __dummy_free(struct device *dev, size_t size,
+ void *vaddr, dma_addr_t dma_handle,
+ unsigned long attrs)
+{
+}
+
+static int __dummy_mmap(struct device *dev,
+ struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size,
+ unsigned long attrs)
+{
+ return -ENXIO;
+}
+
+static dma_addr_t __dummy_map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t size,
+ enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ return 0;
+}
+
+static void __dummy_unmap_page(struct device *dev, dma_addr_t dev_addr,
+ size_t size, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+}
+
+static int __dummy_map_sg(struct device *dev, struct scatterlist *sgl,
+ int nelems, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ return 0;
+}
+
+static void __dummy_unmap_sg(struct device *dev,
+ struct scatterlist *sgl, int nelems,
+ enum dma_data_direction dir,
+ unsigned long attrs)
+{
+}
+
+static void __dummy_sync_single(struct device *dev,
+ dma_addr_t dev_addr, size_t size,
+ enum dma_data_direction dir)
+{
+}
+
+static void __dummy_sync_sg(struct device *dev,
+ struct scatterlist *sgl, int nelems,
+ enum dma_data_direction dir)
+{
+}
+
+static int __dummy_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
+{
+ return 1;
+}
+
+static int __dummy_dma_supported(struct device *hwdev, u64 mask)
+{
+ return 0;
+}
+
+const struct dma_map_ops dummy_dma_ops = {
+ .alloc = __dummy_alloc,
+ .free = __dummy_free,
+ .mmap = __dummy_mmap,
+ .map_page = __dummy_map_page,
+ .unmap_page = __dummy_unmap_page,
+ .map_sg = __dummy_map_sg,
+ .unmap_sg = __dummy_unmap_sg,
+ .sync_single_for_cpu = __dummy_sync_single,
+ .sync_single_for_device = __dummy_sync_single,
+ .sync_sg_for_cpu = __dummy_sync_sg,
+ .sync_sg_for_device = __dummy_sync_sg,
+ .mapping_error = __dummy_mapping_error,
+ .dma_supported = __dummy_dma_supported,
+};
+EXPORT_SYMBOL(dummy_dma_ops);
+
+static int __init arm64_dma_init(void)
+{
+ if (swiotlb_force == SWIOTLB_FORCE ||
+ max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT))
+ swiotlb = 1;
+
+ WARN_TAINT(ARCH_DMA_MINALIGN < cache_line_size(),
+ TAINT_CPU_OUT_OF_SPEC,
+ "ARCH_DMA_MINALIGN smaller than CTR_EL0.CWG (%d < %d)",
+ ARCH_DMA_MINALIGN, cache_line_size());
+
+ return atomic_pool_init();
+}
+arch_initcall(arm64_dma_init);
+
+#ifdef CONFIG_IOMMU_DMA
+#include <linux/dma-iommu.h>
+#include <linux/platform_device.h>
+#include <linux/amba/bus.h>
+
+/* Thankfully, all cache ops are by VA so we can ignore phys here */
+static void flush_page(struct device *dev, const void *virt, phys_addr_t phys)
+{
+ __dma_flush_area(virt, PAGE_SIZE);
+}
+
+static void *__iommu_alloc_attrs(struct device *dev, size_t size,
+ dma_addr_t *handle, gfp_t gfp,
+ unsigned long attrs)
+{
+ bool coherent = is_device_dma_coherent(dev);
+ int ioprot = dma_info_to_prot(DMA_BIDIRECTIONAL, coherent, attrs);
+ size_t iosize = size;
+ void *addr;
+
+ if (WARN(!dev, "cannot create IOMMU mapping for unknown device\n"))
+ return NULL;
+
+ size = PAGE_ALIGN(size);
+
+ /*
+ * Some drivers rely on this, and we probably don't want the
+ * possibility of stale kernel data being read by devices anyway.
+ */
+ gfp |= __GFP_ZERO;
+
+ if (!gfpflags_allow_blocking(gfp)) {
+ struct page *page;
+ /*
+ * In atomic context we can't remap anything, so we'll only
+ * get the virtually contiguous buffer we need by way of a
+ * physically contiguous allocation.
+ */
+ if (coherent) {
+ page = alloc_pages(gfp, get_order(size));
+ addr = page ? page_address(page) : NULL;
+ } else {
+ addr = __alloc_from_pool(size, &page, gfp);
+ }
+ if (!addr)
+ return NULL;
+
+ *handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot);
+ if (iommu_dma_mapping_error(dev, *handle)) {
+ if (coherent)
+ __free_pages(page, get_order(size));
+ else
+ __free_from_pool(addr, size);
+ addr = NULL;
+ }
+ } else if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) {
+ pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, coherent);
+ struct page *page;
+
+ page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT,
+ get_order(size), gfp & __GFP_NOWARN);
+ if (!page)
+ return NULL;
+
+ *handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot);
+ if (iommu_dma_mapping_error(dev, *handle)) {
+ dma_release_from_contiguous(dev, page,
+ size >> PAGE_SHIFT);
+ return NULL;
+ }
+ addr = dma_common_contiguous_remap(page, size, VM_USERMAP,
+ prot,
+ __builtin_return_address(0));
+ if (addr) {
+ if (!coherent)
+ __dma_flush_area(page_to_virt(page), iosize);
+ memset(addr, 0, size);
+ } else {
+ iommu_dma_unmap_page(dev, *handle, iosize, 0, attrs);
+ dma_release_from_contiguous(dev, page,
+ size >> PAGE_SHIFT);
+ }
+ } else {
+ pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, coherent);
+ struct page **pages;
+
+ pages = iommu_dma_alloc(dev, iosize, gfp, attrs, ioprot,
+ handle, flush_page);
+ if (!pages)
+ return NULL;
+
+ addr = dma_common_pages_remap(pages, size, VM_USERMAP, prot,
+ __builtin_return_address(0));
+ if (!addr)
+ iommu_dma_free(dev, pages, iosize, handle);
+ }
+ return addr;
+}
+
+static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
+ dma_addr_t handle, unsigned long attrs)
+{
+ size_t iosize = size;
+
+ size = PAGE_ALIGN(size);
+ /*
+ * @cpu_addr will be one of 4 things depending on how it was allocated:
+ * - A remapped array of pages for contiguous allocations.
+ * - A remapped array of pages from iommu_dma_alloc(), for all
+ * non-atomic allocations.
+ * - A non-cacheable alias from the atomic pool, for atomic
+ * allocations by non-coherent devices.
+ * - A normal lowmem address, for atomic allocations by
+ * coherent devices.
+ * Hence how dodgy the below logic looks...
+ */
+ if (__in_atomic_pool(cpu_addr, size)) {
+ iommu_dma_unmap_page(dev, handle, iosize, 0, 0);
+ __free_from_pool(cpu_addr, size);
+ } else if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) {
+ struct page *page = vmalloc_to_page(cpu_addr);
+
+ iommu_dma_unmap_page(dev, handle, iosize, 0, attrs);
+ dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT);
+ dma_common_free_remap(cpu_addr, size, VM_USERMAP);
+ } else if (is_vmalloc_addr(cpu_addr)){
+ struct vm_struct *area = find_vm_area(cpu_addr);
+
+ if (WARN_ON(!area || !area->pages))
+ return;
+ iommu_dma_free(dev, area->pages, iosize, &handle);
+ dma_common_free_remap(cpu_addr, size, VM_USERMAP);
+ } else {
+ iommu_dma_unmap_page(dev, handle, iosize, 0, 0);
+ __free_pages(virt_to_page(cpu_addr), get_order(size));
+ }
+}
+
+static int __iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size,
+ unsigned long attrs)
+{
+ struct vm_struct *area;
+ int ret;
+
+ vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot,
+ is_device_dma_coherent(dev));
+
+ if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
+ return ret;
+
+ if (!is_vmalloc_addr(cpu_addr)) {
+ unsigned long pfn = page_to_pfn(virt_to_page(cpu_addr));
+ return __swiotlb_mmap_pfn(vma, pfn, size);
+ }
+
+ if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) {
+ /*
+ * DMA_ATTR_FORCE_CONTIGUOUS allocations are always remapped,
+ * hence in the vmalloc space.
+ */
+ unsigned long pfn = vmalloc_to_pfn(cpu_addr);
+ return __swiotlb_mmap_pfn(vma, pfn, size);
+ }
+
+ area = find_vm_area(cpu_addr);
+ if (WARN_ON(!area || !area->pages))
+ return -ENXIO;
+
+ return iommu_dma_mmap(area->pages, size, vma);
+}
+
+static int __iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
+ void *cpu_addr, dma_addr_t dma_addr,
+ size_t size, unsigned long attrs)
+{
+ unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+ struct vm_struct *area = find_vm_area(cpu_addr);
+
+ if (!is_vmalloc_addr(cpu_addr)) {
+ struct page *page = virt_to_page(cpu_addr);
+ return __swiotlb_get_sgtable_page(sgt, page, size);
+ }
+
+ if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) {
+ /*
+ * DMA_ATTR_FORCE_CONTIGUOUS allocations are always remapped,
+ * hence in the vmalloc space.
+ */
+ struct page *page = vmalloc_to_page(cpu_addr);
+ return __swiotlb_get_sgtable_page(sgt, page, size);
+ }
+
+ if (WARN_ON(!area || !area->pages))
+ return -ENXIO;
+
+ return sg_alloc_table_from_pages(sgt, area->pages, count, 0, size,
+ GFP_KERNEL);
+}
+
+static void __iommu_sync_single_for_cpu(struct device *dev,
+ dma_addr_t dev_addr, size_t size,
+ enum dma_data_direction dir)
+{
+ phys_addr_t phys;
+
+ if (is_device_dma_coherent(dev))
+ return;
+
+ phys = iommu_iova_to_phys(iommu_get_domain_for_dev(dev), dev_addr);
+ __dma_unmap_area(phys_to_virt(phys), size, dir);
+}
+
+static void __iommu_sync_single_for_device(struct device *dev,
+ dma_addr_t dev_addr, size_t size,
+ enum dma_data_direction dir)
+{
+ phys_addr_t phys;
+
+ if (is_device_dma_coherent(dev))
+ return;
+
+ phys = iommu_iova_to_phys(iommu_get_domain_for_dev(dev), dev_addr);
+ __dma_map_area(phys_to_virt(phys), size, dir);
+}
+
+static dma_addr_t __iommu_map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t size,
+ enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ bool coherent = is_device_dma_coherent(dev);
+ int prot = dma_info_to_prot(dir, coherent, attrs);
+ dma_addr_t dev_addr = iommu_dma_map_page(dev, page, offset, size, prot);
+
+ if (!iommu_dma_mapping_error(dev, dev_addr) &&
+ (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
+ __iommu_sync_single_for_device(dev, dev_addr, size, dir);
+
+ return dev_addr;
+}
+
+static void __iommu_unmap_page(struct device *dev, dma_addr_t dev_addr,
+ size_t size, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
+ __iommu_sync_single_for_cpu(dev, dev_addr, size, dir);
+
+ iommu_dma_unmap_page(dev, dev_addr, size, dir, attrs);
+}
+
+static void __iommu_sync_sg_for_cpu(struct device *dev,
+ struct scatterlist *sgl, int nelems,
+ enum dma_data_direction dir)
+{
+ struct scatterlist *sg;
+ int i;
+
+ if (is_device_dma_coherent(dev))
+ return;
+
+ for_each_sg(sgl, sg, nelems, i)
+ __dma_unmap_area(sg_virt(sg), sg->length, dir);
+}
+
+static void __iommu_sync_sg_for_device(struct device *dev,
+ struct scatterlist *sgl, int nelems,
+ enum dma_data_direction dir)
+{
+ struct scatterlist *sg;
+ int i;
+
+ if (is_device_dma_coherent(dev))
+ return;
+
+ for_each_sg(sgl, sg, nelems, i)
+ __dma_map_area(sg_virt(sg), sg->length, dir);
+}
+
+static int __iommu_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
+ int nelems, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ bool coherent = is_device_dma_coherent(dev);
+
+ if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
+ __iommu_sync_sg_for_device(dev, sgl, nelems, dir);
+
+ return iommu_dma_map_sg(dev, sgl, nelems,
+ dma_info_to_prot(dir, coherent, attrs));
+}
+
+static void __iommu_unmap_sg_attrs(struct device *dev,
+ struct scatterlist *sgl, int nelems,
+ enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
+ __iommu_sync_sg_for_cpu(dev, sgl, nelems, dir);
+
+ iommu_dma_unmap_sg(dev, sgl, nelems, dir, attrs);
+}
+
+static const struct dma_map_ops iommu_dma_ops = {
+ .alloc = __iommu_alloc_attrs,
+ .free = __iommu_free_attrs,
+ .mmap = __iommu_mmap_attrs,
+ .get_sgtable = __iommu_get_sgtable,
+ .map_page = __iommu_map_page,
+ .unmap_page = __iommu_unmap_page,
+ .map_sg = __iommu_map_sg_attrs,
+ .unmap_sg = __iommu_unmap_sg_attrs,
+ .sync_single_for_cpu = __iommu_sync_single_for_cpu,
+ .sync_single_for_device = __iommu_sync_single_for_device,
+ .sync_sg_for_cpu = __iommu_sync_sg_for_cpu,
+ .sync_sg_for_device = __iommu_sync_sg_for_device,
+ .map_resource = iommu_dma_map_resource,
+ .unmap_resource = iommu_dma_unmap_resource,
+ .mapping_error = iommu_dma_mapping_error,
+};
+
+static int __init __iommu_dma_init(void)
+{
+ return iommu_dma_init();
+}
+arch_initcall(__iommu_dma_init);
+
+static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
+ const struct iommu_ops *ops)
+{
+ struct iommu_domain *domain;
+
+ if (!ops)
+ return;
+
+ /*
+ * The IOMMU core code allocates the default DMA domain, which the
+ * underlying IOMMU driver needs to support via the dma-iommu layer.
+ */
+ domain = iommu_get_domain_for_dev(dev);
+
+ if (!domain)
+ goto out_err;
+
+ if (domain->type == IOMMU_DOMAIN_DMA) {
+ if (iommu_dma_init_domain(domain, dma_base, size, dev))
+ goto out_err;
+
+ dev->dma_ops = &iommu_dma_ops;
+ }
+
+ return;
+
+out_err:
+ pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n",
+ dev_name(dev));
+}
+
+void arch_teardown_dma_ops(struct device *dev)
+{
+ dev->dma_ops = NULL;
+}
+
+#else
+
+static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
+ const struct iommu_ops *iommu)
+{ }
+
+#endif /* CONFIG_IOMMU_DMA */
+
+void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
+ const struct iommu_ops *iommu, bool coherent)
+{
+ if (!dev->dma_ops)
+ dev->dma_ops = &arm64_swiotlb_dma_ops;
+
+ dev->archdata.dma_coherent = coherent;
+ __iommu_setup_dma_ops(dev, dma_base, size, iommu);
+
+#ifdef CONFIG_XEN
+ if (xen_initial_domain()) {
+ dev->archdata.dev_dma_ops = dev->dma_ops;
+ dev->dma_ops = xen_dma_ops;
+ }
+#endif
+}
diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c
new file mode 100644
index 000000000..65dfc8571
--- /dev/null
+++ b/arch/arm64/mm/dump.c
@@ -0,0 +1,413 @@
+/*
+ * Copyright (c) 2014, The Linux Foundation. All rights reserved.
+ * Debug helper to dump the current kernel pagetables of the system
+ * so that we can see what the various memory ranges are set to.
+ *
+ * Derived from x86 and arm implementation:
+ * (C) Copyright 2008 Intel Corporation
+ *
+ * Author: Arjan van de Ven <arjan@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+#include <linux/debugfs.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/io.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+
+#include <asm/fixmap.h>
+#include <asm/kasan.h>
+#include <asm/memory.h>
+#include <asm/pgtable.h>
+#include <asm/pgtable-hwdef.h>
+#include <asm/ptdump.h>
+
+static const struct addr_marker address_markers[] = {
+#ifdef CONFIG_KASAN
+ { KASAN_SHADOW_START, "Kasan shadow start" },
+ { KASAN_SHADOW_END, "Kasan shadow end" },
+#endif
+ { MODULES_VADDR, "Modules start" },
+ { MODULES_END, "Modules end" },
+ { VMALLOC_START, "vmalloc() Area" },
+ { VMALLOC_END, "vmalloc() End" },
+ { FIXADDR_START, "Fixmap start" },
+ { FIXADDR_TOP, "Fixmap end" },
+ { PCI_IO_START, "PCI I/O start" },
+ { PCI_IO_END, "PCI I/O end" },
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+ { VMEMMAP_START, "vmemmap start" },
+ { VMEMMAP_START + VMEMMAP_SIZE, "vmemmap end" },
+#endif
+ { PAGE_OFFSET, "Linear Mapping" },
+ { -1, NULL },
+};
+
+#define pt_dump_seq_printf(m, fmt, args...) \
+({ \
+ if (m) \
+ seq_printf(m, fmt, ##args); \
+})
+
+#define pt_dump_seq_puts(m, fmt) \
+({ \
+ if (m) \
+ seq_printf(m, fmt); \
+})
+
+/*
+ * The page dumper groups page table entries of the same type into a single
+ * description. It uses pg_state to track the range information while
+ * iterating over the pte entries. When the continuity is broken it then
+ * dumps out a description of the range.
