Add a new function, swiotlb_init_io_tlb_mem, for the io_tlb_mem struct initialization to make the code reusable.

Signed-off-by: Claire Chang tientzu@chromium.org --- kernel/dma/swiotlb.c | 53 ++++++++++++++++++++++---------------------- 1 file changed, 27 insertions(+), 26 deletions(-)

diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 8ca7d505d61c..1a1208c81e85 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -168,9 +168,32 @@ void __init swiotlb_update_mem_attributes(void) memset(vaddr, 0, bytes); }

-int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) +static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start, + unsigned long nslabs, bool late_alloc, + bool memory_decrypted) { + 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->index = 0; + mem->late_alloc = late_alloc; + spin_lock_init(&mem->lock); + for (i = 0; i < mem->nslabs; i++) { + mem->slots[i].list = IO_TLB_SEGSIZE - io_tlb_offset(i); + mem->slots[i].orig_addr = INVALID_PHYS_ADDR; + mem->slots[i].alloc_size = 0; + } + + if (memory_decrypted) + set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT); + memset(vaddr, 0, bytes); +} + +int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) +{ struct io_tlb_mem *mem; size_t alloc_size;

@@ -186,16 +209,8 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) if (!mem) panic("%s: Failed to allocate %zu bytes align=0x%lx\n", __func__, alloc_size, PAGE_SIZE); - mem->nslabs = nslabs; - mem->start = __pa(tlb); - mem->end = mem->start + bytes; - mem->index = 0; - spin_lock_init(&mem->lock); - for (i = 0; i < mem->nslabs; i++) { - mem->slots[i].list = IO_TLB_SEGSIZE - io_tlb_offset(i); - mem->slots[i].orig_addr = INVALID_PHYS_ADDR; - mem->slots[i].alloc_size = 0; - } + + swiotlb_init_io_tlb_mem(mem, __pa(tlb), nslabs, false, false);

io_tlb_default_mem = mem; if (verbose) @@ -282,7 +297,6 @@ swiotlb_late_init_with_default_size(size_t default_size) int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) { - unsigned long bytes = nslabs << IO_TLB_SHIFT, i; struct io_tlb_mem *mem;

if (swiotlb_force == SWIOTLB_NO_FORCE) @@ -297,20 +311,7 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) if (!mem) return -ENOMEM;

- mem->nslabs = nslabs; - mem->start = virt_to_phys(tlb); - mem->end = mem->start + bytes; - mem->index = 0; - mem->late_alloc = 1; - spin_lock_init(&mem->lock); - for (i = 0; i < mem->nslabs; i++) { - mem->slots[i].list = IO_TLB_SEGSIZE - io_tlb_offset(i); - mem->slots[i].orig_addr = INVALID_PHYS_ADDR; - mem->slots[i].alloc_size = 0; - } - - set_memory_decrypted((unsigned long)tlb, bytes >> PAGE_SHIFT); - memset(tlb, 0, bytes); + swiotlb_init_io_tlb_mem(mem, virt_to_phys(tlb), nslabs, true, true);

io_tlb_default_mem = mem; swiotlb_print_info();

Always have the pointer to the swiotlb pool used in struct device. This could help simplify the code for other pools.

Signed-off-by: Claire Chang tientzu@chromium.org --- drivers/of/device.c | 3 +++ include/linux/device.h | 4 ++++ include/linux/swiotlb.h | 8 ++++++++ kernel/dma/swiotlb.c | 8 ++++---- 4 files changed, 19 insertions(+), 4 deletions(-)

diff --git a/drivers/of/device.c b/drivers/of/device.c index c5a9473a5fb1..1defdf15ba95 100644 --- a/drivers/of/device.c +++ b/drivers/of/device.c @@ -165,6 +165,9 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,

arch_setup_dma_ops(dev, dma_start, size, iommu, coherent);

