From ace9429bb58fd418f0c81d4c2835699bddf6bde6 Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Thu, 11 Apr 2024 10:27:49 +0200 Subject: Adding upstream version 6.6.15. Signed-off-by: Daniel Baumann --- kernel/dma/Kconfig | 272 +++++++ kernel/dma/Makefile | 12 + kernel/dma/coherent.c | 403 +++++++++++ kernel/dma/contiguous.c | 505 +++++++++++++ kernel/dma/debug.c | 1608 +++++++++++++++++++++++++++++++++++++++++ kernel/dma/debug.h | 130 ++++ kernel/dma/direct.c | 655 +++++++++++++++++ kernel/dma/direct.h | 127 ++++ kernel/dma/dummy.c | 38 + kernel/dma/map_benchmark.c | 358 +++++++++ kernel/dma/mapping.c | 841 +++++++++++++++++++++ kernel/dma/ops_helpers.c | 93 +++ kernel/dma/pool.c | 295 ++++++++ kernel/dma/remap.c | 70 ++ kernel/dma/swiotlb.c | 1725 ++++++++++++++++++++++++++++++++++++++++++++ 15 files changed, 7132 insertions(+) create mode 100644 kernel/dma/Kconfig create mode 100644 kernel/dma/Makefile create mode 100644 kernel/dma/coherent.c create mode 100644 kernel/dma/contiguous.c create mode 100644 kernel/dma/debug.c create mode 100644 kernel/dma/debug.h create mode 100644 kernel/dma/direct.c create mode 100644 kernel/dma/direct.h create mode 100644 kernel/dma/dummy.c create mode 100644 kernel/dma/map_benchmark.c create mode 100644 kernel/dma/mapping.c create mode 100644 kernel/dma/ops_helpers.c create mode 100644 kernel/dma/pool.c create mode 100644 kernel/dma/remap.c create mode 100644 kernel/dma/swiotlb.c (limited to 'kernel/dma') diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig new file mode 100644 index 000000000..f488997b0 --- /dev/null +++ b/kernel/dma/Kconfig @@ -0,0 +1,272 @@ +# SPDX-License-Identifier: GPL-2.0-only + +config NO_DMA + bool + +config HAS_DMA + bool + depends on !NO_DMA + default y + +config DMA_OPS + depends on HAS_DMA + bool + +# +# IOMMU drivers that can bypass the IOMMU code and optionally use the direct +# mapping fast path should select this option and set the dma_ops_bypass +# flag in struct device where applicable +# +config DMA_OPS_BYPASS + bool + +# Lets platform IOMMU driver choose between bypass and IOMMU +config ARCH_HAS_DMA_MAP_DIRECT + bool + +config NEED_SG_DMA_FLAGS + bool + +config NEED_SG_DMA_LENGTH + bool + +config NEED_DMA_MAP_STATE + bool + +config ARCH_DMA_ADDR_T_64BIT + def_bool 64BIT || PHYS_ADDR_T_64BIT + +config ARCH_HAS_DMA_SET_MASK + bool + +# +# Select this option if the architecture needs special handling for +# DMA_ATTR_WRITE_COMBINE. Normally the "uncached" mapping should be what +# people think of when saying write combine, so very few platforms should +# need to enable this. +# +config ARCH_HAS_DMA_WRITE_COMBINE + bool + +# +# Select if the architectures provides the arch_dma_mark_clean hook +# +config ARCH_HAS_DMA_MARK_CLEAN + bool + +config DMA_DECLARE_COHERENT + bool + +config ARCH_HAS_SETUP_DMA_OPS + bool + +config ARCH_HAS_TEARDOWN_DMA_OPS + bool + +config ARCH_HAS_SYNC_DMA_FOR_DEVICE + bool + +config ARCH_HAS_SYNC_DMA_FOR_CPU + bool + select NEED_DMA_MAP_STATE + +config ARCH_HAS_SYNC_DMA_FOR_CPU_ALL + bool + +config ARCH_HAS_DMA_PREP_COHERENT + bool + +config ARCH_HAS_FORCE_DMA_UNENCRYPTED + bool + +# +# Select this option if the architecture assumes DMA devices are coherent +# by default. +# +config ARCH_DMA_DEFAULT_COHERENT + bool + +config SWIOTLB + bool + select NEED_DMA_MAP_STATE + +config SWIOTLB_DYNAMIC + bool "Dynamic allocation of DMA bounce buffers" + default n + depends on SWIOTLB + help + This enables dynamic resizing of the software IO TLB. The kernel + starts with one memory pool at boot and it will allocate additional + pools as needed. To reduce run-time kernel memory requirements, you + may have to specify a smaller size of the initial pool using + "swiotlb=" on the kernel command line. + + If unsure, say N. + +config DMA_BOUNCE_UNALIGNED_KMALLOC + bool + depends on SWIOTLB + +config DMA_RESTRICTED_POOL + bool "DMA Restricted Pool" + depends on OF && OF_RESERVED_MEM && SWIOTLB + help + This enables support for restricted DMA pools which provide a level of + DMA memory protection on systems with limited hardware protection + capabilities, such as those lacking an IOMMU. + + For more information see + + and . + If unsure, say "n". + +# +# Should be selected if we can mmap non-coherent mappings to userspace. +# The only thing that is really required is a way to set an uncached bit +# in the pagetables +# +config DMA_NONCOHERENT_MMAP + default y if !MMU + bool + +config DMA_COHERENT_POOL + select GENERIC_ALLOCATOR + bool + +config DMA_GLOBAL_POOL + select DMA_DECLARE_COHERENT + bool + +config DMA_DIRECT_REMAP + bool + select DMA_COHERENT_POOL + select DMA_NONCOHERENT_MMAP + +config DMA_CMA + bool "DMA Contiguous Memory Allocator" + depends on HAVE_DMA_CONTIGUOUS && CMA + help + This enables the Contiguous Memory Allocator which allows drivers + to allocate big physically-contiguous blocks of memory for use with + hardware components that do not support I/O map nor scatter-gather. + + You can disable CMA by specifying "cma=0" on the kernel's command + line. + + For more information see . + If unsure, say "n". + +if DMA_CMA + +config DMA_NUMA_CMA + bool "Enable separate DMA Contiguous Memory Area for NUMA Node" + depends on NUMA + help + Enable this option to get numa CMA areas so that NUMA devices + can get local memory by DMA coherent APIs. + + You can set the size of pernuma CMA by specifying "cma_pernuma=size" + or set the node id and its size of CMA by specifying "numa_cma= + :size[,:size]" on the kernel's command line. + +comment "Default contiguous memory area size:" + +config CMA_SIZE_MBYTES + int "Size in Mega Bytes" + depends on !CMA_SIZE_SEL_PERCENTAGE + default 0 if X86 + default 16 + help + Defines the size (in MiB) of the default memory area for Contiguous + Memory Allocator. If the size of 0 is selected, CMA is disabled by + default, but it can be enabled by passing cma=size[MG] to the kernel. + + +config CMA_SIZE_PERCENTAGE + int "Percentage of total memory" + depends on !CMA_SIZE_SEL_MBYTES + default 0 if X86 + default 10 + help + Defines the size of the default memory area for Contiguous Memory + Allocator as a percentage of the total memory in the system. + If 0 percent is selected, CMA is disabled by default, but it can be + enabled by passing cma=size[MG] to the kernel. + +choice + prompt "Selected region size" + default CMA_SIZE_SEL_MBYTES + +config CMA_SIZE_SEL_MBYTES + bool "Use mega bytes value only" + +config CMA_SIZE_SEL_PERCENTAGE + bool "Use percentage value only" + +config CMA_SIZE_SEL_MIN + bool "Use lower value (minimum)" + +config CMA_SIZE_SEL_MAX + bool "Use higher value (maximum)" + +endchoice + +config CMA_ALIGNMENT + int "Maximum PAGE_SIZE order of alignment for contiguous buffers" + range 2 12 + default 8 + help + DMA mapping framework by default aligns all buffers to the smallest + PAGE_SIZE order which is greater than or equal to the requested buffer + size. This works well for buffers up to a few hundreds kilobytes, but + for larger buffers it just a memory waste. With this parameter you can + specify the maximum PAGE_SIZE order for contiguous buffers. Larger + buffers will be aligned only to this specified order. The order is + expressed as a power of two multiplied by the PAGE_SIZE. + + For example, if your system defaults to 4KiB pages, the order value + of 8 means that the buffers will be aligned up to 1MiB only. + + If unsure, leave the default value "8". + +endif + +config DMA_API_DEBUG + bool "Enable debugging of DMA-API usage" + select NEED_DMA_MAP_STATE + help + Enable this option to debug the use of the DMA API by device drivers. + With this option you will be able to detect common bugs in device + drivers like double-freeing of DMA mappings or freeing mappings that + were never allocated. + + This option causes a performance degradation. Use only if you want to + debug device drivers and dma interactions. + + If unsure, say N. + +config DMA_API_DEBUG_SG + bool "Debug DMA scatter-gather usage" + default y + depends on DMA_API_DEBUG + help + Perform extra checking that callers of dma_map_sg() have respected the + appropriate segment length/boundary limits for the given device when + preparing DMA scatterlists. + + This is particularly likely to have been overlooked in cases where the + dma_map_sg() API is used for general bulk mapping of pages rather than + preparing literal scatter-gather descriptors, where there is a risk of + unexpected behaviour from DMA API implementations if the scatterlist + is technically out-of-spec. + + If unsure, say N. + +config DMA_MAP_BENCHMARK + bool "Enable benchmarking of streaming DMA mapping" + depends on DEBUG_FS + help + Provides /sys/kernel/debug/dma_map_benchmark that helps with testing + performance of dma_(un)map_page. + + See tools/testing/selftests/dma/dma_map_benchmark.c diff --git a/kernel/dma/Makefile b/kernel/dma/Makefile new file mode 100644 index 000000000..21926e46e --- /dev/null +++ b/kernel/dma/Makefile @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_HAS_DMA) += mapping.o direct.o +obj-$(CONFIG_DMA_OPS) += ops_helpers.o +obj-$(CONFIG_DMA_OPS) += dummy.o +obj-$(CONFIG_DMA_CMA) += contiguous.o +obj-$(CONFIG_DMA_DECLARE_COHERENT) += coherent.o +obj-$(CONFIG_DMA_API_DEBUG) += debug.o +obj-$(CONFIG_SWIOTLB) += swiotlb.o +obj-$(CONFIG_DMA_COHERENT_POOL) += pool.o +obj-$(CONFIG_MMU) += remap.o +obj-$(CONFIG_DMA_MAP_BENCHMARK) += map_benchmark.o diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c new file mode 100644 index 000000000..ff5683a57 --- /dev/null +++ b/kernel/dma/coherent.c @@ -0,0 +1,403 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Coherent per-device memory handling. + * Borrowed from i386 + */ +#include +#include +#include +#include +#include +#include + +struct dma_coherent_mem { + void *virt_base; + dma_addr_t device_base; + unsigned long pfn_base; + int size; + unsigned long *bitmap; + spinlock_t spinlock; + bool use_dev_dma_pfn_offset; +}; + +static inline struct dma_coherent_mem *dev_get_coherent_memory(struct device *dev) +{ + if (dev && dev->dma_mem) + return dev->dma_mem; + return NULL; +} + +static inline dma_addr_t dma_get_device_base(struct device *dev, + struct dma_coherent_mem * mem) +{ + if (mem->use_dev_dma_pfn_offset) + return phys_to_dma(dev, PFN_PHYS(mem->pfn_base)); + return mem->device_base; +} + +static struct dma_coherent_mem *dma_init_coherent_memory(phys_addr_t phys_addr, + dma_addr_t device_addr, size_t size, bool use_dma_pfn_offset) +{ + struct dma_coherent_mem *dma_mem; + int pages = size >> PAGE_SHIFT; + void *mem_base; + + if (!size) + return ERR_PTR(-EINVAL); + + mem_base = memremap(phys_addr, size, MEMREMAP_WC); + if (!mem_base) + return ERR_PTR(-EINVAL); + + dma_mem = kzalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL); + if (!dma_mem) + goto out_unmap_membase; + dma_mem->bitmap = bitmap_zalloc(pages, GFP_KERNEL); + if (!dma_mem->bitmap) + goto out_free_dma_mem; + + dma_mem->virt_base = mem_base; + dma_mem->device_base = device_addr; + dma_mem->pfn_base = PFN_DOWN(phys_addr); + dma_mem->size = pages; + dma_mem->use_dev_dma_pfn_offset = use_dma_pfn_offset; + spin_lock_init(&dma_mem->spinlock); + + return dma_mem; + +out_free_dma_mem: + kfree(dma_mem); +out_unmap_membase: + memunmap(mem_base); + pr_err("Reserved memory: failed to init DMA memory pool at %pa, size %zd MiB\n", + &phys_addr, size / SZ_1M); + return ERR_PTR(-ENOMEM); +} + +static void _dma_release_coherent_memory(struct dma_coherent_mem *mem) +{ + if (!mem) + return; + + memunmap(mem->virt_base); + bitmap_free(mem->bitmap); + kfree(mem); +} + +static int dma_assign_coherent_memory(struct device *dev, + struct dma_coherent_mem *mem) +{ + if (!dev) + return -ENODEV; + + if (dev->dma_mem) + return -EBUSY; + + dev->dma_mem = mem; + return 0; +} + +/* + * Declare a region of memory to be handed out by dma_alloc_coherent() when it + * is asked for coherent memory for this device. This shall only be used + * from platform code, usually based on the device tree description. + * + * phys_addr is the CPU physical address to which the memory is currently + * assigned (this will be ioremapped so the CPU can access the region). + * + * device_addr is the DMA address the device needs to be programmed with to + * actually address this memory (this will be handed out as the dma_addr_t in + * dma_alloc_coherent()). + * + * size is the size of the area (must be a multiple of PAGE_SIZE). + * + * As a simplification for the platforms, only *one* such region of memory may + * be declared per device. + */ +int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, + dma_addr_t device_addr, size_t size) +{ + struct dma_coherent_mem *mem; + int ret; + + mem = dma_init_coherent_memory(phys_addr, device_addr, size, false); + if (IS_ERR(mem)) + return PTR_ERR(mem); + + ret = dma_assign_coherent_memory(dev, mem); + if (ret) + _dma_release_coherent_memory(mem); + return ret; +} + +void dma_release_coherent_memory(struct device *dev) +{ + if (dev) { + _dma_release_coherent_memory(dev->dma_mem); + dev->dma_mem = NULL; + } +} + +static void *__dma_alloc_from_coherent(struct device *dev, + struct dma_coherent_mem *mem, + ssize_t size, dma_addr_t *dma_handle) +{ + int order = get_order(size); + unsigned long flags; + int pageno; + void *ret; + + spin_lock_irqsave(&mem->spinlock, flags); + + if (unlikely(size > ((dma_addr_t)mem->size << PAGE_SHIFT))) + goto err; + + pageno = bitmap_find_free_region(mem->bitmap, mem->size, order); + if (unlikely(pageno < 0)) + goto err; + + /* + * Memory was found in the coherent area. + */ + *dma_handle = dma_get_device_base(dev, mem) + + ((dma_addr_t)pageno << PAGE_SHIFT); + ret = mem->virt_base + ((dma_addr_t)pageno << PAGE_SHIFT); + spin_unlock_irqrestore(&mem->spinlock, flags); + memset(ret, 0, size); + return ret; +err: + spin_unlock_irqrestore(&mem->spinlock, flags); + return NULL; +} + +/** + * dma_alloc_from_dev_coherent() - allocate memory from device coherent pool + * @dev: device from which we allocate memory + * @size: size of requested memory area + * @dma_handle: This will be filled with the correct dma handle + * @ret: This pointer will be filled with the virtual address + * to allocated area. + * + * This function should be only called from per-arch dma_alloc_coherent() + * to support allocation from per-device coherent memory pools. + * + * Returns 0 if dma_alloc_coherent should continue with allocating from + * generic memory areas, or !0 if dma_alloc_coherent should return @ret. + */ +int dma_alloc_from_dev_coherent(struct device *dev, ssize_t size, + dma_addr_t *dma_handle, void **ret) +{ + struct dma_coherent_mem *mem = dev_get_coherent_memory(dev); + + if (!mem) + return 0; + + *ret = __dma_alloc_from_coherent(dev, mem, size, dma_handle); + return 1; +} + +static int __dma_release_from_coherent(struct dma_coherent_mem *mem, + int order, void *vaddr) +{ + if (mem && vaddr >= mem->virt_base && vaddr < + (mem->virt_base + ((dma_addr_t)mem->size << PAGE_SHIFT))) { + int page = (vaddr - mem->virt_base) >> PAGE_SHIFT; + unsigned long flags; + + spin_lock_irqsave(&mem->spinlock, flags); + bitmap_release_region(mem->bitmap, page, order); + spin_unlock_irqrestore(&mem->spinlock, flags); + return 1; + } + return 0; +} + +/** + * dma_release_from_dev_coherent() - free memory to device coherent memory pool + * @dev: device from which the memory was allocated + * @order: the order of pages allocated + * @vaddr: virtual address of allocated pages + * + * This checks whether the memory was allocated from the per-device + * coherent memory pool and if so, releases that memory. + * + * Returns 1 if we correctly released the memory, or 0 if the caller should + * proceed with releasing memory from generic pools. + */ +int dma_release_from_dev_coherent(struct device *dev, int order, void *vaddr) +{ + struct dma_coherent_mem *mem = dev_get_coherent_memory(dev); + + return __dma_release_from_coherent(mem, order, vaddr); +} + +static int __dma_mmap_from_coherent(struct dma_coherent_mem *mem, + struct vm_area_struct *vma, void *vaddr, size_t size, int *ret) +{ + if (mem && vaddr >= mem->virt_base && vaddr + size <= + (mem->virt_base + ((dma_addr_t)mem->size << PAGE_SHIFT))) { + unsigned long off = vma->vm_pgoff; + int start = (vaddr - mem->virt_base) >> PAGE_SHIFT; + unsigned long user_count = vma_pages(vma); + int count = PAGE_ALIGN(size) >> PAGE_SHIFT; + + *ret = -ENXIO; + if (off < count && user_count <= count - off) { + unsigned long pfn = mem->pfn_base + start + off; + *ret = remap_pfn_range(vma, vma->vm_start, pfn, + user_count << PAGE_SHIFT, + vma->vm_page_prot); + } + return 1; + } + return 0; +} + +/** + * dma_mmap_from_dev_coherent() - mmap memory from the device coherent pool + * @dev: device from which the memory was allocated + * @vma: vm_area for the userspace memory + * @vaddr: cpu address returned by dma_alloc_from_dev_coherent + * @size: size of the memory buffer allocated + * @ret: result from remap_pfn_range() + * + * This checks whether the memory was allocated from the per-device + * coherent memory pool and if so, maps that memory to the provided vma. + * + * Returns 1 if @vaddr belongs to the device coherent pool and the caller + * should return @ret, or 0 if they should proceed with mapping memory from + * generic areas. + */ +int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma, + void *vaddr, size_t size, int *ret) +{ + struct dma_coherent_mem *mem = dev_get_coherent_memory(dev); + + return __dma_mmap_from_coherent(mem, vma, vaddr, size, ret); +} + +#ifdef CONFIG_DMA_GLOBAL_POOL +static struct dma_coherent_mem *dma_coherent_default_memory __ro_after_init; + +void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size, + dma_addr_t *dma_handle) +{ + if (!dma_coherent_default_memory) + return NULL; + + return __dma_alloc_from_coherent(dev, dma_coherent_default_memory, size, + dma_handle); +} + +int dma_release_from_global_coherent(int order, void *vaddr) +{ + if (!dma_coherent_default_memory) + return 0; + + return __dma_release_from_coherent(dma_coherent_default_memory, order, + vaddr); +} + +int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *vaddr, + size_t size, int *ret) +{ + if (!dma_coherent_default_memory) + return 0; + + return __dma_mmap_from_coherent(dma_coherent_default_memory, vma, + vaddr, size, ret); +} + +int dma_init_global_coherent(phys_addr_t phys_addr, size_t size) +{ + struct dma_coherent_mem *mem; + + mem = dma_init_coherent_memory(phys_addr, phys_addr, size, true); + if (IS_ERR(mem)) + return PTR_ERR(mem); + dma_coherent_default_memory = mem; + pr_info("DMA: default coherent area is set\n"); + return 0; +} +#endif /* CONFIG_DMA_GLOBAL_POOL */ + +/* + * Support for reserved memory regions defined in device tree + */ +#ifdef CONFIG_OF_RESERVED_MEM +#include +#include +#include + +#ifdef CONFIG_DMA_GLOBAL_POOL +static struct reserved_mem *dma_reserved_default_memory __initdata; +#endif + +static int rmem_dma_device_init(struct reserved_mem *rmem, struct device *dev) +{ + if (!rmem->priv) { + struct dma_coherent_mem *mem; + + mem = dma_init_coherent_memory(rmem->base, rmem->base, + rmem->size, true); + if (IS_ERR(mem)) + return PTR_ERR(mem); + rmem->priv = mem; + } + dma_assign_coherent_memory(dev, rmem->priv); + return 0; +} + +static void rmem_dma_device_release(struct reserved_mem *rmem, + struct device *dev) +{ + if (dev) + dev->dma_mem = NULL; +} + +static const struct reserved_mem_ops rmem_dma_ops = { + .device_init = rmem_dma_device_init, + .device_release = rmem_dma_device_release, +}; + +static int __init rmem_dma_setup(struct reserved_mem *rmem) +{ + unsigned long node = rmem->fdt_node; + + if (of_get_flat_dt_prop(node, "reusable", NULL)) + return -EINVAL; + +#ifdef CONFIG_ARM + if (!of_get_flat_dt_prop(node, "no-map", NULL)) { + pr_err("Reserved memory: regions without no-map are not yet supported\n"); + return -EINVAL; + } +#endif + +#ifdef CONFIG_DMA_GLOBAL_POOL + if (of_get_flat_dt_prop(node, "linux,dma-default", NULL)) { + WARN(dma_reserved_default_memory, + "Reserved memory: region for default DMA coherent area is redefined\n"); + dma_reserved_default_memory = rmem; + } +#endif + + rmem->ops = &rmem_dma_ops; + pr_info("Reserved memory: created DMA memory pool at %pa, size %ld MiB\n", + &rmem->base, (unsigned long)rmem->size / SZ_1M); + return 0; +} + +#ifdef CONFIG_DMA_GLOBAL_POOL +static int __init dma_init_reserved_memory(void) +{ + if (!dma_reserved_default_memory) + return -ENOMEM; + return dma_init_global_coherent(dma_reserved_default_memory->base, + dma_reserved_default_memory->size); +} +core_initcall(dma_init_reserved_memory); +#endif /* CONFIG_DMA_GLOBAL_POOL */ + +RESERVEDMEM_OF_DECLARE(dma, "shared-dma-pool", rmem_dma_setup); +#endif diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c new file mode 100644 index 000000000..f005c66f3 --- /dev/null +++ b/kernel/dma/contiguous.c @@ -0,0 +1,505 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Contiguous Memory Allocator for DMA mapping framework + * Copyright (c) 2010-2011 by Samsung Electronics. + * Written by: + * Marek Szyprowski + * Michal Nazarewicz + * + * Contiguous Memory Allocator + * + * The Contiguous Memory Allocator (CMA) makes it possible to + * allocate big contiguous chunks of memory after the system has + * booted. + * + * Why is it needed? + * + * Various devices on embedded systems have no scatter-getter and/or + * IO map support and require contiguous blocks of memory to + * operate. They include devices such as cameras, hardware video + * coders, etc. + * + * Such devices often require big memory buffers (a full HD frame + * is, for instance, more than 2 mega pixels large, i.e. more than 6 + * MB of memory), which makes mechanisms such as kmalloc() or + * alloc_page() ineffective. + * + * At the same time, a solution where a big memory region is + * reserved for a device is suboptimal since often more memory is + * reserved then strictly required and, moreover, the memory is + * inaccessible to page system even if device drivers don't use it. + * + * CMA tries to solve this issue by operating on memory regions + * where only movable pages can be allocated from. This way, kernel + * can use the memory for pagecache and when device driver requests + * it, allocated pages can be migrated. + */ + +#define pr_fmt(fmt) "cma: " fmt + +#ifdef CONFIG_CMA_DEBUG +#ifndef DEBUG +# define DEBUG +#endif +#endif + +#include + +#include +#include +#include +#include +#include +#include + +#ifdef CONFIG_CMA_SIZE_MBYTES +#define CMA_SIZE_MBYTES CONFIG_CMA_SIZE_MBYTES +#else +#define CMA_SIZE_MBYTES 0 +#endif + +struct cma *dma_contiguous_default_area; + +/* + * Default global CMA area size can be defined in kernel's .config. + * This is useful mainly for distro maintainers to create a kernel + * that works correctly for most supported systems. + * The size can be set in bytes or as a percentage of the total memory + * in the system. + * + * Users, who want to set the size of global CMA area for their system + * should use cma= kernel parameter. + */ +static const phys_addr_t size_bytes __initconst = + (phys_addr_t)CMA_SIZE_MBYTES * SZ_1M; +static phys_addr_t size_cmdline __initdata = -1; +static phys_addr_t base_cmdline __initdata; +static phys_addr_t limit_cmdline __initdata; + +static int __init early_cma(char *p) +{ + if (!p) { + pr_err("Config string not provided\n"); + return -EINVAL; + } + + size_cmdline = memparse(p, &p); + if (*p != '@') + return 0; + base_cmdline = memparse(p + 1, &p); + if (*p != '-') { + limit_cmdline = base_cmdline + size_cmdline; + return 0; + } + limit_cmdline = memparse(p + 1, &p); + + return 0; +} +early_param("cma", early_cma); + +#ifdef CONFIG_DMA_NUMA_CMA + +static struct cma *dma_contiguous_numa_area[MAX_NUMNODES]; +static phys_addr_t numa_cma_size[MAX_NUMNODES] __initdata; +static struct cma *dma_contiguous_pernuma_area[MAX_NUMNODES]; +static phys_addr_t pernuma_size_bytes __initdata; + +static int __init early_numa_cma(char *p) +{ + int nid, count = 0; + unsigned long tmp; + char *s = p; + + while (*s) { + if (sscanf(s, "%lu%n", &tmp, &count) != 1) + break; + + if (s[count] == ':') { + if (tmp >= MAX_NUMNODES) + break; + nid = array_index_nospec(tmp, MAX_NUMNODES); + + s += count + 1; + tmp = memparse(s, &s); + numa_cma_size[nid] = tmp; + + if (*s == ',') + s++; + else + break; + } else + break; + } + + return 0; +} +early_param("numa_cma", early_numa_cma); + +static int __init early_cma_pernuma(char *p) +{ + pernuma_size_bytes = memparse(p, &p); + return 0; +} +early_param("cma_pernuma", early_cma_pernuma); +#endif + +#ifdef CONFIG_CMA_SIZE_PERCENTAGE + +static phys_addr_t __init __maybe_unused cma_early_percent_memory(void) +{ + unsigned long total_pages = PHYS_PFN(memblock_phys_mem_size()); + + return (total_pages * CONFIG_CMA_SIZE_PERCENTAGE / 100) << PAGE_SHIFT; +} + +#else + +static inline __maybe_unused phys_addr_t cma_early_percent_memory(void) +{ + return 0; +} + +#endif + +#ifdef CONFIG_DMA_NUMA_CMA +static void __init dma_numa_cma_reserve(void) +{ + int nid; + + for_each_node(nid) { + int ret; + char name[CMA_MAX_NAME]; + struct cma **cma; + + if (!node_online(nid)) { + if (pernuma_size_bytes || numa_cma_size[nid]) + pr_warn("invalid node %d specified\n", nid); + continue; + } + + if (pernuma_size_bytes) { + + cma = &dma_contiguous_pernuma_area[nid]; + snprintf(name, sizeof(name), "pernuma%d", nid); + ret = cma_declare_contiguous_nid(0, pernuma_size_bytes, 0, 0, + 0, false, name, cma, nid); + if (ret) + pr_warn("%s: reservation failed: err %d, node %d", __func__, + ret, nid); + } + + if (numa_cma_size[nid]) { + + cma = &dma_contiguous_numa_area[nid]; + snprintf(name, sizeof(name), "numa%d", nid); + ret = cma_declare_contiguous_nid(0, numa_cma_size[nid], 0, 0, 0, false, + name, cma, nid); + if (ret) + pr_warn("%s: reservation failed: err %d, node %d", __func__, + ret, nid); + } + } +} +#else +static inline void __init dma_numa_cma_reserve(void) +{ +} +#endif + +/** + * dma_contiguous_reserve() - reserve area(s) for contiguous memory handling + * @limit: End address of the reserved memory (optional, 0 for any). + * + * This function reserves memory from early allocator. It should be + * called by arch specific code once the early allocator (memblock or bootmem) + * has been activated and all other subsystems have already allocated/reserved + * memory. + */ +void __init dma_contiguous_reserve(phys_addr_t limit) +{ + phys_addr_t selected_size = 0; + phys_addr_t selected_base = 0; + phys_addr_t selected_limit = limit; + bool fixed = false; + + dma_numa_cma_reserve(); + + pr_debug("%s(limit %08lx)\n", __func__, (unsigned long)limit); + + if (size_cmdline != -1) { + selected_size = size_cmdline; + selected_base = base_cmdline; + selected_limit = min_not_zero(limit_cmdline, limit); + if (base_cmdline + size_cmdline == limit_cmdline) + fixed = true; + } else { +#ifdef CONFIG_CMA_SIZE_SEL_MBYTES + selected_size = size_bytes; +#elif defined(CONFIG_CMA_SIZE_SEL_PERCENTAGE) + selected_size = cma_early_percent_memory(); +#elif defined(CONFIG_CMA_SIZE_SEL_MIN) + selected_size = min(size_bytes, cma_early_percent_memory()); +#elif defined(CONFIG_CMA_SIZE_SEL_MAX) + selected_size = max(size_bytes, cma_early_percent_memory()); +#endif + } + + if (selected_size && !dma_contiguous_default_area) { + pr_debug("%s: reserving %ld MiB for global area\n", __func__, + (unsigned long)selected_size / SZ_1M); + + dma_contiguous_reserve_area(selected_size, selected_base, + selected_limit, + &dma_contiguous_default_area, + fixed); + } +} + +void __weak +dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) +{ +} + +/** + * dma_contiguous_reserve_area() - reserve custom contiguous area + * @size: Size of the reserved area (in bytes), + * @base: Base address of the reserved area optional, use 0 for any + * @limit: End address of the reserved memory (optional, 0 for any). + * @res_cma: Pointer to store the created cma region. + * @fixed: hint about where to place the reserved area + * + * This function reserves memory from early allocator. It should be + * called by arch specific code once the early allocator (memblock or bootmem) + * has been activated and all other subsystems have already allocated/reserved + * memory. This function allows to create custom reserved areas for specific + * devices. + * + * If @fixed is true, reserve contiguous area at exactly @base. If false, + * reserve in range from @base to @limit. + */ +int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base, + phys_addr_t limit, struct cma **res_cma, + bool fixed) +{ + int ret; + + ret = cma_declare_contiguous(base, size, limit, 0, 0, fixed, + "reserved", res_cma); + if (ret) + return ret; + + /* Architecture specific contiguous memory fixup. */ + dma_contiguous_early_fixup(cma_get_base(*res_cma), + cma_get_size(*res_cma)); + + return 0; +} + +/** + * dma_alloc_from_contiguous() - allocate pages from contiguous area + * @dev: Pointer to device for which the allocation is performed. + * @count: Requested number of pages. + * @align: Requested alignment of pages (in PAGE_SIZE order). + * @no_warn: Avoid printing message about failed allocation. + * + * This function allocates memory buffer for specified device. It uses + * device specific contiguous memory area if available or the default + * global one. Requires architecture specific dev_get_cma_area() helper + * function. + */ +struct page *dma_alloc_from_contiguous(struct device *dev, size_t count, + unsigned int align, bool no_warn) +{ + if (align > CONFIG_CMA_ALIGNMENT) + align = CONFIG_CMA_ALIGNMENT; + + return cma_alloc(dev_get_cma_area(dev), count, align, no_warn); +} + +/** + * dma_release_from_contiguous() - release allocated pages + * @dev: Pointer to device for which the pages were allocated. + * @pages: Allocated pages. + * @count: Number of allocated pages. + * + * This function releases memory allocated by dma_alloc_from_contiguous(). + * It returns false when provided pages do not belong to contiguous area and + * true otherwise. + */ +bool dma_release_from_contiguous(struct device *dev, struct page *pages, + int count) +{ + return cma_release(dev_get_cma_area(dev), pages, count); +} + +static struct page *cma_alloc_aligned(struct cma *cma, size_t size, gfp_t gfp) +{ + unsigned int align = min(get_order(size), CONFIG_CMA_ALIGNMENT); + + return cma_alloc(cma, size >> PAGE_SHIFT, align, gfp & __GFP_NOWARN); +} + +/** + * dma_alloc_contiguous() - allocate contiguous pages + * @dev: Pointer to device for which the allocation is performed. + * @size: Requested allocation size. + * @gfp: Allocation flags. + * + * tries to use device specific contiguous memory area if available, or it + * tries to use per-numa cma, if the allocation fails, it will fallback to + * try default global one. + * + * Note that it bypass one-page size of allocations from the per-numa and + * global area as the addresses within one page are always contiguous, so + * there is no need to waste CMA pages for that kind; it also helps reduce + * fragmentations. + */ +struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp) +{ +#ifdef CONFIG_DMA_NUMA_CMA + int nid = dev_to_node(dev); +#endif + + /* CMA can be used only in the context which permits sleeping */ + if (!gfpflags_allow_blocking(gfp)) + return NULL; + if (dev->cma_area) + return cma_alloc_aligned(dev->cma_area, size, gfp); + if (size <= PAGE_SIZE) + return NULL; + +#ifdef CONFIG_DMA_NUMA_CMA + if (nid != NUMA_NO_NODE && !(gfp & (GFP_DMA | GFP_DMA32))) { + struct cma *cma = dma_contiguous_pernuma_area[nid]; + struct page *page; + + if (cma) { + page = cma_alloc_aligned(cma, size, gfp); + if (page) + return page; + } + + cma = dma_contiguous_numa_area[nid]; + if (cma) { + page = cma_alloc_aligned(cma, size, gfp); + if (page) + return page; + } + } +#endif + if (!dma_contiguous_default_area) + return NULL; + + return cma_alloc_aligned(dma_contiguous_default_area, size, gfp); +} + +/** + * dma_free_contiguous() - release allocated pages + * @dev: Pointer to device for which the pages were allocated. + * @page: Pointer to the allocated pages. + * @size: Size of allocated pages. + * + * This function releases memory allocated by dma_alloc_contiguous(). As the + * cma_release returns false when provided pages do not belong to contiguous + * area and true otherwise, this function then does a fallback __free_pages() + * upon a false-return. + */ +void dma_free_contiguous(struct device *dev, struct page *page, size_t size) +{ + unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; + + /* if dev has its own cma, free page from there */ + if (dev->cma_area) { + if (cma_release(dev->cma_area, page, count)) + return; + } else { + /* + * otherwise, page is from either per-numa cma or default cma + */ +#ifdef CONFIG_DMA_NUMA_CMA + if (cma_release(dma_contiguous_pernuma_area[page_to_nid(page)], + page, count)) + return; + if (cma_release(dma_contiguous_numa_area[page_to_nid(page)], + page, count)) + return; +#endif + if (cma_release(dma_contiguous_default_area, page, count)) + return; + } + + /* not in any cma, free from buddy */ + __free_pages(page, get_order(size)); +} + +/* + * Support for reserved memory regions defined in device tree + */ +#ifdef CONFIG_OF_RESERVED_MEM +#include +#include +#include + +#undef pr_fmt +#define pr_fmt(fmt) fmt + +static int rmem_cma_device_init(struct reserved_mem *rmem, struct device *dev) +{ + dev->cma_area = rmem->priv; + return 0; +} + +static void rmem_cma_device_release(struct reserved_mem *rmem, + struct device *dev) +{ + dev->cma_area = NULL; +} + +static const struct reserved_mem_ops rmem_cma_ops = { + .device_init = rmem_cma_device_init, + .device_release = rmem_cma_device_release, +}; + +static int __init rmem_cma_setup(struct reserved_mem *rmem) +{ + unsigned long node = rmem->fdt_node; + bool default_cma = of_get_flat_dt_prop(node, "linux,cma-default", NULL); + struct cma *cma; + int err; + + if (size_cmdline != -1 && default_cma) { + pr_info("Reserved memory: bypass %s node, using cmdline CMA params instead\n", + rmem->name); + return -EBUSY; + } + + if (!of_get_flat_dt_prop(node, "reusable", NULL) || + of_get_flat_dt_prop(node, "no-map", NULL)) + return -EINVAL; + + if (!IS_ALIGNED(rmem->base | rmem->size, CMA_MIN_ALIGNMENT_BYTES)) { + pr_err("Reserved memory: incorrect alignment of CMA region\n"); + return -EINVAL; + } + + err = cma_init_reserved_mem(rmem->base, rmem->size, 0, rmem->name, &cma); + if (err) { + pr_err("Reserved memory: unable to setup CMA region\n"); + return err; + } + /* Architecture specific contiguous memory fixup. */ + dma_contiguous_early_fixup(rmem->base, rmem->size); + + if (default_cma) + dma_contiguous_default_area = cma; + + rmem->ops = &rmem_cma_ops; + rmem->priv = cma; + + pr_info("Reserved memory: created CMA memory pool at %pa, size %ld MiB\n", + &rmem->base, (unsigned long)rmem->size / SZ_1M); + + return 0; +} +RESERVEDMEM_OF_DECLARE(cma, "shared-dma-pool", rmem_cma_setup); +#endif diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c new file mode 100644 index 000000000..06366acd2 --- /dev/null +++ b/kernel/dma/debug.c @@ -0,0 +1,1608 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2008 Advanced Micro Devices, Inc. + * + * Author: Joerg Roedel + */ + +#define pr_fmt(fmt) "DMA-API: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "debug.h" + +#define HASH_SIZE 16384ULL +#define HASH_FN_SHIFT 13 +#define HASH_FN_MASK (HASH_SIZE - 1) + +#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16) +/* If the pool runs out, add this many new entries at once */ +#define DMA_DEBUG_DYNAMIC_ENTRIES (PAGE_SIZE / sizeof(struct dma_debug_entry)) + +enum { + dma_debug_single, + dma_debug_sg, + dma_debug_coherent, + dma_debug_resource, +}; + +enum map_err_types { + MAP_ERR_CHECK_NOT_APPLICABLE, + MAP_ERR_NOT_CHECKED, + MAP_ERR_CHECKED, +}; + +#define DMA_DEBUG_STACKTRACE_ENTRIES 5 + +/** + * struct dma_debug_entry - track a dma_map* or dma_alloc_coherent mapping + * @list: node on pre-allocated free_entries list + * @dev: 'dev' argument to dma_map_{page|single|sg} or dma_alloc_coherent + * @dev_addr: dma address + * @size: length of the mapping + * @type: single, page, sg, coherent + * @direction: enum dma_data_direction + * @sg_call_ents: 'nents' from dma_map_sg + * @sg_mapped_ents: 'mapped_ents' from dma_map_sg + * @pfn: page frame of the start address + * @offset: offset of mapping relative to pfn + * @map_err_type: track whether dma_mapping_error() was checked + * @stacktrace: support backtraces when a violation is detected + */ +struct dma_debug_entry { + struct list_head list; + struct device *dev; + u64 dev_addr; + u64 size; + int type; + int direction; + int sg_call_ents; + int sg_mapped_ents; + unsigned long pfn; + size_t offset; + enum map_err_types map_err_type; +#ifdef CONFIG_STACKTRACE + unsigned int stack_len; + unsigned long stack_entries[DMA_DEBUG_STACKTRACE_ENTRIES]; +#endif +} ____cacheline_aligned_in_smp; + +typedef bool (*match_fn)(struct dma_debug_entry *, struct dma_debug_entry *); + +struct hash_bucket { + struct list_head list; + spinlock_t lock; +}; + +/* Hash list to save the allocated dma addresses */ +static struct hash_bucket dma_entry_hash[HASH_SIZE]; +/* List of pre-allocated dma_debug_entry's */ +static LIST_HEAD(free_entries); +/* Lock for the list above */ +static DEFINE_SPINLOCK(free_entries_lock); + +/* Global disable flag - will be set in case of an error */ +static bool global_disable __read_mostly; + +/* Early initialization disable flag, set at the end of dma_debug_init */ +static bool dma_debug_initialized __read_mostly; + +static inline bool dma_debug_disabled(void) +{ + return global_disable || !dma_debug_initialized; +} + +/* Global error count */ +static u32 error_count; + +/* Global error show enable*/ +static u32 show_all_errors __read_mostly; +/* Number of errors to show */ +static u32 show_num_errors = 1; + +static u32 num_free_entries; +static u32 min_free_entries; +static u32 nr_total_entries; + +/* number of preallocated entries requested by kernel cmdline */ +static u32 nr_prealloc_entries = PREALLOC_DMA_DEBUG_ENTRIES; + +/* per-driver filter related state */ + +#define NAME_MAX_LEN 64 + +static char current_driver_name[NAME_MAX_LEN] __read_mostly; +static struct device_driver *current_driver __read_mostly; + +static DEFINE_RWLOCK(driver_name_lock); + +static const char *const maperr2str[] = { + [MAP_ERR_CHECK_NOT_APPLICABLE] = "dma map error check not applicable", + [MAP_ERR_NOT_CHECKED] = "dma map error not checked", + [MAP_ERR_CHECKED] = "dma map error checked", +}; + +static const char *type2name[] = { + [dma_debug_single] = "single", + [dma_debug_sg] = "scather-gather", + [dma_debug_coherent] = "coherent", + [dma_debug_resource] = "resource", +}; + +static const char *dir2name[] = { + [DMA_BIDIRECTIONAL] = "DMA_BIDIRECTIONAL", + [DMA_TO_DEVICE] = "DMA_TO_DEVICE", + [DMA_FROM_DEVICE] = "DMA_FROM_DEVICE", + [DMA_NONE] = "DMA_NONE", +}; + +/* + * The access to some variables in this macro is racy. We can't use atomic_t + * here because all these variables are exported to debugfs. Some of them even + * writeable. This is also the reason why a lock won't help much. But anyway, + * the races are no big deal. Here is why: + * + * error_count: the addition is racy, but the worst thing that can happen is + * that we don't count some errors + * show_num_errors: the subtraction is racy. Also no big deal because in + * worst case this will result in one warning more in the + * system log than the user configured. This variable is + * writeable via debugfs. + */ +static inline void dump_entry_trace(struct dma_debug_entry *entry) +{ +#ifdef CONFIG_STACKTRACE + if (entry) { + pr_warn("Mapped at:\n"); + stack_trace_print(entry->stack_entries, entry->stack_len, 0); + } +#endif +} + +static bool driver_filter(struct device *dev) +{ + struct device_driver *drv; + unsigned long flags; + bool ret; + + /* driver filter off */ + if (likely(!current_driver_name[0])) + return true; + + /* driver filter on and initialized */ + if (current_driver && dev && dev->driver == current_driver) + return true; + + /* driver filter on, but we can't filter on a NULL device... */ + if (!dev) + return false; + + if (current_driver || !current_driver_name[0]) + return false; + + /* driver filter on but not yet initialized */ + drv = dev->driver; + if (!drv) + return false; + + /* lock to protect against change of current_driver_name */ + read_lock_irqsave(&driver_name_lock, flags); + + ret = false; + if (drv->name && + strncmp(current_driver_name, drv->name, NAME_MAX_LEN - 1) == 0) { + current_driver = drv; + ret = true; + } + + read_unlock_irqrestore(&driver_name_lock, flags); + + return ret; +} + +#define err_printk(dev, entry, format, arg...) do { \ + error_count += 1; \ + if (driver_filter(dev) && \ + (show_all_errors || show_num_errors > 0)) { \ + WARN(1, pr_fmt("%s %s: ") format, \ + dev ? dev_driver_string(dev) : "NULL", \ + dev ? dev_name(dev) : "NULL", ## arg); \ + dump_entry_trace(entry); \ + } \ + if (!show_all_errors && show_num_errors > 0) \ + show_num_errors -= 1; \ + } while (0); + +/* + * Hash related functions + * + * Every DMA-API request is saved into a struct dma_debug_entry. To + * have quick access to these structs they are stored into a hash. + */ +static int hash_fn(struct dma_debug_entry *entry) +{ + /* + * Hash function is based on the dma address. + * We use bits 20-27 here as the index into the hash + */ + return (entry->dev_addr >> HASH_FN_SHIFT) & HASH_FN_MASK; +} + +/* + * Request exclusive access to a hash bucket for a given dma_debug_entry. + */ +static struct hash_bucket *get_hash_bucket(struct dma_debug_entry *entry, + unsigned long *flags) + __acquires(&dma_entry_hash[idx].lock) +{ + int idx = hash_fn(entry); + unsigned long __flags; + + spin_lock_irqsave(&dma_entry_hash[idx].lock, __flags); + *flags = __flags; + return &dma_entry_hash[idx]; +} + +/* + * Give up exclusive access to the hash bucket + */ +static void put_hash_bucket(struct hash_bucket *bucket, + unsigned long flags) + __releases(&bucket->lock) +{ + spin_unlock_irqrestore(&bucket->lock, flags); +} + +static bool exact_match(struct dma_debug_entry *a, struct dma_debug_entry *b) +{ + return ((a->dev_addr == b->dev_addr) && + (a->dev == b->dev)) ? true : false; +} + +static bool containing_match(struct dma_debug_entry *a, + struct dma_debug_entry *b) +{ + if (a->dev != b->dev) + return false; + + if ((b->dev_addr <= a->dev_addr) && + ((b->dev_addr + b->size) >= (a->dev_addr + a->size))) + return true; + + return false; +} + +/* + * Search a given entry in the hash bucket list + */ +static struct dma_debug_entry *__hash_bucket_find(struct hash_bucket *bucket, + struct dma_debug_entry *ref, + match_fn match) +{ + struct dma_debug_entry *entry, *ret = NULL; + int matches = 0, match_lvl, last_lvl = -1; + + list_for_each_entry(entry, &bucket->list, list) { + if (!match(ref, entry)) + continue; + + /* + * Some drivers map the same physical address multiple + * times. Without a hardware IOMMU this results in the + * same device addresses being put into the dma-debug + * hash multiple times too. This can result in false + * positives being reported. Therefore we implement a + * best-fit algorithm here which returns the entry from + * the hash which fits best to the reference value + * instead of the first-fit. + */ + matches += 1; + match_lvl = 0; + entry->size == ref->size ? ++match_lvl : 0; + entry->type == ref->type ? ++match_lvl : 0; + entry->direction == ref->direction ? ++match_lvl : 0; + entry->sg_call_ents == ref->sg_call_ents ? ++match_lvl : 0; + + if (match_lvl == 4) { + /* perfect-fit - return the result */ + return entry; + } else if (match_lvl > last_lvl) { + /* + * We found an entry that fits better then the + * previous one or it is the 1st match. + */ + last_lvl = match_lvl; + ret = entry; + } + } + + /* + * If we have multiple matches but no perfect-fit, just return + * NULL. + */ + ret = (matches == 1) ? ret : NULL; + + return ret; +} + +static struct dma_debug_entry *bucket_find_exact(struct hash_bucket *bucket, + struct dma_debug_entry *ref) +{ + return __hash_bucket_find(bucket, ref, exact_match); +} + +static struct dma_debug_entry *bucket_find_contain(struct hash_bucket **bucket, + struct dma_debug_entry *ref, + unsigned long *flags) +{ + + struct dma_debug_entry *entry, index = *ref; + int limit = min(HASH_SIZE, (index.dev_addr >> HASH_FN_SHIFT) + 1); + + for (int i = 0; i < limit; i++) { + entry = __hash_bucket_find(*bucket, ref, containing_match); + + if (entry) + return entry; + + /* + * Nothing found, go back a hash bucket + */ + put_hash_bucket(*bucket, *flags); + index.dev_addr -= (1 << HASH_FN_SHIFT); + *bucket = get_hash_bucket(&index, flags); + } + + return NULL; +} + +/* + * Add an entry to a hash bucket + */ +static void hash_bucket_add(struct hash_bucket *bucket, + struct dma_debug_entry *entry) +{ + list_add_tail(&entry->list, &bucket->list); +} + +/* + * Remove entry from a hash bucket list + */ +static void hash_bucket_del(struct dma_debug_entry *entry) +{ + list_del(&entry->list); +} + +static unsigned long long phys_addr(struct dma_debug_entry *entry) +{ + if (entry->type == dma_debug_resource) + return __pfn_to_phys(entry->pfn) + entry->offset; + + return page_to_phys(pfn_to_page(entry->pfn)) + entry->offset; +} + +/* + * For each mapping (initial cacheline in the case of + * dma_alloc_coherent/dma_map_page, initial cacheline in each page of a + * scatterlist, or the cacheline specified in dma_map_single) insert + * into this tree using the cacheline as the key. At + * dma_unmap_{single|sg|page} or dma_free_coherent delete the entry. If + * the entry already exists at insertion time add a tag as a reference + * count for the overlapping mappings. For now, the overlap tracking + * just ensures that 'unmaps' balance 'maps' before marking the + * cacheline idle, but we should also be flagging overlaps as an API + * violation. + * + * Memory usage is mostly constrained by the maximum number of available + * dma-debug entries in that we need a free dma_debug_entry before + * inserting into the tree. In the case of dma_map_page and + * dma_alloc_coherent there is only one dma_debug_entry and one + * dma_active_cacheline entry to track per event. dma_map_sg(), on the + * other hand, consumes a single dma_debug_entry, but inserts 'nents' + * entries into the tree. + */ +static RADIX_TREE(dma_active_cacheline, GFP_ATOMIC); +static DEFINE_SPINLOCK(radix_lock); +#define ACTIVE_CACHELINE_MAX_OVERLAP ((1 << RADIX_TREE_MAX_TAGS) - 1) +#define CACHELINE_PER_PAGE_SHIFT (PAGE_SHIFT - L1_CACHE_SHIFT) +#define CACHELINES_PER_PAGE (1 << CACHELINE_PER_PAGE_SHIFT) + +static phys_addr_t to_cacheline_number(struct dma_debug_entry *entry) +{ + return (entry->pfn << CACHELINE_PER_PAGE_SHIFT) + + (entry->offset >> L1_CACHE_SHIFT); +} + +static int active_cacheline_read_overlap(phys_addr_t cln) +{ + int overlap = 0, i; + + for (i = RADIX_TREE_MAX_TAGS - 1; i >= 0; i--) + if (radix_tree_tag_get(&dma_active_cacheline, cln, i)) + overlap |= 1 << i; + return overlap; +} + +static int active_cacheline_set_overlap(phys_addr_t cln, int overlap) +{ + int i; + + if (overlap > ACTIVE_CACHELINE_MAX_OVERLAP || overlap < 0) + return overlap; + + for (i = RADIX_TREE_MAX_TAGS - 1; i >= 0; i--) + if (overlap & 1 << i) + radix_tree_tag_set(&dma_active_cacheline, cln, i); + else + radix_tree_tag_clear(&dma_active_cacheline, cln, i); + + return overlap; +} + +static void active_cacheline_inc_overlap(phys_addr_t cln) +{ + int overlap = active_cacheline_read_overlap(cln); + + overlap = active_cacheline_set_overlap(cln, ++overlap); + + /* If we overflowed the overlap counter then we're potentially + * leaking dma-mappings. + */ + WARN_ONCE(overlap > ACTIVE_CACHELINE_MAX_OVERLAP, + pr_fmt("exceeded %d overlapping mappings of cacheline %pa\n"), + ACTIVE_CACHELINE_MAX_OVERLAP, &cln); +} + +static int active_cacheline_dec_overlap(phys_addr_t cln) +{ + int overlap = active_cacheline_read_overlap(cln); + + return active_cacheline_set_overlap(cln, --overlap); +} + +static int active_cacheline_insert(struct dma_debug_entry *entry) +{ + phys_addr_t cln = to_cacheline_number(entry); + unsigned long flags; + int rc; + + /* If the device is not writing memory then we don't have any + * concerns about the cpu consuming stale data. This mitigates + * legitimate usages of overlapping mappings. + */ + if (entry->direction == DMA_TO_DEVICE) + return 0; + + spin_lock_irqsave(&radix_lock, flags); + rc = radix_tree_insert(&dma_active_cacheline, cln, entry); + if (rc == -EEXIST) + active_cacheline_inc_overlap(cln); + spin_unlock_irqrestore(&radix_lock, flags); + + return rc; +} + +static void active_cacheline_remove(struct dma_debug_entry *entry) +{ + phys_addr_t cln = to_cacheline_number(entry); + unsigned long flags; + + /* ...mirror the insert case */ + if (entry->direction == DMA_TO_DEVICE) + return; + + spin_lock_irqsave(&radix_lock, flags); + /* since we are counting overlaps the final put of the + * cacheline will occur when the overlap count is 0. + * active_cacheline_dec_overlap() returns -1 in that case + */ + if (active_cacheline_dec_overlap(cln) < 