+ */
+struct pg_state {
+ struct seq_file *seq;
+ const struct addr_marker *marker;
+ unsigned long start_address;
+ unsigned level;
+ u64 current_prot;
+ bool check_wx;
+ unsigned long wx_pages;
+ unsigned long uxn_pages;
+};
+
+struct prot_bits {
+ u64 mask;
+ u64 val;
+ const char *set;
+ const char *clear;
+};
+
+static const struct prot_bits pte_bits[] = {
+ {
+ .mask = PTE_VALID,
+ .val = PTE_VALID,
+ .set = " ",
+ .clear = "F",
+ }, {
+ .mask = PTE_USER,
+ .val = PTE_USER,
+ .set = "USR",
+ .clear = " ",
+ }, {
+ .mask = PTE_RDONLY,
+ .val = PTE_RDONLY,
+ .set = "ro",
+ .clear = "RW",
+ }, {
+ .mask = PTE_PXN,
+ .val = PTE_PXN,
+ .set = "NX",
+ .clear = "x ",
+ }, {
+ .mask = PTE_SHARED,
+ .val = PTE_SHARED,
+ .set = "SHD",
+ .clear = " ",
+ }, {
+ .mask = PTE_AF,
+ .val = PTE_AF,
+ .set = "AF",
+ .clear = " ",
+ }, {
+ .mask = PTE_NG,
+ .val = PTE_NG,
+ .set = "NG",
+ .clear = " ",
+ }, {
+ .mask = PTE_CONT,
+ .val = PTE_CONT,
+ .set = "CON",
+ .clear = " ",
+ }, {
+ .mask = PTE_TABLE_BIT,
+ .val = PTE_TABLE_BIT,
+ .set = " ",
+ .clear = "BLK",
+ }, {
+ .mask = PTE_UXN,
+ .val = PTE_UXN,
+ .set = "UXN",
+ }, {
+ .mask = PTE_ATTRINDX_MASK,
+ .val = PTE_ATTRINDX(MT_DEVICE_nGnRnE),
+ .set = "DEVICE/nGnRnE",
+ }, {
+ .mask = PTE_ATTRINDX_MASK,
+ .val = PTE_ATTRINDX(MT_DEVICE_nGnRE),
+ .set = "DEVICE/nGnRE",
+ }, {
+ .mask = PTE_ATTRINDX_MASK,
+ .val = PTE_ATTRINDX(MT_DEVICE_GRE),
+ .set = "DEVICE/GRE",
+ }, {
+ .mask = PTE_ATTRINDX_MASK,
+ .val = PTE_ATTRINDX(MT_NORMAL_NC),
+ .set = "MEM/NORMAL-NC",
+ }, {
+ .mask = PTE_ATTRINDX_MASK,
+ .val = PTE_ATTRINDX(MT_NORMAL),
+ .set = "MEM/NORMAL",
+ }
+};
+
+struct pg_level {
+ const struct prot_bits *bits;
+ const char *name;
+ size_t num;
+ u64 mask;
+};
+
+static struct pg_level pg_level[] = {
+ {
+ }, { /* pgd */
+ .name = "PGD",
+ .bits = pte_bits,
+ .num = ARRAY_SIZE(pte_bits),
+ }, { /* pud */
+ .name = (CONFIG_PGTABLE_LEVELS > 3) ? "PUD" : "PGD",
+ .bits = pte_bits,
+ .num = ARRAY_SIZE(pte_bits),
+ }, { /* pmd */
+ .name = (CONFIG_PGTABLE_LEVELS > 2) ? "PMD" : "PGD",
+ .bits = pte_bits,
+ .num = ARRAY_SIZE(pte_bits),
+ }, { /* pte */
+ .name = "PTE",
+ .bits = pte_bits,
+ .num = ARRAY_SIZE(pte_bits),
+ },
+};
+
+static void dump_prot(struct pg_state *st, const struct prot_bits *bits,
+ size_t num)
+{
+ unsigned i;
+
+ for (i = 0; i < num; i++, bits++) {
+ const char *s;
+
+ if ((st->current_prot & bits->mask) == bits->val)
+ s = bits->set;
+ else
+ s = bits->clear;
+
+ if (s)
+ pt_dump_seq_printf(st->seq, " %s", s);
+ }
+}
+
+static void note_prot_uxn(struct pg_state *st, unsigned long addr)
+{
+ if (!st->check_wx)
+ return;
+
+ if ((st->current_prot & PTE_UXN) == PTE_UXN)
+ return;
+
+ WARN_ONCE(1, "arm64/mm: Found non-UXN mapping at address %p/%pS\n",
+ (void *)st->start_address, (void *)st->start_address);
+
+ st->uxn_pages += (addr - st->start_address) / PAGE_SIZE;
+}
+
+static void note_prot_wx(struct pg_state *st, unsigned long addr)
+{
+ if (!st->check_wx)
+ return;
+ if ((st->current_prot & PTE_RDONLY) == PTE_RDONLY)
+ return;
+ if ((st->current_prot & PTE_PXN) == PTE_PXN)
+ return;
+
+ WARN_ONCE(1, "arm64/mm: Found insecure W+X mapping at address %p/%pS\n",
+ (void *)st->start_address, (void *)st->start_address);
+
+ st->wx_pages += (addr - st->start_address) / PAGE_SIZE;
+}
+
+static void note_page(struct pg_state *st, unsigned long addr, unsigned level,
+ u64 val)
+{
+ static const char units[] = "KMGTPE";
+ u64 prot = val & pg_level[level].mask;
+
+ if (!st->level) {
+ st->level = level;
+ st->current_prot = prot;
+ st->start_address = addr;
+ pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
+ } else if (prot != st->current_prot || level != st->level ||
+ addr >= st->marker[1].start_address) {
+ const char *unit = units;
+ unsigned long delta;
+
+ if (st->current_prot) {
+ note_prot_uxn(st, addr);
+ note_prot_wx(st, addr);
+ pt_dump_seq_printf(st->seq, "0x%016lx-0x%016lx ",
+ st->start_address, addr);
+
+ delta = (addr - st->start_address) >> 10;
+ while (!(delta & 1023) && unit[1]) {
+ delta >>= 10;
+ unit++;
+ }
+ pt_dump_seq_printf(st->seq, "%9lu%c %s", delta, *unit,
+ pg_level[st->level].name);
+ if (pg_level[st->level].bits)
+ dump_prot(st, pg_level[st->level].bits,
+ pg_level[st->level].num);
+ pt_dump_seq_puts(st->seq, "\n");
+ }
+
+ if (addr >= st->marker[1].start_address) {
+ st->marker++;
+ pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
+ }
+
+ st->start_address = addr;
+ st->current_prot = prot;
+ st->level = level;
+ }
+
+ if (addr >= st->marker[1].start_address) {
+ st->marker++;
+ pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
+ }
+
+}
+
+static void walk_pte(struct pg_state *st, pmd_t *pmdp, unsigned long start)
+{
+ pte_t *ptep = pte_offset_kernel(pmdp, 0UL);
+ unsigned long addr;
+ unsigned i;
+
+ for (i = 0; i < PTRS_PER_PTE; i++, ptep++) {
+ addr = start + i * PAGE_SIZE;
+ note_page(st, addr, 4, READ_ONCE(pte_val(*ptep)));
+ }
+}
+
+static void walk_pmd(struct pg_state *st, pud_t *pudp, unsigned long start)
+{
+ pmd_t *pmdp = pmd_offset(pudp, 0UL);
+ unsigned long addr;
+ unsigned i;
+
+ for (i = 0; i < PTRS_PER_PMD; i++, pmdp++) {
+ pmd_t pmd = READ_ONCE(*pmdp);
+
+ addr = start + i * PMD_SIZE;
+ if (pmd_none(pmd) || pmd_sect(pmd)) {
+ note_page(st, addr, 3, pmd_val(pmd));
+ } else {
+ BUG_ON(pmd_bad(pmd));
+ walk_pte(st, pmdp, addr);
+ }
+ }
+}
+
+static void walk_pud(struct pg_state *st, pgd_t *pgdp, unsigned long start)
+{
+ pud_t *pudp = pud_offset(pgdp, 0UL);
+ unsigned long addr;
+ unsigned i;
+
+ for (i = 0; i < PTRS_PER_PUD; i++, pudp++) {
+ pud_t pud = READ_ONCE(*pudp);
+
+ addr = start + i * PUD_SIZE;
+ if (pud_none(pud) || pud_sect(pud)) {
+ note_page(st, addr, 2, pud_val(pud));
+ } else {
+ BUG_ON(pud_bad(pud));
+ walk_pmd(st, pudp, addr);
+ }
+ }
+}
+
+static void walk_pgd(struct pg_state *st, struct mm_struct *mm,
+ unsigned long start)
+{
+ pgd_t *pgdp = pgd_offset(mm, 0UL);
+ unsigned i;
+ unsigned long addr;
+
+ for (i = 0; i < PTRS_PER_PGD; i++, pgdp++) {
+ pgd_t pgd = READ_ONCE(*pgdp);
+
+ addr = start + i * PGDIR_SIZE;
+ if (pgd_none(pgd)) {
+ note_page(st, addr, 1, pgd_val(pgd));
+ } else {
+ BUG_ON(pgd_bad(pgd));
+ walk_pud(st, pgdp, addr);
+ }
+ }
+}
+
+void ptdump_walk_pgd(struct seq_file *m, struct ptdump_info *info)
+{
+ struct pg_state st = {
+ .seq = m,
+ .marker = info->markers,
+ };
+
+ walk_pgd(&st, info->mm, info->base_addr);
+
+ note_page(&st, 0, 0, 0);
+}
+
+static void ptdump_initialize(void)
+{
+ unsigned i, j;
+
+ for (i = 0; i < ARRAY_SIZE(pg_level); i++)
+ if (pg_level[i].bits)
+ for (j = 0; j < pg_level[i].num; j++)
+ pg_level[i].mask |= pg_level[i].bits[j].mask;
+}
+
+static struct ptdump_info kernel_ptdump_info = {
+ .mm = &init_mm,
+ .markers = address_markers,
+ .base_addr = VA_START,
+};
+
+void ptdump_check_wx(void)
+{
+ struct pg_state st = {
+ .seq = NULL,
+ .marker = (struct addr_marker[]) {
+ { 0, NULL},
+ { -1, NULL},
+ },
+ .check_wx = true,
+ };
+
+ walk_pgd(&st, &init_mm, VA_START);
+ note_page(&st, 0, 0, 0);
+ if (st.wx_pages || st.uxn_pages)
+ pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found, %lu non-UXN pages found\n",
+ st.wx_pages, st.uxn_pages);
+ else
+ pr_info("Checked W+X mappings: passed, no W+X pages found\n");
+}
+
+static int ptdump_init(void)
+{
+ ptdump_initialize();
+ return ptdump_debugfs_register(&kernel_ptdump_info,
+ "kernel_page_tables");
+}
+device_initcall(ptdump_init);
diff --git a/arch/arm64/mm/extable.c b/arch/arm64/mm/extable.c
new file mode 100644
index 000000000..81e694af5
--- /dev/null
+++ b/arch/arm64/mm/extable.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Based on arch/arm/mm/extable.c
+ */
+
+#include <linux/extable.h>
+#include <linux/uaccess.h>
+
+int fixup_exception(struct pt_regs *regs)
+{
+ const struct exception_table_entry *fixup;
+
+ fixup = search_exception_tables(instruction_pointer(regs));
+ if (fixup)
+ regs->pc = (unsigned long)&fixup->fixup + fixup->fixup;
+
+ return fixup != NULL;
+}
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
new file mode 100644
index 000000000..b046006a3
--- /dev/null
+++ b/arch/arm64/mm/fault.c
@@ -0,0 +1,914 @@
+/*
+ * Based on arch/arm/mm/fault.c
+ *
+ * Copyright (C) 1995 Linus Torvalds
+ * Copyright (C) 1995-2004 Russell King
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/extable.h>
+#include <linux/signal.h>
+#include <linux/mm.h>
+#include <linux/hardirq.h>
+#include <linux/init.h>
+#include <linux/kprobes.h>
+#include <linux/uaccess.h>
+#include <linux/page-flags.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/debug.h>
+#include <linux/highmem.h>
+#include <linux/perf_event.h>
+#include <linux/preempt.h>
+#include <linux/hugetlb.h>
+
+#include <asm/bug.h>
+#include <asm/cmpxchg.h>
+#include <asm/cpufeature.h>
+#include <asm/exception.h>
+#include <asm/debug-monitors.h>
+#include <asm/esr.h>
+#include <asm/sysreg.h>
+#include <asm/system_misc.h>
+#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
+#include <asm/traps.h>
+
+#include <acpi/ghes.h>
+
+struct fault_info {
+ int (*fn)(unsigned long addr, unsigned int esr,
+ struct pt_regs *regs);
+ int sig;
+ int code;
+ const char *name;
+};
+
+static const struct fault_info fault_info[];
+
+static inline const struct fault_info *esr_to_fault_info(unsigned int esr)
+{
+ return fault_info + (esr & 63);
+}
+
+#ifdef CONFIG_KPROBES
+static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr)
+{
+ int ret = 0;
+
+ /* kprobe_running() needs smp_processor_id() */
+ if (!user_mode(regs)) {
+ preempt_disable();
+ if (kprobe_running() && kprobe_fault_handler(regs, esr))
+ ret = 1;
+ preempt_enable();
+ }
+
+ return ret;
+}
+#else
+static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr)
+{
+ return 0;
+}
+#endif
+
+static void data_abort_decode(unsigned int esr)
+{
+ pr_alert("Data abort info:\n");
+
+ if (esr & ESR_ELx_ISV) {
+ pr_alert(" Access size = %u byte(s)\n",
+ 1U << ((esr & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT));
+ pr_alert(" SSE = %lu, SRT = %lu\n",
+ (esr & ESR_ELx_SSE) >> ESR_ELx_SSE_SHIFT,
+ (esr & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT);
+ pr_alert(" SF = %lu, AR = %lu\n",
+ (esr & ESR_ELx_SF) >> ESR_ELx_SF_SHIFT,
+ (esr & ESR_ELx_AR) >> ESR_ELx_AR_SHIFT);
+ } else {
+ pr_alert(" ISV = 0, ISS = 0x%08lx\n", esr & ESR_ELx_ISS_MASK);
+ }
+
+ pr_alert(" CM = %lu, WnR = %lu\n",
+ (esr & ESR_ELx_CM) >> ESR_ELx_CM_SHIFT,
+ (esr & ESR_ELx_WNR) >> ESR_ELx_WNR_SHIFT);
+}
+
+static void mem_abort_decode(unsigned int esr)
+{
+ pr_alert("Mem abort info:\n");
+
+ pr_alert(" ESR = 0x%08x\n", esr);
+ pr_alert(" Exception class = %s, IL = %u bits\n",
+ esr_get_class_string(esr),
+ (esr & ESR_ELx_IL) ? 32 : 16);
+ pr_alert(" SET = %lu, FnV = %lu\n",
+ (esr & ESR_ELx_SET_MASK) >> ESR_ELx_SET_SHIFT,
+ (esr & ESR_ELx_FnV) >> ESR_ELx_FnV_SHIFT);
+ pr_alert(" EA = %lu, S1PTW = %lu\n",
+ (esr & ESR_ELx_EA) >> ESR_ELx_EA_SHIFT,
+ (esr & ESR_ELx_S1PTW) >> ESR_ELx_S1PTW_SHIFT);
+
+ if (esr_is_data_abort(esr))
+ data_abort_decode(esr);
+}
+
+/*
+ * Dump out the page tables associated with 'addr' in the currently active mm.
+ */
+void show_pte(unsigned long addr)
+{
+ struct mm_struct *mm;
+ pgd_t *pgdp;
+ pgd_t pgd;
+
+ if (addr < TASK_SIZE) {
+ /* TTBR0 */
+ mm = current->active_mm;
+ if (mm == &init_mm) {
+ pr_alert("[%016lx] user address but active_mm is swapper\n",
+ addr);
+ return;
+ }
+ } else if (addr >= VA_START) {
+ /* TTBR1 */
+ mm = &init_mm;
+ } else {
+ pr_alert("[%016lx] address between user and kernel address ranges\n",
+ addr);
+ return;
+ }
+
+ pr_alert("%s pgtable: %luk pages, %u-bit VAs, pgdp = %p\n",
+ mm == &init_mm ? "swapper" : "user", PAGE_SIZE / SZ_1K,
+ VA_BITS, mm->pgd);
+ pgdp = pgd_offset(mm, addr);
+ pgd = READ_ONCE(*pgdp);
+ pr_alert("[%016lx] pgd=%016llx", addr, pgd_val(pgd));
+
+ do {
+ pud_t *pudp, pud;
+ pmd_t *pmdp, pmd;
+ pte_t *ptep, pte;
+
+ if (pgd_none(pgd) || pgd_bad(pgd))
+ break;
+
+ pudp = pud_offset(pgdp, addr);
+ pud = READ_ONCE(*pudp);
+ pr_cont(", pud=%016llx", pud_val(pud));
+ if (pud_none(pud) || pud_bad(pud))
+ break;
+
+ pmdp = pmd_offset(pudp, addr);
+ pmd = READ_ONCE(*pmdp);
+ pr_cont(", pmd=%016llx", pmd_val(pmd));
+ if (pmd_none(pmd) || pmd_bad(pmd))
+ break;
+
+ ptep = pte_offset_map(pmdp, addr);
+ pte = READ_ONCE(*ptep);
+ pr_cont(", pte=%016llx", pte_val(pte));
+ pte_unmap(ptep);
+ } while(0);
+
+ pr_cont("\n");
+}
+
+/*
+ * This function sets the access flags (dirty, accessed), as well as write
+ * permission, and only to a more permissive setting.
+ *
+ * It needs to cope with hardware update of the accessed/dirty state by other
+ * agents in the system and can safely skip the __sync_icache_dcache() call as,
+ * like set_pte_at(), the PTE is never changed from no-exec to exec here.
+ *
+ * Returns whether or not the PTE actually changed.
+ */
+int ptep_set_access_flags(struct vm_area_struct *vma,
+ unsigned long address, pte_t *ptep,
+ pte_t entry, int dirty)
+{
+ pteval_t old_pteval, pteval;
+ pte_t pte = READ_ONCE(*ptep);
+
+ if (pte_same(pte, entry))
+ return 0;
+
+ /* only preserve the access flags and write permission */
+ pte_val(entry) &= PTE_RDONLY | PTE_AF | PTE_WRITE | PTE_DIRTY;
+
+ /*
+ * Setting the flags must be done atomically to avoid racing with the
+ * hardware update of the access/dirty state. The PTE_RDONLY bit must
+ * be set to the most permissive (lowest value) of *ptep and entry
+ * (calculated as: a & b == ~(~a | ~b)).
+ */
+ pte_val(entry) ^= PTE_RDONLY;
+ pteval = pte_val(pte);
+ do {
+ old_pteval = pteval;
+ pteval ^= PTE_RDONLY;
+ pteval |= pte_val(entry);
+ pteval ^= PTE_RDONLY;
+ pteval = cmpxchg_relaxed(&pte_val(*ptep), old_pteval, pteval);
+ } while (pteval != old_pteval);
+
+ flush_tlb_fix_spurious_fault(vma, address);
+ return 1;
+}
+
+static bool is_el1_instruction_abort(unsigned int esr)
+{
+ return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_CUR;
+}
+
+static inline bool is_el1_permission_fault(unsigned int esr,
+ struct pt_regs *regs,
+ unsigned long addr)
+{
+ unsigned int ec = ESR_ELx_EC(esr);
+ unsigned int fsc_type = esr & ESR_ELx_FSC_TYPE;
+
+ if (ec != ESR_ELx_EC_DABT_CUR && ec != ESR_ELx_EC_IABT_CUR)
+ return false;
+
+ if (fsc_type == ESR_ELx_FSC_PERM)
+ return true;
+
+ if (addr < TASK_SIZE && system_uses_ttbr0_pan())
+ return fsc_type == ESR_ELx_FSC_FAULT &&
+ (regs->pstate & PSR_PAN_BIT);
+
+ return false;
+}
+
+static void die_kernel_fault(const char *msg, unsigned long addr,
+ unsigned int esr, struct pt_regs *regs)
+{
+ bust_spinlocks(1);
+
+ pr_alert("Unable to handle kernel %s at virtual address %016lx\n", msg,
+ addr);
+
+ mem_abort_decode(esr);
+
+ show_pte(addr);
+ die("Oops", regs, esr);
+ bust_spinlocks(0);
+ do_exit(SIGKILL);
+}
+
+static void __do_kernel_fault(unsigned long addr, unsigned int esr,
+ struct pt_regs *regs)
+{
+ const char *msg;
+
+ /*
+ * Are we prepared to handle this kernel fault?
+ * We are almost certainly not prepared to handle instruction faults.
+ */
+ if (!is_el1_instruction_abort(esr) && fixup_exception(regs))
+ return;
+
+ if (is_el1_permission_fault(esr, regs, addr)) {
+ if (esr & ESR_ELx_WNR)
+ msg = "write to read-only memory";
+ else
+ msg = "read from unreadable memory";
+ } else if (addr < PAGE_SIZE) {
+ msg = "NULL pointer dereference";
+ } else {
+ msg = "paging request";
+ }
+
+ die_kernel_fault(msg, addr, esr, regs);
+}
+
+static void __do_user_fault(struct siginfo *info, unsigned int esr)
+{
+ current->thread.fault_address = (unsigned long)info->si_addr;
+
+ /*
+ * If the faulting address is in the kernel, we must sanitize the ESR.
+ * From userspace's point of view, kernel-only mappings don't exist
+ * at all, so we report them as level 0 translation faults.
+ * (This is not quite the way that "no mapping there at all" behaves:
+ * an alignment fault not caused by the memory type would take
+ * precedence over translation fault for a real access to empty
+ * space. Unfortunately we can't easily distinguish "alignment fault
+ * not caused by memory type" from "alignment fault caused by memory
+ * type", so we ignore this wrinkle and just return the translation
+ * fault.)
+ */
+ if (current->thread.fault_address >= TASK_SIZE) {
+ switch (ESR_ELx_EC(esr)) {
+ case ESR_ELx_EC_DABT_LOW:
+ /*
+ * These bits provide only information about the
+ * faulting instruction, which userspace knows already.
+ * We explicitly clear bits which are architecturally
+ * RES0 in case they are given meanings in future.
+ * We always report the ESR as if the fault was taken
+ * to EL1 and so ISV and the bits in ISS[23:14] are
+ * clear. (In fact it always will be a fault to EL1.)
+ */
+ esr &= ESR_ELx_EC_MASK | ESR_ELx_IL |
+ ESR_ELx_CM | ESR_ELx_WNR;
+ esr |= ESR_ELx_FSC_FAULT;
+ break;
+ case ESR_ELx_EC_IABT_LOW:
+ /*
+ * Claim a level 0 translation fault.
+ * All other bits are architecturally RES0 for faults
+ * reported with that DFSC value, so we clear them.
+ */
+ esr &= ESR_ELx_EC_MASK | ESR_ELx_IL;
+ esr |= ESR_ELx_FSC_FAULT;
+ break;
+ default:
+ /*
+ * This should never happen (entry.S only brings us
+ * into this code for insn and data aborts from a lower
+ * exception level). Fail safe by not providing an ESR
+ * context record at all.
+ */
+ WARN(1, "ESR 0x%x is not DABT or IABT from EL0\n", esr);
+ esr = 0;
+ break;
+ }
+ }
+
+ current->thread.fault_code = esr;
+ arm64_force_sig_info(info, esr_to_fault_info(esr)->name, current);
+}
+
+static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *regs)
+{
+ /*
+ * If we are in kernel mode at this point, we have no context to
+ * handle this fault with.
+ */
+ if (user_mode(regs)) {
+ const struct fault_info *inf = esr_to_fault_info(esr);
+ struct siginfo si;
+
+ clear_siginfo(&si);
+ si.si_signo = inf->sig;
+ si.si_code = inf->code;
+ si.si_addr = (void __user *)addr;
+
+ __do_user_fault(&si, esr);
+ } else {
+ __do_kernel_fault(addr, esr, regs);
+ }
+}
+
+#define VM_FAULT_BADMAP 0x010000
+#define VM_FAULT_BADACCESS 0x020000
+
+static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr,
+ unsigned int mm_flags, unsigned long vm_flags,
+ struct task_struct *tsk)
+{
+ struct vm_area_struct *vma;
+ vm_fault_t fault;
+
+ vma = find_vma(mm, addr);
+ fault = VM_FAULT_BADMAP;
+ if (unlikely(!vma))
+ goto out;
+ if (unlikely(vma->vm_start > addr))
+ goto check_stack;
+
+ /*
+ * Ok, we have a good vm_area for this memory access, so we can handle
+ * it.
+ */
+good_area:
+ /*
+ * Check that the permissions on the VMA allow for the fault which
+ * occurred.
+ */
+ if (!(vma->vm_flags & vm_flags)) {
+ fault = VM_FAULT_BADACCESS;
+ goto out;
+ }
+
+ return handle_mm_fault(vma, addr & PAGE_MASK, mm_flags);
+
+check_stack:
+ if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr))
+ goto good_area;
+out:
+ return fault;
+}
+
+static bool is_el0_instruction_abort(unsigned int esr)
+{
+ return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_LOW;
+}
+
+static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
+ struct pt_regs *regs)
+{
+ struct task_struct *tsk;
+ struct mm_struct *mm;
+ struct siginfo si;
+ vm_fault_t fault, major = 0;
+ unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC;
+ unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
+
+ if (notify_page_fault(regs, esr))
+ return 0;
+
+ tsk = current;
+ mm = tsk->mm;
+
+ /*
+ * If we're in an interrupt or have no user context, we must not take
+ * the fault.
+ */
+ if (faulthandler_disabled() || !mm)
+ goto no_context;
+
+ if (user_mode(regs))
+ mm_flags |= FAULT_FLAG_USER;
+
+ if (is_el0_instruction_abort(esr)) {
+ vm_flags = VM_EXEC;
+ } else if ((esr & ESR_ELx_WNR) && !(esr & ESR_ELx_CM)) {
+ vm_flags = VM_WRITE;
+ mm_flags |= FAULT_FLAG_WRITE;
+ }
+
+ if (addr < TASK_SIZE && is_el1_permission_fault(esr, regs, addr)) {
+ /* regs->orig_addr_limit may be 0 if we entered from EL0 */
+ if (regs->orig_addr_limit == KERNEL_DS)
+ die_kernel_fault("access to user memory with fs=KERNEL_DS",
+ addr, esr, regs);
+
+ if (is_el1_instruction_abort(esr))
+ die_kernel_fault("execution of user memory",
+ addr, esr, regs);
+
+ if (!search_exception_tables(regs->pc))
+ die_kernel_fault("access to user memory outside uaccess routines",
+ addr, esr, regs);
+ }
+
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
+
+ /*
+ * As per x86, we may deadlock here. However, since the kernel only
+ * validly references user space from well defined areas of the code,
+ * we can bug out early if this is from code which shouldn't.
+ */
+ if (!down_read_trylock(&mm->mmap_sem)) {
+ if (!user_mode(regs) && !search_exception_tables(regs->pc))
+ goto no_context;
+retry:
+ down_read(&mm->mmap_sem);
+ } else {
+ /*
+ * The above down_read_trylock() might have succeeded in which
+ * case, we'll have missed the might_sleep() from down_read().
+ */
+ might_sleep();
+#ifdef CONFIG_DEBUG_VM
+ if (!user_mode(regs) && !search_exception_tables(regs->pc))
+ goto no_context;
+#endif
+ }
+
+ fault = __do_page_fault(mm, addr, mm_flags, vm_flags, tsk);
+ major |= fault & VM_FAULT_MAJOR;
+
+ if (fault & VM_FAULT_RETRY) {
+ /*
+ * If we need to retry but a fatal signal is pending,
+ * handle the signal first. We do not need to release
+ * the mmap_sem because it would already be released
+ * in __lock_page_or_retry in mm/filemap.c.
+ */
+ if (fatal_signal_pending(current)) {
+ if (!user_mode(regs))
+ goto no_context;
+ return 0;
+ }
+
+ /*
+ * Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk of
+ * starvation.
+ */
+ if (mm_flags & FAULT_FLAG_ALLOW_RETRY) {
+ mm_flags &= ~FAULT_FLAG_ALLOW_RETRY;
+ mm_flags |= FAULT_FLAG_TRIED;
+ goto retry;
+ }
+ }
+ up_read(&mm->mmap_sem);
+
+ /*
+ * Handle the "normal" (no error) case first.
+ */
+ if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP |
+ VM_FAULT_BADACCESS)))) {
+ /*
+ * Major/minor page fault accounting is only done
+ * once. If we go through a retry, it is extremely
+ * likely that the page will be found in page cache at
+ * that point.
+ */
+ if (major) {
+ tsk->maj_flt++;
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs,
+ addr);
+ } else {
+ tsk->min_flt++;
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs,
+ addr);
+ }
+
+ return 0;
+ }
+
+ /*
+ * If we are in kernel mode at this point, we have no context to
+ * handle this fault with.
+ */
+ if (!user_mode(regs))
+ goto no_context;
+
+ if (fault & VM_FAULT_OOM) {
+ /*
+ * We ran out of memory, call the OOM killer, and return to
+ * userspace (which will retry the fault, or kill us if we got
+ * oom-killed).
+ */
+ pagefault_out_of_memory();
+ return 0;
+ }
+
+ clear_siginfo(&si);
+ si.si_addr = (void __user *)addr;
+
+ if (fault & VM_FAULT_SIGBUS) {
+ /*
+ * We had some memory, but were unable to successfully fix up
+ * this page fault.
