From 9f683dfe8099639f9ac859287744a9ed1c3698a0 Mon Sep 17 00:00:00 2001 From: Petr Tesarik Date: Thu, 10 Jul 2025 10:38:29 +0200 Subject: dma-direct: clean up the logic in __dma_direct_alloc_pages() Convert a goto-based loop to a while() loop. To allow the simplification, return early when allocation from CMA is successful. As a bonus, this early return avoids a repeated dma_coherent_ok() check. No functional change. Signed-off-by: Petr Tesarik Signed-off-by: Marek Szyprowski Link: https://lore.kernel.org/r/20250710083829.1853466-1-ptesarik@suse.com --- kernel/dma/direct.c | 31 +++++++++++++------------------ 1 file changed, 13 insertions(+), 18 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 24c359d9c879..302e89580972 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -120,7 +120,7 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, gfp_t gfp, bool allow_highmem) { int node = dev_to_node(dev); - struct page *page = NULL; + struct page *page; u64 phys_limit; WARN_ON_ONCE(!PAGE_ALIGNED(size)); @@ -131,30 +131,25 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, gfp |= dma_direct_optimal_gfp_mask(dev, &phys_limit); page = dma_alloc_contiguous(dev, size, gfp); if (page) { - if (!dma_coherent_ok(dev, page_to_phys(page), size) || - (!allow_highmem && PageHighMem(page))) { - dma_free_contiguous(dev, page, size); - page = NULL; - } + if (dma_coherent_ok(dev, page_to_phys(page), size) && + (allow_highmem || !PageHighMem(page))) + return page; + + dma_free_contiguous(dev, page, size); } -again: - if (!page) - page = alloc_pages_node(node, gfp, get_order(size)); - if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) { + + while ((page = alloc_pages_node(node, gfp, get_order(size))) + && !dma_coherent_ok(dev, page_to_phys(page), size)) { __free_pages(page, get_order(size)); - page = NULL; if (IS_ENABLED(CONFIG_ZONE_DMA32) && phys_limit < DMA_BIT_MASK(64) && - !(gfp & (GFP_DMA32 | GFP_DMA))) { + !(gfp & (GFP_DMA32 | GFP_DMA))) gfp |= GFP_DMA32; - goto again; - } - - if (IS_ENABLED(CONFIG_ZONE_DMA) && !(gfp & GFP_DMA)) { + else if (IS_ENABLED(CONFIG_ZONE_DMA) && !(gfp & GFP_DMA)) gfp = (gfp & ~GFP_DMA32) | GFP_DMA; - goto again; - } + else + return NULL; } return page; -- cgit v1.2.3 From 110aa2c74dbd9de862afc8546d1b9be4c86f9eb0 Mon Sep 17 00:00:00 2001 From: Qianfeng Rong Date: Tue, 5 Aug 2025 10:32:22 +0800 Subject: swiotlb: Remove redundant __GFP_NOWARN Commit 16f5dfbc851b ("gfp: include __GFP_NOWARN in GFP_NOWAIT") made GFP_NOWAIT implicitly include __GFP_NOWARN. Therefore, explicit __GFP_NOWARN combined with GFP_NOWAIT (e.g., `GFP_NOWAIT | __GFP_NOWARN`) is now redundant. Let's clean up these redundant flags across subsystems. No functional changes. Signed-off-by: Qianfeng Rong Signed-off-by: Marek Szyprowski Link: https://lore.kernel.org/r/20250805023222.332920-1-rongqianfeng@vivo.com --- kernel/dma/swiotlb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index abcf3fa63a56..0d37da3d95b6 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -1209,7 +1209,7 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr, nslabs = nr_slots(alloc_size); phys_limit = min_not_zero(*dev->dma_mask, dev->bus_dma_limit); pool = swiotlb_alloc_pool(dev, nslabs, nslabs, 1, phys_limit, - GFP_NOWAIT | __GFP_NOWARN); + GFP_NOWAIT); if (!pool) return -1; -- cgit v1.2.3 From e9e81d86fee63c6d5757841ab557019ddf73786f Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 9 Sep 2025 16:27:31 +0300 Subject: dma-debug: refactor to use physical addresses for page mapping Convert the DMA debug infrastructure from page-based to physical address-based mapping as a preparation to rely on physical address for DMA mapping routines. The refactoring renames debug_dma_map_page() to debug_dma_map_phys() and changes its signature to accept a phys_addr_t parameter instead of struct page and offset. Similarly, debug_dma_unmap_page() becomes debug_dma_unmap_phys(). A new dma_debug_phy type is introduced to distinguish physical address mappings from other debug entry types. All callers throughout the codebase are updated to pass physical addresses directly, eliminating the need for page-to-physical conversion in the debug layer. This refactoring eliminates the need to convert between page pointers and physical addresses in the debug layer, making the code more efficient and consistent with the DMA mapping API's physical address focus. Reviewed-by: Jason Gunthorpe Signed-off-by: Leon Romanovsky [mszyprow: added a fixup] Signed-off-by: Marek Szyprowski Link: https://lore.kernel.org/r/56d1a6769b68dfcbf8b26a75a7329aeb8e3c3b6a.1757423202.git.leonro@nvidia.com Link: https://lore.kernel.org/all/20250910052618.GH341237@unreal/ --- kernel/dma/debug.c | 39 ++++++++++++++++++++------------------- kernel/dma/debug.h | 16 +++++++--------- kernel/dma/mapping.c | 10 +++++----- 3 files changed, 32 insertions(+), 33 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index b82399437db0..b275db9ca6a0 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -40,6 +40,7 @@ enum { dma_debug_coherent, dma_debug_resource, dma_debug_noncoherent, + dma_debug_phy, }; enum map_err_types { @@ -143,6 +144,7 @@ static const char *type2name[] = { [dma_debug_coherent] = "coherent", [dma_debug_resource] = "resource", [dma_debug_noncoherent] = "noncoherent", + [dma_debug_phy] = "phy", }; static const char *dir2name[] = { @@ -1054,17 +1056,16 @@ static void check_unmap(struct dma_debug_entry *ref) dma_entry_free(entry); } -static void check_for_stack(struct device *dev, - struct page *page, size_t offset) +static void check_for_stack(struct device *dev, phys_addr_t phys) { void *addr; struct vm_struct *stack_vm_area = task_stack_vm_area(current); if (!stack_vm_area) { /* Stack is direct-mapped. */ - if (PageHighMem(page)) + if (PhysHighMem(phys)) return; - addr = page_address(page) + offset; + addr = phys_to_virt(phys); if (object_is_on_stack(addr)) err_printk(dev, NULL, "device driver maps memory from stack [addr=%p]\n", addr); } else { @@ -1072,10 +1073,12 @@ static void check_for_stack(struct device *dev, int i; for (i = 0; i < stack_vm_area->nr_pages; i++) { - if (page != stack_vm_area->pages[i]) + if (__phys_to_pfn(phys) != + page_to_pfn(stack_vm_area->pages[i])) continue; - addr = (u8 *)current->stack + i * PAGE_SIZE + offset; + addr = (u8 *)current->stack + i * PAGE_SIZE + + (phys % PAGE_SIZE); err_printk(dev, NULL, "device driver maps memory from stack [probable addr=%p]\n", addr); break; } @@ -1204,9 +1207,8 @@ void debug_dma_map_single(struct device *dev, const void *addr, } EXPORT_SYMBOL(debug_dma_map_single); -void debug_dma_map_page(struct device *dev, struct page *page, size_t offset, - size_t size, int direction, dma_addr_t dma_addr, - unsigned long attrs) +void debug_dma_map_phys(struct device *dev, phys_addr_t phys, size_t size, + int direction, dma_addr_t dma_addr, unsigned long attrs) { struct dma_debug_entry *entry; @@ -1221,19 +1223,18 @@ void debug_dma_map_page(struct device *dev, struct page *page, size_t offset, return; entry->dev = dev; - entry->type = dma_debug_single; - entry->paddr = page_to_phys(page) + offset; + entry->type = dma_debug_phy; + entry->paddr = phys; entry->dev_addr = dma_addr; entry->size = size; entry->direction = direction; entry->map_err_type = MAP_ERR_NOT_CHECKED; - check_for_stack(dev, page, offset); + if (!(attrs & DMA_ATTR_MMIO)) { + check_for_stack(dev, phys); - if (!PageHighMem(page)) { - void *addr = page_address(page) + offset; - - check_for_illegal_area(dev, addr, size); + if (!PhysHighMem(phys)) + check_for_illegal_area(dev, phys_to_virt(phys), size); } add_dma_entry(entry, attrs); @@ -1277,11 +1278,11 @@ void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) } EXPORT_SYMBOL(debug_dma_mapping_error); -void debug_dma_unmap_page(struct device *dev, dma_addr_t dma_addr, +void debug_dma_unmap_phys(struct device *dev, dma_addr_t dma_addr, size_t size, int direction) { struct dma_debug_entry ref = { - .type = dma_debug_single, + .type = dma_debug_phy, .dev = dev, .dev_addr = dma_addr, .size = size, @@ -1305,7 +1306,7 @@ void debug_dma_map_sg(struct device *dev, struct scatterlist *sg, return; for_each_sg(sg, s, nents, i) { - check_for_stack(dev, sg_page(s), s->offset); + check_for_stack(dev, sg_phys(s)); if (!PageHighMem(sg_page(s))) check_for_illegal_area(dev, sg_virt(s), s->length); } diff --git a/kernel/dma/debug.h b/kernel/dma/debug.h index 48757ca13f31..bedae973e725 100644 --- a/kernel/dma/debug.h +++ b/kernel/dma/debug.h @@ -9,12 +9,11 @@ #define _KERNEL_DMA_DEBUG_H #ifdef CONFIG_DMA_API_DEBUG -extern void debug_dma_map_page(struct device *dev, struct page *page, - size_t offset, size_t size, - int direction, dma_addr_t dma_addr, +extern void debug_dma_map_phys(struct device *dev, phys_addr_t phys, + size_t size, int direction, dma_addr_t