Provide a new two step DMA mapping API

index 5746ffaf0061..853247c42f7d 100644
@@ -26,6 +26,7 @@
 #include <linux/mutex.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>

89 lines not on this page · raw message

88 lines not on this page · raw message

index e289ad27d1b5..c9b3893257d4 100644
@@ -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"
 
 /*

index 2a9fa0c8cc00..5746ffaf0061 100644
@@ -1382,7 +1382,6 @@ 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);

@@ -1412,28 +1411,30 @@ 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;

index 4f47a13cb500..f38d16d71dd5 100644
@@ -995,40 +995,12 @@ 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 != sg_page(sg)->pgmap) {
-		state->pgmap = sg_page(sg)->pgmap;
-		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;
+	state->map = pci_p2pdma_map_type(state->pgmap, dev);
+	state->bus_off = to_p2p_pgmap(state->pgmap)->bus_offset;
 }
 
 /**

68 lines not on this page · raw message

55 lines not on this page · raw message

index 1524da363734..6075e0708deb 100644
@@ -76,6 +76,20 @@
 
 #define DMA_BIT_MASK(n)	(((n) == 64) ? ~0ULL : ((1ULL<<(n))-1))
 
+struct dma_iova_state {
+	size_t __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)
+{
+	return 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,

@@ -281,6 +295,25 @@ 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;
+}
+#else /* CONFIG_IOMMU_DMA */
+static inline bool dma_use_iova(struct dma_iova_state *state)
+{
+	return false;
+}
+#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);

index 853247c42f7d..127150f63c95 100644
@@ -1746,6 +1746,85 @@ size_t iommu_dma_max_mapping_size(struct device *dev)
 	return SIZE_MAX;
 }
 
+static bool iommu_dma_iova_alloc(struct device *dev,
+		struct dma_iova_state *state, phys_addr_t phys, 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;
+	size_t iova_off = iova_offset(iovad, phys);
+	dma_addr_t addr;
+
+	if (WARN_ON_ONCE(!size))
+		return false;
+	if (WARN_ON_ONCE(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;
+}
+
+/**
+ * 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)
+{
+	memset(state, 0, sizeof(*state));
+	if (!use_dma_iommu(dev))
+		return false;
+	if (static_branch_unlikely(&iommu_deferred_attach_enabled) &&
+	    iommu_deferred_attach(dev, iommu_get_domain_for_dev(dev)))
+		return false;
+	return iommu_dma_iova_alloc(dev, state, phys, size);
+}
+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(cookie, state->addr - iova_start_pad,
+			iova_align(iovad, size + iova_start_pad), NULL);
+}
+EXPORT_SYMBOL_GPL(dma_iova_free);
+
 void iommu_setup_dma_ops(struct device *dev)
 {
 	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);

index 6075e0708deb..817f11bce7bc 100644
@@ -11,6 +11,7 @@
 #include <linux/scatterlist.h>
 #include <linux/bug.h>
 #include <linux/mem_encrypt.h>
+#include <linux/iommu.h>
 
 /**
  * List of possible attributes associated with a DMA mapping. The semantics

@@ -77,6 +78,7 @@
 #define DMA_BIT_MASK(n)	(((n) == 64) ? ~0ULL : ((1ULL<<(n))-1))
 
 struct dma_iova_state {
+	dma_addr_t addr;
 	size_t __size;
 };
 

@@ -307,11 +309,24 @@ 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);
 #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)
+{
+}
 #endif /* CONFIG_IOMMU_DMA */
 
 #if defined(CONFIG_HAS_DMA) && defined(CONFIG_DMA_NEED_SYNC)

index 127150f63c95..e1eaad500d27 100644
@@ -1161,6 +1161,43 @@ 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 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 != 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;
+}
+
 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)

@@ -1174,42 +1211,14 @@ 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");
-			return DMA_MAPPING_ERROR;
-		}
-
-		trace_swiotlb_bounced(dev, phys, size);
-
-		phys = swiotlb_tbl_map_single(dev, phys, size,
-					      iova_mask(iovad), dir, attrs);
-
+		phys = iommu_dma_map_swiotlb(dev, phys, size, 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);
-		}
+			return phys;
 	}
 
 	if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))

index e1eaad500d27..4a504a879cc0 100644
@@ -1834,6 +1834,265 @@ void dma_iova_free(struct device *dev, struct dma_iova_state *state)
 }
 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 contigueous
+ * 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_offset(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-contigous 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))
+			continue;
+		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(cookie, 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);

index 817f11bce7bc..8074a3b5c807 100644
@@ -313,6 +313,17 @@ static inline bool dma_use_iova(struct dma_iova_state *state)
 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)
 {

@@ -327,6 +338,27 @@ 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)

index 8074a3b5c807..6906edde505d 100644
@@ -410,6 +410,7 @@ 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)
 {

@@ -435,6 +436,10 @@ 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,

index 864a1121bf08..daa97a650778 100644
@@ -442,6 +442,26 @@ 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;
+#ifdef CONFIG_DMA_NEED_SYNC
+	if (!dev->dma_skip_sync)
+		return true;
+#endif
+	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);

index 83c8e617a2c5..6b0943397e1e 100644
@@ -2439,8 +2439,8 @@ static size_t iommu_pgsize(struct iommu_domain *domain, unsigned long iova,
 	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;

@@ -2449,12 +2449,19 @@ 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);
 

@@ -2502,31 +2509,27 @@ 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;
 }

@@ -2612,26 +2615,17 @@ 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;
 

@@ -2654,11 +2648,10 @@ ssize_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
 			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:

index bd722f473635..8927e5f996c2 100644
@@ -799,6 +799,10 @@ 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,

index 126a36571667..5dd655f6766b 100644
@@ -23,6 +23,8 @@ struct mmu_interval_notifier;
  * HMM_PFN_WRITE - if the page memory can be written to (requires HMM_PFN_VALID)
  * HMM_PFN_ERROR - accessing the pfn is impossible and the device should
  *                 fail. ie poisoned memory, special pages, no vma, etc
+ * HMM_PFN_DMA_MAPPED - Flag preserved on input-to-output transformation
+ *                      to mark that page is already DMA mapped
  *
  * On input:
  * 0                 - Return the current state of the page, do not fault it.

@@ -36,6 +38,10 @@ enum hmm_pfn_flags {
 	HMM_PFN_VALID = 1UL << (BITS_PER_LONG - 1),
 	HMM_PFN_WRITE = 1UL << (BITS_PER_LONG - 2),
 	HMM_PFN_ERROR = 1UL << (BITS_PER_LONG - 3),
+
+	/* Sticky flag, carried from Input to Output */
+	HMM_PFN_DMA_MAPPED = 1UL << (BITS_PER_LONG - 7),
+
 	HMM_PFN_ORDER_SHIFT = (BITS_PER_LONG - 8),
 
 	/* Input flags */

@@ -57,6 +63,14 @@ static inline struct page *hmm_pfn_to_page(unsigned long hmm_pfn)
 	return pfn_to_page(hmm_pfn & ~HMM_PFN_FLAGS);
 }
 
+/*
+ * hmm_pfn_to_phys() - return physical address pointed to by a device entry
+ */
+static inline phys_addr_t hmm_pfn_to_phys(unsigned long hmm_pfn)
+{
+	return __pfn_to_phys(hmm_pfn & ~HMM_PFN_FLAGS);
+}
+
 /*
  * hmm_pfn_to_map_order() - return the CPU mapping size order
  *

index 7e0229ae4a5a..2a0c34d7cb2b 100644
@@ -44,8 +44,10 @@ static int hmm_pfns_fill(unsigned long addr, unsigned long end,
 {
 	unsigned long i = (addr - range->start) >> PAGE_SHIFT;
 
-	for (; addr < end; addr += PAGE_SIZE, i++)
-		range->hmm_pfns[i] = cpu_flags;
+	for (; addr < end; addr += PAGE_SIZE, i++) {
+		range->hmm_pfns[i] &= HMM_PFN_DMA_MAPPED;
+		range->hmm_pfns[i] |= cpu_flags;
+	}
 	return 0;
 }
 

@@ -202,8 +204,10 @@ static int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr,
 		return hmm_vma_fault(addr, end, required_fault, walk);
 
 	pfn = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
-	for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++)
-		hmm_pfns[i] = pfn | cpu_flags;
+	for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++) {
+		hmm_pfns[i] &= HMM_PFN_DMA_MAPPED;
+		hmm_pfns[i] |= pfn | cpu_flags;
+	}
 	return 0;
 }
 #else /* CONFIG_TRANSPARENT_HUGEPAGE */

@@ -236,7 +240,7 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 			hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0);
 		if (required_fault)
 			goto fault;
-		*hmm_pfn = 0;
+		*hmm_pfn = *hmm_pfn & HMM_PFN_DMA_MAPPED;
 		return 0;
 	}
 

@@ -253,14 +257,14 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 			cpu_flags = HMM_PFN_VALID;
 			if (is_writable_device_private_entry(entry))
 				cpu_flags |= HMM_PFN_WRITE;
-			*hmm_pfn = swp_offset_pfn(entry) | cpu_flags;
+			*hmm_pfn = (*hmm_pfn & HMM_PFN_DMA_MAPPED) | swp_offset_pfn(entry) | cpu_flags;
 			return 0;
 		}
 
 		required_fault =
 			hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0);
 		if (!required_fault) {
-			*hmm_pfn = 0;
+			*hmm_pfn = *hmm_pfn & HMM_PFN_DMA_MAPPED;
 			return 0;
 		}
 

@@ -304,11 +308,11 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 			pte_unmap(ptep);
 			return -EFAULT;
 		}
-		*hmm_pfn = HMM_PFN_ERROR;
+		*hmm_pfn = (*hmm_pfn & HMM_PFN_DMA_MAPPED) | HMM_PFN_ERROR;
 		return 0;
 	}
 
-	*hmm_pfn = pte_pfn(pte) | cpu_flags;
+	*hmm_pfn = (*hmm_pfn & HMM_PFN_DMA_MAPPED) | pte_pfn(pte) | cpu_flags;
 	return 0;
 
 fault:

@@ -448,8 +452,10 @@ static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end,
 		}
 
 		pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
-		for (i = 0; i < npages; ++i, ++pfn)
-			hmm_pfns[i] = pfn | cpu_flags;
+		for (i = 0; i < npages; ++i, ++pfn) {
+			hmm_pfns[i] &= HMM_PFN_DMA_MAPPED;
+			hmm_pfns[i] |= pfn | cpu_flags;
+		}
 		goto out_unlock;
 	}
 