+ */
+ si.si_signo = SIGBUS;
+ si.si_code = BUS_ADRERR;
+ } else if (fault & VM_FAULT_HWPOISON_LARGE) {
+ unsigned int hindex = VM_FAULT_GET_HINDEX(fault);
+
+ si.si_signo = SIGBUS;
+ si.si_code = BUS_MCEERR_AR;
+ si.si_addr_lsb = hstate_index_to_shift(hindex);
+ } else if (fault & VM_FAULT_HWPOISON) {
+ si.si_signo = SIGBUS;
+ si.si_code = BUS_MCEERR_AR;
+ si.si_addr_lsb = PAGE_SHIFT;
+ } else {
+ /*
+ * Something tried to access memory that isn't in our memory
+ * map.
+ */
+ si.si_signo = SIGSEGV;
+ si.si_code = fault == VM_FAULT_BADACCESS ?
+ SEGV_ACCERR : SEGV_MAPERR;
+ }
+
+ __do_user_fault(&si, esr);
+ return 0;
+
+no_context:
+ __do_kernel_fault(addr, esr, regs);
+ return 0;
+}
+
+static int __kprobes do_translation_fault(unsigned long addr,
+ unsigned int esr,
+ struct pt_regs *regs)
+{
+ if (addr < TASK_SIZE)
+ return do_page_fault(addr, esr, regs);
+
+ do_bad_area(addr, esr, regs);
+ return 0;
+}
+
+static int do_alignment_fault(unsigned long addr, unsigned int esr,
+ struct pt_regs *regs)
+{
+ do_bad_area(addr, esr, regs);
+ return 0;
+}
+
+static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs)
+{
+ return 1; /* "fault" */
+}
+
+static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs)
+{
+ struct siginfo info;
+ const struct fault_info *inf;
+
+ inf = esr_to_fault_info(esr);
+
+ /*
+ * Synchronous aborts may interrupt code which had interrupts masked.
+ * Before calling out into the wider kernel tell the interested
+ * subsystems.
+ */
+ if (IS_ENABLED(CONFIG_ACPI_APEI_SEA)) {
+ if (interrupts_enabled(regs))
+ nmi_enter();
+
+ ghes_notify_sea();
+
+ if (interrupts_enabled(regs))
+ nmi_exit();
+ }
+
+ clear_siginfo(&info);
+ info.si_signo = inf->sig;
+ info.si_errno = 0;
+ info.si_code = inf->code;
+ if (esr & ESR_ELx_FnV)
+ info.si_addr = NULL;
+ else
+ info.si_addr = (void __user *)addr;
+ arm64_notify_die(inf->name, regs, &info, esr);
+
+ return 0;
+}
+
+static const struct fault_info fault_info[] = {
+ { do_bad, SIGKILL, SI_KERNEL, "ttbr address size fault" },
+ { do_bad, SIGKILL, SI_KERNEL, "level 1 address size fault" },
+ { do_bad, SIGKILL, SI_KERNEL, "level 2 address size fault" },
+ { do_bad, SIGKILL, SI_KERNEL, "level 3 address size fault" },
+ { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 0 translation fault" },
+ { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 1 translation fault" },
+ { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 2 translation fault" },
+ { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 8" },
+ { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 access flag fault" },
+ { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 access flag fault" },
+ { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 access flag fault" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 12" },
+ { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 permission fault" },
+ { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 permission fault" },
+ { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 permission fault" },
+ { do_sea, SIGBUS, BUS_OBJERR, "synchronous external abort" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 17" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 18" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 19" },
+ { do_sea, SIGKILL, SI_KERNEL, "level 0 (translation table walk)" },
+ { do_sea, SIGKILL, SI_KERNEL, "level 1 (translation table walk)" },
+ { do_sea, SIGKILL, SI_KERNEL, "level 2 (translation table walk)" },
+ { do_sea, SIGKILL, SI_KERNEL, "level 3 (translation table walk)" },
+ { do_sea, SIGBUS, BUS_OBJERR, "synchronous parity or ECC error" }, // Reserved when RAS is implemented
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 25" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 26" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 27" },
+ { do_sea, SIGKILL, SI_KERNEL, "level 0 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented
+ { do_sea, SIGKILL, SI_KERNEL, "level 1 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented
+ { do_sea, SIGKILL, SI_KERNEL, "level 2 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented
+ { do_sea, SIGKILL, SI_KERNEL, "level 3 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 32" },
+ { do_alignment_fault, SIGBUS, BUS_ADRALN, "alignment fault" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 34" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 35" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 36" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 37" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 38" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 39" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 40" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 41" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 42" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 43" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 44" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 45" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 46" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 47" },
+ { do_bad, SIGKILL, SI_KERNEL, "TLB conflict abort" },
+ { do_bad, SIGKILL, SI_KERNEL, "Unsupported atomic hardware update fault" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 50" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 51" },
+ { do_bad, SIGKILL, SI_KERNEL, "implementation fault (lockdown abort)" },
+ { do_bad, SIGBUS, BUS_OBJERR, "implementation fault (unsupported exclusive)" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 54" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 55" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 56" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 57" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 58" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 59" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 60" },
+ { do_bad, SIGKILL, SI_KERNEL, "section domain fault" },
+ { do_bad, SIGKILL, SI_KERNEL, "page domain fault" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 63" },
+};
+
+int handle_guest_sea(phys_addr_t addr, unsigned int esr)
+{
+ return ghes_notify_sea();
+}
+
+asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
+ struct pt_regs *regs)
+{
+ const struct fault_info *inf = esr_to_fault_info(esr);
+ struct siginfo info;
+
+ if (!inf->fn(addr, esr, regs))
+ return;
+
+ if (!user_mode(regs)) {
+ pr_alert("Unhandled fault at 0x%016lx\n", addr);
+ mem_abort_decode(esr);
+ show_pte(addr);
+ }
+
+ clear_siginfo(&info);
+ info.si_signo = inf->sig;
+ info.si_errno = 0;
+ info.si_code = inf->code;
+ info.si_addr = (void __user *)addr;
+ arm64_notify_die(inf->name, regs, &info, esr);
+}
+
+asmlinkage void __exception do_el0_irq_bp_hardening(void)
+{
+ /* PC has already been checked in entry.S */
+ arm64_apply_bp_hardening();
+}
+
+asmlinkage void __exception do_el0_ia_bp_hardening(unsigned long addr,
+ unsigned int esr,
+ struct pt_regs *regs)
+{
+ /*
+ * We've taken an instruction abort from userspace and not yet
+ * re-enabled IRQs. If the address is a kernel address, apply
+ * BP hardening prior to enabling IRQs and pre-emption.
+ */
+ if (addr > TASK_SIZE)
+ arm64_apply_bp_hardening();
+
+ local_irq_enable();
+ do_mem_abort(addr, esr, regs);
+}
+
+
+asmlinkage void __exception do_sp_pc_abort(unsigned long addr,
+ unsigned int esr,
+ struct pt_regs *regs)
+{
+ struct siginfo info;
+
+ if (user_mode(regs)) {
+ if (instruction_pointer(regs) > TASK_SIZE)
+ arm64_apply_bp_hardening();
+ local_irq_enable();
+ }
+
+ clear_siginfo(&info);
+ info.si_signo = SIGBUS;
+ info.si_errno = 0;
+ info.si_code = BUS_ADRALN;
+ info.si_addr = (void __user *)addr;
+ arm64_notify_die("SP/PC alignment exception", regs, &info, esr);
+}
+
+int __init early_brk64(unsigned long addr, unsigned int esr,
+ struct pt_regs *regs);
+
+/*
+ * __refdata because early_brk64 is __init, but the reference to it is
+ * clobbered at arch_initcall time.
+ * See traps.c and debug-monitors.c:debug_traps_init().
+ */
+static struct fault_info __refdata debug_fault_info[] = {
+ { do_bad, SIGTRAP, TRAP_HWBKPT, "hardware breakpoint" },
+ { do_bad, SIGTRAP, TRAP_HWBKPT, "hardware single-step" },
+ { do_bad, SIGTRAP, TRAP_HWBKPT, "hardware watchpoint" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 3" },
+ { do_bad, SIGTRAP, TRAP_BRKPT, "aarch32 BKPT" },
+ { do_bad, SIGKILL, SI_KERNEL, "aarch32 vector catch" },
+ { early_brk64, SIGTRAP, TRAP_BRKPT, "aarch64 BRK" },
+ { do_bad, SIGKILL, SI_KERNEL, "unknown 7" },
+};
+
+void __init hook_debug_fault_code(int nr,
+ int (*fn)(unsigned long, unsigned int, struct pt_regs *),
+ int sig, int code, const char *name)
+{
+ BUG_ON(nr < 0 || nr >= ARRAY_SIZE(debug_fault_info));
+
+ debug_fault_info[nr].fn = fn;
+ debug_fault_info[nr].sig = sig;
+ debug_fault_info[nr].code = code;
+ debug_fault_info[nr].name = name;
+}
+
+#ifdef CONFIG_ARM64_ERRATUM_1463225
+DECLARE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa);
+
+static int __exception
+cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs)
+{
+ if (user_mode(regs))
+ return 0;
+
+ if (!__this_cpu_read(__in_cortex_a76_erratum_1463225_wa))
+ return 0;
+
+ /*
+ * We've taken a dummy step exception from the kernel to ensure
+ * that interrupts are re-enabled on the syscall path. Return back
+ * to cortex_a76_erratum_1463225_svc_handler() with debug exceptions
+ * masked so that we can safely restore the mdscr and get on with
+ * handling the syscall.
+ */
+ regs->pstate |= PSR_D_BIT;
+ return 1;
+}
+#else
+static int __exception
+cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs)
+{
+ return 0;
+}
+#endif /* CONFIG_ARM64_ERRATUM_1463225 */
+
+asmlinkage int __exception do_debug_exception(unsigned long addr_if_watchpoint,
+ unsigned int esr,
+ struct pt_regs *regs)
+{
+ const struct fault_info *inf = debug_fault_info + DBG_ESR_EVT(esr);
+ unsigned long pc = instruction_pointer(regs);
+ int rv;
+
+ if (cortex_a76_erratum_1463225_debug_handler(regs))
+ return 0;
+
+ /*
+ * Tell lockdep we disabled irqs in entry.S. Do nothing if they were
+ * already disabled to preserve the last enabled/disabled addresses.
+ */
+ if (interrupts_enabled(regs))
+ trace_hardirqs_off();
+
+ if (user_mode(regs) && pc > TASK_SIZE)
+ arm64_apply_bp_hardening();
+
+ if (!inf->fn(addr_if_watchpoint, esr, regs)) {
+ rv = 1;
+ } else {
+ struct siginfo info;
+
+ clear_siginfo(&info);
+ info.si_signo = inf->sig;
+ info.si_errno = 0;
+ info.si_code = inf->code;
+ info.si_addr = (void __user *)pc;
+ arm64_notify_die(inf->name, regs, &info, esr);
+ rv = 0;
+ }
+
+ if (interrupts_enabled(regs))
+ trace_hardirqs_on();
+
+ return rv;
+}
+NOKPROBE_SYMBOL(do_debug_exception);
+
+#ifdef CONFIG_ARM64_PAN
+void cpu_enable_pan(const struct arm64_cpu_capabilities *__unused)
+{
+ /*
+ * We modify PSTATE. This won't work from irq context as the PSTATE
+ * is discarded once we return from the exception.
+ */
+ WARN_ON_ONCE(in_interrupt());
+
+ sysreg_clear_set(sctlr_el1, SCTLR_EL1_SPAN, 0);
+ asm(SET_PSTATE_PAN(1));
+}
+#endif /* CONFIG_ARM64_PAN */
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
new file mode 100644
index 000000000..5c9073bac
--- /dev/null
+++ b/arch/arm64/mm/flush.c
@@ -0,0 +1,106 @@
+/*
+ * Based on arch/arm/mm/flush.c
+ *
+ * Copyright (C) 1995-2002 Russell King
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+
+#include <asm/cacheflush.h>
+#include <asm/cache.h>
+#include <asm/tlbflush.h>
+
+void sync_icache_aliases(void *kaddr, unsigned long len)
+{
+ unsigned long addr = (unsigned long)kaddr;
+
+ if (icache_is_aliasing()) {
+ __clean_dcache_area_pou(kaddr, len);
+ __flush_icache_all();
+ } else {
+ /*
+ * Don't issue kick_all_cpus_sync() after I-cache invalidation
+ * for user mappings.
+ */
+ __flush_icache_range(addr, addr + len);
+ }
+}
+
+static void flush_ptrace_access(struct vm_area_struct *vma, struct page *page,
+ unsigned long uaddr, void *kaddr,
+ unsigned long len)
+{
+ if (vma->vm_flags & VM_EXEC)
+ sync_icache_aliases(kaddr, len);
+}
+
+/*
+ * Copy user data from/to a page which is mapped into a different processes
+ * address space. Really, we want to allow our "user space" model to handle
+ * this.
+ */
+void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
+ unsigned long uaddr, void *dst, const void *src,
+ unsigned long len)
+{
+ memcpy(dst, src, len);
+ flush_ptrace_access(vma, page, uaddr, dst, len);
+}
+
+void __sync_icache_dcache(pte_t pte)
+{
+ struct page *page = pte_page(pte);
+
+ if (!test_and_set_bit(PG_dcache_clean, &page->flags))
+ sync_icache_aliases(page_address(page),
+ PAGE_SIZE << compound_order(page));
+}
+EXPORT_SYMBOL_GPL(__sync_icache_dcache);
+
+/*
+ * This function is called when a page has been modified by the kernel. Mark
+ * it as dirty for later flushing when mapped in user space (if executable,
+ * see __sync_icache_dcache).
+ */
+void flush_dcache_page(struct page *page)
+{
+ if (test_bit(PG_dcache_clean, &page->flags))
+ clear_bit(PG_dcache_clean, &page->flags);
+}
+EXPORT_SYMBOL(flush_dcache_page);
+
+/*
+ * Additional functions defined in assembly.
+ */
+EXPORT_SYMBOL(__flush_icache_range);
+
+#ifdef CONFIG_ARCH_HAS_PMEM_API
+void arch_wb_cache_pmem(void *addr, size_t size)
+{
+ /* Ensure order against any prior non-cacheable writes */
+ dmb(osh);
+ __clean_dcache_area_pop(addr, size);
+}
+EXPORT_SYMBOL_GPL(arch_wb_cache_pmem);
+
+void arch_invalidate_pmem(void *addr, size_t size)
+{
+ __inval_dcache_area(addr, size);
+}
+EXPORT_SYMBOL_GPL(arch_invalidate_pmem);
+#endif
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
new file mode 100644
index 000000000..1d7656761
--- /dev/null
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -0,0 +1,463 @@
+/*
+ * arch/arm64/mm/hugetlbpage.c
+ *
+ * Copyright (C) 2013 Linaro Ltd.
+ *
+ * Based on arch/x86/mm/hugetlbpage.c.
+ *
+ * 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 <linux/init.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <linux/pagemap.h>
+#include <linux/err.h>
+#include <linux/sysctl.h>
+#include <asm/mman.h>
+#include <asm/tlb.h>
+#include <asm/tlbflush.h>
+#include <asm/pgalloc.h>
+
+int pmd_huge(pmd_t pmd)
+{
+ return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);
+}
+
+int pud_huge(pud_t pud)
+{
+#ifndef __PAGETABLE_PMD_FOLDED
+ return pud_val(pud) && !(pud_val(pud) & PUD_TABLE_BIT);
+#else
+ return 0;
+#endif
+}
+
+/*
+ * Select all bits except the pfn
+ */
+static inline pgprot_t pte_pgprot(pte_t pte)
+{
+ unsigned long pfn = pte_pfn(pte);
+
+ return __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte));
+}
+
+static int find_num_contig(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, size_t *pgsize)
+{
+ pgd_t *pgdp = pgd_offset(mm, addr);
+ pud_t *pudp;
+ pmd_t *pmdp;
+
+ *pgsize = PAGE_SIZE;
+ pudp = pud_offset(pgdp, addr);
+ pmdp = pmd_offset(pudp, addr);
+ if ((pte_t *)pmdp == ptep) {
+ *pgsize = PMD_SIZE;
+ return CONT_PMDS;
+ }
+ return CONT_PTES;
+}
+
+static inline int num_contig_ptes(unsigned long size, size_t *pgsize)
+{
+ int contig_ptes = 0;
+
+ *pgsize = size;
+
+ switch (size) {
+#ifdef CONFIG_ARM64_4K_PAGES
+ case PUD_SIZE:
+#endif
+ case PMD_SIZE:
+ contig_ptes = 1;
+ break;
+ case CONT_PMD_SIZE:
+ *pgsize = PMD_SIZE;
+ contig_ptes = CONT_PMDS;
+ break;
+ case CONT_PTE_SIZE:
+ *pgsize = PAGE_SIZE;
+ contig_ptes = CONT_PTES;
+ break;
+ }
+
+ return contig_ptes;
+}
+
+/*
+ * Changing some bits of contiguous entries requires us to follow a
+ * Break-Before-Make approach, breaking the whole contiguous set
+ * before we can change any entries. See ARM DDI 0487A.k_iss10775,
+ * "Misprogramming of the Contiguous bit", page D4-1762.
+ *
+ * This helper performs the break step.
+ */
+static pte_t get_clear_flush(struct mm_struct *mm,
+ unsigned long addr,
+ pte_t *ptep,
+ unsigned long pgsize,
+ unsigned long ncontig)
+{
+ pte_t orig_pte = huge_ptep_get(ptep);
+ bool valid = pte_valid(orig_pte);
+ unsigned long i, saddr = addr;
+
+ for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) {
+ pte_t pte = ptep_get_and_clear(mm, addr, ptep);
+
+ /*
+ * If HW_AFDBM is enabled, then the HW could turn on
+ * the dirty or accessed bit for any page in the set,
+ * so check them all.
+ */
+ if (pte_dirty(pte))
+ orig_pte = pte_mkdirty(orig_pte);
+
+ if (pte_young(pte))
+ orig_pte = pte_mkyoung(orig_pte);
+ }
+
+ if (valid) {
+ struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0);
+ flush_tlb_range(&vma, saddr, addr);
+ }
+ return orig_pte;
+}
+
+/*
+ * Changing some bits of contiguous entries requires us to follow a
+ * Break-Before-Make approach, breaking the whole contiguous set
+ * before we can change any entries. See ARM DDI 0487A.k_iss10775,
+ * "Misprogramming of the Contiguous bit", page D4-1762.
+ *
+ * This helper performs the break step for use cases where the
+ * original pte is not needed.
+ */
+static void clear_flush(struct mm_struct *mm,
+ unsigned long addr,
+ pte_t *ptep,
+ unsigned long pgsize,
+ unsigned long ncontig)
+{
+ struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0);
+ unsigned long i, saddr = addr;
+
+ for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
+ pte_clear(mm, addr, ptep);
+
+ flush_tlb_range(&vma, saddr, addr);
+}
+
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pte)
+{
+ size_t pgsize;
+ int i;
+ int ncontig;
+ unsigned long pfn, dpfn;
+ pgprot_t hugeprot;
+
+ /*
+ * Code needs to be expanded to handle huge swap and migration
+ * entries. Needed for HUGETLB and MEMORY_FAILURE.
+ */
+ WARN_ON(!pte_present(pte));
+
+ if (!pte_cont(pte)) {
+ set_pte_at(mm, addr, ptep, pte);
+ return;
+ }
+
+ ncontig = find_num_contig(mm, addr, ptep, &pgsize);
+ pfn = pte_pfn(pte);
+ dpfn = pgsize >> PAGE_SHIFT;
+ hugeprot = pte_pgprot(pte);
+
+ clear_flush(mm, addr, ptep, pgsize, ncontig);
+
+ for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
+ set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
+}
+
+void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pte, unsigned long sz)
+{
+ int i, ncontig;
+ size_t pgsize;
+
+ ncontig = num_contig_ptes(sz, &pgsize);
+
+ for (i = 0; i < ncontig; i++, ptep++)
+ set_pte(ptep, pte);
+}
+
+pte_t *huge_pte_alloc(struct mm_struct *mm,
+ unsigned long addr, unsigned long sz)
+{
+ pgd_t *pgdp;
+ pud_t *pudp;
+ pmd_t *pmdp;
+ pte_t *ptep = NULL;
+
+ pgdp = pgd_offset(mm, addr);
+ pudp = pud_alloc(mm, pgdp, addr);
+ if (!pudp)
+ return NULL;
+
+ if (sz == PUD_SIZE) {
+ ptep = (pte_t *)pudp;
+ } else if (sz == (PAGE_SIZE * CONT_PTES)) {
+ pmdp = pmd_alloc(mm, pudp, addr);
+ if (!pmdp)
+ return NULL;
+
+ WARN_ON(addr & (sz - 1));
+ /*
+ * Note that if this code were ever ported to the
+ * 32-bit arm platform then it will cause trouble in
+ * the case where CONFIG_HIGHPTE is set, since there
+ * will be no pte_unmap() to correspond with this
+ * pte_alloc_map().
+ */
+ ptep = pte_alloc_map(mm, pmdp, addr);
+ } else if (sz == PMD_SIZE) {
+ if (IS_ENABLED(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) &&
+ pud_none(READ_ONCE(*pudp)))
+ ptep = huge_pmd_share(mm, addr, pudp);
+ else
+ ptep = (pte_t *)pmd_alloc(mm, pudp, addr);
+ } else if (sz == (PMD_SIZE * CONT_PMDS)) {
+ pmdp = pmd_alloc(mm, pudp, addr);
+ WARN_ON(addr & (sz - 1));
+ return (pte_t *)pmdp;
+ }
+
+ return ptep;
+}
+
+pte_t *huge_pte_offset(struct mm_struct *mm,
+ unsigned long addr, unsigned long sz)
+{
+ pgd_t *pgdp;
+ pud_t *pudp, pud;
+ pmd_t *pmdp, pmd;
+
+ pgdp = pgd_offset(mm, addr);
+ if (!pgd_present(READ_ONCE(*pgdp)))
+ return NULL;
+
+ pudp = pud_offset(pgdp, addr);
+ pud = READ_ONCE(*pudp);
+ if (sz != PUD_SIZE && pud_none(pud))
+ return NULL;
+ /* hugepage or swap? */
+ if (pud_huge(pud) || !pud_present(pud))
+ return (pte_t *)pudp;
+ /* table; check the next level */
+
+ if (sz == CONT_PMD_SIZE)
+ addr &= CONT_PMD_MASK;
+
+ pmdp = pmd_offset(pudp, addr);
+ pmd = READ_ONCE(*pmdp);
+ if (!(sz == PMD_SIZE || sz == CONT_PMD_SIZE) &&
+ pmd_none(pmd))
+ return NULL;
+ if (pmd_huge(pmd) || !pmd_present(pmd))
+ return (pte_t *)pmdp;
+
+ if (sz == CONT_PTE_SIZE)
+ return pte_offset_kernel(pmdp, (addr & CONT_PTE_MASK));
+
+ return NULL;
+}
+
+pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
+ struct page *page, int writable)
+{
+ size_t pagesize = huge_page_size(hstate_vma(vma));
+
+ if (pagesize == CONT_PTE_SIZE) {
+ entry = pte_mkcont(entry);
+ } else if (pagesize == CONT_PMD_SIZE) {
+ entry = pmd_pte(pmd_mkcont(pte_pmd(entry)));
+ } else if (pagesize != PUD_SIZE && pagesize != PMD_SIZE) {
+ pr_warn("%s: unrecognized huge page size 0x%lx\n",
+ __func__, pagesize);
+ }
+ return entry;
+}
+
+void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, unsigned long sz)
+{
+ int i, ncontig;
+ size_t pgsize;
+
+ ncontig = num_contig_ptes(sz, &pgsize);
+
+ for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
+ pte_clear(mm, addr, ptep);
+}
+
+pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep)
+{
+ int ncontig;
+ size_t pgsize;
+ pte_t orig_pte = huge_ptep_get(ptep);
+
+ if (!pte_cont(orig_pte))
+ return ptep_get_and_clear(mm, addr, ptep);
+
+ ncontig = find_num_contig(mm, addr, ptep, &pgsize);
+
+ return get_clear_flush(mm, addr, ptep, pgsize, ncontig);
+}
+
+/*
+ * huge_ptep_set_access_flags will update access flags (dirty, accesssed)
+ * and write permission.
