24 files changed, 295 insertions, 276 deletions

diff --git a/Documentation/core-api/dma-api.rst b/Documentation/core-api/dma-api.rst
index 3087bea715ed..ca75b3541679 100644
--- a/Documentation/core-api/dma-api.rst
+++ b/Documentation/core-api/dma-api.rst
@@ -761,7 +761,7 @@ example warning message may look like this::
 	[<ffffffff80235177>] find_busiest_group+0x207/0x8a0
 	[<ffffffff8064784f>] _spin_lock_irqsave+0x1f/0x50
 	[<ffffffff803c7ea3>] check_unmap+0x203/0x490
-	[<ffffffff803c8259>] debug_dma_unmap_page+0x49/0x50
+	[<ffffffff803c8259>] debug_dma_unmap_phys+0x49/0x50
 	[<ffffffff80485f26>] nv_tx_done_optimized+0xc6/0x2c0
 	[<ffffffff80486c13>] nv_nic_irq_optimized+0x73/0x2b0
 	[<ffffffff8026df84>] handle_IRQ_event+0x34/0x70
@@ -855,7 +855,7 @@ that a driver may be leaking mappings.
 dma-debug interface debug_dma_mapping_error() to debug drivers that fail
 to check DMA mapping errors on addresses returned by dma_map_single() and
 dma_map_page() interfaces. This interface clears a flag set by
-debug_dma_map_page() to indicate that dma_mapping_error() has been called by
+debug_dma_map_phys() to indicate that dma_mapping_error() has been called by
 the driver. When driver does unmap, debug_dma_unmap() checks the flag and if
 this flag is still set, prints warning message that includes call trace that
 leads up to the unmap. This interface can be called from dma_mapping_error()
diff --git a/Documentation/core-api/dma-attributes.rst b/Documentation/core-api/dma-attributes.rst
index 1887d92e8e92..0bdc2be65e57 100644
--- a/Documentation/core-api/dma-attributes.rst
+++ b/Documentation/core-api/dma-attributes.rst
@@ -130,3 +130,21 @@ accesses to DMA buffers in both privileged "supervisor" and unprivileged
 subsystem that the buffer is fully accessible at the elevated privilege
 level (and ideally inaccessible or at least read-only at the
 lesser-privileged levels).
+
+DMA_ATTR_MMIO
+-------------
+
+This attribute indicates the physical address is not normal system
+memory. It may not be used with kmap*()/phys_to_virt()/phys_to_page()
+functions, it may not be cacheable, and access using CPU load/store
+instructions may not be allowed.
+
+Usually this will be used to describe MMIO addresses, or other non-cacheable
+register addresses. When DMA mapping this sort of address we call
+the operation Peer to Peer as a one device is DMA'ing to another device.
+For PCI devices the p2pdma APIs must be used to determine if
+DMA_ATTR_MMIO is appropriate.
+
+For architectures that require cache flushing for DMA coherence
+DMA_ATTR_MMIO will not perform any cache flushing. The address
+provided must never be mapped cacheable into the CPU.
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index 4d64a5db50f3..0359ab72cd3b 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -14,7 +14,7 @@
 #define can_map_direct(dev, addr) \
 	((dev)->bus_dma_limit >= phys_to_dma((dev), (addr)))
 
-bool arch_dma_map_page_direct(struct device *dev, phys_addr_t addr)
+bool arch_dma_map_phys_direct(struct device *dev, phys_addr_t addr)
 {
 	if (likely(!dev->bus_dma_limit))
 		return false;
@@ -24,7 +24,7 @@ bool arch_dma_map_page_direct(struct device *dev, phys_addr_t addr)
 
 #define is_direct_handle(dev, h) ((h) >= (dev)->archdata.dma_offset)
 
-bool arch_dma_unmap_page_direct(struct device *dev, dma_addr_t dma_handle)
+bool arch_dma_unmap_phys_direct(struct device *dev, dma_addr_t dma_handle)
 {
 	if (likely(!dev->bus_dma_limit))
 		return false;
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index ea2ef53bd4fe..7944a3af4545 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -724,7 +724,12 @@ static int iommu_dma_init_domain(struct iommu_domain *domain, struct device *dev
 static int dma_info_to_prot(enum dma_data_direction dir, bool coherent,
 		     unsigned long attrs)
 {
-	int prot = coherent ? IOMMU_CACHE : 0;
+	int prot;
+
+	if (attrs & DMA_ATTR_MMIO)
+		prot = IOMMU_MMIO;
+	else
+		prot = coherent ? IOMMU_CACHE : 0;
 
 	if (attrs & DMA_ATTR_PRIVILEGED)
 		prot |= IOMMU_PRIV;
@@ -1190,11 +1195,9 @@ static inline size_t iova_unaligned(struct iova_domain *iovad, phys_addr_t phys,
 	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)
+dma_addr_t iommu_dma_map_phys(struct device *dev, phys_addr_t phys, size_t size,
+		enum dma_data_direction dir, unsigned long attrs)
 {
-	phys_addr_t phys = page_to_phys(page) + offset;
 	bool coherent = dev_is_dma_coherent(dev);
 	int prot = dma_info_to_prot(dir, coherent, attrs);
 	struct iommu_domain *domain = iommu_get_dma_domain(dev);
@@ -1208,27 +1211,34 @@ dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
 	 */
 	if (dev_use_swiotlb(dev, size, dir) &&
 	    iova_unaligned(iovad, phys, size)) {
+		if (attrs & DMA_ATTR_MMIO)
+			return DMA_MAPPING_ERROR;
+
 		phys = iommu_dma_map_swiotlb(dev, phys, size, dir, attrs);
 		if (phys == (phys_addr_t)DMA_MAPPING_ERROR)
 			return DMA_MAPPING_ERROR;
 	}
 
-	if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+	if (!coherent && !(attrs & (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_MMIO)))
 		arch_sync_dma_for_device(phys, size, dir);
 
 	iova = __iommu_dma_map(dev, phys, size, prot, dma_mask);
-	if (iova == DMA_MAPPING_ERROR)
+	if (iova == DMA_MAPPING_ERROR && !(attrs & DMA_ATTR_MMIO))
 		swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs);
 	return iova;
 }
 
-void iommu_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
+void iommu_dma_unmap_phys(struct device *dev, dma_addr_t dma_handle,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
-	struct iommu_domain *domain = iommu_get_dma_domain(dev);
 	phys_addr_t phys;
 