@@ -507,8 +513,10 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
 	}
 
 	pfn = pte_pfn(entry) + ((start & ~hmask) >> PAGE_SHIFT);
-	for (; addr < end; addr += PAGE_SIZE, i++, pfn++)
-		range->hmm_pfns[i] = pfn | cpu_flags;
+	for (; addr < end; addr += PAGE_SIZE, i++, pfn++) {
+		range->hmm_pfns[i] &= HMM_PFN_DMA_MAPPED;
+		range->hmm_pfns[i] |= pfn | cpu_flags;
+	}
 
 	spin_unlock(ptl);
 	return 0;

new file mode 100644
index 000000000000..f6ce2a00d74d
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+#ifndef LINUX_HMM_DMA_H
+#define LINUX_HMM_DMA_H
+
+#include <linux/dma-mapping.h>
+
+struct dma_iova_state;
+struct pci_p2pdma_map_state;
+
+/*
+ * struct hmm_dma_map - array of PFNs and DMA addresses
+ *
+ * @state: DMA IOVA state
+ * @pfns: array of PFNs
+ * @dma_list: array of DMA addresses
+ * @dma_entry_size: size of each DMA entry in the array
+ */
+struct hmm_dma_map {
+	struct dma_iova_state state;
+	unsigned long *pfn_list;
+	dma_addr_t *dma_list;
+	size_t dma_entry_size;
+};
+
+int hmm_dma_map_alloc(struct device *dev, struct hmm_dma_map *map,
+		      size_t nr_entries, size_t dma_entry_size);
+void hmm_dma_map_free(struct device *dev, struct hmm_dma_map *map);
+dma_addr_t hmm_dma_map_pfn(struct device *dev, struct hmm_dma_map *map,
+			   size_t idx, struct pci_p2pdma_map_state *p2pdma_state);
+bool hmm_dma_unmap_pfn(struct device *dev, struct hmm_dma_map *map, size_t idx);
+#endif /* LINUX_HMM_DMA_H */

index 5dd655f6766b..62980ca8f3c5 100644
@@ -23,6 +23,7 @@ struct mmu_interval_notifier;
  * HMM_PFN_WRITE - if the page memory can be written to (requires HMM_PFN_VALID)
  * HMM_PFN_ERROR - accessing the pfn is impossible and the device should
  *                 fail. ie poisoned memory, special pages, no vma, etc
+ * HMM_PFN_P2PDMA_BUS - Bus mapped P2P transfer
  * HMM_PFN_DMA_MAPPED - Flag preserved on input-to-output transformation
  *                      to mark that page is already DMA mapped
  *

@@ -40,6 +41,7 @@ enum hmm_pfn_flags {
 	HMM_PFN_ERROR = 1UL << (BITS_PER_LONG - 3),
 
 	/* Sticky flag, carried from Input to Output */
+	HMM_PFN_P2PDMA_BUS = 1UL << (BITS_PER_LONG - 6),
 	HMM_PFN_DMA_MAPPED = 1UL << (BITS_PER_LONG - 7),
 
 	HMM_PFN_ORDER_SHIFT = (BITS_PER_LONG - 8),

212 lines not on this page · raw message

index e9fa22d31c23..9dba369365af 100644
@@ -296,22 +296,11 @@ EXPORT_SYMBOL(ib_umem_odp_release);
 static int ib_umem_odp_map_dma_single_page(
 		struct ib_umem_odp *umem_odp,
 		unsigned int dma_index,
-		struct page *page,
-		u64 access_mask)
+		struct page *page)
 {
 	struct ib_device *dev = umem_odp->umem.ibdev;
 	dma_addr_t *dma_addr = &umem_odp->dma_list[dma_index];
 
-	if (*dma_addr) {
-		/*
-		 * If the page is already dma mapped it means it went through
-		 * a non-invalidating trasition, like read-only to writable.
-		 * Resync the flags.
-		 */
-		*dma_addr = (*dma_addr & ODP_DMA_ADDR_MASK) | access_mask;
-		return 0;
-	}
-
 	*dma_addr = ib_dma_map_page(dev, page, 0, 1 << umem_odp->page_shift,
 				    DMA_BIDIRECTIONAL);
 	if (ib_dma_mapping_error(dev, *dma_addr)) {

@@ -319,7 +308,6 @@ static int ib_umem_odp_map_dma_single_page(
 		return -EFAULT;
 	}
 	umem_odp->npages++;
-	*dma_addr |= access_mask;
 	return 0;
 }
 

@@ -355,9 +343,6 @@ int ib_umem_odp_map_dma_and_lock(struct ib_umem_odp *umem_odp, u64 user_virt,
 	struct hmm_range range = {};
 	unsigned long timeout;
 
-	if (access_mask == 0)
-		return -EINVAL;
-
 	if (user_virt < ib_umem_start(umem_odp) ||
 	    user_virt + bcnt > ib_umem_end(umem_odp))
 		return -EFAULT;

@@ -383,7 +368,7 @@ int ib_umem_odp_map_dma_and_lock(struct ib_umem_odp *umem_odp, u64 user_virt,
 	if (fault) {
 		range.default_flags = HMM_PFN_REQ_FAULT;
 
-		if (access_mask & ODP_WRITE_ALLOWED_BIT)
+		if (access_mask & HMM_PFN_WRITE)
 			range.default_flags |= HMM_PFN_REQ_WRITE;
 	}
 

@@ -415,22 +400,17 @@ int ib_umem_odp_map_dma_and_lock(struct ib_umem_odp *umem_odp, u64 user_virt,
 	for (pfn_index = 0; pfn_index < num_pfns;
 		pfn_index += 1 << (page_shift - PAGE_SHIFT), dma_index++) {
 
-		if (fault) {
-			/*
-			 * Since we asked for hmm_range_fault() to populate
-			 * pages it shouldn't return an error entry on success.
-			 */
-			WARN_ON(range.hmm_pfns[pfn_index] & HMM_PFN_ERROR);
-			WARN_ON(!(range.hmm_pfns[pfn_index] & HMM_PFN_VALID));
-		} else {
-			if (!(range.hmm_pfns[pfn_index] & HMM_PFN_VALID)) {
-				WARN_ON(umem_odp->dma_list[dma_index]);
-				continue;
-			}
-			access_mask = ODP_READ_ALLOWED_BIT;
-			if (range.hmm_pfns[pfn_index] & HMM_PFN_WRITE)
-				access_mask |= ODP_WRITE_ALLOWED_BIT;
-		}
+		/*
+		 * Since we asked for hmm_range_fault() to populate
+		 * pages it shouldn't return an error entry on success.
+		 */
+		WARN_ON(fault && range.hmm_pfns[pfn_index] & HMM_PFN_ERROR);
+		WARN_ON(fault && !(range.hmm_pfns[pfn_index] & HMM_PFN_VALID));
+		if (!(range.hmm_pfns[pfn_index] & HMM_PFN_VALID))
+			continue;
+
+		if (range.hmm_pfns[pfn_index] & HMM_PFN_DMA_MAPPED)
+			continue;
 
 		hmm_order = hmm_pfn_to_map_order(range.hmm_pfns[pfn_index]);
 		/* If a hugepage was detected and ODP wasn't set for, the umem

@@ -445,13 +425,13 @@ int ib_umem_odp_map_dma_and_lock(struct ib_umem_odp *umem_odp, u64 user_virt,
 		}
 
 		ret = ib_umem_odp_map_dma_single_page(
-				umem_odp, dma_index, hmm_pfn_to_page(range.hmm_pfns[pfn_index]),
-				access_mask);
+				umem_odp, dma_index, hmm_pfn_to_page(range.hmm_pfns[pfn_index]));
 		if (ret < 0) {
 			ibdev_dbg(umem_odp->umem.ibdev,
 				  "ib_umem_odp_map_dma_single_page failed with error %d\n", ret);
 			break;
 		}
+		range.hmm_pfns[pfn_index] |= HMM_PFN_DMA_MAPPED;
 	}
 	/* upon success lock should stay on hold for the callee */
 	if (!ret)

@@ -471,7 +451,6 @@ EXPORT_SYMBOL(ib_umem_odp_map_dma_and_lock);
 void ib_umem_odp_unmap_dma_pages(struct ib_umem_odp *umem_odp, u64 virt,
 				 u64 bound)
 {
-	dma_addr_t dma_addr;
 	dma_addr_t dma;
 	int idx;
 	u64 addr;

@@ -482,34 +461,35 @@ void ib_umem_odp_unmap_dma_pages(struct ib_umem_odp *umem_odp, u64 virt,
 	virt = max_t(u64, virt, ib_umem_start(umem_odp));
 	bound = min_t(u64, bound, ib_umem_end(umem_odp));
 	for (addr = virt; addr < bound; addr += BIT(umem_odp->page_shift)) {
+		unsigned long pfn_idx = (addr - ib_umem_start(umem_odp)) >> PAGE_SHIFT;
+		struct page *page = hmm_pfn_to_page(umem_odp->pfn_list[pfn_idx]);
+
 		idx = (addr - ib_umem_start(umem_odp)) >> umem_odp->page_shift;
 		dma = umem_odp->dma_list[idx];
 
-		/* The access flags guaranteed a valid DMA address in case was NULL */
-		if (dma) {
-			unsigned long pfn_idx = (addr - ib_umem_start(umem_odp)) >> PAGE_SHIFT;
-			struct page *page = hmm_pfn_to_page(umem_odp->pfn_list[pfn_idx]);
-
-			dma_addr = dma & ODP_DMA_ADDR_MASK;
-			ib_dma_unmap_page(dev, dma_addr,
-					  BIT(umem_odp->page_shift),
-					  DMA_BIDIRECTIONAL);
-			if (dma & ODP_WRITE_ALLOWED_BIT) {
-				struct page *head_page = compound_head(page);
-				/*
-				 * set_page_dirty prefers being called with
-				 * the page lock. However, MMU notifiers are
-				 * called sometimes with and sometimes without
-				 * the lock. We rely on the umem_mutex instead
-				 * to prevent other mmu notifiers from
-				 * continuing and allowing the page mapping to
-				 * be removed.
-				 */
-				set_page_dirty(head_page);
-			}
-			umem_odp->dma_list[idx] = 0;
-			umem_odp->npages--;
+		if (!(umem_odp->pfn_list[pfn_idx] & HMM_PFN_VALID))
+			goto clear;
+		if (!(umem_odp->pfn_list[pfn_idx] & HMM_PFN_DMA_MAPPED))
+			goto clear;
+
+		ib_dma_unmap_page(dev, dma, BIT(umem_odp->page_shift),
+				  DMA_BIDIRECTIONAL);
+		if (umem_odp->pfn_list[pfn_idx] & HMM_PFN_WRITE) {
+			struct page *head_page = compound_head(page);
+			/*
+			 * set_page_dirty prefers being called with
+			 * the page lock. However, MMU notifiers are
+			 * called sometimes with and sometimes without
+			 * the lock. We rely on the umem_mutex instead
+			 * to prevent other mmu notifiers from
+			 * continuing and allowing the page mapping to
+			 * be removed.
+			 */
+			set_page_dirty(head_page);
 		}
+		umem_odp->npages--;
+clear:
+		umem_odp->pfn_list[pfn_idx] &= ~HMM_PFN_FLAGS;
 	}
 }
 EXPORT_SYMBOL(ib_umem_odp_unmap_dma_pages);

index 23fd72f7f63d..3e4aaa6319db 100644
@@ -336,6 +336,7 @@ struct mlx5_ib_flow_db {
 #define MLX5_IB_UPD_XLT_PD	      BIT(4)
 #define MLX5_IB_UPD_XLT_ACCESS	      BIT(5)
 #define MLX5_IB_UPD_XLT_INDIRECT      BIT(6)
+#define MLX5_IB_UPD_XLT_DOWNGRADE     BIT(7)
 