+ if (IS_ENABLED(CONFIG_SWIOTLB)) + swiotlb_set_io_tlb_default_mem(dev); + return 0; } EXPORT_SYMBOL_GPL(of_dma_configure_id); diff --git a/include/linux/device.h b/include/linux/device.h index 4443e12238a0..2e9a378c9100 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -432,6 +432,7 @@ struct dev_links_info { * @dma_pools: Dma pools (if dma'ble device). * @dma_mem: Internal for coherent mem override. * @cma_area: Contiguous memory area for dma allocations + * @dma_io_tlb_mem: Pointer to the swiotlb pool used. Not for driver use. * @archdata: For arch-specific additions. * @of_node: Associated device tree node. * @fwnode: Associated device node supplied by platform firmware. @@ -540,6 +541,9 @@ struct device { #ifdef CONFIG_DMA_CMA struct cma *cma_area; /* contiguous memory area for dma allocations */ +#endif +#ifdef CONFIG_SWIOTLB + struct io_tlb_mem *dma_io_tlb_mem; #endif /* arch specific additions */ struct dev_archdata archdata; diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 216854a5e513..008125ccd509 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -108,6 +108,11 @@ static inline bool is_swiotlb_buffer(phys_addr_t paddr) return mem && paddr >= mem->start && paddr < mem->end; }

+static inline void swiotlb_set_io_tlb_default_mem(struct device *dev) +{ + dev->dma_io_tlb_mem = io_tlb_default_mem; +} + void __init swiotlb_exit(void); unsigned int swiotlb_max_segment(void); size_t swiotlb_max_mapping_size(struct device *dev); @@ -119,6 +124,9 @@ static inline bool is_swiotlb_buffer(phys_addr_t paddr) { return false; } +static inline void swiotlb_set_io_tlb_default_mem(struct device *dev) +{ +} static inline void swiotlb_exit(void) { } diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 8a3e2b3b246d..29b950ab1351 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -344,7 +344,7 @@ void __init swiotlb_exit(void) static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size, enum dma_data_direction dir) { - struct io_tlb_mem *mem = io_tlb_default_mem; + struct io_tlb_mem *mem = dev->dma_io_tlb_mem; 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; @@ -426,7 +426,7 @@ static unsigned int wrap_index(struct io_tlb_mem *mem, unsigned int index) static int find_slots(struct device *dev, phys_addr_t orig_addr, size_t alloc_size) { - struct io_tlb_mem *mem = io_tlb_default_mem; + struct io_tlb_mem *mem = dev->dma_io_tlb_mem; unsigned long boundary_mask = dma_get_seg_boundary(dev); dma_addr_t tbl_dma_addr = phys_to_dma_unencrypted(dev, mem->start) & boundary_mask; @@ -503,7 +503,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, size_t mapping_size, size_t alloc_size, enum dma_data_direction dir, unsigned long attrs) { - struct io_tlb_mem *mem = io_tlb_default_mem; + struct io_tlb_mem *mem = dev->dma_io_tlb_mem; unsigned int offset = swiotlb_align_offset(dev, orig_addr); unsigned int i; int index; @@ -554,7 +554,7 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, size_t mapping_size, enum dma_data_direction dir, unsigned long attrs) { - struct io_tlb_mem *mem = io_tlb_default_mem; + struct io_tlb_mem *mem = hwdev->dma_io_tlb_mem; unsigned long flags; unsigned int offset = swiotlb_align_offset(hwdev, tlb_addr); int index = (tlb_addr - offset - mem->start) >> IO_TLB_SHIFT;

Add the initialization function to create restricted DMA pools from matching reserved-memory nodes.

Signed-off-by: Claire Chang tientzu@chromium.org --- include/linux/swiotlb.h | 3 +- kernel/dma/Kconfig | 14 ++++++++ kernel/dma/swiotlb.c | 75 +++++++++++++++++++++++++++++++++++++++++ 3 files changed, 91 insertions(+), 1 deletion(-)

diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 008125ccd509..ec0c01796c8a 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -72,7 +72,8 @@ extern enum swiotlb_force swiotlb_force; * range check to see if the memory was in fact allocated by this * API. * @nslabs: The number of IO TLB blocks (in groups of 64) between @start and - * @end. This is command line adjustable via setup_io_tlb_npages. + * @end. For default swiotlb, this is command line adjustable via + * setup_io_tlb_npages. * @used: The number of used IO TLB block. * @list: The free list describing the number of free entries available * from each index. diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig index 77b405508743..3e961dc39634 100644 --- a/kernel/dma/Kconfig +++ b/kernel/dma/Kconfig @@ -80,6 +80,20 @@ config SWIOTLB bool select NEED_DMA_MAP_STATE

