Merge tag 'dma-mapping-6.16-2025-05-26' of git://git.kernel.org/pub/scm/linux/kernel/git/mszyprowski/linux

Pull dma-mapping updates from Marek Szyprowski:
 "New two step DMA mapping API, which is is a first step to a long path
  to provide alternatives to scatterlist and to remove hacks, abuses and
  design mistakes related to scatterlists.

  This new approach optimizes some calls to DMA-IOMMU layer and cache
  maintenance by batching them, reduces memory usage as it is no need to
  store mapped DMA addresses to unmap them, and reduces some function
  call overhead.  It is a combination effort of many people, lead and
  developed by Christoph Hellwig and Leon Romanovsky"

* tag 'dma-mapping-6.16-2025-05-26' of git://git.kernel.org/pub/scm/linux/kernel/git/mszyprowski/linux:
  docs: core-api: document the IOVA-based API
  dma-mapping: add a dma_need_unmap helper
  dma-mapping: Implement link/unlink ranges API
  iommu/dma: Factor out a iommu_dma_map_swiotlb helper
  dma-mapping: Provide an interface to allow allocate IOVA
  iommu: add kernel-doc for iommu_unmap_fast
  iommu: generalize the batched sync after map interface
  dma-mapping: move the PCI P2PDMA mapping helpers to pci-p2pdma.h
  PCI/P2PDMA: Refactor the p2pdma mapping helpers

10 files changed, 764 insertions, 201 deletions

diff --git a/Documentation/core-api/dma-api.rst b/Documentation/core-api/dma-api.rst
index 8e3cce3d0a23..2ad08517e626 100644
--- a/Documentation/core-api/dma-api.rst
+++ b/Documentation/core-api/dma-api.rst
@@ -530,6 +530,77 @@ routines, e.g.:::
 		....
 	}
 
+Part Ie - IOVA-based DMA mappings
+---------------------------------
+
+These APIs allow a very efficient mapping when using an IOMMU.  They are an
+optional path that requires extra code and are only recommended for drivers
+where DMA mapping performance, or the space usage for storing the DMA addresses
+matter.  All the considerations from the previous section apply here as well.
+
+::
+
+    bool dma_iova_try_alloc(struct device *dev, struct dma_iova_state *state,
+		phys_addr_t phys, size_t size);
+
+Is used to try to allocate IOVA space for mapping operation.  If it returns
+false this API can't be used for the given device and the normal streaming
+DMA mapping API should be used.  The ``struct dma_iova_state`` is allocated
+by the driver and must be kept around until unmap time.
+
+::
+
+    static inline bool dma_use_iova(struct dma_iova_state *state)
+
+Can be used by the driver to check if the IOVA-based API is used after a
+call to dma_iova_try_alloc.  This can be useful in the unmap path.
+
+::
+
+    int dma_iova_link(struct device *dev, struct dma_iova_state *state,
+		phys_addr_t phys, size_t offset, size_t size,
+		enum dma_data_direction dir, unsigned long attrs);
+
+Is used to link ranges to the IOVA previously allocated.  The start of all
+but the first call to dma_iova_link for a given state must be aligned
+to the DMA merge boundary returned by ``dma_get_merge_boundary())``, and
+the size of all but the last range must be aligned to the DMA merge boundary
+as well.
+
+::
+
+    int dma_iova_sync(struct device *dev, struct dma_iova_state *state,
+		size_t offset, size_t size);
+
+Must be called to sync the IOMMU page tables for IOVA-range mapped by one or
+more calls to ``dma_iova_link()``.
+
+For drivers that use a one-shot mapping, all ranges can be unmapped and the
+IOVA freed by calling:
+
+::
+
+   void dma_iova_destroy(struct device *dev, struct dma_iova_state *state,
+		size_t mapped_len, enum dma_data_direction dir,
+                unsigned long attrs);
+
+Alternatively drivers can dynamically manage the IOVA space by unmapping
+and mapping individual regions.  In that case
+
+::
+
+    void dma_iova_unlink(struct device *dev, struct dma_iova_state *state,
+		size_t offset, size_t size, enum dma_data_direction dir,
+		unsigned long attrs);
+
+is used to unmap a range previously mapped, and
+
+::
+
+   void dma_iova_free(struct device *dev, struct dma_iova_state *state);
+
+is used to free the IOVA space.  All regions must have been unmapped using
+``dma_iova_unlink()`` before calling ``dma_iova_free()``.
 
 Part II - Non-coherent DMA allocations
 --------------------------------------
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index a775e4dbe06f..98f7205ec8fb 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -27,6 +27,7 @@
 #include <linux/msi.h>
 #include <linux/of_iommu.h>
 #include <linux/pci.h>
+#include <linux/pci-p2pdma.h>
 #include <linux/scatterlist.h>
 #include <linux/spinlock.h>
 #include <linux/swiotlb.h>
@@ -1137,6 +1138,54 @@ void iommu_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sgl,
 			arch_sync_dma_for_device(sg_phys(sg), sg->length, dir);
 }
 