0) + radix_tree_delete(&dma_active_cacheline, cln); + spin_unlock_irqrestore(&radix_lock, flags); +} + +/* + * Dump mappings entries on kernel space for debugging purposes + */ +void debug_dma_dump_mappings(struct device *dev) +{ + int idx; + phys_addr_t cln; + + for (idx = 0; idx < HASH_SIZE; idx++) { + struct hash_bucket *bucket = &dma_entry_hash[idx]; + struct dma_debug_entry *entry; + unsigned long flags; + + spin_lock_irqsave(&bucket->lock, flags); + list_for_each_entry(entry, &bucket->list, list) { + if (!dev || dev == entry->dev) { + cln = to_cacheline_number(entry); + dev_info(entry->dev, + "%s idx %d P=%llx N=%lx D=%llx L=%llx cln=%pa %s %s\n", + type2name[entry->type], idx, + phys_addr(entry), entry->pfn, + entry->dev_addr, entry->size, + &cln, dir2name[entry->direction], + maperr2str[entry->map_err_type]); + } + } + spin_unlock_irqrestore(&bucket->lock, flags); + + cond_resched(); + } +} + +/* + * Dump mappings entries on user space via debugfs + */ +static int dump_show(struct seq_file *seq, void *v) +{ + int idx; + phys_addr_t cln; + + for (idx = 0; idx < HASH_SIZE; idx++) { + struct hash_bucket *bucket = &dma_entry_hash[idx]; + struct dma_debug_entry *entry; + unsigned long flags; + + spin_lock_irqsave(&bucket->lock, flags); + list_for_each_entry(entry, &bucket->list, list) { + cln = to_cacheline_number(entry); + seq_printf(seq, + "%s %s %s idx %d P=%llx N=%lx D=%llx L=%llx cln=%pa %s %s\n", + dev_driver_string(entry->dev), + dev_name(entry->dev), + type2name[entry->type], idx, + phys_addr(entry), entry->pfn, + entry->dev_addr, entry->size, + &cln, dir2name[entry->direction], + maperr2str[entry->map_err_type]); + } + spin_unlock_irqrestore(&bucket->lock, flags); + } + return 0; +} +DEFINE_SHOW_ATTRIBUTE(dump); + +/* + * Wrapper function for adding an entry to the hash. + * This function takes care of locking itself. + */ +static void add_dma_entry(struct dma_debug_entry *entry, unsigned long attrs) +{ + struct hash_bucket *bucket; + unsigned long flags; + int rc; + + bucket = get_hash_bucket(entry, &flags); + hash_bucket_add(bucket, entry); + put_hash_bucket(bucket, flags); + + rc = active_cacheline_insert(entry); + if (rc == -ENOMEM) { + pr_err_once("cacheline tracking ENOMEM, dma-debug disabled\n"); + global_disable = true; + } else if (rc == -EEXIST && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) { + err_printk(entry->dev, entry, + "cacheline tracking EEXIST, overlapping mappings aren't supported\n"); + } +} + +static int dma_debug_create_entries(gfp_t gfp) +{ + struct dma_debug_entry *entry; + int i; + + entry = (void *)get_zeroed_page(gfp); + if (!entry) + return -ENOMEM; + + for (i = 0; i < DMA_DEBUG_DYNAMIC_ENTRIES; i++) + list_add_tail(&entry[i].list, &free_entries); + + num_free_entries += DMA_DEBUG_DYNAMIC_ENTRIES; + nr_total_entries += DMA_DEBUG_DYNAMIC_ENTRIES; + + return 0; +} + +static struct dma_debug_entry *__dma_entry_alloc(void) +{ + struct dma_debug_entry *entry; + + entry = list_entry(free_entries.next, struct dma_debug_entry, list); + list_del(&entry->list); + memset(entry, 0, sizeof(*entry)); + + num_free_entries -= 1; + if (num_free_entries < min_free_entries) + min_free_entries = num_free_entries; + + return entry; +} + +/* + * This should be called outside of free_entries_lock scope to avoid potential + * deadlocks with serial consoles that use DMA. + */ +static void __dma_entry_alloc_check_leak(u32 nr_entries) +{ + u32 tmp = nr_entries % nr_prealloc_entries; + + /* Shout each time we tick over some multiple of the initial pool */ + if (tmp < DMA_DEBUG_DYNAMIC_ENTRIES) { + pr_info("dma_debug_entry pool grown to %u (%u00%%)\n", + nr_entries, + (nr_entries / nr_prealloc_entries)); + } +} + +/* struct dma_entry allocator + * + * The next two functions implement the allocator for + * struct dma_debug_entries. + */ +static struct dma_debug_entry *dma_entry_alloc(void) +{ + bool alloc_check_leak = false; + struct dma_debug_entry *entry; + unsigned long flags; + u32 nr_entries; + + spin_lock_irqsave(&free_entries_lock, flags); + if (num_free_entries == 0) { + if (dma_debug_create_entries(GFP_ATOMIC)) { + global_disable = true; + spin_unlock_irqrestore(&free_entries_lock, flags); + pr_err("debugging out of memory - disabling\n"); + return NULL; + } + alloc_check_leak = true; + nr_entries = nr_total_entries; + } + + entry = __dma_entry_alloc(); + + spin_unlock_irqrestore(&free_entries_lock, flags); + + if (alloc_check_leak) + __dma_entry_alloc_check_leak(nr_entries); + +#ifdef CONFIG_STACKTRACE + entry->stack_len = stack_trace_save(entry->stack_entries, + ARRAY_SIZE(entry->stack_entries), + 1); +#endif + return entry; +} + +static void dma_entry_free(struct dma_debug_entry *entry) +{ + unsigned long flags; + + active_cacheline_remove(entry); + + /* + * add to beginning of the list - this way the entries are + * more likely cache hot when they are reallocated. + */ + spin_lock_irqsave(&free_entries_lock, flags); + list_add(&entry->list, &free_entries); + num_free_entries += 1; + spin_unlock_irqrestore(&free_entries_lock, flags); +} + +/* + * DMA-API debugging init code + * + * The init code does two things: + * 1. Initialize core data structures + * 2. Preallocate a given number of dma_debug_entry structs + */ + +static ssize_t filter_read(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + char buf[NAME_MAX_LEN + 1]; + unsigned long flags; + int len; + + if (!current_driver_name[0]) + return 0; + + /* + * We can't copy to userspace directly because current_driver_name can + * only be read under the driver_name_lock with irqs disabled. So + * create a temporary copy first. + */ + read_lock_irqsave(&driver_name_lock, flags); + len = scnprintf(buf, NAME_MAX_LEN + 1, "%s\n", current_driver_name); + read_unlock_irqrestore(&driver_name_lock, flags); + + return simple_read_from_buffer(user_buf, count, ppos, buf, len); +} + +static ssize_t filter_write(struct file *file, const char __user *userbuf, + size_t count, loff_t *ppos) +{ + char buf[NAME_MAX_LEN]; + unsigned long flags; + size_t len; + int i; + + /* + * We can't copy from userspace directly. Access to + * current_driver_name is protected with a write_lock with irqs + * disabled. Since copy_from_user can fault and may sleep we + * need to copy to temporary buffer first + */ + len = min(count, (size_t)(NAME_MAX_LEN - 1)); + if (copy_from_user(buf, userbuf, len)) + return -EFAULT; + + buf[len] = 0; + + write_lock_irqsave(&driver_name_lock, flags); + + /* + * Now handle the string we got from userspace very carefully. + * The rules are: + * - only use the first token we got + * - token delimiter is everything looking like a space + * character (' ', '\n', '\t' ...) + * + */ + if (!isalnum(buf[0])) { + /* + * If the first character userspace gave us is not + * alphanumerical then assume the filter should be + * switched off. + */ + if (current_driver_name[0]) + pr_info("switching off dma-debug driver filter\n"); + current_driver_name[0] = 0; + current_driver = NULL; + goto out_unlock; + } + + /* + * Now parse out the first token and use it as the name for the + * driver to filter for. + */ + for (i = 0; i < NAME_MAX_LEN - 1; ++i) { + current_driver_name[i] = buf[i]; + if (isspace(buf[i]) || buf[i] == ' ' || buf[i] == 0) + break; + } + current_driver_name[i] = 0; + current_driver = NULL; + + pr_info("enable driver filter for driver [%s]\n", + current_driver_name); + +out_unlock: + write_unlock_irqrestore(&driver_name_lock, flags); + + return count; +} + +static const struct file_operations filter_fops = { + .read = filter_read, + .write = filter_write, + .llseek = default_llseek, +}; + +static int __init dma_debug_fs_init(void) +{ + struct dentry *dentry = debugfs_create_dir("dma-api", NULL); + + debugfs_create_bool("disabled", 0444, dentry, &global_disable); + debugfs_create_u32("error_count", 0444, dentry, &error_count); + debugfs_create_u32("all_errors", 0644, dentry, &show_all_errors); + debugfs_create_u32("num_errors", 0644, dentry, &show_num_errors); + debugfs_create_u32("num_free_entries", 0444, dentry, &num_free_entries); + debugfs_create_u32("min_free_entries", 0444, dentry, &min_free_entries); + debugfs_create_u32("nr_total_entries", 0444, dentry, &nr_total_entries); + debugfs_create_file("driver_filter", 0644, dentry, NULL, &filter_fops); + debugfs_create_file("dump", 0444, dentry, NULL, &dump_fops); + + return 0; +} +core_initcall_sync(dma_debug_fs_init); + +static int device_dma_allocations(struct device *dev, struct dma_debug_entry **out_entry) +{ + struct dma_debug_entry *entry; + unsigned long flags; + int count = 0, i; + + for (i = 0; i < HASH_SIZE; ++i) { + spin_lock_irqsave(&dma_entry_hash[i].lock, flags); + list_for_each_entry(entry, &dma_entry_hash[i].list, list) { + if (entry->dev == dev) { + count += 1; + *out_entry = entry; + } + } + spin_unlock_irqrestore(&dma_entry_hash[i].lock, flags); + } + + return count; +} + +static int dma_debug_device_change(struct notifier_block *nb, unsigned long action, void *data) +{ + struct device *dev = data; + struct dma_debug_entry *entry; + int count; + + if (dma_debug_disabled()) + return 0; + + switch (action) { + case BUS_NOTIFY_UNBOUND_DRIVER: + count = device_dma_allocations(dev, &entry); + if (count == 0) + break; + err_printk(dev, entry, "device driver has pending " + "DMA allocations while released from device " + "[count=%d]\n" + "One of leaked entries details: " + "[device address=0x%016llx] [size=%llu bytes] " + "[mapped with %s] [mapped as %s]\n", + count, entry->dev_addr, entry->size, + dir2name[entry->direction], type2name[entry->type]); + break; + default: + break; + } + + return 0; +} + +void dma_debug_add_bus(struct bus_type *bus) +{ + struct notifier_block *nb; + + if (dma_debug_disabled()) + return; + + nb = kzalloc(sizeof(struct notifier_block), GFP_KERNEL); + if (nb == NULL) { + pr_err("dma_debug_add_bus: out of memory\n"); + return; + } + + nb->notifier_call = dma_debug_device_change; + + bus_register_notifier(bus, nb); +} + +static int dma_debug_init(void) +{ + int i, nr_pages; + + /* Do not use dma_debug_initialized here, since we really want to be + * called to set dma_debug_initialized + */ + if (global_disable) + return 0; + + for (i = 0; i < HASH_SIZE; ++i) { + INIT_LIST_HEAD(&dma_entry_hash[i].list); + spin_lock_init(&dma_entry_hash[i].lock); + } + + nr_pages = DIV_ROUND_UP(nr_prealloc_entries, DMA_DEBUG_DYNAMIC_ENTRIES); + for (i = 0; i < nr_pages; ++i) + dma_debug_create_entries(GFP_KERNEL); + if (num_free_entries >= nr_prealloc_entries) { + pr_info("preallocated %d debug entries\n", nr_total_entries); + } else if (num_free_entries > 0) { + pr_warn("%d debug entries requested but only %d allocated\n", + nr_prealloc_entries, nr_total_entries); + } else { + pr_err("debugging out of memory error - disabled\n"); + global_disable = true; + + return 0; + } + min_free_entries = num_free_entries; + + dma_debug_initialized = true; + + pr_info("debugging enabled by kernel config\n"); + return 0; +} +core_initcall(dma_debug_init); + +static __init int dma_debug_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (strncmp(str, "off", 3) == 0) { + pr_info("debugging disabled on kernel command line\n"); + global_disable = true; + } + + return 1; +} + +static __init int dma_debug_entries_cmdline(char *str) +{ + if (!str) + return -EINVAL; + if (!get_option(&str, &nr_prealloc_entries)) + nr_prealloc_entries = PREALLOC_DMA_DEBUG_ENTRIES; + return 1; +} + +__setup("dma_debug=", dma_debug_cmdline); +__setup("dma_debug_entries=", dma_debug_entries_cmdline); + +static void check_unmap(struct dma_debug_entry *ref) +{ + struct dma_debug_entry *entry; + struct hash_bucket *bucket; + unsigned long flags; + + bucket = get_hash_bucket(ref, &flags); + entry = bucket_find_exact(bucket, ref); + + if (!entry) { + /* must drop lock before calling dma_mapping_error */ + put_hash_bucket(bucket, flags); + + if (dma_mapping_error(ref->dev, ref->dev_addr)) { + err_printk(ref->dev, NULL, + "device driver tries to free an " + "invalid DMA memory address\n"); + } else { + err_printk(ref->dev, NULL, + "device driver tries to free DMA " + "memory it has not allocated [device " + "address=0x%016llx] [size=%llu bytes]\n", + ref->dev_addr, ref->size); + } + return; + } + + if (ref->size != entry->size) { + err_printk(ref->dev, entry, "device driver frees " + "DMA memory with different size " + "[device address=0x%016llx] [map size=%llu bytes] " + "[unmap size=%llu bytes]\n", + ref->dev_addr, entry->size, ref->size); + } + + if (ref->type != entry->type) { + err_printk(ref->dev, entry, "device driver frees " + "DMA memory with wrong function " + "[device address=0x%016llx] [size=%llu bytes] " + "[mapped as %s] [unmapped as %s]\n", + ref->dev_addr, ref->size, + type2name[entry->type], type2name[ref->type]); + } else if ((entry->type == dma_debug_coherent) && + (phys_addr(ref) != phys_addr(entry))) { + err_printk(ref->dev, entry, "device driver frees " + "DMA memory with different CPU address " + "[device address=0x%016llx] [size=%llu bytes] " + "[cpu alloc address=0x%016llx] " + "[cpu free address=0x%016llx]", + ref->dev_addr, ref->size, + phys_addr(entry), + phys_addr(ref)); + } + + if (ref->sg_call_ents && ref->type == dma_debug_sg && + ref->sg_call_ents != entry->sg_call_ents) { + err_printk(ref->dev, entry, "device driver frees " + "DMA sg list with different entry count " + "[map count=%d] [unmap count=%d]\n", + entry->sg_call_ents, ref->sg_call_ents); + } + + /* + * This may be no bug in reality - but most implementations of the + * DMA API don't handle this properly, so check for it here + */ + if (ref->direction != entry->direction) { + err_printk(ref->dev, entry, "device driver frees " + "DMA memory with different direction " + "[device address=0x%016llx] [size=%llu bytes] " + "[mapped with %s] [unmapped with %s]\n", + ref->dev_addr, ref->size, + dir2name[entry->direction], + dir2name[ref->direction]); + } + + /* + * Drivers should use dma_mapping_error() to check the returned + * addresses of dma_map_single() and dma_map_page(). + * If not, print this warning message. See Documentation/core-api/dma-api.rst. + */ + if (entry->map_err_type == MAP_ERR_NOT_CHECKED) { + err_printk(ref->dev, entry, + "device driver failed to check map error" + "[device address=0x%016llx] [size=%llu bytes] " + "[mapped as %s]", + ref->dev_addr, ref->size, + type2name[entry->type]); + } + + hash_bucket_del(entry); + dma_entry_free(entry); + + put_hash_bucket(bucket, flags); +} + +static void check_for_stack(struct device *dev, + struct page *page, size_t offset) +{ + void *addr; + struct vm_struct *stack_vm_area = task_stack_vm_area(current); + + if (!stack_vm_area) { + /* Stack is direct-mapped. */ + if (PageHighMem(page)) + return; + addr = page_address(page) + offset; + if (object_is_on_stack(addr)) + err_printk(dev, NULL, "device driver maps memory from stack [addr=%p]\n", addr); + } else { + /* Stack is vmalloced. */ + int i; + + for (i = 0; i < stack_vm_area->nr_pages; i++) { + if (page != stack_vm_area->pages[i]) + continue; + + addr = (u8 *)current->stack + i * PAGE_SIZE + offset; + err_printk(dev, NULL, "device driver maps memory from stack [probable addr=%p]\n", addr); + break; + } + } +} + +static void check_for_illegal_area(struct device *dev, void *addr, unsigned long len) +{ + if (memory_intersects(_stext, _etext, addr, len) || + memory_intersects(__start_rodata, __end_rodata, addr, len)) + err_printk(dev, NULL, "device driver maps memory from kernel text or rodata [addr=%p] [len=%lu]\n", addr, len); +} + +static void check_sync(struct device *dev, + struct dma_debug_entry *ref, + bool to_cpu) +{ + struct dma_debug_entry *entry; + struct hash_bucket *bucket; + unsigned long flags; + + bucket = get_hash_bucket(ref, &flags); + + entry = bucket_find_contain(&bucket, ref, &flags); + + if (!entry) { + err_printk(dev, NULL, "device driver tries " + "to sync DMA memory it has not allocated " + "[device address=0x%016llx] [size=%llu bytes]\n", + (unsigned long long)ref->dev_addr, ref->size); + goto out; + } + + if (ref->size > entry->size) { + err_printk(dev, entry, "device driver syncs" + " DMA memory outside allocated range " + "[device address=0x%016llx] " + "[allocation size=%llu bytes] " + "[sync offset+size=%llu]\n", + entry->dev_addr, entry->size, + ref->size); + } + + if (entry->direction == DMA_BIDIRECTIONAL) + goto out; + + if (ref->direction != entry->direction) { + err_printk(dev, entry, "device driver syncs " + "DMA memory with different direction " + "[device address=0x%016llx] [size=%llu bytes] " + "[mapped with %s] [synced with %s]\n", + (unsigned long long)ref->dev_addr, entry->size, + dir2name[entry->direction], + dir2name[ref->direction]); + } + + if (to_cpu && !(entry->direction == DMA_FROM_DEVICE) && + !(ref->direction == DMA_TO_DEVICE)) + err_printk(dev, entry, "device driver syncs " + "device read-only DMA memory for cpu " + "[device address=0x%016llx] [size=%llu bytes] " + "[mapped with %s] [synced with %s]\n", + (unsigned long long)ref->dev_addr, entry->size, + dir2name[entry->direction], + dir2name[ref->direction]); + + if (!to_cpu && !(entry->direction == DMA_TO_DEVICE) && + !(ref->direction == DMA_FROM_DEVICE)) + err_printk(dev, entry, "device driver syncs " + "device write-only DMA memory to device " + "[device address=0x%016llx] [size=%llu bytes] " + "[mapped with %s] [synced with %s]\n", + (unsigned long long)ref->dev_addr, entry->size, + dir2name[entry->direction], + dir2name[ref->direction]); + + if (ref->sg_call_ents && ref->type == dma_debug_sg && + ref->sg_call_ents != entry->sg_call_ents) { + err_printk(ref->dev, entry, "device driver syncs " + "DMA sg list with different entry count " + "[map count=%d] [sync count=%d]\n", + entry->sg_call_ents, ref->sg_call_ents); + } + +out: + put_hash_bucket(bucket, flags); +} + +static void check_sg_segment(struct device *dev, struct scatterlist *sg) +{ +#ifdef CONFIG_DMA_API_DEBUG_SG + unsigned int max_seg = dma_get_max_seg_size(dev); + u64 start, end, boundary = dma_get_seg_boundary(dev); + + /* + * Either the driver forgot to set dma_parms appropriately, or + * whoever generated the list forgot to check them. + */ + if (sg->length > max_seg) + err_printk(dev, NULL, "mapping sg segment longer than device claims to support [len=%u] [max=%u]\n", + sg->length, max_seg); + /* + * In some cases this could potentially be the DMA API + * implementation's fault, but it would usually imply that + * the scatterlist was built inappropriately to begin with. + */ + start = sg_dma_address(sg); + end = start + sg_dma_len(sg) - 1; + if ((start ^ end) & ~boundary) + err_printk(dev, NULL, "mapping sg segment across boundary [start=0x%016llx] [end=0x%016llx] [boundary=0x%016llx]\n", + start, end, boundary); +#endif +} + +void debug_dma_map_single(struct device *dev, const void *addr, + unsigned long len) +{ + if (unlikely(dma_debug_disabled())) + return; + + if (!virt_addr_valid(addr)) + err_printk(dev, NULL, "device driver maps memory from invalid area [addr=%p] [len=%lu]\n", + addr, len); + + if (is_vmalloc_addr(addr)) + err_printk(dev, NULL, "device driver maps memory from vmalloc area [addr=%p] [len=%lu]\n", + addr, len); +} +EXPORT_SYMBOL(debug_dma_map_single); + +void debug_dma_map_page(struct device *dev, struct page *page, size_t offset, + size_t size, int direction, dma_addr_t dma_addr, + unsigned long attrs) +{ + struct dma_debug_entry *entry; + + if (unlikely(dma_debug_disabled())) + return; + + if (dma_mapping_error(dev, dma_addr)) + return; + + entry = dma_entry_alloc(); + if (!entry) + return; + + entry->dev = dev; + entry->type = dma_debug_single; + entry->pfn = page_to_pfn(page); + entry->offset = offset; + entry->dev_addr = dma_addr; + entry->size = size; + entry->direction = direction; + entry->map_err_type = MAP_ERR_NOT_CHECKED; + + check_for_stack(dev, page, offset); + + if (!PageHighMem(page)) { + void *addr = page_address(page) + offset; + + check_for_illegal_area(dev, addr, size); + } + + add_dma_entry(entry, attrs); +} + +void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) +{ + struct dma_debug_entry ref; + struct dma_debug_entry *entry; + struct hash_bucket *bucket; + unsigned long flags; + + if (unlikely(dma_debug_disabled())) + return; + + ref.dev = dev; + ref.dev_addr = dma_addr; + bucket = get_hash_bucket(&ref, &flags); + + list_for_each_entry(entry, &bucket->list, list) { + if (!exact_match(&ref, entry)) + continue; + + /* + * The same physical address can be mapped multiple + * times. Without a hardware IOMMU this results in the + * same device addresses being put into the dma-debug + * hash multiple times too. This can result in false + * positives being reported. Therefore we implement a + * best-fit algorithm here which updates the first entry + * from the hash which fits the reference value and is + * not currently listed as being checked. + */ + if (entry->map_err_type == MAP_ERR_NOT_CHECKED) { + entry->map_err_type = MAP_ERR_CHECKED; + break; + } + } + + put_hash_bucket(bucket, flags); +} +EXPORT_SYMBOL(debug_dma_mapping_error); + +void debug_dma_unmap_page(struct device *dev, dma_addr_t dma_addr, + size_t size, int direction) +{ + struct dma_debug_entry ref = { + .type = dma_debug_single, + .dev = dev, + .dev_addr = dma_addr, + .size = size, + .direction = direction, + }; + + if (unlikely(dma_debug_disabled())) + return; + check_unmap(&ref); +} + +void debug_dma_map_sg(struct device *dev, struct scatterlist *sg, + int nents, int mapped_ents, int direction, + unsigned long attrs) +{ + struct dma_debug_entry *entry; + struct scatterlist *s; + int i; + + if (unlikely(dma_debug_disabled())) + return; + + for_each_sg(sg, s, nents, i) { + check_for_stack(dev, sg_page(s), s->offset); + if (!PageHighMem(sg_page(s))) + check_for_illegal_area(dev, sg_virt(s), s->length); + } + + for_each_sg(sg, s, mapped_ents, i) { + entry = dma_entry_alloc(); + if (!entry) + return; + + entry->type = dma_debug_sg; + entry->dev = dev; + entry->pfn = page_to_pfn(sg_page(s)); + entry->offset = s->offset; + entry->size = sg_dma_len(s); + entry->dev_addr = sg_dma_address(s); + entry->direction = direction; + entry->sg_call_ents = nents; + entry->sg_mapped_ents = mapped_ents; + + check_sg_segment(dev, s); + + add_dma_entry(entry, attrs); + } +} + +static int get_nr_mapped_entries(struct device *dev, + struct dma_debug_entry *ref) +{ + struct dma_debug_entry *entry; + struct hash_bucket *bucket; + unsigned long flags; + int mapped_ents; + + bucket = get_hash_bucket(ref, &flags); + entry = bucket_find_exact(bucket, ref); + mapped_ents = 0; + + if (entry) + mapped_ents = entry->sg_mapped_ents; + put_hash_bucket(bucket, flags); + + return mapped_ents; +} + +void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, + int nelems, int dir) +{ + struct scatterlist *s; + int mapped_ents = 0, i; + + if (unlikely(dma_debug_disabled())) + return; + + for_each_sg(sglist, s, nelems, i) { + + struct dma_debug_entry ref = { + .type = dma_debug_sg, + .dev = dev, + .pfn = page_to_pfn(sg_page(s)), + .offset = s->offset, + .dev_addr = sg_dma_address(s), + .size = sg_dma_len(s), + .direction = dir, + .sg_call_ents = nelems, + }; + + if (mapped_ents && i >= mapped_ents) + break; + + if (!i) + mapped_ents = get_nr_mapped_entries(dev, &ref); + + check_unmap(&ref); + } +} + +void debug_dma_alloc_coherent(struct device *dev, size_t size, + dma_addr_t dma_addr, void *virt, + unsigned long attrs) +{ + struct dma_debug_entry *entry; + + if (unlikely(dma_debug_disabled())) + return; + + if (unlikely(virt == NULL)) + return; + + /* handle vmalloc and linear addresses */ + if (!is_vmalloc_addr(virt) && !virt_addr_valid(virt)) + return; + + entry = dma_entry_alloc(); + if (!entry) + return; + + entry->type = dma_debug_coherent; + entry->dev = dev; + entry->offset = offset_in_page(virt); + entry->size = size; + entry->dev_addr = dma_addr; + entry->direction = DMA_BIDIRECTIONAL; + + if (is_vmalloc_addr(virt)) + entry->pfn = vmalloc_to_pfn(virt); + else + entry->pfn = page_to_pfn(virt_to_page(virt)); + + add_dma_entry(entry, attrs); +} + +void debug_dma_free_coherent(struct device *dev, size_t size, + void *virt, dma_addr_t dma_addr) +{ + struct dma_debug_entry ref = { + .type = dma_debug_coherent, + .dev = dev, + .offset = offset_in_page(virt), + .dev_addr = dma_addr, + .size = size, + .direction = DMA_BIDIRECTIONAL, + }; + + /* handle vmalloc and linear addresses */ + if (!is_vmalloc_addr(virt) && !virt_addr_valid(virt)) + return; + + if (is_vmalloc_addr(virt)) + ref.pfn = vmalloc_to_pfn(virt); + else + ref.pfn = page_to_pfn(virt_to_page(virt)); + + if (unlikely(dma_debug_disabled())) + return; + + check_unmap(&ref); +} + +void