Merge tag 'dma-mapping-5.9' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - make support for dma_ops optional

 - move more code out of line

 - add generic support for a dma_ops bypass mode

 - misc cleanups

* tag 'dma-mapping-5.9' of git://git.infradead.org/users/hch/dma-mapping:
  dma-contiguous: cleanup dma_alloc_contiguous
  dma-debug: use named initializers for dir2name
  powerpc: use the generic dma_ops_bypass mode
  dma-mapping: add a dma_ops_bypass flag to struct device
  dma-mapping: make support for dma ops optional
  dma-mapping: inline the fast path dma-direct calls
  dma-mapping: move the remaining DMA API calls out of line

26 files changed, 415 insertions, 416 deletions

diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index 10862c5a8c76..9c5f06e8eb9b 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -7,6 +7,7 @@ config ALPHA
 	select ARCH_NO_PREEMPT
 	select ARCH_NO_SG_CHAIN
 	select ARCH_USE_CMPXCHG_LOCKREF
+	select DMA_OPS if PCI
 	select FORCE_PCI if !ALPHA_JENSEN
 	select PCI_DOMAINS if PCI
 	select PCI_SYSCALL if PCI
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index c51eaeb1742b..218bf25b369a 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -41,6 +41,7 @@ config ARM
 	select CPU_PM if SUSPEND || CPU_IDLE
 	select DCACHE_WORD_ACCESS if HAVE_EFFICIENT_UNALIGNED_ACCESS
 	select DMA_DECLARE_COHERENT
+	select DMA_OPS
 	select DMA_REMAP if MMU
 	select EDAC_SUPPORT
 	select EDAC_ATOMIC_SCRUB
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 1fa2fe2ef053..5b4ec80bf586 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -192,6 +192,7 @@ config IA64_SGI_UV
 
 config IA64_HP_SBA_IOMMU
 	bool "HP SBA IOMMU support"
+	select DMA_OPS
 	default y
 	help
 	  Say Y here to add support for the SBA IOMMU found on HP zx1 and
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index ca92c3ed2dc5..001c77cd76b9 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -366,6 +366,7 @@ config MACH_JAZZ
 	select ARC_PROMLIB
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
+	select DMA_OPS
 	select FW_ARC
 	select FW_ARC32
 	select ARCH_MAY_HAVE_PC_FDC
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 2667eeb6c6f1..b0f40fcb06fc 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -14,6 +14,7 @@ config PARISC
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
 	select ARCH_NO_SG_CHAIN
 	select ARCH_SUPPORTS_MEMORY_FAILURE
+	select DMA_OPS
 	select RTC_CLASS
 	select RTC_DRV_GENERIC
 	select INIT_ALL_POSSIBLE
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 3b262d87e9c4..29a057908173 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -151,6 +151,8 @@ config PPC
 	select BUILDTIME_TABLE_SORT
 	select CLONE_BACKWARDS
 	select DCACHE_WORD_ACCESS		if PPC64 && CPU_LITTLE_ENDIAN
+	select DMA_OPS				if PPC64
+	select DMA_OPS_BYPASS			if PPC64
 	select DYNAMIC_FTRACE			if FUNCTION_TRACER
 	select EDAC_ATOMIC_SCRUB
 	select EDAC_SUPPORT
diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h
index 266542769e4b..452402215e12 100644
--- a/arch/powerpc/include/asm/device.h
+++ b/arch/powerpc/include/asm/device.h
@@ -19,11 +19,6 @@ struct iommu_table;
  */
 struct dev_archdata {
 	/*
-	 * Set to %true if the dma_iommu_ops are requested to use a direct
-	 * window instead of dynamically mapping memory.
-	 */
-	bool			iommu_bypass : 1;
-	/*
 	 * These two used to be a union. However, with the hybrid ops we need
 	 * both so here we store both a DMA offset for direct mappings and
 	 * an iommu_table for remapped DMA.
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index e486d1d78de2..569fecd7b5b2 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -14,23 +14,6 @@
  * Generic iommu implementation
  */
 
-/*
- * The coherent mask may be smaller than the real mask, check if we can
- * really use a direct window.
- */
-static inline bool dma_iommu_alloc_bypass(struct device *dev)
-{
-	return dev->archdata.iommu_bypass && !iommu_fixed_is_weak &&
-		dma_direct_supported(dev, dev->coherent_dma_mask);
-}
-
-static inline bool dma_iommu_map_bypass(struct device *dev,
-		unsigned long attrs)
-{
-	return dev->archdata.iommu_bypass &&
-		(!iommu_fixed_is_weak || (attrs & DMA_ATTR_WEAK_ORDERING));
-}
-
 /* Allocates a contiguous real buffer and creates mappings over it.
  * Returns the virtual address of the buffer and sets dma_handle
  * to the dma address (mapping) of the first page.
@@ -39,8 +22,6 @@ static void *dma_iommu_alloc_coherent(struct device *dev, size_t size,
 				      dma_addr_t *dma_handle, gfp_t flag,
 				      unsigned long attrs)
 {
-	if (dma_iommu_alloc_bypass(dev))
-		return dma_direct_alloc(dev, size, dma_handle, flag, attrs);
 	return iommu_alloc_coherent(dev, get_iommu_table_base(dev), size,
 				    dma_handle, dev->coherent_dma_mask, flag,
 				    dev_to_node(dev));
@@ -50,11 +31,7 @@ static void dma_iommu_free_coherent(struct device *dev, size_t size,
 				    void *vaddr, dma_addr_t dma_handle,
 				    unsigned long attrs)
 {
-	if (dma_iommu_alloc_bypass(dev))
-		dma_direct_free(dev, size, vaddr, dma_handle, attrs);
-	else
-		iommu_free_coherent(get_iommu_table_base(dev), size, vaddr,
-				dma_handle);
+	iommu_free_coherent(get_iommu_table_base(dev), size, vaddr, dma_handle);
 }
 