dma_addr, unsigned long attrs); -extern void debug_dma_unmap_page(struct device *dev, dma_addr_t addr, +extern void debug_dma_unmap_phys(struct device *dev, dma_addr_t addr, size_t size, int direction); extern void debug_dma_map_sg(struct device *dev, struct scatterlist *sg, @@ -62,14 +61,13 @@ extern void debug_dma_free_pages(struct device *dev, struct page *page, size_t size, int direction, dma_addr_t dma_addr); #else /* CONFIG_DMA_API_DEBUG */ -static inline void debug_dma_map_page(struct device *dev, struct page *page, - size_t offset, size_t size, - int direction, dma_addr_t dma_addr, - unsigned long attrs) +static inline void debug_dma_map_phys(struct device *dev, phys_addr_t phys, + size_t size, int direction, + dma_addr_t dma_addr, unsigned long attrs) { } -static inline void debug_dma_unmap_page(struct device *dev, dma_addr_t addr, +static inline void debug_dma_unmap_phys(struct device *dev, dma_addr_t addr, size_t size, int direction) { } diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 56de28a3b179..0b7e16c69bf1 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -157,6 +157,7 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page, unsigned long attrs) { const struct dma_map_ops *ops = get_dma_ops(dev); + phys_addr_t phys = page_to_phys(page) + offset; dma_addr_t addr; BUG_ON(!valid_dma_direction(dir)); @@ -165,16 +166,15 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page, return DMA_MAPPING_ERROR; if (dma_map_direct(dev, ops) || - arch_dma_map_page_direct(dev, page_to_phys(page) + offset + size)) + arch_dma_map_page_direct(dev, phys + size)) addr = dma_direct_map_page(dev, page, offset, size, dir, attrs); else if (use_dma_iommu(dev)) addr = iommu_dma_map_page(dev, page, offset, size, dir, attrs); else addr = ops->map_page(dev, page, offset, size, dir, attrs); kmsan_handle_dma(page, offset, size, dir); - trace_dma_map_page(dev, page_to_phys(page) + offset, addr, size, dir, - attrs); - debug_dma_map_page(dev, page, offset, size, dir, addr, attrs); + trace_dma_map_page(dev, phys, addr, size, dir, attrs); + debug_dma_map_phys(dev, phys, size, dir, addr, attrs); return addr; } @@ -194,7 +194,7 @@ void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size, else ops->unmap_page(dev, addr, size, dir, attrs); trace_dma_unmap_page(dev, addr, size, dir, attrs); - debug_dma_unmap_page(dev, addr, size, dir); + debug_dma_unmap_phys(dev, addr, size, dir); } EXPORT_SYMBOL(dma_unmap_page_attrs); -- cgit v1.2.3 From 76bb7c49f50ce7687f98eb35e78798584652dd0e Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 9 Sep 2025 16:27:32 +0300 Subject: dma-mapping: rename trace_dma_*map_page to trace_dma_*map_phys As a preparation for following map_page -> map_phys API conversion, let's rename trace_dma_*map_page() to be trace_dma_*map_phys(). Reviewed-by: Jason Gunthorpe Signed-off-by: Leon Romanovsky Signed-off-by: Marek Szyprowski Link: https://lore.kernel.org/r/c0c02d7d8bd4a148072d283353ba227516a76682.1757423202.git.leonro@nvidia.com --- kernel/dma/mapping.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 0b7e16c69bf1..bd3bb6d59d72 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -173,7 +173,7 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page, else addr = ops->map_page(dev, page, offset, size, dir, attrs); kmsan_handle_dma(page, offset, size, dir); - trace_dma_map_page(dev, phys, addr, size, dir, attrs); + trace_dma_map_phys(dev, phys, addr, size, dir, attrs); debug_dma_map_phys(dev, phys, size, dir, addr, attrs); return addr; @@ -193,7 +193,7 @@ void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size, iommu_dma_unmap_page(dev, addr, size, dir, attrs); else ops->unmap_page(dev, addr, size, dir, attrs); - trace_dma_unmap_page(dev, addr, size, dir, attrs); + trace_dma_unmap_phys(dev, addr, size, dir, attrs); debug_dma_unmap_phys(dev, addr, size, dir); } EXPORT_SYMBOL(dma_unmap_page_attrs); -- cgit v1.2.3 From 513559f73700966ded094b090c3ecc6dff877ef9 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 9 Sep 2025 16:27:33 +0300 Subject: iommu/dma: rename iommu_dma_*map_page to iommu_dma_*map_phys Rename the IOMMU DMA mapping functions to better reflect their actual calling convention. The functions iommu_dma_map_page() and iommu_dma_unmap_page() are renamed to iommu_dma_map_phys() and iommu_dma_unmap_phys() respectively, as they already operate on physical addresses rather