-	phys = iommu_iova_to_phys(domain, dma_handle);
+	if (attrs & DMA_ATTR_MMIO) {
+		__iommu_dma_unmap(dev, dma_handle, size);
+		return;
+	}
+
+	phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dma_handle);
 	if (WARN_ON(!phys))
 		return;
 
@@ -1341,7 +1351,7 @@ static void iommu_dma_unmap_sg_swiotlb(struct device *dev, struct scatterlist *s
 	int i;
 
 	for_each_sg(sg, s, nents, i)
-		iommu_dma_unmap_page(dev, sg_dma_address(s),
+		iommu_dma_unmap_phys(dev, sg_dma_address(s),
 				sg_dma_len(s), dir, attrs);
 }
 
@@ -1354,8 +1364,8 @@ static int iommu_dma_map_sg_swiotlb(struct device *dev, struct scatterlist *sg,
 	sg_dma_mark_swiotlb(sg);
 
 	for_each_sg(sg, s, nents, i) {
-		sg_dma_address(s) = iommu_dma_map_page(dev, sg_page(s),
-				s->offset, s->length, dir, attrs);
+		sg_dma_address(s) = iommu_dma_map_phys(dev, sg_phys(s),
+				s->length, dir, attrs);
 		if (sg_dma_address(s) == DMA_MAPPING_ERROR)
 			goto out_unmap;
 		sg_dma_len(s) = s->length;
@@ -1546,20 +1556,6 @@ void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
 		__iommu_dma_unmap(dev, start, end - start);
 }
 
-dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
-	return __iommu_dma_map(dev, phys, size,
-			dma_info_to_prot(dir, false, attrs) | IOMMU_MMIO,
-			dma_get_mask(dev));
-}
-
-void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
-	__iommu_dma_unmap(dev, handle, size);
-}
-
 static void __iommu_dma_free(struct device *dev, size_t size, void *cpu_addr)
 {
 	size_t alloc_size = PAGE_ALIGN(size);
@@ -1838,12 +1834,13 @@ static int __dma_iova_link(struct device *dev, dma_addr_t addr,
 		unsigned long attrs)
 {
 	bool coherent = dev_is_dma_coherent(dev);
+	int prot = dma_info_to_prot(dir, coherent, attrs);
 
-	if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+	if (!coherent && !(attrs & (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_MMIO)))
 		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);
+			prot, GFP_ATOMIC);
 }
 
 static int iommu_dma_iova_bounce_and_link(struct device *dev, dma_addr_t addr,
@@ -1949,9 +1946,13 @@ int dma_iova_link(struct device *dev, struct dma_iova_state *state,
 		return -EIO;
 
 	if (dev_use_swiotlb(dev, size, dir) &&
-	    iova_unaligned(iovad, phys, size))
+	    iova_unaligned(iovad, phys, size)) {
+		if (attrs & DMA_ATTR_MMIO)
+			return -EPERM;
+
 		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,
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index f5062061c408..c147145a6593 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -378,7 +378,7 @@ static int vring_map_one_sg(const struct vring_virtqueue *vq, struct scatterlist
 		 * is initialized by the hardware. Explicitly check/unpoison it
 		 * depending on the direction.
 		 */
-		kmsan_handle_dma(sg_page(sg), sg->offset, sg->length, direction);
+		kmsan_handle_dma(sg_phys(sg), sg->length, direction);
 		*addr = (dma_addr_t)sg_phys(sg);
 		return 0;
 	}
@@ -3157,7 +3157,7 @@ dma_addr_t virtqueue_dma_map_single_attrs(struct virtqueue *_vq, void *ptr,
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
 	if (!vq->use_dma_api) {
-		kmsan_handle_dma(virt_to_page(ptr), offset_in_page(ptr), size, dir);
+		kmsan_handle_dma(virt_to_phys(ptr), size, dir);
 		return (dma_addr_t)virt_to_phys(ptr);
 	}
 
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index da1a7d3d377c..dd7747a2de87 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -392,6 +392,25 @@ xen_swiotlb_sync_sg_for_device(struct device *dev, struct scatterlist *sgl,
 	}
 }
 
+static dma_addr_t xen_swiotlb_direct_map_resource(struct device *dev,
+						  phys_addr_t paddr,
+						  size_t size,
+						  enum dma_data_direction dir,
+						  unsigned long attrs)
+{
+	dma_addr_t dma_addr = paddr;
+
+	if (unlikely(!dma_capable(dev, dma_addr, size, false))) {
+		dev_err_once(dev,
+			     "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
+			     &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
+		WARN_ON_ONCE(1);
+		return DMA_MAPPING_ERROR;
+	}
+
+	return dma_addr;
+}
+
 /*
  * Return whether the given device DMA address mask can be supported
  * properly.  For example, if your device can only drive the low 24-bits
@@ -426,5 +445,5 @@ const struct dma_map_ops xen_swiotlb_dma_ops = {
 	.alloc_pages_op = dma_common_alloc_pages,
 	.free_pages = dma_common_free_pages,
 	.max_mapping_size = swiotlb_max_mapping_size,
-	.map_resource = dma_direct_map_resource,
+	.map_resource = xen_swiotlb_direct_map_resource,
 };
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index f3bc0bcd7098..c249912456f9 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -149,7 +149,5 @@ void dma_direct_free_pages(struct device *dev, size_t size,
 		struct page *page, dma_addr_t dma_addr,
 		enum dma_data_direction dir);
 int dma_direct_supported(struct device *dev, u64 mask);
-dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir, unsigned long attrs);
 
 #endif /* _LINUX_DMA_DIRECT_H */
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 332b80c42b6f..10882d00cb17 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -395,15 +395,15 @@ void *arch_dma_set_uncached(void *addr, size_t size);
 void arch_dma_clear_uncached(void *addr, size_t size);
 