+static phys_addr_t iommu_dma_map_swiotlb(struct device *dev, phys_addr_t phys,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
+	struct iova_domain *iovad = &domain->iova_cookie->iovad;
+
+	if (!is_swiotlb_active(dev)) {
+		dev_warn_once(dev, "DMA bounce buffers are inactive, unable to map unaligned transaction.\n");
+		return (phys_addr_t)DMA_MAPPING_ERROR;
+	}
+
+	trace_swiotlb_bounced(dev, phys, size);
+
+	phys = swiotlb_tbl_map_single(dev, phys, size, iova_mask(iovad), dir,
+			attrs);
+
+	/*
+	 * 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 (phys != (phys_addr_t)DMA_MAPPING_ERROR && 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);
+
+		/* Post-padding */
+		start = virt + size;
+		memset((void *)start, 0, iova_align(iovad, start) - start);
+	}
+
+	return phys;
+}
+
+/*
+ * Checks if a physical buffer has unaligned boundaries with respect to
+ * the IOMMU granule. Returns non-zero if either the start or end
+ * address is not aligned to the granule boundary.
+ */
+static inline size_t iova_unaligned(struct iova_domain *iovad, phys_addr_t phys,
+				    size_t size)
+{
+	return iova_offset(iovad, phys | size);
+}
+
 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)
@@ -1150,42 +1199,14 @@ dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
 	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 both the physical buffer start address and size are page aligned,
+	 * we don't need to use a bounce page.
 	 */
 	if (dev_use_swiotlb(dev, size, dir) &&
-	    iova_offset(iovad, phys | size)) {
-		if (!is_swiotlb_active(dev)) {
-			dev_warn_once(dev, "DMA bounce buffers are inactive, unable to map unaligned transaction.\n");
+	    iova_unaligned(iovad, phys, size)) {
+		phys = iommu_dma_map_swiotlb(dev, phys, size, dir, attrs);
+		if (phys == (phys_addr_t)DMA_MAPPING_ERROR)
 			return DMA_MAPPING_ERROR;
-		}
-
-		trace_swiotlb_bounced(dev, phys, size);
-
-		phys = swiotlb_tbl_map_single(dev, phys, size,
-					      iova_mask(iovad), dir, attrs);
-
-		if (phys == DMA_MAPPING_ERROR)
-			return DMA_MAPPING_ERROR;
-
-		/*
-		 * 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);
-
-			/* Post-padding */
-			start = virt + size;
-			memset((void *)start, 0,
-			       iova_align(iovad, start) - start);
-		}
 	}
 
 	if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
@@ -1359,7 +1380,6 @@ int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 	struct scatterlist *s, *prev = NULL;
 	int prot = dma_info_to_prot(dir, dev_is_dma_coherent(dev), attrs);
 	struct pci_p2pdma_map_state p2pdma_state = {};
-	enum pci_p2pdma_map_type map;
 	dma_addr_t iova;
 	size_t iova_len = 0;
 	unsigned long mask = dma_get_seg_boundary(dev);
@@ -1389,28 +1409,30 @@ int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 		size_t s_length = s->length;
 		size_t pad_len = (mask - iova_len + 1) & mask;
 
-		if (is_pci_p2pdma_page(sg_page(s))) {
-			map = pci_p2pdma_map_segment(&p2pdma_state, dev, s);
-			switch (map) {
-			case PCI_P2PDMA_MAP_BUS_ADDR:
-				/*
-				 * iommu_map_sg() will skip this segment as
-				 * it is marked as a bus address,
-				 * __finalise_sg() will copy the dma address
-				 * into the output segment.
-				 */
-				continue;
-			case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE:
-				/*
-				 * Mapping through host bridge should be
-				 * mapped with regular IOVAs, thus we
-				 * do nothing here and continue below.
-				 */
-				break;
-			default:
-				ret = -EREMOTEIO;
-				goto out_restore_sg;
-			}
+		switch (pci_p2pdma_state(&p2pdma_state, dev, sg_page(s))) {
+		case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE:
+			/*
+			 * Mapping through host bridge should be mapped with
+			 * regular IOVAs, thus we do nothing here and continue
+			 * below.
+			 */
+			break;
+		case PCI_P2PDMA_MAP_NONE:
+			break;
+		case PCI_P2PDMA_MAP_BUS_ADDR:
+			/*
+			 * iommu_map_sg() will skip this segment as it is marked
+			 * as a bus address, __finalise_sg() will copy the dma
+			 * address into the output segment.
+			 */
+			s->dma_address = pci_p2pdma_bus_addr_map(&p2pdma_state,
+						sg_phys(s));
+			sg_dma_len(s) = sg->length;
+			sg_dma_mark_bus_address(s);
+			continue;
+		default:
+			ret = -EREMOTEIO;
+			goto out_restore_sg;
 		}
 
 		sg_dma_address(s) = s_iova_off;
@@ -1721,6 +1743,354 @@ size_t iommu_dma_max_mapping_size(struct device *dev)
 	return SIZE_MAX;
 }
 