 /* Creates TCEs for a user provided buffer.  The user buffer must be
@@ -67,9 +44,6 @@ static dma_addr_t dma_iommu_map_page(struct device *dev, struct page *page,
 				     enum dma_data_direction direction,
 				     unsigned long attrs)
 {
-	if (dma_iommu_map_bypass(dev, attrs))
-		return dma_direct_map_page(dev, page, offset, size, direction,
-				attrs);
 	return iommu_map_page(dev, get_iommu_table_base(dev), page, offset,
 			      size, dma_get_mask(dev), direction, attrs);
 }
@@ -79,11 +53,8 @@ static void dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle,
 				 size_t size, enum dma_data_direction direction,
 				 unsigned long attrs)
 {
-	if (!dma_iommu_map_bypass(dev, attrs))
-		iommu_unmap_page(get_iommu_table_base(dev), dma_handle, size,
-				direction,  attrs);
-	else
-		dma_direct_unmap_page(dev, dma_handle, size, direction, attrs);
+	iommu_unmap_page(get_iommu_table_base(dev), dma_handle, size, direction,
+			 attrs);
 }
 
 
@@ -91,8 +62,6 @@ static int dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
 			    int nelems, enum dma_data_direction direction,
 			    unsigned long attrs)
 {
-	if (dma_iommu_map_bypass(dev, attrs))
-		return dma_direct_map_sg(dev, sglist, nelems, direction, attrs);
 	return ppc_iommu_map_sg(dev, get_iommu_table_base(dev), sglist, nelems,
 				dma_get_mask(dev), direction, attrs);
 }
@@ -101,11 +70,8 @@ static void dma_iommu_unmap_sg(struct device *dev, struct scatterlist *sglist,
 		int nelems, enum dma_data_direction direction,
 		unsigned long attrs)
 {
-	if (!dma_iommu_map_bypass(dev, attrs))
-		ppc_iommu_unmap_sg(get_iommu_table_base(dev), sglist, nelems,
+	ppc_iommu_unmap_sg(get_iommu_table_base(dev), sglist, nelems,
 			   direction, attrs);
-	else
-		dma_direct_unmap_sg(dev, sglist, nelems, direction, attrs);
 }
 
 static bool dma_iommu_bypass_supported(struct device *dev, u64 mask)
@@ -113,8 +79,9 @@ static bool dma_iommu_bypass_supported(struct device *dev, u64 mask)
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct pci_controller *phb = pci_bus_to_host(pdev->bus);
 
-	return phb->controller_ops.iommu_bypass_supported &&
-		phb->controller_ops.iommu_bypass_supported(pdev, mask);
+	if (iommu_fixed_is_weak || !phb->controller_ops.iommu_bypass_supported)
+		return false;
+	return phb->controller_ops.iommu_bypass_supported(pdev, mask);
 }
 
 /* We support DMA to/from any memory page via the iommu */
@@ -123,7 +90,7 @@ int dma_iommu_dma_supported(struct device *dev, u64 mask)
 	struct iommu_table *tbl = get_iommu_table_base(dev);
 
 	if (dev_is_pci(dev) && dma_iommu_bypass_supported(dev, mask)) {
-		dev->archdata.iommu_bypass = true;
+		dev->dma_ops_bypass = true;
 		dev_dbg(dev, "iommu: 64-bit OK, using fixed ops\n");
 		return 1;
 	}
@@ -141,7 +108,7 @@ int dma_iommu_dma_supported(struct device *dev, u64 mask)
 	}
 
 	dev_dbg(dev, "iommu: not 64-bit, using default ops\n");
-	dev->archdata.iommu_bypass = false;
+	dev->dma_ops_bypass = false;
 	return 1;
 }
 
@@ -153,47 +120,12 @@ u64 dma_iommu_get_required_mask(struct device *dev)
 	if (!tbl)
 		return 0;
 
-	if (dev_is_pci(dev)) {
-		u64 bypass_mask = dma_direct_get_required_mask(dev);
-
-		if (dma_iommu_bypass_supported(dev, bypass_mask))
-			return bypass_mask;
-	}
-
 	mask = 1ULL < (fls_long(tbl->it_offset + tbl->it_size) - 1);
 	mask += mask - 1;
 