 /* Private QP creation flags to be passed in ib_qp_init_attr.create_flags.
  *

index 4b37446758fd..78887500ce15 100644
@@ -34,6 +34,7 @@
 #include <linux/kernel.h>
 #include <linux/dma-buf.h>
 #include <linux/dma-resv.h>
+#include <linux/hmm.h>
 
 #include "mlx5_ib.h"
 #include "cmd.h"

@@ -158,22 +159,12 @@ static void populate_klm(struct mlx5_klm *pklm, size_t idx, size_t nentries,
 	}
 }
 
-static u64 umem_dma_to_mtt(dma_addr_t umem_dma)
-{
-	u64 mtt_entry = umem_dma & ODP_DMA_ADDR_MASK;
-
-	if (umem_dma & ODP_READ_ALLOWED_BIT)
-		mtt_entry |= MLX5_IB_MTT_READ;
-	if (umem_dma & ODP_WRITE_ALLOWED_BIT)
-		mtt_entry |= MLX5_IB_MTT_WRITE;
-
-	return mtt_entry;
-}
-
 static void populate_mtt(__be64 *pas, size_t idx, size_t nentries,
 			 struct mlx5_ib_mr *mr, int flags)
 {
 	struct ib_umem_odp *odp = to_ib_umem_odp(mr->umem);
+	bool downgrade = flags & MLX5_IB_UPD_XLT_DOWNGRADE;
+	unsigned long pfn;
 	dma_addr_t pa;
 	size_t i;
 

@@ -181,8 +172,17 @@ static void populate_mtt(__be64 *pas, size_t idx, size_t nentries,
 		return;
 
 	for (i = 0; i < nentries; i++) {
+		pfn = odp->pfn_list[idx + i];
+		if (!(pfn & HMM_PFN_VALID))
+			/* ODP initialization */
+			continue;
+
 		pa = odp->dma_list[idx + i];
-		pas[i] = cpu_to_be64(umem_dma_to_mtt(pa));
+		pa |= MLX5_IB_MTT_READ;
+		if ((pfn & HMM_PFN_WRITE) && !downgrade)
+			pa |= MLX5_IB_MTT_WRITE;
+
+		pas[i] = cpu_to_be64(pa);
 	}
 }
 

@@ -286,8 +286,7 @@ static bool mlx5_ib_invalidate_range(struct mmu_interval_notifier *mni,
 		 * estimate the cost of another UMR vs. the cost of bigger
 		 * UMR.
 		 */
-		if (umem_odp->dma_list[idx] &
-		    (ODP_READ_ALLOWED_BIT | ODP_WRITE_ALLOWED_BIT)) {
+		if (umem_odp->pfn_list[idx] & HMM_PFN_VALID) {
 			if (!in_block) {
 				blk_start_idx = idx;
 				in_block = 1;

@@ -668,7 +667,7 @@ static int pagefault_real_mr(struct mlx5_ib_mr *mr, struct ib_umem_odp *odp,
 {
 	int page_shift, ret, np;
 	bool downgrade = flags & MLX5_PF_FLAGS_DOWNGRADE;
-	u64 access_mask;
+	u64 access_mask = 0;
 	u64 start_idx;
 	bool fault = !(flags & MLX5_PF_FLAGS_SNAPSHOT);
 	u32 xlt_flags = MLX5_IB_UPD_XLT_ATOMIC;

@@ -676,12 +675,14 @@ static int pagefault_real_mr(struct mlx5_ib_mr *mr, struct ib_umem_odp *odp,
 	if (flags & MLX5_PF_FLAGS_ENABLE)
 		xlt_flags |= MLX5_IB_UPD_XLT_ENABLE;
 
+	if (flags & MLX5_PF_FLAGS_DOWNGRADE)
+		xlt_flags |= MLX5_IB_UPD_XLT_DOWNGRADE;
+
 	page_shift = odp->page_shift;
 	start_idx = (user_va - ib_umem_start(odp)) >> page_shift;
-	access_mask = ODP_READ_ALLOWED_BIT;
 
 	if (odp->umem.writable && !downgrade)
-		access_mask |= ODP_WRITE_ALLOWED_BIT;
+		access_mask |= HMM_PFN_WRITE;
 
 	np = ib_umem_odp_map_dma_and_lock(odp, user_va, bcnt, access_mask, fault);
 	if (np < 0)

index 0844c1d05ac6..a345c26a745d 100644
@@ -8,6 +8,7 @@
 
 #include <rdma/ib_umem.h>
 #include <rdma/ib_verbs.h>
+#include <linux/hmm.h>
 
 struct ib_umem_odp {
 	struct ib_umem umem;

@@ -67,19 +68,6 @@ static inline size_t ib_umem_odp_num_pages(struct ib_umem_odp *umem_odp)
 	       umem_odp->page_shift;
 }
 
-/*
- * The lower 2 bits of the DMA address signal the R/W permissions for
- * the entry. To upgrade the permissions, provide the appropriate
- * bitmask to the map_dma_pages function.
- *
- * Be aware that upgrading a mapped address might result in change of
- * the DMA address for the page.
- */
-#define ODP_READ_ALLOWED_BIT  (1<<0ULL)
-#define ODP_WRITE_ALLOWED_BIT (1<<1ULL)
-
-#define ODP_DMA_ADDR_MASK (~(ODP_READ_ALLOWED_BIT | ODP_WRITE_ALLOWED_BIT))
-
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
 
 struct ib_umem_odp *

index 9dba369365af..30cd8f353476 100644
@@ -41,6 +41,7 @@
 #include <linux/hugetlb.h>
 #include <linux/interval_tree.h>
 #include <linux/hmm.h>
+#include <linux/hmm-dma.h>
 #include <linux/pagemap.h>
 
 #include <rdma/ib_umem_odp.h>

@@ -50,6 +51,7 @@
 static inline int ib_init_umem_odp(struct ib_umem_odp *umem_odp,
 				   const struct mmu_interval_notifier_ops *ops)
 {
+	struct ib_device *dev = umem_odp->umem.ibdev;
 	int ret;
 
 	umem_odp->umem.is_odp = 1;

@@ -59,7 +61,6 @@ static inline int ib_init_umem_odp(struct ib_umem_odp *umem_odp,
 		size_t page_size = 1UL << umem_odp->page_shift;
 		unsigned long start;
 		unsigned long end;
-		size_t ndmas, npfns;
 
 		start = ALIGN_DOWN(umem_odp->umem.address, page_size);
 		if (check_add_overflow(umem_odp->umem.address,

@@ -70,36 +71,23 @@ static inline int ib_init_umem_odp(struct ib_umem_odp *umem_odp,
 		if (unlikely(end < page_size))
 			return -EOVERFLOW;
 
-		ndmas = (end - start) >> umem_odp->page_shift;
-		if (!ndmas)
-			return -EINVAL;
-
-		npfns = (end - start) >> PAGE_SHIFT;
-		umem_odp->pfn_list = kvcalloc(
-			npfns, sizeof(*umem_odp->pfn_list), GFP_KERNEL);
-		if (!umem_odp->pfn_list)
-			return -ENOMEM;
-
-		umem_odp->dma_list = kvcalloc(
-			ndmas, sizeof(*umem_odp->dma_list), GFP_KERNEL);
-		if (!umem_odp->dma_list) {
-			ret = -ENOMEM;
-			goto out_pfn_list;
-		}
+		ret = hmm_dma_map_alloc(dev->dma_device, &umem_odp->map,
+					(end - start) >> PAGE_SHIFT,
+					1 << umem_odp->page_shift);
+		if (ret)
+			return ret;
 
 		ret = mmu_interval_notifier_insert(&umem_odp->notifier,
 						   umem_odp->umem.owning_mm,
 						   start, end - start, ops);
 		if (ret)
-			goto out_dma_list;
+			goto out_free_map;
 	}
 
 	return 0;
 
-out_dma_list:
-	kvfree(umem_odp->dma_list);
-out_pfn_list:
-	kvfree(umem_odp->pfn_list);
+out_free_map:
+	hmm_dma_map_free(dev->dma_device, &umem_odp->map);
 	return ret;
 }
 

@@ -262,6 +250,8 @@ EXPORT_SYMBOL(ib_umem_odp_get);
 
 void ib_umem_odp_release(struct ib_umem_odp *umem_odp)
 {
+	struct ib_device *dev = umem_odp->umem.ibdev;
+
 	/*
 	 * Ensure that no more pages are mapped in the umem.
 	 *

@@ -274,48 +264,17 @@ void ib_umem_odp_release(struct ib_umem_odp *umem_odp)
 					    ib_umem_end(umem_odp));
 		mutex_unlock(&umem_odp->umem_mutex);
 		mmu_interval_notifier_remove(&umem_odp->notifier);
-		kvfree(umem_odp->dma_list);
-		kvfree(umem_odp->pfn_list);
+		hmm_dma_map_free(dev->dma_device, &umem_odp->map);
 	}
 	put_pid(umem_odp->tgid);
 	kfree(umem_odp);
 }
 EXPORT_SYMBOL(ib_umem_odp_release);
 
-/*
- * Map for DMA and insert a single page into the on-demand paging page tables.
- *
- * @umem: the umem to insert the page to.
- * @dma_index: index in the umem to add the dma to.
- * @page: the page struct to map and add.
- * @access_mask: access permissions needed for this page.
- *
- * The function returns -EFAULT if the DMA mapping operation fails.
- *
- */
-static int ib_umem_odp_map_dma_single_page(
-		struct ib_umem_odp *umem_odp,
-		unsigned int dma_index,
-		struct page *page)
-{
-	struct ib_device *dev = umem_odp->umem.ibdev;
-	dma_addr_t *dma_addr = &umem_odp->dma_list[dma_index];
-
-	*dma_addr = ib_dma_map_page(dev, page, 0, 1 << umem_odp->page_shift,
-				    DMA_BIDIRECTIONAL);
-	if (ib_dma_mapping_error(dev, *dma_addr)) {
-		*dma_addr = 0;
-		return -EFAULT;
-	}
-	umem_odp->npages++;
-	return 0;
-}
-
 /**
  * ib_umem_odp_map_dma_and_lock - DMA map userspace memory in an ODP MR and lock it.
  *
  * Maps the range passed in the argument to DMA addresses.
- * The DMA addresses of the mapped pages is updated in umem_odp->dma_list.
  * Upon success the ODP MR will be locked to let caller complete its device
  * page table update.
  *

@@ -372,7 +331,7 @@ int ib_umem_odp_map_dma_and_lock(struct ib_umem_odp *umem_odp, u64 user_virt,
 			range.default_flags |= HMM_PFN_REQ_WRITE;
 	}
 
