From 69031f500865ee3eee19566a1b9c40a189817eaa Mon Sep 17 00:00:00 2001 From: Claire Chang Date: Sat, 19 Jun 2021 11:40:34 +0800 Subject: swiotlb: Set dev->dma_io_tlb_mem to the swiotlb pool used 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 Reviewed-by: Christoph Hellwig Tested-by: Stefano Stabellini Tested-by: Will Deacon Acked-by: Stefano Stabellini Signed-off-by: Konrad Rzeszutek Wilk --- include/linux/device.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 59940f1744c1..2a22875238a6 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -423,6 +423,7 @@ 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. @@ -531,6 +532,9 @@ 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; -- cgit v1.2.3-59-g8ed1b From 7fd856aa7f4261ddac62ea59d8383fef22a0690e Mon Sep 17 00:00:00 2001 From: Claire Chang Date: Sat, 19 Jun 2021 11:40:35 +0800 Subject: swiotlb: Update is_swiotlb_buffer to add a struct device argument Update is_swiotlb_buffer to add a struct device argument. This will be useful later to allow for different pools. Signed-off-by: Claire Chang Reviewed-by: Christoph Hellwig Tested-by: Stefano Stabellini Tested-by: Will Deacon Acked-by: Stefano Stabellini Signed-off-by: Konrad Rzeszutek Wilk --- drivers/iommu/dma-iommu.c | 12 ++++++------ drivers/xen/swiotlb-xen.c | 2 +- include/linux/swiotlb.h | 7 ++++--- kernel/dma/direct.c | 6 +++--- kernel/dma/direct.h | 6 +++--- 5 files changed, 17 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 98ba927aee1a..4e34e8b26579 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -506,7 +506,7 @@ static void __iommu_dma_unmap_swiotlb(struct device *dev, dma_addr_t dma_addr, __iommu_dma_unmap(dev, dma_addr, size); - if (unlikely(is_swiotlb_buffer(phys))) + if (unlikely(is_swiotlb_buffer(dev, phys))) swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs); } @@ -577,7 +577,7 @@ static dma_addr_t __iommu_dma_map_swiotlb(struct device *dev, phys_addr_t phys, } iova = __iommu_dma_map(dev, phys, aligned_size, prot, dma_mask); - if (iova == DMA_MAPPING_ERROR && is_swiotlb_buffer(phys)) + if (iova == DMA_MAPPING_ERROR && is_swiotlb_buffer(dev, phys)) swiotlb_tbl_unmap_single(dev, phys, org_size, dir, attrs); return iova; } @@ -783,7 +783,7 @@ static void iommu_dma_sync_single_for_cpu(struct device *dev, if (!dev_is_dma_coherent(dev)) arch_sync_dma_for_cpu(phys, size, dir); - if (is_swiotlb_buffer(phys)) + if (is_swiotlb_buffer(dev, phys)) swiotlb_sync_single_for_cpu(dev, phys, size, dir); } @@ -796,7 +796,7 @@ static void iommu_dma_sync_single_for_device(struct device *dev, return; phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dma_handle); - if (is_swiotlb_buffer(phys)) + if (is_swiotlb_buffer(dev, phys)) swiotlb_sync_single_for_device(dev, phys, size, dir); if (!dev_is_dma_coherent(dev)) @@ -817,7 +817,7 @@ static void iommu_dma_sync_sg_for_cpu(struct device *dev, if (!dev_is_dma_coherent(dev)) arch_sync_dma_for_cpu(sg_phys(sg), sg->length, dir); - if (is_swiotlb_buffer(sg_phys(sg))) + if (is_swiotlb_buffer(dev, sg_phys(sg))) swiotlb_sync_single_for_cpu(dev, sg_phys(sg), sg->length, dir); } @@ -834,7 +834,7 @@ static void iommu_dma_sync_sg_for_device(struct device *dev, return; for_each_sg(sgl, sg, nelems, i) { - if (is_swiotlb_buffer(sg_phys(sg))) + if (is_swiotlb_buffer(dev, sg_phys(sg))) swiotlb_sync_single_for_device(dev, sg_phys(sg), sg->length, dir); diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 24d11861ac7d..0c4fb34f11ab 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -100,7 +100,7 @@ static int is_xen_swiotlb_buffer(struct device *dev, dma_addr_t dma_addr) * in