 	return mask;
 }
 
-static void dma_iommu_sync_for_cpu(struct device *dev, dma_addr_t addr,
-		size_t size, enum dma_data_direction dir)
-{
-	if (dma_iommu_alloc_bypass(dev))
-		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
-}
-
-static void dma_iommu_sync_for_device(struct device *dev, dma_addr_t addr,
-		size_t sz, enum dma_data_direction dir)
-{
-	if (dma_iommu_alloc_bypass(dev))
-		dma_direct_sync_single_for_device(dev, addr, sz, dir);
-}
-
-extern void dma_iommu_sync_sg_for_cpu(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
-{
-	if (dma_iommu_alloc_bypass(dev))
-		dma_direct_sync_sg_for_cpu(dev, sgl, nents, dir);
-}
-
-extern void dma_iommu_sync_sg_for_device(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
-{
-	if (dma_iommu_alloc_bypass(dev))
-		dma_direct_sync_sg_for_device(dev, sgl, nents, dir);
-}
-
 const struct dma_map_ops dma_iommu_ops = {
 	.alloc			= dma_iommu_alloc_coherent,
 	.free			= dma_iommu_free_coherent,
@@ -203,10 +135,6 @@ const struct dma_map_ops dma_iommu_ops = {
 	.map_page		= dma_iommu_map_page,
 	.unmap_page		= dma_iommu_unmap_page,
 	.get_required_mask	= dma_iommu_get_required_mask,
-	.sync_single_for_cpu	= dma_iommu_sync_for_cpu,
-	.sync_single_for_device	= dma_iommu_sync_for_device,
-	.sync_sg_for_cpu	= dma_iommu_sync_sg_for_cpu,
-	.sync_sg_for_device	= dma_iommu_sync_sg_for_device,
 	.mmap			= dma_common_mmap,
 	.get_sgtable		= dma_common_get_sgtable,
 };
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index e55debeeef9a..8c0b52940165 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -112,6 +112,7 @@ config S390
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select BUILDTIME_TABLE_SORT
 	select CLONE_BACKWARDS2
+	select DMA_OPS if PCI
 	select DYNAMIC_FTRACE if FUNCTION_TRACER
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CPU_AUTOPROBE
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 5bf2dc163540..5db1faaaee31 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -15,6 +15,7 @@ config SPARC
 	default y
 	select ARCH_MIGHT_HAVE_PC_PARPORT if SPARC64 && PCI
 	select ARCH_MIGHT_HAVE_PC_SERIO
+	select DMA_OPS
 	select OF
 	select OF_PROMTREE
 	select HAVE_ASM_MODVERSIONS
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index addb27d68c6e..5f17f1f2c4c9 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -909,6 +909,7 @@ config DMI
 
 config GART_IOMMU
 	bool "Old AMD GART IOMMU support"
+	select DMA_OPS
 	select IOMMU_HELPER
 	select SWIOTLB
 	depends on X86_64 && PCI && AMD_NB
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 905a2beaf885..2927a9d16eaa 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -1183,6 +1183,8 @@ static void setup_dma_device(struct ib_device *device)
 	struct device *parent = device->dev.parent;
 
 	WARN_ON_ONCE(device->dma_device);
+
+#ifdef CONFIG_DMA_OPS
 	if (device->dev.dma_ops) {
 		/*
 		 * The caller provided custom DMA operations. Copy the
@@ -1203,7 +1205,9 @@ static void setup_dma_device(struct ib_device *device)
 			else
 				WARN_ON_ONCE(true);
 		}
-	} else {
+	} else
+#endif /* CONFIG_DMA_OPS */
+	{
 		/*
 		 * The caller did not provide custom DMA operations. Use the
 		 * DMA mapping operations of the parent device.
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index b0f308cb7f7c..b622af72448f 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -97,6 +97,7 @@ config OF_IOMMU
 # IOMMU-agnostic DMA-mapping layer
 config IOMMU_DMA
 	bool
+	select DMA_OPS
 	select IOMMU_API
 	select IOMMU_IOVA
 	select IRQ_MSI_IOMMU
@@ -183,6 +184,7 @@ config DMAR_TABLE
 config INTEL_IOMMU
 	bool "Support for Intel IOMMU using DMA Remapping Devices"
 	depends on PCI_MSI && ACPI && (X86 || IA64)
+	select DMA_OPS
 	select IOMMU_API
 	select IOMMU_IOVA
 	select NEED_DMA_MAP_STATE
diff --git a/drivers/macintosh/macio_asic.c b/drivers/macintosh/macio_asic.c
index 92d142d2b75f..49af60bdac92 100644
--- a/drivers/macintosh/macio_asic.c
+++ b/drivers/macintosh/macio_asic.c
@@ -382,7 +382,7 @@ static struct macio_dev * macio_add_one_device(struct macio_chip *chip,
 	dma_set_max_seg_size(&dev->ofdev.dev, 65536);
 	dma_set_seg_boundary(&dev->ofdev.dev, 0xffffffff);
 
-#ifdef CONFIG_PCI
+#if defined(CONFIG_PCI) && defined(CONFIG_DMA_OPS)
 	/* Set the DMA ops to the ones from the PCI device, this could be
 	 * fishy if we didn't know that on PowerMac it's always direct ops
 	 * or iommu ops that will work fine
@@ -391,7 +391,7 @@ static struct macio_dev * macio_add_one_device(struct macio_chip *chip,
 	 */
 	dev->ofdev.dev.archdata = chip->lbus.pdev->dev.archdata;
 	dev->ofdev.dev.dma_ops = chip->lbus.pdev->dev.dma_ops;
-#endif /* CONFIG_PCI */
+#endif /* CONFIG_PCI && CONFIG_DMA_OPS */
 
