Fixes for dma-iommu swiotlb bounce buffers
Subsystems (5)
v5 cover Fixes for dma-iommu swiotlb bounce buffers
From: David Stevens <[email protected]>
This patch set includes various fixes for dma-iommu's swiotlb bounce buffers for untrusted devices. There are four fixes for correctness issues, one for a performance issue, and one for general cleanup.
The min_align_mask issue was found when running fio on an untrusted nvme device with bs=512. The other issues were found via code inspection, so I don't have any specific use cases where things were not working, nor any concrete performance numbers.
v4 -> v5:
- Fix xen build error
- Move _swiotlb refactor into its own patch
v3 -> v4:
- Fold _swiotlb functions into _page functions
- Add patch to align swiotlb buffer to iovad granule
- Combine if checks in iommu_dma_sync_sg_* functions
v2 -> v3:
- Add new patch to address min_align_mask bug
- Set SKIP_CPU_SYNC flag after syncing in map/unmap
- Properly call arch_sync_dma_for_cpu in iommu_dma_sync_sg_for_cpu
v1 -> v2:
- Split fixes into dedicated patches
- Less invasive changes to fix arch_sync when mapping
- Leave dev_is_untrusted check for strict iommu
David Stevens (7):
dma-iommu: fix sync_sg with swiotlb
dma-iommu: fix arch_sync_dma for map
dma-iommu: skip extra sync during unmap w/swiotlb
dma-iommu: fold _swiotlb helpers into callers
dma-iommu: Check CONFIG_SWIOTLB more broadly
swiotlb: support aligned swiotlb buffers
dma-iommu: account for min_align_mask
drivers/iommu/dma-iommu.c | 193 +++++++++++++++++--------------------- drivers/xen/swiotlb-xen.c | 2 +- include/linux/swiotlb.h | 3 +- kernel/dma/swiotlb.c | 11 ++- 4 files changed, 98 insertions(+), 111 deletions(-)
Signature · 1 line
2.33.0.rc1.237.g0d66db33f3-goog
PATCH v5 1/7 dma-iommu: fix sync_sg with swiotlb
From: David Stevens <[email protected]>
The is_swiotlb_buffer function takes the physical address of the swiotlb buffer, not the physical address of the original buffer. The sglist contains the physical addresses of the original buffer, so for the sync_sg functions to work properly when a bounce buffer might have been used, we need to use iommu_iova_to_phys to look up the physical address. This is what sync_single does, so call that function on each sglist segment.
The previous code mostly worked because swiotlb does the transfer on map and unmap. However, any callers which use DMA_ATTR_SKIP_CPU_SYNC with sglists or which call sync_sg would not have had anything copied to the bounce buffer.
--- drivers/iommu/dma-iommu.c | 33 +++++++++++++-------------------- 1 file changed, 13 insertions(+), 20 deletions(-)
drivers/iommu/dma-iommu.c +13 -20
@@ -810,17 +810,13 @@ static void iommu_dma_sync_sg_for_cpu(struct device *dev,struct scatterlist *sg;int i; -if (dev_is_dma_coherent (dev) && !dev_is_untrusted (dev)) -return ; - -for_each_sg (sgl, sg, nelems, i) { -if (!dev_is_dma_coherent (dev)) +if (dev_is_untrusted (dev)) +for_each_sg (sgl, sg, nelems, i) +iommu_dma_sync_single_for_cpu (dev,sg_dma_address (sg), + sg->length, dir); +else if (!dev_is_dma_coherent (dev)) +for_each_sg (sgl, sg, nelems, i)arch_sync_dma_for_cpu (sg_phys (sg), sg->length, dir); - -if (is_swiotlb_buffer (sg_phys (sg))) -swiotlb_sync_single_for_cpu (dev,sg_phys (sg), - sg->length, dir); - } } static void iommu_dma_sync_sg_for_device(struct device *dev,
@@ -830,17 +826,14 @@ static void iommu_dma_sync_sg_for_device(struct device *dev,struct scatterlist *sg;int i; -if (dev_is_dma_coherent (dev) && !dev_is_untrusted (dev)) -return ; - -for_each_sg (sgl, sg, nelems, i) { -if (is_swiotlb_buffer (sg_phys (sg))) -swiotlb_sync_single_for_device (dev,sg_phys (sg), - sg->length, dir); - -if (!dev_is_dma_coherent (dev)) +if (dev_is_untrusted (dev)) +for_each_sg (sgl, sg, nelems, i) +iommu_dma_sync_single_for_device (dev, +sg_dma_address (sg), + sg->length, dir); +else if (!dev_is_dma_coherent (dev)) +for_each_sg (sgl, sg, nelems, i)arch_sync_dma_for_device (sg_phys (sg), sg->length, dir); - } } static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
Signature · 1 line
2.33.0.rc1.237.g0d66db33f3-goog
PATCH v5 2/7 dma-iommu: fix arch_sync_dma for map
In reply to David StevensFrom: David Stevens <[email protected]>
When calling arch_sync_dma, we need to pass it the memory that's actually being used for dma. When using swiotlb bounce buffers, this is the bounce buffer. Move arch_sync_dma into the __iommu_dma_map_swiotlb helper, so it can use the bounce buffer address if necessary.
