Merge tag 'dma-mapping-7.0-2026-03-25' into dma-mapping-for-next

dma-mapping fixes for Linux 7.0

A set of fixes for DMA-mapping subsystem, which resolve false-positive
warnings from KMSAN and DMA-API debug (Shigeru Yoshida and Leon
Romanovsky) as well as a simple build fix (Miguel Ojeda).

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>

Author: mszyprow

Documentation/core-api/dma-attributes.rst

@@ -149,11 +149,33 @@ For architectures that require cache flushing for DMA coherence
 DMA_ATTR_MMIO will not perform any cache flushing. The address
 provided must never be mapped cacheable into the CPU.
 
-DMA_ATTR_CPU_CACHE_CLEAN
-------------------------
-
-This attribute indicates the CPU will not dirty any cacheline overlapping this
-DMA_FROM_DEVICE/DMA_BIDIRECTIONAL buffer while it is mapped. This allows
-multiple small buffers to safely share a cacheline without risk of data
-corruption, suppressing DMA debug warnings about overlapping mappings.
-All mappings sharing a cacheline should have this attribute.
+DMA_ATTR_DEBUGGING_IGNORE_CACHELINES
+------------------------------------
+
+This attribute indicates that CPU cache lines may overlap for buffers mapped
+with DMA_FROM_DEVICE or DMA_BIDIRECTIONAL.
+
+Such overlap may occur when callers map multiple small buffers that reside
+within the same cache line. In this case, callers must guarantee that the CPU
+will not dirty these cache lines after the mappings are established. When this
+condition is met, multiple buffers can safely share a cache line without risking
+data corruption.
+
+All mappings that share a cache line must set this attribute to suppress DMA
+debug warnings about overlapping mappings.
+
+DMA_ATTR_REQUIRE_COHERENT
+-------------------------
+
+DMA mapping requests with the DMA_ATTR_REQUIRE_COHERENT fail on any
+system where SWIOTLB or cache management is required. This should only
+be used to support uAPI designs that require continuous HW DMA
+coherence with userspace processes, for example RDMA and DRM. At a
+minimum the memory being mapped must be userspace memory from
+pin_user_pages() or similar.
+
+Drivers should consider using dma_mmap_pages() instead of this
+interface when building their uAPIs, when possible.
+
+It must never be used in an in-kernel driver that only works with
+kernel memory.

arch/sparc/kernel/iommu.c

@@ -312,6 +312,8 @@ static dma_addr_t dma_4u_map_phys(struct device *dev, phys_addr_t phys,
 	if (direction != DMA_TO_DEVICE)
 		iopte_protection |= IOPTE_WRITE;
 
+	phys &= IO_PAGE_MASK;
+
 	for (i = 0; i < npages; i++, base++, phys += IO_PAGE_SIZE)
 		iopte_val(*base) = iopte_protection | phys;
 

arch/sparc/kernel/pci_sun4v.c

@@ -410,6 +410,8 @@ static dma_addr_t dma_4v_map_phys(struct device *dev, phys_addr_t phys,
 
 	iommu_batch_start(dev, prot, entry);
 
+	phys &= IO_PAGE_MASK;
+
 	for (i = 0; i < npages; i++, phys += IO_PAGE_SIZE) {
 		long err = iommu_batch_add(phys, mask);
 		if (unlikely(err < 0L))

drivers/infiniband/core/umem.c

@@ -55,7 +55,8 @@ static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int d
 
 	if (dirty)
 		ib_dma_unmap_sgtable_attrs(dev, &umem->sgt_append.sgt,
-					   DMA_BIDIRECTIONAL, 0);
+					   DMA_BIDIRECTIONAL,
+					   DMA_ATTR_REQUIRE_COHERENT);
 
 	for_each_sgtable_sg(&umem->sgt_append.sgt, sg, i) {
 		unpin_user_page_range_dirty_lock(sg_page(sg),
@@ -169,7 +170,7 @@ struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr,
 	unsigned long lock_limit;
 	unsigned long new_pinned;
 	unsigned long cur_base;
-	unsigned long dma_attr = 0;
+	unsigned long dma_attr = DMA_ATTR_REQUIRE_COHERENT;
 	struct mm_struct *mm;
 	unsigned long npages;
 	int pinned, ret;

drivers/iommu/dma-iommu.c

@@ -1219,7 +1219,7 @@ dma_addr_t iommu_dma_map_phys(struct device *dev, phys_addr_t phys, size_t size,
 	 */
 	if (dev_use_swiotlb(dev, size, dir) &&
 	    iova_unaligned(iovad, phys, size)) {
-		if (attrs & DMA_ATTR_MMIO)
+		if (attrs & (DMA_ATTR_MMIO | DMA_ATTR_REQUIRE_COHERENT))
 			return DMA_MAPPING_ERROR;
 
 		phys = iommu_dma_map_swiotlb(dev, phys, size, dir, attrs);
@@ -1233,7 +1233,8 @@ dma_addr_t iommu_dma_map_phys(struct device *dev, phys_addr_t phys, size_t size,
 	}
 
 	iova = __iommu_dma_map(dev, phys, size, prot, dma_mask);
-	if (iova == DMA_MAPPING_ERROR && !(attrs & DMA_ATTR_MMIO))
+	if (iova == DMA_MAPPING_ERROR &&
+	    !(attrs & (DMA_ATTR_MMIO | DMA_ATTR_REQUIRE_COHERENT)))
 		swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs);
 	return iova;
 }
@@ -1243,7 +1244,7 @@ void iommu_dma_unmap_phys(struct device *dev, dma_addr_t dma_handle,
 {
 	phys_addr_t phys;
 