-	range.hmm_pfns = &(umem_odp->pfn_list[pfn_start_idx]);
+	range.hmm_pfns = &(umem_odp->map.pfn_list[pfn_start_idx]);
 	timeout = jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
 
 retry:

@@ -423,15 +382,6 @@ int ib_umem_odp_map_dma_and_lock(struct ib_umem_odp *umem_odp, u64 user_virt,
 				  __func__, hmm_order, page_shift);
 			break;
 		}
-
-		ret = ib_umem_odp_map_dma_single_page(
-				umem_odp, dma_index, hmm_pfn_to_page(range.hmm_pfns[pfn_index]));
-		if (ret < 0) {
-			ibdev_dbg(umem_odp->umem.ibdev,
-				  "ib_umem_odp_map_dma_single_page failed with error %d\n", ret);
-			break;
-		}
-		range.hmm_pfns[pfn_index] |= HMM_PFN_DMA_MAPPED;
 	}
 	/* upon success lock should stay on hold for the callee */
 	if (!ret)

@@ -451,30 +401,23 @@ EXPORT_SYMBOL(ib_umem_odp_map_dma_and_lock);
 void ib_umem_odp_unmap_dma_pages(struct ib_umem_odp *umem_odp, u64 virt,
 				 u64 bound)
 {
-	dma_addr_t dma;
-	int idx;
-	u64 addr;
 	struct ib_device *dev = umem_odp->umem.ibdev;
+	u64 addr;
 
 	lockdep_assert_held(&umem_odp->umem_mutex);
 
 	virt = max_t(u64, virt, ib_umem_start(umem_odp));
 	bound = min_t(u64, bound, ib_umem_end(umem_odp));
 	for (addr = virt; addr < bound; addr += BIT(umem_odp->page_shift)) {
-		unsigned long pfn_idx = (addr - ib_umem_start(umem_odp)) >> PAGE_SHIFT;
-		struct page *page = hmm_pfn_to_page(umem_odp->pfn_list[pfn_idx]);
-
-		idx = (addr - ib_umem_start(umem_odp)) >> umem_odp->page_shift;
-		dma = umem_odp->dma_list[idx];
+		u64 offset = addr - ib_umem_start(umem_odp);
+		size_t idx = offset >> umem_odp->page_shift;
+		unsigned long pfn = umem_odp->map.pfn_list[idx];
 
-		if (!(umem_odp->pfn_list[pfn_idx] & HMM_PFN_VALID))
-			goto clear;
-		if (!(umem_odp->pfn_list[pfn_idx] & HMM_PFN_DMA_MAPPED))
+		if (!hmm_dma_unmap_pfn(dev->dma_device, &umem_odp->map, idx))
 			goto clear;
 
-		ib_dma_unmap_page(dev, dma, BIT(umem_odp->page_shift),
-				  DMA_BIDIRECTIONAL);
-		if (umem_odp->pfn_list[pfn_idx] & HMM_PFN_WRITE) {
+		if (pfn & HMM_PFN_WRITE) {
+			struct page *page = hmm_pfn_to_page(pfn);
 			struct page *head_page = compound_head(page);
 			/*
 			 * set_page_dirty prefers being called with

@@ -489,7 +432,7 @@ void ib_umem_odp_unmap_dma_pages(struct ib_umem_odp *umem_odp, u64 virt,
 		}
 		umem_odp->npages--;
 clear:
-		umem_odp->pfn_list[pfn_idx] &= ~HMM_PFN_FLAGS;
+		umem_odp->map.pfn_list[idx] &= ~HMM_PFN_FLAGS;
 	}
 }
 EXPORT_SYMBOL(ib_umem_odp_unmap_dma_pages);

index 3e4aaa6319db..1bae5595c729 100644
@@ -1444,8 +1444,8 @@ void mlx5_ib_odp_cleanup_one(struct mlx5_ib_dev *ibdev);
 int __init mlx5_ib_odp_init(void);
 void mlx5_ib_odp_cleanup(void);
 int mlx5_odp_init_mkey_cache(struct mlx5_ib_dev *dev);
-void mlx5_odp_populate_xlt(void *xlt, size_t idx, size_t nentries,
-			   struct mlx5_ib_mr *mr, int flags);
+int mlx5_odp_populate_xlt(void *xlt, size_t idx, size_t nentries,
+			  struct mlx5_ib_mr *mr, int flags);
 
 int mlx5_ib_advise_mr_prefetch(struct ib_pd *pd,
 			       enum ib_uverbs_advise_mr_advice advice,

@@ -1466,8 +1466,11 @@ static inline int mlx5_odp_init_mkey_cache(struct mlx5_ib_dev *dev)
 {
 	return 0;
 }
-static inline void mlx5_odp_populate_xlt(void *xlt, size_t idx, size_t nentries,
-					 struct mlx5_ib_mr *mr, int flags) {}
+static inline int mlx5_odp_populate_xlt(void *xlt, size_t idx, size_t nentries,
+					struct mlx5_ib_mr *mr, int flags)
+{
+	return -EOPNOTSUPP;
+}
 
 static inline int
 mlx5_ib_advise_mr_prefetch(struct ib_pd *pd,

index 78887500ce15..fbb2a5670c32 100644
@@ -35,6 +35,8 @@
 #include <linux/dma-buf.h>
 #include <linux/dma-resv.h>
 #include <linux/hmm.h>
+#include <linux/hmm-dma.h>
+#include <linux/pci-p2pdma.h>
 
 #include "mlx5_ib.h"
 #include "cmd.h"

@@ -159,40 +161,50 @@ static void populate_klm(struct mlx5_klm *pklm, size_t idx, size_t nentries,
 	}
 }
 
-static void populate_mtt(__be64 *pas, size_t idx, size_t nentries,
-			 struct mlx5_ib_mr *mr, int flags)
+static int populate_mtt(__be64 *pas, size_t start, size_t nentries,
+			struct mlx5_ib_mr *mr, int flags)
 {
 	struct ib_umem_odp *odp = to_ib_umem_odp(mr->umem);
 	bool downgrade = flags & MLX5_IB_UPD_XLT_DOWNGRADE;
-	unsigned long pfn;
-	dma_addr_t pa;
+	struct pci_p2pdma_map_state p2pdma_state = {};
+	struct ib_device *dev = odp->umem.ibdev;
 	size_t i;
 
 	if (flags & MLX5_IB_UPD_XLT_ZAP)
-		return;
+		return 0;
 
 	for (i = 0; i < nentries; i++) {
-		pfn = odp->pfn_list[idx + i];
+		unsigned long pfn = odp->map.pfn_list[start + i];
+		dma_addr_t dma_addr;
+
+		pfn = odp->map.pfn_list[start + i];
 		if (!(pfn & HMM_PFN_VALID))
 			/* ODP initialization */
 			continue;
 
-		pa = odp->dma_list[idx + i];
-		pa |= MLX5_IB_MTT_READ;
+		dma_addr = hmm_dma_map_pfn(dev->dma_device, &odp->map,
+					   start + i, &p2pdma_state);
+		if (ib_dma_mapping_error(dev, dma_addr))
+			return -EFAULT;
+
+		dma_addr |= MLX5_IB_MTT_READ;
 		if ((pfn & HMM_PFN_WRITE) && !downgrade)
-			pa |= MLX5_IB_MTT_WRITE;
+			dma_addr |= MLX5_IB_MTT_WRITE;
 
-		pas[i] = cpu_to_be64(pa);
+		pas[i] = cpu_to_be64(dma_addr);
+		odp->npages++;
 	}
+	return 0;
 }
 
-void mlx5_odp_populate_xlt(void *xlt, size_t idx, size_t nentries,
-			   struct mlx5_ib_mr *mr, int flags)
+int mlx5_odp_populate_xlt(void *xlt, size_t idx, size_t nentries,
+			  struct mlx5_ib_mr *mr, int flags)
 {
 	if (flags & MLX5_IB_UPD_XLT_INDIRECT) {
 		populate_klm(xlt, idx, nentries, mr, flags);
+		return 0;
 	} else {
-		populate_mtt(xlt, idx, nentries, mr, flags);
+		return populate_mtt(xlt, idx, nentries, mr, flags);
 	}
 }
 

@@ -286,7 +298,7 @@ static bool mlx5_ib_invalidate_range(struct mmu_interval_notifier *mni,
 		 * estimate the cost of another UMR vs. the cost of bigger
 		 * UMR.
 		 */
-		if (umem_odp->pfn_list[idx] & HMM_PFN_VALID) {
+		if (umem_odp->map.pfn_list[idx] & HMM_PFN_VALID) {
 			if (!in_block) {
 				blk_start_idx = idx;
 				in_block = 1;

index 887fd6fa3ba9..d7fa94ab23cf 100644
@@ -811,7 +811,17 @@ int mlx5r_umr_update_xlt(struct mlx5_ib_mr *mr, u64 idx, int npages,
 		size_to_map = npages * desc_size;
 		dma_sync_single_for_cpu(ddev, sg.addr, sg.length,
 					DMA_TO_DEVICE);
-		mlx5_odp_populate_xlt(xlt, idx, npages, mr, flags);
+		/*
+		 * npages is the maximum number of pages to map, but we
+		 * can't guarantee that all pages are actually mapped.
+		 *
+		 * For example, if page is p2p of type which is not supported
+		 * for mapping, the number of pages mapped will be less than
+		 * requested.
+		 */
+		err = mlx5_odp_populate_xlt(xlt, idx, npages, mr, flags);
+		if (err)
+			return err;
 		dma_sync_single_for_device(ddev, sg.addr, sg.length,
 					   DMA_TO_DEVICE);
 		sg.length = ALIGN(size_to_map, MLX5_UMR_FLEX_ALIGNMENT);

index a345c26a745d..2a24bf791c10 100644
@@ -8,24 +8,17 @@
 
 #include <rdma/ib_umem.h>
 #include <rdma/ib_verbs.h>
-#include <linux/hmm.h>
+#include <linux/hmm-dma.h>
 
 struct ib_umem_odp {
 	struct ib_umem umem;
 	struct mmu_interval_notifier notifier;
 	struct pid *tgid;
 
-	/* An array of the pfns included in the on-demand paging umem. */
-	unsigned long *pfn_list;
+	struct hmm_dma_map map;
 
 	/*
-	 * An array with DMA addresses mapped for pfns in pfn_list.
-	 * The lower two bits designate access permissions.
-	 * See ODP_READ_ALLOWED_BIT and ODP_WRITE_ALLOWED_BIT.
-	 */
-	dma_addr_t		*dma_list;
-	/*
-	 * The umem_mutex protects the page_list and dma_list fields of an ODP
+	 * The umem_mutex protects the page_list field of an ODP
 	 * umem, allowing only a single thread to map/unmap pages. The mutex
 	 * also protects access to the mmu notifier counters.
 	 */

index 41a4b0cf4297..fdc3e515741f 100644
@@ -318,8 +318,7 @@ static int _create_mkey(struct mlx5_core_dev *mdev, u32 pdn,
 			struct mlx5_vhca_recv_buf *recv_buf,
 			u32 *mkey)
 {
-	size_t npages = buf ? DIV_ROUND_UP(buf->allocated_length, PAGE_SIZE) :
-				recv_buf->npages;
+	size_t npages = buf ? buf->npages : recv_buf->npages;
 	int err = 0, inlen;
 	__be64 *mtt;
 	void *mkc;