Now that iommu_dma_map_sg delegates to a function which takes care of architectural syncing in the untrusted device case, the call to iommu_dma_sync_sg_for_device can be moved so it only occurs for trusted devices. Doing the sync for untrusted devices before mapping never really worked, since it needs to be able to target swiotlb buffers.
This also moves the architectural sync to before the call to __iommu_dma_map, to guarantee that untrusted devices can't see stale data they shouldn't see.
--- drivers/iommu/dma-iommu.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-)
drivers/iommu/dma-iommu.c +7 -9
@@ -576,6 +576,9 @@ static dma_addr_t __iommu_dma_map_swiotlb(struct device *dev, phys_addr_t phys,memset (padding_start,0 , padding_size); } +if (!coherent && !(attrs &DMA_ATTR_SKIP_CPU_SYNC )) +arch_sync_dma_for_device (phys, org_size, dir); + iova =__iommu_dma_map (dev, phys, aligned_size, prot, dma_mask);if (iova ==DMA_MAPPING_ERROR &&is_swiotlb_buffer (phys))swiotlb_tbl_unmap_single (dev, phys, org_size, dir, attrs);
@@ -842,14 +845,9 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page, {phys_addr_t phys =page_to_phys (page) + offset;bool coherent =dev_is_dma_coherent (dev); -dma_addr_t dma_handle; - dma_handle =__iommu_dma_map_swiotlb (dev, phys, size,dma_get_mask (dev), +return __iommu_dma_map_swiotlb (dev, phys, size,dma_get_mask (dev), coherent, dir, attrs); -if (!coherent && !(attrs &DMA_ATTR_SKIP_CPU_SYNC ) && - dma_handle !=DMA_MAPPING_ERROR ) -arch_sync_dma_for_device (phys, size, dir); -return dma_handle; } static void iommu_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
@@ -992,12 +990,12 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, iommu_deferred_attach(dev, domain))return 0 ; -if (!(attrs &DMA_ATTR_SKIP_CPU_SYNC )) -iommu_dma_sync_sg_for_device (dev, sg, nents, dir); -if (dev_is_untrusted (dev))return iommu_dma_map_sg_swiotlb (dev, sg, nents, dir, attrs); +if (!(attrs &DMA_ATTR_SKIP_CPU_SYNC )) +iommu_dma_sync_sg_for_device (dev, sg, nents, dir); +/* * Work out how much IOVA space we need, and align the segments to * IOVA granules for the IOMMU driver to handle. With some clever
Signature · 1 line
2.33.0.rc1.237.g0d66db33f3-goog
Re: [PATCH v5 2/7] dma-iommu: fix arch_sync_dma for map
Looks good,
PATCH v5 3/7 dma-iommu: skip extra sync during unmap w/swiotlb
In reply to David StevensFrom: David Stevens <[email protected]>
Calling the iommu_dma_sync_*_for_cpu functions during unmap can cause two copies out of the swiotlb buffer. Do the arch sync directly in __iommu_dma_unmap_swiotlb instead to avoid this. This makes the call to iommu_dma_sync_sg_for_cpu for untrusted devices in iommu_dma_unmap_sg no longer necessary, so move that invocation later in the function.