+/**
+ * dma_iova_try_alloc - Try to allocate an IOVA space
+ * @dev: Device to allocate the IOVA space for
+ * @state: IOVA state
+ * @phys: physical address
+ * @size: IOVA size
+ *
+ * Check if @dev supports the IOVA-based DMA API, and if yes allocate IOVA space
+ * for the given base address and size.
+ *
+ * Note: @phys is only used to calculate the IOVA alignment. Callers that always
+ * do PAGE_SIZE aligned transfers can safely pass 0 here.
+ *
+ * Returns %true if the IOVA-based DMA API can be used and IOVA space has been
+ * allocated, or %false if the regular DMA API should be used.
+ */
+bool dma_iova_try_alloc(struct device *dev, struct dma_iova_state *state,
+		phys_addr_t phys, size_t size)
+{
+	struct iommu_dma_cookie *cookie;
+	struct iommu_domain *domain;
+	struct iova_domain *iovad;
+	size_t iova_off;
+	dma_addr_t addr;
+
+	memset(state, 0, sizeof(*state));
+	if (!use_dma_iommu(dev))
+		return false;
+
+	domain = iommu_get_dma_domain(dev);
+	cookie = domain->iova_cookie;
+	iovad = &cookie->iovad;
+	iova_off = iova_offset(iovad, phys);
+
+	if (static_branch_unlikely(&iommu_deferred_attach_enabled) &&
+	    iommu_deferred_attach(dev, iommu_get_domain_for_dev(dev)))
+		return false;
+
+	if (WARN_ON_ONCE(!size))
+		return false;
+
+	/*
+	 * DMA_IOVA_USE_SWIOTLB is flag which is set by dma-iommu
+	 * internals, make sure that caller didn't set it and/or
+	 * didn't use this interface to map SIZE_MAX.
+	 */
+	if (WARN_ON_ONCE((u64)size & DMA_IOVA_USE_SWIOTLB))
+		return false;
+
+	addr = iommu_dma_alloc_iova(domain,
+			iova_align(iovad, size + iova_off),
+			dma_get_mask(dev), dev);
+	if (!addr)
+		return false;
+
+	state->addr = addr + iova_off;
+	state->__size = size;
+	return true;
+}
+EXPORT_SYMBOL_GPL(dma_iova_try_alloc);
+
+/**
+ * dma_iova_free - Free an IOVA space
+ * @dev: Device to free the IOVA space for
+ * @state: IOVA state
+ *
+ * Undoes a successful dma_try_iova_alloc().
+ *
+ * Note that all dma_iova_link() calls need to be undone first.  For callers
+ * that never call dma_iova_unlink(), dma_iova_destroy() can be used instead
+ * which unlinks all ranges and frees the IOVA space in a single efficient
+ * operation.
+ */
+void dma_iova_free(struct device *dev, struct dma_iova_state *state)
+{
+	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 iova_start_pad = iova_offset(iovad, state->addr);
+	size_t size = dma_iova_size(state);
+
+	iommu_dma_free_iova(domain, state->addr - iova_start_pad,
+			iova_align(iovad, size + iova_start_pad), NULL);
+}
+EXPORT_SYMBOL_GPL(dma_iova_free);
+
+static int __dma_iova_link(struct device *dev, dma_addr_t addr,
+		phys_addr_t phys, size_t size, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+	bool coherent = dev_is_dma_coherent(dev);
+
+	if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		arch_sync_dma_for_device(phys, size, dir);
+
+	return iommu_map_nosync(iommu_get_dma_domain(dev), addr, phys, size,
+			dma_info_to_prot(dir, coherent, attrs), GFP_ATOMIC);
+}
+
+static int iommu_dma_iova_bounce_and_link(struct device *dev, dma_addr_t addr,
+		phys_addr_t phys, size_t bounce_len,
+		enum dma_data_direction dir, unsigned long attrs,
+		size_t iova_start_pad)
+{
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
+	struct iova_domain *iovad = &domain->iova_cookie->iovad;
+	phys_addr_t bounce_phys;
+	int error;
+
+	bounce_phys = iommu_dma_map_swiotlb(dev, phys, bounce_len, dir, attrs);
+	if (bounce_phys == DMA_MAPPING_ERROR)
+		return -ENOMEM;
+
+	error = __dma_iova_link(dev, addr - iova_start_pad,
+			bounce_phys - iova_start_pad,
+			iova_align(iovad, bounce_len), dir, attrs);
+	if (error)
+		swiotlb_tbl_unmap_single(dev, bounce_phys, bounce_len, dir,
+				attrs);
+	return error;
+}
+
+static int iommu_dma_iova_link_swiotlb(struct device *dev,
+		struct dma_iova_state *state, phys_addr_t phys, size_t offset,
+		size_t size, 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;
+	struct iova_domain *iovad = &cookie->iovad;
+	size_t iova_start_pad = iova_offset(iovad, phys);
+	size_t iova_end_pad = iova_offset(iovad, phys + size);
+	dma_addr_t addr = state->addr + offset;
+	size_t mapped = 0;
+	int error;
+
+	if (iova_start_pad) {
+		size_t bounce_len = min(size, iovad->granule - iova_start_pad);
+
+		error = iommu_dma_iova_bounce_and_link(dev, addr, phys,
+				bounce_len, dir, attrs, iova_start_pad);
+		if (error)
+			return error;
+		state->__size |= DMA_IOVA_USE_SWIOTLB;
+
+		mapped += bounce_len;
+		size -= bounce_len;
+		if (!size)
+			return 0;
+	}
+
+	size -= iova_end_pad;
+	error = __dma_iova_link(dev, addr + mapped, phys + mapped, size, dir,
+			attrs);
+	if (error)
+		goto out_unmap;
+	mapped += size;
+
+	if (iova_end_pad) {
+		error = iommu_dma_iova_bounce_and_link(dev, addr + mapped,
+				phys + mapped, iova_end_pad, dir, attrs, 0);
+		if (error)
+			goto out_unmap;
+		state->__size |= DMA_IOVA_USE_SWIOTLB;
+	}
+
+	return 0;
+
+out_unmap:
+	dma_iova_unlink(dev, state, 0, mapped, dir, attrs);
+	return error;
+}
+
+/**
+ * dma_iova_link - Link a range of IOVA space
+ * @dev: DMA device
+ * @state: IOVA state
+ * @phys: physical address to link
+ * @offset: offset into the IOVA state to map into
+ * @size: size of the buffer
+ * @dir: DMA direction
+ * @attrs: attributes of mapping properties
+ *