@@ -375,7 +374,7 @@ static int mlx5vf_dma_data_buffer(struct mlx5_vhca_data_buffer *buf)
 	if (mvdev->mdev_detach)
 		return -ENOTCONN;
 
-	if (buf->dmaed || !buf->allocated_length)
+	if (buf->dmaed || !buf->npages)
 		return -EINVAL;
 
 	ret = dma_map_sgtable(mdev->device, &buf->table.sgt, buf->dma_dir, 0);

@@ -444,7 +443,7 @@ static int mlx5vf_add_migration_pages(struct mlx5_vhca_data_buffer *buf,
 
 		if (ret)
 			goto err;
-		buf->allocated_length += filled * PAGE_SIZE;
+		buf->npages += filled;
 		/* clean input for another bulk allocation */
 		memset(page_list, 0, filled * sizeof(*page_list));
 		to_fill = min_t(unsigned int, to_alloc,

@@ -460,8 +459,7 @@ static int mlx5vf_add_migration_pages(struct mlx5_vhca_data_buffer *buf,
 }
 
 struct mlx5_vhca_data_buffer *
-mlx5vf_alloc_data_buffer(struct mlx5_vf_migration_file *migf,
-			 size_t length,
+mlx5vf_alloc_data_buffer(struct mlx5_vf_migration_file *migf, u32 npages,
 			 enum dma_data_direction dma_dir)
 {
 	struct mlx5_vhca_data_buffer *buf;

@@ -473,9 +471,8 @@ mlx5vf_alloc_data_buffer(struct mlx5_vf_migration_file *migf,
 
 	buf->dma_dir = dma_dir;
 	buf->migf = migf;
-	if (length) {
-		ret = mlx5vf_add_migration_pages(buf,
-				DIV_ROUND_UP_ULL(length, PAGE_SIZE));
+	if (npages) {
+		ret = mlx5vf_add_migration_pages(buf, npages);
 		if (ret)
 			goto end;
 

@@ -501,8 +498,8 @@ void mlx5vf_put_data_buffer(struct mlx5_vhca_data_buffer *buf)
 }
 
 struct mlx5_vhca_data_buffer *
-mlx5vf_get_data_buffer(struct mlx5_vf_migration_file *migf,
-		       size_t length, enum dma_data_direction dma_dir)
+mlx5vf_get_data_buffer(struct mlx5_vf_migration_file *migf, u32 npages,
+		       enum dma_data_direction dma_dir)
 {
 	struct mlx5_vhca_data_buffer *buf, *temp_buf;
 	struct list_head free_list;

@@ -517,7 +514,7 @@ mlx5vf_get_data_buffer(struct mlx5_vf_migration_file *migf,
 	list_for_each_entry_safe(buf, temp_buf, &migf->avail_list, buf_elm) {
 		if (buf->dma_dir == dma_dir) {
 			list_del_init(&buf->buf_elm);
-			if (buf->allocated_length >= length) {
+			if (buf->npages >= npages) {
 				spin_unlock_irq(&migf->list_lock);
 				goto found;
 			}

@@ -531,7 +528,7 @@ mlx5vf_get_data_buffer(struct mlx5_vf_migration_file *migf,
 		}
 	}
 	spin_unlock_irq(&migf->list_lock);
-	buf = mlx5vf_alloc_data_buffer(migf, length, dma_dir);
+	buf = mlx5vf_alloc_data_buffer(migf, npages, dma_dir);
 
 found:
 	while ((temp_buf = list_first_entry_or_null(&free_list,

@@ -712,7 +709,7 @@ int mlx5vf_cmd_save_vhca_state(struct mlx5vf_pci_core_device *mvdev,
 	MLX5_SET(save_vhca_state_in, in, op_mod, 0);
 	MLX5_SET(save_vhca_state_in, in, vhca_id, mvdev->vhca_id);
 	MLX5_SET(save_vhca_state_in, in, mkey, buf->mkey);
-	MLX5_SET(save_vhca_state_in, in, size, buf->allocated_length);
+	MLX5_SET(save_vhca_state_in, in, size, buf->npages * PAGE_SIZE);
 	MLX5_SET(save_vhca_state_in, in, incremental, inc);
 	MLX5_SET(save_vhca_state_in, in, set_track, track);
 

@@ -734,8 +731,11 @@ int mlx5vf_cmd_save_vhca_state(struct mlx5vf_pci_core_device *mvdev,
 	}
 
 	if (!header_buf) {
-		header_buf = mlx5vf_get_data_buffer(migf,
-			sizeof(struct mlx5_vf_migration_header), DMA_NONE);
+		header_buf = mlx5vf_get_data_buffer(
+			migf,
+			DIV_ROUND_UP(sizeof(struct mlx5_vf_migration_header),
+				     PAGE_SIZE),
+			DMA_NONE);
 		if (IS_ERR(header_buf)) {
 			err = PTR_ERR(header_buf);
 			goto err_free;

index df421dc6de04..7d4a833b6900 100644
@@ -56,7 +56,7 @@ struct mlx5_vhca_data_buffer {
 	struct sg_append_table table;
 	loff_t start_pos;
 	u64 length;
-	u64 allocated_length;
+	u32 npages;
 	u32 mkey;
 	enum dma_data_direction dma_dir;
 	u8 dmaed:1;

@@ -217,12 +217,12 @@ int mlx5vf_cmd_alloc_pd(struct mlx5_vf_migration_file *migf);
 void mlx5vf_cmd_dealloc_pd(struct mlx5_vf_migration_file *migf);
 void mlx5fv_cmd_clean_migf_resources(struct mlx5_vf_migration_file *migf);
 struct mlx5_vhca_data_buffer *
-mlx5vf_alloc_data_buffer(struct mlx5_vf_migration_file *migf,
-			 size_t length, enum dma_data_direction dma_dir);
+mlx5vf_alloc_data_buffer(struct mlx5_vf_migration_file *migf, u32 npages,
+			 enum dma_data_direction dma_dir);
 void mlx5vf_free_data_buffer(struct mlx5_vhca_data_buffer *buf);
 struct mlx5_vhca_data_buffer *
-mlx5vf_get_data_buffer(struct mlx5_vf_migration_file *migf,
-		       size_t length, enum dma_data_direction dma_dir);
+mlx5vf_get_data_buffer(struct mlx5_vf_migration_file *migf, u32 npages,
+		       enum dma_data_direction dma_dir);
 void mlx5vf_put_data_buffer(struct mlx5_vhca_data_buffer *buf);
 struct page *mlx5vf_get_migration_page(struct mlx5_vhca_data_buffer *buf,
 				       unsigned long offset);

142 lines not on this page · raw message

index fdc3e515741f..1832a6c1f35d 100644
@@ -313,39 +313,21 @@ static int mlx5vf_cmd_get_vhca_id(struct mlx5_core_dev *mdev, u16 function_id,
 	return ret;
 }
 
-static int _create_mkey(struct mlx5_core_dev *mdev, u32 pdn,
-			struct mlx5_vhca_data_buffer *buf,
-			struct mlx5_vhca_recv_buf *recv_buf,
-			u32 *mkey)
+static u32 *alloc_mkey_in(u32 npages, u32 pdn)
 {
-	size_t npages = buf ? buf->npages : recv_buf->npages;
-	int err = 0, inlen;
-	__be64 *mtt;
+	int inlen;
 	void *mkc;
 	u32 *in;
 
 	inlen = MLX5_ST_SZ_BYTES(create_mkey_in) +
-		sizeof(*mtt) * round_up(npages, 2);
+		sizeof(__be64) * round_up(npages, 2);
 
-	in = kvzalloc(inlen, GFP_KERNEL);
+	in = kvzalloc(inlen, GFP_KERNEL_ACCOUNT);
 	if (!in)
-		return -ENOMEM;
+		return NULL;
 
 	MLX5_SET(create_mkey_in, in, translations_octword_actual_size,
 		 DIV_ROUND_UP(npages, 2));
-	mtt = (__be64 *)MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt);
-
-	if (buf) {
-		struct sg_dma_page_iter dma_iter;
-
-		for_each_sgtable_dma_page(&buf->table.sgt, &dma_iter, 0)
-			*mtt++ = cpu_to_be64(sg_page_iter_dma_address(&dma_iter));
-	} else {
-		int i;
-
-		for (i = 0; i < npages; i++)
-			*mtt++ = cpu_to_be64(recv_buf->dma_addrs[i]);
-	}
 
 	mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry);
 	MLX5_SET(mkc, mkc, access_mode_1_0, MLX5_MKC_ACCESS_MODE_MTT);

@@ -359,9 +341,29 @@ static int _create_mkey(struct mlx5_core_dev *mdev, u32 pdn,
 	MLX5_SET(mkc, mkc, log_page_size, PAGE_SHIFT);
 	MLX5_SET(mkc, mkc, translations_octword_size, DIV_ROUND_UP(npages, 2));
 	MLX5_SET64(mkc, mkc, len, npages * PAGE_SIZE);
-	err = mlx5_core_create_mkey(mdev, mkey, in, inlen);
-	kvfree(in);
-	return err;
+
+	return in;
+}
+
+static int create_mkey(struct mlx5_core_dev *mdev, u32 npages,
+		       struct mlx5_vhca_data_buffer *buf, u32 *mkey_in,
+		       u32 *mkey)
+{
+	__be64 *mtt;
+	int inlen;
+
+	mtt = (__be64 *)MLX5_ADDR_OF(create_mkey_in, mkey_in, klm_pas_mtt);
+	if (buf) {
+		struct sg_dma_page_iter dma_iter;
+
+		for_each_sgtable_dma_page(&buf->table.sgt, &dma_iter, 0)
+			*mtt++ = cpu_to_be64(sg_page_iter_dma_address(&dma_iter));
+	}
+
+	inlen = MLX5_ST_SZ_BYTES(create_mkey_in) +
+		sizeof(__be64) * round_up(npages, 2);
+
+	return mlx5_core_create_mkey(mdev, mkey, mkey_in, inlen);
 }
 
 static int mlx5vf_dma_data_buffer(struct mlx5_vhca_data_buffer *buf)

@@ -374,20 +376,28 @@ static int mlx5vf_dma_data_buffer(struct mlx5_vhca_data_buffer *buf)
 	if (mvdev->mdev_detach)
 		return -ENOTCONN;
 
-	if (buf->dmaed || !buf->npages)
+	if (buf->mkey_in || !buf->npages)
 		return -EINVAL;
 
 	ret = dma_map_sgtable(mdev->device, &buf->table.sgt, buf->dma_dir, 0);
 	if (ret)
 		return ret;
 