+config DMA_RESTRICTED_POOL + bool "DMA Restricted Pool" + depends on OF && OF_RESERVED_MEM + select 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 + <Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt> + and <kernel/dma/swiotlb.c>. + 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 diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 29b950ab1351..c4a071d6a63f 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -39,6 +39,13 @@ #ifdef CONFIG_DEBUG_FS #include <linux/debugfs.h> #endif +#ifdef CONFIG_DMA_RESTRICTED_POOL +#include <linux/io.h> +#include <linux/of.h> +#include <linux/of_fdt.h> +#include <linux/of_reserved_mem.h> +#include <linux/slab.h> +#endif

#include <asm/io.h> #include <asm/dma.h> @@ -688,3 +695,71 @@ static int __init swiotlb_create_default_debugfs(void) late_initcall(swiotlb_create_default_debugfs);

#endif + +#ifdef CONFIG_DMA_RESTRICTED_POOL +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; + + /* + * 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) { + mem = kzalloc(struct_size(mem, slots, nslabs), GFP_KERNEL); + if (!mem) + return -ENOMEM; + + swiotlb_init_io_tlb_mem(mem, rmem->base, nslabs, false, true); + + rmem->priv = mem; + + if (IS_ENABLED(CONFIG_DEBUG_FS)) { + mem->debugfs = + debugfs_create_dir(rmem->name, debugfs_dir); + swiotlb_create_debugfs_files(mem); + } + } + + 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; + + if (PageHighMem(pfn_to_page(PHYS_PFN(rmem->base)))) { + pr_err("Restricted DMA pool must be accessible within the linear mapping."); + 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 */

Update is_swiotlb_active to add a struct device argument. This will be useful later to allow for restricted DMA pool.

Signed-off-by: Claire Chang tientzu@chromium.org --- drivers/gpu/drm/i915/gem/i915_gem_internal.c | 2 +- drivers/gpu/drm/nouveau/nouveau_ttm.c | 2 +- drivers/pci/xen-pcifront.c | 2 +- include/linux/swiotlb.h | 4 ++-- kernel/dma/direct.c | 2 +- kernel/dma/swiotlb.c | 4 ++-- 6 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_internal.c b/drivers/gpu/drm/i915/gem/i915_gem_internal.c index ce6b664b10aa..89a894354263 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_internal.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_internal.c @@ -42,7 +42,7 @@ static int i915_gem_object_get_pages_internal(struct drm_i915_gem_object *obj)

max_order = MAX_ORDER; #ifdef CONFIG_SWIOTLB - if (is_swiotlb_active()) { + if (is_swiotlb_active(obj->base.dev->dev)) { unsigned int max_segment;

max_segment = swiotlb_max_segment(); diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c index f4c2e46b6fe1..2ca9d9a9e5d5 100644 --- a/drivers/gpu/drm/nouveau/nouveau_ttm.c +++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c @@ -276,7 +276,7 @@ nouveau_ttm_init(struct nouveau_drm *drm) }

#if IS_ENABLED(CONFIG_SWIOTLB) && IS_ENABLED(CONFIG_X86) - need_swiotlb = is_swiotlb_active(); + need_swiotlb = is_swiotlb_active(dev->dev); #endif

ret = ttm_device_init(&drm->ttm.bdev, &nouveau_bo_driver, drm->dev->dev, diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c index b7a8f3a1921f..0d56985bfe81 100644 --- a/drivers/pci/xen-pcifront.c +++ b/drivers/pci/xen-pcifront.c @@ -693,7 +693,7 @@ static int pcifront_connect_and_init_dma(struct pcifront_device *pdev)

spin_unlock(&pcifront_dev_lock);