--- drivers/iommu/dma-iommu.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-)
drivers/iommu/dma-iommu.c +6 -5
@@ -504,6 +504,9 @@ static void __iommu_dma_unmap_swiotlb(struct device *dev, dma_addr_t dma_addr,if (WARN_ON (!phys))return ; +if (!(attrs &DMA_ATTR_SKIP_CPU_SYNC ) && !dev_is_dma_coherent (dev)) +arch_sync_dma_for_cpu (phys, size, dir); +__iommu_dma_unmap (dev, dma_addr, size);if (unlikely (is_swiotlb_buffer (phys)))
@@ -853,8 +856,6 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,static void iommu_dma_unmap_page (struct device *dev,dma_addr_t dma_handle,size_t size,enum dma_data_direction dir,unsigned long attrs) { -if (!(attrs &DMA_ATTR_SKIP_CPU_SYNC )) -iommu_dma_sync_single_for_cpu (dev, dma_handle, size, dir);__iommu_dma_unmap_swiotlb (dev, dma_handle, size, dir, attrs); }
@@ -1062,14 +1063,14 @@ static void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg,struct scatterlist *tmp;int i; -if (!(attrs &DMA_ATTR_SKIP_CPU_SYNC )) -iommu_dma_sync_sg_for_cpu (dev, sg, nents, dir); -if (dev_is_untrusted (dev)) {iommu_dma_unmap_sg_swiotlb (dev, sg, nents, dir, attrs);return ; } +if (!(attrs &DMA_ATTR_SKIP_CPU_SYNC )) +iommu_dma_sync_sg_for_cpu (dev, sg, nents, dir); +/* * The scatterlist segments are mapped into a single * contiguous IOVA allocation, so this is incredibly easy.
Signature · 1 line
2.33.0.rc1.237.g0d66db33f3-goog
Re: [PATCH v5 3/7] dma-iommu: skip extra sync during unmap w/swiotlb
Looks good,
PATCH v5 4/7 dma-iommu: fold _swiotlb helpers into callers
In reply to David StevensFrom: David Stevens <[email protected]>
Fold the _swiotlb helper functions into the respective _page functions, since recent fixes have moved all logic from the _page functions to the _swiotlb functions.
--- drivers/iommu/dma-iommu.c | 136 +++++++++++++++++--------------------- 1 file changed, 60 insertions(+), 76 deletions(-)
drivers/iommu/dma-iommu.c +60 -76
@@ -493,26 +493,6 @@ static void __iommu_dma_unmap(struct device *dev, dma_addr_t dma_addr,iommu_dma_free_iova (cookie, dma_addr, size, iotlb_gather.freelist); } -static void __iommu_dma_unmap_swiotlb (struct device *dev,dma_addr_t dma_addr, -size_t size,enum dma_data_direction dir, -unsigned long attrs) -{ -struct iommu_domain *domain =iommu_get_dma_domain (dev); -phys_addr_t phys; - - phys =iommu_iova_to_phys (domain, dma_addr); -if (WARN_ON (!phys)) -return ; - -if (!(attrs &DMA_ATTR_SKIP_CPU_SYNC ) && !dev_is_dma_coherent (dev)) -arch_sync_dma_for_cpu (phys, size, dir); - -__iommu_dma_unmap (dev, dma_addr, size); - -if (unlikely (is_swiotlb_buffer (phys))) -swiotlb_tbl_unmap_single (dev, phys, size, dir, attrs); -} -static dma_addr_t __iommu_dma_map (struct device *dev,phys_addr_t phys,size_t size,int prot,u64 dma_mask) {
@@ -539,55 +519,6 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,return iova + iova_off; } -static dma_addr_t __iommu_dma_map_swiotlb (struct device *dev,phys_addr_t phys, -size_t org_size,dma_addr_t dma_mask,bool coherent, -enum dma_data_direction dir,unsigned long attrs) -{ -int prot =dma_info_to_prot (dir, coherent, attrs); -struct iommu_domain *domain =iommu_get_dma_domain (dev); -struct iommu_dma_cookie *cookie = domain->iova_cookie; -struct iova_domain *iovad = &cookie->iovad; -size_t aligned_size = org_size; -void *padding_start; -size_t padding_size; -dma_addr_t iova; - -/* -* If both the physical buffer start address and size are -* page aligned, we don't need to use a bounce page. -*/ -if (IS_ENABLED (CONFIG_SWIOTLB ) &&dev_is_untrusted (dev) && -iova_offset (iovad, phys | org_size)) { - aligned_size =iova_align (iovad, org_size); - phys =swiotlb_tbl_map_single (dev, phys, org_size, - aligned_size, dir, attrs); - -if (phys ==DMA_MAPPING_ERROR ) -return DMA_MAPPING_ERROR ; - -/* Cleanup the padding area. */ - padding_start =phys_to_virt (phys); - padding_size = aligned_size; - -if (!(attrs &DMA_ATTR_SKIP_CPU_SYNC ) && - (dir ==DMA_TO_DEVICE || - dir ==DMA_BIDIRECTIONAL )) { - padding_start += org_size; - padding_size -= org_size; - } - -memset (padding_start,0 , padding_size); - } - -if (!coherent && !(attrs &DMA_ATTR_SKIP_CPU_SYNC )) -arch_sync_dma_for_device (phys, org_size, dir); - - iova =__iommu_dma_map (dev, phys, aligned_size, prot, dma_mask); -if (iova ==DMA_MAPPING_ERROR &&is_swiotlb_buffer (phys)) -swiotlb_tbl_unmap_single (dev, phys, org_size, dir, attrs); -return iova; -} -static void __iommu_dma_free_pages (struct page **pages,int count) {while (count--)
