diff options
Diffstat (limited to 'drivers/iommu/dma-iommu.c')
| -rw-r--r-- | drivers/iommu/dma-iommu.c | 244 |
1 files changed, 124 insertions, 120 deletions
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 50ccc4f1ef81..2a9fa0c8cc00 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -17,6 +17,7 @@ #include <linux/gfp.h> #include <linux/huge_mm.h> #include <linux/iommu.h> +#include <linux/iommu-dma.h> #include <linux/iova.h> #include <linux/irq.h> #include <linux/list_sort.h> @@ -32,6 +33,7 @@ #include <trace/events/swiotlb.h> #include "dma-iommu.h" +#include "iommu-pages.h" struct iommu_dma_msi_page { struct list_head list; @@ -156,7 +158,7 @@ static void fq_ring_free_locked(struct iommu_dma_cookie *cookie, struct iova_fq if (fq->entries[idx].counter >= counter) break; - put_pages_list(&fq->entries[idx].freelist); + iommu_put_pages_list(&fq->entries[idx].freelist); free_iova_fast(&cookie->iovad, fq->entries[idx].iova_pfn, fq->entries[idx].pages); @@ -254,7 +256,7 @@ static void iommu_dma_free_fq_single(struct iova_fq *fq) int idx; fq_ring_for_each(idx, fq) - put_pages_list(&fq->entries[idx].freelist); + iommu_put_pages_list(&fq->entries[idx].freelist); vfree(fq); } @@ -267,7 +269,7 @@ static void iommu_dma_free_fq_percpu(struct iova_fq __percpu *percpu_fq) struct iova_fq *fq = per_cpu_ptr(percpu_fq, cpu); fq_ring_for_each(idx, fq) - put_pages_list(&fq->entries[idx].freelist); + iommu_put_pages_list(&fq->entries[idx].freelist); } free_percpu(percpu_fq); @@ -660,19 +662,16 @@ static void iommu_dma_init_options(struct iommu_dma_options *options, /** * iommu_dma_init_domain - Initialise a DMA mapping domain * @domain: IOMMU domain previously prepared by iommu_get_dma_cookie() - * @base: IOVA at which the mappable address space starts - * @limit: Last address of the IOVA space * @dev: Device the domain is being initialised for * - * @base and @limit + 1 should be exact multiples of IOMMU page granularity to - * avoid rounding surprises. If necessary, we reserve the page at address 0 + * If the geometry and dma_range_map include address 0, we reserve that page * to ensure it is an invalid IOVA. It is safe to reinitialise a domain, but * any change which could make prior IOVAs invalid will fail. */ -static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base, - dma_addr_t limit, struct device *dev) +static int iommu_dma_init_domain(struct iommu_domain *domain, struct device *dev) { struct iommu_dma_cookie *cookie = domain->iova_cookie; + const struct bus_dma_region *map = dev->dma_range_map; unsigned long order, base_pfn; struct iova_domain *iovad; int ret; @@ -684,19 +683,19 @@ static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base, /* Use the smallest supported page size for IOVA granularity */ order = __ffs(domain->pgsize_bitmap); - base_pfn = max_t(unsigned long, 1, base >> order); + base_pfn = 1; /* Check the domain allows at least some access to the device... */ - if (domain->geometry.force_aperture) { - if (base > domain->geometry.aperture_end || - limit < domain->geometry.aperture_start) { + if (map) { + if (dma_range_map_min(map) > domain->geometry.aperture_end || + dma_range_map_max(map) < domain->geometry.aperture_start) { pr_warn("specified DMA range outside IOMMU capability\n"); return -EFAULT; } - /* ...then finally give it a kicking to make sure it fits */ - base_pfn = max_t(unsigned long, base_pfn, - domain->geometry.aperture_start >> order); } + /* ...then finally give it a kicking to make sure it fits */ + base_pfn = max_t(unsigned long, base_pfn, + domain->geometry.aperture_start >> order); /* start_pfn is always nonzero for an already-initialised domain */ mutex_lock(&cookie->mutex); @@ -859,6 +858,11 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys, iommu_deferred_attach(dev, domain)) return DMA_MAPPING_ERROR; + /* If anyone ever wants this we'd need support in the IOVA allocator */ + if (dev_WARN_ONCE(dev, dma_get_min_align_mask(dev) > iova_mask(iovad), + "Unsupported alignment constraint\n")) + return DMA_MAPPING_ERROR; + size = iova_align(iovad, size + iova_off); iova = iommu_dma_alloc_iova(domain, size, dma_mask, dev); @@ -936,8 +940,7 @@ static struct page **__iommu_dma_alloc_pages(struct device *dev, * but an IOMMU which supports smaller pages might not map the whole thing. */ static struct page **__iommu_dma_alloc_noncontiguous(struct device *dev, - size_t size, struct sg_table *sgt, gfp_t gfp, pgprot_t prot, - unsigned long attrs) + size_t size, struct sg_table *sgt, gfp_t gfp, unsigned long attrs) { struct iommu_domain *domain = iommu_get_dma_domain(dev); struct iommu_dma_cookie *cookie = domain->iova_cookie; @@ -1011,15 +1014,14 @@ out_free_pages: } static void *iommu_dma_alloc_remap(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp, pgprot_t prot, - unsigned long attrs) + dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) { struct page **pages; struct sg_table sgt; void *vaddr; + pgprot_t prot = dma_pgprot(dev, PAGE_KERNEL, attrs); - pages = __iommu_dma_alloc_noncontiguous(dev, size, &sgt, gfp, prot, - attrs); + pages = __iommu_dma_alloc_noncontiguous(dev, size, &sgt, gfp, attrs); if (!pages) return NULL; *dma_handle = sgt.sgl->dma_address; @@ -1036,9 +1038,23 @@ out_unmap: return NULL; } -static struct sg_table *iommu_dma_alloc_noncontiguous(struct device *dev, - size_t size, enum dma_data_direction dir, gfp_t gfp, - unsigned long attrs) +/* + * This is the actual return value from the iommu_dma_alloc_noncontiguous. + * + * The users of the DMA API should only care about the sg_table, but to make + * the DMA-API internal vmaping and freeing easier we stash away the page + * array as well (except for the fallback case). This can go away any time, + * e.g. when a vmap-variant that takes a scatterlist comes along. + */ +struct dma_sgt_handle { + struct sg_table sgt; + struct page **pages; +}; +#define sgt_handle(sgt) \ + container_of((sgt), struct dma_sgt_handle, sgt) + +struct sg_table *iommu_dma_alloc_noncontiguous(struct device *dev, size_t size, + enum dma_data_direction dir, gfp_t gfp, unsigned long attrs) { struct dma_sgt_handle *sh; @@ -1046,8 +1062,7 @@ static struct sg_table *iommu_dma_alloc_noncontiguous(struct device *dev, if (!sh) return NULL; - sh->pages = __iommu_dma_alloc_noncontiguous(dev, size, &sh->sgt, gfp, - PAGE_KERNEL, attrs); + sh->pages = __iommu_dma_alloc_noncontiguous(dev, size, &sh->sgt, gfp, attrs); if (!sh->pages) { kfree(sh); return NULL; @@ -1055,7 +1070,7 @@ static struct sg_table *iommu_dma_alloc_noncontiguous(struct device *dev, return &sh->sgt; } -static void iommu_dma_free_noncontiguous(struct device *dev, size_t size, +void iommu_dma_free_noncontiguous(struct device *dev, size_t size, struct sg_table *sgt, enum dma_data_direction dir) { struct dma_sgt_handle *sh = sgt_handle(sgt); @@ -1066,8 +1081,26 @@ static void iommu_dma_free_noncontiguous(struct device *dev, size_t size, kfree(sh); } -static void iommu_dma_sync_single_for_cpu(struct device *dev, - dma_addr_t dma_handle, size_t size, enum dma_data_direction dir) +void *iommu_dma_vmap_noncontiguous(struct device *dev, size_t size, + struct sg_table *sgt) +{ + unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; + + return vmap(sgt_handle(sgt)->pages, count, VM_MAP, PAGE_KERNEL); +} + +int iommu_dma_mmap_noncontiguous(struct device *dev, struct vm_area_struct *vma, + size_t size, struct sg_table *sgt) +{ + 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); +} + +void iommu_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, + size_t size, enum dma_data_direction dir) { phys_addr_t phys; @@ -1078,12 +1111,11 @@ 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(dev, phys)) - swiotlb_sync_single_for_cpu(dev, phys, size, dir); + swiotlb_sync_single_for_cpu(dev, phys, size, dir); } -static void iommu_dma_sync_single_for_device(struct device *dev, - dma_addr_t dma_handle, size_t size, enum dma_data_direction dir) +void iommu_dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, + size_t size, enum dma_data_direction dir) { phys_addr_t phys; @@ -1091,16 +1123,14 @@ 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(dev, phys)) - swiotlb_sync_single_for_device(dev, phys, size, dir); + swiotlb_sync_single_for_device(dev, phys, size, dir); if (!dev_is_dma_coherent(dev)) arch_sync_dma_for_device(phys, size, dir); } -static void iommu_dma_sync_sg_for_cpu(struct device *dev, - struct scatterlist *sgl, int nelems, - enum dma_data_direction dir) +void iommu_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl, + int nelems, enum dma_data_direction dir) { struct scatterlist *sg; int i; @@ -1114,9 +1144,8 @@ static void iommu_dma_sync_sg_for_cpu(struct device *dev, arch_sync_dma_for_cpu(sg_phys(sg), sg->length, dir); } -static void iommu_dma_sync_sg_for_device(struct device *dev, - struct scatterlist *sgl, int nelems, - enum dma_data_direction dir) +void iommu_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sgl, + int nelems, enum dma_data_direction dir) { struct scatterlist *sg; int i; @@ -1131,9 +1160,9 @@ static void iommu_dma_sync_sg_for_device(struct device *dev, 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, - unsigned long offset, size_t size, enum dma_data_direction dir, - unsigned long attrs) +dma_addr_t iommu_dma_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; bool coherent = dev_is_dma_coherent(dev); @@ -1149,9 +1178,6 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page, */ if (dev_use_swiotlb(dev, size, dir) && iova_offset(iovad, phys | size)) { - void *padding_start; - size_t padding_size, aligned_size; - if (!is_swiotlb_active(dev)) { dev_warn_once(dev, "DMA bounce buffers are inactive, unable to map unaligned transaction.\n"); return DMA_MAPPING_ERROR; @@ -1159,36 +1185,42 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page, trace_swiotlb_bounced(dev, phys, size); - aligned_size = iova_align(iovad, size); - phys = swiotlb_tbl_map_single(dev, phys, size, aligned_size, + phys = swiotlb_tbl_map_single(dev, phys, size, iova_mask(iovad), 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; + /* + * Untrusted devices should not see padding areas with random + * leftover kernel data, so zero the pre- and post-padding. + * swiotlb_tbl_map_single() has initialized the bounce buffer + * proper to the contents of the original memory buffer. + */ + if (dev_is_untrusted(dev)) { + size_t start, virt = (size_t)phys_to_virt(phys); + + /* Pre-padding */ + start = iova_align_down(iovad, virt); + memset((void *)start, 0, virt - start); - if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) && - (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) { - padding_start += size; - padding_size -= size; + /* Post-padding */ + start = virt + size; + memset((void *)start, 0, + iova_align(iovad, start) - start); } - - 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, size, prot, dma_mask); - if (iova == DMA_MAPPING_ERROR && is_swiotlb_buffer(dev, phys)) + if (iova == DMA_MAPPING_ERROR) 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, +void iommu_dma_unmap_page(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction dir, unsigned long attrs) { struct iommu_domain *domain = iommu_get_dma_domain(dev); @@ -1203,8 +1235,7 @@ static void iommu_dma_unmap_page(struct device *dev, dma_addr_t dma_handle, __iommu_dma_unmap(dev, dma_handle, size); - if (unlikely(is_swiotlb_buffer(dev, phys))) - swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs); + swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs); } /* @@ -1342,8 +1373,8 @@ out_unmap: * impedance-matching, to be able to hand off a suitably-aligned list, * but still preserve the original offsets and sizes for the caller. */ -static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, unsigned long attrs) +int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, unsigned long attrs) { struct iommu_domain *domain = iommu_get_dma_domain(dev); struct iommu_dma_cookie *cookie = domain->iova_cookie; @@ -1462,8 +1493,8 @@ out: return ret; } -static void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, unsigned long attrs) +void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, unsigned long attrs) { dma_addr_t end = 0, start; struct scatterlist *tmp; @@ -1512,7 +1543,7 @@ static void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg, __iommu_dma_unmap(dev, start, end - start); } -static dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys, +dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys, size_t size, enum dma_data_direction dir, unsigned long attrs) { return __iommu_dma_map(dev, phys, size, @@ -1520,7 +1551,7 @@ static dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys, dma_get_mask(dev)); } -static void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle, +void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle, size_t size, enum dma_data_direction dir, unsigned long attrs) { __iommu_dma_unmap(dev, handle, size); @@ -1557,7 +1588,7 @@ static void __iommu_dma_free(struct device *dev, size_t size, void *cpu_addr) dma_free_contiguous(dev, page, alloc_size); } -static void iommu_dma_free(struct device *dev, size_t size, void *cpu_addr, +void iommu_dma_free(struct device *dev, size_t size, void *cpu_addr, dma_addr_t handle, unsigned long attrs) { __iommu_dma_unmap(dev, handle, size); @@ -1601,8 +1632,8 @@ out_free_pages: return NULL; } -static void *iommu_dma_alloc(struct device *dev, size_t size, - dma_addr_t *handle, gfp_t gfp, unsigned long attrs) +void *iommu_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, + gfp_t gfp, unsigned long attrs) { bool coherent = dev_is_dma_coherent(dev); int ioprot = dma_info_to_prot(DMA_BIDIRECTIONAL, coherent, attrs); @@ -1613,8 +1644,7 @@ static void *iommu_dma_alloc(struct device *dev, size_t size, if (gfpflags_allow_blocking(gfp) && !(attrs & DMA_ATTR_FORCE_CONTIGUOUS)) { - return iommu_dma_alloc_remap(dev, size, handle, gfp, - dma_pgprot(dev, PAGE_KERNEL, attrs), attrs); + return iommu_dma_alloc_remap(dev, size, handle, gfp, attrs); } if (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && @@ -1636,7 +1666,7 @@ static void *iommu_dma_alloc(struct device *dev, size_t size, return cpu_addr; } -static int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma, +int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs) { @@ -1667,7 +1697,7 @@ static int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma, vma->vm_page_prot); } -static int iommu_dma_get_sgtable(struct device *dev, struct sg_table *sgt, +int iommu_dma_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs) { @@ -1694,69 +1724,43 @@ static int iommu_dma_get_sgtable(struct device *dev, struct sg_table *sgt, return ret; } -static unsigned long iommu_dma_get_merge_boundary(struct device *dev) +unsigned long iommu_dma_get_merge_boundary(struct device *dev) { struct iommu_domain *domain = iommu_get_dma_domain(dev); return (1UL << __ffs(domain->pgsize_bitmap)) - 1; } -static size_t iommu_dma_opt_mapping_size(void) +size_t iommu_dma_opt_mapping_size(void) { return iova_rcache_range(); } -static const struct dma_map_ops iommu_dma_ops = { - .flags = DMA_F_PCI_P2PDMA_SUPPORTED, - .alloc = iommu_dma_alloc, - .free = iommu_dma_free, - .alloc_pages = dma_common_alloc_pages, - .free_pages = dma_common_free_pages, - .alloc_noncontiguous = iommu_dma_alloc_noncontiguous, - .free_noncontiguous = iommu_dma_free_noncontiguous, - .mmap = iommu_dma_mmap, - .get_sgtable = iommu_dma_get_sgtable, - .map_page = iommu_dma_map_page, - .unmap_page = iommu_dma_unmap_page, - .map_sg = iommu_dma_map_sg, - .unmap_sg = iommu_dma_unmap_sg, - .sync_single_for_cpu = iommu_dma_sync_single_for_cpu, - .sync_single_for_device = iommu_dma_sync_single_for_device, - .sync_sg_for_cpu = iommu_dma_sync_sg_for_cpu, - .sync_sg_for_device = iommu_dma_sync_sg_for_device, - .map_resource = iommu_dma_map_resource, - .unmap_resource = iommu_dma_unmap_resource, - .get_merge_boundary = iommu_dma_get_merge_boundary, - .opt_mapping_size = iommu_dma_opt_mapping_size, -}; +size_t iommu_dma_max_mapping_size(struct device *dev) +{ + if (dev_is_untrusted(dev)) + return swiotlb_max_mapping_size(dev); -/* - * The IOMMU core code allocates the default DMA domain, which the underlying - * IOMMU driver needs to support via the dma-iommu layer. - */ -void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit) + return SIZE_MAX; +} + +void iommu_setup_dma_ops(struct device *dev) { struct iommu_domain *domain = iommu_get_domain_for_dev(dev); - if (!domain) - goto out_err; + if (dev_is_pci(dev)) + dev->iommu->pci_32bit_workaround = !iommu_dma_forcedac; - /* - * The IOMMU core code allocates the default DMA domain, which the - * underlying IOMMU driver needs to support via the dma-iommu layer. - */ - if (iommu_is_dma_domain(domain)) { - if (iommu_dma_init_domain(domain, dma_base, dma_limit, dev)) - goto out_err; - dev->dma_ops = &iommu_dma_ops; - } + dev->dma_iommu = iommu_is_dma_domain(domain); + if (dev->dma_iommu && iommu_dma_init_domain(domain, dev)) + goto out_err; return; out_err: - pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n", - dev_name(dev)); + pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n", + dev_name(dev)); + dev->dma_iommu = false; } -EXPORT_SYMBOL_GPL(iommu_setup_dma_ops); static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev, phys_addr_t msi_addr, struct iommu_domain *domain) |