than page structures. The calling convention changes from accepting (struct page *page, unsigned long offset) to (phys_addr_t phys), which eliminates the need for page-to-physical address conversion within the functions. This renaming prepares for the broader DMA API conversion from page-based to physical address-based mapping throughout the kernel. All callers are updated to pass physical addresses directly, including dma_map_page_attrs(), scatterlist mapping functions, and DMA page allocation helpers. The change simplifies the code by removing the page_to_phys() + offset calculation that was previously done inside the IOMMU functions. Reviewed-by: Jason Gunthorpe Signed-off-by: Leon Romanovsky Signed-off-by: Marek Szyprowski Link: https://lore.kernel.org/r/ed172f95f8f57782beae04f782813366894e98df.1757423202.git.leonro@nvidia.com --- kernel/dma/mapping.c | 4 ++-- kernel/dma/ops_helpers.c | 6 +++--- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index bd3bb6d59d72..90ad728205b9 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -169,7 +169,7 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page, arch_dma_map_page_direct(dev, phys + size)) addr = dma_direct_map_page(dev, page, offset, size, dir, attrs); else if (use_dma_iommu(dev)) - addr = iommu_dma_map_page(dev, page, offset, size, dir, attrs); + addr = iommu_dma_map_phys(dev, phys, size, dir, attrs); else addr = ops->map_page(dev, page, offset, size, dir, attrs); kmsan_handle_dma(page, offset, size, dir); @@ -190,7 +190,7 @@ void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size, arch_dma_unmap_page_direct(dev, addr + size)) dma_direct_unmap_page(dev, addr, size, dir, attrs); else if (use_dma_iommu(dev)) - iommu_dma_unmap_page(dev, addr, size, dir, attrs); + iommu_dma_unmap_phys(dev, addr, size, dir, attrs); else ops->unmap_page(dev, addr, size, dir, attrs); trace_dma_unmap_phys(dev, addr, size, dir, attrs); diff --git a/kernel/dma/ops_helpers.c b/kernel/dma/ops_helpers.c index 9afd569eadb9..6f9d604d9d40 100644 --- a/kernel/dma/ops_helpers.c +++ b/kernel/dma/ops_helpers.c @@ -72,8 +72,8 @@ struct page *dma_common_alloc_pages(struct device *dev, size_t size, return NULL; if (use_dma_iommu(dev)) - *dma_handle = iommu_dma_map_page(dev, page, 0, size, dir, - DMA_ATTR_SKIP_CPU_SYNC); + *dma_handle = iommu_dma_map_phys(dev, page_to_phys(page), size, + dir, DMA_ATTR_SKIP_CPU_SYNC); else *dma_handle = ops->map_page(dev, page, 0, size, dir, DMA_ATTR_SKIP_CPU_SYNC); @@ -92,7 +92,7 @@ void dma_common_free_pages(struct device *dev, size_t size, struct page *page, const struct dma_map_ops *ops = get_dma_ops(dev); if (use_dma_iommu(dev)) - iommu_dma_unmap_page(dev, dma_handle, size, dir, + iommu_dma_unmap_phys(dev, dma_handle, size, dir, DMA_ATTR_SKIP_CPU_SYNC); else if (ops->unmap_page) ops->unmap_page(dev, dma_handle, size, dir, -- cgit v1.2.3 From e53d29f957b36ba1666331956c6ccb047bb157d2 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 9 Sep 2025 16:27:35 +0300 Subject: dma-mapping: convert dma_direct_*map_page to be phys_addr_t based Convert the DMA direct mapping functions to accept physical addresses directly instead of page+offset parameters. The functions were already operating on physical addresses internally, so this change eliminates the redundant page-to-physical conversion at the API boundary. The functions dma_direct_map_page() and dma_direct_unmap_page() are renamed to dma_direct_map_phys() and dma_direct_unmap_phys() respectively, with their calling convention changed from (struct page *page, unsigned long offset) to (phys_addr_t phys). Architecture-specific functions arch_dma_map_page_direct() and arch_dma_unmap_page_direct() are similarly renamed to arch_dma_map_phys_direct() and arch_dma_unmap_phys_direct(). The is_pci_p2pdma_page() checks are replaced with DMA_ATTR_MMIO checks to allow integration with dma_direct_map_resource and dma_direct_map_phys() is extended to support MMIO path either. Reviewed-by: Jason Gunthorpe Signed-off-by: Leon Romanovsky Signed-off-by: Marek Szyprowski Link: https://lore.kernel.org/r/bb15a22f76dc2e26683333ff54e789606cfbfcf0.1757423202.git.leonro@nvidia.com --- kernel/dma/direct.c | 6 +++--- kernel/dma/direct.h | 57 +++++++++++++++++++++++++++++++++------------------- kernel/dma/mapping.c | 8 ++++---- 3 files changed, 43 insertions(+), 28 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 