+ * Link a range of IOVA space for the given IOVA state without IOTLB sync.
+ * This function is used to link multiple physical addresses in contiguous
+ * IOVA space without performing costly IOTLB sync.
+ *
+ * The caller is responsible to call to dma_iova_sync() to sync IOTLB at
+ * the end of linkage.
+ */
+int dma_iova_link(struct device *dev, struct dma_iova_state *state,
+		phys_addr_t phys, size_t offset, size_t size,
+		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;
+	struct iova_domain *iovad = &cookie->iovad;
+	size_t iova_start_pad = iova_offset(iovad, phys);
+
+	if (WARN_ON_ONCE(iova_start_pad && offset > 0))
+		return -EIO;
+
+	if (dev_use_swiotlb(dev, size, dir) &&
+	    iova_unaligned(iovad, phys, size))
+		return iommu_dma_iova_link_swiotlb(dev, state, phys, offset,
+				size, dir, attrs);
+
+	return __dma_iova_link(dev, state->addr + offset - iova_start_pad,
+			phys - iova_start_pad,
+			iova_align(iovad, size + iova_start_pad), dir, attrs);
+}
+EXPORT_SYMBOL_GPL(dma_iova_link);
+
+/**
+ * dma_iova_sync - Sync IOTLB
+ * @dev: DMA device
+ * @state: IOVA state
+ * @offset: offset into the IOVA state to sync
+ * @size: size of the buffer
+ *
+ * Sync IOTLB for the given IOVA state. This function should be called on
+ * the IOVA-contiguous range created by one ore more dma_iova_link() calls
+ * to sync the IOTLB.
+ */
+int dma_iova_sync(struct device *dev, struct dma_iova_state *state,
+		size_t offset, size_t size)
+{
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_domain *iovad = &cookie->iovad;
+	dma_addr_t addr = state->addr + offset;
+	size_t iova_start_pad = iova_offset(iovad, addr);
+
+	return iommu_sync_map(domain, addr - iova_start_pad,
+		      iova_align(iovad, size + iova_start_pad));
+}
+EXPORT_SYMBOL_GPL(dma_iova_sync);
+
+static void iommu_dma_iova_unlink_range_slow(struct device *dev,
+		dma_addr_t addr, size_t size, 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;
+	struct iova_domain *iovad = &cookie->iovad;
+	size_t iova_start_pad = iova_offset(iovad, addr);
+	dma_addr_t end = addr + size;
+
+	do {
+		phys_addr_t phys;
+		size_t len;
+
+		phys = iommu_iova_to_phys(domain, addr);
+		if (WARN_ON(!phys))
+			/* Something very horrible happen here */
+			return;
+
+		len = min_t(size_t,
+			end - addr, iovad->granule - iova_start_pad);
+
+		if (!dev_is_dma_coherent(dev) &&
+		    !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+			arch_sync_dma_for_cpu(phys, len, dir);
+
+		swiotlb_tbl_unmap_single(dev, phys, len, dir, attrs);
+
+		addr += len;
+		iova_start_pad = 0;
+	} while (addr < end);
+}
+
+static void __iommu_dma_iova_unlink(struct device *dev,
+		struct dma_iova_state *state, size_t offset, size_t size,
+		enum dma_data_direction dir, unsigned long attrs,
+		bool free_iova)
+{
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_domain *iovad = &cookie->iovad;
+	dma_addr_t addr = state->addr + offset;
+	size_t iova_start_pad = iova_offset(iovad, addr);
+	struct iommu_iotlb_gather iotlb_gather;
+	size_t unmapped;
+
+	if ((state->__size & DMA_IOVA_USE_SWIOTLB) ||
+	    (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)))
+		iommu_dma_iova_unlink_range_slow(dev, addr, size, dir, attrs);
+
+	iommu_iotlb_gather_init(&iotlb_gather);
+	iotlb_gather.queued = free_iova && READ_ONCE(cookie->fq_domain);
+
+	size = iova_align(iovad, size + iova_start_pad);
+	addr -= iova_start_pad;
+	unmapped = iommu_unmap_fast(domain, addr, size, &iotlb_gather);
+	WARN_ON(unmapped != size);
+
+	if (!iotlb_gather.queued)
+		iommu_iotlb_sync(domain, &iotlb_gather);
+	if (free_iova)
+		iommu_dma_free_iova(domain, addr, size, &iotlb_gather);
+}
+
+/**
+ * dma_iova_unlink - Unlink a range of IOVA space
+ * @dev: DMA device
+ * @state: IOVA state
+ * @offset: offset into the IOVA state to unlink
+ * @size: size of the buffer
+ * @dir: DMA direction
+ * @attrs: attributes of mapping properties
+ *
+ * Unlink a range of IOVA space for the given IOVA state.
+ */
+void dma_iova_unlink(struct device *dev, struct dma_iova_state *state,
+		size_t offset, size_t size, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+	 __iommu_dma_iova_unlink(dev, state, offset, size, dir, attrs, false);
+}
+EXPORT_SYMBOL_GPL(dma_iova_unlink);
+
+/**
+ * dma_iova_destroy - Finish a DMA mapping transaction
+ * @dev: DMA device
+ * @state: IOVA state
+ * @mapped_len: number of bytes to unmap
+ * @dir: DMA direction
+ * @attrs: attributes of mapping properties
+ *
+ * Unlink the IOVA range up to @mapped_len and free the entire IOVA space. The
+ * range of IOVA from dma_addr to @mapped_len must all be linked, and be the
+ * only linked IOVA in state.
+ */
+void dma_iova_destroy(struct device *dev, struct dma_iova_state *state,
+		size_t mapped_len, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+	if (mapped_len)
+		__iommu_dma_iova_unlink(dev, state, 0, mapped_len, dir, attrs,
+				true);
+	else
+		/*
+		 * We can be here if first call to dma_iova_link() failed and
+		 * there is nothing to unlink, so let's be more clear.
+		 */
+		dma_iova_free(dev, state);
+}
+EXPORT_SYMBOL_GPL(dma_iova_destroy);
+
 void iommu_setup_dma_ops(struct device *dev)
 {
 	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 9d728800a862..6c02f93422ce 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -2443,8 +2443,8 @@ out_set_count:
 	return pgsize;
 }
 