 #ifdef CONFIG_ARCH_HAS_DMA_MAP_DIRECT
-bool arch_dma_map_page_direct(struct device *dev, phys_addr_t addr);
-bool arch_dma_unmap_page_direct(struct device *dev, dma_addr_t dma_handle);
+bool arch_dma_map_phys_direct(struct device *dev, phys_addr_t addr);
+bool arch_dma_unmap_phys_direct(struct device *dev, dma_addr_t dma_handle);
 bool arch_dma_map_sg_direct(struct device *dev, struct scatterlist *sg,
 		int nents);
 bool arch_dma_unmap_sg_direct(struct device *dev, struct scatterlist *sg,
 		int nents);
 #else
-#define arch_dma_map_page_direct(d, a)		(false)
-#define arch_dma_unmap_page_direct(d, a)	(false)
+#define arch_dma_map_phys_direct(d, a)		(false)
+#define arch_dma_unmap_phys_direct(d, a)	(false)
 #define arch_dma_map_sg_direct(d, s, n)		(false)
 #define arch_dma_unmap_sg_direct(d, s, n)	(false)
 #endif
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 55c03e5fe8cb..8248ff9363ee 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -59,6 +59,26 @@
 #define DMA_ATTR_PRIVILEGED		(1UL << 9)
 
 /*
+ * DMA_ATTR_MMIO - Indicates memory-mapped I/O (MMIO) region for DMA mapping
+ *
+ * This attribute indicates the physical address is not normal system
+ * memory. It may not be used with kmap*()/phys_to_virt()/phys_to_page()
+ * functions, it may not be cacheable, and access using CPU load/store
+ * instructions may not be allowed.
+ *
+ * Usually this will be used to describe MMIO addresses, or other non-cacheable
+ * register addresses. When DMA mapping this sort of address we call
+ * the operation Peer to Peer as a one device is DMA'ing to another device.
+ * For PCI devices the p2pdma APIs must be used to determine if DMA_ATTR_MMIO
+ * is appropriate.
+ *
+ * For architectures that require cache flushing for DMA coherence
+ * DMA_ATTR_MMIO will not perform any cache flushing. The address
+ * provided must never be mapped cacheable into the CPU.
+ */
+#define DMA_ATTR_MMIO		(1UL << 10)
+
+/*
  * A dma_addr_t can hold any valid DMA or bus address for the platform.  It can
  * be given to a device to use as a DMA source or target.  It is specific to a
  * given device and there may be a translation between the CPU physical address
@@ -118,6 +138,10 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
 		unsigned long attrs);
 void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size,
 		enum dma_data_direction dir, unsigned long attrs);
+dma_addr_t dma_map_phys(struct device *dev, phys_addr_t phys, size_t size,
+		enum dma_data_direction dir, unsigned long attrs);
+void dma_unmap_phys(struct device *dev, dma_addr_t addr, size_t size,
+		enum dma_data_direction dir, unsigned long attrs);
 unsigned int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
 		int nents, enum dma_data_direction dir, unsigned long attrs);
 void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg,
@@ -172,6 +196,15 @@ static inline void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 }
+static inline dma_addr_t dma_map_phys(struct device *dev, phys_addr_t phys,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	return DMA_MAPPING_ERROR;
+}
+static inline void dma_unmap_phys(struct device *dev, dma_addr_t addr,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+}
 static inline unsigned int dma_map_sg_attrs(struct device *dev,
 		struct scatterlist *sg, int nents, enum dma_data_direction dir,
 		unsigned long attrs)
diff --git a/include/linux/iommu-dma.h b/include/linux/iommu-dma.h
index 508beaa44c39..a92b3ff9b934 100644
--- a/include/linux/iommu-dma.h
+++ b/include/linux/iommu-dma.h
@@ -21,10 +21,9 @@ static inline bool use_dma_iommu(struct device *dev)
 }
 #endif /* CONFIG_IOMMU_DMA */
 
-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);
-void iommu_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
+dma_addr_t iommu_dma_map_phys(struct device *dev, phys_addr_t phys, size_t size,
+		enum dma_data_direction dir, unsigned long attrs);
+void iommu_dma_unmap_phys(struct device *dev, dma_addr_t dma_handle,
 		size_t size, enum dma_data_direction dir, unsigned long attrs);
 int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 		enum dma_data_direction dir, unsigned long attrs);
@@ -43,10 +42,6 @@ size_t iommu_dma_opt_mapping_size(void);
 size_t iommu_dma_max_mapping_size(struct device *dev);
 void iommu_dma_free(struct device *dev, size_t size, void *cpu_addr,
 		dma_addr_t handle, unsigned long attrs);
-dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
-		size_t size, enum dma_data_direction dir, unsigned long attrs);
-void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir, unsigned long attrs);
 struct sg_table *iommu_dma_alloc_noncontiguous(struct device *dev, size_t size,
 		enum dma_data_direction dir, gfp_t gfp, unsigned long attrs);
 void iommu_dma_free_noncontiguous(struct device *dev, size_t size,
diff --git a/include/linux/kmsan.h b/include/linux/kmsan.h
index 2b1432cc16d5..f2fd221107bb 100644
--- a/include/linux/kmsan.h
+++ b/include/linux/kmsan.h
@@ -182,8 +182,7 @@ void kmsan_iounmap_page_range(unsigned long start, unsigned long end);
 
 /**
  * kmsan_handle_dma() - Handle a DMA data transfer.
- * @page:   first page of the buffer.
- * @offset: offset of the buffer within the first page.
+ * @phys:   physical address of the buffer.
  * @size:   buffer size.
  * @dir:    one of possible dma_data_direction values.
  *
@@ -192,7 +191,7 @@ void kmsan_iounmap_page_range(unsigned long start, unsigned long end);
  * * initializes the buffer, if it is copied from device;
  * * does both, if this is a DMA_BIDIRECTIONAL transfer.
  */
-void kmsan_handle_dma(struct page *page, size_t offset, size_t size,
+void kmsan_handle_dma(phys_addr_t phys, size_t size,
 		      enum dma_data_direction dir);
 
 /**
@@ -372,8 +371,8 @@ static inline void kmsan_iounmap_page_range(unsigned long start,
 {
 }
 
-static inline void kmsan_handle_dma(struct page *page, size_t offset,
-				    size_t size, enum dma_data_direction dir)
+static inline void kmsan_handle_dma(phys_addr_t phys, size_t size,
+				    enum dma_data_direction dir)
 {
 }
 
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 48e27768e7ba..0091ad1986bf 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -618,6 +618,7 @@ FOLIO_FLAG(dropbehind, FOLIO_HEAD_PAGE)
 #else
 PAGEFLAG_FALSE(HighMem, highmem)
 #endif
+#define PhysHighMem(__p) (PageHighMem(phys_to_page(__p)))
 