+ *
+ * For a contiguous huge pte range we need to check whether or not write
+ * permission has to change only on the first pte in the set. Then for
+ * all the contiguous ptes we need to check whether or not there is a
+ * discrepancy between dirty or young.
+ */
+static int __cont_access_flags_changed(pte_t *ptep, pte_t pte, int ncontig)
+{
+ int i;
+
+ if (pte_write(pte) != pte_write(huge_ptep_get(ptep)))
+ return 1;
+
+ for (i = 0; i < ncontig; i++) {
+ pte_t orig_pte = huge_ptep_get(ptep + i);
+
+ if (pte_dirty(pte) != pte_dirty(orig_pte))
+ return 1;
+
+ if (pte_young(pte) != pte_young(orig_pte))
+ return 1;
+ }
+
+ return 0;
+}
+
+int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep,
+ pte_t pte, int dirty)
+{
+ int ncontig, i;
+ size_t pgsize = 0;
+ unsigned long pfn = pte_pfn(pte), dpfn;
+ pgprot_t hugeprot;
+ pte_t orig_pte;
+
+ if (!pte_cont(pte))
+ return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
+
+ ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
+ dpfn = pgsize >> PAGE_SHIFT;
+
+ if (!__cont_access_flags_changed(ptep, pte, ncontig))
+ return 0;
+
+ orig_pte = get_clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
+
+ /* Make sure we don't lose the dirty or young state */
+ if (pte_dirty(orig_pte))
+ pte = pte_mkdirty(pte);
+
+ if (pte_young(orig_pte))
+ pte = pte_mkyoung(pte);
+
+ hugeprot = pte_pgprot(pte);
+ for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
+ set_pte_at(vma->vm_mm, addr, ptep, pfn_pte(pfn, hugeprot));
+
+ return 1;
+}
+
+void huge_ptep_set_wrprotect(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep)
+{
+ unsigned long pfn, dpfn;
+ pgprot_t hugeprot;
+ int ncontig, i;
+ size_t pgsize;
+ pte_t pte;
+
+ if (!pte_cont(READ_ONCE(*ptep))) {
+ ptep_set_wrprotect(mm, addr, ptep);
+ return;
+ }
+
+ ncontig = find_num_contig(mm, addr, ptep, &pgsize);
+ dpfn = pgsize >> PAGE_SHIFT;
+
+ pte = get_clear_flush(mm, addr, ptep, pgsize, ncontig);
+ pte = pte_wrprotect(pte);
+
+ hugeprot = pte_pgprot(pte);
+ pfn = pte_pfn(pte);
+
+ for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
+ set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
+}
+
+void huge_ptep_clear_flush(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep)
+{
+ size_t pgsize;
+ int ncontig;
+
+ if (!pte_cont(READ_ONCE(*ptep))) {
+ ptep_clear_flush(vma, addr, ptep);
+ return;
+ }
+
+ ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
+ clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
+}
+
+static __init int setup_hugepagesz(char *opt)
+{
+ unsigned long ps = memparse(opt, &opt);
+
+ switch (ps) {
+#ifdef CONFIG_ARM64_4K_PAGES
+ case PUD_SIZE:
+#endif
+ case PMD_SIZE * CONT_PMDS:
+ case PMD_SIZE:
+ case PAGE_SIZE * CONT_PTES:
+ hugetlb_add_hstate(ilog2(ps) - PAGE_SHIFT);
+ return 1;
+ }
+
+ hugetlb_bad_size();
+ pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10);
+ return 0;
+}
+__setup("hugepagesz=", setup_hugepagesz);
+
+#ifdef CONFIG_ARM64_64K_PAGES
+static __init int add_default_hugepagesz(void)
+{
+ if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL)
+ hugetlb_add_hstate(CONT_PTE_SHIFT);
+ return 0;
+}
+arch_initcall(add_default_hugepagesz);
+#endif
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
new file mode 100644
index 000000000..29d2f4258
--- /dev/null
+++ b/arch/arm64/mm/init.c
@@ -0,0 +1,694 @@
+/*
+ * Based on arch/arm/mm/init.c
+ *
+ * Copyright (C) 1995-2005 Russell King
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/errno.h>
+#include <linux/swap.h>
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/cache.h>
+#include <linux/mman.h>
+#include <linux/nodemask.h>
+#include <linux/initrd.h>
+#include <linux/gfp.h>
+#include <linux/memblock.h>
+#include <linux/sort.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/dma-mapping.h>
+#include <linux/dma-contiguous.h>
+#include <linux/efi.h>
+#include <linux/swiotlb.h>
+#include <linux/vmalloc.h>
+#include <linux/mm.h>
+#include <linux/kexec.h>
+#include <linux/crash_dump.h>
+
+#include <asm/boot.h>
+#include <asm/fixmap.h>
+#include <asm/kasan.h>
+#include <asm/kernel-pgtable.h>
+#include <asm/memory.h>
+#include <asm/numa.h>
+#include <asm/sections.h>
+#include <asm/setup.h>
+#include <asm/sizes.h>
+#include <asm/tlb.h>
+#include <asm/alternative.h>
+
+/*
+ * We need to be able to catch inadvertent references to memstart_addr
+ * that occur (potentially in generic code) before arm64_memblock_init()
+ * executes, which assigns it its actual value. So use a default value
+ * that cannot be mistaken for a real physical address.
+ */
+s64 memstart_addr __ro_after_init = -1;
+phys_addr_t arm64_dma_phys_limit __ro_after_init;
+
+#ifdef CONFIG_BLK_DEV_INITRD
+static int __init early_initrd(char *p)
+{
+ unsigned long start, size;
+ char *endp;
+
+ start = memparse(p, &endp);
+ if (*endp == ',') {
+ size = memparse(endp + 1, NULL);
+
+ initrd_start = start;
+ initrd_end = start + size;
+ }
+ return 0;
+}
+early_param("initrd", early_initrd);
+#endif
+
+#ifdef CONFIG_KEXEC_CORE
+/*
+ * reserve_crashkernel() - reserves memory for crash kernel
+ *
+ * This function reserves memory area given in "crashkernel=" kernel command
+ * line parameter. The memory reserved is used by dump capture kernel when
+ * primary kernel is crashing.
+ */
+static void __init reserve_crashkernel(void)
+{
+ unsigned long long crash_base, crash_size;
+ int ret;
+
+ ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
+ &crash_size, &crash_base);
+ /* no crashkernel= or invalid value specified */
+ if (ret || !crash_size)
+ return;
+
+ crash_size = PAGE_ALIGN(crash_size);
+
+ if (crash_base == 0) {
+ /* Current arm64 boot protocol requires 2MB alignment */
+ crash_base = memblock_find_in_range(0, ARCH_LOW_ADDRESS_LIMIT,
+ crash_size, SZ_2M);
+ if (crash_base == 0) {
+ pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
+ crash_size);
+ return;
+ }
+ } else {
+ /* User specifies base address explicitly. */
+ if (!memblock_is_region_memory(crash_base, crash_size)) {
+ pr_warn("cannot reserve crashkernel: region is not memory\n");
+ return;
+ }
+
+ if (memblock_is_region_reserved(crash_base, crash_size)) {
+ pr_warn("cannot reserve crashkernel: region overlaps reserved memory\n");
+ return;
+ }
+
+ if (!IS_ALIGNED(crash_base, SZ_2M)) {
+ pr_warn("cannot reserve crashkernel: base address is not 2MB aligned\n");
+ return;
+ }
+ }
+ memblock_reserve(crash_base, crash_size);
+
+ pr_info("crashkernel reserved: 0x%016llx - 0x%016llx (%lld MB)\n",
+ crash_base, crash_base + crash_size, crash_size >> 20);
+
+ crashk_res.start = crash_base;
+ crashk_res.end = crash_base + crash_size - 1;
+}
+
+static void __init kexec_reserve_crashkres_pages(void)
+{
+#ifdef CONFIG_HIBERNATION
+ phys_addr_t addr;
+ struct page *page;
+
+ if (!crashk_res.end)
+ return;
+
+ /*
+ * To reduce the size of hibernation image, all the pages are
+ * marked as Reserved initially.
+ */
+ for (addr = crashk_res.start; addr < (crashk_res.end + 1);
+ addr += PAGE_SIZE) {
+ page = phys_to_page(addr);
+ SetPageReserved(page);
+ }
+#endif
+}
+#else
+static void __init reserve_crashkernel(void)
+{
+}
+
+static void __init kexec_reserve_crashkres_pages(void)
+{
+}
+#endif /* CONFIG_KEXEC_CORE */
+
+#ifdef CONFIG_CRASH_DUMP
+static int __init early_init_dt_scan_elfcorehdr(unsigned long node,
+ const char *uname, int depth, void *data)
+{
+ const __be32 *reg;
+ int len;
+
+ if (depth != 1 || strcmp(uname, "chosen") != 0)
+ return 0;
+
+ reg = of_get_flat_dt_prop(node, "linux,elfcorehdr", &len);
+ if (!reg || (len < (dt_root_addr_cells + dt_root_size_cells)))
+ return 1;
+
+ elfcorehdr_addr = dt_mem_next_cell(dt_root_addr_cells, &reg);
+ elfcorehdr_size = dt_mem_next_cell(dt_root_size_cells, &reg);
+
+ return 1;
+}
+
+/*
+ * reserve_elfcorehdr() - reserves memory for elf core header
+ *
+ * This function reserves the memory occupied by an elf core header
+ * described in the device tree. This region contains all the
+ * information about primary kernel's core image and is used by a dump
+ * capture kernel to access the system memory on primary kernel.
+ */
+static void __init reserve_elfcorehdr(void)
+{
+ of_scan_flat_dt(early_init_dt_scan_elfcorehdr, NULL);
+
+ if (!elfcorehdr_size)
+ return;
+
+ if (memblock_is_region_reserved(elfcorehdr_addr, elfcorehdr_size)) {
+ pr_warn("elfcorehdr is overlapped\n");
+ return;
+ }
+
+ memblock_reserve(elfcorehdr_addr, elfcorehdr_size);
+
+ pr_info("Reserving %lldKB of memory at 0x%llx for elfcorehdr\n",
+ elfcorehdr_size >> 10, elfcorehdr_addr);
+}
+#else
+static void __init reserve_elfcorehdr(void)
+{
+}
+#endif /* CONFIG_CRASH_DUMP */
+/*
+ * Return the maximum physical address for ZONE_DMA32 (DMA_BIT_MASK(32)). It
+ * currently assumes that for memory starting above 4G, 32-bit devices will
+ * use a DMA offset.
+ */
+static phys_addr_t __init max_zone_dma_phys(void)
+{
+ phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, 32);
+ return min(offset + (1ULL << 32), memblock_end_of_DRAM());
+}
+
+#ifdef CONFIG_NUMA
+
+static void __init zone_sizes_init(unsigned long min, unsigned long max)
+{
+ unsigned long max_zone_pfns[MAX_NR_ZONES] = {0};
+
+#ifdef CONFIG_ZONE_DMA32
+ max_zone_pfns[ZONE_DMA32] = PFN_DOWN(max_zone_dma_phys());
+#endif
+ max_zone_pfns[ZONE_NORMAL] = max;
+
+ free_area_init_nodes(max_zone_pfns);
+}
+
+#else
+
+static void __init zone_sizes_init(unsigned long min, unsigned long max)
+{
+ struct memblock_region *reg;
+ unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES];
+ unsigned long max_dma = min;
+
+ memset(zone_size, 0, sizeof(zone_size));
+
+ /* 4GB maximum for 32-bit only capable devices */
+#ifdef CONFIG_ZONE_DMA32
+ max_dma = PFN_DOWN(arm64_dma_phys_limit);
+ zone_size[ZONE_DMA32] = max_dma - min;
+#endif
+ zone_size[ZONE_NORMAL] = max - max_dma;
+
+ memcpy(zhole_size, zone_size, sizeof(zhole_size));
+
+ for_each_memblock(memory, reg) {
+ unsigned long start = memblock_region_memory_base_pfn(reg);
+ unsigned long end = memblock_region_memory_end_pfn(reg);
+
+ if (start >= max)
+ continue;
+
+#ifdef CONFIG_ZONE_DMA32
+ if (start < max_dma) {
+ unsigned long dma_end = min(end, max_dma);
+ zhole_size[ZONE_DMA32] -= dma_end - start;
+ }
+#endif
+ if (end > max_dma) {
+ unsigned long normal_end = min(end, max);
+ unsigned long normal_start = max(start, max_dma);
+ zhole_size[ZONE_NORMAL] -= normal_end - normal_start;
+ }
+ }
+
+ free_area_init_node(0, zone_size, min, zhole_size);
+}
+
+#endif /* CONFIG_NUMA */
+
+#ifdef CONFIG_HAVE_ARCH_PFN_VALID
+int pfn_valid(unsigned long pfn)
+{
+ phys_addr_t addr = pfn << PAGE_SHIFT;
+
+ if ((addr >> PAGE_SHIFT) != pfn)
+ return 0;
+ return memblock_is_map_memory(addr);
+}
+EXPORT_SYMBOL(pfn_valid);
+#endif
+
+#ifndef CONFIG_SPARSEMEM
+static void __init arm64_memory_present(void)
+{
+}
+#else
+static void __init arm64_memory_present(void)
+{
+ struct memblock_region *reg;
+
+ for_each_memblock(memory, reg) {
+ int nid = memblock_get_region_node(reg);
+
+ memory_present(nid, memblock_region_memory_base_pfn(reg),
+ memblock_region_memory_end_pfn(reg));
+ }
+}
+#endif
+
+static phys_addr_t memory_limit = PHYS_ADDR_MAX;
+
+/*
+ * Limit the memory size that was specified via FDT.
+ */
+static int __init early_mem(char *p)
+{
+ if (!p)
+ return 1;
+
+ memory_limit = memparse(p, &p) & PAGE_MASK;
+ pr_notice("Memory limited to %lldMB\n", memory_limit >> 20);
+
+ return 0;
+}
+early_param("mem", early_mem);
+
+static int __init early_init_dt_scan_usablemem(unsigned long node,
+ const char *uname, int depth, void *data)
+{
+ struct memblock_region *usablemem = data;
+ const __be32 *reg;
+ int len;
+
+ if (depth != 1 || strcmp(uname, "chosen") != 0)
+ return 0;
+
+ reg = of_get_flat_dt_prop(node, "linux,usable-memory-range", &len);
+ if (!reg || (len < (dt_root_addr_cells + dt_root_size_cells)))
+ return 1;
+
+ usablemem->base = dt_mem_next_cell(dt_root_addr_cells, &reg);
+ usablemem->size = dt_mem_next_cell(dt_root_size_cells, &reg);
+
+ return 1;
+}
+
+static void __init fdt_enforce_memory_region(void)
+{
+ struct memblock_region reg = {
+ .size = 0,
+ };
+
+ of_scan_flat_dt(early_init_dt_scan_usablemem, &reg);
+
+ if (reg.size)
+ memblock_cap_memory_range(reg.base, reg.size);
+}
+
+void __init arm64_memblock_init(void)
+{
+ const s64 linear_region_size = -(s64)PAGE_OFFSET;
+
+ /* Handle linux,usable-memory-range property */
+ fdt_enforce_memory_region();
+
+ /* Remove memory above our supported physical address size */
+ memblock_remove(1ULL << PHYS_MASK_SHIFT, ULLONG_MAX);
+
+ /*
+ * Ensure that the linear region takes up exactly half of the kernel
+ * virtual address space. This way, we can distinguish a linear address
+ * from a kernel/module/vmalloc address by testing a single bit.
+ */
+ BUILD_BUG_ON(linear_region_size != BIT(VA_BITS - 1));
+
+ /*
+ * Select a suitable value for the base of physical memory.
+ */
+ memstart_addr = round_down(memblock_start_of_DRAM(),
+ ARM64_MEMSTART_ALIGN);
+
+ /*
+ * Remove the memory that we will not be able to cover with the
+ * linear mapping. Take care not to clip the kernel which may be
+ * high in memory.
+ */
+ memblock_remove(max_t(u64, memstart_addr + linear_region_size,
+ __pa_symbol(_end)), ULLONG_MAX);
+ if (memstart_addr + linear_region_size < memblock_end_of_DRAM()) {
+ /* ensure that memstart_addr remains sufficiently aligned */
+ memstart_addr = round_up(memblock_end_of_DRAM() - linear_region_size,
+ ARM64_MEMSTART_ALIGN);
+ memblock_remove(0, memstart_addr);
+ }
+
+ /*
+ * Apply the memory limit if it was set. Since the kernel may be loaded
+ * high up in memory, add back the kernel region that must be accessible
+ * via the linear mapping.
+ */
+ if (memory_limit != PHYS_ADDR_MAX) {
+ memblock_mem_limit_remove_map(memory_limit);
+ memblock_add(__pa_symbol(_text), (u64)(_end - _text));
+ }
+
+ if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && initrd_start) {
+ /*
+ * Add back the memory we just removed if it results in the
+ * initrd to become inaccessible via the linear mapping.
+ * Otherwise, this is a no-op
+ */
+ u64 base = initrd_start & PAGE_MASK;
+ u64 size = PAGE_ALIGN(initrd_end) - base;
+
+ /*
+ * We can only add back the initrd memory if we don't end up
+ * with more memory than we can address via the linear mapping.
+ * It is up to the bootloader to position the kernel and the
+ * initrd reasonably close to each other (i.e., within 32 GB of
+ * each other) so that all granule/#levels combinations can
+ * always access both.
+ */
+ if (WARN(base < memblock_start_of_DRAM() ||
+ base + size > memblock_start_of_DRAM() +
+ linear_region_size,
+ "initrd not fully accessible via the linear mapping -- please check your bootloader ...\n")) {
+ initrd_start = 0;
+ } else {
+ memblock_remove(base, size); /* clear MEMBLOCK_ flags */
+ memblock_add(base, size);
+ memblock_reserve(base, size);
+ }
+ }
+
+ if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
+ extern u16 memstart_offset_seed;
+ u64 range = linear_region_size -
+ (memblock_end_of_DRAM() - memblock_start_of_DRAM());
+
+ /*
+ * If the size of the linear region exceeds, by a sufficient
+ * margin, the size of the region that the available physical
+ * memory spans, randomize the linear region as well.
+ */
+ if (memstart_offset_seed > 0 && range >= ARM64_MEMSTART_ALIGN) {
+ range /= ARM64_MEMSTART_ALIGN;
+ memstart_addr -= ARM64_MEMSTART_ALIGN *
+ ((range * memstart_offset_seed) >> 16);
+ }
+ }
+
+ /*
+ * Register the kernel text, kernel data, initrd, and initial
+ * pagetables with memblock.
+ */
+ memblock_reserve(__pa_symbol(_text), _end - _text);
+#ifdef CONFIG_BLK_DEV_INITRD
+ if (initrd_start) {
+ memblock_reserve(initrd_start, initrd_end - initrd_start);
+
+ /* the generic initrd code expects virtual addresses */
+ initrd_start = __phys_to_virt(initrd_start);
+ initrd_end = __phys_to_virt(initrd_end);
+ }
+#endif
+
+ early_init_fdt_scan_reserved_mem();
+
+ /* 4GB maximum for 32-bit only capable devices */
+ if (IS_ENABLED(CONFIG_ZONE_DMA32))
+ arm64_dma_phys_limit = max_zone_dma_phys();
+ else
+ arm64_dma_phys_limit = PHYS_MASK + 1;
+
+ reserve_crashkernel();
+
+ reserve_elfcorehdr();
+
+ high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
+
+ dma_contiguous_reserve(arm64_dma_phys_limit);
+
+ memblock_allow_resize();
+}
+
+void __init bootmem_init(void)
+{
+ unsigned long min, max;
+
+ min = PFN_UP(memblock_start_of_DRAM());
+ max = PFN_DOWN(memblock_end_of_DRAM());
+
+ early_memtest(min << PAGE_SHIFT, max << PAGE_SHIFT);
+
+ max_pfn = max_low_pfn = max;
+
+ arm64_numa_init();
+ /*
+ * Sparsemem tries to allocate bootmem in memory_present(), so must be
+ * done after the fixed reservations.
+ */
+ arm64_memory_present();
+
+ sparse_init();
+ zone_sizes_init(min, max);
+
+ memblock_dump_all();
+}
+
+#ifndef CONFIG_SPARSEMEM_VMEMMAP
+static inline void free_memmap(unsigned long start_pfn, unsigned long end_pfn)
+{
+ struct page *start_pg, *end_pg;
+ unsigned long pg, pgend;
+
+ /*
+ * Convert start_pfn/end_pfn to a struct page pointer.
+ */
+ start_pg = pfn_to_page(start_pfn - 1) + 1;
+ end_pg = pfn_to_page(end_pfn - 1) + 1;
+
+ /*
+ * Convert to physical addresses, and round start upwards and end
+ * downwards.
+ */
+ pg = (unsigned long)PAGE_ALIGN(__pa(start_pg));
+ pgend = (unsigned long)__pa(end_pg) & PAGE_MASK;
+
+ /*
+ * If there are free pages between these, free the section of the
+ * memmap array.
+ */
+ if (pg < pgend)
+ free_bootmem(pg, pgend - pg);
+}
+
+/*
+ * The mem_map array can get very big. Free the unused area of the memory map.
+ */
+static void __init free_unused_memmap(void)
+{
+ unsigned long start, prev_end = 0;
+ struct memblock_region *reg;
+
+ for_each_memblock(memory, reg) {
+ start = __phys_to_pfn(reg->base);
+
+#ifdef CONFIG_SPARSEMEM
+ /*
+ * Take care not to free memmap entries that don't exist due
+ * to SPARSEMEM sections which aren't present.
+ */
+ start = min(start, ALIGN(prev_end, PAGES_PER_SECTION));
+#endif
+ /*
+ * If we had a previous bank, and there is a space between the
+ * current bank and the previous, free it.
+ */
+ if (prev_end && prev_end < start)
+ free_memmap(prev_end, start);
+
+ /*
+ * Align up here since the VM subsystem insists that the
+ * memmap entries are valid from the bank end aligned to
+ * MAX_ORDER_NR_PAGES.
+ */
+ prev_end = ALIGN(__phys_to_pfn(reg->base + reg->size),
+ MAX_ORDER_NR_PAGES);
+ }
+
+#ifdef CONFIG_SPARSEMEM
+ if (!IS_ALIGNED(prev_end, PAGES_PER_SECTION))
+ free_memmap(prev_end, ALIGN(prev_end, PAGES_PER_SECTION));
+#endif
+}
+#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
+
+/*
+ * mem_init() marks the free areas in the mem_map and tells us how much memory
+ * is free. This is done after various parts of the system have claimed their
+ * memory after the kernel image.