302e89580972..ba7524f169bc 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -448,7 +448,7 @@ void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, if (sg_dma_is_bus_address(sg)) sg_dma_unmark_bus_address(sg); else - dma_direct_unmap_page(dev, sg->dma_address, + dma_direct_unmap_phys(dev, sg->dma_address, sg_dma_len(sg), dir, attrs); } } @@ -471,8 +471,8 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, */ break; case PCI_P2PDMA_MAP_NONE: - sg->dma_address = dma_direct_map_page(dev, sg_page(sg), - sg->offset, sg->length, dir, attrs); + sg->dma_address = dma_direct_map_phys(dev, sg_phys(sg), + sg->length, dir, attrs); if (sg->dma_address == DMA_MAPPING_ERROR) { ret = -EIO; goto out_unmap; diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h index d2c0b7e632fc..da2fadf45bcd 100644 --- a/kernel/dma/direct.h +++ b/kernel/dma/direct.h @@ -80,42 +80,57 @@ static inline void dma_direct_sync_single_for_cpu(struct device *dev, arch_dma_mark_clean(paddr, size); } -static inline dma_addr_t dma_direct_map_page(struct device *dev, - struct page *page, unsigned long offset, size_t size, - enum dma_data_direction dir, unsigned long attrs) +static inline dma_addr_t dma_direct_map_phys(struct device *dev, + phys_addr_t phys, size_t size, enum dma_data_direction dir, + unsigned long attrs) { - phys_addr_t phys = page_to_phys(page) + offset; - dma_addr_t dma_addr = phys_to_dma(dev, phys); + dma_addr_t dma_addr; if (is_swiotlb_force_bounce(dev)) { - if (is_pci_p2pdma_page(page)) - return DMA_MAPPING_ERROR; + if (attrs & DMA_ATTR_MMIO) + goto err_overflow; + return swiotlb_map(dev, phys, size, dir, attrs); } - if (unlikely(!dma_capable(dev, dma_addr, size, true)) || - dma_kmalloc_needs_bounce(dev, size, dir)) { - if (is_pci_p2pdma_page(page)) - return DMA_MAPPING_ERROR; - if (is_swiotlb_active(dev)) - return swiotlb_map(dev, phys, size, dir, attrs); - - dev_WARN_ONCE(dev, 1, - "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n", - &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit); - return DMA_MAPPING_ERROR; + if (attrs & DMA_ATTR_MMIO) { + dma_addr = phys; + if (unlikely(!dma_capable(dev, dma_addr, size, false))) + goto err_overflow; + } else { + dma_addr = phys_to_dma(dev, phys); + if (unlikely(!dma_capable(dev, dma_addr, size, true)) || + dma_kmalloc_needs_bounce(dev, size, dir)) { + if (is_swiotlb_active(dev)) + return swiotlb_map(dev, phys, size, dir, attrs); + + goto err_overflow; + } } - if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + if (!dev_is_dma_coherent(dev) && + !(attrs & (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_MMIO))) arch_sync_dma_for_device(phys, size, dir); return dma_addr; + +err_overflow: + dev_WARN_ONCE( + dev, 1, + "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n", + &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit); + return DMA_MAPPING_ERROR; } -static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, +static inline void dma_direct_unmap_phys(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { - phys_addr_t phys = dma_to_phys(dev, addr); + phys_addr_t phys; + + if (attrs & DMA_ATTR_MMIO) + /* nothing to do: uncached and no swiotlb */ + return; + phys = dma_to_phys(dev, addr); if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) dma_direct_sync_single_for_cpu(dev, addr, size, dir); diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 90ad728205b9..3ac7d15e095f 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -166,8 +166,8 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page, return DMA_MAPPING_ERROR; if (dma_map_direct(dev, ops) || - arch_dma_map_page_direct(dev, phys + size)) - addr = dma_direct_map_page(dev, page, offset, size, dir, attrs); + arch_dma_map_phys_direct(dev, phys + size)) + addr = dma_direct_map_phys(dev, phys, size, dir, attrs); else if (use_dma_iommu(dev)) addr = iommu_dma_map_phys(dev, phys, size, dir, attrs); else @@ -187,8 +187,8 @@ void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size, BUG_ON(!valid_dma_direction(dir)); if (dma_map_direct(dev, ops) || - arch_dma_unmap_page_direct(dev, addr + size)) - dma_direct_unmap_page(dev, addr, size, dir, attrs); + arch_dma_unmap_phys_direct(dev, addr + size)) + dma_direct_unmap_phys(dev, addr, size, dir, attrs); else if (use_dma_iommu(dev)) iommu_dma_unmap_phys(dev, addr, size, dir, attrs); else -- cgit v1.2.3 From 6eb1e769b2c13a33cb2ca694454a7561d3d72c0a Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 