-static int __iommu_map(struct iommu_domain *domain, unsigned long iova,
-		       phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
+int iommu_map_nosync(struct iommu_domain *domain, unsigned long iova,
+		phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	const struct iommu_domain_ops *ops = domain->ops;
 	unsigned long orig_iova = iova;
@@ -2453,12 +2453,19 @@ static int __iommu_map(struct iommu_domain *domain, unsigned long iova,
 	phys_addr_t orig_paddr = paddr;
 	int ret = 0;
 
+	might_sleep_if(gfpflags_allow_blocking(gfp));
+
 	if (unlikely(!(domain->type & __IOMMU_DOMAIN_PAGING)))
 		return -EINVAL;
 
 	if (WARN_ON(!ops->map_pages || domain->pgsize_bitmap == 0UL))
 		return -ENODEV;
 
+	/* Discourage passing strange GFP flags */
+	if (WARN_ON_ONCE(gfp & (__GFP_COMP | __GFP_DMA | __GFP_DMA32 |
+				__GFP_HIGHMEM)))
+		return -EINVAL;
+
 	/* find out the minimum page size supported */
 	min_pagesz = 1 << __ffs(domain->pgsize_bitmap);
 
@@ -2506,31 +2513,27 @@ static int __iommu_map(struct iommu_domain *domain, unsigned long iova,
 	return ret;
 }
 
-int iommu_map(struct iommu_domain *domain, unsigned long iova,
-	      phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
+int iommu_sync_map(struct iommu_domain *domain, unsigned long iova, size_t size)
 {
 	const struct iommu_domain_ops *ops = domain->ops;
-	int ret;
 
-	might_sleep_if(gfpflags_allow_blocking(gfp));
-
-	/* Discourage passing strange GFP flags */
-	if (WARN_ON_ONCE(gfp & (__GFP_COMP | __GFP_DMA | __GFP_DMA32 |
-				__GFP_HIGHMEM)))
-		return -EINVAL;
+	if (!ops->iotlb_sync_map)
+		return 0;
+	return ops->iotlb_sync_map(domain, iova, size);
+}
 
-	ret = __iommu_map(domain, iova, paddr, size, prot, gfp);
-	if (ret == 0 && ops->iotlb_sync_map) {
-		ret = ops->iotlb_sync_map(domain, iova, size);
-		if (ret)
-			goto out_err;
-	}
+int iommu_map(struct iommu_domain *domain, unsigned long iova,
+	      phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
+{
+	int ret;
 
-	return ret;
+	ret = iommu_map_nosync(domain, iova, paddr, size, prot, gfp);
+	if (ret)
+		return ret;
 
-out_err:
-	/* undo mappings already done */
-	iommu_unmap(domain, iova, size);
+	ret = iommu_sync_map(domain, iova, size);
+	if (ret)
+		iommu_unmap(domain, iova, size);
 
 	return ret;
 }
@@ -2618,6 +2621,25 @@ size_t iommu_unmap(struct iommu_domain *domain,
 }
 EXPORT_SYMBOL_GPL(iommu_unmap);
 
+/**
+ * iommu_unmap_fast() - Remove mappings from a range of IOVA without IOTLB sync
+ * @domain: Domain to manipulate
+ * @iova: IO virtual address to start
+ * @size: Length of the range starting from @iova
+ * @iotlb_gather: range information for a pending IOTLB flush
+ *
+ * iommu_unmap_fast() will remove a translation created by iommu_map().
+ * It can't subdivide a mapping created by iommu_map(), so it should be
+ * called with IOVA ranges that match what was passed to iommu_map(). The
+ * range can aggregate contiguous iommu_map() calls so long as no individual
+ * range is split.
+ *
+ * Basically iommu_unmap_fast() is the same as iommu_unmap() but for callers
+ * which manage the IOTLB flushing externally to perform a batched sync.
+ *
+ * Returns: Number of bytes of IOVA unmapped. iova + res will be the point
+ * unmapping stopped.
+ */
 size_t iommu_unmap_fast(struct iommu_domain *domain,
 			unsigned long iova, size_t size,
 			struct iommu_iotlb_gather *iotlb_gather)
@@ -2630,26 +2652,17 @@ ssize_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
 		     struct scatterlist *sg, unsigned int nents, int prot,
 		     gfp_t gfp)
 {
-	const struct iommu_domain_ops *ops = domain->ops;
 	size_t len = 0, mapped = 0;
 	phys_addr_t start;
 	unsigned int i = 0;
 	int ret;
 
-	might_sleep_if(gfpflags_allow_blocking(gfp));
-
-	/* Discourage passing strange GFP flags */
-	if (WARN_ON_ONCE(gfp & (__GFP_COMP | __GFP_DMA | __GFP_DMA32 |
-				__GFP_HIGHMEM)))
-		return -EINVAL;
-
 	while (i <= nents) {
 		phys_addr_t s_phys = sg_phys(sg);
 
 		if (len && s_phys != start + len) {
-			ret = __iommu_map(domain, iova + mapped, start,
+			ret = iommu_map_nosync(domain, iova + mapped, start,
 					len, prot, gfp);
-
 			if (ret)
 				goto out_err;
 
@@ -2672,11 +2685,10 @@ next:
 			sg = sg_next(sg);
 	}
 
-	if (ops->iotlb_sync_map) {
-		ret = ops->iotlb_sync_map(domain, iova, mapped);
-		if (ret)
-			goto out_err;
-	}
+	ret = iommu_sync_map(domain, iova, mapped);
+	if (ret)
+		goto out_err;
+
 	return mapped;
 
 out_err:
diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c
index 19214ec81fbb..8d955c25aed3 100644
--- a/drivers/pci/p2pdma.c
+++ b/drivers/pci/p2pdma.c
@@ -1004,40 +1004,12 @@ static enum pci_p2pdma_map_type pci_p2pdma_map_type(struct dev_pagemap *pgmap,
 	return type;
 }
 