our domain. Therefore _only_ check address within our domain. */ if (pfn_valid(PFN_DOWN(paddr))) - return is_swiotlb_buffer(paddr); + return is_swiotlb_buffer(dev, paddr); return 0; } diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 216854a5e513..d1f3d95881cd 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -2,6 +2,7 @@ #ifndef __LINUX_SWIOTLB_H #define __LINUX_SWIOTLB_H +#include #include #include #include @@ -101,9 +102,9 @@ struct io_tlb_mem { }; extern struct io_tlb_mem *io_tlb_default_mem; -static inline bool is_swiotlb_buffer(phys_addr_t paddr) +static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) { - struct io_tlb_mem *mem = io_tlb_default_mem; + struct io_tlb_mem *mem = dev->dma_io_tlb_mem; return mem && paddr >= mem->start && paddr < mem->end; } @@ -115,7 +116,7 @@ bool is_swiotlb_active(void); void __init swiotlb_adjust_size(unsigned long size); #else #define swiotlb_force SWIOTLB_NO_FORCE -static inline bool is_swiotlb_buffer(phys_addr_t paddr) +static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) { return false; } diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index f737e3347059..84c9feb5474a 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -343,7 +343,7 @@ void dma_direct_sync_sg_for_device(struct device *dev, for_each_sg(sgl, sg, nents, i) { phys_addr_t paddr = dma_to_phys(dev, sg_dma_address(sg)); - if (unlikely(is_swiotlb_buffer(paddr))) + if (unlikely(is_swiotlb_buffer(dev, paddr))) swiotlb_sync_single_for_device(dev, paddr, sg->length, dir); @@ -369,7 +369,7 @@ void dma_direct_sync_sg_for_cpu(struct device *dev, if (!dev_is_dma_coherent(dev)) arch_sync_dma_for_cpu(paddr, sg->length, dir); - if (unlikely(is_swiotlb_buffer(paddr))) + if (unlikely(is_swiotlb_buffer(dev, paddr))) swiotlb_sync_single_for_cpu(dev, paddr, sg->length, dir); @@ -504,7 +504,7 @@ size_t dma_direct_max_mapping_size(struct device *dev) bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr) { return !dev_is_dma_coherent(dev) || - is_swiotlb_buffer(dma_to_phys(dev, dma_addr)); + is_swiotlb_buffer(dev, dma_to_phys(dev, dma_addr)); } /** diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h index 50afc05b6f1d..13e9e7158d94 100644 --- a/kernel/dma/direct.h +++ b/kernel/dma/direct.h @@ -56,7 +56,7 @@ static inline void dma_direct_sync_single_for_device(struct device *dev, { phys_addr_t paddr = dma_to_phys(dev, addr); - if (unlikely(is_swiotlb_buffer(paddr))) + if (unlikely(is_swiotlb_buffer(dev, paddr))) swiotlb_sync_single_for_device(dev, paddr, size, dir); if (!dev_is_dma_coherent(dev)) @@ -73,7 +73,7 @@ static inline void dma_direct_sync_single_for_cpu(struct device *dev, arch_sync_dma_for_cpu_all(); } - if (unlikely(is_swiotlb_buffer(paddr))) + if (unlikely(is_swiotlb_buffer(dev, paddr))) swiotlb_sync_single_for_cpu(dev, paddr, size, dir); if (dir == DMA_FROM_DEVICE) @@ -113,7 +113,7 @@ static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) dma_direct_sync_single_for_cpu(dev, addr, size, dir); - if (unlikely(is_swiotlb_buffer(phys))) + if (unlikely(is_swiotlb_buffer(dev, phys))) swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs); } #endif /* _KERNEL_DMA_DIRECT_H */ -- cgit v1.2.3-59-g8ed1b From 6f2beb268a5d35504a636c4a3b7aaa76ec32d96c Mon Sep 17 00:00:00 2001 From: Claire Chang Date: Sat, 19 Jun 2021 11:40:36 +0800 Subject: swiotlb: Update is_swiotlb_active to add a struct device argument Update is_swiotlb_active to add a struct device argument. This will be useful later to allow for different pools. Signed-off-by: Claire Chang Reviewed-by: Christoph Hellwig Tested-by: Stefano Stabellini Tested-by: Will Deacon Acked-by: Stefano Stabellini Signed-off-by: Konrad Rzeszutek Wilk --- 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(-) (limited to 'include/linux') 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 d1f3d95881cd..dd1c30a83058 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -112,7 +112,7 @@ static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) 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 @@ -132,7 +132,7 @@ 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 33d413beddd4..d8677d6637dd 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -662,9 +662,9 @@ 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); -- cgit v1.2.3-59-g8ed1b From 903cd0f315fe426c6a64c54ed389de0becb663dc Mon Sep 17 00:00:00 2001 From: Claire Chang Date: Thu, 24 Jun 2021 23:55:20 +0800 Subject: swiotlb: Use is_swiotlb_force_bounce for swiotlb data bouncing Propagate the swiotlb_force into io_tlb_default_mem->force_bounce and use it to determine whether to bounce the data or not. This will be useful later to allow for different pools. Signed-off-by: Claire Chang Reviewed-by: Christoph Hellwig Tested-by: Stefano Stabellini Tested-by: Will Deacon Acked-by: Stefano Stabellini Signed-off-by: Konrad Rzeszutek Wilk [v2: Includes Will's fix] --- drivers/xen/swiotlb-xen.c | 2 +- include/linux/swiotlb.h | 13 +++++++++++++ kernel/dma/direct.c | 2 +- kernel/dma/direct.h | 2 +- kernel/dma/swiotlb.c | 4 ++++ 5 files changed, 20 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 0c4fb34f11ab..785ec7e8be01 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -374,7 +374,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, if (dma_capable(dev, dev_addr, size, true) && !range_straddles_page_boundary(phys, size) && !xen_arch_need_swiotlb(dev, phys, dev_addr) && - swiotlb_force != SWIOTLB_FORCE) + !is_swiotlb_force_bounce(dev)) goto done; /* diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index dd1c30a83058..da348671b0d5 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -84,6 +84,7 @@ extern enum swiotlb_force swiotlb_force; * unmap calls. * @debugfs: The dentry to debugfs. * @late_alloc: %true if allocated using the page allocator + * @force_bounce: %true if swiotlb bouncing is forced */ struct io_tlb_mem { phys_addr_t start; @@ -94,6 +95,7 @@ struct io_tlb_mem { spinlock_t lock; struct dentry *debugfs; bool late_alloc; + bool force_bounce; struct io_tlb_slot { phys_addr_t orig_addr; size_t alloc_size; @@ -109,6 +111,13 @@ static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) return mem && paddr >= mem->start && paddr < mem->end; } +static inline bool is_swiotlb_force_bounce(struct device *dev) +{ + struct io_tlb_mem *mem = dev->dma_io_tlb_mem; + + return mem && mem->force_bounce; +} + void __init swiotlb_exit(void); unsigned int swiotlb_max_segment(void); size_t swiotlb_max_mapping_size(struct device *dev); @@ -120,6 +129,10 @@ static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) { return false; } +static inline bool is_swiotlb_force_bounce(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..a92465b4eb12 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -496,7 +496,7 @@ 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) || is_swiotlb_force_bounce(dev))) return swiotlb_max_mapping_size(dev); return SIZE_MAX; } diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h index 13e9e7158d94..4632b0f4f72e 100644 --- a/kernel/dma/direct.h +++ b/kernel/dma/direct.h @@ -87,7 +87,7 @@ 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 (is_swiotlb_force_bounce(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 