9 Sep 2025 16:27:36 +0300 Subject: kmsan: convert kmsan_handle_dma to use physical addresses Convert the KMSAN DMA handling function from page-based to physical address-based interface. The refactoring renames kmsan_handle_dma() parameters from accepting (struct page *page, size_t offset, size_t size) to (phys_addr_t phys, size_t size). The existing semantics where callers are expected to provide only kmap memory is continued here. Reviewed-by: Jason Gunthorpe Signed-off-by: Leon Romanovsky Signed-off-by: Marek Szyprowski Link: https://lore.kernel.org/r/3557cbaf66e935bc794f37d2b891ef75cbf2c80c.1757423202.git.leonro@nvidia.com --- kernel/dma/mapping.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 3ac7d15e095f..e47bcf7cc43d 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -172,7 +172,8 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page, addr = iommu_dma_map_phys(dev, phys, size, dir, attrs); else addr = ops->map_page(dev, page, offset, size, dir, attrs); - kmsan_handle_dma(page, offset, size, dir); + + kmsan_handle_dma(phys, size, dir); trace_dma_map_phys(dev, phys, addr, size, dir, attrs); debug_dma_map_phys(dev, phys, size, dir, addr, attrs); -- cgit v1.2.3 From 18c9cbb042c930eb37f68df216319a371f4fcb22 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 9 Sep 2025 16:27:37 +0300 Subject: dma-mapping: implement DMA_ATTR_MMIO for dma_(un)map_page_attrs() Make dma_map_page_attrs() and dma_map_page_attrs() respect DMA_ATTR_MMIO. DMA_ATR_MMIO makes the functions behave the same as dma_(un)map_resource(): - No swiotlb is possible - Legacy dma_ops arches use ops->map_resource() - No kmsan - No arch_dma_map_phys_direct() The prior patches have made the internal functions called here support DMA_ATTR_MMIO. This is also preparation for turning dma_map_resource() into an inline calling dma_map_phys(DMA_ATTR_MMIO) to consolidate the flows. Reviewed-by: Jason Gunthorpe Signed-off-by: Leon Romanovsky Signed-off-by: Marek Szyprowski Link: https://lore.kernel.org/r/3660e2c78ea409d6c483a215858fb3af52cd0ed3.1757423202.git.leonro@nvidia.com --- kernel/dma/mapping.c | 26 +++++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index e47bcf7cc43d..95eab531e227 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -158,6 +158,7 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page, { const struct dma_map_ops *ops = get_dma_ops(dev); phys_addr_t phys = page_to_phys(page) + offset; + bool is_mmio = attrs & DMA_ATTR_MMIO; dma_addr_t addr; BUG_ON(!valid_dma_direction(dir)); @@ -166,14 +167,25 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page, return DMA_MAPPING_ERROR; if (dma_map_direct(dev, ops) || - arch_dma_map_phys_direct(dev, phys + size)) + (!is_mmio && arch_dma_map_phys_direct(dev, phys + size))) addr = dma_direct_map_phys(dev, phys, size, dir, attrs); else if (use_dma_iommu(dev)) addr = iommu_dma_map_phys(dev, phys, size, dir, attrs); - else + else if (is_mmio) { + if (!ops->map_resource) + return DMA_MAPPING_ERROR; + + addr = ops->map_resource(dev, phys, size, dir, attrs); + } else { + /* + * The dma_ops API contract for ops->map_page() requires + * kmappable memory, while ops->map_resource() does not. + */ addr = ops->map_page(dev, page, offset, size, dir, attrs); + } - kmsan_handle_dma(phys, size, dir); + if (!is_mmio) + kmsan_handle_dma(phys, size, dir); trace_dma_map_phys(dev, phys, addr, size, dir, attrs); debug_dma_map_phys(dev, phys, size, dir, addr, attrs); @@ -185,14 +197,18 @@ void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { const struct dma_map_ops *ops = get_dma_ops(dev); + bool is_mmio = attrs & DMA_ATTR_MMIO; BUG_ON(!valid_dma_direction(dir)); if (dma_map_direct(dev, ops) || - arch_dma_unmap_phys_direct(dev, addr + size)) + (!is_mmio && arch_dma_unmap_phys_direct(dev, addr + size))) dma_direct_unmap_phys(dev, addr, size, dir, attrs); else if (use_dma_iommu(dev)) iommu_dma_unmap_phys(dev, addr, size, dir, attrs); - else + else if (is_mmio) { + if (ops->unmap_resource) + ops->unmap_resource(dev, addr, size, dir, attrs); + } else ops->unmap_page(dev, addr, size, dir, attrs); trace_dma_unmap_phys(dev, addr, size, dir, attrs); debug_dma_unmap_phys(dev, addr, size, dir); -- cgit v1.2.3 From f7326196a781622b33bfbdabb00f5e72b5fb5679 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 9 Sep 2025 16:27:39 +0300 Subject: dma-mapping: export