-/**
- * pci_p2pdma_map_segment - map an sg segment determining the mapping type
- * @state: State structure that should be declared outside of the for_each_sg()
- *	loop and initialized to zero.
- * @dev: DMA device that's doing the mapping operation
- * @sg: scatterlist segment to map
- *
- * This is a helper to be used by non-IOMMU dma_map_sg() implementations where
- * the sg segment is the same for the page_link and the dma_address.
- *
- * Attempt to map a single segment in an SGL with the PCI bus address.
- * The segment must point to a PCI P2PDMA page and thus must be
- * wrapped in a is_pci_p2pdma_page(sg_page(sg)) check.
- *
- * Returns the type of mapping used and maps the page if the type is
- * PCI_P2PDMA_MAP_BUS_ADDR.
- */
-enum pci_p2pdma_map_type
-pci_p2pdma_map_segment(struct pci_p2pdma_map_state *state, struct device *dev,
-		       struct scatterlist *sg)
+void __pci_p2pdma_update_state(struct pci_p2pdma_map_state *state,
+		struct device *dev, struct page *page)
 {
-	if (state->pgmap != page_pgmap(sg_page(sg))) {
-		state->pgmap = page_pgmap(sg_page(sg));
-		state->map = pci_p2pdma_map_type(state->pgmap, dev);
-		state->bus_off = to_p2p_pgmap(state->pgmap)->bus_offset;
-	}
-
-	if (state->map == PCI_P2PDMA_MAP_BUS_ADDR) {
-		sg->dma_address = sg_phys(sg) + state->bus_off;
-		sg_dma_len(sg) = sg->length;
-		sg_dma_mark_bus_address(sg);
-	}
-
-	return state->map;
+	state->pgmap = page_pgmap(page);
+	state->map = pci_p2pdma_map_type(state->pgmap, dev);
+	state->bus_off = to_p2p_pgmap(state->pgmap)->bus_offset;
 }
 
 /**
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index e172522cd936..f48e5fb88bd5 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -434,58 +434,4 @@ static inline void debug_dma_dump_mappings(struct device *dev)
 #endif /* CONFIG_DMA_API_DEBUG */
 
 extern const struct dma_map_ops dma_dummy_ops;
-
-enum pci_p2pdma_map_type {
-	/*
-	 * PCI_P2PDMA_MAP_UNKNOWN: Used internally for indicating the mapping
-	 * type hasn't been calculated yet. Functions that return this enum
-	 * never return this value.
-	 */
-	PCI_P2PDMA_MAP_UNKNOWN = 0,
-
-	/*
-	 * PCI_P2PDMA_MAP_NOT_SUPPORTED: Indicates the transaction will
-	 * traverse the host bridge and the host bridge is not in the
-	 * allowlist. DMA Mapping routines should return an error when
-	 * this is returned.
-	 */
-	PCI_P2PDMA_MAP_NOT_SUPPORTED,
-
-	/*
-	 * PCI_P2PDMA_BUS_ADDR: Indicates that two devices can talk to
-	 * each other directly through a PCI switch and the transaction will
-	 * not traverse the host bridge. Such a mapping should program
-	 * the DMA engine with PCI bus addresses.
-	 */
-	PCI_P2PDMA_MAP_BUS_ADDR,
-
-	/*
-	 * PCI_P2PDMA_MAP_THRU_HOST_BRIDGE: Indicates two devices can talk
-	 * to each other, but the transaction traverses a host bridge on the
-	 * allowlist. In this case, a normal mapping either with CPU physical
-	 * addresses (in the case of dma-direct) or IOVA addresses (in the
-	 * case of IOMMUs) should be used to program the DMA engine.
-	 */
-	PCI_P2PDMA_MAP_THRU_HOST_BRIDGE,
-};
-
-struct pci_p2pdma_map_state {
-	struct dev_pagemap *pgmap;
-	int map;
-	u64 bus_off;
-};
-
-#ifdef CONFIG_PCI_P2PDMA
-enum pci_p2pdma_map_type
-pci_p2pdma_map_segment(struct pci_p2pdma_map_state *state, struct device *dev,
-		       struct scatterlist *sg);
-#else /* CONFIG_PCI_P2PDMA */
-static inline enum pci_p2pdma_map_type
-pci_p2pdma_map_segment(struct pci_p2pdma_map_state *state, struct device *dev,
-		       struct scatterlist *sg)
-{
-	return PCI_P2PDMA_MAP_NOT_SUPPORTED;
-}
-#endif /* CONFIG_PCI_P2PDMA */
-
 #endif /* _LINUX_DMA_MAP_OPS_H */
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 85ab710ec0e7..55c03e5fe8cb 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -72,6 +72,22 @@
 
 #define DMA_BIT_MASK(n)	(((n) == 64) ? ~0ULL : ((1ULL<<(n))-1))
 
+struct dma_iova_state {
+	dma_addr_t addr;
+	u64 __size;
+};
+
+/*
+ * Use the high bit to mark if we used swiotlb for one or more ranges.
+ */
+#define DMA_IOVA_USE_SWIOTLB		(1ULL << 63)
+
+static inline size_t dma_iova_size(struct dma_iova_state *state)
+{
+	/* Casting is needed for 32-bits systems */
+	return (size_t)(state->__size & ~DMA_IOVA_USE_SWIOTLB);
+}
+
 #ifdef CONFIG_DMA_API_DEBUG
 void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr);
 void debug_dma_map_single(struct device *dev, const void *addr,
@@ -277,6 +293,70 @@ static inline int dma_mmap_noncontiguous(struct device *dev,
 }
 #endif /* CONFIG_HAS_DMA */
 