- if (!err && !is_swiotlb_active()) { + if (!err && !is_swiotlb_active(&pdev->xdev->dev)) { err = pci_xen_swiotlb_init_late(); if (err) dev_err(&pdev->xdev->dev, "Could not setup SWIOTLB!\n"); diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 921b469c6ad2..06cf17a80f5c 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -118,7 +118,7 @@ static inline void swiotlb_set_io_tlb_default_mem(struct device *dev) void __init swiotlb_exit(void); unsigned int swiotlb_max_segment(void); size_t swiotlb_max_mapping_size(struct device *dev); -bool is_swiotlb_active(void); +bool is_swiotlb_active(struct device *dev); void __init swiotlb_adjust_size(unsigned long size); #else #define swiotlb_force SWIOTLB_NO_FORCE @@ -141,7 +141,7 @@ static inline size_t swiotlb_max_mapping_size(struct device *dev) return SIZE_MAX; }

-static inline bool is_swiotlb_active(void) +static inline bool is_swiotlb_active(struct device *dev) { return false; } diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 84c9feb5474a..7a88c34d0867 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -495,7 +495,7 @@ int dma_direct_supported(struct device *dev, u64 mask) size_t dma_direct_max_mapping_size(struct device *dev) { /* If SWIOTLB is active, use its maximum mapping size */ - if (is_swiotlb_active() && + if (is_swiotlb_active(dev) && (dma_addressing_limited(dev) || swiotlb_force == SWIOTLB_FORCE)) return swiotlb_max_mapping_size(dev); return SIZE_MAX; diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index c4a071d6a63f..21e99907edd6 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -666,9 +666,9 @@ size_t swiotlb_max_mapping_size(struct device *dev) return ((size_t)IO_TLB_SIZE) * IO_TLB_SEGSIZE; }

-bool is_swiotlb_active(void) +bool is_swiotlb_active(struct device *dev) { - return io_tlb_default_mem != NULL; + return dev->dma_io_tlb_mem != NULL; } EXPORT_SYMBOL_GPL(is_swiotlb_active);

Regardless of swiotlb setting, the restricted DMA pool is preferred if available.

The restricted DMA pools provide a basic level of protection against the DMA overwriting buffer contents at unexpected times. However, to protect against general data leakage and system memory corruption, the system needs to provide a way to lock down the memory access, e.g., MPU.

Note that is_dev_swiotlb_force doesn't check if swiotlb_force == SWIOTLB_FORCE. Otherwise the memory allocation behavior with default swiotlb will be changed by the following patche ("dma-direct: Allocate memory from restricted DMA pool if available").

Signed-off-by: Claire Chang tientzu@chromium.org --- include/linux/swiotlb.h | 10 +++++++++- kernel/dma/direct.c | 3 ++- kernel/dma/direct.h | 3 ++- kernel/dma/swiotlb.c | 1 + 4 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 06cf17a80f5c..8200c100fe10 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -85,6 +85,7 @@ extern enum swiotlb_force swiotlb_force; * unmap calls. * @debugfs: The dentry to debugfs. * @late_alloc: %true if allocated using the page allocator + * @force_swiotlb: %true if swiotlb is forced */ struct io_tlb_mem { phys_addr_t start; @@ -95,6 +96,7 @@ struct io_tlb_mem { spinlock_t lock; struct dentry *debugfs; bool late_alloc; + bool force_swiotlb; struct io_tlb_slot { phys_addr_t orig_addr; size_t alloc_size; @@ -115,6 +117,11 @@ static inline void swiotlb_set_io_tlb_default_mem(struct device *dev) dev->dma_io_tlb_mem = io_tlb_default_mem; }