-	ret = _create_mkey(mdev, buf->migf->pdn, buf, NULL, &buf->mkey);
-	if (ret)
+	buf->mkey_in = alloc_mkey_in(buf->npages, buf->migf->pdn);
+	if (!buf->mkey_in) {
+		ret = -ENOMEM;
 		goto err;
+	}
 
-	buf->dmaed = true;
+	ret = create_mkey(mdev, buf->npages, buf, buf->mkey_in, &buf->mkey);
+	if (ret)
+		goto err_create_mkey;
 
 	return 0;
+
+err_create_mkey:
+	kvfree(buf->mkey_in);
+	buf->mkey_in = NULL;
 err:
 	dma_unmap_sgtable(mdev->device, &buf->table.sgt, buf->dma_dir, 0);
 	return ret;

@@ -401,8 +411,9 @@ void mlx5vf_free_data_buffer(struct mlx5_vhca_data_buffer *buf)
 	lockdep_assert_held(&migf->mvdev->state_mutex);
 	WARN_ON(migf->mvdev->mdev_detach);
 
-	if (buf->dmaed) {
+	if (buf->mkey_in) {
 		mlx5_core_destroy_mkey(migf->mvdev->mdev, buf->mkey);
+		kvfree(buf->mkey_in);
 		dma_unmap_sgtable(migf->mvdev->mdev->device, &buf->table.sgt,
 				  buf->dma_dir, 0);
 	}

@@ -779,7 +790,7 @@ int mlx5vf_cmd_load_vhca_state(struct mlx5vf_pci_core_device *mvdev,
 	if (mvdev->mdev_detach)
 		return -ENOTCONN;
 
-	if (!buf->dmaed) {
+	if (!buf->mkey_in) {
 		err = mlx5vf_dma_data_buffer(buf);
 		if (err)
 			return err;

@@ -1380,56 +1391,54 @@ static int alloc_recv_pages(struct mlx5_vhca_recv_buf *recv_buf,
 	kvfree(recv_buf->page_list);
 	return -ENOMEM;
 }
+static void unregister_dma_pages(struct mlx5_core_dev *mdev, u32 npages,
+				 u32 *mkey_in)
+{
+	dma_addr_t addr;
+	__be64 *mtt;
+	int i;
+
+	mtt = (__be64 *)MLX5_ADDR_OF(create_mkey_in, mkey_in, klm_pas_mtt);
+	for (i = npages - 1; i >= 0; i--) {
+		addr = be64_to_cpu(mtt[i]);
+		dma_unmap_single(mdev->device, addr, PAGE_SIZE,
+				DMA_FROM_DEVICE);
+	}
+}
 
-static int register_dma_recv_pages(struct mlx5_core_dev *mdev,
-				   struct mlx5_vhca_recv_buf *recv_buf)
+static int register_dma_pages(struct mlx5_core_dev *mdev, u32 npages,
+			      struct page **page_list, u32 *mkey_in)
 {
-	int i, j;
+	dma_addr_t addr;
+	__be64 *mtt;
+	int i;
 
-	recv_buf->dma_addrs = kvcalloc(recv_buf->npages,
-				       sizeof(*recv_buf->dma_addrs),
-				       GFP_KERNEL_ACCOUNT);
-	if (!recv_buf->dma_addrs)
-		return -ENOMEM;
+	mtt = (__be64 *)MLX5_ADDR_OF(create_mkey_in, mkey_in, klm_pas_mtt);
 
-	for (i = 0; i < recv_buf->npages; i++) {
-		recv_buf->dma_addrs[i] = dma_map_page(mdev->device,
-						      recv_buf->page_list[i],
-						      0, PAGE_SIZE,
-						      DMA_FROM_DEVICE);
-		if (dma_mapping_error(mdev->device, recv_buf->dma_addrs[i]))
+	for (i = 0; i < npages; i++) {
+		addr = dma_map_page(mdev->device, page_list[i], 0, PAGE_SIZE,
+				    DMA_FROM_DEVICE);
+		if (dma_mapping_error(mdev->device, addr))
 			goto error;
+
+		*mtt++ = cpu_to_be64(addr);
 	}
+
 	return 0;
 
 error:
-	for (j = 0; j < i; j++)
-		dma_unmap_single(mdev->device, recv_buf->dma_addrs[j],
-				 PAGE_SIZE, DMA_FROM_DEVICE);
-
-	kvfree(recv_buf->dma_addrs);
+	unregister_dma_pages(mdev, i, mkey_in);
 	return -ENOMEM;
 }
 
-static void unregister_dma_recv_pages(struct mlx5_core_dev *mdev,
-				      struct mlx5_vhca_recv_buf *recv_buf)
-{
-	int i;
-
-	for (i = 0; i < recv_buf->npages; i++)
-		dma_unmap_single(mdev->device, recv_buf->dma_addrs[i],
-				 PAGE_SIZE, DMA_FROM_DEVICE);
-
-	kvfree(recv_buf->dma_addrs);
-}
-
 static void mlx5vf_free_qp_recv_resources(struct mlx5_core_dev *mdev,
 					  struct mlx5_vhca_qp *qp)
 {
 	struct mlx5_vhca_recv_buf *recv_buf = &qp->recv_buf;
 
 	mlx5_core_destroy_mkey(mdev, recv_buf->mkey);
-	unregister_dma_recv_pages(mdev, recv_buf);
+	unregister_dma_pages(mdev, recv_buf->npages, recv_buf->mkey_in);
+	kvfree(recv_buf->mkey_in);
 	free_recv_pages(&qp->recv_buf);
 }
 

@@ -1445,18 +1454,29 @@ static int mlx5vf_alloc_qp_recv_resources(struct mlx5_core_dev *mdev,
 	if (err < 0)
 		return err;
 
-	err = register_dma_recv_pages(mdev, recv_buf);
-	if (err)
+	recv_buf->mkey_in = alloc_mkey_in(npages, pdn);
+	if (!recv_buf->mkey_in) {
+		err = -ENOMEM;
 		goto end;
+	}
+
+	err = register_dma_pages(mdev, npages, recv_buf->page_list,
+				 recv_buf->mkey_in);
+	if (err)
+		goto err_register_dma;
 
-	err = _create_mkey(mdev, pdn, NULL, recv_buf, &recv_buf->mkey);
+	err = create_mkey(mdev, npages, NULL, recv_buf->mkey_in,
+			  &recv_buf->mkey);
 	if (err)
 		goto err_create_mkey;
 
 	return 0;
 
 err_create_mkey:
-	unregister_dma_recv_pages(mdev, recv_buf);
+	unregister_dma_pages(mdev, npages, recv_buf->mkey_in);
+err_register_dma:
+	kvfree(recv_buf->mkey_in);
+	recv_buf->mkey_in = NULL;
 end:
 	free_recv_pages(recv_buf);
 	return err;

index 7d4a833b6900..25dd6ff54591 100644
@@ -58,8 +58,8 @@ struct mlx5_vhca_data_buffer {
 	u64 length;
 	u32 npages;
 	u32 mkey;
+	u32 *mkey_in;
 	enum dma_data_direction dma_dir;
-	u8 dmaed:1;
 	u8 stop_copy_chunk_num;
 	struct list_head buf_elm;
 	struct mlx5_vf_migration_file *migf;

@@ -133,8 +133,8 @@ struct mlx5_vhca_cq {
 struct mlx5_vhca_recv_buf {
 	u32 npages;
 	struct page **page_list;
-	dma_addr_t *dma_addrs;
 	u32 next_rq_offset;
+	u32 *mkey_in;
 	u32 mkey;
 };
 

index 1832a6c1f35d..cde1481ed23c 100644
@@ -345,25 +345,81 @@ static u32 *alloc_mkey_in(u32 npages, u32 pdn)
 	return in;
 }
 
-static int create_mkey(struct mlx5_core_dev *mdev, u32 npages,
-		       struct mlx5_vhca_data_buffer *buf, u32 *mkey_in,
+static int create_mkey(struct mlx5_core_dev *mdev, u32 npages, u32 *mkey_in,
 		       u32 *mkey)
 {
+	int inlen = MLX5_ST_SZ_BYTES(create_mkey_in) +
+		sizeof(__be64) * round_up(npages, 2);
+
+	return mlx5_core_create_mkey(mdev, mkey, mkey_in, inlen);
+}
+
+static void unregister_dma_pages(struct mlx5_core_dev *mdev, u32 npages,
+				 u32 *mkey_in, struct dma_iova_state *state,
+				 enum dma_data_direction dir)
+{
+	dma_addr_t addr;
 	__be64 *mtt;
-	int inlen;
+	int i;
 
-	mtt = (__be64 *)MLX5_ADDR_OF(create_mkey_in, mkey_in, klm_pas_mtt);
-	if (buf) {
-		struct sg_dma_page_iter dma_iter;
+	WARN_ON_ONCE(dir == DMA_NONE);
 
-		for_each_sgtable_dma_page(&buf->table.sgt, &dma_iter, 0)
-			*mtt++ = cpu_to_be64(sg_page_iter_dma_address(&dma_iter));
+	if (dma_use_iova(state)) {
+		dma_iova_destroy(mdev->device, state, npages * PAGE_SIZE, dir, 0);
+	} else {
+		mtt = (__be64 *)MLX5_ADDR_OF(create_mkey_in, mkey_in,
+					     klm_pas_mtt);
+		for (i = npages - 1; i >= 0; i--) {
+			addr = be64_to_cpu(mtt[i]);
+			dma_unmap_page(mdev->device, addr, PAGE_SIZE, dir);
+		}
 	}
+}
 
-	inlen = MLX5_ST_SZ_BYTES(create_mkey_in) +
-		sizeof(__be64) * round_up(npages, 2);
+static int register_dma_pages(struct mlx5_core_dev *mdev, u32 npages,
+			      struct page **page_list, u32 *mkey_in,
+			      struct dma_iova_state *state,
+			      enum dma_data_direction dir)
+{
+	dma_addr_t addr;
+	size_t mapped = 0;
+	__be64 *mtt;
+	int i, err;
 
-	return mlx5_core_create_mkey(mdev, mkey, mkey_in, inlen);
+	WARN_ON_ONCE(dir == DMA_NONE);
+
+	mtt = (__be64 *)MLX5_ADDR_OF(create_mkey_in, mkey_in, klm_pas_mtt);
+
+	if (dma_iova_try_alloc(mdev->device, state, 0, npages * PAGE_SIZE)) {
+		addr = state->addr;
+		for (i = 0; i < npages; i++) {
+			err = dma_iova_link(mdev->device, state,
+					    page_to_phys(page_list[i]), mapped,
+					    PAGE_SIZE, dir, 0);
+			if (err)
+				goto error;
+			*mtt++ = cpu_to_be64(addr);
+			addr += PAGE_SIZE;
+			mapped += PAGE_SIZE;
+		}
+		err = dma_iova_sync(mdev->device, state, 0, mapped);
+		if (err)
+			goto error;
+	} else {
+		for (i = 0; i < npages; i++) {
+			addr = dma_map_page(mdev->device, page_list[i], 0,
+					    PAGE_SIZE, dir);
+			err = dma_mapping_error(mdev->device, addr);
+			if (err)
+				goto error;
+			*mtt++ = cpu_to_be64(addr);
+		}
+	}
+	return 0;
+
+error:
+	unregister_dma_pages(mdev, i, mkey_in, state, dir);
+	return err;
 }
 
 static int mlx5vf_dma_data_buffer(struct mlx5_vhca_data_buffer *buf)