 #ifdef DEBUG
 	printk("preparing mdev @%p, ofdev @%p, dev @%p, kobj @%p\n",
diff --git a/drivers/misc/mic/Kconfig b/drivers/misc/mic/Kconfig
index 8f201d019f5a..b9bb086785db 100644
--- a/drivers/misc/mic/Kconfig
+++ b/drivers/misc/mic/Kconfig
@@ -4,6 +4,7 @@ menu "Intel MIC & related support"
 config INTEL_MIC_BUS
 	tristate "Intel MIC Bus Driver"
 	depends on 64BIT && PCI && X86
+	select DMA_OPS
 	help
 	  This option is selected by any driver which registers a
 	  device or driver on the MIC Bus, such as CONFIG_INTEL_MIC_HOST,
@@ -19,6 +20,7 @@ config INTEL_MIC_BUS
 config SCIF_BUS
 	tristate "SCIF Bus Driver"
 	depends on 64BIT && PCI && X86
+	select DMA_OPS
 	help
 	  This option is selected by any driver which registers a
 	  device or driver on the SCIF Bus, such as CONFIG_INTEL_MIC_HOST
@@ -33,6 +35,7 @@ config SCIF_BUS
 
 config VOP_BUS
 	tristate "VOP Bus Driver"
+	select DMA_OPS
 	help
 	  This option is selected by any driver which registers a
 	  device or driver on the VOP Bus, such as CONFIG_INTEL_MIC_HOST
@@ -49,6 +52,7 @@ config INTEL_MIC_HOST
 	tristate "Intel MIC Host Driver"
 	depends on 64BIT && PCI && X86
 	depends on INTEL_MIC_BUS && SCIF_BUS && MIC_COSM && VOP_BUS
+	select DMA_OPS
 	help
 	  This enables Host Driver support for the Intel Many Integrated
 	  Core (MIC) family of PCIe form factor coprocessor devices that
diff --git a/drivers/vdpa/Kconfig b/drivers/vdpa/Kconfig
index 3e1ceb8e9f2b..d93a69b12f81 100644
--- a/drivers/vdpa/Kconfig
+++ b/drivers/vdpa/Kconfig
@@ -11,6 +11,7 @@ if VDPA
 config VDPA_SIM
 	tristate "vDPA device simulator"
 	depends on RUNTIME_TESTING_MENU && HAS_DMA
+	select DMA_OPS
 	select VHOST_RING
 	default n
 	help
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index 727f11eb46b2..1d339ef92422 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -179,6 +179,7 @@ config XEN_GRANT_DMA_ALLOC
 
 config SWIOTLB_XEN
 	def_bool y
+	select DMA_OPS
 	select SWIOTLB
 
 config XEN_PCIDEV_BACKEND
diff --git a/include/linux/device.h b/include/linux/device.h
index 4e2e9d3a2eda..06d3b7622082 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -525,6 +525,11 @@ struct dev_links_info {
  *		  sync_state() callback.
  * @dma_coherent: this particular device is dma coherent, even if the
  *		architecture supports non-coherent devices.
+ * @dma_ops_bypass: If set to %true then the dma_ops are bypassed for the
+ *		streaming DMA operations (->map_* / ->unmap_* / ->sync_*),
+ *		and optionall (if the coherent mask is large enough) also
+ *		for dma allocations.  This flag is managed by the dma ops
+ *		instance from ->dma_supported.
  *
  * At the lowest level, every device in a Linux system is represented by an
  * instance of struct device. The device structure contains the information
@@ -574,8 +579,9 @@ struct device {
 #ifdef CONFIG_GENERIC_MSI_IRQ
 	struct list_head	msi_list;
 #endif
-
+#ifdef CONFIG_DMA_OPS
 	const struct dma_map_ops *dma_ops;
+#endif
 	u64		*dma_mask;	/* dma mask (if dma'able device) */
 	u64		coherent_dma_mask;/* Like dma_mask, but for
 					     alloc_coherent mappings as
@@ -628,6 +634,9 @@ struct device {
     defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL)
 	bool			dma_coherent:1;
 #endif
+#ifdef CONFIG_DMA_OPS_BYPASS
+	bool			dma_ops_bypass : 1;
+#endif
 };
 
 static inline struct device *kobj_to_dev(struct kobject *kobj)
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index ab2e20cba951..5a3ce2a24794 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -1,10 +1,16 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Internals of the DMA direct mapping implementation.  Only for use by the
+ * DMA mapping code and IOMMU drivers.
+ */
 #ifndef _LINUX_DMA_DIRECT_H
 #define _LINUX_DMA_DIRECT_H 1
 
 #include <linux/dma-mapping.h>
+#include <linux/dma-noncoherent.h>
 #include <linux/memblock.h> /* for min_low_pfn */
 #include <linux/mem_encrypt.h>
+#include <linux/swiotlb.h>
 
 extern unsigned int zone_dma_bits;
 