new dma_*map_phys() interface Introduce new DMA mapping functions dma_map_phys() and dma_unmap_phys() that operate directly on physical addresses instead of page+offset parameters. This provides a more efficient interface for drivers that already have physical addresses available. The new functions are implemented as the primary mapping layer, with the existing dma_map_page_attrs()/dma_map_resource() and dma_unmap_page_attrs()/dma_unmap_resource() functions converted to simple wrappers around the phys-based implementations. In case dma_map_page_attrs(), the struct page is converted to physical address with help of page_to_phys() function and dma_map_resource() provides physical address as is together with addition of DMA_ATTR_MMIO attribute. The old page-based API is preserved in mapping.c to ensure that existing code won't be affected by changing EXPORT_SYMBOL to EXPORT_SYMBOL_GPL variant for dma_*map_phys(). Reviewed-by: Jason Gunthorpe Reviewed-by: Keith Busch Signed-off-by: Leon Romanovsky Signed-off-by: Marek Szyprowski Link: https://lore.kernel.org/r/54cc52af91777906bbe4a386113437ba0bcfba9c.1757423202.git.leonro@nvidia.com --- kernel/dma/debug.c | 43 -------------------------------- kernel/dma/debug.h | 21 ---------------- kernel/dma/direct.c | 16 ------------ kernel/dma/mapping.c | 69 ++++++++++++++++++++++++++++------------------------ 4 files changed, 37 insertions(+), 112 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index b275db9ca6a0..1e5c64cb6a42 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -38,7 +38,6 @@ enum { dma_debug_single, dma_debug_sg, dma_debug_coherent, - dma_debug_resource, dma_debug_noncoherent, dma_debug_phy, }; @@ -142,7 +141,6 @@ static const char *type2name[] = { [dma_debug_single] = "single", [dma_debug_sg] = "scatter-gather", [dma_debug_coherent] = "coherent", - [dma_debug_resource] = "resource", [dma_debug_noncoherent] = "noncoherent", [dma_debug_phy] = "phy", }; @@ -1446,47 +1444,6 @@ void debug_dma_free_coherent(struct device *dev, size_t size, check_unmap(&ref); } -void debug_dma_map_resource(struct device *dev, phys_addr_t addr, size_t size, - int direction, dma_addr_t dma_addr, - unsigned long attrs) -{ - struct dma_debug_entry *entry; - - if (unlikely(dma_debug_disabled())) - return; - - entry = dma_entry_alloc(); - if (!entry) - return; - - entry->type = dma_debug_resource; - entry->dev = dev; - entry->paddr = addr; - entry->size = size; - entry->dev_addr = dma_addr; - entry->direction = direction; - entry->map_err_type = MAP_ERR_NOT_CHECKED; - - add_dma_entry(entry, attrs); -} - -void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr, - size_t size, int direction) -{ - struct dma_debug_entry ref = { - .type = dma_debug_resource, - .dev = dev, - .dev_addr = dma_addr, - .size = size, - .direction = direction, - }; - - if (unlikely(dma_debug_disabled())) - return; - - check_unmap(&ref); -} - void debug_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size, int direction) { diff --git a/kernel/dma/debug.h b/kernel/dma/debug.h index bedae973e725..da7be0bddcf6 100644 --- a/kernel/dma/debug.h +++ b/kernel/dma/debug.h @@ -30,14 +30,6 @@ extern void debug_dma_alloc_coherent(struct device *dev, size_t size, extern void debug_dma_free_coherent(struct device *dev, size_t size, void *virt, dma_addr_t addr); -extern void debug_dma_map_resource(struct device *dev, phys_addr_t addr, - size_t size, int direction, - dma_addr_t dma_addr, - unsigned long attrs); - -extern void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr, - size_t size, int direction); - extern void debug_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size, int direction); @@ -95,19 +87,6 @@ static inline void debug_dma_free_coherent(struct device *dev, size_t size, { } -static inline void debug_dma_map_resource(struct device *dev, phys_addr_t addr, - size_t size, int direction, - dma_addr_t dma_addr, - unsigned long attrs) -{ -} - -static inline void debug_dma_unmap_resource(struct device *dev, - dma_addr_t dma_addr, size_t size, - int direction) -{ -} - static inline void debug_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size, int direction) diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index ba7524f169bc..1f9ee9759426 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -497,22 +497,6 @@ out_unmap: return ret; } -dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir, unsigned