@@ -379,96 +435,93 @@ static int mlx5vf_dma_data_buffer(struct mlx5_vhca_data_buffer *buf)
 	if (buf->mkey_in || !buf->npages)
 		return -EINVAL;
 
-	ret = dma_map_sgtable(mdev->device, &buf->table.sgt, buf->dma_dir, 0);
-	if (ret)
-		return ret;
-
 	buf->mkey_in = alloc_mkey_in(buf->npages, buf->migf->pdn);
-	if (!buf->mkey_in) {
-		ret = -ENOMEM;
-		goto err;
-	}
+	if (!buf->mkey_in)
+		return -ENOMEM;
 
-	ret = create_mkey(mdev, buf->npages, buf, buf->mkey_in, &buf->mkey);
+	ret = register_dma_pages(mdev, buf->npages, buf->page_list,
+				 buf->mkey_in, &buf->state, buf->dma_dir);
+	if (ret)
+		goto err_register_dma;
+
+	ret = create_mkey(mdev, buf->npages, buf->mkey_in, &buf->mkey);
 	if (ret)
 		goto err_create_mkey;
 
 	return 0;
 
 err_create_mkey:
+	unregister_dma_pages(mdev, buf->npages, buf->mkey_in, &buf->state,
+			     buf->dma_dir);
+err_register_dma:
 	kvfree(buf->mkey_in);
 	buf->mkey_in = NULL;
-err:
-	dma_unmap_sgtable(mdev->device, &buf->table.sgt, buf->dma_dir, 0);
 	return ret;
 }
 
+static void free_page_list(u32 npages, struct page **page_list)
+{
+	int i;
+
+	/* Undo alloc_pages_bulk_array() */
+	for (i = npages - 1; i >= 0; i--)
+		__free_page(page_list[i]);
+
+	kvfree(page_list);
+}
+
 void mlx5vf_free_data_buffer(struct mlx5_vhca_data_buffer *buf)
 {
-	struct mlx5_vf_migration_file *migf = buf->migf;
-	struct sg_page_iter sg_iter;
+	struct mlx5vf_pci_core_device *mvdev = buf->migf->mvdev;
+	struct mlx5_core_dev *mdev = mvdev->mdev;
 
-	lockdep_assert_held(&migf->mvdev->state_mutex);
-	WARN_ON(migf->mvdev->mdev_detach);
+	lockdep_assert_held(&mvdev->state_mutex);
+	WARN_ON(mvdev->mdev_detach);
 
 	if (buf->mkey_in) {
-		mlx5_core_destroy_mkey(migf->mvdev->mdev, buf->mkey);
+		mlx5_core_destroy_mkey(mdev, buf->mkey);
+		unregister_dma_pages(mdev, buf->npages, buf->mkey_in,
+				     &buf->state, buf->dma_dir);
 		kvfree(buf->mkey_in);
-		dma_unmap_sgtable(migf->mvdev->mdev->device, &buf->table.sgt,
-				  buf->dma_dir, 0);
 	}
 
-	/* Undo alloc_pages_bulk_array() */
-	for_each_sgtable_page(&buf->table.sgt, &sg_iter, 0)
-		__free_page(sg_page_iter_page(&sg_iter));
-	sg_free_append_table(&buf->table);
+	free_page_list(buf->npages, buf->page_list);
 	kfree(buf);
 }
 
-static int mlx5vf_add_migration_pages(struct mlx5_vhca_data_buffer *buf,
-				      unsigned int npages)
+static int mlx5vf_add_pages(struct page ***page_list, unsigned int npages)
 {
-	unsigned int to_alloc = npages;
-	struct page **page_list;
-	unsigned long filled;
-	unsigned int to_fill;
-	int ret;
+	unsigned int filled = 0, done = 0;
+	int i;
 
-	to_fill = min_t(unsigned int, npages, PAGE_SIZE / sizeof(*page_list));
-	page_list = kvzalloc(to_fill * sizeof(*page_list), GFP_KERNEL_ACCOUNT);
-	if (!page_list)
+	*page_list = kvcalloc(npages, sizeof(struct page *), GFP_KERNEL_ACCOUNT);
+	if (!*page_list)
 		return -ENOMEM;
 
-	do {
-		filled = alloc_pages_bulk_array(GFP_KERNEL_ACCOUNT, to_fill,
-						page_list);
-		if (!filled) {
-			ret = -ENOMEM;
+	for (;;) {
+		filled = alloc_pages_bulk_array(GFP_KERNEL_ACCOUNT,
+						npages - done,
+						*page_list + done);
+		if (!filled)
 			goto err;
-		}
-		to_alloc -= filled;
-		ret = sg_alloc_append_table_from_pages(
-			&buf->table, page_list, filled, 0,
-			filled << PAGE_SHIFT, UINT_MAX, SG_MAX_SINGLE_ALLOC,
-			GFP_KERNEL_ACCOUNT);
 
-		if (ret)
-			goto err;
-		buf->npages += filled;
-		/* clean input for another bulk allocation */
-		memset(page_list, 0, filled * sizeof(*page_list));
-		to_fill = min_t(unsigned int, to_alloc,
-				PAGE_SIZE / sizeof(*page_list));
-	} while (to_alloc > 0);
+		done += filled;
+		if (done == npages)
+			break;
+	}
 
-	kvfree(page_list);
 	return 0;
 
 err:
-	kvfree(page_list);
-	return ret;
+	for (i = 0; i < done; i++)
+		__free_page(*page_list[i]);
+
+	kvfree(*page_list);
+	*page_list = NULL;
+	return -ENOMEM;
 }
 
+
 struct mlx5_vhca_data_buffer *
 mlx5vf_alloc_data_buffer(struct mlx5_vf_migration_file *migf, u32 npages,
 			 enum dma_data_direction dma_dir)

@@ -483,10 +536,12 @@ mlx5vf_alloc_data_buffer(struct mlx5_vf_migration_file *migf, u32 npages,
 	buf->dma_dir = dma_dir;
 	buf->migf = migf;
 	if (npages) {
-		ret = mlx5vf_add_migration_pages(buf, npages);
+		ret = mlx5vf_add_pages(&buf->page_list, npages);
 		if (ret)
 			goto end;
 
+		buf->npages = npages;
+
 		if (dma_dir != DMA_NONE) {
 			ret = mlx5vf_dma_data_buffer(buf);
 			if (ret)

@@ -1345,101 +1400,16 @@ static void mlx5vf_destroy_qp(struct mlx5_core_dev *mdev,
 	kfree(qp);
 }
 
-static void free_recv_pages(struct mlx5_vhca_recv_buf *recv_buf)
-{
-	int i;
-
-	/* Undo alloc_pages_bulk_array() */
-	for (i = 0; i < recv_buf->npages; i++)
-		__free_page(recv_buf->page_list[i]);
-
-	kvfree(recv_buf->page_list);
-}
-
-static int alloc_recv_pages(struct mlx5_vhca_recv_buf *recv_buf,
-			    unsigned int npages)
-{
-	unsigned int filled = 0, done = 0;
-	int i;
-
-	recv_buf->page_list = kvcalloc(npages, sizeof(*recv_buf->page_list),
-				       GFP_KERNEL_ACCOUNT);
-	if (!recv_buf->page_list)
-		return -ENOMEM;
-
-	for (;;) {
-		filled = alloc_pages_bulk_array(GFP_KERNEL_ACCOUNT,
-						npages - done,
-						recv_buf->page_list + done);
-		if (!filled)
-			goto err;
-
-		done += filled;
-		if (done == npages)
-			break;
-	}
-
-	recv_buf->npages = npages;
-	return 0;
-
-err:
-	for (i = 0; i < npages; i++) {
-		if (recv_buf->page_list[i])
-			__free_page(recv_buf->page_list[i]);
-	}
-
-	kvfree(recv_buf->page_list);
-	return -ENOMEM;
-}
-static void unregister_dma_pages(struct mlx5_core_dev *mdev, u32 npages,
-				 u32 *mkey_in)
-{
-	dma_addr_t addr;
-	__be64 *mtt;
-	int i;
-
-	mtt = (__be64 *)MLX5_ADDR_OF(create_mkey_in, mkey_in, klm_pas_mtt);
-	for (i = npages - 1; i >= 0; i--) {
-		addr = be64_to_cpu(mtt[i]);
-		dma_unmap_single(mdev->device, addr, PAGE_SIZE,
-				DMA_FROM_DEVICE);
-	}
-}
-
-static int register_dma_pages(struct mlx5_core_dev *mdev, u32 npages,
-			      struct page **page_list, u32 *mkey_in)
-{
-	dma_addr_t addr;
-	__be64 *mtt;
-	int i;
-
-	mtt = (__be64 *)MLX5_ADDR_OF(create_mkey_in, mkey_in, klm_pas_mtt);
-
-	for (i = 0; i < npages; i++) {
-		addr = dma_map_page(mdev->device, page_list[i], 0, PAGE_SIZE,
-				    DMA_FROM_DEVICE);
-		if (dma_mapping_error(mdev->device, addr))
-			goto error;
-
-		*mtt++ = cpu_to_be64(addr);
-	}
-
-	return 0;
-
-error:
-	unregister_dma_pages(mdev, i, mkey_in);
-	return -ENOMEM;
-}
-
 static void mlx5vf_free_qp_recv_resources(struct mlx5_core_dev *mdev,
 					  struct mlx5_vhca_qp *qp)
 {
 	struct mlx5_vhca_recv_buf *recv_buf = &qp->recv_buf;
 
 	mlx5_core_destroy_mkey(mdev, recv_buf->mkey);
-	unregister_dma_pages(mdev, recv_buf->npages, recv_buf->mkey_in);
+	unregister_dma_pages(mdev, recv_buf->npages, recv_buf->mkey_in,
+			     &recv_buf->state, DMA_FROM_DEVICE);
 	kvfree(recv_buf->mkey_in);
-	free_recv_pages(&qp->recv_buf);
+	free_page_list(recv_buf->npages, recv_buf->page_list);
 }
 
 static int mlx5vf_alloc_qp_recv_resources(struct mlx5_core_dev *mdev,

@@ -1450,10 +1420,12 @@ static int mlx5vf_alloc_qp_recv_resources(struct mlx5_core_dev *mdev,
 	struct mlx5_vhca_recv_buf *recv_buf = &qp->recv_buf;
 	int err;
 