-	if (attrs & DMA_ATTR_MMIO) {
+	if (attrs & (DMA_ATTR_MMIO | DMA_ATTR_REQUIRE_COHERENT)) {
 		__iommu_dma_unmap(dev, dma_handle, size);
 		return;
 	}
@@ -1957,9 +1958,21 @@ int dma_iova_link(struct device *dev, struct dma_iova_state *state,
 	if (WARN_ON_ONCE(iova_start_pad && offset > 0))
 		return -EIO;
 
+	/*
+	 * DMA_IOVA_USE_SWIOTLB is set on state after some entry
+	 * took SWIOTLB path, which we were supposed to prevent
+	 * for DMA_ATTR_REQUIRE_COHERENT attribute.
+	 */
+	if (WARN_ON_ONCE((state->__size & DMA_IOVA_USE_SWIOTLB) &&
+			 (attrs & DMA_ATTR_REQUIRE_COHERENT)))
+		return -EOPNOTSUPP;
+
+	if (!dev_is_dma_coherent(dev) && (attrs & DMA_ATTR_REQUIRE_COHERENT))
+		return -EOPNOTSUPP;
+
 	if (dev_use_swiotlb(dev, size, dir) &&
 	    iova_unaligned(iovad, phys, size)) {
-		if (attrs & DMA_ATTR_MMIO)
+		if (attrs & (DMA_ATTR_MMIO | DMA_ATTR_REQUIRE_COHERENT))
 			return -EPERM;
 
 		return iommu_dma_iova_link_swiotlb(dev, state, phys, offset,

drivers/virtio/virtio_ring.c

@@ -2912,10 +2912,10 @@ EXPORT_SYMBOL_GPL(virtqueue_add_inbuf);
  * @data: the token identifying the buffer.
  * @gfp: how to do memory allocations (if necessary).
  *
- * Same as virtqueue_add_inbuf but passes DMA_ATTR_CPU_CACHE_CLEAN to indicate
- * that the CPU will not dirty any cacheline overlapping this buffer while it
- * is available, and to suppress overlapping cacheline warnings in DMA debug
- * builds.
+ * Same as virtqueue_add_inbuf but passes DMA_ATTR_DEBUGGING_IGNORE_CACHELINES
+ * to indicate that the CPU will not dirty any cacheline overlapping this buffer
+ * while it is available, and to suppress overlapping cacheline warnings in DMA
+ * debug builds.
  *
  * Caller must ensure we don't call this with other virtqueue operations
  * at the same time (except where noted).
@@ -2928,7 +2928,7 @@ int virtqueue_add_inbuf_cache_clean(struct virtqueue *vq,
 				    gfp_t gfp)
 {
 	return virtqueue_add(vq, &sg, num, 0, 1, data, NULL, false, gfp,
-			     DMA_ATTR_CPU_CACHE_CLEAN);
+			     DMA_ATTR_DEBUGGING_IGNORE_CACHELINES);
 }
 EXPORT_SYMBOL_GPL(virtqueue_add_inbuf_cache_clean);
 

include/linux/dma-mapping.h

@@ -80,11 +80,18 @@
 #define DMA_ATTR_MMIO		(1UL << 10)
 
 /*
- * DMA_ATTR_CPU_CACHE_CLEAN: Indicates the CPU will not dirty any cacheline
- * overlapping this buffer while it is mapped for DMA. All mappings sharing
- * a cacheline must have this attribute for this to be considered safe.
+ * DMA_ATTR_DEBUGGING_IGNORE_CACHELINES: Indicates the CPU cache line can be
+ * overlapped. All mappings sharing a cacheline must have this attribute for
+ * this to be considered safe.
  */
-#define DMA_ATTR_CPU_CACHE_CLEAN	(1UL << 11)
+#define DMA_ATTR_DEBUGGING_IGNORE_CACHELINES	(1UL << 11)
+
+/*
+ * DMA_ATTR_REQUIRE_COHERENT: Indicates that DMA coherency is required.
+ * All mappings that carry this attribute can't work with SWIOTLB and cache
+ * flushing.
+ */
+#define DMA_ATTR_REQUIRE_COHERENT	(1UL << 12)
 