@@ -87,4 +93,102 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
 		unsigned long attrs);
 int dma_direct_supported(struct device *dev, u64 mask);
 bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr);
+int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
+		enum dma_data_direction dir, unsigned long attrs);
+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);
+size_t dma_direct_max_mapping_size(struct device *dev);
+
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
+    defined(CONFIG_SWIOTLB)
+void dma_direct_sync_sg_for_device(struct device *dev, struct scatterlist *sgl,
+		int nents, enum dma_data_direction dir);
+#else
+static inline void dma_direct_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+}
+#endif
+
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
+    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \
+    defined(CONFIG_SWIOTLB)
+void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
+		int nents, enum dma_data_direction dir, unsigned long attrs);
+void dma_direct_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir);
+#else
+static inline void dma_direct_unmap_sg(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+}
+static inline void dma_direct_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+}
+#endif
+
+static inline void dma_direct_sync_single_for_device(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+	phys_addr_t paddr = dma_to_phys(dev, addr);
+
+	if (unlikely(is_swiotlb_buffer(paddr)))
+		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE);
+
+	if (!dev_is_dma_coherent(dev))
+		arch_sync_dma_for_device(paddr, size, dir);
+}
+
+static inline void dma_direct_sync_single_for_cpu(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+	phys_addr_t paddr = dma_to_phys(dev, addr);
+
+	if (!dev_is_dma_coherent(dev)) {
+		arch_sync_dma_for_cpu(paddr, size, dir);
+		arch_sync_dma_for_cpu_all();
+	}
+
+	if (unlikely(is_swiotlb_buffer(paddr)))
+		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
+}
+
+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)
+{
+	phys_addr_t phys = page_to_phys(page) + offset;
+	dma_addr_t dma_addr = phys_to_dma(dev, phys);
+
+	if (unlikely(swiotlb_force == SWIOTLB_FORCE))
+		return swiotlb_map(dev, phys, size, dir, attrs);
+
+	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
+		if (swiotlb_force != SWIOTLB_NO_FORCE)
+			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 (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		arch_sync_dma_for_device(phys, size, dir);
+	return dma_addr;
+}
+
+static inline void dma_direct_unmap_page(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);
+
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
+
+	if (unlikely(is_swiotlb_buffer(phys)))
+		swiotlb_tbl_unmap_single(dev, phys, size, size, dir, attrs);
+}
 #endif /* _LINUX_DMA_DIRECT_H */
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index a33ed3954ed4..39da883c8619 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -188,76 +188,10 @@ static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma,
 }
 #endif /* CONFIG_DMA_DECLARE_COHERENT */
 
-static inline bool dma_is_direct(const struct dma_map_ops *ops)
-{
-	return likely(!ops);
-}
-
-/*
- * All the dma_direct_* declarations are here just for the indirect call bypass,
- * and must not be used directly drivers!
- */
-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);
-int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
-		enum dma_data_direction dir, unsigned long attrs);
-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);
-
-#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
-    defined(CONFIG_SWIOTLB)
-void dma_direct_sync_single_for_device(struct device *dev,
-		dma_addr_t addr, size_t size, enum dma_data_direction dir);
-void dma_direct_sync_sg_for_device(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir);
-#else
-static inline void dma_direct_sync_single_for_device(struct device *dev,
-		dma_addr_t addr, size_t size, enum dma_data_direction dir)
-{
-}
-static inline void dma_direct_sync_sg_for_device(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
-{
-}
-#endif
-
-#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
-    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \
-    defined(CONFIG_SWIOTLB)
-void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
-		size_t size, enum dma_data_direction dir, unsigned long attrs);
-void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
-		int nents, enum dma_data_direction dir, unsigned long attrs);
-void dma_direct_sync_single_for_cpu(struct device *dev,
-		dma_addr_t addr, size_t size, enum dma_data_direction dir);
-void dma_direct_sync_sg_for_cpu(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir);
-#else
-static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
-}
-static inline void dma_direct_unmap_sg(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir,
-		unsigned long attrs)
-{
-}
-static inline void dma_direct_sync_single_for_cpu(struct device *dev,
-		dma_addr_t addr, size_t size, enum dma_data_direction dir)
-{
-}
-static inline void dma_direct_sync_sg_for_cpu(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
-{
-}
-#endif
-
-size_t dma_direct_max_mapping_size(struct device *dev);
-
 #ifdef CONFIG_HAS_DMA
 #include <asm/dma-mapping.h>
 