@@ -848,15 +779,69 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page, {phys_addr_t phys =page_to_phys (page) + offset;bool coherent =dev_is_dma_coherent (dev); +int prot =dma_info_to_prot (dir, coherent, attrs); +struct iommu_domain *domain =iommu_get_dma_domain (dev); +struct iommu_dma_cookie *cookie = domain->iova_cookie; +struct iova_domain *iovad = &cookie->iovad; +size_t aligned_size = size; +dma_addr_t iova, dma_mask =dma_get_mask (dev); + +/* +* If both the physical buffer start address and size are +* page aligned, we don't need to use a bounce page. +*/ +if (IS_ENABLED (CONFIG_SWIOTLB ) &&dev_is_untrusted (dev) && +iova_offset (iovad, phys | size)) { +void *padding_start; +size_t padding_size; -return __iommu_dma_map_swiotlb (dev, phys, size,dma_get_mask (dev), - coherent, dir, attrs); + aligned_size =iova_align (iovad, size); + phys =swiotlb_tbl_map_single (dev, phys, size, + aligned_size, dir, attrs); + +if (phys ==DMA_MAPPING_ERROR ) +return DMA_MAPPING_ERROR ; + +/* Cleanup the padding area. */ + padding_start =phys_to_virt (phys); + padding_size = aligned_size; + +if (!(attrs &DMA_ATTR_SKIP_CPU_SYNC ) && + (dir ==DMA_TO_DEVICE || + dir ==DMA_BIDIRECTIONAL )) { + padding_start += size; + padding_size -= size; + } + +memset (padding_start,0 , padding_size); + } + +if (!coherent && !(attrs &DMA_ATTR_SKIP_CPU_SYNC )) +arch_sync_dma_for_device (phys, size, dir); + + iova =__iommu_dma_map (dev, phys, aligned_size, prot, dma_mask); +if (iova ==DMA_MAPPING_ERROR &&is_swiotlb_buffer (phys)) +swiotlb_tbl_unmap_single (dev, phys, size, dir, attrs); +return iova; }static void iommu_dma_unmap_page (struct device *dev,dma_addr_t dma_handle,size_t size,enum dma_data_direction dir,unsigned long attrs) { -__iommu_dma_unmap_swiotlb (dev, dma_handle, size, dir, attrs); +struct iommu_domain *domain =iommu_get_dma_domain (dev); +phys_addr_t phys; + + phys =iommu_iova_to_phys (domain, dma_handle); +if (WARN_ON (!phys)) +return ; + +if (!(attrs &DMA_ATTR_SKIP_CPU_SYNC ) && !dev_is_dma_coherent (dev)) +arch_sync_dma_for_cpu (phys, size, dir); + +__iommu_dma_unmap (dev, dma_handle, size); + +if (unlikely (is_swiotlb_buffer (phys))) +swiotlb_tbl_unmap_single (dev, phys, size, dir, attrs); }/*
@@ -941,7 +926,7 @@ static void iommu_dma_unmap_sg_swiotlb(struct device *dev, struct scatterlist *sint i;for_each_sg (sg, s, nents, i) -__iommu_dma_unmap_swiotlb (dev,sg_dma_address (s), +iommu_dma_unmap_page (dev,sg_dma_address (s),sg_dma_len (s), dir, attrs); }
@@ -952,9 +937,8 @@ static int iommu_dma_map_sg_swiotlb(struct device *dev, struct scatterlist *sg,int i;for_each_sg (sg, s, nents, i) { -sg_dma_address (s) =__iommu_dma_map_swiotlb (dev,sg_phys (s), - s->length,dma_get_mask (dev), -dev_is_dma_coherent (dev), dir, attrs); +sg_dma_address (s) =iommu_dma_map_page (dev,sg_page (s), + s->offset, s->length, dir, attrs);if (sg_dma_address (s) ==DMA_MAPPING_ERROR ) goto out_unmap;sg_dma_len (s) = s->length;
Signature · 1 line
2.33.0.rc1.237.g0d66db33f3-goog
Re: [PATCH v5 4/7] dma-iommu: fold _swiotlb helpers into callers
drivers/iommu/dma-iommu.c static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page, · line 811
Quoted 3 lines
drivers/iommu/dma-iommu.c +3
-0+if (!(attrs &DMA_ATTR_SKIP_CPU_SYNC ) && + (dir ==DMA_TO_DEVICE || + dir ==DMA_BIDIRECTIONAL )) {
Nit: the two dire checks easily fit onto a single line and are easier to follow that way.