+ */
+void __init mem_init(void)
+{
+ if (swiotlb_force == SWIOTLB_FORCE ||
+ max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT))
+ swiotlb_init(1);
+ else
+ swiotlb_force = SWIOTLB_NO_FORCE;
+
+ set_max_mapnr(pfn_to_page(max_pfn) - mem_map);
+
+#ifndef CONFIG_SPARSEMEM_VMEMMAP
+ free_unused_memmap();
+#endif
+ /* this will put all unused low memory onto the freelists */
+ free_all_bootmem();
+
+ kexec_reserve_crashkres_pages();
+
+ mem_init_print_info(NULL);
+
+ /*
+ * Check boundaries twice: Some fundamental inconsistencies can be
+ * detected at build time already.
+ */
+#ifdef CONFIG_COMPAT
+ BUILD_BUG_ON(TASK_SIZE_32 > TASK_SIZE_64);
+#endif
+
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+ /*
+ * Make sure we chose the upper bound of sizeof(struct page)
+ * correctly when sizing the VMEMMAP array.
+ */
+ BUILD_BUG_ON(sizeof(struct page) > (1 << STRUCT_PAGE_MAX_SHIFT));
+#endif
+
+ if (PAGE_SIZE >= 16384 && get_num_physpages() <= 128) {
+ extern int sysctl_overcommit_memory;
+ /*
+ * On a machine this small we won't get anywhere without
+ * overcommit, so turn it on by default.
+ */
+ sysctl_overcommit_memory = OVERCOMMIT_ALWAYS;
+ }
+}
+
+void free_initmem(void)
+{
+ free_reserved_area(lm_alias(__init_begin),
+ lm_alias(__init_end),
+ 0, "unused kernel");
+ /*
+ * Unmap the __init region but leave the VM area in place. This
+ * prevents the region from being reused for kernel modules, which
+ * is not supported by kallsyms.
+ */
+ unmap_kernel_range((u64)__init_begin, (u64)(__init_end - __init_begin));
+}
+
+#ifdef CONFIG_BLK_DEV_INITRD
+
+static int keep_initrd __initdata;
+
+void __init free_initrd_mem(unsigned long start, unsigned long end)
+{
+ if (!keep_initrd) {
+ free_reserved_area((void *)start, (void *)end, 0, "initrd");
+ memblock_free(__virt_to_phys(start), end - start);
+ }
+}
+
+static int __init keepinitrd_setup(char *__unused)
+{
+ keep_initrd = 1;
+ return 1;
+}
+
+__setup("keepinitrd", keepinitrd_setup);
+#endif
+
+/*
+ * Dump out memory limit information on panic.
+ */
+static int dump_mem_limit(struct notifier_block *self, unsigned long v, void *p)
+{
+ if (memory_limit != PHYS_ADDR_MAX) {
+ pr_emerg("Memory Limit: %llu MB\n", memory_limit >> 20);
+ } else {
+ pr_emerg("Memory Limit: none\n");
+ }
+ return 0;
+}
+
+static struct notifier_block mem_limit_notifier = {
+ .notifier_call = dump_mem_limit,
+};
+
+static int __init register_mem_limit_dumper(void)
+{
+ atomic_notifier_chain_register(&panic_notifier_list,
+ &mem_limit_notifier);
+ return 0;
+}
+__initcall(register_mem_limit_dumper);
diff --git a/arch/arm64/mm/ioremap.c b/arch/arm64/mm/ioremap.c
new file mode 100644
index 000000000..c4c8cd4c3
--- /dev/null
+++ b/arch/arm64/mm/ioremap.c
@@ -0,0 +1,113 @@
+/*
+ * Based on arch/arm/mm/ioremap.c
+ *
+ * (C) Copyright 1995 1996 Linus Torvalds
+ * Hacked for ARM by Phil Blundell <philb@gnu.org>
+ * Hacked to allow all architectures to build, and various cleanups
+ * by Russell King
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
+#include <linux/io.h>
+
+#include <asm/fixmap.h>
+#include <asm/tlbflush.h>
+#include <asm/pgalloc.h>
+
+static void __iomem *__ioremap_caller(phys_addr_t phys_addr, size_t size,
+ pgprot_t prot, void *caller)
+{
+ unsigned long last_addr;
+ unsigned long offset = phys_addr & ~PAGE_MASK;
+ int err;
+ unsigned long addr;
+ struct vm_struct *area;
+
+ /*
+ * Page align the mapping address and size, taking account of any
+ * offset.
+ */
+ phys_addr &= PAGE_MASK;
+ size = PAGE_ALIGN(size + offset);
+
+ /*
+ * Don't allow wraparound, zero size or outside PHYS_MASK.
+ */
+ last_addr = phys_addr + size - 1;
+ if (!size || last_addr < phys_addr || (last_addr & ~PHYS_MASK))
+ return NULL;
+
+ /*
+ * Don't allow RAM to be mapped.
+ */
+ if (WARN_ON(pfn_valid(__phys_to_pfn(phys_addr))))
+ return NULL;
+
+ area = get_vm_area_caller(size, VM_IOREMAP, caller);
+ if (!area)
+ return NULL;
+ addr = (unsigned long)area->addr;
+ area->phys_addr = phys_addr;
+
+ err = ioremap_page_range(addr, addr + size, phys_addr, prot);
+ if (err) {
+ vunmap((void *)addr);
+ return NULL;
+ }
+
+ return (void __iomem *)(offset + addr);
+}
+
+void __iomem *__ioremap(phys_addr_t phys_addr, size_t size, pgprot_t prot)
+{
+ return __ioremap_caller(phys_addr, size, prot,
+ __builtin_return_address(0));
+}
+EXPORT_SYMBOL(__ioremap);
+
+void __iounmap(volatile void __iomem *io_addr)
+{
+ unsigned long addr = (unsigned long)io_addr & PAGE_MASK;
+
+ /*
+ * We could get an address outside vmalloc range in case
+ * of ioremap_cache() reusing a RAM mapping.
+ */
+ if (is_vmalloc_addr((void *)addr))
+ vunmap((void *)addr);
+}
+EXPORT_SYMBOL(__iounmap);
+
+void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size)
+{
+ /* For normal memory we already have a cacheable mapping. */
+ if (pfn_valid(__phys_to_pfn(phys_addr)))
+ return (void __iomem *)__phys_to_virt(phys_addr);
+
+ return __ioremap_caller(phys_addr, size, __pgprot(PROT_NORMAL),
+ __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_cache);
+
+/*
+ * Must be called after early_fixmap_init
+ */
+void __init early_ioremap_init(void)
+{
+ early_ioremap_setup();
+}
diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
new file mode 100644
index 000000000..12145874c
--- /dev/null
+++ b/arch/arm64/mm/kasan_init.c
@@ -0,0 +1,244 @@
+/*
+ * This file contains kasan initialization code for ARM64.
+ *
+ * Copyright (c) 2015 Samsung Electronics Co., Ltd.
+ * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com>
+ *
+ * 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) "kasan: " fmt
+#include <linux/bootmem.h>
+#include <linux/kasan.h>
+#include <linux/kernel.h>
+#include <linux/sched/task.h>
+#include <linux/memblock.h>
+#include <linux/start_kernel.h>
+#include <linux/mm.h>
+
+#include <asm/mmu_context.h>
+#include <asm/kernel-pgtable.h>
+#include <asm/page.h>
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+#include <asm/sections.h>
+#include <asm/tlbflush.h>
+
+static pgd_t tmp_pg_dir[PTRS_PER_PGD] __initdata __aligned(PGD_SIZE);
+
+/*
+ * The p*d_populate functions call virt_to_phys implicitly so they can't be used
+ * directly on kernel symbols (bm_p*d). All the early functions are called too
+ * early to use lm_alias so __p*d_populate functions must be used to populate
+ * with the physical address from __pa_symbol.
+ */
+
+static phys_addr_t __init kasan_alloc_zeroed_page(int node)
+{
+ void *p = memblock_virt_alloc_try_nid(PAGE_SIZE, PAGE_SIZE,
+ __pa(MAX_DMA_ADDRESS),
+ MEMBLOCK_ALLOC_ACCESSIBLE, node);
+ return __pa(p);
+}
+
+static pte_t *__init kasan_pte_offset(pmd_t *pmdp, unsigned long addr, int node,
+ bool early)
+{
+ if (pmd_none(READ_ONCE(*pmdp))) {
+ phys_addr_t pte_phys = early ? __pa_symbol(kasan_zero_pte)
+ : kasan_alloc_zeroed_page(node);
+ __pmd_populate(pmdp, pte_phys, PMD_TYPE_TABLE);
+ }
+
+ return early ? pte_offset_kimg(pmdp, addr)
+ : pte_offset_kernel(pmdp, addr);
+}
+
+static pmd_t *__init kasan_pmd_offset(pud_t *pudp, unsigned long addr, int node,
+ bool early)
+{
+ if (pud_none(READ_ONCE(*pudp))) {
+ phys_addr_t pmd_phys = early ? __pa_symbol(kasan_zero_pmd)
+ : kasan_alloc_zeroed_page(node);
+ __pud_populate(pudp, pmd_phys, PMD_TYPE_TABLE);
+ }
+
+ return early ? pmd_offset_kimg(pudp, addr) : pmd_offset(pudp, addr);
+}
+
+static pud_t *__init kasan_pud_offset(pgd_t *pgdp, unsigned long addr, int node,
+ bool early)
+{
+ if (pgd_none(READ_ONCE(*pgdp))) {
+ phys_addr_t pud_phys = early ? __pa_symbol(kasan_zero_pud)
+ : kasan_alloc_zeroed_page(node);
+ __pgd_populate(pgdp, pud_phys, PMD_TYPE_TABLE);
+ }
+
+ return early ? pud_offset_kimg(pgdp, addr) : pud_offset(pgdp, addr);
+}
+
+static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr,
+ unsigned long end, int node, bool early)
+{
+ unsigned long next;
+ pte_t *ptep = kasan_pte_offset(pmdp, addr, node, early);
+
+ do {
+ phys_addr_t page_phys = early ? __pa_symbol(kasan_zero_page)
+ : kasan_alloc_zeroed_page(node);
+ next = addr + PAGE_SIZE;
+ set_pte(ptep, pfn_pte(__phys_to_pfn(page_phys), PAGE_KERNEL));
+ } while (ptep++, addr = next, addr != end && pte_none(READ_ONCE(*ptep)));
+}
+
+static void __init kasan_pmd_populate(pud_t *pudp, unsigned long addr,
+ unsigned long end, int node, bool early)
+{
+ unsigned long next;
+ pmd_t *pmdp = kasan_pmd_offset(pudp, addr, node, early);
+
+ do {
+ next = pmd_addr_end(addr, end);
+ kasan_pte_populate(pmdp, addr, next, node, early);
+ } while (pmdp++, addr = next, addr != end && pmd_none(READ_ONCE(*pmdp)));
+}
+
+static void __init kasan_pud_populate(pgd_t *pgdp, unsigned long addr,
+ unsigned long end, int node, bool early)
+{
+ unsigned long next;
+ pud_t *pudp = kasan_pud_offset(pgdp, addr, node, early);
+
+ do {
+ next = pud_addr_end(addr, end);
+ kasan_pmd_populate(pudp, addr, next, node, early);
+ } while (pudp++, addr = next, addr != end && pud_none(READ_ONCE(*pudp)));
+}
+
+static void __init kasan_pgd_populate(unsigned long addr, unsigned long end,
+ int node, bool early)
+{
+ unsigned long next;
+ pgd_t *pgdp;
+
+ pgdp = pgd_offset_k(addr);
+ do {
+ next = pgd_addr_end(addr, end);
+ kasan_pud_populate(pgdp, addr, next, node, early);
+ } while (pgdp++, addr = next, addr != end);
+}
+
+/* The early shadow maps everything to a single page of zeroes */
+asmlinkage void __init kasan_early_init(void)
+{
+ BUILD_BUG_ON(KASAN_SHADOW_OFFSET !=
+ KASAN_SHADOW_END - (1UL << (64 - KASAN_SHADOW_SCALE_SHIFT)));
+ BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_START, PGDIR_SIZE));
+ BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, PGDIR_SIZE));
+ kasan_pgd_populate(KASAN_SHADOW_START, KASAN_SHADOW_END, NUMA_NO_NODE,
+ true);
+}
+
+/* Set up full kasan mappings, ensuring that the mapped pages are zeroed */
+static void __init kasan_map_populate(unsigned long start, unsigned long end,
+ int node)
+{
+ kasan_pgd_populate(start & PAGE_MASK, PAGE_ALIGN(end), node, false);
+}
+
+/*
+ * Copy the current shadow region into a new pgdir.
+ */
+void __init kasan_copy_shadow(pgd_t *pgdir)
+{
+ pgd_t *pgdp, *pgdp_new, *pgdp_end;
+
+ pgdp = pgd_offset_k(KASAN_SHADOW_START);
+ pgdp_end = pgd_offset_k(KASAN_SHADOW_END);
+ pgdp_new = pgd_offset_raw(pgdir, KASAN_SHADOW_START);
+ do {
+ set_pgd(pgdp_new, READ_ONCE(*pgdp));
+ } while (pgdp++, pgdp_new++, pgdp != pgdp_end);
+}
+
+static void __init clear_pgds(unsigned long start,
+ unsigned long end)
+{
+ /*
+ * Remove references to kasan page tables from
+ * swapper_pg_dir. pgd_clear() can't be used
+ * here because it's nop on 2,3-level pagetable setups
+ */
+ for (; start < end; start += PGDIR_SIZE)
+ set_pgd(pgd_offset_k(start), __pgd(0));
+}
+
+void __init kasan_init(void)
+{
+ u64 kimg_shadow_start, kimg_shadow_end;
+ u64 mod_shadow_start, mod_shadow_end;
+ struct memblock_region *reg;
+ int i;
+
+ kimg_shadow_start = (u64)kasan_mem_to_shadow(_text) & PAGE_MASK;
+ kimg_shadow_end = PAGE_ALIGN((u64)kasan_mem_to_shadow(_end));
+
+ mod_shadow_start = (u64)kasan_mem_to_shadow((void *)MODULES_VADDR);
+ mod_shadow_end = (u64)kasan_mem_to_shadow((void *)MODULES_END);
+
+ /*
+ * We are going to perform proper setup of shadow memory.
+ * At first we should unmap early shadow (clear_pgds() call bellow).
+ * However, instrumented code couldn't execute without shadow memory.
+ * tmp_pg_dir used to keep early shadow mapped until full shadow
+ * setup will be finished.
+ */
+ memcpy(tmp_pg_dir, swapper_pg_dir, sizeof(tmp_pg_dir));
+ dsb(ishst);
+ cpu_replace_ttbr1(lm_alias(tmp_pg_dir));
+
+ clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END);
+
+ kasan_map_populate(kimg_shadow_start, kimg_shadow_end,
+ early_pfn_to_nid(virt_to_pfn(lm_alias(_text))));
+
+ kasan_populate_zero_shadow((void *)KASAN_SHADOW_START,
+ (void *)mod_shadow_start);
+ kasan_populate_zero_shadow((void *)kimg_shadow_end,
+ kasan_mem_to_shadow((void *)PAGE_OFFSET));
+
+ if (kimg_shadow_start > mod_shadow_end)
+ kasan_populate_zero_shadow((void *)mod_shadow_end,
+ (void *)kimg_shadow_start);
+
+ for_each_memblock(memory, reg) {
+ void *start = (void *)__phys_to_virt(reg->base);
+ void *end = (void *)__phys_to_virt(reg->base + reg->size);
+
+ if (start >= end)
+ break;
+
+ kasan_map_populate((unsigned long)kasan_mem_to_shadow(start),
+ (unsigned long)kasan_mem_to_shadow(end),
+ early_pfn_to_nid(virt_to_pfn(start)));
+ }
+
+ /*
+ * KAsan may reuse the contents of kasan_zero_pte directly, so we
+ * should make sure that it maps the zero page read-only.
+ */
+ for (i = 0; i < PTRS_PER_PTE; i++)
+ set_pte(&kasan_zero_pte[i],
+ pfn_pte(sym_to_pfn(kasan_zero_page), PAGE_KERNEL_RO));
+
+ memset(kasan_zero_page, 0, PAGE_SIZE);
+ cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
+
+ /* At this point kasan is fully initialized. Enable error messages */
+ init_task.kasan_depth = 0;
+ pr_info("KernelAddressSanitizer initialized\n");
+}
diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c
new file mode 100644
index 000000000..157f2caa1
--- /dev/null
+++ b/arch/arm64/mm/mmap.c
@@ -0,0 +1,157 @@
+/*
+ * Based on arch/arm/mm/mmap.c
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/elf.h>
+#include <linux/fs.h>
+#include <linux/memblock.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/export.h>
+#include <linux/shm.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/mm.h>
+#include <linux/io.h>
+#include <linux/personality.h>
+#include <linux/random.h>
+
+#include <asm/cputype.h>
+
+/*
+ * 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 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;
+}
+
+unsigned long arch_mmap_rnd(void)
+{
+ unsigned long rnd;
+
+#ifdef CONFIG_COMPAT
+ if (test_thread_flag(TIF_32BIT))
+ rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1);
+ else
+#endif
+ rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
+ return rnd << PAGE_SHIFT;
+}
+
+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);
+}
+
+/*
+ * This function, called very early during the creation of a new process VM
+ * image, sets up which VM layout function to use:
+ */
+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();
+
+ /*
+ * Fall back to the standard layout if the personality bit is set, or
+ * if the expected stack growth is unlimited:
+ */
+ 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;
+ }
+}
+
+/*
+ * You really shouldn't be using read() or write() on /dev/mem. This might go
+ * away in the future.
+ */
+int valid_phys_addr_range(phys_addr_t addr, size_t size)
+{
+ /*
+ * Check whether addr is covered by a memory region without the
+ * MEMBLOCK_NOMAP attribute, and whether that region covers the
+ * entire range. In theory, this could lead to false negatives
+ * if the range is covered by distinct but adjacent memory regions
+ * that only differ in other attributes. However, few of such
+ * attributes have been defined, and it is debatable whether it
+ * follows that /dev/mem read() calls should be able traverse
+ * such boundaries.
+ */
+ return memblock_is_region_memory(addr, size) &&
+ memblock_is_map_memory(addr);
+}
+
+/*
+ * Do not allow /dev/mem mappings beyond the supported physical range.
+ */
+int valid_mmap_phys_addr_range(unsigned long pfn, size_t size)
+{
+ return !(((pfn << PAGE_SHIFT) + size) & ~PHYS_MASK);
+}
+
+#ifdef CONFIG_STRICT_DEVMEM
+
+#include <linux/ioport.h>
+
+/*
+ * devmem_is_allowed() checks to see if /dev/mem access to a certain address
+ * is valid. The argument is a physical page number. We mimic x86 here by
+ * disallowing access to system RAM as well as device-exclusive MMIO regions.
+ * This effectively disable read()/write() on /dev/mem.
+ */
+int devmem_is_allowed(unsigned long pfn)
+{
+ if (iomem_is_exclusive(pfn << PAGE_SHIFT))
+ return 0;
+ if (!page_is_ram(pfn))
+ return 1;
+ return 0;
+}
+
+#endif
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
new file mode 100644
index 000000000..b0a83dbed
--- /dev/null
+++ b/arch/arm64/mm/mmu.c
@@ -0,0 +1,1041 @@
+/*
+ * Based on arch/arm/mm/mmu.c
+ *
+ * Copyright (C) 1995-2005 Russell King
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/cache.h>
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/ioport.h>
+#include <linux/kexec.h>
+#include <linux/libfdt.h>
+#include <linux/mman.h>
+#include <linux/nodemask.h>
+#include <linux/memblock.h>
+#include <linux/fs.h>
+#include <linux/io.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
+
+#include <asm/barrier.h>
+#include <asm/cputype.h>
+#include <asm/fixmap.h>
+#include <asm/kasan.h>
+#include <asm/kernel-pgtable.h>
+#include <asm/sections.h>
+#include <asm/setup.h>
+#include <asm/sizes.h>
+#include <asm/tlb.h>
+#include <asm/memblock.h>
+#include <asm/mmu_context.h>
+#include <asm/ptdump.h>
+#include <asm/tlbflush.h>
+
+#define NO_BLOCK_MAPPINGS BIT(0)
+#define NO_CONT_MAPPINGS BIT(1)
+
+u64 idmap_t0sz = TCR_T0SZ(VA_BITS);
+u64 idmap_ptrs_per_pgd = PTRS_PER_PGD;
+
+u64 kimage_voffset __ro_after_init;
+EXPORT_SYMBOL(kimage_voffset);
+
+/*
+ * Empty_zero_page is a special page that is used for zero-initialized data
+ * and COW.
+ */
+unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss;
+EXPORT_SYMBOL(empty_zero_page);
+
+static pte_t bm_pte[PTRS_PER_PTE] __page_aligned_bss;
+static pmd_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss __maybe_unused;
+static pud_t bm_pud[PTRS_PER_PUD] __page_aligned_bss __maybe_unused;
+
+pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+ unsigned long size, pgprot_t vma_prot)
+{
+ if (!pfn_valid(pfn))
+ return pgprot_noncached(vma_prot);
+ else if (file->f_flags & O_SYNC)
+ return pgprot_writecombine(vma_prot);
+ return vma_prot;
+}
+EXPORT_SYMBOL(phys_mem_access_prot);
+
+static phys_addr_t __init early_pgtable_alloc(void)
+{
+ phys_addr_t phys;
+ void *ptr;
+
+ phys = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+
+ /*
+ * The FIX_{PGD,PUD,PMD} slots may be in active use, but the FIX_PTE
+ * slot will be free, so we can (ab)use the FIX_PTE slot to initialise
+ * any level of table.
+ */
+ ptr = pte_set_fixmap(phys);
+
+ memset(ptr, 0, PAGE_SIZE);
+
+ /*
+ * Implicit barriers also ensure the zeroed page is visible to the page
+ * table walker
+ */
+ pte_clear_fixmap();
+
+ return phys;
+}
+
+static bool pgattr_change_is_safe(u64 old, u64 new)
+{
+ /*
+ * The following mapping attributes may be updated in live
+ * kernel mappings without the need for break-before-make.
+ */
+ static const pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE | PTE_NG;
+
+ /* creating or taking down mappings is always safe */
+ if (old == 0 || new == 0)
+ return true;
+
+ /* live contiguous mappings may not be manipulated at all */
+ if ((old | new) & PTE_CONT)
+ return false;
+
+ /* Transitioning from Non-Global to Global is unsafe */
+ if (old & ~new & PTE_NG)
+ return false;
+
+ return ((old ^ new) & ~mask) == 0;
+}
+
+static void init_pte(pmd_t *pmdp, unsigned long addr, unsigned long end,
+ phys_addr_t phys, pgprot_t prot)
+{
+ pte_t *ptep;
+
+ ptep = pte_set_fixmap_offset(pmdp, addr);
+ do {
+ pte_t old_pte = READ_ONCE(*ptep);
+
+ set_pte(ptep, pfn_pte(__phys_to_pfn(phys), prot));
+
+ /*
+ * After the PTE entry has been populated once, we
+ * only allow updates to the permission attributes.