debug_dma_map_resource(struct device *dev, phys_addr_t addr, size_t size, + int direction, dma_addr_t dma_addr, + unsigned long attrs) +{ + struct dma_debug_entry *entry; + + if (unlikely(dma_debug_disabled())) + return; + + entry = dma_entry_alloc(); + if (!entry) + return; + + entry->type = dma_debug_resource; + entry->dev = dev; + entry->pfn = PHYS_PFN(addr); + entry->offset = offset_in_page(addr); + entry->size = size; + entry->dev_addr = dma_addr; + entry->direction = direction; + entry->map_err_type = MAP_ERR_NOT_CHECKED; + + add_dma_entry(entry, attrs); +} + +void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr, + size_t size, int direction) +{ + struct dma_debug_entry ref = { + .type = dma_debug_resource, + .dev = dev, + .dev_addr = dma_addr, + .size = size, + .direction = direction, + }; + + if (unlikely(dma_debug_disabled())) + return; + + check_unmap(&ref); +} + +void debug_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, + size_t size, int direction) +{ + struct dma_debug_entry ref; + + if (unlikely(dma_debug_disabled())) + return; + + ref.type = dma_debug_single; + ref.dev = dev; + ref.dev_addr = dma_handle; + ref.size = size; + ref.direction = direction; + ref.sg_call_ents = 0; + + check_sync(dev, &ref, true); +} + +void debug_dma_sync_single_for_device(struct device *dev, + dma_addr_t dma_handle, size_t size, + int direction) +{ + struct dma_debug_entry ref; + + if (unlikely(dma_debug_disabled())) + return; + + ref.type = dma_debug_single; + ref.dev = dev; + ref.dev_addr = dma_handle; + ref.size = size; + ref.direction = direction; + ref.sg_call_ents = 0; + + check_sync(dev, &ref, false); +} + +void debug_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, + int nelems, int direction) +{ + struct scatterlist *s; + int mapped_ents = 0, i; + + if (unlikely(dma_debug_disabled())) + return; + + for_each_sg(sg, s, nelems, i) { + + struct dma_debug_entry ref = { + .type = dma_debug_sg, + .dev = dev, + .pfn = page_to_pfn(sg_page(s)), + .offset = s->offset, + .dev_addr = sg_dma_address(s), + .size = sg_dma_len(s), + .direction = direction, + .sg_call_ents = nelems, + }; + + if (!i) + mapped_ents = get_nr_mapped_entries(dev, &ref); + + if (i >= mapped_ents) + break; + + check_sync(dev, &ref, true); + } +} + +void debug_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, + int nelems, int direction) +{ + struct scatterlist *s; + int mapped_ents = 0, i; + + if (unlikely(dma_debug_disabled())) + return; + + for_each_sg(sg, s, nelems, i) { + + struct dma_debug_entry ref = { + .type = dma_debug_sg, + .dev = dev, + .pfn = page_to_pfn(sg_page(s)), + .offset = s->offset, + .dev_addr = sg_dma_address(s), + .size = sg_dma_len(s), + .direction = direction, + .sg_call_ents = nelems, + }; + if (!i) + mapped_ents = get_nr_mapped_entries(dev, &ref); + + if (i >= mapped_ents) + break; + + check_sync(dev, &ref, false); + } +} + +static int __init dma_debug_driver_setup(char *str) +{ + int i; + + for (i = 0; i < NAME_MAX_LEN - 1; ++i, ++str) { + current_driver_name[i] = *str; + if (*str == 0) + break; + } + + if (current_driver_name[0]) + pr_info("enable driver filter for driver [%s]\n", + current_driver_name); + + + return 1; +} +__setup("dma_debug_driver=", dma_debug_driver_setup); diff --git a/kernel/dma/debug.h b/kernel/dma/debug.h new file mode 100644 index 000000000..f525197d3 --- /dev/null +++ b/kernel/dma/debug.h @@ -0,0 +1,130 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2008 Advanced Micro Devices, Inc. + * + * Author: Joerg Roedel + */ + +#ifndef _KERNEL_DMA_DEBUG_H +#define _KERNEL_DMA_DEBUG_H + +#ifdef CONFIG_DMA_API_DEBUG +extern void debug_dma_map_page(struct device *dev, struct page *page, + size_t offset, size_t size, + int direction, dma_addr_t dma_addr, + unsigned long attrs); + +extern void debug_dma_unmap_page(struct device *dev, dma_addr_t addr, + size_t size, int direction); + +extern void debug_dma_map_sg(struct device *dev, struct scatterlist *sg, + int nents, int mapped_ents, int direction, + unsigned long attrs); + +extern void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, + int nelems, int dir); + +extern void debug_dma_alloc_coherent(struct device *dev, size_t size, + dma_addr_t dma_addr, void *virt, + unsigned long attrs); + +extern void debug_dma_free_coherent(struct device *dev, size_t size, + void *virt, dma_addr_t addr); + +extern void debug_dma_map_resource(struct device *dev, phys_addr_t addr, + size_t size, int direction, + dma_addr_t dma_addr, + unsigned long attrs); + +extern void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr, + size_t size, int direction); + +extern void debug_dma_sync_single_for_cpu(struct device *dev, + dma_addr_t dma_handle, size_t size, + int direction); + +extern void debug_dma_sync_single_for_device(struct device *dev, + dma_addr_t dma_handle, + size_t size, int direction); + +extern void debug_dma_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sg, + int nelems, int direction); + +extern void debug_dma_sync_sg_for_device(struct device *dev, + struct scatterlist *sg, + int nelems, int direction); +#else /* CONFIG_DMA_API_DEBUG */ +static inline void debug_dma_map_page(struct device *dev, struct page *page, + size_t offset, size_t size, + int direction, dma_addr_t dma_addr, + unsigned long attrs) +{ +} + +static inline void debug_dma_unmap_page(struct device *dev, dma_addr_t addr, + size_t size, int direction) +{ +} + +static inline void debug_dma_map_sg(struct device *dev, struct scatterlist *sg, + int nents, int mapped_ents, int direction, + unsigned long attrs) +{ +} + +static inline void debug_dma_unmap_sg(struct device *dev, + struct scatterlist *sglist, + int nelems, int dir) +{ +} + +static inline void debug_dma_alloc_coherent(struct device *dev, size_t size, + dma_addr_t dma_addr, void *virt, + unsigned long attrs) +{ +} + +static inline void debug_dma_free_coherent(struct device *dev, size_t size, + void *virt, dma_addr_t addr) +{ +} + +static inline void debug_dma_map_resource(struct device *dev, phys_addr_t addr, + size_t size, int direction, + dma_addr_t dma_addr, + unsigned long attrs) +{ +} + +static inline void debug_dma_unmap_resource(struct device *dev, + dma_addr_t dma_addr, size_t size, + int direction) +{ +} + +static inline void debug_dma_sync_single_for_cpu(struct device *dev, + dma_addr_t dma_handle, + size_t size, int direction) +{ +} + +static inline void debug_dma_sync_single_for_device(struct device *dev, + dma_addr_t dma_handle, + size_t size, int direction) +{ +} + +static inline void debug_dma_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sg, + int nelems, int direction) +{ +} + +static inline void debug_dma_sync_sg_for_device(struct device *dev, + struct scatterlist *sg, + int nelems, int direction) +{ +} +#endif /* CONFIG_DMA_API_DEBUG */ +#endif /* _KERNEL_DMA_DEBUG_H */ diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c new file mode 100644 index 000000000..9596ae1aa --- /dev/null +++ b/kernel/dma/direct.c @@ -0,0 +1,655 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2018-2020 Christoph Hellwig. + * + * DMA operations that map physical memory directly without using an IOMMU. + */ +#include /* for max_pfn */ +#include +#include +#include +#include +#include +#include +#include +#include +#include "direct.h" + +/* + * Most architectures use ZONE_DMA for the first 16 Megabytes, but some use + * it for entirely different regions. In that case the arch code needs to + * override the variable below for dma-direct to work properly. + */ +unsigned int zone_dma_bits __ro_after_init = 24; + +static inline dma_addr_t phys_to_dma_direct(struct device *dev, + phys_addr_t phys) +{ + if (force_dma_unencrypted(dev)) + return phys_to_dma_unencrypted(dev, phys); + return phys_to_dma(dev, phys); +} + +static inline struct page *dma_direct_to_page(struct device *dev, + dma_addr_t dma_addr) +{ + return pfn_to_page(PHYS_PFN(dma_to_phys(dev, dma_addr))); +} + +u64 dma_direct_get_required_mask(struct device *dev) +{ + phys_addr_t phys = (phys_addr_t)(max_pfn - 1) << PAGE_SHIFT; + u64 max_dma = phys_to_dma_direct(dev, phys); + + return (1ULL << (fls64(max_dma) - 1)) * 2 - 1; +} + +static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 *phys_limit) +{ + u64 dma_limit = min_not_zero( + dev->coherent_dma_mask, + dev->bus_dma_limit); + + /* + * Optimistically try the zone that the physical address mask falls + * into first. If that returns memory that isn't actually addressable + * we will fallback to the next lower zone and try again. + * + * Note that GFP_DMA32 and GFP_DMA are no ops without the corresponding + * zones. + */ + *phys_limit = dma_to_phys(dev, dma_limit); + if (*phys_limit <= DMA_BIT_MASK(zone_dma_bits)) + return GFP_DMA; + if (*phys_limit <= DMA_BIT_MASK(32)) + return GFP_DMA32; + return 0; +} + +bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size) +{ + dma_addr_t dma_addr = phys_to_dma_direct(dev, phys); + + if (dma_addr == DMA_MAPPING_ERROR) + return false; + return dma_addr + size - 1 <= + min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit); +} + +static int dma_set_decrypted(struct device *dev, void *vaddr, size_t size) +{ + if (!force_dma_unencrypted(dev)) + return 0; + return set_memory_decrypted((unsigned long)vaddr, PFN_UP(size)); +} + +static int dma_set_encrypted(struct device *dev, void *vaddr, size_t size) +{ + int ret; + + if (!force_dma_unencrypted(dev)) + return 0; + ret = set_memory_encrypted((unsigned long)vaddr, PFN_UP(size)); + if (ret) + pr_warn_ratelimited("leaking DMA memory that can't be re-encrypted\n"); + return ret; +} + +static void __dma_direct_free_pages(struct device *dev, struct page *page, + size_t size) +{ + if (swiotlb_free(dev, page, size)) + return; + dma_free_contiguous(dev, page, size); +} + +static struct page *dma_direct_alloc_swiotlb(struct device *dev, size_t size) +{ + struct page *page = swiotlb_alloc(dev, size); + + if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) { + swiotlb_free(dev, page, size); + return NULL; + } + + return page; +} + +static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, + gfp_t gfp, bool allow_highmem) +{ + int node = dev_to_node(dev); + struct page *page = NULL; + u64 phys_limit; + + WARN_ON_ONCE(!PAGE_ALIGNED(size)); + + if (is_swiotlb_for_alloc(dev)) + return dma_direct_alloc_swiotlb(dev, size); + + gfp |= dma_direct_optimal_gfp_mask(dev, &phys_limit); + page = dma_alloc_contiguous(dev, size, gfp); + if (page) { + if (!dma_coherent_ok(dev, page_to_phys(page), size) || + (!allow_highmem && PageHighMem(page))) { + dma_free_contiguous(dev, page, size); + page = NULL; + } + } +again: + if (!page) + page = alloc_pages_node(node, gfp, get_order(size)); + if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) { + dma_free_contiguous(dev, page, size); + page = NULL; + + if (IS_ENABLED(CONFIG_ZONE_DMA32) && + phys_limit < DMA_BIT_MASK(64) && + !(gfp & (GFP_DMA32 | GFP_DMA))) { + gfp |= GFP_DMA32; + goto again; + } + + if (IS_ENABLED(CONFIG_ZONE_DMA) && !(gfp & GFP_DMA)) { + gfp = (gfp & ~GFP_DMA32) | GFP_DMA; + goto again; + } + } + + return page; +} + +/* + * Check if a potentially blocking operations needs to dip into the atomic + * pools for the given device/gfp. + */ +static bool dma_direct_use_pool(struct device *dev, gfp_t gfp) +{ + return !gfpflags_allow_blocking(gfp) && !is_swiotlb_for_alloc(dev); +} + +static void *dma_direct_alloc_from_pool(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t gfp) +{ + struct page *page; + u64 phys_limit; + void *ret; + + if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_DMA_COHERENT_POOL))) + return NULL; + + gfp |= dma_direct_optimal_gfp_mask(dev, &phys_limit); + page = dma_alloc_from_pool(dev, size, &ret, gfp, dma_coherent_ok); + if (!page) + return NULL; + *dma_handle = phys_to_dma_direct(dev, page_to_phys(page)); + return ret; +} + +static void *dma_direct_alloc_no_mapping(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t gfp) +{ + struct page *page; + + page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO, true); + if (!page) + return NULL; + + /* remove any dirty cache lines on the kernel alias */ + if (!PageHighMem(page)) + arch_dma_prep_coherent(page, size); + + /* return the page pointer as the opaque cookie */ + *dma_handle = phys_to_dma_direct(dev, page_to_phys(page)); + return page; +} + +void *dma_direct_alloc(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) +{ + bool remap = false, set_uncached = false; + struct page *page; + void *ret; + + size = PAGE_ALIGN(size); + if (attrs & DMA_ATTR_NO_WARN) + gfp |= __GFP_NOWARN; + + if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) && + !force_dma_unencrypted(dev) && !is_swiotlb_for_alloc(dev)) + return dma_direct_alloc_no_mapping(dev, size, dma_handle, gfp); + + if (!dev_is_dma_coherent(dev)) { + /* + * Fallback to the arch handler if it exists. This should + * eventually go away. + */ + if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) && + !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && + !IS_ENABLED(CONFIG_DMA_GLOBAL_POOL) && + !is_swiotlb_for_alloc(dev)) + return arch_dma_alloc(dev, size, dma_handle, gfp, + attrs); + + /* + * If there is a global pool, always allocate from it for + * non-coherent devices. + */ + if (IS_ENABLED(CONFIG_DMA_GLOBAL_POOL)) + return dma_alloc_from_global_coherent(dev, size, + dma_handle); + + /* + * Otherwise remap if the architecture is asking for it. But + * given that remapping memory is a blocking operation we'll + * instead have to dip into the atomic pools. + */ + remap = IS_ENABLED(CONFIG_DMA_DIRECT_REMAP); + if (remap) { + if (dma_direct_use_pool(dev, gfp)) + return dma_direct_alloc_from_pool(dev, size, + dma_handle, gfp); + } else { + if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED)) + return NULL; + set_uncached = true; + } + } + + /* + * Decrypting memory may block, so allocate the memory from the atomic + * pools if we can't block. + */ + if (force_dma_unencrypted(dev) && dma_direct_use_pool(dev, gfp)) + return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp); + + /* we always manually zero the memory once we are done */ + page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO, true); + if (!page) + return NULL; + + /* + * dma_alloc_contiguous can return highmem pages depending on a + * combination the cma= arguments and per-arch setup. These need to be + * remapped to return a kernel virtual address. + */ + if (PageHighMem(page)) { + remap = true; + set_uncached = false; + } + + if (remap) { + pgprot_t prot = dma_pgprot(dev, PAGE_KERNEL, attrs); + + if (force_dma_unencrypted(dev)) + prot = pgprot_decrypted(prot); + + /* remove any dirty cache lines on the kernel alias */ + arch_dma_prep_coherent(page, size); + + /* create a coherent mapping */ + ret = dma_common_contiguous_remap(page, size, prot, + __builtin_return_address(0)); + if (!ret) + goto out_free_pages; + } else { + ret = page_address(page); + if (dma_set_decrypted(dev, ret, size)) + goto out_free_pages; + } + + memset(ret, 0, size); + + if (set_uncached) { + arch_dma_prep_coherent(page, size); + ret = arch_dma_set_uncached(ret, size); + if (IS_ERR(ret)) + goto out_encrypt_pages; + } + + *dma_handle = phys_to_dma_direct(dev, page_to_phys(page)); + return ret; + +out_encrypt_pages: + if (dma_set_encrypted(dev, page_address(page), size)) + return NULL; +out_free_pages: + __dma_direct_free_pages(dev, page, size); + return NULL; +} + +void dma_direct_free(struct device *dev, size_t size, + void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs) +{ + unsigned int page_order = get_order(size); + + if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) && + !force_dma_unencrypted(dev) && !is_swiotlb_for_alloc(dev)) { + /* cpu_addr is a struct page cookie, not a kernel address */ + dma_free_contiguous(dev, cpu_addr, size); + return; + } + + if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) && + !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && + !IS_ENABLED(CONFIG_DMA_GLOBAL_POOL) && + !dev_is_dma_coherent(dev) && + !is_swiotlb_for_alloc(dev)) { + arch_dma_free(dev, size, cpu_addr, dma_addr, attrs); + return; + } + + if (IS_ENABLED(CONFIG_DMA_GLOBAL_POOL) && + !dev_is_dma_coherent(dev)) { + if (!dma_release_from_global_coherent(page_order, cpu_addr)) + WARN_ON_ONCE(1); + return; + } + + /* If cpu_addr is not from an atomic pool, dma_free_from_pool() fails */ + if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) && + dma_free_from_pool(dev, cpu_addr, PAGE_ALIGN(size))) + return; + + if (is_vmalloc_addr(cpu_addr)) { + vunmap(cpu_addr); + } else { + if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_CLEAR_UNCACHED)) + arch_dma_clear_uncached(cpu_addr, size); + if (dma_set_encrypted(dev, cpu_addr, size)) + return; + } + + __dma_direct_free_pages(dev, dma_direct_to_page(dev, dma_addr), size); +} + +struct page *dma_direct_alloc_pages(struct device *dev, size_t size, + dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp) +{ + struct page *page; + void *ret; + + if (force_dma_unencrypted(dev) && dma_direct_use_pool(dev, gfp)) + return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp); + + page = __dma_direct_alloc_pages(dev, size, gfp, false); + if (!page) + return NULL; + + ret = page_address(page); + if (dma_set_decrypted(dev, ret, size)) + goto out_free_pages; + memset(ret, 0, size); + *dma_handle = phys_to_dma_direct(dev, page_to_phys(page)); + return page; +out_free_pages: + __dma_direct_free_pages(dev, page, size); + return NULL; +} + +void dma_direct_free_pages(struct device *dev, size_t size, + struct page *page, dma_addr_t dma_addr, + enum dma_data_direction dir) +{ + void *vaddr = page_address(page); + + /* If cpu_addr is not from an atomic pool, dma_free_from_pool() fails */ + if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) && + dma_free_from_pool(dev, vaddr, size)) + return; + + if (dma_set_encrypted(dev, vaddr, size)) + return; + __dma_direct_free_pages(dev, page, size); +} + +#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ + defined(CONFIG_SWIOTLB) +void dma_direct_sync_sg_for_device(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir) +{ + struct scatterlist *sg; + int i; + + for_each_sg(sgl, sg, nents, i) { + phys_addr_t paddr = dma_to_phys(dev, sg_dma_address(sg)); + + if (unlikely(is_swiotlb_buffer(dev, paddr))) + swiotlb_sync_single_for_device(dev, paddr, sg->length, + dir); + + if (!dev_is_dma_coherent(dev)) + arch_sync_dma_for_device(paddr, sg->length, + dir); + } +} +#endif + +#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \ + defined(CONFIG_SWIOTLB) +void dma_direct_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir) +{ + struct scatterlist *sg; + int i; + + for_each_sg(sgl, sg, nents, i) { + phys_addr_t paddr = dma_to_phys(dev, sg_dma_address(sg)); + + if (!dev_is_dma_coherent(dev)) + arch_sync_dma_for_cpu(paddr, sg->length, dir); + + if (unlikely(is_swiotlb_buffer(dev, paddr))) + swiotlb_sync_single_for_cpu(dev, paddr, sg->length, + dir); + + if (dir == DMA_FROM_DEVICE) + arch_dma_mark_clean(paddr, sg->length); + } + + if (!dev_is_dma_coherent(dev)) + arch_sync_dma_for_cpu_all(); +} + +/* + * Unmaps segments, except for ones marked as pci_p2pdma which do not + * require any further action as they contain a bus address. + */ +void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, + int nents, enum dma_data_direction dir, unsigned long attrs) +{ + struct scatterlist *sg; + int i; + + for_each_sg(sgl, sg, nents, i) { + if (sg_dma_is_bus_address(sg)) + sg_dma_unmark_bus_address(sg); + else + dma_direct_unmap_page(dev, sg->dma_address, + sg_dma_len(sg), dir, attrs); + } +} +#endif + +int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, + enum dma_data_direction dir, unsigned long attrs) +{ + struct pci_p2pdma_map_state p2pdma_state = {}; + enum pci_p2pdma_map_type map; + struct scatterlist *sg; + int i, ret; + + for_each_sg(sgl, sg, nents, i) { + if (is_pci_p2pdma_page(sg_page(sg))) { + map = pci_p2pdma_map_segment(&p2pdma_state, dev, sg); + switch (map) { + case PCI_P2PDMA_MAP_BUS_ADDR: + continue; + case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE: + /* + * Any P2P mapping that traverses the PCI + * host bridge must be mapped with CPU physical + * address and not PCI bus addresses. This is + * done with dma_direct_map_page() below. + */ + break; + default: + ret = -EREMOTEIO; + goto out_unmap; + } + } + + sg->dma_address = dma_direct_map_page(dev, sg_page(sg), + sg->offset, sg->length, dir, attrs); + if (sg->dma_address == DMA_MAPPING_ERROR) { + ret = -EIO; + goto out_unmap; + } + sg_dma_len(sg) = sg->length; + } + + return nents; + +out_unmap: + dma_direct_unmap_sg(dev, sgl, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC); + return ret; +} + +dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr, + size_t size, enum dma_data_direction dir, unsigned long attrs) +{ + dma_addr_t dma_addr = paddr; + + if (unlikely(!dma_capable(dev, dma_addr, size, false))) { + dev_err_once(dev, + "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n", + &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit); + WARN_ON_ONCE(1); + return DMA_MAPPING_ERROR; + } + + return dma_addr; +} + +int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs) +{ + struct page *page = dma_direct_to_page(dev, dma_addr); + int ret; + + ret = sg_alloc_table(sgt, 1, GFP_KERNEL); + if (!ret) + sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0); + return ret; +} + +bool dma_direct_can_mmap(struct device *dev) +{ + return dev_is_dma_coherent(dev) || + IS_ENABLED(CONFIG_DMA_NONCOHERENT_MMAP); +} + +int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs) +{ + unsigned long user_count = vma_pages(vma); + unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; + unsigned long pfn = PHYS_PFN(dma_to_phys(dev, dma_addr)); + int ret = -ENXIO; + + vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs); + if (force_dma_unencrypted(dev)) + vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot); + + if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret)) + return ret; + if (dma_mmap_from_global_coherent(vma, cpu_addr, size, &ret)) + return ret; + + if (vma->vm_pgoff >= count || user_count > count - vma->vm_pgoff) + return -ENXIO; + return remap_pfn_range(vma, vma->vm_start, pfn + vma->vm_pgoff, + user_count << PAGE_SHIFT, vma->vm_page_prot); +} + +int dma_direct_supported(struct device *dev, u64 mask) +{ + u64 min_mask = (max_pfn - 1) << PAGE_SHIFT; + + /* + * Because 32-bit DMA masks are so common we expect every architecture + * to be able to satisfy them - either by not supporting more physical + * memory, or by providing a ZONE_DMA32. If neither is the case, the + * architecture needs to use an IOMMU instead of the direct mapping. + */ + if (mask >= DMA_BIT_MASK(32)) + return 1; + + /* + * This check needs to be against the actual bit mask value, so use + * phys_to_dma_unencrypted() here so that the SME encryption mask isn't + * part of the check. + */ + if (IS_ENABLED(CONFIG_ZONE_DMA)) + min_mask = min_t(u64, min_mask, DMA_BIT_MASK(zone_dma_bits)); + return mask >= phys_to_dma_unencrypted(dev, min_mask); +} + +size_t dma_direct_max_mapping_size(struct device *dev) +{ + /* If SWIOTLB is active, use its maximum mapping size */ + if (is_swiotlb_active(dev) && + (dma_addressing_limited(dev) || is_swiotlb_force_bounce(dev))) + return swiotlb_max_mapping_size(dev); + return SIZE_MAX; +} + +bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr) +{ + return !dev_is_dma_coherent(dev) || + is_swiotlb_buffer(dev, dma_to_phys(dev, dma_addr)); +} + +/** + * dma_direct_set_offset - Assign scalar offset for a single DMA range. + * @dev: device pointer; needed to "own" the alloced memory. + * @cpu_start: beginning of memory region covered by this offset. + * @dma_start: beginning of DMA/PCI region covered by this offset. + * @size: size of the region. + * + * This is for the simple case of a uniform offset which cannot + * be discovered by "dma-ranges". + * + * It returns -ENOMEM if out of memory, -EINVAL if a map + * already exists, 0 otherwise. + * + * Note: any call to this from a driver is a bug. The mapping needs + * to be described by the device tree or other firmware interfaces. + */ +int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start, + dma_addr_t dma_start, u64 size) +{ + struct bus_dma_region *map; + u64 offset = (u64)cpu_start - (u64)dma_start; + + if (dev->dma_range_map) { + dev_err(dev, "attempt to add DMA range to existing map\n"); + return -EINVAL; + } + + if (!offset) + return 0; + + map = kcalloc(2, sizeof(*map), GFP_KERNEL); + if (!map) + return -ENOMEM; + map[0].cpu_start = cpu_start; + map[0].dma_start = dma_start; + map[0].offset = offset; + map[0].size = size; + dev->dma_range_map = map; + return 0; +} diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h new file mode 100644 index 000000000..97ec892ea --- /dev/null +++ b/kernel/dma/direct.h @@ -0,0 +1,127 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2018 Christoph Hellwig. + * + * DMA operations that map physical memory directly without using an IOMMU. + */ +#ifndef _KERNEL_DMA_DIRECT_H +#define _KERNEL_DMA_DIRECT_H + +#include +#include + +int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs); +bool dma_direct_can_mmap(struct device *dev); +int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs); +bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr); +int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, + enum dma_data_direction dir, unsigned long attrs); +size_t dma_direct_max_mapping_size(struct device *dev); + +#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ + defined(CONFIG_SWIOTLB) +void dma_direct_sync_sg_for_device(struct device *dev, struct scatterlist *sgl, + int nents, enum dma_data_direction dir); +#else +static inline void dma_direct_sync_sg_for_device(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir) +{ +} +#endif + +#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \ + defined(CONFIG_SWIOTLB) +void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, + int nents, enum dma_data_direction dir, unsigned long attrs); +void dma_direct_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir); +#else +static inline void dma_direct_unmap_sg(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir, + unsigned long attrs) +{ +} +static inline void dma_direct_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir) +{ +} +#endif + +static inline void dma_direct_sync_single_for_device(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir) +{ + phys_addr_t paddr = dma_to_phys(dev, addr); + + if (unlikely(is_swiotlb_buffer(dev, paddr))) + swiotlb_sync_single_for_device(dev, paddr, size, dir); + + if (!dev_is_dma_coherent(dev)) + arch_sync_dma_for_device(paddr, size, dir); +} + +static inline void dma_direct_sync_single_for_cpu(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir) +{ + phys_addr_t paddr = dma_to_phys(dev, addr); + + if (!dev_is_dma_coherent(dev)) { + arch_sync_dma_for_cpu(paddr, size, dir); + arch_sync_dma_for_cpu_all(); + } + + if (unlikely(is_swiotlb_buffer(dev, paddr))) + swiotlb_sync_single_for_cpu(dev, paddr, size, dir); + + if (dir == DMA_FROM_DEVICE) + arch_dma_mark_clean(paddr, size); +} + +static inline dma_addr_t dma_direct_map_page(struct device *dev, + struct page *page, unsigned long offset, size_t size, + enum dma_data_direction dir, unsigned long attrs) +{ + phys_addr_t phys = page_to_phys(page) + offset; + dma_addr_t dma_addr = phys_to_dma(dev, phys); + + if (is_swiotlb_force_bounce(dev)) { + if (is_pci_p2pdma_page(page)) + return DMA_MAPPING_ERROR; + return swiotlb_map(dev, phys, size, dir, attrs); + } + + if (unlikely(!dma_capable(dev, dma_addr, size, true)) || + dma_kmalloc_needs_bounce(dev, size, dir)) { + if (is_pci_p2pdma_page(page)) + return DMA_MAPPING_ERROR; + if (is_swiotlb_active(dev)) + return swiotlb_map(dev, phys, size, dir, attrs); + + dev_WARN_ONCE(dev, 1, + "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n", + &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit); + return DMA_MAPPING_ERROR; + } + + if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + arch_sync_dma_for_device(phys, size, dir); + return dma_addr; +} + +static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir, unsigned long attrs) +{ + phys_addr_t phys = dma_to_phys(dev, addr); + + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + dma_direct_sync_single_for_cpu(dev, addr, size, dir); + + if (unlikely(is_swiotlb_buffer(dev, phys))) + swiotlb_tbl_unmap_single(dev, phys, size, dir, + attrs | DMA_ATTR_SKIP_CPU_SYNC); +} +#endif /* _KERNEL_DMA_DIRECT_H */ diff --git a/kernel/dma/dummy.c b/kernel/dma/dummy.c new file mode 100644 index 000000000..b492d59ac --- /dev/null +++ b/kernel/dma/dummy.c @@ -0,0 +1,38 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Dummy DMA ops that always fail. + */ +#include + +static int dma_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 dma_dummy_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, enum dma_data_direction dir, + unsigned long attrs) +{ + return DMA_MAPPING_ERROR; +} + +static int dma_dummy_map_sg(struct device *dev, struct scatterlist *sgl, + int nelems, enum dma_data_direction dir, + unsigned long attrs) +{ + return -EINVAL; +} + +static int dma_dummy_supported(struct device *hwdev, u64 mask) +{ + return 0; +} + +const struct dma_map_ops dma_dummy_ops = { + .mmap = dma_dummy_mmap, + .map_page = dma_dummy_map_page, + .map_sg = dma_dummy_map_sg, + .dma_supported = dma_dummy_supported, +}; diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c new file mode 100644 index 000000000..02205ab53 --- /dev/null +++ b/kernel/dma/map_benchmark.c @@ -0,0 +1,358 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020 HiSilicon Limited. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct map_benchmark_data { + struct map_benchmark bparam; + struct device *dev; + struct dentry *debugfs; + enum dma_data_direction dir; + atomic64_t sum_map_100ns; + atomic64_t sum_unmap_100ns; + atomic64_t sum_sq_map; + atomic64_t sum_sq_unmap; + atomic64_t loops; +}; + +static int map_benchmark_thread(void *data) +{ + void *buf; + dma_addr_t dma_addr; + struct map_benchmark_data *map = data; + int npages = map->bparam.granule; + u64 size = npages * PAGE_SIZE; + int ret = 0; + + buf = alloc_pages_exact(size, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + while (!kthread_should_stop()) { + u64 map_100ns, unmap_100ns, map_sq, unmap_sq; + ktime_t map_stime, map_etime, unmap_stime, unmap_etime; + ktime_t map_delta, unmap_delta; + + /* + * for a non-coherent device, if we don't stain them in the + * cache, this will give an underestimate of the real-world + * overhead of BIDIRECTIONAL or TO_DEVICE mappings; + * 66 means evertything goes well! 66 is lucky. + */ + if (map->dir != DMA_FROM_DEVICE) + memset(buf, 0x66, size); + + map_stime = ktime_get(); + dma_addr = dma_map_single(map->dev, buf, size, map->dir); + if (unlikely(dma_mapping_error(map->dev, dma_addr))) { + pr_err("dma_map_single failed on %s\n", + dev_name(map->dev)); + ret = -ENOMEM; + goto out; + } + map_etime = ktime_get(); + map_delta = ktime_sub(map_etime, map_stime); + + /* Pretend DMA is transmitting */ + ndelay(map->bparam.dma_trans_ns); + + unmap_stime = ktime_get(); + dma_unmap_single(map->dev, dma_addr, size, map->dir); + unmap_etime = ktime_get(); + unmap_delta = ktime_sub(unmap_etime, unmap_stime); + + /* calculate sum and sum of squares */ + + map_100ns = div64_ul(map_delta, 100); + unmap_100ns = div64_ul(unmap_delta, 100); + map_sq = map_100ns * map_100ns; + unmap_sq = unmap_100ns * unmap_100ns; + + atomic64_add(map_100ns, &map->sum_map_100ns); + atomic64_add(unmap_100ns, &map->sum_unmap_100ns); + atomic64_add(map_sq, &map->sum_sq_map); + atomic64_add(unmap_sq, &map->sum_sq_unmap); + atomic64_inc(&map->loops); + } + +out: + free_pages_exact(buf, size); + return ret; +} + +static int do_map_benchmark(struct map_benchmark_data *map) +{ + struct task_struct **tsk; + int threads = map->bparam.threads; + int node = map->bparam.node; + const cpumask_t *cpu_mask = cpumask_of_node(node); + u64 loops; + int ret = 0; + int i; + + tsk = kmalloc_array(threads, sizeof(*tsk), GFP_KERNEL); + if (!tsk) + return -ENOMEM; + + get_device(map->dev); + + for (i = 0; i < threads; i++) { + tsk[i] = kthread_create_on_node(map_benchmark_thread, map, + map->bparam.node, "dma-map-benchmark/%d", i); + if (IS_ERR(tsk[i])) { + pr_err("create dma_map thread failed\n"); + ret = PTR_ERR(tsk[i]); + goto out; + } + + if (node != NUMA_NO_NODE) + kthread_bind_mask(tsk[i], cpu_mask); + } + + /* clear the old value in the previous benchmark */ + atomic64_set(&map->sum_map_100ns, 0); + atomic64_set(&map->sum_unmap_100ns, 0); + atomic64_set(&map->sum_sq_map, 0); + atomic64_set(&map->sum_sq_unmap, 0); + atomic64_set(&map->loops, 0); + + for (i = 0; i < threads; i++) { + get_task_struct(tsk[i]); + wake_up_process(tsk[i]); + } + + msleep_interruptible(map->bparam.seconds * 1000); + + /* wait for the completion of benchmark threads */ + for (i = 0; i < threads; i++) { + ret = kthread_stop(tsk[i]); + if (ret) + goto out; + } + + loops = atomic64_read(&map->loops); + if (likely(loops > 0)) { + u64 map_variance, unmap_variance; + u64 sum_map = atomic64_read(&map->sum_map_100ns); + u64 sum_unmap = atomic64_read(&map->sum_unmap_100ns); + u64 sum_sq_map = atomic64_read(&map->sum_sq_map); + u64 sum_sq_unmap = atomic64_read(&map->sum_sq_unmap); + + /* average latency */ + map->bparam.avg_map_100ns = div64_u64(sum_map, loops); + map->bparam.avg_unmap_100ns = div64_u64(sum_unmap, loops); + + /* standard deviation of latency */ + map_variance = div64_u64(sum_sq_map, loops) - + map->bparam.avg_map_100ns * + map->bparam.avg_map_100ns; + unmap_variance = div64_u64(sum_sq_unmap, loops) - + map->bparam.avg_unmap_100ns * + map->bparam.avg_unmap_100ns; + map->bparam.map_stddev = int_sqrt64(map_variance); + map->bparam.unmap_stddev = int_sqrt64(unmap_variance); + } + +out: + for (i = 0; i < threads; i++) + put_task_struct(tsk[i]); + put_device(map->dev); + kfree(tsk); + return ret; +} + +static long map_benchmark_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + struct map_benchmark_data *map = file->private_data; + void __user *argp = (void __user *)arg; + u64 old_dma_mask; + int ret; + + if (copy_from_user(&map->bparam, argp, sizeof(map->bparam))) + return -EFAULT; + + switch (cmd) { + case DMA_MAP_BENCHMARK: + if (map->bparam.threads == 0 || + map->bparam.threads > DMA_MAP_MAX_THREADS) { + pr_err("invalid thread number\n"); + return -EINVAL; + } + + if (map->bparam.seconds == 0 || + map->bparam.seconds > DMA_MAP_MAX_SECONDS) { + pr_err("invalid duration seconds\n"); + return -EINVAL; + } + + if (map->bparam.dma_trans_ns > DMA_MAP_MAX_TRANS_DELAY) { + pr_err("invalid transmission delay\n"); + return -EINVAL; + } + + if (map->bparam.node != NUMA_NO_NODE && + !node_possible(map->bparam.node)) { + pr_err("invalid numa node\n"); + return -EINVAL; + } + + if (map->bparam.granule < 1 || map->bparam.granule > 1024) { + pr_err("invalid granule size\n"); + return -EINVAL; + } + + switch (map->bparam.dma_dir) { + case DMA_MAP_BIDIRECTIONAL: + map->dir = DMA_BIDIRECTIONAL; + break; + case DMA_MAP_FROM_DEVICE: + map->dir = DMA_FROM_DEVICE; + break; + case DMA_MAP_TO_DEVICE: + map->dir = DMA_TO_DEVICE; + break; + default: + pr_err("invalid DMA direction\n"); + return -EINVAL; + } + + old_dma_mask = dma_get_mask(map->dev); + + ret = dma_set_mask(map->dev, + DMA_BIT_MASK(map->bparam.dma_bits)); + if (ret) { + pr_err("failed to set dma_mask on device %s\n", + dev_name(map->dev)); + return -EINVAL; + } + + ret = do_map_benchmark(map); + + /* + * restore the original dma_mask as many devices' dma_mask are + * set by architectures, acpi, busses. When we bind them back + * to their original drivers, those drivers shouldn't see + * dma_mask changed by benchmark + */ + dma_set_mask(map->dev, old_dma_mask); + break; + default: + return -EINVAL; + } + + if (copy_to_user(argp, &map->bparam, sizeof(map->bparam))) + return -EFAULT; + + return ret; +} + +static const struct file_operations map_benchmark_fops = { + .open = simple_open, + .unlocked_ioctl = map_benchmark_ioctl, +}; + +static void map_benchmark_remove_debugfs(void *data) +{ + struct map_benchmark_data *map = (struct map_benchmark_data *)data; + + debugfs_remove(map->debugfs); +} + +static int __map_benchmark_probe(struct device *dev) +{ + struct dentry *entry; + struct map_benchmark_data *map; + int ret; + + map = devm_kzalloc(dev, sizeof(*map), GFP_KERNEL); + if (!map) + return -ENOMEM; + map->dev = dev; + + ret = devm_add_action(dev, map_benchmark_remove_debugfs, map); + if (ret) { + pr_err("Can't add debugfs remove action\n"); + return ret; + } + + /* + * we only permit a device bound with this driver, 2nd probe + * will fail + */ + entry = debugfs_create_file("dma_map_benchmark", 0600, NULL, map, + &map_benchmark_fops); + if (IS_ERR(entry)) + return PTR_ERR(entry); + map->debugfs = entry; + + return 0; +} + +static int map_benchmark_platform_probe(struct platform_device *pdev) +{ + return __map_benchmark_probe(&pdev->dev); +} + +static struct platform_driver map_benchmark_platform_driver = { + .driver = { + .name = "dma_map_benchmark", + }, + .probe = map_benchmark_platform_probe, +}; + +static int +map_benchmark_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + return __map_benchmark_probe(&pdev->dev); +} + +static struct pci_driver map_benchmark_pci_driver = { + .name = "dma_map_benchmark", + .probe = map_benchmark_pci_probe, +}; + +static int __init map_benchmark_init(void) +{ + int ret; + + ret = pci_register_driver(&map_benchmark_pci_driver); + if (ret) + return ret; + + ret = platform_driver_register(&map_benchmark_platform_driver); + if (ret) { + pci_unregister_driver(&map_benchmark_pci_driver); + return ret; + } + + return 0; +} + +static void __exit map_benchmark_cleanup(void) +{ + platform_driver_unregister(&map_benchmark_platform_driver); + pci_unregister_driver(&map_benchmark_pci_driver); +} + +module_init(map_benchmark_init); +module_exit(map_benchmark_cleanup); + +MODULE_AUTHOR("Barry Song "); +MODULE_DESCRIPTION("dma_map benchmark driver"); diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c new file mode 100644 index 000000000..e323ca48f --- /dev/null +++ b/kernel/dma/mapping.c @@ -0,0 +1,841 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * arch-independent dma-mapping routines + * + * Copyright (c) 2006 SUSE Linux Products GmbH + * Copyright (c) 2006 Tejun Heo + */ +#include /* for max_pfn */ +#include +#include +#include +#include +#include +#include +#include +#include +#include "debug.h" +#include "direct.h" + +#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) +bool dma_default_coherent = IS_ENABLED(CONFIG_ARCH_DMA_DEFAULT_COHERENT); +#endif + +/* + * Managed DMA API + */ +struct dma_devres { + size_t size; + void *vaddr; + dma_addr_t dma_handle; + unsigned long attrs; +}; + +static void dmam_release(struct device *dev, void *res) +{ + struct dma_devres *this = res; + + dma_free_attrs(dev, this->size, this->vaddr, this->dma_handle, + this->attrs); +} + +static int dmam_match(struct device *dev, void *res, void *match_data) +{ + struct dma_devres *this = res, *match = match_data; + + if (this->vaddr == match->vaddr) { + WARN_ON(this->size != match->size || + this->dma_handle != match->dma_handle); + return 1; + } + return 0; +} + +/** + * dmam_free_coherent - Managed dma_free_coherent() + * @dev: Device to free coherent memory for + * @size: Size of allocation + * @vaddr: Virtual address of the memory to free + * @dma_handle: DMA handle of the memory to free + * + * Managed dma_free_coherent(). + */ +void dmam_free_coherent(struct device *dev, size_t size, void *vaddr, + dma_addr_t dma_handle) +{ + struct dma_devres match_data = { size, vaddr, dma_handle }; + + dma_free_coherent(dev, size, vaddr, dma_handle); + WARN_ON(devres_destroy(dev, dmam_release, dmam_match, &match_data)); +} +EXPORT_SYMBOL(dmam_free_coherent); + +/** + * dmam_alloc_attrs - Managed dma_alloc_attrs() + * @dev: Device to allocate non_coherent memory for + * @size: Size of allocation + * @dma_handle: Out argument for allocated DMA handle + * @gfp: Allocation flags + * @attrs: Flags in the DMA_ATTR_* namespace. + * + * Managed dma_alloc_attrs(). Memory allocated using this function will be + * automatically released on driver detach. + * + * RETURNS: + * Pointer to allocated memory on success, NULL on failure. + */ +void *dmam_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, + gfp_t gfp, unsigned long attrs) +{ + struct dma_devres *dr; + void *vaddr; + + dr = devres_alloc(dmam_release, sizeof(*dr), gfp); + if (!dr) + return NULL; + + vaddr = dma_alloc_attrs(dev, size, dma_handle, gfp, attrs); + if (!vaddr) { + devres_free(dr); + return NULL; + } + + dr->vaddr = vaddr; + dr->dma_handle = *dma_handle; + dr->size = size; + dr->attrs = attrs; + + devres_add(dev, dr); + + return vaddr; +} +EXPORT_SYMBOL(dmam_alloc_attrs); + +static bool dma_go_direct(struct device *dev, dma_addr_t mask, + const struct dma_map_ops *ops) +{ + if (likely(!ops)) + return true; +#ifdef CONFIG_DMA_OPS_BYPASS + if (dev->dma_ops_bypass) + return min_not_zero(mask, dev->bus_dma_limit) >= + dma_direct_get_required_mask(dev); +#endif + return false; +} + + +/* + * Check if the devices uses a direct mapping for streaming DMA operations. + * This allows IOMMU drivers to set a bypass mode if the DMA mask is large + * enough. + */ +static inline bool dma_alloc_direct(struct device *dev, + const struct dma_map_ops *ops) +{ + return dma_go_direct(dev, dev->coherent_dma_mask, ops); +} + +static inline bool dma_map_direct(struct device *dev, + const struct dma_map_ops *ops) +{ + return dma_go_direct(dev, *dev->dma_mask, ops); +} + +dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page, + size_t offset, size_t size, enum dma_data_direction dir, + unsigned long attrs) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + dma_addr_t addr; + + BUG_ON(!valid_dma_direction(dir)); + + if (WARN_ON_ONCE(!dev->dma_mask)) + return DMA_MAPPING_ERROR; + + if (dma_map_direct(dev, ops) || + arch_dma_map_page_direct(dev, page_to_phys(page) + offset + size)) + addr = dma_direct_map_page(dev, page, offset, size, dir, attrs); + else + addr = ops->map_page(dev, page, offset, size, dir, attrs); + kmsan_handle_dma(page, offset, size, dir); + debug_dma_map_page(dev, page, offset, size, dir, addr, attrs); + + return addr; +} +EXPORT_SYMBOL(dma_map_page_attrs); + +void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size, + enum dma_data_direction dir, unsigned long attrs) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + BUG_ON(!valid_dma_direction(dir)); + if (dma_map_direct(dev, ops) || + arch_dma_unmap_page_direct(dev, addr + size)) + dma_direct_unmap_page(dev, addr, size, dir, attrs); + else if (ops->unmap_page) + ops->unmap_page(dev, addr, size, dir, attrs); + debug_dma_unmap_page(dev, addr, size, dir); +} +EXPORT_SYMBOL(dma_unmap_page_attrs); + +static int __dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir, unsigned long attrs) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + int ents; + + BUG_ON(!valid_dma_direction(dir)); + + if (WARN_ON_ONCE(!dev->dma_mask)) + return 0; + + if (dma_map_direct(dev, ops) || + arch_dma_map_sg_direct(dev, sg, nents)) + ents = dma_direct_map_sg(dev, sg, nents, dir, attrs); + else + ents = ops->map_sg(dev, sg, nents, dir, attrs); + + if (ents > 0) { + kmsan_handle_dma_sg(sg, nents, dir); + debug_dma_map_sg(dev, sg, nents, ents, dir, attrs); + } else if (WARN_ON_ONCE(ents != -EINVAL && ents != -ENOMEM && + ents != -EIO && ents != -EREMOTEIO)) { + return -EIO; + } + + return ents; +} + +/** + * dma_map_sg_attrs - Map the given buffer for DMA + * @dev: The device for which to perform the DMA operation + * @sg: The sg_table object describing the buffer + * @nents: Number of entries to map + * @dir: DMA direction + * @attrs: Optional DMA attributes for the map operation + * + * Maps a buffer described by a scatterlist passed in the sg argument with + * nents segments for the @dir DMA operation by the @dev device. + * + * Returns the number of mapped entries (which can be less than nents) + * on success. Zero is returned for any error. + * + * dma_unmap_sg_attrs() should be used to unmap the buffer with the + * original sg and original nents (not the value returned by this funciton). + */ +unsigned int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir, unsigned long attrs) +{ + int ret; + + ret = __dma_map_sg_attrs(dev, sg, nents, dir, attrs); + if (ret < 0) + return 0; + return ret; +} +EXPORT_SYMBOL(dma_map_sg_attrs); + +/** + * dma_map_sgtable - Map the given buffer for DMA + * @dev: The device for which to perform the DMA operation + * @sgt: The sg_table object describing the buffer + * @dir: DMA direction + * @attrs: Optional DMA attributes for the map operation + * + * Maps a buffer described by a scatterlist stored in the given sg_table + * object for the @dir DMA operation by the @dev device. After success, the + * ownership for the buffer is transferred to the DMA domain. One has to + * call dma_sync_sgtable_for_cpu() or dma_unmap_sgtable() to move the + * ownership of the buffer back to the CPU domain before touching the + * buffer by the CPU. + * + * Returns 0 on success or a negative error code on error. The following + * error codes are supported with the given meaning: + * + * -EINVAL An invalid argument, unaligned access or other error + * in usage. Will not succeed if retried. + * -ENOMEM Insufficient resources (like memory or IOVA space) to + * complete the mapping. Should succeed if retried later. + * -EIO Legacy error code with an unknown meaning. eg. this is + * returned if a lower level call returned + * DMA_MAPPING_ERROR. + * -EREMOTEIO The DMA device cannot access P2PDMA memory specified + * in the sg_table. This will not succeed if retried. + */ +int dma_map_sgtable(struct device *dev, struct sg_table *sgt, + enum dma_data_direction dir, unsigned long attrs) +{ + int nents; + + nents = __dma_map_sg_attrs(dev, sgt->sgl, sgt->orig_nents, dir, attrs); + if (nents < 0) + return nents; + sgt->nents = nents; + return 0; +} +EXPORT_SYMBOL_GPL(dma_map_sgtable); + +void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir, + unsigned long attrs) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + BUG_ON(!valid_dma_direction(dir)); + debug_dma_unmap_sg(dev, sg, nents, dir); + if (dma_map_direct(dev, ops) || + arch_dma_unmap_sg_direct(dev, sg, nents)) + dma_direct_unmap_sg(dev, sg, nents, dir, attrs); + else if (ops->unmap_sg) + ops->unmap_sg(dev, sg, nents, dir, attrs); +} +EXPORT_SYMBOL(dma_unmap_sg_attrs); + +dma_addr_t dma_map_resource(struct device *dev, phys_addr_t phys_addr, + size_t size, enum dma_data_direction dir, unsigned long attrs) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + dma_addr_t addr = DMA_MAPPING_ERROR; + + BUG_ON(!valid_dma_direction(dir)); + + if (WARN_ON_ONCE(!dev->dma_mask)) + return DMA_MAPPING_ERROR; + + if (dma_map_direct(dev, ops)) + addr = dma_direct_map_resource(dev, phys_addr, size, dir, attrs); + else if (ops->map_resource) + addr = ops->map_resource(dev, phys_addr, size, dir, attrs); + + debug_dma_map_resource(dev, phys_addr, size, dir, addr, attrs); + return addr; +} +EXPORT_SYMBOL(dma_map_resource); + +void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size, + enum dma_data_direction dir, unsigned long attrs) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + BUG_ON(!valid_dma_direction(dir)); + if (!dma_map_direct(dev, ops) && ops->unmap_resource) + ops->unmap_resource(dev, addr, size, dir, attrs); + debug_dma_unmap_resource(dev, addr, size, dir); +} +EXPORT_SYMBOL(dma_unmap_resource); + +void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, + enum dma_data_direction dir) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + BUG_ON(!valid_dma_direction(dir)); + if (dma_map_direct(dev, ops)) + dma_direct_sync_single_for_cpu(dev, addr, size, dir); + else if (ops->sync_single_for_cpu) + ops->sync_single_for_cpu(dev, addr, size, dir); + debug_dma_sync_single_for_cpu(dev, addr, size, dir); +} +EXPORT_SYMBOL(dma_sync_single_for_cpu); + +void dma_sync_single_for_device(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + BUG_ON(!valid_dma_direction(dir)); + if (dma_map_direct(dev, ops)) + dma_direct_sync_single_for_device(dev, addr, size, dir); + else if (ops->sync_single_for_device) + ops->sync_single_for_device(dev, addr, size, dir); + debug_dma_sync_single_for_device(dev, addr, size, dir); +} +EXPORT_SYMBOL(dma_sync_single_for_device); + +void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, + int nelems, enum dma_data_direction dir) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + BUG_ON(!valid_dma_direction(dir)); + if (dma_map_direct(dev, ops)) + dma_direct_sync_sg_for_cpu(dev, sg, nelems, dir); + else if (ops->sync_sg_for_cpu) + ops->sync_sg_for_cpu(dev, sg, nelems, dir); + debug_dma_sync_sg_for_cpu(dev, sg, nelems, dir); +} +EXPORT_SYMBOL(dma_sync_sg_for_cpu); + +void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, + int nelems, enum dma_data_direction