Otherwise looks good:
PATCH v5 5/7 dma-iommu: Check CONFIG_SWIOTLB more broadly
In reply to David StevensFrom: David Stevens <[email protected]>
Introduce a new dev_use_swiotlb function to guard swiotlb code, instead of overloading dev_is_untrusted. This allows CONFIG_SWIOTLB to be checked more broadly, so the swiotlb related code can be removed more aggressively.
--- drivers/iommu/dma-iommu.c | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-)
drivers/iommu/dma-iommu.c +12 -7
@@ -317,6 +317,11 @@ static bool dev_is_untrusted(struct device *dev)return dev_is_pci (dev) &&to_pci_dev (dev)->untrusted; } +static bool dev_use_swiotlb (struct device *dev) +{ +return IS_ENABLED (CONFIG_SWIOTLB ) &&dev_is_untrusted (dev); +} +/** * iommu_dma_init_domain - Initialise a DMA mapping domain * @domain: IOMMU domain previously prepared by iommu_get_dma_cookie()
@@ -713,7 +718,7 @@ static void iommu_dma_sync_single_for_cpu(struct device *dev, {phys_addr_t phys; -if (dev_is_dma_coherent (dev) && !dev_is_untrusted (dev)) +if (dev_is_dma_coherent (dev) && !dev_use_swiotlb (dev))return ; phys =iommu_iova_to_phys (iommu_get_dma_domain (dev), dma_handle);
@@ -729,7 +734,7 @@ static void iommu_dma_sync_single_for_device(struct device *dev, {phys_addr_t phys; -if (dev_is_dma_coherent (dev) && !dev_is_untrusted (dev)) +if (dev_is_dma_coherent (dev) && !dev_use_swiotlb (dev))return ; phys =iommu_iova_to_phys (iommu_get_dma_domain (dev), dma_handle);
@@ -747,7 +752,7 @@ static void iommu_dma_sync_sg_for_cpu(struct device *dev,struct scatterlist *sg;int i; -if (dev_is_untrusted (dev)) +if (dev_use_swiotlb (dev))for_each_sg (sgl, sg, nelems, i)iommu_dma_sync_single_for_cpu (dev,sg_dma_address (sg), sg->length, dir);
@@ -763,7 +768,7 @@ static void iommu_dma_sync_sg_for_device(struct device *dev,struct scatterlist *sg;int i; -if (dev_is_untrusted (dev)) +if (dev_use_swiotlb (dev))for_each_sg (sgl, sg, nelems, i) iommu_dma_sync_single_for_device(dev, sg_dma_address(sg),
@@ -790,7 +795,7 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,* If both the physical buffer start address and size are * page aligned, we don't need to use a bounce page. */ -if (IS_ENABLED (CONFIG_SWIOTLB ) &&dev_is_untrusted (dev) && +if (IS_ENABLED (CONFIG_SWIOTLB ) &&dev_use_swiotlb (dev) &&iova_offset (iovad, phys | size)) {void *padding_start;size_t padding_size;
@@ -975,7 +980,7 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, iommu_deferred_attach(dev, domain))return 0 ; -if (dev_is_untrusted (dev)) +if (dev_use_swiotlb (dev))return iommu_dma_map_sg_swiotlb (dev, sg, nents, dir, attrs);if (!(attrs &DMA_ATTR_SKIP_CPU_SYNC ))
@@ -1047,7 +1052,7 @@ static void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg,struct scatterlist *tmp;int i; -if (dev_is_untrusted (dev)) { +if (dev_use_swiotlb (dev)) {iommu_dma_unmap_sg_swiotlb (dev, sg, nents, dir, attrs);return ; }
Signature · 1 line
2.33.0.rc1.237.g0d66db33f3-goog
Re: [PATCH v5 5/7] dma-iommu: Check CONFIG_SWIOTLB more broadly
drivers/iommu/dma-iommu.c static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page, · line 799
Quoted 3 lines
drivers/iommu/dma-iommu.c +1
-1-if (IS_ENABLED (CONFIG_SWIOTLB ) &&dev_is_untrusted (dev) && +if (IS_ENABLED (CONFIG_SWIOTLB ) &&dev_use_swiotlb (dev) &&iova_offset (iovad, phys | size)) {
This can drop the explicit CONFIG_SWIOTLB check now (and make the remaining conditional fit onto a single line).