 /*
  * A dma_addr_t can hold any valid DMA or bus address for the platform.  It can
@@ -248,8 +255,8 @@ static inline void *dma_alloc_attrs(struct device *dev, size_t size,
 {
 	return NULL;
 }
-static void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr,
-		dma_addr_t dma_handle, unsigned long attrs)
+static inline void dma_free_attrs(struct device *dev, size_t size,
+		void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs)
 {
 }
 static inline void *dmam_alloc_attrs(struct device *dev, size_t size,

include/trace/events/dma.h

@@ -32,7 +32,9 @@ TRACE_DEFINE_ENUM(DMA_NONE);
 		{ DMA_ATTR_ALLOC_SINGLE_PAGES, "ALLOC_SINGLE_PAGES" }, \
 		{ DMA_ATTR_NO_WARN, "NO_WARN" }, \
 		{ DMA_ATTR_PRIVILEGED, "PRIVILEGED" }, \
-		{ DMA_ATTR_MMIO, "MMIO" })
+		{ DMA_ATTR_MMIO, "MMIO" }, \
+		{ DMA_ATTR_DEBUGGING_IGNORE_CACHELINES, "CACHELINES_OVERLAP" }, \
+		{ DMA_ATTR_REQUIRE_COHERENT, "REQUIRE_COHERENT" })
 
 DECLARE_EVENT_CLASS(dma_map,
 	TP_PROTO(struct device *dev, phys_addr_t phys_addr, dma_addr_t dma_addr,

kernel/dma/debug.c

@@ -453,7 +453,7 @@ static int active_cacheline_set_overlap(phys_addr_t cln, int overlap)
 	return overlap;
 }
 
-static void active_cacheline_inc_overlap(phys_addr_t cln)
+static void active_cacheline_inc_overlap(phys_addr_t cln, bool is_cache_clean)
 {
 	int overlap = active_cacheline_read_overlap(cln);
 
@@ -462,7 +462,7 @@ static void active_cacheline_inc_overlap(phys_addr_t cln)
 	/* If we overflowed the overlap counter then we're potentially
 	 * leaking dma-mappings.
 	 */
-	WARN_ONCE(overlap > ACTIVE_CACHELINE_MAX_OVERLAP,
+	WARN_ONCE(!is_cache_clean && overlap > ACTIVE_CACHELINE_MAX_OVERLAP,
 		  pr_fmt("exceeded %d overlapping mappings of cacheline %pa\n"),
 		  ACTIVE_CACHELINE_MAX_OVERLAP, &cln);
 }
@@ -495,7 +495,7 @@ static int active_cacheline_insert(struct dma_debug_entry *entry,
 	if (rc == -EEXIST) {
 		struct dma_debug_entry *existing;
 
-		active_cacheline_inc_overlap(cln);
+		active_cacheline_inc_overlap(cln, entry->is_cache_clean);
 		existing = radix_tree_lookup(&dma_active_cacheline, cln);
 		/* A lookup failure here after we got -EEXIST is unexpected. */
 		WARN_ON(!existing);
@@ -601,7 +601,8 @@ static void add_dma_entry(struct dma_debug_entry *entry, unsigned long attrs)
 	unsigned long flags;
 	int rc;
 
-	entry->is_cache_clean = !!(attrs & DMA_ATTR_CPU_CACHE_CLEAN);
+	entry->is_cache_clean = attrs & (DMA_ATTR_DEBUGGING_IGNORE_CACHELINES |
+					 DMA_ATTR_REQUIRE_COHERENT);
 
 	bucket = get_hash_bucket(entry, &flags);
 	hash_bucket_add(bucket, entry);

kernel/dma/direct.h

@@ -89,8 +89,8 @@ static inline dma_addr_t dma_direct_map_phys(struct device *dev,
 	dma_addr_t dma_addr;
 
 	if (is_swiotlb_force_bounce(dev)) {
-		if (attrs & DMA_ATTR_MMIO)
-			goto err_overflow;
+		if (attrs & (DMA_ATTR_MMIO | DMA_ATTR_REQUIRE_COHERENT))
+			return DMA_MAPPING_ERROR;
 
 		return swiotlb_map(dev, phys, size, dir, attrs);
 	}
@@ -103,7 +103,8 @@ static inline dma_addr_t dma_direct_map_phys(struct device *dev,
 		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))
+			if (is_swiotlb_active(dev) &&
+			    !(attrs & DMA_ATTR_REQUIRE_COHERENT))
 				return swiotlb_map(dev, phys, size, dir, attrs);
 
 			goto err_overflow;
@@ -132,7 +133,7 @@ static inline void dma_direct_unmap_phys(struct device *dev, dma_addr_t addr,
 {
 	phys_addr_t phys;
 
-	if (attrs & DMA_ATTR_MMIO)
+	if (attrs & (DMA_ATTR_MMIO | DMA_ATTR_REQUIRE_COHERENT))
 		/* nothing to do: uncached and no swiotlb */
 		return;