dir) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + BUG_ON(!valid_dma_direction(dir)); + if (dma_map_direct(dev, ops)) + dma_direct_sync_sg_for_device(dev, sg, nelems, dir); + else if (ops->sync_sg_for_device) + ops->sync_sg_for_device(dev, sg, nelems, dir); + debug_dma_sync_sg_for_device(dev, sg, nelems, dir); +} +EXPORT_SYMBOL(dma_sync_sg_for_device); + +/* + * The whole dma_get_sgtable() idea is fundamentally unsafe - it seems + * that the intention is to allow exporting memory allocated via the + * coherent DMA APIs through the dma_buf API, which only accepts a + * scattertable. This presents a couple of problems: + * 1. Not all memory allocated via the coherent DMA APIs is backed by + * a struct page + * 2. Passing coherent DMA memory into the streaming APIs is not allowed + * as we will try to flush the memory through a different alias to that + * actually being used (and the flushes are redundant.) + */ +int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + if (dma_alloc_direct(dev, ops)) + return dma_direct_get_sgtable(dev, sgt, cpu_addr, dma_addr, + size, attrs); + if (!ops->get_sgtable) + return -ENXIO; + return ops->get_sgtable(dev, sgt, cpu_addr, dma_addr, size, attrs); +} +EXPORT_SYMBOL(dma_get_sgtable_attrs); + +#ifdef CONFIG_MMU +/* + * Return the page attributes used for mapping dma_alloc_* memory, either in + * kernel space if remapping is needed, or to userspace through dma_mmap_*. + */ +pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs) +{ + if (dev_is_dma_coherent(dev)) + return prot; +#ifdef CONFIG_ARCH_HAS_DMA_WRITE_COMBINE + if (attrs & DMA_ATTR_WRITE_COMBINE) + return pgprot_writecombine(prot); +#endif + return pgprot_dmacoherent(prot); +} +#endif /* CONFIG_MMU */ + +/** + * dma_can_mmap - check if a given device supports dma_mmap_* + * @dev: device to check + * + * Returns %true if @dev supports dma_mmap_coherent() and dma_mmap_attrs() to + * map DMA allocations to userspace. + */ +bool dma_can_mmap(struct device *dev) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + if (dma_alloc_direct(dev, ops)) + return dma_direct_can_mmap(dev); + return ops->mmap != NULL; +} +EXPORT_SYMBOL_GPL(dma_can_mmap); + +/** + * dma_mmap_attrs - map a coherent DMA allocation into user space + * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices + * @vma: vm_area_struct describing requested user mapping + * @cpu_addr: kernel CPU-view address returned from dma_alloc_attrs + * @dma_addr: device-view address returned from dma_alloc_attrs + * @size: size of memory originally requested in dma_alloc_attrs + * @attrs: attributes of mapping properties requested in dma_alloc_attrs + * + * Map a coherent DMA buffer previously allocated by dma_alloc_attrs into user + * space. The coherent DMA buffer must not be freed by the driver until the + * user space mapping has been released. + */ +int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + if (dma_alloc_direct(dev, ops)) + return dma_direct_mmap(dev, vma, cpu_addr, dma_addr, size, + attrs); + if (!ops->mmap) + return -ENXIO; + return ops->mmap(dev, vma, cpu_addr, dma_addr, size, attrs); +} +EXPORT_SYMBOL(dma_mmap_attrs); + +u64 dma_get_required_mask(struct device *dev) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + if (dma_alloc_direct(dev, ops)) + return dma_direct_get_required_mask(dev); + if (ops->get_required_mask) + return ops->get_required_mask(dev); + + /* + * We require every DMA ops implementation to at least support a 32-bit + * DMA mask (and use bounce buffering if that isn't supported in + * hardware). As the direct mapping code has its own routine to + * actually report an optimal mask we default to 32-bit here as that + * is the right thing for most IOMMUs, and at least not actively + * harmful in general. + */ + return DMA_BIT_MASK(32); +} +EXPORT_SYMBOL_GPL(dma_get_required_mask); + +void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, + gfp_t flag, unsigned long attrs) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + void *cpu_addr; + + WARN_ON_ONCE(!dev->coherent_dma_mask); + + /* + * DMA allocations can never be turned back into a page pointer, so + * requesting compound pages doesn't make sense (and can't even be + * supported at all by various backends). + */ + if (WARN_ON_ONCE(flag & __GFP_COMP)) + return NULL; + + if (dma_alloc_from_dev_coherent(dev, size, dma_handle, &cpu_addr)) + return cpu_addr; + + /* let the implementation decide on the zone to allocate from: */ + flag &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM); + + if (dma_alloc_direct(dev, ops)) + cpu_addr = dma_direct_alloc(dev, size, dma_handle, flag, attrs); + else if (ops->alloc) + cpu_addr = ops->alloc(dev, size, dma_handle, flag, attrs); + else + return NULL; + + debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr, attrs); + return cpu_addr; +} +EXPORT_SYMBOL(dma_alloc_attrs); + +void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t dma_handle, unsigned long attrs) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + if (dma_release_from_dev_coherent(dev, get_order(size), cpu_addr)) + return; + /* + * On non-coherent platforms which implement DMA-coherent buffers via + * non-cacheable remaps, ops->free() may call vunmap(). Thus getting + * this far in IRQ context is a) at risk of a BUG_ON() or trying to + * sleep on some machines, and b) an indication that the driver is + * probably misusing the coherent API anyway. + */ + WARN_ON(irqs_disabled()); + + if (!cpu_addr) + return; + + debug_dma_free_coherent(dev, size, cpu_addr, dma_handle); + if (dma_alloc_direct(dev, ops)) + dma_direct_free(dev, size, cpu_addr, dma_handle, attrs); + else if (ops->free) + ops->free(dev, size, cpu_addr, dma_handle, attrs); +} +EXPORT_SYMBOL(dma_free_attrs); + +static struct page *__dma_alloc_pages(struct device *dev, size_t size, + dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + if (WARN_ON_ONCE(!dev->coherent_dma_mask)) + return NULL; + if (WARN_ON_ONCE(gfp & (__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM))) + return NULL; + if (WARN_ON_ONCE(gfp & __GFP_COMP)) + return NULL; + + size = PAGE_ALIGN(size); + if (dma_alloc_direct(dev, ops)) + return dma_direct_alloc_pages(dev, size, dma_handle, dir, gfp); + if (!ops->alloc_pages) + return NULL; + return ops->alloc_pages(dev, size, dma_handle, dir, gfp); +} + +struct page *dma_alloc_pages(struct device *dev, size_t size, + dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp) +{ + struct page *page = __dma_alloc_pages(dev, size, dma_handle, dir, gfp); + + if (page) + debug_dma_map_page(dev, page, 0, size, dir, *dma_handle, 0); + return page; +} +EXPORT_SYMBOL_GPL(dma_alloc_pages); + +static void __dma_free_pages(struct device *dev, size_t size, struct page *page, + dma_addr_t dma_handle, enum dma_data_direction dir) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + size = PAGE_ALIGN(size); + if (dma_alloc_direct(dev, ops)) + dma_direct_free_pages(dev, size, page, dma_handle, dir); + else if (ops->free_pages) + ops->free_pages(dev, size, page, dma_handle, dir); +} + +void dma_free_pages(struct device *dev, size_t size, struct page *page, + dma_addr_t dma_handle, enum dma_data_direction dir) +{ + debug_dma_unmap_page(dev, dma_handle, size, dir); + __dma_free_pages(dev, size, page, dma_handle, dir); +} +EXPORT_SYMBOL_GPL(dma_free_pages); + +int dma_mmap_pages(struct device *dev, struct vm_area_struct *vma, + size_t size, struct page *page) +{ + unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; + + if (vma->vm_pgoff >= count || vma_pages(vma) > count - vma->vm_pgoff) + return -ENXIO; + return remap_pfn_range(vma, vma->vm_start, + page_to_pfn(page) + vma->vm_pgoff, + vma_pages(vma) << PAGE_SHIFT, vma->vm_page_prot); +} +EXPORT_SYMBOL_GPL(dma_mmap_pages); + +static struct sg_table *alloc_single_sgt(struct device *dev, size_t size, + enum dma_data_direction dir, gfp_t gfp) +{ + struct sg_table *sgt; + struct page *page; + + sgt = kmalloc(sizeof(*sgt), gfp); + if (!sgt) + return NULL; + if (sg_alloc_table(sgt, 1, gfp)) + goto out_free_sgt; + page = __dma_alloc_pages(dev, size, &sgt->sgl->dma_address, dir, gfp); + if (!page) + goto out_free_table; + sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0); + sg_dma_len(sgt->sgl) = sgt->sgl->length; + return sgt; +out_free_table: + sg_free_table(sgt); +out_free_sgt: + kfree(sgt); + return NULL; +} + +struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size, + enum dma_data_direction dir, gfp_t gfp, unsigned long attrs) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + struct sg_table *sgt; + + if (WARN_ON_ONCE(attrs & ~DMA_ATTR_ALLOC_SINGLE_PAGES)) + return NULL; + if (WARN_ON_ONCE(gfp & __GFP_COMP)) + return NULL; + + if (ops && ops->alloc_noncontiguous) + sgt = ops->alloc_noncontiguous(dev, size, dir, gfp, attrs); + else + sgt = alloc_single_sgt(dev, size, dir, gfp); + + if (sgt) { + sgt->nents = 1; + debug_dma_map_sg(dev, sgt->sgl, sgt->orig_nents, 1, dir, attrs); + } + return sgt; +} +EXPORT_SYMBOL_GPL(dma_alloc_noncontiguous); + +static void free_single_sgt(struct device *dev, size_t size, + struct sg_table *sgt, enum dma_data_direction dir) +{ + __dma_free_pages(dev, size, sg_page(sgt->sgl), sgt->sgl->dma_address, + dir); + sg_free_table(sgt); + kfree(sgt); +} + +void dma_free_noncontiguous(struct device *dev, size_t size, + struct sg_table *sgt, enum dma_data_direction dir) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + debug_dma_unmap_sg(dev, sgt->sgl, sgt->orig_nents, dir); + if (ops && ops->free_noncontiguous) + ops->free_noncontiguous(dev, size, sgt, dir); + else + free_single_sgt(dev, size, sgt, dir); +} +EXPORT_SYMBOL_GPL(dma_free_noncontiguous); + +void *dma_vmap_noncontiguous(struct device *dev, size_t size, + struct sg_table *sgt) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; + + if (ops && ops->alloc_noncontiguous) + return vmap(sgt_handle(sgt)->pages, count, VM_MAP, PAGE_KERNEL); + return page_address(sg_page(sgt->sgl)); +} +EXPORT_SYMBOL_GPL(dma_vmap_noncontiguous); + +void dma_vunmap_noncontiguous(struct device *dev, void *vaddr) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + if (ops && ops->alloc_noncontiguous) + vunmap(vaddr); +} +EXPORT_SYMBOL_GPL(dma_vunmap_noncontiguous); + +int dma_mmap_noncontiguous(struct device *dev, struct vm_area_struct *vma, + size_t size, struct sg_table *sgt) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + if (ops && ops->alloc_noncontiguous) { + unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; + + if (vma->vm_pgoff >= count || + vma_pages(vma) > count - vma->vm_pgoff) + return -ENXIO; + return vm_map_pages(vma, sgt_handle(sgt)->pages, count); + } + return dma_mmap_pages(dev, vma, size, sg_page(sgt->sgl)); +} +EXPORT_SYMBOL_GPL(dma_mmap_noncontiguous); + +static int dma_supported(struct device *dev, u64 mask) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + /* + * ->dma_supported sets the bypass flag, so we must always call + * into the method here unless the device is truly direct mapped. + */ + if (!ops) + return dma_direct_supported(dev, mask); + if (!ops->dma_supported) + return 1; + return ops->dma_supported(dev, mask); +} + +bool dma_pci_p2pdma_supported(struct device *dev) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + /* if ops is not set, dma direct will be used which supports P2PDMA */ + if (!ops) + return true; + + /* + * Note: dma_ops_bypass is not checked here because P2PDMA should + * not be used with dma mapping ops that do not have support even + * if the specific device is bypassing them. + */ + + return ops->flags & DMA_F_PCI_P2PDMA_SUPPORTED; +} +EXPORT_SYMBOL_GPL(dma_pci_p2pdma_supported); + +int dma_set_mask(struct device *dev, u64 mask) +{ + /* + * Truncate the mask to the actually supported dma_addr_t width to + * avoid generating unsupportable addresses. + */ + mask = (dma_addr_t)mask; + + if (!dev->dma_mask || !dma_supported(dev, mask)) + return -EIO; + + arch_dma_set_mask(dev, mask); + *dev->dma_mask = mask; + return 0; +} +EXPORT_SYMBOL(dma_set_mask); + +int dma_set_coherent_mask(struct device *dev, u64 mask) +{ + /* + * Truncate the mask to the actually supported dma_addr_t width to + * avoid generating unsupportable addresses. + */ + mask = (dma_addr_t)mask; + + if (!dma_supported(dev, mask)) + return -EIO; + + dev->coherent_dma_mask = mask; + return 0; +} +EXPORT_SYMBOL(dma_set_coherent_mask); + +size_t dma_max_mapping_size(struct device *dev) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + size_t size = SIZE_MAX; + + if (dma_map_direct(dev, ops)) + size = dma_direct_max_mapping_size(dev); + else if (ops && ops->max_mapping_size) + size = ops->max_mapping_size(dev); + + return size; +} +EXPORT_SYMBOL_GPL(dma_max_mapping_size); + +size_t dma_opt_mapping_size(struct device *dev) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + size_t size = SIZE_MAX; + + if (ops && ops->opt_mapping_size) + size = ops->opt_mapping_size(); + + return min(dma_max_mapping_size(dev), size); +} +EXPORT_SYMBOL_GPL(dma_opt_mapping_size); + +bool dma_need_sync(struct device *dev, dma_addr_t dma_addr) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + if (dma_map_direct(dev, ops)) + return dma_direct_need_sync(dev, dma_addr); + return ops->sync_single_for_cpu || ops->sync_single_for_device; +} +EXPORT_SYMBOL_GPL(dma_need_sync); + +unsigned long dma_get_merge_boundary(struct device *dev) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + if (!ops || !ops->get_merge_boundary) + return 0; /* can't merge */ + + return ops->get_merge_boundary(dev); +} +EXPORT_SYMBOL_GPL(dma_get_merge_boundary); diff --git a/kernel/dma/ops_helpers.c b/kernel/dma/ops_helpers.c new file mode 100644 index 000000000..af4a6ef48 --- /dev/null +++ b/kernel/dma/ops_helpers.c @@ -0,0 +1,93 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Helpers for DMA ops implementations. These generally rely on the fact that + * the allocated memory contains normal pages in the direct kernel mapping. + */ +#include + +static struct page *dma_common_vaddr_to_page(void *cpu_addr) +{ + if (is_vmalloc_addr(cpu_addr)) + return vmalloc_to_page(cpu_addr); + return virt_to_page(cpu_addr); +} + +/* + * Create scatter-list for the already allocated DMA buffer. + */ +int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs) +{ + struct page *page = dma_common_vaddr_to_page(cpu_addr); + int ret; + + ret = sg_alloc_table(sgt, 1, GFP_KERNEL); + if (!ret) + sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0); + return ret; +} + +/* + * Create userspace mapping for the DMA-coherent memory. + */ +int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs) +{ +#ifdef CONFIG_MMU + unsigned long user_count = vma_pages(vma); + unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; + unsigned long off = vma->vm_pgoff; + struct page *page = dma_common_vaddr_to_page(cpu_addr); + int ret = -ENXIO; + + vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs); + + if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret)) + return ret; + + if (off >= count || user_count > count - off) + return -ENXIO; + + return remap_pfn_range(vma, vma->vm_start, + page_to_pfn(page) + vma->vm_pgoff, + user_count << PAGE_SHIFT, vma->vm_page_prot); +#else + return -ENXIO; +#endif /* CONFIG_MMU */ +} + +struct page *dma_common_alloc_pages(struct device *dev, size_t size, + dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + struct page *page; + + page = dma_alloc_contiguous(dev, size, gfp); + if (!page) + page = alloc_pages_node(dev_to_node(dev), gfp, get_order(size)); + if (!page) + return NULL; + + *dma_handle = ops->map_page(dev, page, 0, size, dir, + DMA_ATTR_SKIP_CPU_SYNC); + if (*dma_handle == DMA_MAPPING_ERROR) { + dma_free_contiguous(dev, page, size); + return NULL; + } + + memset(page_address(page), 0, size); + return page; +} + +void dma_common_free_pages(struct device *dev, size_t size, struct page *page, + dma_addr_t dma_handle, enum dma_data_direction dir) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + if (ops->unmap_page) + ops->unmap_page(dev, dma_handle, size, dir, + DMA_ATTR_SKIP_CPU_SYNC); + dma_free_contiguous(dev, page, size); +} diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c new file mode 100644 index 000000000..b481c48a3 --- /dev/null +++ b/kernel/dma/pool.c @@ -0,0 +1,295 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2012 ARM Ltd. + * Copyright (C) 2020 Google LLC + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static struct gen_pool *atomic_pool_dma __ro_after_init; +static unsigned long pool_size_dma; +static struct gen_pool *atomic_pool_dma32 __ro_after_init; +static unsigned long pool_size_dma32; +static struct gen_pool *atomic_pool_kernel __ro_after_init; +static unsigned long pool_size_kernel; + +/* Size can be defined by the coherent_pool command line */ +static size_t atomic_pool_size; + +/* Dynamic background expansion when the atomic pool is near capacity */ +static struct work_struct atomic_pool_work; + +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 __init dma_atomic_pool_debugfs_init(void) +{ + struct dentry *root; + + root = debugfs_create_dir("dma_pools", NULL); + debugfs_create_ulong("pool_size_dma", 0400, root, &pool_size_dma); + debugfs_create_ulong("pool_size_dma32", 0400, root, &pool_size_dma32); + debugfs_create_ulong("pool_size_kernel", 0400, root, &pool_size_kernel); +} + +static void dma_atomic_pool_size_add(gfp_t gfp, size_t size) +{ + if (gfp & __GFP_DMA) + pool_size_dma += size; + else if (gfp & __GFP_DMA32) + pool_size_dma32 += size; + else + pool_size_kernel += size; +} + +static bool cma_in_zone(gfp_t gfp) +{ + unsigned long size; + phys_addr_t end; + struct cma *cma; + + cma = dev_get_cma_area(NULL); + if (!cma) + return false; + + size = cma_get_size(cma); + if (!size) + return false; + + /* CMA can't cross zone boundaries, see cma_activate_area() */ + end = cma_get_base(cma) + size - 1; + if (IS_ENABLED(CONFIG_ZONE_DMA) && (gfp & GFP_DMA)) + return end <= DMA_BIT_MASK(zone_dma_bits); + if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp & GFP_DMA32)) + return end <= DMA_BIT_MASK(32); + return true; +} + +static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size, + gfp_t gfp) +{ + unsigned int order; + struct page *page = NULL; + void *addr; + int ret = -ENOMEM; + + /* Cannot allocate larger than MAX_ORDER */ + order = min(get_order(pool_size), MAX_ORDER); + + do { + pool_size = 1 << (PAGE_SHIFT + order); + if (cma_in_zone(gfp)) + page = dma_alloc_from_contiguous(NULL, 1 << order, + order, false); + if (!page) + page = alloc_pages(gfp, order); + } while (!page && order-- > 0); + if (!page) + goto out; + + arch_dma_prep_coherent(page, pool_size); + +#ifdef CONFIG_DMA_DIRECT_REMAP + addr = dma_common_contiguous_remap(page, pool_size, + pgprot_dmacoherent(PAGE_KERNEL), + __builtin_return_address(0)); + if (!addr) + goto free_page; +#else + addr = page_to_virt(page); +#endif + /* + * Memory in the atomic DMA pools must be unencrypted, the pools do not + * shrink so no re-encryption occurs in dma_direct_free(). + */ + ret = set_memory_decrypted((unsigned long)page_to_virt(page), + 1 << order); + if (ret) + goto remove_mapping; + ret = gen_pool_add_virt(pool, (unsigned long)addr, page_to_phys(page), + pool_size, NUMA_NO_NODE); + if (ret) + goto encrypt_mapping; + + dma_atomic_pool_size_add(gfp, pool_size); + return 0; + +encrypt_mapping: + ret = set_memory_encrypted((unsigned long)page_to_virt(page), + 1 << order); + if (WARN_ON_ONCE(ret)) { + /* Decrypt succeeded but encrypt failed, purposely leak */ + goto out; + } +remove_mapping: +#ifdef CONFIG_DMA_DIRECT_REMAP + dma_common_free_remap(addr, pool_size); +free_page: + __free_pages(page, order); +#endif +out: + return ret; +} + +static void atomic_pool_resize(struct gen_pool *pool, gfp_t gfp) +{ + if (pool && gen_pool_avail(pool) < atomic_pool_size) + atomic_pool_expand(pool, gen_pool_size(pool), gfp); +} + +static void atomic_pool_work_fn(struct work_struct *work) +{ + if (IS_ENABLED(CONFIG_ZONE_DMA)) + atomic_pool_resize(atomic_pool_dma, + GFP_KERNEL | GFP_DMA); + if (IS_ENABLED(CONFIG_ZONE_DMA32)) + atomic_pool_resize(atomic_pool_dma32, + GFP_KERNEL | GFP_DMA32); + atomic_pool_resize(atomic_pool_kernel, GFP_KERNEL); +} + +static __init struct gen_pool *__dma_atomic_pool_init(size_t pool_size, + gfp_t gfp) +{ + struct gen_pool *pool; + int ret; + + pool = gen_pool_create(PAGE_SHIFT, NUMA_NO_NODE); + if (!pool) + return NULL; + + gen_pool_set_algo(pool, gen_pool_first_fit_order_align, NULL); + + ret = atomic_pool_expand(pool, pool_size, gfp); + if (ret) { + gen_pool_destroy(pool); + pr_err("DMA: failed to allocate %zu KiB %pGg pool for atomic allocation\n", + pool_size >> 10, &gfp); + return NULL; + } + + pr_info("DMA: preallocated %zu KiB %pGg pool for atomic allocations\n", + gen_pool_size(pool) >> 10, &gfp); + return pool; +} + +static int __init dma_atomic_pool_init(void) +{ + int ret = 0; + + /* + * If coherent_pool was not used on the command line, default the pool + * sizes to 128KB per 1GB of memory, min 128KB, max MAX_ORDER. + */ + if (!atomic_pool_size) { + unsigned long pages = totalram_pages() / (SZ_1G / SZ_128K); + pages = min_t(unsigned long, pages, MAX_ORDER_NR_PAGES); + atomic_pool_size = max_t(size_t, pages << PAGE_SHIFT, SZ_128K); + } + INIT_WORK(&atomic_pool_work, atomic_pool_work_fn); + + atomic_pool_kernel = __dma_atomic_pool_init(atomic_pool_size, + GFP_KERNEL); + if (!atomic_pool_kernel) + ret = -ENOMEM; + if (has_managed_dma()) { + atomic_pool_dma = __dma_atomic_pool_init(atomic_pool_size, + GFP_KERNEL | GFP_DMA); + if (!atomic_pool_dma) + ret = -ENOMEM; + } + if (IS_ENABLED(CONFIG_ZONE_DMA32)) { + atomic_pool_dma32 = __dma_atomic_pool_init(atomic_pool_size, + GFP_KERNEL | GFP_DMA32); + if (!atomic_pool_dma32) + ret = -ENOMEM; + } + + dma_atomic_pool_debugfs_init(); + return ret; +} +postcore_initcall(dma_atomic_pool_init); + +static inline struct gen_pool *dma_guess_pool(struct gen_pool *prev, gfp_t gfp) +{ + if (prev == NULL) { + if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp & GFP_DMA32)) + return atomic_pool_dma32; + if (atomic_pool_dma && (gfp & GFP_DMA)) + return atomic_pool_dma; + return atomic_pool_kernel; + } + if (prev == atomic_pool_kernel) + return atomic_pool_dma32 ? atomic_pool_dma32 : atomic_pool_dma; + if (prev == atomic_pool_dma32) + return atomic_pool_dma; + return NULL; +} + +static struct page *__dma_alloc_from_pool(struct device *dev, size_t size, + struct gen_pool *pool, void **cpu_addr, + bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t)) +{ + unsigned long addr; + phys_addr_t phys; + + addr = gen_pool_alloc(pool, size); + if (!addr) + return NULL; + + phys = gen_pool_virt_to_phys(pool, addr); + if (phys_addr_ok && !phys_addr_ok(dev, phys, size)) { + gen_pool_free(pool, addr, size); + return NULL; + } + + if (gen_pool_avail(pool) < atomic_pool_size) + schedule_work(&atomic_pool_work); + + *cpu_addr = (void *)addr; + memset(*cpu_addr, 0, size); + return pfn_to_page(__phys_to_pfn(phys)); +} + +struct page *dma_alloc_from_pool(struct device *dev, size_t size, + void **cpu_addr, gfp_t gfp, + bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t)) +{ + struct gen_pool *pool = NULL; + struct page *page; + + while ((pool = dma_guess_pool(pool, gfp))) { + page = __dma_alloc_from_pool(dev, size, pool, cpu_addr, + phys_addr_ok); + if (page) + return page; + } + + WARN(1, "Failed to get suitable pool for %s\n", dev_name(dev)); + return NULL; +} + +bool dma_free_from_pool(struct device *dev, void *start, size_t size) +{ + struct gen_pool *pool = NULL; + + while ((pool = dma_guess_pool(pool, 0))) { + if (!gen_pool_has_addr(pool, (unsigned long)start, size)) + continue; + gen_pool_free(pool, (unsigned long)start, size); + return true; + } + + return false; +} diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c new file mode 100644 index 000000000..27596f3b4 --- /dev/null +++ b/kernel/dma/remap.c @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2014 The Linux Foundation + */ +#include +#include +#include + +struct page **dma_common_find_pages(void *cpu_addr) +{ + struct vm_struct *area = find_vm_area(cpu_addr); + + if (!area || area->flags != VM_DMA_COHERENT) + return NULL; + return area->pages; +} + +/* + * Remaps an array of PAGE_SIZE pages into another vm_area. + * Cannot be used in non-sleeping contexts + */ +void *dma_common_pages_remap(struct page **pages, size_t size, + pgprot_t prot, const void *caller) +{ + void *vaddr; + + vaddr = vmap(pages, PAGE_ALIGN(size) >> PAGE_SHIFT, + VM_DMA_COHERENT, prot); + if (vaddr) + find_vm_area(vaddr)->pages = pages; + return vaddr; +} + +/* + * Remaps an allocated contiguous