+#ifdef CONFIG_IOMMU_DMA
+/**
+ * dma_use_iova - check if the IOVA API is used for this state
+ * @state: IOVA state
+ *
+ * Return %true if the DMA transfers uses the dma_iova_*() calls or %false if
+ * they can't be used.
+ */
+static inline bool dma_use_iova(struct dma_iova_state *state)
+{
+	return state->__size != 0;
+}
+
+bool dma_iova_try_alloc(struct device *dev, struct dma_iova_state *state,
+		phys_addr_t phys, size_t size);
+void dma_iova_free(struct device *dev, struct dma_iova_state *state);
+void dma_iova_destroy(struct device *dev, struct dma_iova_state *state,
+		size_t mapped_len, enum dma_data_direction dir,
+		unsigned long attrs);
+int dma_iova_sync(struct device *dev, struct dma_iova_state *state,
+		size_t offset, size_t size);
+int dma_iova_link(struct device *dev, struct dma_iova_state *state,
+		phys_addr_t phys, size_t offset, size_t size,
+		enum dma_data_direction dir, unsigned long attrs);
+void dma_iova_unlink(struct device *dev, struct dma_iova_state *state,
+		size_t offset, size_t size, enum dma_data_direction dir,
+		unsigned long attrs);
+#else /* CONFIG_IOMMU_DMA */
+static inline bool dma_use_iova(struct dma_iova_state *state)
+{
+	return false;
+}
+static inline bool dma_iova_try_alloc(struct device *dev,
+		struct dma_iova_state *state, phys_addr_t phys, size_t size)
+{
+	return false;
+}
+static inline void dma_iova_free(struct device *dev,
+		struct dma_iova_state *state)
+{
+}
+static inline void dma_iova_destroy(struct device *dev,
+		struct dma_iova_state *state, size_t mapped_len,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+}
+static inline int dma_iova_sync(struct device *dev,
+		struct dma_iova_state *state, size_t offset, size_t size)
+{
+	return -EOPNOTSUPP;
+}
+static inline int dma_iova_link(struct device *dev,
+		struct dma_iova_state *state, phys_addr_t phys, size_t offset,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	return -EOPNOTSUPP;
+}
+static inline void dma_iova_unlink(struct device *dev,
+		struct dma_iova_state *state, size_t offset, size_t size,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+}
+#endif /* CONFIG_IOMMU_DMA */
+
 #if defined(CONFIG_HAS_DMA) && defined(CONFIG_DMA_NEED_SYNC)
 void __dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size,
 		enum dma_data_direction dir);
@@ -326,6 +406,7 @@ static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
 {
 	return dma_dev_need_sync(dev) ? __dma_need_sync(dev, dma_addr) : false;
 }
+bool dma_need_unmap(struct device *dev);
 #else /* !CONFIG_HAS_DMA || !CONFIG_DMA_NEED_SYNC */
 static inline bool dma_dev_need_sync(const struct device *dev)
 {
@@ -351,6 +432,10 @@ static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
 {
 	return false;
 }
+static inline bool dma_need_unmap(struct device *dev)
+{
+	return false;
+}
 #endif /* !CONFIG_HAS_DMA || !CONFIG_DMA_NEED_SYNC */
 
 struct page *dma_alloc_pages(struct device *dev, size_t size,
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 3a8d35d41fda..15cdadace993 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -872,6 +872,10 @@ extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev);
 extern struct iommu_domain *iommu_get_dma_domain(struct device *dev);
 extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
 		     phys_addr_t paddr, size_t size, int prot, gfp_t gfp);
+int iommu_map_nosync(struct iommu_domain *domain, unsigned long iova,
+		phys_addr_t paddr, size_t size, int prot, gfp_t gfp);
+int iommu_sync_map(struct iommu_domain *domain, unsigned long iova,
+		size_t size);
 extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 			  size_t size);
 extern size_t iommu_unmap_fast(struct iommu_domain *domain,
diff --git a/include/linux/pci-p2pdma.h b/include/linux/pci-p2pdma.h
index 2c07aa6b7665..075c20b161d9 100644
--- a/include/linux/pci-p2pdma.h
+++ b/include/linux/pci-p2pdma.h
@@ -104,4 +104,89 @@ static inline struct pci_dev *pci_p2pmem_find(struct device *client)
 	return pci_p2pmem_find_many(&client, 1);
 }
 