+static inline bool is_dev_swiotlb_force(struct device *dev) +{ + return dev->dma_io_tlb_mem->force_swiotlb; +} + void __init swiotlb_exit(void); unsigned int swiotlb_max_segment(void); size_t swiotlb_max_mapping_size(struct device *dev); @@ -126,8 +133,9 @@ static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) { return false; } -static inline void swiotlb_set_io_tlb_default_mem(struct device *dev) +static inline bool is_dev_swiotlb_force(struct device *dev) { + return false; } static inline void swiotlb_exit(void) { diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 7a88c34d0867..078f7087e466 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -496,7 +496,8 @@ 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) || swiotlb_force == SWIOTLB_FORCE)) + (dma_addressing_limited(dev) || swiotlb_force == SWIOTLB_FORCE || + is_dev_swiotlb_force(dev))) return swiotlb_max_mapping_size(dev); return SIZE_MAX; } diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h index 13e9e7158d94..f94813674e23 100644 --- a/kernel/dma/direct.h +++ b/kernel/dma/direct.h @@ -87,7 +87,8 @@ static inline dma_addr_t dma_direct_map_page(struct device *dev, phys_addr_t phys = page_to_phys(page) + offset; dma_addr_t dma_addr = phys_to_dma(dev, phys);

- if (unlikely(swiotlb_force == SWIOTLB_FORCE)) + if (unlikely(swiotlb_force == SWIOTLB_FORCE) || + is_dev_swiotlb_force(dev)) return swiotlb_map(dev, phys, size, dir, attrs);

if (unlikely(!dma_capable(dev, dma_addr, size, true))) { diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 21e99907edd6..e5ccc198d0a7 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -714,6 +714,7 @@ static int rmem_swiotlb_device_init(struct reserved_mem *rmem, return -ENOMEM;

swiotlb_init_io_tlb_mem(mem, rmem->base, nslabs, false, true); + mem->force_swiotlb = true;

rmem->priv = mem;

Add a new function, release_slots, to make the code reusable for supporting different bounce buffer pools, e.g. restricted DMA pool.

Signed-off-by: Claire Chang tientzu@chromium.org --- kernel/dma/swiotlb.c | 35 ++++++++++++++++++++--------------- 1 file changed, 20 insertions(+), 15 deletions(-)

diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 364c6c822063..a6562573f090 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -554,27 +554,15 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, return tlb_addr; }

-/* - * tlb_addr is the physical address of the bounce buffer to unmap. - */ -void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, - size_t mapping_size, enum dma_data_direction dir, - unsigned long attrs) +static void release_slots(struct device *dev, phys_addr_t tlb_addr) { - struct io_tlb_mem *mem = hwdev->dma_io_tlb_mem; + struct io_tlb_mem *mem = dev->dma_io_tlb_mem; unsigned long flags; - unsigned int offset = swiotlb_align_offset(hwdev, tlb_addr); + 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 count, i;

- /* - * First, sync the memory before unmapping the entry - */ - if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) && - (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)) - swiotlb_bounce(hwdev, tlb_addr, mapping_size, DMA_FROM_DEVICE); - /* * Return the buffer to the free list by setting the corresponding * entries to indicate the number of contiguous entries available. @@ -609,6 +597,23 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, spin_unlock_irqrestore(&mem->lock, flags); }

+/* + * 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); + + 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) {

Add the functions, swiotlb_{alloc,free} to support the memory allocation from restricted DMA pool.

Signed-off-by: Claire Chang tientzu@chromium.org --- include/linux/swiotlb.h | 15 +++++++++++++++ kernel/dma/swiotlb.c | 35 +++++++++++++++++++++++++++++++++-- 2 files changed, 48 insertions(+), 2 deletions(-)

diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 8200c100fe10..d3374497a4f8 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -162,4 +162,19 @@ static inline void swiotlb_adjust_size(unsigned long size) extern void swiotlb_print_info(void); extern void swiotlb_set_max_segment(unsigned int);

+#ifdef CONFIG_DMA_RESTRICTED_POOL +struct page *swiotlb_alloc(struct device *dev, size_t size); +bool swiotlb_free(struct device *dev, struct page *page, size_t size); +#else +static inline struct page *swiotlb_alloc(struct device *dev, size_t size) +{ + return NULL; +} +static inline bool swiotlb_free(struct device *dev, struct page *page, + size_t size) +{ + return false; +} +#endif /* CONFIG_DMA_RESTRICTED_POOL */ + #endif /* __LINUX_SWIOTLB_H */ diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index a6562573f090..0a19858da5b8 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -461,8 +461,9 @@ static int find_slots(struct device *dev, phys_addr_t orig_addr,

index = wrap = wrap_index(mem, ALIGN(mem->index, stride)); do { - if ((slot_addr(tbl_dma_addr, index) & iotlb_align_mask) != - (orig_addr & iotlb_align_mask)) { + if (orig_addr && + (slot_addr(tbl_dma_addr, index) & iotlb_align_mask) != + (orig_addr & iotlb_align_mask)) { index = wrap_index(mem, index + 1); continue; } @@ -702,6 +703,36 @@ late_initcall(swiotlb_create_default_debugfs); #endif