d8677d6637dd..04319dd22d28 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -179,6 +179,10 @@ static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start, mem->end = mem->start + bytes; mem->index = 0; mem->late_alloc = late_alloc; + + if (swiotlb_force == SWIOTLB_FORCE) + mem->force_bounce = true; + spin_lock_init(&mem->lock); for (i = 0; i < mem->nslabs; i++) { mem->slots[i].list = IO_TLB_SEGSIZE - io_tlb_offset(i); -- cgit v1.2.3-59-g8ed1b From f4111e39a52aa5d5136d890bbd1aa87c1c8fe3bc Mon Sep 17 00:00:00 2001 From: Claire Chang Date: Sat, 19 Jun 2021 11:40:40 +0800 Subject: swiotlb: Add restricted DMA alloc/free support Add the functions, swiotlb_{alloc,free} and is_swiotlb_for_alloc to support the memory allocation from restricted DMA pool. The restricted DMA pool is preferred if available. 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. Signed-off-by: Claire Chang Reviewed-by: Christoph Hellwig Tested-by: Stefano Stabellini Tested-by: Will Deacon Acked-by: Stefano Stabellini Signed-off-by: Konrad Rzeszutek Wilk --- include/linux/swiotlb.h | 26 ++++++++++++++++++++++++++ kernel/dma/direct.c | 49 +++++++++++++++++++++++++++++++++++++------------ kernel/dma/swiotlb.c | 38 ++++++++++++++++++++++++++++++++++++-- 3 files changed, 99 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index da348671b0d5..3b9454d1e498 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -85,6 +85,7 @@ extern enum swiotlb_force swiotlb_force; * @debugfs: The dentry to debugfs. * @late_alloc: %true if allocated using the page allocator * @force_bounce: %true if swiotlb bouncing is forced + * @for_alloc: %true if the pool is used for memory allocation */ struct io_tlb_mem { phys_addr_t start; @@ -96,6 +97,7 @@ struct io_tlb_mem { struct dentry *debugfs; bool late_alloc; bool force_bounce; + bool for_alloc; struct io_tlb_slot { phys_addr_t orig_addr; size_t alloc_size; @@ -158,4 +160,28 @@ 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); + +static inline bool is_swiotlb_for_alloc(struct device *dev) +{ + return dev->dma_io_tlb_mem->for_alloc; +} +#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; +} +static inline bool is_swiotlb_for_alloc(struct device *dev) +{ + return false; +} +#endif /* CONFIG_DMA_RESTRICTED_POOL */ + #endif /* __LINUX_SWIOTLB_H */ diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index a92465b4eb12..2de33e5d302b 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -75,6 +75,15 @@ static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size) min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit); } +static void __dma_direct_free_pages(struct device *dev, struct page *page, + size_t size) +{ + if (IS_ENABLED(CONFIG_DMA_RESTRICTED_POOL) && + swiotlb_free(dev, page, size)) + return; + dma_free_contiguous(dev, page, size); +} + static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, gfp_t gfp) { @@ -86,6 +95,16 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask, &phys_limit); + if (IS_ENABLED(CONFIG_DMA_RESTRICTED_POOL) && + is_swiotlb_for_alloc(dev)) { + page = swiotlb_alloc(dev, size); + if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) { + __dma_direct_free_pages(dev, page, size); + return NULL; + } + return page; + } + page = dma_alloc_contiguous(dev, size, gfp); if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) { dma_free_contiguous(dev, page, size); @@ -142,7 +161,7 @@ void *dma_direct_alloc(struct device *dev, size_t size, gfp |= __GFP_NOWARN; if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) && - !force_dma_unencrypted(dev)) { + !force_dma_unencrypted(dev) && !is_swiotlb_for_alloc(dev)) { page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO); if (!page) return NULL; @@ -155,18 +174,23 @@ void *dma_direct_alloc(struct device *dev, size_t size, } if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) && - !