+#ifdef CONFIG_DMA_OPS
 static inline const struct dma_map_ops *get_dma_ops(struct device *dev)
 {
 	if (dev->dma_ops)
@@ -270,165 +204,16 @@ static inline void set_dma_ops(struct device *dev,
 {
 	dev->dma_ops = dma_ops;
 }
-
-static inline 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)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-	dma_addr_t addr;
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
-		addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
-	else
-		addr = ops->map_page(dev, page, offset, size, dir, attrs);
-	debug_dma_map_page(dev, page, offset, size, dir, addr);
-
-	return addr;
-}
-
-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)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
-		dma_direct_unmap_page(dev, addr, size, dir, attrs);
-	else if (ops->unmap_page)
-		ops->unmap_page(dev, addr, size, dir, attrs);
-	debug_dma_unmap_page(dev, addr, size, dir);
-}
-
-/*
- * dma_maps_sg_attrs returns 0 on error and > 0 on success.
- * It should never return a value < 0.
- */
-static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
-				   int nents, enum dma_data_direction dir,
-				   unsigned long attrs)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-	int ents;
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
-		ents = dma_direct_map_sg(dev, sg, nents, dir, attrs);
-	else
-		ents = ops->map_sg(dev, sg, nents, dir, attrs);
-	BUG_ON(ents < 0);
-	debug_dma_map_sg(dev, sg, nents, ents, dir);
-
-	return ents;
-}
-
-static inline void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg,
-				      int nents, enum dma_data_direction dir,
-				      unsigned long attrs)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	debug_dma_unmap_sg(dev, sg, nents, dir);
-	if (dma_is_direct(ops))
-		dma_direct_unmap_sg(dev, sg, nents, dir, attrs);
-	else if (ops->unmap_sg)
-		ops->unmap_sg(dev, sg, nents, dir, attrs);
-}
-
-static inline 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));
-
-	/* Don't allow RAM to be mapped */
-	if (WARN_ON_ONCE(pfn_valid(PHYS_PFN(phys_addr))))
-		return DMA_MAPPING_ERROR;
-
-	if (dma_is_direct(ops))
-		addr = dma_direct_map_resource(dev, phys_addr, size, dir, attrs);
-	else if (ops->map_resource)
-		addr = ops->map_resource(dev, phys_addr, size, dir, attrs);
-
-	debug_dma_map_resource(dev, phys_addr, size, dir, addr);
-	return addr;
-}
-
-static inline 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_is_direct(ops) && ops->unmap_resource)
-		ops->unmap_resource(dev, addr, size, dir, attrs);
-	debug_dma_unmap_resource(dev, addr, size, dir);
-}
-
-static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
-					   size_t size,
-					   enum dma_data_direction dir)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
-		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
-	else if (ops->sync_single_for_cpu)
-		ops->sync_single_for_cpu(dev, addr, size, dir);
-	debug_dma_sync_single_for_cpu(dev, addr, size, dir);
-}
-
-static inline void dma_sync_single_for_device(struct device *dev,
-					      dma_addr_t addr, size_t size,
-					      enum dma_data_direction dir)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
-		dma_direct_sync_single_for_device(dev, addr, size, dir);
-	else if (ops->sync_single_for_device)
-		ops->sync_single_for_device(dev, addr, size, dir);
-	debug_dma_sync_single_for_device(dev, addr, size, dir);
-}
-
-static inline void
-dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
-		    int nelems, enum dma_data_direction dir)
+#else /* CONFIG_DMA_OPS */
+static inline const struct dma_map_ops *get_dma_ops(struct device *dev)
 {
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
-		dma_direct_sync_sg_for_cpu(dev, sg, nelems, dir);
-	else if (ops->sync_sg_for_cpu)
-		ops->sync_sg_for_cpu(dev, sg, nelems, dir);
-	debug_dma_sync_sg_for_cpu(dev, sg, nelems, dir);
+	return NULL;
 }
-
-static inline void
-dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
-		       int nelems, enum dma_data_direction dir)
+static inline void set_dma_ops(struct device *dev,
+			       const struct dma_map_ops *dma_ops)
 {
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
-		dma_direct_sync_sg_for_device(dev, sg, nelems, dir);
-	else if (ops->sync_sg_for_device)
-		ops->sync_sg_for_device(dev, sg, nelems, dir);
-	debug_dma_sync_sg_for_device(dev, sg, nelems, dir);
-
 }
+#endif /* CONFIG_DMA_OPS */
 
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
@@ -439,6 +224,28 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 	return 0;
 }
 
+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);
+void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size,
+		enum dma_data_direction dir, unsigned long attrs);
+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,
+				      int nents, enum dma_data_direction dir,
+				      unsigned long 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);
+void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size,
+		enum dma_data_direction dir, unsigned long attrs);
+void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size,
+		enum dma_data_direction dir);
+void dma_sync_single_for_device(struct device *dev, dma_addr_t addr,
+		size_t size, enum dma_data_direction dir);
+void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
+		    int nelems, enum dma_data_direction dir);
+void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
+		       int nelems, enum dma_data_direction dir);
 void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t flag, unsigned long attrs);
 void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr,
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index 1da3f44f2565..f4770fcfa62b 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -5,6 +5,17 @@ config HAS_DMA
 	depends on !NO_DMA
 	default y
 
+config DMA_OPS
+	bool
+
+#
+# IOMMU drivers that can bypass the IOMMU code and optionally use the direct
+# mapping fast path should select this option and set the dma_ops_bypass
+# flag in struct device where applicable
+#
+config DMA_OPS_BYPASS
+	bool
+
 config NEED_SG_DMA_LENGTH
 	bool
 
@@ -60,6 +71,7 @@ config DMA_NONCOHERENT_CACHE_SYNC
 config DMA_VIRT_OPS
 	bool
 	depends on HAS_DMA
+	select DMA_OPS
 
 config SWIOTLB
 	bool
diff --git a/kernel/dma/Makefile b/kernel/dma/Makefile
index 370f63344e9c..32c7c1942bbd 100644
--- a/kernel/dma/Makefile
+++ b/kernel/dma/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
-obj-$(CONFIG_HAS_DMA)			+= mapping.o direct.o dummy.o
+obj-$(CONFIG_HAS_DMA)			+= mapping.o direct.o
+obj-$(CONFIG_DMA_OPS)			+= dummy.o
 obj-$(CONFIG_DMA_CMA)			+= contiguous.o
 obj-$(CONFIG_DMA_DECLARE_COHERENT)	+= coherent.o
 obj-$(CONFIG_DMA_VIRT_OPS)		+= virt.o
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 15bc5026c485..cff7e60968b9 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -215,6 +215,13 @@ bool dma_release_from_contiguous(struct device *dev, struct page *pages,
 	return cma_release(dev_get_cma_area(dev), pages, count);
 }
 