-	err = alloc_recv_pages(recv_buf, npages);
-	if (err < 0)
+	err = mlx5vf_add_pages(&recv_buf->page_list, npages);
+	if (err)
 		return err;
 
+	recv_buf->npages = npages;
+
 	recv_buf->mkey_in = alloc_mkey_in(npages, pdn);
 	if (!recv_buf->mkey_in) {
 		err = -ENOMEM;

@@ -1461,24 +1433,25 @@ static int mlx5vf_alloc_qp_recv_resources(struct mlx5_core_dev *mdev,
 	}
 
 	err = register_dma_pages(mdev, npages, recv_buf->page_list,
-				 recv_buf->mkey_in);
+				 recv_buf->mkey_in, &recv_buf->state,
+				 DMA_FROM_DEVICE);
 	if (err)
 		goto err_register_dma;
 
-	err = create_mkey(mdev, npages, NULL, recv_buf->mkey_in,
-			  &recv_buf->mkey);
+	err = create_mkey(mdev, npages, recv_buf->mkey_in, &recv_buf->mkey);
 	if (err)
 		goto err_create_mkey;
 
 	return 0;
 
 err_create_mkey:
-	unregister_dma_pages(mdev, npages, recv_buf->mkey_in);
+	unregister_dma_pages(mdev, npages, recv_buf->mkey_in, &recv_buf->state,
+			     DMA_FROM_DEVICE);
 err_register_dma:
 	kvfree(recv_buf->mkey_in);
 	recv_buf->mkey_in = NULL;
 end:
-	free_recv_pages(recv_buf);
+	free_page_list(npages, recv_buf->page_list);
 	return err;
 }
 

index 25dd6ff54591..d7821b5ca772 100644
@@ -53,7 +53,8 @@ struct mlx5_vf_migration_header {
 };
 
 struct mlx5_vhca_data_buffer {
-	struct sg_append_table table;
+	struct page **page_list;
+	struct dma_iova_state state;
 	loff_t start_pos;
 	u64 length;
 	u32 npages;

@@ -63,10 +64,6 @@ struct mlx5_vhca_data_buffer {
 	u8 stop_copy_chunk_num;
 	struct list_head buf_elm;
 	struct mlx5_vf_migration_file *migf;
-	/* Optimize mlx5vf_get_migration_page() for sequential access */
-	struct scatterlist *last_offset_sg;
-	unsigned int sg_last_entry;
-	unsigned long last_offset;
 };
 
 struct mlx5vf_async_data {

@@ -133,6 +130,7 @@ struct mlx5_vhca_cq {
 struct mlx5_vhca_recv_buf {
 	u32 npages;
 	struct page **page_list;
+	struct dma_iova_state state;
 	u32 next_rq_offset;
 	u32 *mkey_in;
 	u32 mkey;

@@ -224,8 +222,17 @@ struct mlx5_vhca_data_buffer *
 mlx5vf_get_data_buffer(struct mlx5_vf_migration_file *migf, u32 npages,
 		       enum dma_data_direction dma_dir);
 void mlx5vf_put_data_buffer(struct mlx5_vhca_data_buffer *buf);
-struct page *mlx5vf_get_migration_page(struct mlx5_vhca_data_buffer *buf,
-				       unsigned long offset);
+static inline struct page *
+mlx5vf_get_migration_page(struct mlx5_vhca_data_buffer *buf,
+			  unsigned long offset)
+{
+	int page_entry = offset / PAGE_SIZE;
+
+	if (page_entry >= buf->npages)
+		return NULL;
+
+	return buf->page_list[page_entry];
+}
 void mlx5vf_state_mutex_unlock(struct mlx5vf_pci_core_device *mvdev);
 void mlx5vf_disable_fds(struct mlx5vf_pci_core_device *mvdev,
 			enum mlx5_vf_migf_state *last_save_state);

index a1dbee3be1e0..d6cf97101c41 100644
@@ -34,37 +34,6 @@ static struct mlx5vf_pci_core_device *mlx5vf_drvdata(struct pci_dev *pdev)
 			    core_device);
 }
 
-struct page *
-mlx5vf_get_migration_page(struct mlx5_vhca_data_buffer *buf,
-			  unsigned long offset)
-{
-	unsigned long cur_offset = 0;
-	struct scatterlist *sg;
-	unsigned int i;
-
-	/* All accesses are sequential */
-	if (offset < buf->last_offset || !buf->last_offset_sg) {
-		buf->last_offset = 0;
-		buf->last_offset_sg = buf->table.sgt.sgl;
-		buf->sg_last_entry = 0;
-	}
-
-	cur_offset = buf->last_offset;
-
-	for_each_sg(buf->last_offset_sg, sg,
-			buf->table.sgt.orig_nents - buf->sg_last_entry, i) {
-		if (offset < sg->length + cur_offset) {
-			buf->last_offset_sg = sg;
-			buf->sg_last_entry += i;
-			buf->last_offset = cur_offset;
-			return nth_page(sg_page(sg),
-					(offset - cur_offset) / PAGE_SIZE);
-		}
-		cur_offset += sg->length;
-	}
-	return NULL;
-}
-
 static void mlx5vf_disable_fd(struct mlx5_vf_migration_file *migf)
 {
 	mutex_lock(&migf->lock);

index 30cd8f353476..51d518989914 100644
@@ -48,41 +48,44 @@
 
 #include "uverbs.h"
 
-static inline int ib_init_umem_odp(struct ib_umem_odp *umem_odp,
-				   const struct mmu_interval_notifier_ops *ops)
+static void ib_init_umem_implicit_odp(struct ib_umem_odp *umem_odp)
+{
+	umem_odp->is_implicit_odp = 1;
+	umem_odp->umem.is_odp = 1;
+	mutex_init(&umem_odp->umem_mutex);
+}
+
+static int ib_init_umem_odp(struct ib_umem_odp *umem_odp,
+			    const struct mmu_interval_notifier_ops *ops)
 {
 	struct ib_device *dev = umem_odp->umem.ibdev;
+	size_t page_size = 1UL << umem_odp->page_shift;
+	unsigned long start;
+	unsigned long end;
 	int ret;
 
 	umem_odp->umem.is_odp = 1;
 	mutex_init(&umem_odp->umem_mutex);
 
-	if (!umem_odp->is_implicit_odp) {
-		size_t page_size = 1UL << umem_odp->page_shift;
-		unsigned long start;
-		unsigned long end;
-
-		start = ALIGN_DOWN(umem_odp->umem.address, page_size);
-		if (check_add_overflow(umem_odp->umem.address,
-				       (unsigned long)umem_odp->umem.length,
-				       &end))
-			return -EOVERFLOW;
-		end = ALIGN(end, page_size);
-		if (unlikely(end < page_size))
-			return -EOVERFLOW;
-
-		ret = hmm_dma_map_alloc(dev->dma_device, &umem_odp->map,
-					(end - start) >> PAGE_SHIFT,
-					1 << umem_odp->page_shift);
-		if (ret)
-			return ret;
-
-		ret = mmu_interval_notifier_insert(&umem_odp->notifier,
-						   umem_odp->umem.owning_mm,
-						   start, end - start, ops);
-		if (ret)
-			goto out_free_map;
-	}
+	start = ALIGN_DOWN(umem_odp->umem.address, page_size);
+	if (check_add_overflow(umem_odp->umem.address,
+			       (unsigned long)umem_odp->umem.length, &end))
+		return -EOVERFLOW;
+	end = ALIGN(end, page_size);
+	if (unlikely(end < page_size))
+		return -EOVERFLOW;
+
+	ret = hmm_dma_map_alloc(dev->dma_device, &umem_odp->map,
+				(end - start) >> PAGE_SHIFT,
+				1 << umem_odp->page_shift);
+	if (ret)
+		return ret;
+
+	ret = mmu_interval_notifier_insert(&umem_odp->notifier,
+					   umem_odp->umem.owning_mm, start,
+					   end - start, ops);
+	if (ret)
+		goto out_free_map;
 
 	return 0;
 

@@ -106,7 +109,6 @@ struct ib_umem_odp *ib_umem_odp_alloc_implicit(struct ib_device *device,
 {
 	struct ib_umem *umem;
 	struct ib_umem_odp *umem_odp;
-	int ret;
 
 	if (access & IB_ACCESS_HUGETLB)
 		return ERR_PTR(-EINVAL);

@@ -118,16 +120,10 @@ struct ib_umem_odp *ib_umem_odp_alloc_implicit(struct ib_device *device,
 	umem->ibdev = device;
 	umem->writable = ib_access_writable(access);
 	umem->owning_mm = current->mm;
-	umem_odp->is_implicit_odp = 1;
 	umem_odp->page_shift = PAGE_SHIFT;
 
 	umem_odp->tgid = get_task_pid(current->group_leader, PIDTYPE_PID);
-	ret = ib_init_umem_odp(umem_odp, NULL);
-	if (ret) {
-		put_pid(umem_odp->tgid);
-		kfree(umem_odp);
-		return ERR_PTR(ret);
-	}
+	ib_init_umem_implicit_odp(umem_odp);
 	return umem_odp;
 }
 EXPORT_SYMBOL(ib_umem_odp_alloc_implicit);

@@ -248,7 +244,7 @@ struct ib_umem_odp *ib_umem_odp_get(struct ib_device *device,
 }
 EXPORT_SYMBOL(ib_umem_odp_get);
 
-void ib_umem_odp_release(struct ib_umem_odp *umem_odp)
+static void ib_umem_odp_free(struct ib_umem_odp *umem_odp)
 {
 	struct ib_device *dev = umem_odp->umem.ibdev;
 

@@ -258,14 +254,19 @@ void ib_umem_odp_release(struct ib_umem_odp *umem_odp)
 	 * It is the driver's responsibility to ensure, before calling us,
 	 * that the hardware will not attempt to access the MR any more.
 	 */
-	if (!umem_odp->is_implicit_odp) {
-		mutex_lock(&umem_odp->umem_mutex);
-		ib_umem_odp_unmap_dma_pages(umem_odp, ib_umem_start(umem_odp),
-					    ib_umem_end(umem_odp));
-		mutex_unlock(&umem_odp->umem_mutex);
-		mmu_interval_notifier_remove(&umem_odp->notifier);
-		hmm_dma_map_free(dev->dma_device, &umem_odp->map);
-	}
+	mutex_lock(&umem_odp->umem_mutex);
+	ib_umem_odp_unmap_dma_pages(umem_odp, ib_umem_start(umem_odp),
+				    ib_umem_end(umem_odp));
+	mutex_unlock(&umem_odp->umem_mutex);
+	mmu_interval_notifier_remove(&umem_odp->notifier);
+	hmm_dma_map_free(dev->dma_device, &umem_odp->map);
+}
+
+void ib_umem_odp_release(struct ib_umem_odp *umem_odp)
+{
+	if (!umem_odp->is_implicit_odp)
+		ib_umem_odp_free(umem_odp);
+
 	put_pid(umem_odp->tgid);
 	kfree(umem_odp);
 }