+enum pci_p2pdma_map_type {
+	/*
+	 * PCI_P2PDMA_MAP_UNKNOWN: Used internally as an initial state before
+	 * the mapping type has been calculated. Exported routines for the API
+	 * will never return this value.
+	 */
+	PCI_P2PDMA_MAP_UNKNOWN = 0,
+
+	/*
+	 * Not a PCI P2PDMA transfer.
+	 */
+	PCI_P2PDMA_MAP_NONE,
+
+	/*
+	 * PCI_P2PDMA_MAP_NOT_SUPPORTED: Indicates the transaction will
+	 * traverse the host bridge and the host bridge is not in the
+	 * allowlist. DMA Mapping routines should return an error when
+	 * this is returned.
+	 */
+	PCI_P2PDMA_MAP_NOT_SUPPORTED,
+
+	/*
+	 * PCI_P2PDMA_MAP_BUS_ADDR: Indicates that two devices can talk to
+	 * each other directly through a PCI switch and the transaction will
+	 * not traverse the host bridge. Such a mapping should program
+	 * the DMA engine with PCI bus addresses.
+	 */
+	PCI_P2PDMA_MAP_BUS_ADDR,
+
+	/*
+	 * PCI_P2PDMA_MAP_THRU_HOST_BRIDGE: Indicates two devices can talk
+	 * to each other, but the transaction traverses a host bridge on the
+	 * allowlist. In this case, a normal mapping either with CPU physical
+	 * addresses (in the case of dma-direct) or IOVA addresses (in the
+	 * case of IOMMUs) should be used to program the DMA engine.
+	 */
+	PCI_P2PDMA_MAP_THRU_HOST_BRIDGE,
+};
+
+struct pci_p2pdma_map_state {
+	struct dev_pagemap *pgmap;
+	enum pci_p2pdma_map_type map;
+	u64 bus_off;
+};
+
+/* helper for pci_p2pdma_state(), do not use directly */
+void __pci_p2pdma_update_state(struct pci_p2pdma_map_state *state,
+		struct device *dev, struct page *page);
+
+/**
+ * pci_p2pdma_state - check the P2P transfer state of a page
+ * @state:	P2P state structure
+ * @dev:	device to transfer to/from
+ * @page:	page to map
+ *
+ * Check if @page is a PCI P2PDMA page, and if yes of what kind.  Returns the
+ * map type, and updates @state with all information needed for a P2P transfer.
+ */
+static inline enum pci_p2pdma_map_type
+pci_p2pdma_state(struct pci_p2pdma_map_state *state, struct device *dev,
+		struct page *page)
+{
+	if (IS_ENABLED(CONFIG_PCI_P2PDMA) && is_pci_p2pdma_page(page)) {
+		if (state->pgmap != page_pgmap(page))
+			__pci_p2pdma_update_state(state, dev, page);
+		return state->map;
+	}
+	return PCI_P2PDMA_MAP_NONE;
+}
+
+/**
+ * pci_p2pdma_bus_addr_map - Translate a physical address to a bus address
+ *			     for a PCI_P2PDMA_MAP_BUS_ADDR transfer.
+ * @state:	P2P state structure
+ * @paddr:	physical address to map
+ *
+ * Map a physically contiguous PCI_P2PDMA_MAP_BUS_ADDR transfer.
+ */
+static inline dma_addr_t
+pci_p2pdma_bus_addr_map(struct pci_p2pdma_map_state *state, phys_addr_t paddr)
+{
+	WARN_ON_ONCE(state->map != PCI_P2PDMA_MAP_BUS_ADDR);
+	return paddr + state->bus_off;
+}
+
 #endif /* _LINUX_PCI_P2P_H */
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index b8fe0b3d0ffb..24c359d9c879 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -13,6 +13,7 @@
 #include <linux/vmalloc.h>
 #include <linux/set_memory.h>
 #include <linux/slab.h>
+#include <linux/pci-p2pdma.h>
 #include "direct.h"
 
 /*
@@ -462,34 +463,33 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
 		enum dma_data_direction dir, unsigned long attrs)
 {
 	struct pci_p2pdma_map_state p2pdma_state = {};
-	enum pci_p2pdma_map_type map;
 	struct scatterlist *sg;
 	int i, ret;
 
 	for_each_sg(sgl, sg, nents, i) {
-		if (is_pci_p2pdma_page(sg_page(sg))) {
-			map = pci_p2pdma_map_segment(&p2pdma_state, dev, sg);
-			switch (map) {
-			case PCI_P2PDMA_MAP_BUS_ADDR:
-				continue;
-			case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE:
-				/*
-				 * Any P2P mapping that traverses the PCI
-				 * host bridge must be mapped with CPU physical
-				 * address and not PCI bus addresses. This is
-				 * done with dma_direct_map_page() below.
-				 */
-				break;
-			default:
-				ret = -EREMOTEIO;
+		switch (pci_p2pdma_state(&p2pdma_state, dev, sg_page(sg))) {
+		case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE:
+			/*
+			 * Any P2P mapping that traverses the PCI host bridge
+			 * must be mapped with CPU physical address and not PCI
+			 * bus addresses.
+			 */
+			break;
+		case PCI_P2PDMA_MAP_NONE:
+			sg->dma_address = dma_direct_map_page(dev, sg_page(sg),
+					sg->offset, sg->length, dir, attrs);
+			if (sg->dma_address == DMA_MAPPING_ERROR) {
+				ret = -EIO;
 				goto out_unmap;
 			}
-		}
-
-		sg->dma_address = dma_direct_map_page(dev, sg_page(sg),
-				sg->offset, sg->length, dir, attrs);
-		if (sg->dma_address == DMA_MAPPING_ERROR) {
-			ret = -EIO;
+			break;
+		case PCI_P2PDMA_MAP_BUS_ADDR:
+			sg->dma_address = pci_p2pdma_bus_addr_map(&p2pdma_state,
+					sg_phys(sg));
+			sg_dma_mark_bus_address(sg);
+			continue;
+		default:
+			ret = -EREMOTEIO;
 			goto out_unmap;
 		}
 		sg_dma_len(sg) = sg->length;
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 051a32988040..107e4a4d251d 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -443,6 +443,24 @@ bool __dma_need_sync(struct device *dev, dma_addr_t dma_addr)
 }
 EXPORT_SYMBOL_GPL(__dma_need_sync);
 
+/**
+ * dma_need_unmap - does this device need dma_unmap_* operations
+ * @dev: device to check
+ *
+ * If this function returns %false, drivers can skip calling dma_unmap_* after
+ * finishing an I/O.  This function must be called after all mappings that might
+ * need to be unmapped have been performed.
+ */
+bool dma_need_unmap(struct device *dev)
+{
+	if (!dma_map_direct(dev, get_dma_ops(dev)))
+		return true;
+	if (!dev->dma_skip_sync)
+		return true;
+	return IS_ENABLED(CONFIG_DMA_API_DEBUG);
+}
+EXPORT_SYMBOL_GPL(dma_need_unmap);
+
 static void dma_setup_need_sync(struct device *dev)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);