 /* Does kmap_local_folio() only allow access to one page of the folio? */
 #ifdef CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP
diff --git a/include/trace/events/dma.h b/include/trace/events/dma.h
index d8ddc27b6a7c..5da59fd8121d 100644
--- a/include/trace/events/dma.h
+++ b/include/trace/events/dma.h
@@ -31,7 +31,8 @@ TRACE_DEFINE_ENUM(DMA_NONE);
 		{ DMA_ATTR_FORCE_CONTIGUOUS, "FORCE_CONTIGUOUS" }, \
 		{ DMA_ATTR_ALLOC_SINGLE_PAGES, "ALLOC_SINGLE_PAGES" }, \
 		{ DMA_ATTR_NO_WARN, "NO_WARN" }, \
-		{ DMA_ATTR_PRIVILEGED, "PRIVILEGED" })
+		{ DMA_ATTR_PRIVILEGED, "PRIVILEGED" }, \
+		{ DMA_ATTR_MMIO, "MMIO" })
 
 DECLARE_EVENT_CLASS(dma_map,
 	TP_PROTO(struct device *dev, phys_addr_t phys_addr, dma_addr_t dma_addr,
@@ -71,8 +72,7 @@ DEFINE_EVENT(dma_map, name, \
 		 size_t size, enum dma_data_direction dir, unsigned long attrs), \
 	TP_ARGS(dev, phys_addr, dma_addr, size, dir, attrs))
 
-DEFINE_MAP_EVENT(dma_map_page);
-DEFINE_MAP_EVENT(dma_map_resource);
+DEFINE_MAP_EVENT(dma_map_phys);
 
 DECLARE_EVENT_CLASS(dma_unmap,
 	TP_PROTO(struct device *dev, dma_addr_t addr, size_t size,
@@ -109,8 +109,7 @@ DEFINE_EVENT(dma_unmap, name, \
 		 enum dma_data_direction dir, unsigned long attrs), \
 	TP_ARGS(dev, addr, size, dir, attrs))
 
-DEFINE_UNMAP_EVENT(dma_unmap_page);
-DEFINE_UNMAP_EVENT(dma_unmap_resource);
+DEFINE_UNMAP_EVENT(dma_unmap_phys);
 
 DECLARE_EVENT_CLASS(dma_alloc_class,
 	TP_PROTO(struct device *dev, void *virt_addr, dma_addr_t dma_addr,
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index b82399437db0..1e5c64cb6a42 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -38,8 +38,8 @@ enum {
 	dma_debug_single,
 	dma_debug_sg,
 	dma_debug_coherent,
-	dma_debug_resource,
 	dma_debug_noncoherent,
+	dma_debug_phy,
 };
 
 enum map_err_types {
@@ -141,8 +141,8 @@ static const char *type2name[] = {
 	[dma_debug_single] = "single",
 	[dma_debug_sg] = "scatter-gather",
 	[dma_debug_coherent] = "coherent",
-	[dma_debug_resource] = "resource",
 	[dma_debug_noncoherent] = "noncoherent",
+	[dma_debug_phy] = "phy",
 };
 
 static const char *dir2name[] = {
@@ -1054,17 +1054,16 @@ static void check_unmap(struct dma_debug_entry *ref)
 	dma_entry_free(entry);
 }
 
-static void check_for_stack(struct device *dev,
-			    struct page *page, size_t offset)
+static void check_for_stack(struct device *dev, phys_addr_t phys)
 {
 	void *addr;
 	struct vm_struct *stack_vm_area = task_stack_vm_area(current);
 
 	if (!stack_vm_area) {
 		/* Stack is direct-mapped. */
-		if (PageHighMem(page))
+		if (PhysHighMem(phys))
 			return;
-		addr = page_address(page) + offset;
+		addr = phys_to_virt(phys);
 		if (object_is_on_stack(addr))
 			err_printk(dev, NULL, "device driver maps memory from stack [addr=%p]\n", addr);
 	} else {
@@ -1072,10 +1071,12 @@ static void check_for_stack(struct device *dev,
 		int i;
 
 		for (i = 0; i < stack_vm_area->nr_pages; i++) {
-			if (page != stack_vm_area->pages[i])
+			if (__phys_to_pfn(phys) !=
+			    page_to_pfn(stack_vm_area->pages[i]))
 				continue;
 
-			addr = (u8 *)current->stack + i * PAGE_SIZE + offset;
+			addr = (u8 *)current->stack + i * PAGE_SIZE +
+			       (phys % PAGE_SIZE);
 			err_printk(dev, NULL, "device driver maps memory from stack [probable addr=%p]\n", addr);
 			break;
 		}
@@ -1204,9 +1205,8 @@ void debug_dma_map_single(struct device *dev, const void *addr,
 }
 EXPORT_SYMBOL(debug_dma_map_single);
 
-void debug_dma_map_page(struct device *dev, struct page *page, size_t offset,
-			size_t size, int direction, dma_addr_t dma_addr,
-			unsigned long attrs)
+void debug_dma_map_phys(struct device *dev, phys_addr_t phys, size_t size,
+		int direction, dma_addr_t dma_addr, unsigned long attrs)
 {
 	struct dma_debug_entry *entry;
 
@@ -1221,19 +1221,18 @@ void debug_dma_map_page(struct device *dev, struct page *page, size_t offset,
 		return;
 
 	entry->dev       = dev;
-	entry->type      = dma_debug_single;
-	entry->paddr	 = page_to_phys(page) + offset;
+	entry->type      = dma_debug_phy;
+	entry->paddr	 = phys;
 	entry->dev_addr  = dma_addr;
 	entry->size      = size;
 	entry->direction = direction;
 	entry->map_err_type = MAP_ERR_NOT_CHECKED;
 
-	check_for_stack(dev, page, offset);
+	if (!(attrs & DMA_ATTR_MMIO)) {
+		check_for_stack(dev, phys);
 
-	if (!PageHighMem(page)) {
-		void *addr = page_address(page) + offset;
-
-		check_for_illegal_area(dev, addr, size);
+		if (!PhysHighMem(phys))
+			check_for_illegal_area(dev, phys_to_virt(phys), size);
 	}
 
 	add_dma_entry(entry, attrs);
@@ -1277,11 +1276,11 @@ void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 }
 EXPORT_SYMBOL(debug_dma_mapping_error);
 