+static struct page *cma_alloc_aligned(struct cma *cma, size_t size, gfp_t gfp)
+{
+	unsigned int align = min(get_order(size), CONFIG_CMA_ALIGNMENT);
+
+	return cma_alloc(cma, size >> PAGE_SHIFT, align, gfp & __GFP_NOWARN);
+}
+
 /**
  * dma_alloc_contiguous() - allocate contiguous pages
  * @dev:   Pointer to device for which the allocation is performed.
@@ -231,24 +238,14 @@ bool dma_release_from_contiguous(struct device *dev, struct page *pages,
  */
 struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp)
 {
-	size_t count = size >> PAGE_SHIFT;
-	struct page *page = NULL;
-	struct cma *cma = NULL;
-
-	if (dev && dev->cma_area)
-		cma = dev->cma_area;
-	else if (count > 1)
-		cma = dma_contiguous_default_area;
-
 	/* CMA can be used only in the context which permits sleeping */
-	if (cma && gfpflags_allow_blocking(gfp)) {
-		size_t align = get_order(size);
-		size_t cma_align = min_t(size_t, align, CONFIG_CMA_ALIGNMENT);
-
-		page = cma_alloc(cma, count, cma_align, gfp & __GFP_NOWARN);
-	}
-
-	return page;
+	if (!gfpflags_allow_blocking(gfp))
+		return NULL;
+	if (dev->cma_area)
+		return cma_alloc_aligned(dev->cma_area, size, gfp);
+	if (size <= PAGE_SIZE || !dma_contiguous_default_area)
+		return NULL;
+	return cma_alloc_aligned(dma_contiguous_default_area, size, gfp);
 }
 
 /**
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index d628ab09d97b..5aba04075530 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -144,8 +144,12 @@ static const char *type2name[] = {
 	[dma_debug_resource] = "resource",
 };
 
-static const char *dir2name[4] = { "DMA_BIDIRECTIONAL", "DMA_TO_DEVICE",
-				   "DMA_FROM_DEVICE", "DMA_NONE" };
+static const char *dir2name[] = {
+	[DMA_BIDIRECTIONAL]	= "DMA_BIDIRECTIONAL",
+	[DMA_TO_DEVICE]		= "DMA_TO_DEVICE",
+	[DMA_FROM_DEVICE]	= "DMA_FROM_DEVICE",
+	[DMA_NONE]		= "DMA_NONE",
+};
 
 /*
  * The access to some variables in this macro is racy. We can't use atomic_t
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 67f060b86a73..bb0041e99659 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -10,11 +10,9 @@
 #include <linux/dma-direct.h>
 #include <linux/scatterlist.h>
 #include <linux/dma-contiguous.h>
-#include <linux/dma-noncoherent.h>
 #include <linux/pfn.h>
 #include <linux/vmalloc.h>
 #include <linux/set_memory.h>
-#include <linux/swiotlb.h>
 
 /*
  * Most architectures use ZONE_DMA for the first 16 Megabytes, but some use it
@@ -304,19 +302,6 @@ void dma_direct_free(struct device *dev, size_t size,
 
 #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
     defined(CONFIG_SWIOTLB)
-void dma_direct_sync_single_for_device(struct device *dev,
-		dma_addr_t addr, size_t size, enum dma_data_direction dir)
-{
-	phys_addr_t paddr = dma_to_phys(dev, addr);
-
-	if (unlikely(is_swiotlb_buffer(paddr)))
-		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE);
-
-	if (!dev_is_dma_coherent(dev))
-		arch_sync_dma_for_device(paddr, size, dir);
-}
-EXPORT_SYMBOL(dma_direct_sync_single_for_device);
-
 void dma_direct_sync_sg_for_device(struct device *dev,
 		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
 {
@@ -335,27 +320,11 @@ void dma_direct_sync_sg_for_device(struct device *dev,
 					dir);
 	}
 }
-EXPORT_SYMBOL(dma_direct_sync_sg_for_device);
 #endif
 
 #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
     defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \
     defined(CONFIG_SWIOTLB)
-void dma_direct_sync_single_for_cpu(struct device *dev,
-		dma_addr_t addr, size_t size, enum dma_data_direction dir)
-{
-	phys_addr_t paddr = dma_to_phys(dev, addr);
-
-	if (!dev_is_dma_coherent(dev)) {
-		arch_sync_dma_for_cpu(paddr, size, dir);
-		arch_sync_dma_for_cpu_all();
-	}
-
-	if (unlikely(is_swiotlb_buffer(paddr)))
-		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
-}
-EXPORT_SYMBOL(dma_direct_sync_single_for_cpu);
-
 void dma_direct_sync_sg_for_cpu(struct device *dev,
 		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
 {
@@ -376,20 +345,6 @@ void dma_direct_sync_sg_for_cpu(struct device *dev,
 	if (!dev_is_dma_coherent(dev))
 		arch_sync_dma_for_cpu_all();
 }
-EXPORT_SYMBOL(dma_direct_sync_sg_for_cpu);
-
-void dma_direct_unmap_page(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);
-
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
-
-	if (unlikely(is_swiotlb_buffer(phys)))
-		swiotlb_tbl_unmap_single(dev, phys, size, size, dir, attrs);
-}
-EXPORT_SYMBOL(dma_direct_unmap_page);
 
 void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
 		int nents, enum dma_data_direction dir, unsigned long attrs)
@@ -401,35 +356,8 @@ void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
 		dma_direct_unmap_page(dev, sg->dma_address, sg_dma_len(sg), dir,
 			     attrs);
 }
-EXPORT_SYMBOL(dma_direct_unmap_sg);
 #endif
 
-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)
-{
-	phys_addr_t phys = page_to_phys(page) + offset;
-	dma_addr_t dma_addr = phys_to_dma(dev, phys);
-
-	if (unlikely(swiotlb_force == SWIOTLB_FORCE))
-		return swiotlb_map(dev, phys, size, dir, attrs);
-
-	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
-		if (swiotlb_force != SWIOTLB_NO_FORCE)
-			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 (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		arch_sync_dma_for_device(phys, size, dir);
-	return dma_addr;
-}
-EXPORT_SYMBOL(dma_direct_map_page);
-
 int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
 		enum dma_data_direction dir, unsigned long attrs)
 {
@@ -450,7 +378,6 @@ out_unmap:
 	dma_direct_unmap_sg(dev, sgl, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC);
 	return 0;
 }
-EXPORT_SYMBOL(dma_direct_map_sg);
 