long attrs) -{ - dma_addr_t dma_addr = paddr; - - if (unlikely(!dma_capable(dev, dma_addr, size, false))) { - dev_err_once(dev, - "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n", - &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit); - WARN_ON_ONCE(1); - return DMA_MAPPING_ERROR; - } - - return dma_addr; -} - int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs) diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 95eab531e227..fe7472f13b10 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -152,12 +152,10 @@ static inline bool dma_map_direct(struct device *dev, return dma_go_direct(dev, *dev->dma_mask, ops); } -dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page, - size_t offset, size_t size, enum dma_data_direction dir, - unsigned long attrs) +dma_addr_t dma_map_phys(struct device *dev, phys_addr_t phys, size_t size, + enum dma_data_direction dir, unsigned long attrs) { const struct dma_map_ops *ops = get_dma_ops(dev); - phys_addr_t phys = page_to_phys(page) + offset; bool is_mmio = attrs & DMA_ATTR_MMIO; dma_addr_t addr; @@ -177,6 +175,9 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page, addr = ops->map_resource(dev, phys, size, dir, attrs); } else { + struct page *page = phys_to_page(phys); + size_t offset = offset_in_page(phys); + /* * The dma_ops API contract for ops->map_page() requires * kmappable memory, while ops->map_resource() does not. @@ -191,9 +192,26 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page, return addr; } +EXPORT_SYMBOL_GPL(dma_map_phys); + +dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page, + size_t offset, size_t size, enum dma_data_direction dir, + unsigned long attrs) +{ + phys_addr_t phys = page_to_phys(page) + offset; + + if (unlikely(attrs & DMA_ATTR_MMIO)) + return DMA_MAPPING_ERROR; + + if (IS_ENABLED(CONFIG_DMA_API_DEBUG) && + WARN_ON_ONCE(is_zone_device_page(page))) + return DMA_MAPPING_ERROR; + + return dma_map_phys(dev, phys, size, dir, attrs); +} EXPORT_SYMBOL(dma_map_page_attrs); -void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size, +void dma_unmap_phys(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { const struct dma_map_ops *ops = get_dma_ops(dev); @@ -213,6 +231,16 @@ void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size, trace_dma_unmap_phys(dev, addr, size, dir, attrs); debug_dma_unmap_phys(dev, addr, size, dir); } +EXPORT_SYMBOL_GPL(dma_unmap_phys); + +void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size, + enum dma_data_direction dir, unsigned long attrs) +{ + if (unlikely(attrs & DMA_ATTR_MMIO)) + return; + + dma_unmap_phys(dev, addr, size, dir, attrs); +} EXPORT_SYMBOL(dma_unmap_page_attrs); static int __dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, @@ -338,41 +366,18 @@ EXPORT_SYMBOL(dma_unmap_sg_attrs); dma_addr_t dma_map_resource(struct device *dev, phys_addr_t phys_addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { - const struct dma_map_ops *ops = get_dma_ops(dev); - dma_addr_t addr = DMA_MAPPING_ERROR; - - BUG_ON(!valid_dma_direction(dir)); - - if (WARN_ON_ONCE(!dev->dma_mask)) + if (IS_ENABLED(CONFIG_DMA_API_DEBUG) && + WARN_ON_ONCE(pfn_valid(PHYS_PFN(phys_addr)))) return DMA_MAPPING_ERROR; - if (dma_map_direct(dev, ops)) - addr = dma_direct_map_resource(dev, phys_addr, size, dir, attrs); - else if (use_dma_iommu(dev)) - addr = iommu_dma_map_resource(dev, phys_addr, size, dir, attrs); - else if (ops->map_resource) - addr = ops->map_resource(dev, phys_addr, size, dir, attrs); - - trace_dma_map_resource(dev, phys_addr, addr, size, dir, attrs); - debug_dma_map_resource(dev, phys_addr, size, dir, addr, attrs); - return addr; + return dma_map_phys(dev, phys_addr, size, dir, attrs | DMA_ATTR_MMIO); } EXPORT_SYMBOL(dma_map_resource); void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { - const struct dma_map_ops *ops = get_dma_ops(dev); - - BUG_ON(!valid_dma_direction(dir)); - if (dma_map_direct(dev, ops)) - ; /* nothing to do: uncached and no swiotlb */ - else if (use_dma_iommu(dev)) - iommu_dma_unmap_resource(dev, addr, size, dir, attrs); - else if (ops->unmap_resource) - ops->unmap_resource(dev, addr, size, dir, attrs); - trace_dma_unmap_resource(dev, addr, size, dir, attrs); - debug_dma_unmap_resource(dev, addr, size, dir); + dma_unmap_phys(dev, addr, size, dir, attrs | DMA_ATTR_MMIO); } EXPORT_SYMBOL(dma_unmap_resource); -- cgit v1.2.3