-void debug_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
+void debug_dma_unmap_phys(struct device *dev, dma_addr_t dma_addr,
 			  size_t size, int direction)
 {
 	struct dma_debug_entry ref = {
-		.type           = dma_debug_single,
+		.type           = dma_debug_phy,
 		.dev            = dev,
 		.dev_addr       = dma_addr,
 		.size           = size,
@@ -1305,7 +1304,7 @@ void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
 		return;
 
 	for_each_sg(sg, s, nents, i) {
-		check_for_stack(dev, sg_page(s), s->offset);
+		check_for_stack(dev, sg_phys(s));
 		if (!PageHighMem(sg_page(s)))
 			check_for_illegal_area(dev, sg_virt(s), s->length);
 	}
@@ -1445,47 +1444,6 @@ void debug_dma_free_coherent(struct device *dev, size_t size,
 	check_unmap(&ref);
 }
 
-void debug_dma_map_resource(struct device *dev, phys_addr_t addr, size_t size,
-			    int direction, dma_addr_t dma_addr,
-			    unsigned long attrs)
-{
-	struct dma_debug_entry *entry;
-
-	if (unlikely(dma_debug_disabled()))
-		return;
-
-	entry = dma_entry_alloc();
-	if (!entry)
-		return;
-
-	entry->type		= dma_debug_resource;
-	entry->dev		= dev;
-	entry->paddr		= addr;
-	entry->size		= size;
-	entry->dev_addr		= dma_addr;
-	entry->direction	= direction;
-	entry->map_err_type	= MAP_ERR_NOT_CHECKED;
-
-	add_dma_entry(entry, attrs);
-}
-
-void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr,
-			      size_t size, int direction)
-{
-	struct dma_debug_entry ref = {
-		.type           = dma_debug_resource,
-		.dev            = dev,
-		.dev_addr       = dma_addr,
-		.size           = size,
-		.direction      = direction,
-	};
-
-	if (unlikely(dma_debug_disabled()))
-		return;
-
-	check_unmap(&ref);
-}
-
 void debug_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
 				   size_t size, int direction)
 {
diff --git a/kernel/dma/debug.h b/kernel/dma/debug.h
index 48757ca13f31..da7be0bddcf6 100644
--- a/kernel/dma/debug.h
+++ b/kernel/dma/debug.h
@@ -9,12 +9,11 @@
 #define _KERNEL_DMA_DEBUG_H
 
 #ifdef CONFIG_DMA_API_DEBUG
-extern void debug_dma_map_page(struct device *dev, struct page *page,
-			       size_t offset, size_t size,
-			       int direction, dma_addr_t dma_addr,
+extern void debug_dma_map_phys(struct device *dev, phys_addr_t phys,
+			       size_t size, int direction, dma_addr_t dma_addr,
 			       unsigned long attrs);
 
-extern void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
+extern void debug_dma_unmap_phys(struct device *dev, dma_addr_t addr,
 				 size_t size, int direction);
 
 extern void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
@@ -31,14 +30,6 @@ extern void debug_dma_alloc_coherent(struct device *dev, size_t size,
 extern void debug_dma_free_coherent(struct device *dev, size_t size,
 				    void *virt, dma_addr_t addr);
 
-extern void debug_dma_map_resource(struct device *dev, phys_addr_t addr,
-				   size_t size, int direction,
-				   dma_addr_t dma_addr,
-				   unsigned long attrs);
-
-extern void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr,
-				     size_t size, int direction);
-
 extern void debug_dma_sync_single_for_cpu(struct device *dev,
 					  dma_addr_t dma_handle, size_t size,
 					  int direction);
@@ -62,14 +53,13 @@ extern void debug_dma_free_pages(struct device *dev, struct page *page,
 				 size_t size, int direction,
 				 dma_addr_t dma_addr);
 #else /* CONFIG_DMA_API_DEBUG */
-static inline void debug_dma_map_page(struct device *dev, struct page *page,
-				      size_t offset, size_t size,
-				      int direction, dma_addr_t dma_addr,
-				      unsigned long attrs)
+static inline void debug_dma_map_phys(struct device *dev, phys_addr_t phys,
+				      size_t size, int direction,
+				      dma_addr_t dma_addr, unsigned long attrs)
 {
 }
 
-static inline void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
+static inline void debug_dma_unmap_phys(struct device *dev, dma_addr_t addr,
 					size_t size, int direction)
 {
 }
@@ -97,19 +87,6 @@ static inline void debug_dma_free_coherent(struct device *dev, size_t size,
 {
 }
 
-static inline void debug_dma_map_resource(struct device *dev, phys_addr_t addr,
-					  size_t size, int direction,
-					  dma_addr_t dma_addr,
-					  unsigned long attrs)
-{
-}
-
-static inline void debug_dma_unmap_resource(struct device *dev,
-					    dma_addr_t dma_addr, size_t size,
-					    int direction)
-{
-}
-
 static inline void debug_dma_sync_single_for_cpu(struct device *dev,
 						 dma_addr_t dma_handle,
 						 size_t size, int direction)
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 24c359d9c879..1f9ee9759426 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -120,7 +120,7 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 		gfp_t gfp, bool allow_highmem)
 {
 	int node = dev_to_node(dev);
-	struct page *page = NULL;
+	struct page *page;
 	u64 phys_limit;
 
 	WARN_ON_ONCE(!PAGE_ALIGNED(size));
@@ -131,30 +131,25 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 	gfp |= dma_direct_optimal_gfp_mask(dev, &phys_limit);
 	page = dma_alloc_contiguous(dev, size, gfp);
 	if (page) {
-		if (!dma_coherent_ok(dev, page_to_phys(page), size) ||
-		    (!allow_highmem && PageHighMem(page))) {
-			dma_free_contiguous(dev, page, size);
-			page = NULL;
-		}
+		if (dma_coherent_ok(dev, page_to_phys(page), size) &&
+		    (allow_highmem || !PageHighMem(page)))
+			return page;
+
+		dma_free_contiguous(dev, page, size);
 	}
-again:
-	if (!page)
-		page = alloc_pages_node(node, gfp, get_order(size));
-	if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
+
+	while ((page = alloc_pages_node(node, gfp, get_order(size)))
+	       && !dma_coherent_ok(dev, page_to_phys(page), size)) {
 		__free_pages(page, get_order(size));
-		page = NULL;
 