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && - !dev_is_dma_coherent(dev)) + !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && !dev_is_dma_coherent(dev) && + !is_swiotlb_for_alloc(dev)) return arch_dma_alloc(dev, size, dma_handle, gfp, attrs); /* * Remapping or decrypting memory may block. If either is required and * we can't block, allocate the memory from the atomic pools. + * If restricted DMA (i.e., is_swiotlb_for_alloc) is required, one must + * set up another device coherent pool by shared-dma-pool and use + * dma_alloc_from_dev_coherent instead. */ if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) && !gfpflags_allow_blocking(gfp) && (force_dma_unencrypted(dev) || - (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && !dev_is_dma_coherent(dev)))) + (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && + !dev_is_dma_coherent(dev))) && + !is_swiotlb_for_alloc(dev)) return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp); /* we always manually zero the memory once we are done */ @@ -237,7 +261,7 @@ out_encrypt_pages: return NULL; } out_free_pages: - dma_free_contiguous(dev, page, size); + __dma_direct_free_pages(dev, page, size); return NULL; } @@ -247,15 +271,15 @@ void dma_direct_free(struct device *dev, size_t size, unsigned int page_order = get_order(size); if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) && - !force_dma_unencrypted(dev)) { + !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) && - !dev_is_dma_coherent(dev)) { + !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && !dev_is_dma_coherent(dev) && + !is_swiotlb_for_alloc(dev)) { arch_dma_free(dev, size, cpu_addr, dma_addr, attrs); return; } @@ -273,7 +297,7 @@ void dma_direct_free(struct device *dev, size_t size, else if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_CLEAR_UNCACHED)) arch_dma_clear_uncached(cpu_addr, size); - dma_free_contiguous(dev, dma_direct_to_page(dev, dma_addr), size); + __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, @@ -283,7 +307,8 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size, void *ret; if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) && - force_dma_unencrypted(dev) && !gfpflags_allow_blocking(gfp)) + force_dma_unencrypted(dev) && !gfpflags_allow_blocking(gfp) && + !is_swiotlb_for_alloc(dev)) return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp); page = __dma_direct_alloc_pages(dev, size, gfp); @@ -310,7 +335,7 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size, *dma_handle = phys_to_dma_direct(dev, page_to_phys(page)); return page; out_free_pages: - dma_free_contiguous(dev, page, size); + __dma_direct_free_pages(dev, page, size); return NULL; } @@ -329,7 +354,7 @@ void dma_direct_free_pages(struct device *dev, size_t size, if (force_dma_unencrypted(dev)) set_memory_encrypted((unsigned long)vaddr, 1 << page_order); - dma_free_contiguous(dev, page, size); + __dma_direct_free_pages(dev, page, size); } #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 23b6df3a6ab7..44fc3d10f017 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -462,8 +462,9 @@ static int swiotlb_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; } @@ -702,3 +703,36 @@ static int __init swiotlb_create_default_debugfs(void) 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 = swiotlb_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; + + swiotlb_release_slots(dev, tlb_addr); + + return true; +} + +#endif /* CONFIG_DMA_RESTRICTED_POOL */ -- cgit v1.2.3-59-g8ed1b From 0b84e4f8b793eb4045fd64f6f514165a7974cd16 Mon Sep 17 00:00:00 2001 From: Claire Chang Date: Sat, 19 Jun 2021 11:40:41 +0800 Subject: swiotlb: Add restricted DMA pool initialization Add the initialization function to create restricted DMA pools from matching reserved-memory nodes. 