region into another vm_area. + * Cannot be used in non-sleeping contexts + */ +void *dma_common_contiguous_remap(struct page *page, size_t size, + pgprot_t prot, const void *caller) +{ + int count = PAGE_ALIGN(size) >> PAGE_SHIFT; + struct page **pages; + void *vaddr; + int i; + + pages = kvmalloc_array(count, sizeof(struct page *), GFP_KERNEL); + if (!pages) + return NULL; + for (i = 0; i < count; i++) + pages[i] = nth_page(page, i); + vaddr = vmap(pages, count, VM_DMA_COHERENT, prot); + kvfree(pages); + + return vaddr; +} + +/* + * Unmaps a range previously mapped by dma_common_*_remap + */ +void dma_common_free_remap(void *cpu_addr, size_t size) +{ + struct vm_struct *area = find_vm_area(cpu_addr); + + if (!area || area->flags != VM_DMA_COHERENT) { + WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr); + return; + } + + vunmap(cpu_addr); +} diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c new file mode 100644 index 000000000..2048194a0 --- /dev/null +++ b/kernel/dma/swiotlb.c @@ -0,0 +1,1725 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Dynamic DMA mapping support. + * + * This implementation is a fallback for platforms that do not support + * I/O TLBs (aka DMA address translation hardware). + * Copyright (C) 2000 Asit Mallick + * Copyright (C) 2000 Goutham Rao + * Copyright (C) 2000, 2003 Hewlett-Packard Co + * David Mosberger-Tang + * + * 03/05/07 davidm Switch from PCI-DMA to generic device DMA API. + * 00/12/13 davidm Rename to swiotlb.c and add mark_clean() to avoid + * unnecessary i-cache flushing. + * 04/07/.. ak Better overflow handling. Assorted fixes. + * 05/09/10 linville Add support for syncing ranges, support syncing for + * DMA_BIDIRECTIONAL mappings, miscellaneous cleanup. + * 08/12/11 beckyb Add highmem support + */ + +#define pr_fmt(fmt) "software IO TLB: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#ifdef CONFIG_DMA_RESTRICTED_POOL +#include +#include +#include +#include +#endif + +#define CREATE_TRACE_POINTS +#include + +#define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT)) + +/* + * Minimum IO TLB size to bother booting with. Systems with mainly + * 64bit capable cards will only lightly use the swiotlb. If we can't + * allocate a contiguous 1MB, we're probably in trouble anyway. + */ +#define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT) + +#define INVALID_PHYS_ADDR (~(phys_addr_t)0) + +/** + * struct io_tlb_slot - IO TLB slot descriptor + * @orig_addr: The original address corresponding to a mapped entry. + * @alloc_size: Size of the allocated buffer. + * @list: The free list describing the number of free entries available + * from each index. + */ +struct io_tlb_slot { + phys_addr_t orig_addr; + size_t alloc_size; + unsigned int list; +}; + +static bool swiotlb_force_bounce; +static bool swiotlb_force_disable; + +#ifdef CONFIG_SWIOTLB_DYNAMIC + +static void swiotlb_dyn_alloc(struct work_struct *work); + +static struct io_tlb_mem io_tlb_default_mem = { + .lock = __SPIN_LOCK_UNLOCKED(io_tlb_default_mem.lock), + .pools = LIST_HEAD_INIT(io_tlb_default_mem.pools), + .dyn_alloc = __WORK_INITIALIZER(io_tlb_default_mem.dyn_alloc, + swiotlb_dyn_alloc), +}; + +#else /* !CONFIG_SWIOTLB_DYNAMIC */ + +static struct io_tlb_mem io_tlb_default_mem; + +#endif /* CONFIG_SWIOTLB_DYNAMIC */ + +static unsigned long default_nslabs = IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT; +static unsigned long default_nareas; + +/** + * struct io_tlb_area - IO TLB memory area descriptor + * + * This is a single area with a single lock. + * + * @used: The number of used IO TLB block. + * @index: The slot index to start searching in this area for next round. + * @lock: The lock to protect the above data structures in the map and + * unmap calls. + */ +struct io_tlb_area { + unsigned long used; + unsigned int index; + spinlock_t lock; +}; + +/* + * Round up number of slabs to the next power of 2. The last area is going + * be smaller than the rest if default_nslabs is not power of two. + * The number of slot in an area should be a multiple of IO_TLB_SEGSIZE, + * otherwise a segment may span two or more areas. It conflicts with free + * contiguous slots tracking: free slots are treated contiguous no matter + * whether they cross an area boundary. + * + * Return true if default_nslabs is rounded up. + */ +static bool round_up_default_nslabs(void) +{ + if (!default_nareas) + return false; + + if (default_nslabs < IO_TLB_SEGSIZE * default_nareas) + default_nslabs = IO_TLB_SEGSIZE * default_nareas; + else if (is_power_of_2(default_nslabs)) + return false; + default_nslabs = roundup_pow_of_two(default_nslabs); + return true; +} + +/** + * swiotlb_adjust_nareas() - adjust the number of areas and slots + * @nareas: Desired number of areas. Zero is treated as 1. + * + * Adjust the default number of areas in a memory pool. + * The default size of the memory pool may also change to meet minimum area + * size requirements. + */ +static void swiotlb_adjust_nareas(unsigned int nareas) +{ + if (!nareas) + nareas = 1; + else if (!is_power_of_2(nareas)) + nareas = roundup_pow_of_two(nareas); + + default_nareas = nareas; + + pr_info("area num %d.\n", nareas); + if (round_up_default_nslabs()) + pr_info("SWIOTLB bounce buffer size roundup to %luMB", + (default_nslabs << IO_TLB_SHIFT) >> 20); +} + +/** + * limit_nareas() - get the maximum number of areas for a given memory pool size + * @nareas: Desired number of areas. + * @nslots: Total number of slots in the memory pool. + * + * Limit the number of areas to the maximum possible number of areas in + * a memory pool of the given size. + * + * Return: Maximum possible number of areas. + */ +static unsigned int limit_nareas(unsigned int nareas, unsigned long nslots) +{ + if (nslots < nareas * IO_TLB_SEGSIZE) + return nslots / IO_TLB_SEGSIZE; + return nareas; +} + +static int __init +setup_io_tlb_npages(char *str) +{ + if (isdigit(*str)) { + /* avoid tail segment of size < IO_TLB_SEGSIZE */ + default_nslabs = + ALIGN(simple_strtoul(str, &str, 0), IO_TLB_SEGSIZE); + } + if (*str == ',') + ++str; + if (isdigit(*str)) + swiotlb_adjust_nareas(simple_strtoul(str, &str, 0)); + if (*str == ',') + ++str; + if (!strcmp(str, "force")) + swiotlb_force_bounce = true; + else if (!strcmp(str, "noforce")) + swiotlb_force_disable = true; + + return 0; +} +early_param("swiotlb", setup_io_tlb_npages); + +unsigned long swiotlb_size_or_default(void) +{ + return default_nslabs << IO_TLB_SHIFT; +} + +void __init swiotlb_adjust_size(unsigned long size) +{ + /* + * If swiotlb parameter has not been specified, give a chance to + * architectures such as those supporting memory encryption to + * adjust/expand SWIOTLB size for their use. + */ + if (default_nslabs != IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT) + return; + + size = ALIGN(size, IO_TLB_SIZE); + default_nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE); + if (round_up_default_nslabs()) + size = default_nslabs << IO_TLB_SHIFT; + pr_info("SWIOTLB bounce buffer size adjusted to %luMB", size >> 20); +} + +void swiotlb_print_info(void) +{ + struct io_tlb_pool *mem = &io_tlb_default_mem.defpool; + + if (!mem->nslabs) { + pr_warn("No low mem\n"); + return; + } + + pr_info("mapped [mem %pa-%pa] (%luMB)\n", &mem->start, &mem->end, + (mem->nslabs << IO_TLB_SHIFT) >> 20); +} + +static inline unsigned long io_tlb_offset(unsigned long val) +{ + return val & (IO_TLB_SEGSIZE - 1); +} + +static inline unsigned long nr_slots(u64 val) +{ + return DIV_ROUND_UP(val, IO_TLB_SIZE); +} + +/* + * Early SWIOTLB allocation may be too early to allow an architecture to + * perform the desired operations. This function allows the architecture to + * call SWIOTLB when the operations are possible. It needs to be called + * before the SWIOTLB memory is used. + */ +void __init swiotlb_update_mem_attributes(void) +{ + struct io_tlb_pool *mem = &io_tlb_default_mem.defpool; + unsigned long bytes; + + if (!mem->nslabs || mem->late_alloc) + return; + bytes = PAGE_ALIGN(mem->nslabs << IO_TLB_SHIFT); + set_memory_decrypted((unsigned long)mem->vaddr, bytes >> PAGE_SHIFT); +} + +static void swiotlb_init_io_tlb_pool(struct io_tlb_pool *mem, phys_addr_t start, + unsigned long nslabs, bool late_alloc, unsigned int nareas) +{ + void *vaddr = phys_to_virt(start); + unsigned long bytes = nslabs << IO_TLB_SHIFT, i; + + mem->nslabs = nslabs; + mem->start = start; + mem->end = mem->start + bytes; + mem->late_alloc = late_alloc; + mem->nareas = nareas; + mem->area_nslabs = nslabs / mem->nareas; + + for (i = 0; i < mem->nareas; i++) { + spin_lock_init(&mem->areas[i].lock); + mem->areas[i].index = 0; + mem->areas[i].used = 0; + } + + for (i = 0; i < mem->nslabs; i++) { + mem->slots[i].list = min(IO_TLB_SEGSIZE - io_tlb_offset(i), + mem->nslabs - i); + mem->slots[i].orig_addr = INVALID_PHYS_ADDR; + mem->slots[i].alloc_size = 0; + } + + memset(vaddr, 0, bytes); + mem->vaddr = vaddr; + return; +} + +/** + * add_mem_pool() - add a memory pool to the allocator + * @mem: Software IO TLB allocator. + * @pool: Memory pool to be added. + */ +static void add_mem_pool(struct io_tlb_mem *mem, struct io_tlb_pool *pool) +{ +#ifdef CONFIG_SWIOTLB_DYNAMIC + spin_lock(&mem->lock); + list_add_rcu(&pool->node, &mem->pools); + mem->nslabs += pool->nslabs; + spin_unlock(&mem->lock); +#else + mem->nslabs = pool->nslabs; +#endif +} + +static void __init *swiotlb_memblock_alloc(unsigned long nslabs, + unsigned int flags, + int (*remap)(void *tlb, unsigned long nslabs)) +{ + size_t bytes = PAGE_ALIGN(nslabs << IO_TLB_SHIFT); + void *tlb; + + /* + * By default allocate the bounce buffer memory from low memory, but + * allow to pick a location everywhere for hypervisors with guest + * memory encryption. + */ + if (flags & SWIOTLB_ANY) + tlb = memblock_alloc(bytes, PAGE_SIZE); + else + tlb = memblock_alloc_low(bytes, PAGE_SIZE); + + if (!tlb) { + pr_warn("%s: Failed to allocate %zu bytes tlb structure\n", + __func__, bytes); + return NULL; + } + + if (remap && remap(tlb, nslabs) < 0) { + memblock_free(tlb, PAGE_ALIGN(bytes)); + pr_warn("%s: Failed to remap %zu bytes\n", __func__, bytes); + return NULL; + } + + return tlb; +} + +/* + * Statically reserve bounce buffer space and initialize bounce buffer data + * structures for the software IO TLB used to implement the DMA API. + */ +void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags, + int (*remap)(void *tlb, unsigned long nslabs)) +{ + struct io_tlb_pool *mem = &io_tlb_default_mem.defpool; + unsigned long nslabs; + unsigned int nareas; + size_t alloc_size; + void *tlb; + + if (!addressing_limit && !swiotlb_force_bounce) + return; + if (swiotlb_force_disable) + return; + + io_tlb_default_mem.force_bounce = + swiotlb_force_bounce || (flags & SWIOTLB_FORCE); + +#ifdef CONFIG_SWIOTLB_DYNAMIC + if (!remap) + io_tlb_default_mem.can_grow = true; + if (flags & SWIOTLB_ANY) + io_tlb_default_mem.phys_limit = virt_to_phys(high_memory - 1); + else + io_tlb_default_mem.phys_limit = ARCH_LOW_ADDRESS_LIMIT; +#endif + + if (!default_nareas) + swiotlb_adjust_nareas(num_possible_cpus()); + + nslabs = default_nslabs; + nareas = limit_nareas(default_nareas, nslabs); + while ((tlb = swiotlb_memblock_alloc(nslabs, flags, remap)) == NULL) { + if (nslabs <= IO_TLB_MIN_SLABS) + return; + nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE); + nareas = limit_nareas(nareas, nslabs); + } + + if (default_nslabs != nslabs) { + pr_info("SWIOTLB bounce buffer size adjusted %lu -> %lu slabs", + default_nslabs, nslabs); + default_nslabs = nslabs; + } + + alloc_size = PAGE_ALIGN(array_size(sizeof(*mem->slots), nslabs)); + mem->slots = memblock_alloc(alloc_size, PAGE_SIZE); + if (!mem->slots) { + pr_warn("%s: Failed to allocate %zu bytes align=0x%lx\n", + __func__, alloc_size, PAGE_SIZE); + return; + } + + mem->areas = memblock_alloc(array_size(sizeof(struct io_tlb_area), + nareas), SMP_CACHE_BYTES); + if (!mem->areas) { + pr_warn("%s: Failed to allocate mem->areas.\n", __func__); + return; + } + + swiotlb_init_io_tlb_pool(mem, __pa(tlb), nslabs, false, nareas); + add_mem_pool(&io_tlb_default_mem, mem); + + if (flags & SWIOTLB_VERBOSE) + swiotlb_print_info(); +} + +void __init swiotlb_init(bool addressing_limit, unsigned int flags) +{ + swiotlb_init_remap(addressing_limit, flags, NULL); +} + +/* + * Systems with larger DMA zones (those that don't support ISA) can + * initialize the swiotlb later using the slab allocator if needed. + * This should be just like above, but with some error catching. + */ +int swiotlb_init_late(size_t size, gfp_t gfp_mask, + int (*remap)(void *tlb, unsigned long nslabs)) +{ + struct io_tlb_pool *mem = &io_tlb_default_mem.defpool; + unsigned long nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE); + unsigned int nareas; + unsigned char *vstart = NULL; + unsigned int order, area_order; + bool retried = false; + int rc = 0; + + if (io_tlb_default_mem.nslabs) + return 0; + + if (swiotlb_force_disable) + return 0; + + io_tlb_default_mem.force_bounce = swiotlb_force_bounce; + +#ifdef CONFIG_SWIOTLB_DYNAMIC + if (!remap) + io_tlb_default_mem.can_grow = true; + if (IS_ENABLED(CONFIG_ZONE_DMA) && (gfp_mask & __GFP_DMA)) + io_tlb_default_mem.phys_limit = DMA_BIT_MASK(zone_dma_bits); + else if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp_mask & __GFP_DMA32)) + io_tlb_default_mem.phys_limit = DMA_BIT_MASK(32); + else + io_tlb_default_mem.phys_limit = virt_to_phys(high_memory - 1); +#endif + + if (!default_nareas) + swiotlb_adjust_nareas(num_possible_cpus()); + +retry: + order = get_order(nslabs << IO_TLB_SHIFT); + nslabs = SLABS_PER_PAGE << order; + + while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) { + vstart = (void *)__get_free_pages(gfp_mask | __GFP_NOWARN, + order); + if (vstart) + break; + order--; + nslabs = SLABS_PER_PAGE << order; + retried = true; + } + + if (!vstart) + return -ENOMEM; + + if (remap) + rc = remap(vstart, nslabs); + if (rc) { + free_pages((unsigned long)vstart, order); + + nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE); + if (nslabs < IO_TLB_MIN_SLABS) + return rc; + retried = true; + goto retry; + } + + if (retried) { + pr_warn("only able to allocate %ld MB\n", + (PAGE_SIZE << order) >> 20); + } + + nareas = limit_nareas(default_nareas, nslabs); + area_order = get_order(array_size(sizeof(*mem->areas), nareas)); + mem->areas = (struct io_tlb_area *) + __get_free_pages(GFP_KERNEL | __GFP_ZERO, area_order); + if (!mem->areas) + goto error_area; + + mem->slots = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, + get_order(array_size(sizeof(*mem->slots), nslabs))); + if (!mem->slots) + goto error_slots; + + set_memory_decrypted((unsigned long)vstart, + (nslabs << IO_TLB_SHIFT) >> PAGE_SHIFT); + swiotlb_init_io_tlb_pool(mem, virt_to_phys(vstart), nslabs, true, + nareas); + add_mem_pool(&io_tlb_default_mem, mem); + + swiotlb_print_info(); + return 0; + +error_slots: + free_pages((unsigned long)mem->areas, area_order); +error_area: + free_pages((unsigned long)vstart, order); + return -ENOMEM; +} + +void __init swiotlb_exit(void) +{ + struct io_tlb_pool *mem = &io_tlb_default_mem.defpool; + unsigned long tbl_vaddr; + size_t tbl_size, slots_size; + unsigned int area_order; + + if (swiotlb_force_bounce) + return; + + if (!mem->nslabs) + return; + + pr_info("tearing down default memory pool\n"); + tbl_vaddr = (unsigned long)phys_to_virt(mem->start); + tbl_size = PAGE_ALIGN(mem->end - mem->start); + slots_size = PAGE_ALIGN(array_size(sizeof(*mem->slots), mem->nslabs)); + + set_memory_encrypted(tbl_vaddr, tbl_size >> PAGE_SHIFT); + if (mem->late_alloc) { + area_order = get_order(array_size(sizeof(*mem->areas), + mem->nareas)); + free_pages((unsigned long)mem->areas, area_order); + free_pages(tbl_vaddr, get_order(tbl_size)); + free_pages((unsigned long)mem->slots, get_order(slots_size)); + } else { + memblock_free_late(__pa(mem->areas), + array_size(sizeof(*mem->areas), mem->nareas)); + memblock_free_late(mem->start, tbl_size); + memblock_free_late(__pa(mem->slots), slots_size); + } + + memset(mem, 0, sizeof(*mem)); +} + +#ifdef CONFIG_SWIOTLB_DYNAMIC + +/** + * alloc_dma_pages() - allocate pages to be used for DMA + * @gfp: GFP flags for the allocation. + * @bytes: Size of the buffer. + * @phys_limit: Maximum allowed physical address of the buffer. + * + * Allocate pages from the buddy allocator. If successful, make the allocated + * pages decrypted that they can be used for DMA. + * + * Return: Decrypted pages, %NULL on allocation failure, or ERR_PTR(-EAGAIN) + * if the allocated physical address was above @phys_limit. + */ +static struct page *alloc_dma_pages(gfp_t gfp, size_t bytes, u64 phys_limit) +{ + unsigned int order = get_order(bytes); + struct page *page; + phys_addr_t paddr; + void *vaddr; + + page = alloc_pages(gfp, order); + if (!page) + return NULL; + + paddr = page_to_phys(page); + if (paddr + bytes - 1 > phys_limit) { + __free_pages(page, order); + return ERR_PTR(-EAGAIN); + } + + vaddr = phys_to_virt(paddr); + if (set_memory_decrypted((unsigned long)vaddr, PFN_UP(bytes))) + goto error; + return page; + +error: + /* Intentional leak if pages cannot be encrypted again. */ + if (!set_memory_encrypted((unsigned long)vaddr, PFN_UP(bytes))) + __free_pages(page, order); + return NULL; +} + +/** + * swiotlb_alloc_tlb() - allocate a dynamic IO TLB buffer + * @dev: Device for which a memory pool is allocated. + * @bytes: Size of the buffer. + * @phys_limit: Maximum allowed physical address of the buffer. + * @gfp: GFP flags for the allocation. + * + * Return: Allocated pages, or %NULL on allocation failure. + */ +static struct page *swiotlb_alloc_tlb(struct device *dev, size_t bytes, + u64 phys_limit, gfp_t gfp) +{ + struct page *page; + + /* + * Allocate from the atomic pools if memory is encrypted and + * the allocation is atomic, because decrypting may block. + */ + if (!gfpflags_allow_blocking(gfp) && dev && force_dma_unencrypted(dev)) { + void *vaddr; + + if (!IS_ENABLED(CONFIG_DMA_COHERENT_POOL)) + return NULL; + + return dma_alloc_from_pool(dev, bytes, &vaddr, gfp, + dma_coherent_ok); + } + + gfp &= ~GFP_ZONEMASK; + if (phys_limit <= DMA_BIT_MASK(zone_dma_bits)) + gfp |= __GFP_DMA; + else if (phys_limit <= DMA_BIT_MASK(32)) + gfp |= __GFP_DMA32; + + while (IS_ERR(page = alloc_dma_pages(gfp, bytes, phys_limit))) { + if (IS_ENABLED(CONFIG_ZONE_DMA32) && + phys_limit < DMA_BIT_MASK(64) && + !(gfp & (__GFP_DMA32 | __GFP_DMA))) + gfp |= __GFP_DMA32; + else if (IS_ENABLED(CONFIG_ZONE_DMA) && + !(gfp & __GFP_DMA)) + gfp = (gfp & ~__GFP_DMA32) | __GFP_DMA; + else + return NULL; + } + + return page; +} + +/** + * swiotlb_free_tlb() - free a dynamically allocated IO TLB buffer + * @vaddr: Virtual address of the buffer. + * @bytes: Size of the buffer. + */ +static void swiotlb_free_tlb(void *vaddr, size_t bytes) +{ + if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) && + dma_free_from_pool(NULL, vaddr, bytes)) + return; + + /* Intentional leak if pages cannot be encrypted again. */ + if (!set_memory_encrypted((unsigned long)vaddr, PFN_UP(bytes))) + __free_pages(virt_to_page(vaddr), get_order(bytes)); +} + +/** + * swiotlb_alloc_pool() - allocate a new IO TLB memory pool + * @dev: Device for which a memory pool is allocated. + * @minslabs: Minimum number of slabs. + * @nslabs: Desired (maximum) number of slabs. + * @nareas: Number of areas. + * @phys_limit: Maximum DMA buffer physical address. + * @gfp: GFP flags for the allocations. + * + * Allocate and initialize a new IO TLB memory pool. The actual number of + * slabs may be reduced if allocation of @nslabs fails. If even + * @minslabs cannot be allocated, this function fails. + * + * Return: New memory pool, or %NULL on allocation failure. + */ +static struct io_tlb_pool *swiotlb_alloc_pool(struct device *dev, + unsigned long minslabs, unsigned long nslabs, + unsigned int nareas, u64 phys_limit, gfp_t gfp) +{ + struct io_tlb_pool *pool; + unsigned int slot_order; + struct page *tlb; + size_t pool_size; + size_t tlb_size; + + if (nslabs > SLABS_PER_PAGE << MAX_ORDER) { + nslabs = SLABS_PER_PAGE << MAX_ORDER; + nareas = limit_nareas(nareas, nslabs); + } + + pool_size = sizeof(*pool) + array_size(sizeof(*pool->areas), nareas); + pool = kzalloc(pool_size, gfp); + if (!pool) + goto error; + pool->areas = (void *)pool + sizeof(*pool); + + tlb_size = nslabs << IO_TLB_SHIFT; + while (!(tlb = swiotlb_alloc_tlb(dev, tlb_size, phys_limit, gfp))) { + if (nslabs <= minslabs) + goto error_tlb; + nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE); + nareas = limit_nareas(nareas, nslabs); + tlb_size = nslabs << IO_TLB_SHIFT; + } + + slot_order = get_order(array_size(sizeof(*pool->slots), nslabs)); + pool->slots = (struct io_tlb_slot *) + __get_free_pages(gfp, slot_order); + if (!pool->slots) + goto error_slots; + + swiotlb_init_io_tlb_pool(pool, page_to_phys(tlb), nslabs, true, nareas); + return pool; + +error_slots: + swiotlb_free_tlb(page_address(tlb), tlb_size); +error_tlb: + kfree(pool); +error: + return NULL; +} + +/** + * swiotlb_dyn_alloc() - dynamic memory pool allocation worker + * @work: Pointer to dyn_alloc in struct io_tlb_mem. + */ +static void swiotlb_dyn_alloc(struct work_struct *work) +{ + struct io_tlb_mem *mem = + container_of(work, struct io_tlb_mem, dyn_alloc); + struct io_tlb_pool *pool; + + pool = swiotlb_alloc_pool(NULL, IO_TLB_MIN_SLABS, default_nslabs, + default_nareas, mem->phys_limit, GFP_KERNEL); + if (!pool) { + pr_warn_ratelimited("Failed to allocate new pool"); + return; + } + + add_mem_pool(mem, pool); +} + +/** + * swiotlb_dyn_free() - RCU callback to free a memory pool + * @rcu: RCU head in the corresponding struct io_tlb_pool. + */ +static void swiotlb_dyn_free(struct rcu_head *rcu) +{ + struct io_tlb_pool *pool = container_of(rcu, struct io_tlb_pool, rcu); + size_t slots_size = array_size(sizeof(*pool->slots), pool->nslabs); + size_t tlb_size = pool->end - pool->start; + + free_pages((unsigned long)pool->slots, get_order(slots_size)); + swiotlb_free_tlb(pool->vaddr, tlb_size); + kfree(pool); +} + +/** + * swiotlb_find_pool() - find the IO TLB pool for a physical address + * @dev: Device which has mapped the DMA buffer. + * @paddr: Physical address within the DMA buffer. + * + * Find the IO TLB memory pool descriptor which contains the given physical + * address, if any. + * + * Return: Memory pool which contains @paddr, or %NULL if none. + */ +struct io_tlb_pool *swiotlb_find_pool(struct device *dev, phys_addr_t paddr) +{ + struct io_tlb_mem *mem = dev->dma_io_tlb_mem; + struct io_tlb_pool *pool; + + rcu_read_lock(); + list_for_each_entry_rcu(pool, &mem->pools, node) { + if (paddr >= pool->start && paddr < pool->end) + goto out; + } + + list_for_each_entry_rcu(pool, &dev->dma_io_tlb_pools, node) { + if (paddr >= pool->start && paddr < pool->end) + goto out; + } + pool = NULL; +out: + rcu_read_unlock(); + return pool; +} + +/** + * swiotlb_del_pool() - remove an IO TLB pool from a device + * @dev: Owning device. + * @pool: Memory pool to be removed. + */ +static void swiotlb_del_pool(struct device *dev, struct io_tlb_pool *pool) +{ + unsigned long flags; + + spin_lock_irqsave(&dev->dma_io_tlb_lock, flags); + list_del_rcu(&pool->node); + spin_unlock_irqrestore(&dev->dma_io_tlb_lock, flags); + + call_rcu(&pool->rcu, swiotlb_dyn_free); +} + +#endif /* CONFIG_SWIOTLB_DYNAMIC */ + +/** + * swiotlb_dev_init() - initialize swiotlb fields in &struct device + * @dev: Device to be initialized. + */ +void swiotlb_dev_init(struct device *dev) +{ + dev->dma_io_tlb_mem = &io_tlb_default_mem; +#ifdef CONFIG_SWIOTLB_DYNAMIC + INIT_LIST_HEAD(&dev->dma_io_tlb_pools); + spin_lock_init(&dev->dma_io_tlb_lock); + dev->dma_uses_io_tlb = false; +#endif +} + +/* + * Return the offset into a iotlb slot required to keep the device happy. + */ +static unsigned int swiotlb_align_offset(struct device *dev, u64 addr) +{ + return addr & dma_get_min_align_mask(dev) & (IO_TLB_SIZE - 1); +} + +/* + * Bounce: copy the swiotlb buffer from or back to the original dma location + */ +static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size, + enum dma_data_direction dir) +{ + struct io_tlb_pool *mem = swiotlb_find_pool(dev, tlb_addr); + int index = (tlb_addr - mem->start) >> IO_TLB_SHIFT; + phys_addr_t orig_addr = mem->slots[index].orig_addr; + size_t alloc_size = mem->slots[index].alloc_size; + unsigned long pfn = PFN_DOWN(orig_addr); + unsigned char *vaddr = mem->vaddr + tlb_addr - mem->start; + unsigned int tlb_offset, orig_addr_offset; + + if (orig_addr == INVALID_PHYS_ADDR) + return; + + tlb_offset = tlb_addr & (IO_TLB_SIZE - 1); + orig_addr_offset = swiotlb_align_offset(dev, orig_addr); + if (tlb_offset < orig_addr_offset) { + dev_WARN_ONCE(dev, 1, + "Access before mapping start detected. orig offset %u, requested offset %u.