 		if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
 		    phys_limit < DMA_BIT_MASK(64) &&
-		    !(gfp & (GFP_DMA32 | GFP_DMA))) {
+		    !(gfp & (GFP_DMA32 | GFP_DMA)))
 			gfp |= GFP_DMA32;
-			goto again;
-		}
-
-		if (IS_ENABLED(CONFIG_ZONE_DMA) && !(gfp & GFP_DMA)) {
+		else if (IS_ENABLED(CONFIG_ZONE_DMA) && !(gfp & GFP_DMA))
 			gfp = (gfp & ~GFP_DMA32) | GFP_DMA;
-			goto again;
-		}
+		else
+			return NULL;
 	}
 
 	return page;
@@ -453,7 +448,7 @@ void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
 		if (sg_dma_is_bus_address(sg))
 			sg_dma_unmark_bus_address(sg);
 		else
-			dma_direct_unmap_page(dev, sg->dma_address,
+			dma_direct_unmap_phys(dev, sg->dma_address,
 					      sg_dma_len(sg), dir, attrs);
 	}
 }
@@ -476,8 +471,8 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
 			 */
 			break;
 		case PCI_P2PDMA_MAP_NONE:
-			sg->dma_address = dma_direct_map_page(dev, sg_page(sg),
-					sg->offset, sg->length, dir, attrs);
+			sg->dma_address = dma_direct_map_phys(dev, sg_phys(sg),
+					sg->length, dir, attrs);
 			if (sg->dma_address == DMA_MAPPING_ERROR) {
 				ret = -EIO;
 				goto out_unmap;
@@ -502,22 +497,6 @@ out_unmap:
 	return ret;
 }
 
-dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
-	dma_addr_t dma_addr = paddr;
-
-	if (unlikely(!dma_capable(dev, dma_addr, size, false))) {
-		dev_err_once(dev,
-			     "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
-			     &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
-		WARN_ON_ONCE(1);
-		return DMA_MAPPING_ERROR;
-	}
-
-	return dma_addr;
-}
-
 int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		unsigned long attrs)
diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
index d2c0b7e632fc..da2fadf45bcd 100644
--- a/kernel/dma/direct.h
+++ b/kernel/dma/direct.h
@@ -80,42 +80,57 @@ static inline void dma_direct_sync_single_for_cpu(struct device *dev,
 		arch_dma_mark_clean(paddr, size);
 }
 
-static inline dma_addr_t dma_direct_map_page(struct device *dev,
-		struct page *page, unsigned long offset, size_t size,
-		enum dma_data_direction dir, unsigned long attrs)
+static inline dma_addr_t dma_direct_map_phys(struct device *dev,
+		phys_addr_t phys, size_t size, enum dma_data_direction dir,
+		unsigned long attrs)
 {
-	phys_addr_t phys = page_to_phys(page) + offset;
-	dma_addr_t dma_addr = phys_to_dma(dev, phys);
+	dma_addr_t dma_addr;
 
 	if (is_swiotlb_force_bounce(dev)) {
-		if (is_pci_p2pdma_page(page))
-			return DMA_MAPPING_ERROR;
+		if (attrs & DMA_ATTR_MMIO)
+			goto err_overflow;
+
 		return swiotlb_map(dev, phys, size, dir, attrs);
 	}
 
-	if (unlikely(!dma_capable(dev, dma_addr, size, true)) ||
-	    dma_kmalloc_needs_bounce(dev, size, dir)) {
-		if (is_pci_p2pdma_page(page))
-			return DMA_MAPPING_ERROR;
-		if (is_swiotlb_active(dev))
-			return swiotlb_map(dev, phys, size, dir, attrs);
-
-		dev_WARN_ONCE(dev, 1,
-			     "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
-			     &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
-		return DMA_MAPPING_ERROR;
+	if (attrs & DMA_ATTR_MMIO) {
+		dma_addr = phys;
+		if (unlikely(!dma_capable(dev, dma_addr, size, false)))
+			goto err_overflow;
+	} else {
+		dma_addr = phys_to_dma(dev, phys);
+		if (unlikely(!dma_capable(dev, dma_addr, size, true)) ||
+		    dma_kmalloc_needs_bounce(dev, size, dir)) {
+			if (is_swiotlb_active(dev))
+				return swiotlb_map(dev, phys, size, dir, attrs);
+
+			goto err_overflow;
+		}
 	}
 
-	if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+	if (!dev_is_dma_coherent(dev) &&
+	    !(attrs & (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_MMIO)))
 		arch_sync_dma_for_device(phys, size, dir);
 	return dma_addr;
+
+err_overflow:
+	dev_WARN_ONCE(
+		dev, 1,
+		"DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
+		&dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
+	return DMA_MAPPING_ERROR;
 }
 
-static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
+static inline void dma_direct_unmap_phys(struct device *dev, dma_addr_t addr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
-	phys_addr_t phys = dma_to_phys(dev, addr);
+	phys_addr_t phys;
+
+	if (attrs & DMA_ATTR_MMIO)
+		/* nothing to do: uncached and no swiotlb */
+		return;
 
+	phys = dma_to_phys(dev, addr);
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
 
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 56de28a3b179..fe7472f13b10 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -152,11 +152,11 @@ static inline bool dma_map_direct(struct device *dev,
 	return dma_go_direct(dev, *dev->dma_mask, ops);
 }
 
-dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
-		size_t offset, size_t size, enum dma_data_direction dir,
-		unsigned long attrs)
+dma_addr_t dma_map_phys(struct device *dev, phys_addr_t phys, size_t size,
+		enum dma_data_direction dir, unsigned long attrs)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
+	bool is_mmio = attrs & DMA_ATTR_MMIO;
 	dma_addr_t addr;
 
 	BUG_ON(!valid_dma_direction(dir));
@@ -165,36 +165,81 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
 		return DMA_MAPPING_ERROR;
 
 	if (dma_map_direct(dev, ops) ||
-	    arch_dma_map_page_direct(dev, page_to_phys(page) + offset + size))
-		addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
+	    (!is_mmio && arch_dma_map_phys_direct(dev, phys + size)))
+		addr = dma_direct_map_phys(dev, phys, size, dir, attrs);
 	else if (use_dma_iommu(dev))
-		addr = iommu_dma_map_page(dev, page, offset, size, dir, attrs);
-	else
+		addr = iommu_dma_map_phys(dev, phys, size, dir, attrs);
+	else if (is_mmio) {
+		if (!ops->map_resource)
+			return DMA_MAPPING_ERROR;
+
+		addr = ops->map_resource(dev, phys, size, dir, attrs);
+	} else {
+		struct page *page = phys_to_page(phys);
+		size_t offset = offset_in_page(phys);
+
+		/*
+		 * The dma_ops API contract for ops->map_page() requires
+		 * kmappable memory, while ops->map_resource() does not.
+		 */
 		addr = ops->map_page(dev, page, offset, size, dir, attrs);
-	kmsan_handle_dma(page, offset, size, dir);
-	trace_dma_map_page(dev, page_to_phys(page) + offset, addr, size, dir,
-			   attrs);
-	debug_dma_map_page(dev, page, offset, size, dir, addr, attrs);
+	}
+
+	if (!is_mmio)
+		kmsan_handle_dma(phys, size, dir);
+	trace_dma_map_phys(dev, phys, addr, size, dir, attrs);
+	debug_dma_map_phys(dev, phys, size, dir, addr, attrs);
 