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. Signed-off-by: Claire Chang Reviewed-by: Christoph Hellwig Tested-by: Stefano Stabellini Tested-by: Will Deacon Signed-off-by: Konrad Rzeszutek Wilk --- include/linux/swiotlb.h | 3 +- kernel/dma/Kconfig | 14 +++++++++ kernel/dma/swiotlb.c | 76 +++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 92 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 3b9454d1e498..39284ff2a6cd 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -73,7 +73,8 @@ 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 + + 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 diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 44fc3d10f017..0ffbaae9fba2 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -39,6 +39,13 @@ #ifdef CONFIG_DEBUG_FS #include #endif +#ifdef CONFIG_DMA_RESTRICTED_POOL +#include +#include +#include +#include +#include +#endif #include #include @@ -735,4 +742,73 @@ bool swiotlb_free(struct device *dev, struct page *page, size_t size) 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; + + /* + * 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; + + set_memory_decrypted((unsigned long)phys_to_virt(rmem->base), + rmem->size >> PAGE_SHIFT); + swiotlb_init_io_tlb_mem(mem, rmem->base, nslabs, false); + mem->force_bounce = true; + mem->for_alloc = 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 */ -- cgit v1.2.3-59-g8ed1b From 463e862ac63ef27fca423782536f6465abc3f180 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 20 Jul 2021 14:38:24 +0100 Subject: swiotlb: Convert io_default_tlb_mem to static allocation Since commit 69031f500865 ("swiotlb: Set dev->dma_io_tlb_mem to the swiotlb pool used"), 'struct device' may hold a copy of the global 'io_default_tlb_mem' pointer if the device is using swiotlb for DMA. A subsequent call to swiotlb_exit() will therefore leave dangling pointers behind in these device structures, resulting in KASAN splats such as: | BUG: KASAN: use-after-free in __iommu_dma_unmap_swiotlb+0x64/0xb0 | Read of size 8 at addr ffff8881d7830000 by task swapper/0/0 | | CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.12.0-rc3-debug #1 | Hardware name: HP HP Desktop M01-F1xxx/87D6, BIOS F.12 12/17/2020 | Call Trace: | | dump_stack+0x9c/0xcf | print_address_description.constprop.0+0x18/0x130 | kasan_report.cold+0x7f/0x111 | __iommu_dma_unmap_swiotlb+0x64/0xb0 | nvme_pci_complete_rq+0x73/0x130 | blk_complete_reqs+0x6f/0x80 | __do_softirq+0xfc/0x3be Convert 'io_default_tlb_mem' to a static structure, so that the per-device pointers remain valid after swiotlb_exit() has been invoked. All users are updated to reference the static structure directly, using the 'nslabs' field to determine whether swiotlb has been initialised. The 'slots' array is still allocated dynamically and referenced via a pointer rather than a flexible array member. Cc: Claire Chang Cc: Christoph Hellwig Cc: Robin Murphy Cc: Konrad Rzeszutek Wilk Fixes: 69031f500865 ("swiotlb: Set dev->dma_io_tlb_mem to the swiotlb pool used") Reported-by: Nathan Chancellor Tested-by: Nathan Chancellor Tested-by: Claire Chang Reviewed-by: Christoph Hellwig