PATCH v5 6/7 swiotlb: support aligned swiotlb buffers
In reply to David StevensFrom: David Stevens <[email protected]>
Add an argument to swiotlb_tbl_map_single that specifies the desired alignment of the allocated buffer. This is used by dma-iommu to ensure the buffer is aligned to the iova granule size when using swiotlb with untrusted sub-granule mappings. This addresses an issue where adjacent slots could be exposed to the untrusted device if IO_TLB_SIZE < iova granule < PAGE_SIZE.
--- drivers/iommu/dma-iommu.c | 4 ++-- drivers/xen/swiotlb-xen.c | 2 +- include/linux/swiotlb.h | 3 ++- kernel/dma/swiotlb.c | 11 +++++++---- 4 files changed, 12 insertions(+), 8 deletions(-)
drivers/iommu/dma-iommu.c +2 -2
@@ -801,8 +801,8 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,size_t padding_size; aligned_size =iova_align (iovad, size); - phys =swiotlb_tbl_map_single (dev, phys, size, - aligned_size, dir, attrs); + phys =swiotlb_tbl_map_single (dev, phys, size, aligned_size, +iova_mask (iovad), dir, attrs);if (phys ==DMA_MAPPING_ERROR )return DMA_MAPPING_ERROR ;
drivers/xen/swiotlb-xen.c +1 -1
@@ -382,7 +382,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,*/ trace_swiotlb_bounced (dev, dev_addr, size, swiotlb_force); - map =swiotlb_tbl_map_single (dev, phys, size, size, dir, attrs); + map =swiotlb_tbl_map_single (dev, phys, size, size,0 , dir, attrs);if (map == (phys_addr_t )DMA_MAPPING_ERROR )return DMA_MAPPING_ERROR ;
include/linux/swiotlb.h +2 -1
@@ -44,7 +44,8 @@ extern void __init swiotlb_update_mem_attributes(void);phys_addr_t swiotlb_tbl_map_single (struct device *hwdev,phys_addr_t phys,size_t mapping_size,size_t alloc_size, -enum dma_data_direction dir,unsigned long attrs); +unsigned int alloc_aligned_mask,enum dma_data_direction dir, +unsigned long attrs); extern void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
kernel/dma/swiotlb.c +7 -4
@@ -427,7 +427,7 @@ static unsigned int wrap_index(struct io_tlb_mem *mem, unsigned int index)* allocate a buffer from that IO TLB pool. */ static int find_slots (struct device *dev,phys_addr_t orig_addr, -size_t alloc_size) +size_t alloc_size,unsigned int alloc_align_mask) {struct io_tlb_mem *mem = io_tlb_default_mem;unsigned long boundary_mask =dma_get_seg_boundary (dev);
@@ -450,6 +450,7 @@ static int find_slots(struct device *dev, phys_addr_t orig_addr, stride = (iotlb_align_mask >>IO_TLB_SHIFT ) +1 ;if (alloc_size >=PAGE_SIZE ) stride =max (stride, stride << (PAGE_SHIFT -IO_TLB_SHIFT )); + stride =max (stride, (alloc_align_mask >>IO_TLB_SHIFT ) +1 );spin_lock_irqsave (&mem->lock, flags);if (unlikely (nslots > mem->nslabs - mem->used))
@@ -504,7 +505,8 @@ static int find_slots(struct device *dev, phys_addr_t orig_addr,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) +unsigned int alloc_align_mask,enum dma_data_direction dir, +unsigned long attrs) {struct io_tlb_mem *mem = io_tlb_default_mem;unsigned int offset =swiotlb_align_offset (dev, orig_addr);
@@ -524,7 +526,8 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,return (phys_addr_t )DMA_MAPPING_ERROR ; } - index =find_slots (dev, orig_addr, alloc_size + offset); + index =find_slots (dev, orig_addr, + alloc_size + offset, alloc_align_mask);if (index ==-1 ) {if (!(attrs &DMA_ATTR_NO_WARN )) dev_warn_ratelimited(dev,
