Provide a new two step DMA mapping API

Currently the only efficient way to map a complex memory description through
the DMA API is by using the scatter list APIs. The SG APIs are unique in that
they efficiently combine the two fundamental operations of sizing and allocating
a large IOVA window from the IOMMU and processing all the per-address
swiotlb/flushing/p2p/map details.

This uniqueness has been a long standing pain point as the scatter list API
is mandatory, but expensive to use. It prevents any kind of optimization or
feature improvement (such as avoiding struct page for P2P) due to the
impossibility of improving the scatter list.

Several approaches have been explored to expand the DMA API with additional
scatterlist-like structures (BIO, rlist), instead split up the DMA API
to allow callers to bring their own data structure.

The API is split up into parts:
 - Allocate IOVA space:
    To do any pre-allocation required. This is done based on the caller
    supplying some details about how much IOMMU address space it would need
    in worst case.
 - Map and unmap relevant structures to pre-allocated IOVA space:
    Perform the actual mapping into the pre-allocated IOVA. This is very
    similar to dma_map_page().

Thanks

Signed-off-by: Leon Romanovsky <leon@kernel.org>

3 files changed, 479 insertions, 125 deletions

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index cb7e29dcac15..1569efe71118 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 c8033ca66377..66b0bf6418ef 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -2440,8 +2440,8 @@ 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;
@@ -2450,12 +2450,19 @@ 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);
 
@@ -2503,31 +2510,27 @@ 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;
 }
@@ -2615,6 +2618,25 @@ 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)
@@ -2627,26 +2649,17 @@ 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;
 
@@ -2669,11 +2682,10 @@ 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;
 }
 
 /**