 	return addr;
 }
+EXPORT_SYMBOL_GPL(dma_map_phys);
+
+dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
+		size_t offset, size_t size, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+	phys_addr_t phys = page_to_phys(page) + offset;
+
+	if (unlikely(attrs & DMA_ATTR_MMIO))
+		return DMA_MAPPING_ERROR;
+
+	if (IS_ENABLED(CONFIG_DMA_API_DEBUG) &&
+	    WARN_ON_ONCE(is_zone_device_page(page)))
+		return DMA_MAPPING_ERROR;
+
+	return dma_map_phys(dev, phys, size, dir, attrs);
+}
 EXPORT_SYMBOL(dma_map_page_attrs);
 
-void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size,
+void dma_unmap_phys(struct device *dev, dma_addr_t addr, size_t size,
 		enum dma_data_direction dir, unsigned long attrs)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
+	bool is_mmio = attrs & DMA_ATTR_MMIO;
 
 	BUG_ON(!valid_dma_direction(dir));
 	if (dma_map_direct(dev, ops) ||
-	    arch_dma_unmap_page_direct(dev, addr + size))
-		dma_direct_unmap_page(dev, addr, size, dir, attrs);
+	    (!is_mmio && arch_dma_unmap_phys_direct(dev, addr + size)))
+		dma_direct_unmap_phys(dev, addr, size, dir, attrs);
 	else if (use_dma_iommu(dev))
-		iommu_dma_unmap_page(dev, addr, size, dir, attrs);
-	else
+		iommu_dma_unmap_phys(dev, addr, size, dir, attrs);
+	else if (is_mmio) {
+		if (ops->unmap_resource)
+			ops->unmap_resource(dev, addr, size, dir, attrs);
+	} else
 		ops->unmap_page(dev, addr, size, dir, attrs);
-	trace_dma_unmap_page(dev, addr, size, dir, attrs);
-	debug_dma_unmap_page(dev, addr, size, dir);
+	trace_dma_unmap_phys(dev, addr, size, dir, attrs);
+	debug_dma_unmap_phys(dev, addr, size, dir);
+}
+EXPORT_SYMBOL_GPL(dma_unmap_phys);
+
+void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size,
+		 enum dma_data_direction dir, unsigned long attrs)
+{
+	if (unlikely(attrs & DMA_ATTR_MMIO))
+		return;
+
+	dma_unmap_phys(dev, addr, size, dir, attrs);
 }
 EXPORT_SYMBOL(dma_unmap_page_attrs);
 
@@ -321,41 +366,18 @@ EXPORT_SYMBOL(dma_unmap_sg_attrs);
 dma_addr_t dma_map_resource(struct device *dev, phys_addr_t phys_addr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-	dma_addr_t addr = DMA_MAPPING_ERROR;
-
-	BUG_ON(!valid_dma_direction(dir));
-
-	if (WARN_ON_ONCE(!dev->dma_mask))
+	if (IS_ENABLED(CONFIG_DMA_API_DEBUG) &&
+	    WARN_ON_ONCE(pfn_valid(PHYS_PFN(phys_addr))))
 		return DMA_MAPPING_ERROR;
 
-	if (dma_map_direct(dev, ops))
-		addr = dma_direct_map_resource(dev, phys_addr, size, dir, attrs);
-	else if (use_dma_iommu(dev))
-		addr = iommu_dma_map_resource(dev, phys_addr, size, dir, attrs);
-	else if (ops->map_resource)
-		addr = ops->map_resource(dev, phys_addr, size, dir, attrs);
-
-	trace_dma_map_resource(dev, phys_addr, addr, size, dir, attrs);
-	debug_dma_map_resource(dev, phys_addr, size, dir, addr, attrs);
-	return addr;
+	return dma_map_phys(dev, phys_addr, size, dir, attrs | DMA_ATTR_MMIO);
 }
 EXPORT_SYMBOL(dma_map_resource);
 
 void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size,
 		enum dma_data_direction dir, unsigned long attrs)
 {
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (dma_map_direct(dev, ops))
-		; /* nothing to do: uncached and no swiotlb */
-	else if (use_dma_iommu(dev))
-		iommu_dma_unmap_resource(dev, addr, size, dir, attrs);
-	else if (ops->unmap_resource)
-		ops->unmap_resource(dev, addr, size, dir, attrs);
-	trace_dma_unmap_resource(dev, addr, size, dir, attrs);
-	debug_dma_unmap_resource(dev, addr, size, dir);
+	dma_unmap_phys(dev, addr, size, dir, attrs | DMA_ATTR_MMIO);
 }
 EXPORT_SYMBOL(dma_unmap_resource);
 
diff --git a/kernel/dma/ops_helpers.c b/kernel/dma/ops_helpers.c
index 9afd569eadb9..6f9d604d9d40 100644
--- a/kernel/dma/ops_helpers.c
+++ b/kernel/dma/ops_helpers.c
@@ -72,8 +72,8 @@ struct page *dma_common_alloc_pages(struct device *dev, size_t size,
 		return NULL;
 