\n", + orig_addr_offset, tlb_offset); + return; + } + + tlb_offset -= orig_addr_offset; + if (tlb_offset > alloc_size) { + dev_WARN_ONCE(dev, 1, + "Buffer overflow detected. Allocation size: %zu. Mapping size: %zu+%u.\n", + alloc_size, size, tlb_offset); + return; + } + + orig_addr += tlb_offset; + alloc_size -= tlb_offset; + + if (size > alloc_size) { + dev_WARN_ONCE(dev, 1, + "Buffer overflow detected. Allocation size: %zu. Mapping size: %zu.\n", + alloc_size, size); + size = alloc_size; + } + + if (PageHighMem(pfn_to_page(pfn))) { + unsigned int offset = orig_addr & ~PAGE_MASK; + struct page *page; + unsigned int sz = 0; + unsigned long flags; + + while (size) { + sz = min_t(size_t, PAGE_SIZE - offset, size); + + local_irq_save(flags); + page = pfn_to_page(pfn); + if (dir == DMA_TO_DEVICE) + memcpy_from_page(vaddr, page, offset, sz); + else + memcpy_to_page(page, offset, vaddr, sz); + local_irq_restore(flags); + + size -= sz; + pfn++; + vaddr += sz; + offset = 0; + } + } else if (dir == DMA_TO_DEVICE) { + memcpy(vaddr, phys_to_virt(orig_addr), size); + } else { + memcpy(phys_to_virt(orig_addr), vaddr, size); + } +} + +static inline phys_addr_t slot_addr(phys_addr_t start, phys_addr_t idx) +{ + return start + (idx << IO_TLB_SHIFT); +} + +/* + * Carefully handle integer overflow which can occur when boundary_mask == ~0UL. + */ +static inline unsigned long get_max_slots(unsigned long boundary_mask) +{ + return (boundary_mask >> IO_TLB_SHIFT) + 1; +} + +static unsigned int wrap_area_index(struct io_tlb_pool *mem, unsigned int index) +{ + if (index >= mem->area_nslabs) + return 0; + return index; +} + +/* + * Track the total used slots with a global atomic value in order to have + * correct information to determine the high water mark. The mem_used() + * function gives imprecise results because there's no locking across + * multiple areas. + */ +#ifdef CONFIG_DEBUG_FS +static void inc_used_and_hiwater(struct io_tlb_mem *mem, unsigned int nslots) +{ + unsigned long old_hiwater, new_used; + + new_used = atomic_long_add_return(nslots, &mem->total_used); + old_hiwater = atomic_long_read(&mem->used_hiwater); + do { + if (new_used <= old_hiwater) + break; + } while (!atomic_long_try_cmpxchg(&mem->used_hiwater, + &old_hiwater, new_used)); +} + +static void dec_used(struct io_tlb_mem *mem, unsigned int nslots) +{ + atomic_long_sub(nslots, &mem->total_used); +} + +#else /* !CONFIG_DEBUG_FS */ +static void inc_used_and_hiwater(struct io_tlb_mem *mem, unsigned int nslots) +{ +} +static void dec_used(struct io_tlb_mem *mem, unsigned int nslots) +{ +} +#endif /* CONFIG_DEBUG_FS */ + +/** + * swiotlb_area_find_slots() - search for slots in one IO TLB memory area + * @dev: Device which maps the buffer. + * @pool: Memory pool to be searched. + * @area_index: Index of the IO TLB memory area to be searched. + * @orig_addr: Original (non-bounced) IO buffer address. + * @alloc_size: Total requested size of the bounce buffer, + * including initial alignment padding. + * @alloc_align_mask: Required alignment of the allocated buffer. + * + * Find a suitable sequence of IO TLB entries for the request and allocate + * a buffer from the given IO TLB memory area. + * This function takes care of locking. + * + * Return: Index of the first allocated slot, or -1 on error. + */ +static int swiotlb_area_find_slots(struct device *dev, struct io_tlb_pool *pool, + int area_index, phys_addr_t orig_addr, size_t alloc_size, + unsigned int alloc_align_mask) +{ + struct io_tlb_area *area = pool->areas + area_index; + unsigned long boundary_mask = dma_get_seg_boundary(dev); + dma_addr_t tbl_dma_addr = + phys_to_dma_unencrypted(dev, pool->start) & boundary_mask; + unsigned long max_slots = get_max_slots(boundary_mask); + unsigned int iotlb_align_mask = + dma_get_min_align_mask(dev) | alloc_align_mask; + unsigned int nslots = nr_slots(alloc_size), stride; + unsigned int offset = swiotlb_align_offset(dev, orig_addr); + unsigned int index, slots_checked, count = 0, i; + unsigned long flags; + unsigned int slot_base; + unsigned int slot_index; + + BUG_ON(!nslots); + BUG_ON(area_index >= pool->nareas); + + /* + * For allocations of PAGE_SIZE or larger only look for page aligned + * allocations. + */ + if (alloc_size >= PAGE_SIZE) + iotlb_align_mask |= ~PAGE_MASK; + iotlb_align_mask &= ~(IO_TLB_SIZE - 1); + + /* + * For mappings with an alignment requirement don't bother looping to + * unaligned slots once we found an aligned one. + */ + stride = (iotlb_align_mask >> IO_TLB_SHIFT) + 1; + + spin_lock_irqsave(&area->lock, flags); + if (unlikely(nslots > pool->area_nslabs - area->used)) + goto not_found; + + slot_base = area_index * pool->area_nslabs; + index = area->index; + + for (slots_checked = 0; slots_checked < pool->area_nslabs; ) { + slot_index = slot_base + index; + + if (orig_addr && + (slot_addr(tbl_dma_addr, slot_index) & + iotlb_align_mask) != (orig_addr & iotlb_align_mask)) { + index = wrap_area_index(pool, index + 1); + slots_checked++; + continue; + } + + if (!iommu_is_span_boundary(slot_index, nslots, + nr_slots(tbl_dma_addr), + max_slots)) { + if (pool->slots[slot_index].list >= nslots) + goto found; + } + index = wrap_area_index(pool, index + stride); + slots_checked += stride; + } + +not_found: + spin_unlock_irqrestore(&area->lock, flags); + return -1; + +found: + /* + * If we find a slot that indicates we have 'nslots' number of + * contiguous buffers, we allocate the buffers from that slot onwards + * and set the list of free entries to '0' indicating unavailable. + */ + for (i = slot_index; i < slot_index + nslots; i++) { + pool->slots[i].list = 0; + pool->slots[i].alloc_size = alloc_size - (offset + + ((i - slot_index) << IO_TLB_SHIFT)); + } + for (i = slot_index - 1; + io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 && + pool->slots[i].list; i--) + pool->slots[i].list = ++count; + + /* + * Update the indices to avoid searching in the next round. + */ + area->index = wrap_area_index(pool, index + nslots); + area->used += nslots; + spin_unlock_irqrestore(&area->lock, flags); + + inc_used_and_hiwater(dev->dma_io_tlb_mem, nslots); + return slot_index; +} + +/** + * swiotlb_pool_find_slots() - search for slots in one memory pool + * @dev: Device which maps the buffer. + * @pool: Memory pool to be searched. + * @orig_addr: Original (non-bounced) IO buffer address. + * @alloc_size: Total requested size of the bounce buffer, + * including initial alignment padding. + * @alloc_align_mask: Required alignment of the allocated buffer. + * + * Search through one memory pool to find a sequence of slots that match the + * allocation constraints. + * + * Return: Index of the first allocated slot, or -1 on error. + */ +static int swiotlb_pool_find_slots(struct device *dev, struct io_tlb_pool *pool, + phys_addr_t orig_addr, size_t alloc_size, + unsigned int alloc_align_mask) +{ + int start = raw_smp_processor_id() & (pool->nareas - 1); + int i = start, index; + + do { + index = swiotlb_area_find_slots(dev, pool, i, orig_addr, + alloc_size, alloc_align_mask); + if (index >= 0) + return index; + if (++i >= pool->nareas) + i = 0; + } while (i != start); + + return -1; +} + +#ifdef CONFIG_SWIOTLB_DYNAMIC + +/** + * swiotlb_find_slots() - search for slots in the whole swiotlb + * @dev: Device which maps the buffer. + * @orig_addr: Original (non-bounced) IO buffer address. + * @alloc_size: Total requested size of the bounce buffer, + * including initial alignment padding. + * @alloc_align_mask: Required alignment of the allocated buffer. + * @retpool: Used memory pool, updated on return. + * + * Search through the whole software IO TLB to find a sequence of slots that + * match the allocation constraints. + * + * Return: Index of the first allocated slot, or -1 on error. + */ +static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr, + size_t alloc_size, unsigned int alloc_align_mask, + struct io_tlb_pool **retpool) +{ + struct io_tlb_mem *mem = dev->dma_io_tlb_mem; + struct io_tlb_pool *pool; + unsigned long nslabs; + unsigned long flags; + u64 phys_limit; + int index; + + rcu_read_lock(); + list_for_each_entry_rcu(pool, &mem->pools, node) { + index = swiotlb_pool_find_slots(dev, pool, orig_addr, + alloc_size, alloc_align_mask); + if (index >= 0) { + rcu_read_unlock(); + goto found; + } + } + rcu_read_unlock(); + if (!mem->can_grow) + return -1; + + schedule_work(&mem->dyn_alloc); + + nslabs = nr_slots(alloc_size); + phys_limit = min_not_zero(*dev->dma_mask, dev->bus_dma_limit); + pool = swiotlb_alloc_pool(dev, nslabs, nslabs, 1, phys_limit, + GFP_NOWAIT | __GFP_NOWARN); + if (!pool) + return -1; + + index = swiotlb_pool_find_slots(dev, pool, orig_addr, + alloc_size, alloc_align_mask); + if (index < 0) { + swiotlb_dyn_free(&pool->rcu); + return -1; + } + + pool->transient = true; + spin_lock_irqsave(&dev->dma_io_tlb_lock, flags); + list_add_rcu(&pool->node, &dev->dma_io_tlb_pools); + spin_unlock_irqrestore(&dev->dma_io_tlb_lock, flags); + +found: + WRITE_ONCE(dev->dma_uses_io_tlb, true); + + /* + * The general barrier orders reads and writes against a presumed store + * of the SWIOTLB buffer address by a device driver (to a driver private + * data structure). It serves two purposes. + * + * First, the store to dev->dma_uses_io_tlb must be ordered before the + * presumed store. This guarantees that the returned buffer address + * cannot be passed to another CPU before updating dev->dma_uses_io_tlb. + * + * Second, the load from mem->pools must be ordered before the same + * presumed store. This guarantees that the returned buffer address + * cannot be observed by another CPU before an update of the RCU list + * that was made by swiotlb_dyn_alloc() on a third CPU (cf. multicopy + * atomicity). + * + * See also the comment in is_swiotlb_buffer(). + */ + smp_mb(); + + *retpool = pool; + return index; +} + +#else /* !CONFIG_SWIOTLB_DYNAMIC */ + +static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr, + size_t alloc_size, unsigned int alloc_align_mask, + struct io_tlb_pool **retpool) +{ + *retpool = &dev->dma_io_tlb_mem->defpool; + return swiotlb_pool_find_slots(dev, *retpool, + orig_addr, alloc_size, alloc_align_mask); +} + +#endif /* CONFIG_SWIOTLB_DYNAMIC */ + +#ifdef CONFIG_DEBUG_FS + +/** + * mem_used() - get number of used slots in an allocator + * @mem: Software IO TLB allocator. + * + * The result is accurate in this version of the function, because an atomic + * counter is available if CONFIG_DEBUG_FS is set. + * + * Return: Number of used slots. + */ +static unsigned long mem_used(struct io_tlb_mem *mem) +{ + return atomic_long_read(&mem->total_used); +} + +#else /* !CONFIG_DEBUG_FS */ + +/** + * mem_pool_used() - get number of used slots in a memory pool + * @pool: Software IO TLB memory pool. + * + * The result is not accurate, see mem_used(). + * + * Return: Approximate number of used slots. + */ +static unsigned long mem_pool_used(struct io_tlb_pool *pool) +{ + int i; + unsigned long used = 0; + + for (i = 0; i < pool->nareas; i++) + used += pool->areas[i].used; + return used; +} + +/** + * mem_used() - get number of used slots in an allocator + * @mem: Software IO TLB allocator. + * + * The result is not accurate, because there is no locking of individual + * areas. + * + * Return: Approximate number of used slots. + */ +static unsigned long mem_used(struct io_tlb_mem *mem) +{ +#ifdef CONFIG_SWIOTLB_DYNAMIC + struct io_tlb_pool *pool; + unsigned long used = 0; + + rcu_read_lock(); + list_for_each_entry_rcu(pool, &mem->pools, node) + used += mem_pool_used(pool); + rcu_read_unlock(); + + return used; +#else + return mem_pool_used(&mem->defpool); +#endif +} + +#endif /* CONFIG_DEBUG_FS */ + +phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, + size_t mapping_size, size_t alloc_size, + unsigned int alloc_align_mask, enum dma_data_direction dir, + unsigned long attrs) +{ + struct io_tlb_mem *mem = dev->dma_io_tlb_mem; + unsigned int offset = swiotlb_align_offset(dev, orig_addr); + struct io_tlb_pool *pool; + unsigned int i; + int index; + phys_addr_t tlb_addr; + + if (!mem || !mem->nslabs) { + dev_warn_ratelimited(dev, + "Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer"); + return (phys_addr_t)DMA_MAPPING_ERROR; + } + + if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) + pr_warn_once("Memory encryption is active and system is using DMA bounce buffers\n"); + + if (mapping_size > alloc_size) { + dev_warn_once(dev, "Invalid sizes (mapping: %zd bytes, alloc: %zd bytes)", + mapping_size, alloc_size); + return (phys_addr_t)DMA_MAPPING_ERROR; + } + + index = swiotlb_find_slots(dev, orig_addr, + alloc_size + offset, alloc_align_mask, &pool); + if (index == -1) { + if (!(attrs & DMA_ATTR_NO_WARN)) + dev_warn_ratelimited(dev, + "swiotlb buffer is full (sz: %zd bytes), total %lu (slots), used %lu (slots)\n", + alloc_size, mem->nslabs, mem_used(mem)); + return (phys_addr_t)DMA_MAPPING_ERROR; + } + + /* + * Save away the mapping from the original address to the DMA address. + * This is needed when we sync the memory. Then we sync the buffer if + * needed. + */ + for (i = 0; i < nr_slots(alloc_size + offset); i++) + pool->slots[index + i].orig_addr = slot_addr(orig_addr, i); + tlb_addr = slot_addr(pool->start, index) + offset; + /* + * When dir == DMA_FROM_DEVICE we could omit the copy from the orig + * to the tlb buffer, if we knew for sure the device will + * overwrite the entire current content. But we don't. Thus + * unconditional bounce may prevent leaking swiotlb content (i.e. + * kernel memory) to user-space. + */ + swiotlb_bounce(dev, tlb_addr, mapping_size, DMA_TO_DEVICE); + return tlb_addr; +} + +static void swiotlb_release_slots(struct device *dev, phys_addr_t tlb_addr) +{ + struct io_tlb_pool *mem = swiotlb_find_pool(dev, tlb_addr); + unsigned long flags; + unsigned int offset = swiotlb_align_offset(dev, tlb_addr); + int index = (tlb_addr - offset - mem->start) >> IO_TLB_SHIFT; + int nslots = nr_slots(mem->slots[index].alloc_size + offset); + int aindex = index / mem->area_nslabs; + struct io_tlb_area *area = &mem->areas[aindex]; + int count, i; + + /* + * Return the buffer to the free list by setting the corresponding + * entries to indicate the number of contiguous entries available. + * While returning the entries to the free list, we merge the entries + * with slots below and above the pool being returned. + */ + BUG_ON(aindex >= mem->nareas); + + spin_lock_irqsave(&area->lock, flags); + if (index + nslots < ALIGN(index + 1, IO_TLB_SEGSIZE)) + count = mem->slots[index + nslots].list; + else + count = 0; + + /* + * Step 1: return the slots to the free list, merging the slots with + * superceeding slots + */ + for (i = index + nslots - 1; i >= index; i--) { + mem->slots[i].list = ++count; + mem->slots[i].orig_addr = INVALID_PHYS_ADDR; + mem->slots[i].alloc_size = 0; + } + + /* + * Step 2: merge the returned slots with the preceding slots, if + * available (non zero) + */ + for (i = index - 1; + io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 && mem->slots[i].list; + i--) + mem->slots[i].list = ++count; + area->used -= nslots; + spin_unlock_irqrestore(&area->lock, flags); + + dec_used(dev->dma_io_tlb_mem, nslots); +} + +#ifdef CONFIG_SWIOTLB_DYNAMIC + +/** + * swiotlb_del_transient() - delete a transient memory pool + * @dev: Device which mapped the buffer. + * @tlb_addr: Physical address within a bounce buffer. + * + * Check whether the address belongs to a transient SWIOTLB memory pool. + * If yes, then delete the pool. + * + * Return: %true if @tlb_addr belonged to a transient pool that was released. + */ +static bool swiotlb_del_transient(struct device *dev, phys_addr_t tlb_addr) +{ + struct io_tlb_pool *pool; + + pool = swiotlb_find_pool(dev, tlb_addr); + if (!pool->transient) + return false; + + dec_used(dev->dma_io_tlb_mem, pool->nslabs); + swiotlb_del_pool(dev, pool); + return true; +} + +#else /* !CONFIG_SWIOTLB_DYNAMIC */ + +static inline bool swiotlb_del_transient(struct device *dev, + phys_addr_t tlb_addr) +{ + return false; +} + +#endif /* CONFIG_SWIOTLB_DYNAMIC */ + +/* + * tlb_addr is the physical address of the bounce buffer to unmap. + */ +void swiotlb_tbl_unmap_single(struct device *dev, phys_addr_t tlb_addr, + size_t mapping_size, enum dma_data_direction dir, + unsigned long attrs) +{ + /* + * First, sync the memory before unmapping the entry + */ + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) && + (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)) + swiotlb_bounce(dev, tlb_addr, mapping_size, DMA_FROM_DEVICE); + + if (swiotlb_del_transient(dev, tlb_addr)) + return; + swiotlb_release_slots(dev, tlb_addr); +} + +void swiotlb_sync_single_for_device(struct device *dev, phys_addr_t tlb_addr, + size_t size, enum dma_data_direction dir) +{ + if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) + swiotlb_bounce(dev, tlb_addr, size, DMA_TO_DEVICE); + else + BUG_ON(dir != DMA_FROM_DEVICE); +} + +void swiotlb_sync_single_for_cpu(struct device *dev, phys_addr_t tlb_addr, + size_t size, enum dma_data_direction dir) +{ + if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) + swiotlb_bounce(dev, tlb_addr, size, DMA_FROM_DEVICE); + else + BUG_ON(dir != DMA_TO_DEVICE); +} + +/* + * Create a swiotlb mapping for the buffer at @paddr, and in case of DMAing + * to the device copy the data into it as well. + */ +dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size, + enum dma_data_direction dir, unsigned long attrs) +{ + phys_addr_t swiotlb_addr; + dma_addr_t dma_addr; + + trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size); + + swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, size, 0, dir, + attrs); + if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR) + return DMA_MAPPING_ERROR; + + /* Ensure that the address returned is DMA'ble */ + dma_addr = phys_to_dma_unencrypted(dev, swiotlb_addr); + if (unlikely(!dma_capable(dev, dma_addr, size, true))) { + swiotlb_tbl_unmap_single(dev, swiotlb_addr, size, dir, + attrs | DMA_ATTR_SKIP_CPU_SYNC); + dev_WARN_ONCE(dev, 1, + "swiotlb addr %pad+%zu overflow (mask %llx, bus limit %llx).\n", + &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit); + return DMA_MAPPING_ERROR; + } + + if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + arch_sync_dma_for_device(swiotlb_addr, size, dir); + return dma_addr; +} + +size_t swiotlb_max_mapping_size(struct device *dev) +{ + int min_align_mask = dma_get_min_align_mask(dev); + int min_align = 0; + + /* + * swiotlb_find_slots() skips slots according to + * min align mask. This affects max mapping size. + * Take it into acount here. + */ + if (min_align_mask) + min_align = roundup(min_align_mask, IO_TLB_SIZE); + + return ((size_t)IO_TLB_SIZE) * IO_TLB_SEGSIZE - min_align; +} + +/** + * is_swiotlb_allocated() - check if the default software IO TLB is initialized + */ +bool is_swiotlb_allocated(void) +{ + return io_tlb_default_mem.nslabs; +} + +bool is_swiotlb_active(struct device *dev) +{ + struct io_tlb_mem *mem = dev->dma_io_tlb_mem; + + return mem && mem->nslabs; +} + +/** + * default_swiotlb_base() - get the base address of the default SWIOTLB + * + * Get the lowest physical address used by the default software IO TLB pool. + */ +phys_addr_t default_swiotlb_base(void) +{ +#ifdef CONFIG_SWIOTLB_DYNAMIC + io_tlb_default_mem.can_grow = false; +#endif + return io_tlb_default_mem.defpool.start; +} + +/** + * default_swiotlb_limit() - get the address limit of the default SWIOTLB + * + * Get the highest physical address used by the default software IO TLB pool. + */ +phys_addr_t default_swiotlb_limit(void) +{ +#ifdef CONFIG_SWIOTLB_DYNAMIC + return io_tlb_default_mem.phys_limit; +#else + return io_tlb_default_mem.defpool.end - 1; +#endif +} + +#ifdef CONFIG_DEBUG_FS + +static int io_tlb_used_get(void *data, u64 *val) +{ + struct io_tlb_mem *mem = data; + + *val = mem_used(mem); + return 0; +} + +static int io_tlb_hiwater_get(void *data, u64 *val) +{ + struct io_tlb_mem *mem = data; + + *val = atomic_long_read(&mem->used_hiwater); + return 0; +} + +static int io_tlb_hiwater_set(void *data, u64 val) +{ + struct io_tlb_mem *mem = data; + + /* Only allow setting to zero */ + if (val != 0) + return -EINVAL; + + atomic_long_set(&mem->used_hiwater, val); + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(fops_io_tlb_used, io_tlb_used_get, NULL, "%llu\n"); +DEFINE_DEBUGFS_ATTRIBUTE(fops_io_tlb_hiwater, io_tlb_hiwater_get, + io_tlb_hiwater_set, "%llu\n"); + +static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem, + const char *dirname) +{ + atomic_long_set(&mem->total_used, 0); + atomic_long_set(&mem->used_hiwater, 0); + + mem->debugfs = debugfs_create_dir(dirname, io_tlb_default_mem.debugfs); + if (!mem->nslabs) + return; + + debugfs_create_ulong("io_tlb_nslabs", 0400, mem->debugfs, &mem->nslabs); + debugfs_create_file("io_tlb_used", 0400, mem->debugfs, mem, + &fops_io_tlb_used); + debugfs_create_file("io_tlb_used_hiwater", 0600, mem->debugfs, mem, + &fops_io_tlb_hiwater); +} + +static int __init swiotlb_create_default_debugfs(void) +{ + swiotlb_create_debugfs_files(&io_tlb_default_mem, "swiotlb"); + return 0; +} + +late_initcall(swiotlb_create_default_debugfs); + +#else /* !CONFIG_DEBUG_FS */ + +static inline void swiotlb_create_debugfs_files(struct io_tlb_mem *mem, + const char *dirname) +{ +} + +#endif /* CONFIG_DEBUG_FS */ + +#ifdef CONFIG_DMA_RESTRICTED_POOL + +struct page *swiotlb_alloc(struct device *dev, size_t size) +{ + struct io_tlb_mem *mem = dev->dma_io_tlb_mem; + struct io_tlb_pool *pool; + phys_addr_t tlb_addr; + int index; + + if (!mem) + return NULL; + + index = swiotlb_find_slots(dev, 0, size, 0, &pool); + if (index == -1) + return NULL; + + tlb_addr = slot_addr(pool->start, index); + + return pfn_to_page(PFN_DOWN(tlb_addr)); +} + +bool swiotlb_free(struct device *dev, struct page *page, size_t size) +{ + phys_addr_t tlb_addr = page_to_phys(page); + + if (!is_swiotlb_buffer(dev, tlb_addr)) + return false; + + swiotlb_release_slots(dev, tlb_addr); + + return true; +} + +static int rmem_swiotlb_device_init(struct reserved_mem *rmem, + struct device *dev) +{ + struct io_tlb_mem *mem = rmem->priv; + unsigned long nslabs = rmem->size >> IO_TLB_SHIFT; + + /* Set Per-device io tlb area to one */ + unsigned int nareas = 1; + + if (PageHighMem(pfn_to_page(PHYS_PFN(rmem->base)))) { + dev_err(dev, "Restricted DMA pool must be accessible within the linear mapping."); + return -EINVAL; + } + + /* + * Since multiple devices can share the same pool, the private data, + * io_tlb_mem struct, will be initialized by the first device attached + * to it. + */ + if (!mem) { + struct io_tlb_pool *pool; + + mem = kzalloc(sizeof(*mem), GFP_KERNEL); + if (!mem) + return -ENOMEM; + pool = &mem->defpool; + + pool->slots = kcalloc(nslabs, sizeof(*pool->slots), GFP_KERNEL); + if (!pool->slots) { + kfree(mem); + return -ENOMEM; + } + + pool->areas = kcalloc(nareas, sizeof(*pool->areas), + GFP_KERNEL); + if (!pool->areas) { + kfree(pool->slots); + kfree(mem); + return -ENOMEM; + } + + set_memory_decrypted((unsigned long)phys_to_virt(rmem->base), + rmem->size >> PAGE_SHIFT); + swiotlb_init_io_tlb_pool(pool, rmem->base, nslabs, + false, nareas); + mem->force_bounce = true; + mem->for_alloc = true; +#ifdef CONFIG_SWIOTLB_DYNAMIC + spin_lock_init(&mem->lock); +#endif + add_mem_pool(mem, pool); + + rmem->priv = mem; + + swiotlb_create_debugfs_files(mem, rmem->name); + } + + dev->dma_io_tlb_mem = mem; + + return 0; +} + +static void rmem_swiotlb_device_release(struct reserved_mem *rmem, + struct device *dev) +{ + dev->dma_io_tlb_mem = &io_tlb_default_mem; +} + +static const struct reserved_mem_ops rmem_swiotlb_ops = { + .device_init = rmem_swiotlb_device_init, + .device_release = rmem_swiotlb_device_release, +}; + +static int __init rmem_swiotlb_setup(struct reserved_mem *rmem) +{ + unsigned long node = rmem->fdt_node; + + if (of_get_flat_dt_prop(node, "reusable", NULL) || + of_get_flat_dt_prop(node, "linux,cma-default", NULL) || + of_get_flat_dt_prop(node, "linux,dma-default", NULL) || + of_get_flat_dt_prop(node, "no-map", NULL)) + return -EINVAL; + + rmem->ops = &rmem_swiotlb_ops; + pr_info("Reserved memory: created restricted DMA pool at %pa, size %ld MiB\n", + &rmem->base, (unsigned long)rmem->size / SZ_1M); + return 0; +} + +RESERVEDMEM_OF_DECLARE(dma, "restricted-dma-pool", rmem_swiotlb_setup); +#endif /* CONFIG_DMA_RESTRICTED_POOL */ -- cgit v1.2.3