+ */
+ BUG_ON(!pgattr_change_is_safe(pte_val(old_pte),
+ READ_ONCE(pte_val(*ptep))));
+
+ phys += PAGE_SIZE;
+ } while (ptep++, addr += PAGE_SIZE, addr != end);
+
+ pte_clear_fixmap();
+}
+
+static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
+ unsigned long end, phys_addr_t phys,
+ pgprot_t prot,
+ phys_addr_t (*pgtable_alloc)(void),
+ int flags)
+{
+ unsigned long next;
+ pmd_t pmd = READ_ONCE(*pmdp);
+
+ BUG_ON(pmd_sect(pmd));
+ if (pmd_none(pmd)) {
+ phys_addr_t pte_phys;
+ BUG_ON(!pgtable_alloc);
+ pte_phys = pgtable_alloc();
+ __pmd_populate(pmdp, pte_phys, PMD_TYPE_TABLE);
+ pmd = READ_ONCE(*pmdp);
+ }
+ BUG_ON(pmd_bad(pmd));
+
+ do {
+ pgprot_t __prot = prot;
+
+ next = pte_cont_addr_end(addr, end);
+
+ /* use a contiguous mapping if the range is suitably aligned */
+ if ((((addr | next | phys) & ~CONT_PTE_MASK) == 0) &&
+ (flags & NO_CONT_MAPPINGS) == 0)
+ __prot = __pgprot(pgprot_val(prot) | PTE_CONT);
+
+ init_pte(pmdp, addr, next, phys, __prot);
+
+ phys += next - addr;
+ } while (addr = next, addr != end);
+}
+
+static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end,
+ phys_addr_t phys, pgprot_t prot,
+ phys_addr_t (*pgtable_alloc)(void), int flags)
+{
+ unsigned long next;
+ pmd_t *pmdp;
+
+ pmdp = pmd_set_fixmap_offset(pudp, addr);
+ do {
+ pmd_t old_pmd = READ_ONCE(*pmdp);
+
+ next = pmd_addr_end(addr, end);
+
+ /* try section mapping first */
+ if (((addr | next | phys) & ~SECTION_MASK) == 0 &&
+ (flags & NO_BLOCK_MAPPINGS) == 0) {
+ pmd_set_huge(pmdp, phys, prot);
+
+ /*
+ * After the PMD entry has been populated once, we
+ * only allow updates to the permission attributes.
+ */
+ BUG_ON(!pgattr_change_is_safe(pmd_val(old_pmd),
+ READ_ONCE(pmd_val(*pmdp))));
+ } else {
+ alloc_init_cont_pte(pmdp, addr, next, phys, prot,
+ pgtable_alloc, flags);
+
+ BUG_ON(pmd_val(old_pmd) != 0 &&
+ pmd_val(old_pmd) != READ_ONCE(pmd_val(*pmdp)));
+ }
+ phys += next - addr;
+ } while (pmdp++, addr = next, addr != end);
+
+ pmd_clear_fixmap();
+}
+
+static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
+ unsigned long end, phys_addr_t phys,
+ pgprot_t prot,
+ phys_addr_t (*pgtable_alloc)(void), int flags)
+{
+ unsigned long next;
+ pud_t pud = READ_ONCE(*pudp);
+
+ /*
+ * Check for initial section mappings in the pgd/pud.
+ */
+ BUG_ON(pud_sect(pud));
+ if (pud_none(pud)) {
+ phys_addr_t pmd_phys;
+ BUG_ON(!pgtable_alloc);
+ pmd_phys = pgtable_alloc();
+ __pud_populate(pudp, pmd_phys, PUD_TYPE_TABLE);
+ pud = READ_ONCE(*pudp);
+ }
+ BUG_ON(pud_bad(pud));
+
+ do {
+ pgprot_t __prot = prot;
+
+ next = pmd_cont_addr_end(addr, end);
+
+ /* use a contiguous mapping if the range is suitably aligned */
+ if ((((addr | next | phys) & ~CONT_PMD_MASK) == 0) &&
+ (flags & NO_CONT_MAPPINGS) == 0)
+ __prot = __pgprot(pgprot_val(prot) | PTE_CONT);
+
+ init_pmd(pudp, addr, next, phys, __prot, pgtable_alloc, flags);
+
+ phys += next - addr;
+ } while (addr = next, addr != end);
+}
+
+static inline bool use_1G_block(unsigned long addr, unsigned long next,
+ unsigned long phys)
+{
+ if (PAGE_SHIFT != 12)
+ return false;
+
+ if (((addr | next | phys) & ~PUD_MASK) != 0)
+ return false;
+
+ return true;
+}
+
+static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
+ phys_addr_t phys, pgprot_t prot,
+ phys_addr_t (*pgtable_alloc)(void),
+ int flags)
+{
+ unsigned long next;
+ pud_t *pudp;
+ pgd_t pgd = READ_ONCE(*pgdp);
+
+ if (pgd_none(pgd)) {
+ phys_addr_t pud_phys;
+ BUG_ON(!pgtable_alloc);
+ pud_phys = pgtable_alloc();
+ __pgd_populate(pgdp, pud_phys, PUD_TYPE_TABLE);
+ pgd = READ_ONCE(*pgdp);
+ }
+ BUG_ON(pgd_bad(pgd));
+
+ pudp = pud_set_fixmap_offset(pgdp, addr);
+ do {
+ pud_t old_pud = READ_ONCE(*pudp);
+
+ next = pud_addr_end(addr, end);
+
+ /*
+ * For 4K granule only, attempt to put down a 1GB block
+ */
+ if (use_1G_block(addr, next, phys) &&
+ (flags & NO_BLOCK_MAPPINGS) == 0) {
+ pud_set_huge(pudp, phys, prot);
+
+ /*
+ * After the PUD entry has been populated once, we
+ * only allow updates to the permission attributes.
+ */
+ BUG_ON(!pgattr_change_is_safe(pud_val(old_pud),
+ READ_ONCE(pud_val(*pudp))));
+ } else {
+ alloc_init_cont_pmd(pudp, addr, next, phys, prot,
+ pgtable_alloc, flags);
+
+ BUG_ON(pud_val(old_pud) != 0 &&
+ pud_val(old_pud) != READ_ONCE(pud_val(*pudp)));
+ }
+ phys += next - addr;
+ } while (pudp++, addr = next, addr != end);
+
+ pud_clear_fixmap();
+}
+
+static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
+ unsigned long virt, phys_addr_t size,
+ pgprot_t prot,
+ phys_addr_t (*pgtable_alloc)(void),
+ int flags)
+{
+ unsigned long addr, length, end, next;
+ pgd_t *pgdp = pgd_offset_raw(pgdir, virt);
+
+ /*
+ * If the virtual and physical address don't have the same offset
+ * within a page, we cannot map the region as the caller expects.
+ */
+ if (WARN_ON((phys ^ virt) & ~PAGE_MASK))
+ return;
+
+ phys &= PAGE_MASK;
+ addr = virt & PAGE_MASK;
+ length = PAGE_ALIGN(size + (virt & ~PAGE_MASK));
+
+ end = addr + length;
+ do {
+ next = pgd_addr_end(addr, end);
+ alloc_init_pud(pgdp, addr, next, phys, prot, pgtable_alloc,
+ flags);
+ phys += next - addr;
+ } while (pgdp++, addr = next, addr != end);
+}
+
+static phys_addr_t pgd_pgtable_alloc(void)
+{
+ void *ptr = (void *)__get_free_page(PGALLOC_GFP);
+ if (!ptr || !pgtable_page_ctor(virt_to_page(ptr)))
+ BUG();
+
+ /* Ensure the zeroed page is visible to the page table walker */
+ dsb(ishst);
+ return __pa(ptr);
+}
+
+/*
+ * This function can only be used to modify existing table entries,
+ * without allocating new levels of table. Note that this permits the
+ * creation of new section or page entries.
+ */
+static void __init create_mapping_noalloc(phys_addr_t phys, unsigned long virt,
+ phys_addr_t size, pgprot_t prot)
+{
+ if (virt < VMALLOC_START) {
+ pr_warn("BUG: not creating mapping for %pa at 0x%016lx - outside kernel range\n",
+ &phys, virt);
+ return;
+ }
+ __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL,
+ NO_CONT_MAPPINGS);
+}
+
+void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
+ unsigned long virt, phys_addr_t size,
+ pgprot_t prot, bool page_mappings_only)
+{
+ int flags = 0;
+
+ BUG_ON(mm == &init_mm);
+
+ if (page_mappings_only)
+ flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
+
+ __create_pgd_mapping(mm->pgd, phys, virt, size, prot,
+ pgd_pgtable_alloc, flags);
+}
+
+static void update_mapping_prot(phys_addr_t phys, unsigned long virt,
+ phys_addr_t size, pgprot_t prot)
+{
+ if (virt < VMALLOC_START) {
+ pr_warn("BUG: not updating mapping for %pa at 0x%016lx - outside kernel range\n",
+ &phys, virt);
+ return;
+ }
+
+ __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL,
+ NO_CONT_MAPPINGS);
+
+ /* flush the TLBs after updating live kernel mappings */
+ flush_tlb_kernel_range(virt, virt + size);
+}
+
+static void __init __map_memblock(pgd_t *pgdp, phys_addr_t start,
+ phys_addr_t end, pgprot_t prot, int flags)
+{
+ __create_pgd_mapping(pgdp, start, __phys_to_virt(start), end - start,
+ prot, early_pgtable_alloc, flags);
+}
+
+void __init mark_linear_text_alias_ro(void)
+{
+ /*
+ * Remove the write permissions from the linear alias of .text/.rodata
+ */
+ update_mapping_prot(__pa_symbol(_text), (unsigned long)lm_alias(_text),
+ (unsigned long)__init_begin - (unsigned long)_text,
+ PAGE_KERNEL_RO);
+}
+
+static void __init map_mem(pgd_t *pgdp)
+{
+ phys_addr_t kernel_start = __pa_symbol(_text);
+ phys_addr_t kernel_end = __pa_symbol(__init_begin);
+ struct memblock_region *reg;
+ int flags = 0;
+
+ if (debug_pagealloc_enabled())
+ flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
+
+ /*
+ * Take care not to create a writable alias for the
+ * read-only text and rodata sections of the kernel image.
+ * So temporarily mark them as NOMAP to skip mappings in
+ * the following for-loop
+ */
+ memblock_mark_nomap(kernel_start, kernel_end - kernel_start);
+#ifdef CONFIG_KEXEC_CORE
+ if (crashk_res.end)
+ memblock_mark_nomap(crashk_res.start,
+ resource_size(&crashk_res));
+#endif
+
+ /* map all the memory banks */
+ for_each_memblock(memory, reg) {
+ phys_addr_t start = reg->base;
+ phys_addr_t end = start + reg->size;
+
+ if (start >= end)
+ break;
+ if (memblock_is_nomap(reg))
+ continue;
+
+ __map_memblock(pgdp, start, end, PAGE_KERNEL, flags);
+ }
+
+ /*
+ * Map the linear alias of the [_text, __init_begin) interval
+ * as non-executable now, and remove the write permission in
+ * mark_linear_text_alias_ro() below (which will be called after
+ * alternative patching has completed). This makes the contents
+ * of the region accessible to subsystems such as hibernate,
+ * but protects it from inadvertent modification or execution.
+ * Note that contiguous mappings cannot be remapped in this way,
+ * so we should avoid them here.
+ */
+ __map_memblock(pgdp, kernel_start, kernel_end,
+ PAGE_KERNEL, NO_CONT_MAPPINGS);
+ memblock_clear_nomap(kernel_start, kernel_end - kernel_start);
+
+#ifdef CONFIG_KEXEC_CORE
+ /*
+ * Use page-level mappings here so that we can shrink the region
+ * in page granularity and put back unused memory to buddy system
+ * through /sys/kernel/kexec_crash_size interface.
+ */
+ if (crashk_res.end) {
+ __map_memblock(pgdp, crashk_res.start, crashk_res.end + 1,
+ PAGE_KERNEL,
+ NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS);
+ memblock_clear_nomap(crashk_res.start,
+ resource_size(&crashk_res));
+ }
+#endif
+}
+
+void mark_rodata_ro(void)
+{
+ unsigned long section_size;
+
+ /*
+ * mark .rodata as read only. Use __init_begin rather than __end_rodata
+ * to cover NOTES and EXCEPTION_TABLE.
+ */
+ section_size = (unsigned long)__init_begin - (unsigned long)__start_rodata;
+ update_mapping_prot(__pa_symbol(__start_rodata), (unsigned long)__start_rodata,
+ section_size, PAGE_KERNEL_RO);
+
+ debug_checkwx();
+}
+
+static void __init map_kernel_segment(pgd_t *pgdp, void *va_start, void *va_end,
+ pgprot_t prot, struct vm_struct *vma,
+ int flags, unsigned long vm_flags)
+{
+ phys_addr_t pa_start = __pa_symbol(va_start);
+ unsigned long size = va_end - va_start;
+
+ BUG_ON(!PAGE_ALIGNED(pa_start));
+ BUG_ON(!PAGE_ALIGNED(size));
+
+ __create_pgd_mapping(pgdp, pa_start, (unsigned long)va_start, size, prot,
+ early_pgtable_alloc, flags);
+
+ if (!(vm_flags & VM_NO_GUARD))
+ size += PAGE_SIZE;
+
+ vma->addr = va_start;
+ vma->phys_addr = pa_start;
+ vma->size = size;
+ vma->flags = VM_MAP | vm_flags;
+ vma->caller = __builtin_return_address(0);
+
+ vm_area_add_early(vma);
+}
+
+static int __init parse_rodata(char *arg)
+{
+ return strtobool(arg, &rodata_enabled);
+}
+early_param("rodata", parse_rodata);
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+static int __init map_entry_trampoline(void)
+{
+ int i;
+
+ pgprot_t prot = rodata_enabled ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC;
+ phys_addr_t pa_start = __pa_symbol(__entry_tramp_text_start);
+
+ /* The trampoline is always mapped and can therefore be global */
+ pgprot_val(prot) &= ~PTE_NG;
+
+ /* Map only the text into the trampoline page table */
+ memset(tramp_pg_dir, 0, PGD_SIZE);
+ __create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS,
+ entry_tramp_text_size(), prot, pgd_pgtable_alloc,
+ 0);
+
+ /* Map both the text and data into the kernel page table */
+ for (i = 0; i < DIV_ROUND_UP(entry_tramp_text_size(), PAGE_SIZE); i++)
+ __set_fixmap(FIX_ENTRY_TRAMP_TEXT1 - i,
+ pa_start + i * PAGE_SIZE, prot);
+
+ if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
+ extern char __entry_tramp_data_start[];
+
+ __set_fixmap(FIX_ENTRY_TRAMP_DATA,
+ __pa_symbol(__entry_tramp_data_start),
+ PAGE_KERNEL_RO);
+ }
+
+ return 0;
+}
+core_initcall(map_entry_trampoline);
+#endif
+
+/*
+ * Create fine-grained mappings for the kernel.
+ */
+static void __init map_kernel(pgd_t *pgdp)
+{
+ static struct vm_struct vmlinux_text, vmlinux_rodata, vmlinux_inittext,
+ vmlinux_initdata, vmlinux_data;
+
+ /*
+ * External debuggers may need to write directly to the text
+ * mapping to install SW breakpoints. Allow this (only) when
+ * explicitly requested with rodata=off.
+ */
+ pgprot_t text_prot = rodata_enabled ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC;
+
+ /*
+ * Only rodata will be remapped with different permissions later on,
+ * all other segments are allowed to use contiguous mappings.
+ */
+ map_kernel_segment(pgdp, _text, _etext, text_prot, &vmlinux_text, 0,
+ VM_NO_GUARD);
+ map_kernel_segment(pgdp, __start_rodata, __inittext_begin, PAGE_KERNEL,
+ &vmlinux_rodata, NO_CONT_MAPPINGS, VM_NO_GUARD);
+ map_kernel_segment(pgdp, __inittext_begin, __inittext_end, text_prot,
+ &vmlinux_inittext, 0, VM_NO_GUARD);
+ map_kernel_segment(pgdp, __initdata_begin, __initdata_end, PAGE_KERNEL,
+ &vmlinux_initdata, 0, VM_NO_GUARD);
+ map_kernel_segment(pgdp, _data, _end, PAGE_KERNEL, &vmlinux_data, 0, 0);
+
+ if (!READ_ONCE(pgd_val(*pgd_offset_raw(pgdp, FIXADDR_START)))) {
+ /*
+ * The fixmap falls in a separate pgd to the kernel, and doesn't
+ * live in the carveout for the swapper_pg_dir. We can simply
+ * re-use the existing dir for the fixmap.
+ */
+ set_pgd(pgd_offset_raw(pgdp, FIXADDR_START),
+ READ_ONCE(*pgd_offset_k(FIXADDR_START)));
+ } else if (CONFIG_PGTABLE_LEVELS > 3) {
+ /*
+ * The fixmap shares its top level pgd entry with the kernel
+ * mapping. This can really only occur when we are running
+ * with 16k/4 levels, so we can simply reuse the pud level
+ * entry instead.
+ */
+ BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES));
+ pud_populate(&init_mm,
+ pud_set_fixmap_offset(pgdp, FIXADDR_START),
+ lm_alias(bm_pmd));
+ pud_clear_fixmap();
+ } else {
+ BUG();
+ }
+
+ kasan_copy_shadow(pgdp);
+}
+
+/*
+ * paging_init() sets up the page tables, initialises the zone memory
+ * maps and sets up the zero page.
+ */
+void __init paging_init(void)
+{
+ phys_addr_t pgd_phys = early_pgtable_alloc();
+ pgd_t *pgdp = pgd_set_fixmap(pgd_phys);
+
+ map_kernel(pgdp);
+ map_mem(pgdp);
+
+ /*
+ * We want to reuse the original swapper_pg_dir so we don't have to
+ * communicate the new address to non-coherent secondaries in
+ * secondary_entry, and so cpu_switch_mm can generate the address with
+ * adrp+add rather than a load from some global variable.
+ *
+ * To do this we need to go via a temporary pgd.
+ */
+ cpu_replace_ttbr1(__va(pgd_phys));
+ memcpy(swapper_pg_dir, pgdp, PGD_SIZE);
+ cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
+
+ pgd_clear_fixmap();
+ memblock_free(pgd_phys, PAGE_SIZE);
+
+ /*
+ * We only reuse the PGD from the swapper_pg_dir, not the pud + pmd
+ * allocated with it.
+ */
+ memblock_free(__pa_symbol(swapper_pg_dir) + PAGE_SIZE,
+ __pa_symbol(swapper_pg_end) - __pa_symbol(swapper_pg_dir)
+ - PAGE_SIZE);
+}
+
+/*
+ * Check whether a kernel address is valid (derived from arch/x86/).
+ */
+int kern_addr_valid(unsigned long addr)
+{
+ pgd_t *pgdp;
+ pud_t *pudp, pud;
+ pmd_t *pmdp, pmd;
+ pte_t *ptep, pte;
+
+ if ((((long)addr) >> VA_BITS) != -1UL)
+ return 0;
+
+ pgdp = pgd_offset_k(addr);
+ if (pgd_none(READ_ONCE(*pgdp)))
+ return 0;
+
+ pudp = pud_offset(pgdp, addr);
+ pud = READ_ONCE(*pudp);
+ if (pud_none(pud))
+ return 0;
+
+ if (pud_sect(pud))
+ return pfn_valid(pud_pfn(pud));
+
+ pmdp = pmd_offset(pudp, addr);
+ pmd = READ_ONCE(*pmdp);
+ if (pmd_none(pmd))
+ return 0;
+
+ if (pmd_sect(pmd))
+ return pfn_valid(pmd_pfn(pmd));
+
+ ptep = pte_offset_kernel(pmdp, addr);
+ pte = READ_ONCE(*ptep);
+ if (pte_none(pte))
+ return 0;
+
+ return pfn_valid(pte_pfn(pte));
+}
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+#if !ARM64_SWAPPER_USES_SECTION_MAPS
+int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
+ struct vmem_altmap *altmap)
+{
+ return vmemmap_populate_basepages(start, end, node);
+}
+#else /* !ARM64_SWAPPER_USES_SECTION_MAPS */
+int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
+ struct vmem_altmap *altmap)
+{
+ unsigned long addr = start;
+ unsigned long next;
+ pgd_t *pgdp;
+ pud_t *pudp;
+ pmd_t *pmdp;
+
+ do {
+ next = pmd_addr_end(addr, end);
+
+ pgdp = vmemmap_pgd_populate(addr, node);
+ if (!pgdp)
+ return -ENOMEM;
+
+ pudp = vmemmap_pud_populate(pgdp, addr, node);
+ if (!pudp)
+ return -ENOMEM;
+
+ pmdp = pmd_offset(pudp, addr);
+ if (pmd_none(READ_ONCE(*pmdp))) {
+ void *p = NULL;
+
+ p = vmemmap_alloc_block_buf(PMD_SIZE, node);
+ if (!p)
+ return -ENOMEM;
+
+ pmd_set_huge(pmdp, __pa(p), __pgprot(PROT_SECT_NORMAL));
+ } else
+ vmemmap_verify((pte_t *)pmdp, node, addr, next);
+ } while (addr = next, addr != end);
+
+ return 0;
+}
+#endif /* CONFIG_ARM64_64K_PAGES */
+void vmemmap_free(unsigned long start, unsigned long end,
+ struct vmem_altmap *altmap)
+{
+}
+#endif /* CONFIG_SPARSEMEM_VMEMMAP */
+
+static inline pud_t * fixmap_pud(unsigned long addr)
+{
+ pgd_t *pgdp = pgd_offset_k(addr);
+ pgd_t pgd = READ_ONCE(*pgdp);
+
+ BUG_ON(pgd_none(pgd) || pgd_bad(pgd));
+
+ return pud_offset_kimg(pgdp, addr);
+}
+
+static inline pmd_t * fixmap_pmd(unsigned long addr)
+{
+ pud_t *pudp = fixmap_pud(addr);
+ pud_t pud = READ_ONCE(*pudp);
+
+ BUG_ON(pud_none(pud) || pud_bad(pud));
+
+ return pmd_offset_kimg(pudp, addr);
+}
+
+static inline pte_t * fixmap_pte(unsigned long addr)
+{
+ return &bm_pte[pte_index(addr)];
+}
+
+/*
+ * The p*d_populate functions call virt_to_phys implicitly so they can't be used
+ * directly on kernel symbols (bm_p*d). This function is called too early to use
+ * lm_alias so __p*d_populate functions must be used to populate with the
+ * physical address from __pa_symbol.
+ */
+void __init early_fixmap_init(void)
+{
+ pgd_t *pgdp, pgd;
+ pud_t *pudp;
+ pmd_t *pmdp;
+ unsigned long addr = FIXADDR_START;
+
+ pgdp = pgd_offset_k(addr);
+ pgd = READ_ONCE(*pgdp);
+ if (CONFIG_PGTABLE_LEVELS > 3 &&
+ !(pgd_none(pgd) || pgd_page_paddr(pgd) == __pa_symbol(bm_pud))) {
+ /*
+ * We only end up here if the kernel mapping and the fixmap
+ * share the top level pgd entry, which should only happen on
+ * 16k/4 levels configurations.