#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; + phys_addr_t tlb_addr; + int index; + + if (!mem) + return NULL; + + index = find_slots(dev, 0, size); + if (index == -1) + return NULL; + + tlb_addr = slot_addr(mem->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; + + release_slots(dev, tlb_addr); + + return true; +} + static int rmem_swiotlb_device_init(struct reserved_mem *rmem, struct device *dev) {

Introduce the new compatible string, restricted-dma-pool, for restricted DMA. One can specify the address and length of the restricted DMA memory region by restricted-dma-pool in the reserved-memory node.

Signed-off-by: Claire Chang tientzu@chromium.org --- .../reserved-memory/reserved-memory.txt | 36 +++++++++++++++++-- 1 file changed, 33 insertions(+), 3 deletions(-)

diff --git a/Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt b/Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt index e8d3096d922c..46804f24df05 100644 --- a/Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt +++ b/Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt @@ -51,6 +51,23 @@ compatible (optional) - standard definition used as a shared pool of DMA buffers for a set of devices. It can be used by an operating system to instantiate the necessary pool management subsystem if necessary. + - restricted-dma-pool: This indicates a region of memory meant to be + used as a pool of restricted DMA buffers for a set of devices. The + memory region would be the only region accessible to those devices. + When using this, the no-map and reusable properties must not be set, + so the operating system can create a virtual mapping that will be used + for synchronization. The main purpose for restricted DMA is to + mitigate the lack of DMA access control on systems without an IOMMU, + which could result in the DMA accessing the system memory at + unexpected times and/or unexpected addresses, possibly leading to data + leakage or corruption. The feature on its own provides a basic level + of protection against the DMA overwriting buffer contents at + unexpected times. However, to protect against general data leakage and + system memory corruption, the system needs to provide way to lock down + the memory access, e.g., MPU. Note that since coherent allocation + needs remapping, one must set up another device coherent pool by + shared-dma-pool and use dma_alloc_from_dev_coherent instead for atomic + coherent allocation. - vendor specific string in the form <vendor>,[<device>-]<usage> no-map (optional) - empty property - Indicates the operating system must not create a virtual mapping @@ -85,10 +102,11 @@ memory-region-names (optional) - a list of names, one for each corresponding

Example ------- -This example defines 3 contiguous regions are defined for Linux kernel: +This example defines 4 contiguous regions for Linux kernel: one default of all device drivers (named linux,cma@72000000 and 64MiB in size), -one dedicated to the framebuffer device (named framebuffer@78000000, 8MiB), and -one for multimedia processing (named multimedia-memory@77000000, 64MiB). +one dedicated to the framebuffer device (named framebuffer@78000000, 8MiB), +one for multimedia processing (named multimedia-memory@77000000, 64MiB), and +one for restricted dma pool (named restricted_dma_reserved@0x50000000, 64MiB).

/ { #address-cells = <1>; @@ -120,6 +138,11 @@ one for multimedia processing (named multimedia-memory@77000000, 64MiB). compatible = "acme,multimedia-memory"; reg = <0x77000000 0x4000000>; }; + + restricted_dma_reserved: restricted_dma_reserved { + compatible = "restricted-dma-pool"; + reg = <0x50000000 0x4000000>; + }; };

/* ... */ @@ -138,4 +161,11 @@ one for multimedia processing (named multimedia-memory@77000000, 64MiB). memory-region = <&multimedia_reserved>; /* ... */ }; + + pcie_device: pcie_device@0,0 { + reg = <0x83010000 0x0 0x00000000 0x0 0x00100000 + 0x83010000 0x0 0x00100000 0x0 0x00100000>; + memory-region = <&restricted_dma_mem_reserved>; + /* ... */ + }; };