 	if (use_dma_iommu(dev))
-		*dma_handle = iommu_dma_map_page(dev, page, 0, size, dir,
-						 DMA_ATTR_SKIP_CPU_SYNC);
+		*dma_handle = iommu_dma_map_phys(dev, page_to_phys(page), size,
+						 dir, DMA_ATTR_SKIP_CPU_SYNC);
 	else
 		*dma_handle = ops->map_page(dev, page, 0, size, dir,
 					    DMA_ATTR_SKIP_CPU_SYNC);
@@ -92,7 +92,7 @@ void dma_common_free_pages(struct device *dev, size_t size, struct page *page,
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	if (use_dma_iommu(dev))
-		iommu_dma_unmap_page(dev, dma_handle, size, dir,
+		iommu_dma_unmap_phys(dev, dma_handle, size, dir,
 				     DMA_ATTR_SKIP_CPU_SYNC);
 	else if (ops->unmap_page)
 		ops->unmap_page(dev, dma_handle, size, dir,
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index abcf3fa63a56..0d37da3d95b6 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -1209,7 +1209,7 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
 	nslabs = nr_slots(alloc_size);
 	phys_limit = min_not_zero(*dev->dma_mask, dev->bus_dma_limit);
 	pool = swiotlb_alloc_pool(dev, nslabs, nslabs, 1, phys_limit,
-				  GFP_NOWAIT | __GFP_NOWARN);
+				  GFP_NOWAIT);
 	if (!pool)
 		return -1;
 
diff --git a/mm/hmm.c b/mm/hmm.c
index 3e00f08722d5..87562914670a 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -806,7 +806,7 @@ dma_addr_t hmm_dma_map_pfn(struct device *dev, struct hmm_dma_map *map,
 	case PCI_P2PDMA_MAP_NONE:
 		break;
 	case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE:
-		attrs |= DMA_ATTR_SKIP_CPU_SYNC;
+		attrs |= DMA_ATTR_MMIO;
 		pfns[idx] |= HMM_PFN_P2PDMA;
 		break;
 	case PCI_P2PDMA_MAP_BUS_ADDR:
@@ -835,8 +835,8 @@ dma_addr_t hmm_dma_map_pfn(struct device *dev, struct hmm_dma_map *map,
 		if (WARN_ON_ONCE(dma_need_unmap(dev) && !dma_addrs))
 			goto error;
 
-		dma_addr = dma_map_page(dev, page, 0, map->dma_entry_size,
-					DMA_BIDIRECTIONAL);
+		dma_addr = dma_map_phys(dev, paddr, map->dma_entry_size,
+					DMA_BIDIRECTIONAL, attrs);
 		if (dma_mapping_error(dev, dma_addr))
 			goto error;
 
@@ -871,16 +871,17 @@ bool hmm_dma_unmap_pfn(struct device *dev, struct hmm_dma_map *map, size_t idx)
 	if ((pfns[idx] & valid_dma) != valid_dma)
 		return false;
 
+	if (pfns[idx] & HMM_PFN_P2PDMA)
+		attrs |= DMA_ATTR_MMIO;
+
 	if (pfns[idx] & HMM_PFN_P2PDMA_BUS)
 		; /* no need to unmap bus address P2P mappings */
-	else if (dma_use_iova(state)) {
-		if (pfns[idx] & HMM_PFN_P2PDMA)
-			attrs |= DMA_ATTR_SKIP_CPU_SYNC;
+	else if (dma_use_iova(state))
 		dma_iova_unlink(dev, state, idx * map->dma_entry_size,
 				map->dma_entry_size, DMA_BIDIRECTIONAL, attrs);
-	} else if (dma_need_unmap(dev))
-		dma_unmap_page(dev, dma_addrs[idx], map->dma_entry_size,
-			       DMA_BIDIRECTIONAL);
+	else if (dma_need_unmap(dev))
+		dma_unmap_phys(dev, dma_addrs[idx], map->dma_entry_size,
+			       DMA_BIDIRECTIONAL, attrs);
 
 	pfns[idx] &=
 		~(HMM_PFN_DMA_MAPPED | HMM_PFN_P2PDMA | HMM_PFN_P2PDMA_BUS);
diff --git a/mm/kmsan/hooks.c b/mm/kmsan/hooks.c
index 97de3d6194f0..90bee565b9bc 100644
--- a/mm/kmsan/hooks.c
+++ b/mm/kmsan/hooks.c
@@ -336,14 +336,16 @@ static void kmsan_handle_dma_page(const void *addr, size_t size,
 }
 
 /* Helper function to handle DMA data transfers. */
-void kmsan_handle_dma(struct page *page, size_t offset, size_t size,
+void kmsan_handle_dma(phys_addr_t phys, size_t size,
 		      enum dma_data_direction dir)
 {
-	u64 page_offset, to_go, addr;
+	struct page *page = phys_to_page(phys);
+	u64 page_offset, to_go;
+	void *addr;
 
-	if (PageHighMem(page))
+	if (PhysHighMem(phys))
 		return;
-	addr = (u64)page_address(page) + offset;
+	addr = page_to_virt(page);
 	/*
 	 * The kernel may occasionally give us adjacent DMA pages not belonging
 	 * to the same allocation. Process them separately to avoid triggering
@@ -366,8 +368,7 @@ void kmsan_handle_dma_sg(struct scatterlist *sg, int nents,
 	int i;
 
 	for_each_sg(sg, item, nents, i)
-		kmsan_handle_dma(sg_page(item), item->offset, item->length,
-				 dir);
+		kmsan_handle_dma(sg_phys(item), item->length, dir);
 }
 
 /* Functions from kmsan-checks.h follow. */
diff --git a/rust/kernel/dma.rs b/rust/kernel/dma.rs
index 2569c21208e3..4e0af3e1a3b9 100644
--- a/rust/kernel/dma.rs
+++ b/rust/kernel/dma.rs
@@ -252,6 +252,9 @@ pub mod attrs {
     /// Indicates that the buffer is fully accessible at an elevated privilege level (and
     /// ideally inaccessible or at least read-only at lesser-privileged levels).
     pub const DMA_ATTR_PRIVILEGED: Attrs = Attrs(bindings::DMA_ATTR_PRIVILEGED);
+
+    /// Indicates that the buffer is MMIO memory.
+    pub const DMA_ATTR_MMIO: Attrs = Attrs(bindings::DMA_ATTR_MMIO);
 }
 
 /// DMA data direction.
diff --git a/tools/virtio/linux/kmsan.h b/tools/virtio/linux/kmsan.h
index 272b5aa285d5..6cd2e3efd03d 100644
--- a/tools/virtio/linux/kmsan.h
+++ b/tools/virtio/linux/kmsan.h
@@ -4,7 +4,7 @@
 
 #include <linux/gfp.h>
 
-inline void kmsan_handle_dma(struct page *page, size_t offset, size_t size,
+inline void kmsan_handle_dma(phys_addr_t phys, size_t size,
 			     enum dma_data_direction dir)
 {
 }