Signed-off-by: Will Deacon Signed-off-by: Konrad Rzeszutek Wilk --- drivers/base/core.c | 2 +- drivers/xen/swiotlb-xen.c | 4 +-- include/linux/swiotlb.h | 4 +-- kernel/dma/swiotlb.c | 66 ++++++++++++++++++++++++++--------------------- 4 files changed, 41 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/core.c b/drivers/base/core.c index ea5b85354526..b49824001cfa 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2848,7 +2848,7 @@ void device_initialize(struct device *dev) dev->dma_coherent = dma_default_coherent; #endif #ifdef CONFIG_SWIOTLB - dev->dma_io_tlb_mem = io_tlb_default_mem; + dev->dma_io_tlb_mem = &io_tlb_default_mem; #endif } EXPORT_SYMBOL_GPL(device_initialize); diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 785ec7e8be01..f06d9b4f1e0f 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -164,7 +164,7 @@ int __ref xen_swiotlb_init(void) int rc = -ENOMEM; char *start; - if (io_tlb_default_mem != NULL) { + if (io_tlb_default_mem.nslabs) { pr_warn("swiotlb buffer already initialized\n"); return -EEXIST; } @@ -547,7 +547,7 @@ xen_swiotlb_sync_sg_for_device(struct device *dev, struct scatterlist *sgl, static int xen_swiotlb_dma_supported(struct device *hwdev, u64 mask) { - return xen_phys_to_dma(hwdev, io_tlb_default_mem->end - 1) <= mask; + return xen_phys_to_dma(hwdev, io_tlb_default_mem.end - 1) <= mask; } const struct dma_map_ops xen_swiotlb_dma_ops = { diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 39284ff2a6cd..b0cb2a9973f4 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -103,9 +103,9 @@ struct io_tlb_mem { phys_addr_t orig_addr; size_t alloc_size; unsigned int list; - } slots[]; + } *slots; }; -extern struct io_tlb_mem *io_tlb_default_mem; +extern struct io_tlb_mem io_tlb_default_mem; static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) { diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index f1a9ae7fad8f..7948f274f9bb 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -70,7 +70,7 @@ enum swiotlb_force swiotlb_force; -struct io_tlb_mem *io_tlb_default_mem; +struct io_tlb_mem io_tlb_default_mem; /* * Max segment that we can provide which (if pages are contingous) will @@ -101,7 +101,7 @@ early_param("swiotlb", setup_io_tlb_npages); unsigned int swiotlb_max_segment(void) { - return io_tlb_default_mem ? max_segment : 0; + return io_tlb_default_mem.nslabs ? max_segment : 0; } EXPORT_SYMBOL_GPL(swiotlb_max_segment); @@ -134,9 +134,9 @@ void __init swiotlb_adjust_size(unsigned long size) void swiotlb_print_info(void) { - struct io_tlb_mem *mem = io_tlb_default_mem; + struct io_tlb_mem *mem = &io_tlb_default_mem; - if (!mem) { + if (!mem->nslabs) { pr_warn("No low mem\n"); return; } @@ -163,11 +163,11 @@ static inline unsigned long nr_slots(u64 val) */ void __init swiotlb_update_mem_attributes(void) { - struct io_tlb_mem *mem = io_tlb_default_mem; + struct io_tlb_mem *mem = &io_tlb_default_mem; void *vaddr; unsigned long bytes; - if (!mem || mem->late_alloc) + if (!mem->nslabs || mem->late_alloc) return; vaddr = phys_to_virt(mem->start); bytes = PAGE_ALIGN(mem->nslabs << IO_TLB_SHIFT); @@ -201,25 +201,24 @@ static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start, int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) { - struct io_tlb_mem *mem; + struct io_tlb_mem *mem = &io_tlb_default_mem; size_t alloc_size; if (swiotlb_force == SWIOTLB_NO_FORCE) return 0; /* protect against double initialization */ - if (WARN_ON_ONCE(io_tlb_default_mem)) + if (WARN_ON_ONCE(mem->nslabs)) return -ENOMEM; - alloc_size = PAGE_ALIGN(struct_size(mem, slots, nslabs)); - mem = memblock_alloc(alloc_size, PAGE_SIZE); - if (!mem) + alloc_size = PAGE_ALIGN(array_size(sizeof(*mem->slots), nslabs)); + mem->slots = memblock_alloc(alloc_size, PAGE_SIZE); + if (!mem->slots) panic("%s: Failed to allocate %zu bytes align=0x%lx\n", __func__, alloc_size, PAGE_SIZE); swiotlb_init_io_tlb_mem(mem, __pa(tlb), nslabs, false); - io_tlb_default_mem = mem; if (verbose) swiotlb_print_info(); swiotlb_set_max_segment(mem->nslabs << IO_TLB_SHIFT); @@ -304,26 +303,24 @@ swiotlb_late_init_with_default_size(size_t default_size) int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) { - struct io_tlb_mem *mem; + struct io_tlb_mem *mem = &io_tlb_default_mem; unsigned long bytes = nslabs << IO_TLB_SHIFT; if (swiotlb_force == SWIOTLB_NO_FORCE) return 0; /* protect against double initialization */ - if (WARN_ON_ONCE(io_tlb_default_mem)) + if (WARN_ON_ONCE(mem->nslabs)) return -ENOMEM; - mem = (void *)__get_free_pages(GFP_KERNEL, - get_order(struct_size(mem, slots, nslabs))); - if (!mem) + mem->slots = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, + get_order(array_size(sizeof(*mem->slots), nslabs))); + if (!mem->slots) return -ENOMEM; - memset(mem, 0, sizeof(*mem)); set_memory_decrypted((unsigned long)tlb, bytes >> PAGE_SHIFT); swiotlb_init_io_tlb_mem(mem, virt_to_phys(tlb), nslabs, true); - io_tlb_default_mem = mem; swiotlb_print_info(); swiotlb_set_max_segment(mem->nslabs << IO_TLB_SHIFT); return 0; @@ -331,18 +328,18 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) void __init swiotlb_exit(void) { - struct io_tlb_mem *mem = io_tlb_default_mem; size_t size; + struct io_tlb_mem *mem = &io_tlb_default_mem; - if (!mem) + if (!mem->nslabs) return; - size = struct_size(mem, slots, mem->nslabs); + size = array_size(sizeof(*mem->slots), mem->nslabs); if (mem->late_alloc) - free_pages((unsigned long)mem, get_order(size)); + free_pages((unsigned long)mem->slots, get_order(size)); else - memblock_free_late(__pa(mem), PAGE_ALIGN(size)); - io_tlb_default_mem = NULL; + memblock_free_late(__pa(mem->slots), PAGE_ALIGN(size)); + memset(mem, 0, sizeof(*mem)); } /* @@ -696,7 +693,9 @@ size_t swiotlb_max_mapping_size(struct device *dev) bool is_swiotlb_active(struct device *dev) { - return dev->dma_io_tlb_mem != NULL; + struct io_tlb_mem *mem = dev->dma_io_tlb_mem; + + return mem && mem->nslabs; } EXPORT_SYMBOL_GPL(is_swiotlb_active); @@ -711,10 +710,10 @@ static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem) static int __init swiotlb_create_default_debugfs(void) { - struct io_tlb_mem *mem = io_tlb_default_mem; + struct io_tlb_mem *mem = &io_tlb_default_mem; debugfs_dir = debugfs_create_dir("swiotlb", NULL); - if (mem) { + if (mem->nslabs) { mem->debugfs = debugfs_dir; swiotlb_create_debugfs_files(mem); } @@ -783,10 +782,17 @@ static int rmem_swiotlb_device_init(struct reserved_mem *rmem, * to it. */ if (!mem) { - mem = kzalloc(struct_size(mem, slots, nslabs), GFP_KERNEL); + mem = kzalloc(sizeof(*mem), GFP_KERNEL); if (!mem) return -ENOMEM; + mem->slots = kzalloc(array_size(sizeof(*mem->slots), nslabs), + GFP_KERNEL); + if (!mem->slots) { + kfree(mem); + return -ENOMEM; + } + set_memory_decrypted((unsigned long)phys_to_virt(rmem->base), rmem->size >> PAGE_SHIFT); swiotlb_init_io_tlb_mem(mem, rmem->base, nslabs, false); @@ -806,7 +812,7 @@ static int rmem_swiotlb_device_init(struct reserved_mem *rmem, static void rmem_swiotlb_device_release(struct reserved_mem *rmem, struct device *dev) { - dev->dma_io_tlb_mem = io_tlb_default_mem; + dev->dma_io_tlb_mem = &io_tlb_default_mem; } static const struct reserved_mem_ops rmem_swiotlb_ops = { -- cgit v1.2.3-59-g8ed1b