+ */
+ BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES));
+ pudp = pud_offset_kimg(pgdp, addr);
+ } else {
+ if (pgd_none(pgd))
+ __pgd_populate(pgdp, __pa_symbol(bm_pud), PUD_TYPE_TABLE);
+ pudp = fixmap_pud(addr);
+ }
+ if (pud_none(READ_ONCE(*pudp)))
+ __pud_populate(pudp, __pa_symbol(bm_pmd), PMD_TYPE_TABLE);
+ pmdp = fixmap_pmd(addr);
+ __pmd_populate(pmdp, __pa_symbol(bm_pte), PMD_TYPE_TABLE);
+
+ /*
+ * The boot-ioremap range spans multiple pmds, for which
+ * we are not prepared:
+ */
+ BUILD_BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT)
+ != (__fix_to_virt(FIX_BTMAP_END) >> PMD_SHIFT));
+
+ if ((pmdp != fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)))
+ || pmdp != fixmap_pmd(fix_to_virt(FIX_BTMAP_END))) {
+ WARN_ON(1);
+ pr_warn("pmdp %p != %p, %p\n",
+ pmdp, fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)),
+ fixmap_pmd(fix_to_virt(FIX_BTMAP_END)));
+ pr_warn("fix_to_virt(FIX_BTMAP_BEGIN): %08lx\n",
+ fix_to_virt(FIX_BTMAP_BEGIN));
+ pr_warn("fix_to_virt(FIX_BTMAP_END): %08lx\n",
+ fix_to_virt(FIX_BTMAP_END));
+
+ pr_warn("FIX_BTMAP_END: %d\n", FIX_BTMAP_END);
+ pr_warn("FIX_BTMAP_BEGIN: %d\n", FIX_BTMAP_BEGIN);
+ }
+}
+
+/*
+ * Unusually, this is also called in IRQ context (ghes_iounmap_irq) so if we
+ * ever need to use IPIs for TLB broadcasting, then we're in trouble here.
+ */
+void __set_fixmap(enum fixed_addresses idx,
+ phys_addr_t phys, pgprot_t flags)
+{
+ unsigned long addr = __fix_to_virt(idx);
+ pte_t *ptep;
+
+ BUG_ON(idx <= FIX_HOLE || idx >= __end_of_fixed_addresses);
+
+ ptep = fixmap_pte(addr);
+
+ if (pgprot_val(flags)) {
+ set_pte(ptep, pfn_pte(phys >> PAGE_SHIFT, flags));
+ } else {
+ pte_clear(&init_mm, addr, ptep);
+ flush_tlb_kernel_range(addr, addr+PAGE_SIZE);
+ }
+}
+
+void *__init __fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot)
+{
+ const u64 dt_virt_base = __fix_to_virt(FIX_FDT);
+ int offset;
+ void *dt_virt;
+
+ /*
+ * Check whether the physical FDT address is set and meets the minimum
+ * alignment requirement. Since we are relying on MIN_FDT_ALIGN to be
+ * at least 8 bytes so that we can always access the magic and size
+ * fields of the FDT header after mapping the first chunk, double check
+ * here if that is indeed the case.
+ */
+ BUILD_BUG_ON(MIN_FDT_ALIGN < 8);
+ if (!dt_phys || dt_phys % MIN_FDT_ALIGN)
+ return NULL;
+
+ /*
+ * Make sure that the FDT region can be mapped without the need to
+ * allocate additional translation table pages, so that it is safe
+ * to call create_mapping_noalloc() this early.
+ *
+ * On 64k pages, the FDT will be mapped using PTEs, so we need to
+ * be in the same PMD as the rest of the fixmap.
+ * On 4k pages, we'll use section mappings for the FDT so we only
+ * have to be in the same PUD.
+ */
+ BUILD_BUG_ON(dt_virt_base % SZ_2M);
+
+ BUILD_BUG_ON(__fix_to_virt(FIX_FDT_END) >> SWAPPER_TABLE_SHIFT !=
+ __fix_to_virt(FIX_BTMAP_BEGIN) >> SWAPPER_TABLE_SHIFT);
+
+ offset = dt_phys % SWAPPER_BLOCK_SIZE;
+ dt_virt = (void *)dt_virt_base + offset;
+
+ /* map the first chunk so we can read the size from the header */
+ create_mapping_noalloc(round_down(dt_phys, SWAPPER_BLOCK_SIZE),
+ dt_virt_base, SWAPPER_BLOCK_SIZE, prot);
+
+ if (fdt_magic(dt_virt) != FDT_MAGIC)
+ return NULL;
+
+ *size = fdt_totalsize(dt_virt);
+ if (*size > MAX_FDT_SIZE)
+ return NULL;
+
+ if (offset + *size > SWAPPER_BLOCK_SIZE)
+ create_mapping_noalloc(round_down(dt_phys, SWAPPER_BLOCK_SIZE), dt_virt_base,
+ round_up(offset + *size, SWAPPER_BLOCK_SIZE), prot);
+
+ return dt_virt;
+}
+
+void *__init fixmap_remap_fdt(phys_addr_t dt_phys)
+{
+ void *dt_virt;
+ int size;
+
+ dt_virt = __fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL_RO);
+ if (!dt_virt)
+ return NULL;
+
+ memblock_reserve(dt_phys, size);
+ return dt_virt;
+}
+
+int __init arch_ioremap_pud_supported(void)
+{
+ /*
+ * Only 4k granule supports level 1 block mappings.
+ * SW table walks can't handle removal of intermediate entries.
+ */
+ return IS_ENABLED(CONFIG_ARM64_4K_PAGES) &&
+ !IS_ENABLED(CONFIG_ARM64_PTDUMP_DEBUGFS);
+}
+
+int __init arch_ioremap_pmd_supported(void)
+{
+ /* See arch_ioremap_pud_supported() */
+ return !IS_ENABLED(CONFIG_ARM64_PTDUMP_DEBUGFS);
+}
+
+int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot)
+{
+ pgprot_t sect_prot = __pgprot(PUD_TYPE_SECT |
+ pgprot_val(mk_sect_prot(prot)));
+ pud_t new_pud = pfn_pud(__phys_to_pfn(phys), sect_prot);
+
+ /* Only allow permission changes for now */
+ if (!pgattr_change_is_safe(READ_ONCE(pud_val(*pudp)),
+ pud_val(new_pud)))
+ return 0;
+
+ BUG_ON(phys & ~PUD_MASK);
+ set_pud(pudp, new_pud);
+ return 1;
+}
+
+int pmd_set_huge(pmd_t *pmdp, phys_addr_t phys, pgprot_t prot)
+{
+ pgprot_t sect_prot = __pgprot(PMD_TYPE_SECT |
+ pgprot_val(mk_sect_prot(prot)));
+ pmd_t new_pmd = pfn_pmd(__phys_to_pfn(phys), sect_prot);
+
+ /* Only allow permission changes for now */
+ if (!pgattr_change_is_safe(READ_ONCE(pmd_val(*pmdp)),
+ pmd_val(new_pmd)))
+ return 0;
+
+ BUG_ON(phys & ~PMD_MASK);
+ set_pmd(pmdp, new_pmd);
+ return 1;
+}
+
+int pud_clear_huge(pud_t *pudp)
+{
+ if (!pud_sect(READ_ONCE(*pudp)))
+ return 0;
+ pud_clear(pudp);
+ return 1;
+}
+
+int pmd_clear_huge(pmd_t *pmdp)
+{
+ if (!pmd_sect(READ_ONCE(*pmdp)))
+ return 0;
+ pmd_clear(pmdp);
+ return 1;
+}
+
+int pmd_free_pte_page(pmd_t *pmdp, unsigned long addr)
+{
+ pte_t *table;
+ pmd_t pmd;
+
+ pmd = READ_ONCE(*pmdp);
+
+ if (!pmd_present(pmd))
+ return 1;
+ if (!pmd_table(pmd)) {
+ VM_WARN_ON(!pmd_table(pmd));
+ return 1;
+ }
+
+ table = pte_offset_kernel(pmdp, addr);
+ pmd_clear(pmdp);
+ __flush_tlb_kernel_pgtable(addr);
+ pte_free_kernel(NULL, table);
+ return 1;
+}
+
+int pud_free_pmd_page(pud_t *pudp, unsigned long addr)
+{
+ pmd_t *table;
+ pmd_t *pmdp;
+ pud_t pud;
+ unsigned long next, end;
+
+ pud = READ_ONCE(*pudp);
+
+ if (!pud_present(pud))
+ return 1;
+ if (!pud_table(pud)) {
+ VM_WARN_ON(!pud_table(pud));
+ return 1;
+ }
+
+ table = pmd_offset(pudp, addr);
+ pmdp = table;
+ next = addr;
+ end = addr + PUD_SIZE;
+ do {
+ pmd_free_pte_page(pmdp, next);
+ } while (pmdp++, next += PMD_SIZE, next != end);
+
+ pud_clear(pudp);
+ __flush_tlb_kernel_pgtable(addr);
+ pmd_free(NULL, table);
+ return 1;
+}
diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
new file mode 100644
index 000000000..15eaf1e09
--- /dev/null
+++ b/arch/arm64/mm/numa.c
@@ -0,0 +1,470 @@
+/*
+ * NUMA support, based on the x86 implementation.
+ *
+ * Copyright (C) 2015 Cavium Inc.
+ * Author: Ganapatrao Kulkarni <gkulkarni@cavium.com>
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#define pr_fmt(fmt) "NUMA: " fmt
+
+#include <linux/acpi.h>
+#include <linux/bootmem.h>
+#include <linux/memblock.h>
+#include <linux/module.h>
+#include <linux/of.h>
+
+#include <asm/acpi.h>
+#include <asm/sections.h>
+
+struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
+EXPORT_SYMBOL(node_data);
+nodemask_t numa_nodes_parsed __initdata;
+static int cpu_to_node_map[NR_CPUS] = { [0 ... NR_CPUS-1] = NUMA_NO_NODE };
+
+static int numa_distance_cnt;
+static u8 *numa_distance;
+bool numa_off;
+
+static __init int numa_parse_early_param(char *opt)
+{
+ if (!opt)
+ return -EINVAL;
+ if (!strncmp(opt, "off", 3))
+ numa_off = true;
+
+ return 0;
+}
+early_param("numa", numa_parse_early_param);
+
+cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
+EXPORT_SYMBOL(node_to_cpumask_map);
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+
+/*
+ * Returns a pointer to the bitmask of CPUs on Node 'node'.
+ */
+const struct cpumask *cpumask_of_node(int node)
+{
+
+ if (node == NUMA_NO_NODE)
+ return cpu_all_mask;
+
+ if (WARN_ON(node < 0 || node >= nr_node_ids))
+ return cpu_none_mask;
+
+ if (WARN_ON(node_to_cpumask_map[node] == NULL))
+ return cpu_online_mask;
+
+ return node_to_cpumask_map[node];
+}
+EXPORT_SYMBOL(cpumask_of_node);
+
+#endif
+
+static void numa_update_cpu(unsigned int cpu, bool remove)
+{
+ int nid = cpu_to_node(cpu);
+
+ if (nid == NUMA_NO_NODE)
+ return;
+
+ if (remove)
+ cpumask_clear_cpu(cpu, node_to_cpumask_map[nid]);
+ else
+ cpumask_set_cpu(cpu, node_to_cpumask_map[nid]);
+}
+
+void numa_add_cpu(unsigned int cpu)
+{
+ numa_update_cpu(cpu, false);
+}
+
+void numa_remove_cpu(unsigned int cpu)
+{
+ numa_update_cpu(cpu, true);
+}
+
+void numa_clear_node(unsigned int cpu)
+{
+ numa_remove_cpu(cpu);
+ set_cpu_numa_node(cpu, NUMA_NO_NODE);
+}
+
+/*
+ * Allocate node_to_cpumask_map based on number of available nodes
+ * Requires node_possible_map to be valid.
+ *
+ * Note: cpumask_of_node() is not valid until after this is done.
+ * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.)
+ */
+static void __init setup_node_to_cpumask_map(void)
+{
+ int node;
+
+ /* setup nr_node_ids if not done yet */
+ if (nr_node_ids == MAX_NUMNODES)
+ setup_nr_node_ids();
+
+ /* allocate and clear the mapping */
+ for (node = 0; node < nr_node_ids; node++) {
+ alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]);
+ cpumask_clear(node_to_cpumask_map[node]);
+ }
+
+ /* cpumask_of_node() will now work */
+ pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids);
+}
+
+/*
+ * Set the cpu to node and mem mapping
+ */
+void numa_store_cpu_info(unsigned int cpu)
+{
+ set_cpu_numa_node(cpu, cpu_to_node_map[cpu]);
+}
+
+void __init early_map_cpu_to_node(unsigned int cpu, int nid)
+{
+ /* fallback to node 0 */
+ if (nid < 0 || nid >= MAX_NUMNODES || numa_off)
+ nid = 0;
+
+ cpu_to_node_map[cpu] = nid;
+
+ /*
+ * We should set the numa node of cpu0 as soon as possible, because it
+ * has already been set up online before. cpu_to_node(0) will soon be
+ * called.
+ */
+ if (!cpu)
+ set_cpu_numa_node(cpu, nid);
+}
+
+#ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
+unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
+EXPORT_SYMBOL(__per_cpu_offset);
+
+static int __init early_cpu_to_node(int cpu)
+{
+ return cpu_to_node_map[cpu];
+}
+
+static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
+{
+ return node_distance(early_cpu_to_node(from), early_cpu_to_node(to));
+}
+
+static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size,
+ size_t align)
+{
+ int nid = early_cpu_to_node(cpu);
+
+ return memblock_virt_alloc_try_nid(size, align,
+ __pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, nid);
+}
+
+static void __init pcpu_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,
+ pcpu_cpu_distance,
+ pcpu_fc_alloc, pcpu_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
+
+/**
+ * numa_add_memblk - Set node id to memblk
+ * @nid: NUMA node ID of the new memblk
+ * @start: Start address of the new memblk
+ * @end: End address of the new memblk
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+int __init numa_add_memblk(int nid, u64 start, u64 end)
+{
+ int ret;
+
+ ret = memblock_set_node(start, (end - start), &memblock.memory, nid);
+ if (ret < 0) {
+ pr_err("memblock [0x%llx - 0x%llx] failed to add on node %d\n",
+ start, (end - 1), nid);
+ return ret;
+ }
+
+ node_set(nid, numa_nodes_parsed);
+ return ret;
+}
+
+/**
+ * Initialize NODE_DATA for a node on the local memory
+ */
+static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
+{
+ const size_t nd_size = roundup(sizeof(pg_data_t), SMP_CACHE_BYTES);
+ u64 nd_pa;
+ void *nd;
+ int tnid;
+
+ if (start_pfn >= end_pfn)
+ pr_info("Initmem setup node %d [<memory-less node>]\n", nid);
+
+ nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
+ nd = __va(nd_pa);
+
+ /* report and initialize */
+ pr_info("NODE_DATA [mem %#010Lx-%#010Lx]\n",
+ nd_pa, nd_pa + nd_size - 1);
+ tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
+ if (tnid != nid)
+ pr_info("NODE_DATA(%d) on node %d\n", nid, tnid);
+
+ node_data[nid] = nd;
+ memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
+ NODE_DATA(nid)->node_id = nid;
+ NODE_DATA(nid)->node_start_pfn = start_pfn;
+ NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn;
+}
+
+/**
+ * numa_free_distance
+ *
+ * The current table is freed.
+ */
+void __init numa_free_distance(void)
+{
+ size_t size;
+
+ if (!numa_distance)
+ return;
+
+ size = numa_distance_cnt * numa_distance_cnt *
+ sizeof(numa_distance[0]);
+
+ memblock_free(__pa(numa_distance), size);
+ numa_distance_cnt = 0;
+ numa_distance = NULL;
+}
+
+/**
+ *
+ * Create a new NUMA distance table.
+ *
+ */
+static int __init numa_alloc_distance(void)
+{
+ size_t size;
+ u64 phys;
+ int i, j;
+
+ size = nr_node_ids * nr_node_ids * sizeof(numa_distance[0]);
+ phys = memblock_find_in_range(0, PFN_PHYS(max_pfn),
+ size, PAGE_SIZE);
+ if (WARN_ON(!phys))
+ return -ENOMEM;
+
+ memblock_reserve(phys, size);
+
+ numa_distance = __va(phys);
+ numa_distance_cnt = nr_node_ids;
+
+ /* fill with the default distances */
+ for (i = 0; i < numa_distance_cnt; i++)
+ for (j = 0; j < numa_distance_cnt; j++)
+ numa_distance[i * numa_distance_cnt + j] = i == j ?
+ LOCAL_DISTANCE : REMOTE_DISTANCE;
+
+ pr_debug("Initialized distance table, cnt=%d\n", numa_distance_cnt);
+
+ return 0;
+}
+
+/**
+ * numa_set_distance - Set inter node NUMA distance from node to node.
+ * @from: the 'from' node to set distance
+ * @to: the 'to' node to set distance
+ * @distance: NUMA distance
+ *
+ * Set the distance from node @from to @to to @distance.
+ * If distance table doesn't exist, a warning is printed.
+ *
+ * If @from or @to is higher than the highest known node or lower than zero
+ * or @distance doesn't make sense, the call is ignored.
+ *
+ */
+void __init numa_set_distance(int from, int to, int distance)
+{
+ if (!numa_distance) {
+ pr_warn_once("Warning: distance table not allocated yet\n");
+ return;
+ }
+
+ if (from >= numa_distance_cnt || to >= numa_distance_cnt ||
+ from < 0 || to < 0) {
+ pr_warn_once("Warning: node ids are out of bound, from=%d to=%d distance=%d\n",
+ from, to, distance);
+ return;
+ }
+
+ if ((u8)distance != distance ||
+ (from == to && distance != LOCAL_DISTANCE)) {
+ pr_warn_once("Warning: invalid distance parameter, from=%d to=%d distance=%d\n",
+ from, to, distance);
+ return;
+ }
+
+ numa_distance[from * numa_distance_cnt + to] = distance;
+}
+
+/**
+ * Return NUMA distance @from to @to
+ */
+int __node_distance(int from, int to)
+{
+ if (from >= numa_distance_cnt || to >= numa_distance_cnt)
+ return from == to ? LOCAL_DISTANCE : REMOTE_DISTANCE;
+ return numa_distance[from * numa_distance_cnt + to];
+}
+EXPORT_SYMBOL(__node_distance);
+
+static int __init numa_register_nodes(void)
+{
+ int nid;
+ struct memblock_region *mblk;
+
+ /* Check that valid nid is set to memblks */
+ for_each_memblock(memory, mblk)
+ if (mblk->nid == NUMA_NO_NODE || mblk->nid >= MAX_NUMNODES) {
+ pr_warn("Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n",
+ mblk->nid, mblk->base,
+ mblk->base + mblk->size - 1);
+ return -EINVAL;
+ }
+
+ /* Finally register nodes. */
+ for_each_node_mask(nid, numa_nodes_parsed) {
+ unsigned long start_pfn, end_pfn;
+
+ get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
+ setup_node_data(nid, start_pfn, end_pfn);
+ node_set_online(nid);
+ }
+
+ /* Setup online nodes to actual nodes*/
+ node_possible_map = numa_nodes_parsed;
+
+ return 0;
+}
+
+static int __init numa_init(int (*init_func)(void))
+{
+ int ret;
+
+ nodes_clear(numa_nodes_parsed);
+ nodes_clear(node_possible_map);
+ nodes_clear(node_online_map);
+ numa_free_distance();
+
+ ret = numa_alloc_distance();
+ if (ret < 0)
+ return ret;
+
+ ret = init_func();
+ if (ret < 0)
+ return ret;
+
+ if (nodes_empty(numa_nodes_parsed)) {
+ pr_info("No NUMA configuration found\n");
+ return -EINVAL;
+ }
+
+ ret = numa_register_nodes();
+ if (ret < 0)
+ return ret;
+
+ setup_node_to_cpumask_map();
+
+ return 0;
+}
+
+/**
+ * dummy_numa_init - Fallback dummy NUMA init
+ *
+ * Used if there's no underlying NUMA architecture, NUMA initialization
+ * fails, or NUMA is disabled on the command line.
+ *
+ * Must online at least one node (node 0) and add memory blocks that cover all
+ * allowed memory. It is unlikely that this function fails.
+ */
+static int __init dummy_numa_init(void)
+{
+ int ret;
+ struct memblock_region *mblk;
+
+ if (numa_off)
+ pr_info("NUMA disabled\n"); /* Forced off on command line. */
+ pr_info("Faking a node at [mem %#018Lx-%#018Lx]\n",
+ memblock_start_of_DRAM(), memblock_end_of_DRAM() - 1);
+
+ for_each_memblock(memory, mblk) {
+ ret = numa_add_memblk(0, mblk->base, mblk->base + mblk->size);
+ if (!ret)
+ continue;
+
+ pr_err("NUMA init failed\n");
+ return ret;
+ }
+
+ numa_off = true;
+ return 0;
+}
+
+/**
+ * arm64_numa_init - Initialize NUMA
+ *
+ * Try each configured NUMA initialization method until one succeeds. The
+ * last fallback is dummy single node config encomapssing whole memory.
+ */
+void __init arm64_numa_init(void)
+{
+ if (!numa_off) {
+ if (!acpi_disabled && !numa_init(arm64_acpi_numa_init))
+ return;
+ if (acpi_disabled && !numa_init(of_numa_init))
+ return;
+ }
+
+ numa_init(dummy_numa_init);
+}
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
new file mode 100644
index 000000000..a56359373
--- /dev/null
+++ b/arch/arm64/mm/pageattr.c
@@ -0,0 +1,187 @@
+/*
+ * Copyright (c) 2014, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only 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 <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/vmalloc.h>
+
+#include <asm/pgtable.h>
+#include <asm/set_memory.h>
+#include <asm/tlbflush.h>
+
+struct page_change_data {
+ pgprot_t set_mask;
+ pgprot_t clear_mask;
+};
+
+static int change_page_range(pte_t *ptep, pgtable_t token, unsigned long addr,
+ void *data)
+{
+ struct page_change_data *cdata = data;
+ pte_t pte = READ_ONCE(*ptep);
+
+ pte = clear_pte_bit(pte, cdata->clear_mask);
+ pte = set_pte_bit(pte, cdata->set_mask);
+
+ set_pte(ptep, pte);
+ return 0;
+}
+
+/*
+ * This function assumes that the range is mapped with PAGE_SIZE pages.
+ */
+static int __change_memory_common(unsigned long start, unsigned long size,
+ pgprot_t set_mask, pgprot_t clear_mask)
+{
+ struct page_change_data data;
+ int ret;
+
+ data.set_mask = set_mask;
+ data.clear_mask = clear_mask;
+
+ ret = apply_to_page_range(&init_mm, start, size, change_page_range,
+ &data);
+
+ flush_tlb_kernel_range(start, start + size);
+ return ret;
+}
+
+static int change_memory_common(unsigned long addr, int numpages,
+ pgprot_t set_mask, pgprot_t clear_mask)
+{
+ unsigned long start = addr;
+ unsigned long size = PAGE_SIZE*numpages;
+ unsigned long end = start + size;
+ struct vm_struct *area;
+
+ if (!PAGE_ALIGNED(addr)) {
+ start &= PAGE_MASK;
+ end = start + size;
+ WARN_ON_ONCE(1);
+ }
+
+ /*
+ * Kernel VA mappings are always live, and splitting live section
+ * mappings into page mappings may cause TLB conflicts. This means
+ * we have to ensure that changing the permission bits of the range
+ * we are operating on does not result in such splitting.
+ *
+ * Let's restrict ourselves to mappings created by vmalloc (or vmap).
+ * Those are guaranteed to consist entirely of page mappings, and
+ * splitting is never needed.
+ *
+ * So check whether the [addr, addr + size) interval is entirely
+ * covered by precisely one VM area that has the VM_ALLOC flag set.