@@ -636,7 +639,7 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size,trace_swiotlb_bounced (dev,phys_to_dma (dev, paddr), size, swiotlb_force); - swiotlb_addr =swiotlb_tbl_map_single (dev, paddr, size, size, dir, + 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 ;
Signature · 1 line
2.33.0.rc1.237.g0d66db33f3-goog
PATCH v5 7/7 dma-iommu: account for min_align_mask
In reply to David StevensFrom: David Stevens <[email protected]>
For devices which set min_align_mask, swiotlb preserves the offset of the original physical address within that mask. Since __iommu_dma_map accounts for non-aligned addresses, passing a non-aligned swiotlb address with the swiotlb aligned size results in the offset being accounted for twice in the size passed to iommu_map_atomic. The extra page exposed to DMA is also not cleaned up by __iommu_dma_unmap, since that function unmaps with the correct size. This causes mapping failures if the iova gets reused, due to collisions in the iommu page tables.
To fix this, pass the original size to __iommu_dma_map, since that function already handles alignment.
Additionally, when swiotlb returns non-aligned addresses, there is padding at the start of the bounce buffer that needs to be cleared.
--- drivers/iommu/dma-iommu.c | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-)
drivers/iommu/dma-iommu.c +13 -11
@@ -788,7 +788,6 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,struct iommu_domain *domain =iommu_get_dma_domain (dev);struct iommu_dma_cookie *cookie = domain->iova_cookie;struct iova_domain *iovad = &cookie->iovad; -size_t aligned_size = size;dma_addr_t iova, dma_mask =dma_get_mask (dev);/*
@@ -797,8 +796,8 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,*/ if (IS_ENABLED (CONFIG_SWIOTLB ) &&dev_use_swiotlb (dev) &&iova_offset (iovad, phys | size)) { -void *padding_start; -size_t padding_size; +void *tlb_start; +size_t aligned_size, iova_off, mapping_end_off; aligned_size =iova_align (iovad, size); phys = swiotlb_tbl_map_single(dev, phys, size, aligned_size,
@@ -807,24 +806,27 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,if (phys ==DMA_MAPPING_ERROR )return DMA_MAPPING_ERROR ; -/* Cleanup the padding area. */ - padding_start =phys_to_virt (phys); - padding_size = aligned_size; + iova_off =iova_offset (iovad, phys); + tlb_start =phys_to_virt (phys - iova_off);if (!(attrs &DMA_ATTR_SKIP_CPU_SYNC ) && (dir ==DMA_TO_DEVICE || dir ==DMA_BIDIRECTIONAL )) { - padding_start += size; - padding_size -= size; +/* Cleanup the padding area. */ + mapping_end_off = iova_off + size; +memset (tlb_start,0 , iova_off); +memset (tlb_start + mapping_end_off,0 , + aligned_size - mapping_end_off); + }else { +/* Nothing was sync'ed, so clear the whole buffer. */ +memset (tlb_start,0 , aligned_size); } - -memset (padding_start,0 , padding_size); }if (!coherent && !(attrs &DMA_ATTR_SKIP_CPU_SYNC ))arch_sync_dma_for_device (phys, size, dir); - iova =__iommu_dma_map (dev, phys, aligned_size, prot, dma_mask); + iova =__iommu_dma_map (dev, phys, size, prot, dma_mask);if (iova ==DMA_MAPPING_ERROR &&is_swiotlb_buffer (phys))swiotlb_tbl_unmap_single (dev, phys, size, dir, attrs);return iova;
Signature · 1 line
2.33.0.rc1.237.g0d66db33f3-goog