+ */
+ area = find_vm_area((void *)addr);
+ if (!area ||
+ end > (unsigned long)area->addr + area->size ||
+ !(area->flags & VM_ALLOC))
+ return -EINVAL;
+
+ if (!numpages)
+ return 0;
+
+ return __change_memory_common(start, size, set_mask, clear_mask);
+}
+
+int set_memory_ro(unsigned long addr, int numpages)
+{
+ return change_memory_common(addr, numpages,
+ __pgprot(PTE_RDONLY),
+ __pgprot(PTE_WRITE));
+}
+
+int set_memory_rw(unsigned long addr, int numpages)
+{
+ return change_memory_common(addr, numpages,
+ __pgprot(PTE_WRITE),
+ __pgprot(PTE_RDONLY));
+}
+
+int set_memory_nx(unsigned long addr, int numpages)
+{
+ return change_memory_common(addr, numpages,
+ __pgprot(PTE_PXN),
+ __pgprot(0));
+}
+EXPORT_SYMBOL_GPL(set_memory_nx);
+
+int set_memory_x(unsigned long addr, int numpages)
+{
+ return change_memory_common(addr, numpages,
+ __pgprot(0),
+ __pgprot(PTE_PXN));
+}
+EXPORT_SYMBOL_GPL(set_memory_x);
+
+int set_memory_valid(unsigned long addr, int numpages, int enable)
+{
+ if (enable)
+ return __change_memory_common(addr, PAGE_SIZE * numpages,
+ __pgprot(PTE_VALID),
+ __pgprot(0));
+ else
+ return __change_memory_common(addr, PAGE_SIZE * numpages,
+ __pgprot(0),
+ __pgprot(PTE_VALID));
+}
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+void __kernel_map_pages(struct page *page, int numpages, int enable)
+{
+ set_memory_valid((unsigned long)page_address(page), numpages, enable);
+}
+#ifdef CONFIG_HIBERNATION
+/*
+ * When built with CONFIG_DEBUG_PAGEALLOC and CONFIG_HIBERNATION, this function
+ * is used to determine if a linear map page has been marked as not-valid by
+ * CONFIG_DEBUG_PAGEALLOC. Walk the page table and check the PTE_VALID bit.
+ * This is based on kern_addr_valid(), which almost does what we need.
+ *
+ * Because this is only called on the kernel linear map, p?d_sect() implies
+ * p?d_present(). When debug_pagealloc is enabled, sections mappings are
+ * disabled.
+ */
+bool kernel_page_present(struct page *page)
+{
+ pgd_t *pgdp;
+ pud_t *pudp, pud;
+ pmd_t *pmdp, pmd;
+ pte_t *ptep;
+ unsigned long addr = (unsigned long)page_address(page);
+
+ pgdp = pgd_offset_k(addr);
+ if (pgd_none(READ_ONCE(*pgdp)))
+ return false;
+
+ pudp = pud_offset(pgdp, addr);
+ pud = READ_ONCE(*pudp);
+ if (pud_none(pud))
+ return false;
+ if (pud_sect(pud))
+ return true;
+
+ pmdp = pmd_offset(pudp, addr);
+ pmd = READ_ONCE(*pmdp);
+ if (pmd_none(pmd))
+ return false;
+ if (pmd_sect(pmd))
+ return true;
+
+ ptep = pte_offset_kernel(pmdp, addr);
+ return pte_valid(READ_ONCE(*ptep));
+}
+#endif /* CONFIG_HIBERNATION */
+#endif /* CONFIG_DEBUG_PAGEALLOC */
diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c
new file mode 100644
index 000000000..289f9113a
--- /dev/null
+++ b/arch/arm64/mm/pgd.c
@@ -0,0 +1,65 @@
+/*
+ * PGD allocation/freeing
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/mm.h>
+#include <linux/gfp.h>
+#include <linux/highmem.h>
+#include <linux/slab.h>
+
+#include <asm/pgalloc.h>
+#include <asm/page.h>
+#include <asm/tlbflush.h>
+
+static struct kmem_cache *pgd_cache __ro_after_init;
+
+pgd_t *pgd_alloc(struct mm_struct *mm)
+{
+ if (PGD_SIZE == PAGE_SIZE)
+ return (pgd_t *)__get_free_page(PGALLOC_GFP);
+ else
+ return kmem_cache_alloc(pgd_cache, PGALLOC_GFP);
+}
+
+void pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+ if (PGD_SIZE == PAGE_SIZE)
+ free_page((unsigned long)pgd);
+ else
+ kmem_cache_free(pgd_cache, pgd);
+}
+
+void __init pgd_cache_init(void)
+{
+ if (PGD_SIZE == PAGE_SIZE)
+ return;
+
+#ifdef CONFIG_ARM64_PA_BITS_52
+ /*
+ * With 52-bit physical addresses, the architecture requires the
+ * top-level table to be aligned to at least 64 bytes.
+ */
+ BUILD_BUG_ON(PGD_SIZE < 64);
+#endif
+
+ /*
+ * Naturally aligned pgds required by the architecture.
+ */
+ pgd_cache = kmem_cache_create("pgd_cache", PGD_SIZE, PGD_SIZE,
+ SLAB_PANIC, NULL);
+}
diff --git a/arch/arm64/mm/physaddr.c b/arch/arm64/mm/physaddr.c
new file mode 100644
index 000000000..67a9ba9ea
--- /dev/null
+++ b/arch/arm64/mm/physaddr.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bug.h>
+#include <linux/export.h>
+#include <linux/types.h>
+#include <linux/mmdebug.h>
+#include <linux/mm.h>
+
+#include <asm/memory.h>
+
+phys_addr_t __virt_to_phys(unsigned long x)
+{
+ WARN(!__is_lm_address(x),
+ "virt_to_phys used for non-linear address: %pK (%pS)\n",
+ (void *)x,
+ (void *)x);
+
+ return __virt_to_phys_nodebug(x);
+}
+EXPORT_SYMBOL(__virt_to_phys);
+
+phys_addr_t __phys_addr_symbol(unsigned long x)
+{
+ /*
+ * This is bounds checking against the kernel image only.
+ * __pa_symbol should only be used on kernel symbol addresses.
+ */
+ VIRTUAL_BUG_ON(x < (unsigned long) KERNEL_START ||
+ x > (unsigned long) KERNEL_END);
+ return __pa_symbol_nodebug(x);
+}
+EXPORT_SYMBOL(__phys_addr_symbol);
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
new file mode 100644
index 000000000..ec6aa1863
--- /dev/null
+++ b/arch/arm64/mm/proc.S
@@ -0,0 +1,475 @@
+/*
+ * Based on arch/arm/mm/proc.S
+ *
+ * Copyright (C) 2001 Deep Blue Solutions Ltd.
+ * Copyright (C) 2012 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/asm-offsets.h>
+#include <asm/hwcap.h>
+#include <asm/pgtable.h>
+#include <asm/pgtable-hwdef.h>
+#include <asm/cpufeature.h>
+#include <asm/alternative.h>
+
+#ifdef CONFIG_ARM64_64K_PAGES
+#define TCR_TG_FLAGS TCR_TG0_64K | TCR_TG1_64K
+#elif defined(CONFIG_ARM64_16K_PAGES)
+#define TCR_TG_FLAGS TCR_TG0_16K | TCR_TG1_16K
+#else /* CONFIG_ARM64_4K_PAGES */
+#define TCR_TG_FLAGS TCR_TG0_4K | TCR_TG1_4K
+#endif
+
+#ifdef CONFIG_RANDOMIZE_BASE
+#define TCR_KASLR_FLAGS TCR_NFD1
+#else
+#define TCR_KASLR_FLAGS 0
+#endif
+
+#define TCR_SMP_FLAGS TCR_SHARED
+
+/* PTWs cacheable, inner/outer WBWA */
+#define TCR_CACHE_FLAGS TCR_IRGN_WBWA | TCR_ORGN_WBWA
+
+#define MAIR(attr, mt) ((attr) << ((mt) * 8))
+
+/*
+ * cpu_do_idle()
+ *
+ * Idle the processor (wait for interrupt).
+ */
+ENTRY(cpu_do_idle)
+ dsb sy // WFI may enter a low-power mode
+ wfi
+ ret
+ENDPROC(cpu_do_idle)
+
+#ifdef CONFIG_CPU_PM
+/**
+ * cpu_do_suspend - save CPU registers context
+ *
+ * x0: virtual address of context pointer
+ */
+ENTRY(cpu_do_suspend)
+ mrs x2, tpidr_el0
+ mrs x3, tpidrro_el0
+ mrs x4, contextidr_el1
+ mrs x5, osdlr_el1
+ mrs x6, cpacr_el1
+ mrs x7, tcr_el1
+ mrs x8, vbar_el1
+ mrs x9, mdscr_el1
+ mrs x10, oslsr_el1
+ mrs x11, sctlr_el1
+alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
+ mrs x12, tpidr_el1
+alternative_else
+ mrs x12, tpidr_el2
+alternative_endif
+ mrs x13, sp_el0
+ stp x2, x3, [x0]
+ stp x4, x5, [x0, #16]
+ stp x6, x7, [x0, #32]
+ stp x8, x9, [x0, #48]
+ stp x10, x11, [x0, #64]
+ stp x12, x13, [x0, #80]
+ ret
+ENDPROC(cpu_do_suspend)
+
+/**
+ * cpu_do_resume - restore CPU register context
+ *
+ * x0: Address of context pointer
+ */
+ .pushsection ".idmap.text", "awx"
+ENTRY(cpu_do_resume)
+ ldp x2, x3, [x0]
+ ldp x4, x5, [x0, #16]
+ ldp x6, x8, [x0, #32]
+ ldp x9, x10, [x0, #48]
+ ldp x11, x12, [x0, #64]
+ ldp x13, x14, [x0, #80]
+ msr tpidr_el0, x2
+ msr tpidrro_el0, x3
+ msr contextidr_el1, x4
+ msr cpacr_el1, x6
+
+ /* Don't change t0sz here, mask those bits when restoring */
+ mrs x7, tcr_el1
+ bfi x8, x7, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
+
+ msr tcr_el1, x8
+ msr vbar_el1, x9
+
+ /*
+ * __cpu_setup() cleared MDSCR_EL1.MDE and friends, before unmasking
+ * debug exceptions. By restoring MDSCR_EL1 here, we may take a debug
+ * exception. Mask them until local_daif_restore() in cpu_suspend()
+ * resets them.
+ */
+ disable_daif
+ msr mdscr_el1, x10
+
+ msr sctlr_el1, x12
+alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
+ msr tpidr_el1, x13
+alternative_else
+ msr tpidr_el2, x13
+alternative_endif
+ msr sp_el0, x14
+ /*
+ * Restore oslsr_el1 by writing oslar_el1
+ */
+ msr osdlr_el1, x5
+ ubfx x11, x11, #1, #1
+ msr oslar_el1, x11
+ reset_pmuserenr_el0 x0 // Disable PMU access from EL0
+
+alternative_if ARM64_HAS_RAS_EXTN
+ msr_s SYS_DISR_EL1, xzr
+alternative_else_nop_endif
+
+ isb
+ ret
+ENDPROC(cpu_do_resume)
+ .popsection
+#endif
+
+/*
+ * cpu_do_switch_mm(pgd_phys, tsk)
+ *
+ * Set the translation table base pointer to be pgd_phys.
+ *
+ * - pgd_phys - physical address of new TTB
+ */
+ENTRY(cpu_do_switch_mm)
+ mrs x2, ttbr1_el1
+ mmid x1, x1 // get mm->context.id
+ phys_to_ttbr x3, x0
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+ bfi x3, x1, #48, #16 // set the ASID field in TTBR0
+#endif
+ bfi x2, x1, #48, #16 // set the ASID
+ msr ttbr1_el1, x2 // in TTBR1 (since TCR.A1 is set)
+ isb
+ msr ttbr0_el1, x3 // now update TTBR0
+ isb
+ b post_ttbr_update_workaround // Back to C code...
+ENDPROC(cpu_do_switch_mm)
+
+ .pushsection ".idmap.text", "awx"
+
+.macro __idmap_cpu_set_reserved_ttbr1, tmp1, tmp2
+ adrp \tmp1, empty_zero_page
+ phys_to_ttbr \tmp2, \tmp1
+ msr ttbr1_el1, \tmp2
+ isb
+ tlbi vmalle1
+ dsb nsh
+ isb
+.endm
+
+/*
+ * void idmap_cpu_replace_ttbr1(phys_addr_t new_pgd)
+ *
+ * This is the low-level counterpart to cpu_replace_ttbr1, and should not be
+ * called by anything else. It can only be executed from a TTBR0 mapping.
+ */
+ENTRY(idmap_cpu_replace_ttbr1)
+ save_and_disable_daif flags=x2
+
+ __idmap_cpu_set_reserved_ttbr1 x1, x3
+
+ phys_to_ttbr x3, x0
+ msr ttbr1_el1, x3
+ isb
+
+ restore_daif x2
+
+ ret
+ENDPROC(idmap_cpu_replace_ttbr1)
+ .popsection
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+ .pushsection ".idmap.text", "awx"
+
+ .macro __idmap_kpti_get_pgtable_ent, type
+ dc cvac, cur_\()\type\()p // Ensure any existing dirty
+ dmb sy // lines are written back before
+ ldr \type, [cur_\()\type\()p] // loading the entry
+ tbz \type, #0, skip_\()\type // Skip invalid and
+ tbnz \type, #11, skip_\()\type // non-global entries
+ .endm
+
+ .macro __idmap_kpti_put_pgtable_ent_ng, type
+ orr \type, \type, #PTE_NG // Same bit for blocks and pages
+ str \type, [cur_\()\type\()p] // Update the entry and ensure
+ dmb sy // that it is visible to all
+ dc civac, cur_\()\type\()p // CPUs.
+ .endm
+
+/*
+ * void __kpti_install_ng_mappings(int cpu, int num_cpus, phys_addr_t swapper)
+ *
+ * Called exactly once from stop_machine context by each CPU found during boot.
+ */
+__idmap_kpti_flag:
+ .long 1
+ENTRY(idmap_kpti_install_ng_mappings)
+ cpu .req w0
+ num_cpus .req w1
+ swapper_pa .req x2
+ swapper_ttb .req x3
+ flag_ptr .req x4
+ cur_pgdp .req x5
+ end_pgdp .req x6
+ pgd .req x7
+ cur_pudp .req x8
+ end_pudp .req x9
+ pud .req x10
+ cur_pmdp .req x11
+ end_pmdp .req x12
+ pmd .req x13
+ cur_ptep .req x14
+ end_ptep .req x15
+ pte .req x16
+
+ mrs swapper_ttb, ttbr1_el1
+ adr flag_ptr, __idmap_kpti_flag
+
+ cbnz cpu, __idmap_kpti_secondary
+
+ /* We're the boot CPU. Wait for the others to catch up */
+ sevl
+1: wfe
+ ldaxr w18, [flag_ptr]
+ eor w18, w18, num_cpus
+ cbnz w18, 1b
+
+ /* We need to walk swapper, so turn off the MMU. */
+ pre_disable_mmu_workaround
+ mrs x18, sctlr_el1
+ bic x18, x18, #SCTLR_ELx_M
+ msr sctlr_el1, x18
+ isb
+
+ /* Everybody is enjoying the idmap, so we can rewrite swapper. */
+ /* PGD */
+ mov cur_pgdp, swapper_pa
+ add end_pgdp, cur_pgdp, #(PTRS_PER_PGD * 8)
+do_pgd: __idmap_kpti_get_pgtable_ent pgd
+ tbnz pgd, #1, walk_puds
+next_pgd:
+ __idmap_kpti_put_pgtable_ent_ng pgd
+skip_pgd:
+ add cur_pgdp, cur_pgdp, #8
+ cmp cur_pgdp, end_pgdp
+ b.ne do_pgd
+
+ /* Publish the updated tables and nuke all the TLBs */
+ dsb sy
+ tlbi vmalle1is
+ dsb ish
+ isb
+
+ /* We're done: fire up the MMU again */
+ mrs x18, sctlr_el1
+ orr x18, x18, #SCTLR_ELx_M
+ msr sctlr_el1, x18
+ isb
+
+ /*
+ * Invalidate the local I-cache so that any instructions fetched
+ * speculatively from the PoC are discarded, since they may have
+ * been dynamically patched at the PoU.
+ */
+ ic iallu
+ dsb nsh
+ isb
+
+ /* Set the flag to zero to indicate that we're all done */
+ str wzr, [flag_ptr]
+ ret
+
+ /* PUD */
+walk_puds:
+ .if CONFIG_PGTABLE_LEVELS > 3
+ pte_to_phys cur_pudp, pgd
+ add end_pudp, cur_pudp, #(PTRS_PER_PUD * 8)
+do_pud: __idmap_kpti_get_pgtable_ent pud
+ tbnz pud, #1, walk_pmds
+next_pud:
+ __idmap_kpti_put_pgtable_ent_ng pud
+skip_pud:
+ add cur_pudp, cur_pudp, 8
+ cmp cur_pudp, end_pudp
+ b.ne do_pud
+ b next_pgd
+ .else /* CONFIG_PGTABLE_LEVELS <= 3 */
+ mov pud, pgd
+ b walk_pmds
+next_pud:
+ b next_pgd
+ .endif
+
+ /* PMD */
+walk_pmds:
+ .if CONFIG_PGTABLE_LEVELS > 2
+ pte_to_phys cur_pmdp, pud
+ add end_pmdp, cur_pmdp, #(PTRS_PER_PMD * 8)
+do_pmd: __idmap_kpti_get_pgtable_ent pmd
+ tbnz pmd, #1, walk_ptes
+next_pmd:
+ __idmap_kpti_put_pgtable_ent_ng pmd
+skip_pmd:
+ add cur_pmdp, cur_pmdp, #8
+ cmp cur_pmdp, end_pmdp
+ b.ne do_pmd
+ b next_pud
+ .else /* CONFIG_PGTABLE_LEVELS <= 2 */
+ mov pmd, pud
+ b walk_ptes
+next_pmd:
+ b next_pud
+ .endif
+
+ /* PTE */
+walk_ptes:
+ pte_to_phys cur_ptep, pmd
+ add end_ptep, cur_ptep, #(PTRS_PER_PTE * 8)
+do_pte: __idmap_kpti_get_pgtable_ent pte
+ __idmap_kpti_put_pgtable_ent_ng pte
+skip_pte:
+ add cur_ptep, cur_ptep, #8
+ cmp cur_ptep, end_ptep
+ b.ne do_pte
+ b next_pmd
+
+ /* Secondary CPUs end up here */
+__idmap_kpti_secondary:
+ /* Uninstall swapper before surgery begins */
+ __idmap_cpu_set_reserved_ttbr1 x18, x17
+
+ /* Increment the flag to let the boot CPU we're ready */
+1: ldxr w18, [flag_ptr]
+ add w18, w18, #1
+ stxr w17, w18, [flag_ptr]
+ cbnz w17, 1b
+
+ /* Wait for the boot CPU to finish messing around with swapper */
+ sevl
+1: wfe
+ ldxr w18, [flag_ptr]
+ cbnz w18, 1b
+
+ /* All done, act like nothing happened */
+ msr ttbr1_el1, swapper_ttb
+ isb
+ ret
+
+ .unreq cpu
+ .unreq num_cpus
+ .unreq swapper_pa
+ .unreq swapper_ttb
+ .unreq flag_ptr
+ .unreq cur_pgdp
+ .unreq end_pgdp
+ .unreq pgd
+ .unreq cur_pudp
+ .unreq end_pudp
+ .unreq pud
+ .unreq cur_pmdp
+ .unreq end_pmdp
+ .unreq pmd
+ .unreq cur_ptep
+ .unreq end_ptep
+ .unreq pte
+ENDPROC(idmap_kpti_install_ng_mappings)
+ .popsection
+#endif
+
+/*
+ * __cpu_setup
+ *
+ * Initialise the processor for turning the MMU on. Return in x0 the
+ * value of the SCTLR_EL1 register.
+ */
+ .pushsection ".idmap.text", "awx"
+ENTRY(__cpu_setup)
+ tlbi vmalle1 // Invalidate local TLB
+ dsb nsh
+
+ mov x0, #3 << 20
+ msr cpacr_el1, x0 // Enable FP/ASIMD
+ mov x0, #1 << 12 // Reset mdscr_el1 and disable
+ msr mdscr_el1, x0 // access to the DCC from EL0
+ isb // Unmask debug exceptions now,
+ enable_dbg // since this is per-cpu
+ reset_pmuserenr_el0 x0 // Disable PMU access from EL0
+ /*
+ * Memory region attributes for LPAE:
+ *
+ * n = AttrIndx[2:0]
+ * n MAIR
+ * DEVICE_nGnRnE 000 00000000
+ * DEVICE_nGnRE 001 00000100
+ * DEVICE_GRE 010 00001100
+ * NORMAL_NC 011 01000100
+ * NORMAL 100 11111111
+ * NORMAL_WT 101 10111011
+ */
+ ldr x5, =MAIR(0x00, MT_DEVICE_nGnRnE) | \
+ MAIR(0x04, MT_DEVICE_nGnRE) | \
+ MAIR(0x0c, MT_DEVICE_GRE) | \
+ MAIR(0x44, MT_NORMAL_NC) | \
+ MAIR(0xff, MT_NORMAL) | \
+ MAIR(0xbb, MT_NORMAL_WT)
+ msr mair_el1, x5
+ /*
+ * Prepare SCTLR
+ */
+ mov_q x0, SCTLR_EL1_SET
+ /*
+ * Set/prepare TCR and TTBR. We use 512GB (39-bit) address range for
+ * both user and kernel.
+ */
+ ldr x10, =TCR_TxSZ(VA_BITS) | TCR_CACHE_FLAGS | TCR_SMP_FLAGS | \
+ TCR_TG_FLAGS | TCR_KASLR_FLAGS | TCR_ASID16 | \
+ TCR_TBI0 | TCR_A1
+ tcr_set_idmap_t0sz x10, x9
+
+ /*
+ * Set the IPS bits in TCR_EL1.
+ */
+ tcr_compute_pa_size x10, #TCR_IPS_SHIFT, x5, x6
+#ifdef CONFIG_ARM64_HW_AFDBM
+ /*
+ * Enable hardware update of the Access Flags bit.
+ * Hardware dirty bit management is enabled later,
+ * via capabilities.
+ */
+ mrs x9, ID_AA64MMFR1_EL1
+ and x9, x9, #0xf
+ cbz x9, 1f
+ orr x10, x10, #TCR_HA // hardware Access flag update
+1:
+#endif /* CONFIG_ARM64_HW_AFDBM */
+ msr tcr_el1, x10
+ ret // return to head.S
+ENDPROC(__cpu_setup)
diff --git a/arch/arm64/mm/ptdump_debugfs.c b/arch/arm64/mm/ptdump_debugfs.c
new file mode 100644
index 000000000..24d786fc3
--- /dev/null
+++ b/arch/arm64/mm/ptdump_debugfs.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+#include <asm/ptdump.h>
+
+static int ptdump_show(struct seq_file *m, void *v)
+{
+ struct ptdump_info *info = m->private;
+ ptdump_walk_pgd(m, info);
+ return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(ptdump);
+
+int ptdump_debugfs_register(struct ptdump_info *info, const char *name)
+{
+ struct dentry *pe;
+ pe = debugfs_create_file(name, 0400, NULL, info, &ptdump_fops);
+ return pe ? 0 : -ENOMEM;
+
+}
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-02 00:50:51 +0000