 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)
@@ -467,7 +394,6 @@ dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
 
 	return dma_addr;
 }
-EXPORT_SYMBOL(dma_direct_map_resource);
 
 int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index a8c18c9a796f..0d129421e75f 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -105,6 +105,196 @@ void *dmam_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
 }
 EXPORT_SYMBOL(dmam_alloc_attrs);
 
+static bool dma_go_direct(struct device *dev, dma_addr_t mask,
+		const struct dma_map_ops *ops)
+{
+	if (likely(!ops))
+		return true;
+#ifdef CONFIG_DMA_OPS_BYPASS
+	if (dev->dma_ops_bypass)
+		return min_not_zero(mask, dev->bus_dma_limit) >=
+			    dma_direct_get_required_mask(dev);
+#endif
+	return false;
+}
+
+
+/*
+ * Check if the devices uses a direct mapping for streaming DMA operations.
+ * This allows IOMMU drivers to set a bypass mode if the DMA mask is large
+ * enough.
+ */
+static inline bool dma_alloc_direct(struct device *dev,
+		const struct dma_map_ops *ops)
+{
+	return dma_go_direct(dev, dev->coherent_dma_mask, ops);
+}
+
+static inline bool dma_map_direct(struct device *dev,
+		const struct dma_map_ops *ops)
+{
+	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)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	dma_addr_t addr;
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (dma_map_direct(dev, ops))
+		addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
+	else
+		addr = ops->map_page(dev, page, offset, size, dir, attrs);
+	debug_dma_map_page(dev, page, offset, size, dir, addr);
+
+	return addr;
+}
+EXPORT_SYMBOL(dma_map_page_attrs);
+
+void dma_unmap_page_attrs(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))
+		dma_direct_unmap_page(dev, addr, size, dir, attrs);
+	else if (ops->unmap_page)
+		ops->unmap_page(dev, addr, size, dir, attrs);
+	debug_dma_unmap_page(dev, addr, size, dir);
+}
+EXPORT_SYMBOL(dma_unmap_page_attrs);
+
+/*
+ * dma_maps_sg_attrs returns 0 on error and > 0 on success.
+ * It should never return a value < 0.
+ */
+int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int nents,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	int ents;
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (dma_map_direct(dev, ops))
+		ents = dma_direct_map_sg(dev, sg, nents, dir, attrs);
+	else
+		ents = ops->map_sg(dev, sg, nents, dir, attrs);
+	BUG_ON(ents < 0);
+	debug_dma_map_sg(dev, sg, nents, ents, dir);
+
+	return ents;
+}
+EXPORT_SYMBOL(dma_map_sg_attrs);
+
+void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg,
+				      int nents, enum dma_data_direction dir,
+				      unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	debug_dma_unmap_sg(dev, sg, nents, dir);
+	if (dma_map_direct(dev, ops))
+		dma_direct_unmap_sg(dev, sg, nents, dir, attrs);
+	else if (ops->unmap_sg)
+		ops->unmap_sg(dev, sg, nents, dir, attrs);
+}
+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));
+
+	/* Don't allow RAM to be mapped */
+	if (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 (ops->map_resource)
+		addr = ops->map_resource(dev, phys_addr, size, dir, attrs);
+
+	debug_dma_map_resource(dev, phys_addr, size, dir, addr);
+	return addr;
+}
+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) && ops->unmap_resource)
+		ops->unmap_resource(dev, addr, size, dir, attrs);
+	debug_dma_unmap_resource(dev, addr, size, dir);
+}
+EXPORT_SYMBOL(dma_unmap_resource);
+
+void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size,
+		enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (dma_map_direct(dev, ops))
+		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
+	else if (ops->sync_single_for_cpu)
+		ops->sync_single_for_cpu(dev, addr, size, dir);
+	debug_dma_sync_single_for_cpu(dev, addr, size, dir);
+}
+EXPORT_SYMBOL(dma_sync_single_for_cpu);
+
+void dma_sync_single_for_device(struct device *dev, dma_addr_t addr,
+		size_t size, enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (dma_map_direct(dev, ops))
+		dma_direct_sync_single_for_device(dev, addr, size, dir);
+	else if (ops->sync_single_for_device)
+		ops->sync_single_for_device(dev, addr, size, dir);
+	debug_dma_sync_single_for_device(dev, addr, size, dir);
+}
+EXPORT_SYMBOL(dma_sync_single_for_device);
+
+void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
+		    int nelems, enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (dma_map_direct(dev, ops))
+		dma_direct_sync_sg_for_cpu(dev, sg, nelems, dir);
+	else if (ops->sync_sg_for_cpu)
+		ops->sync_sg_for_cpu(dev, sg, nelems, dir);
+	debug_dma_sync_sg_for_cpu(dev, sg, nelems, dir);
+}
+EXPORT_SYMBOL(dma_sync_sg_for_cpu);
+
+void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
+		       int nelems, enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (dma_map_direct(dev, ops))
+		dma_direct_sync_sg_for_device(dev, sg, nelems, dir);
+	else if (ops->sync_sg_for_device)
+		ops->sync_sg_for_device(dev, sg, nelems, dir);
+	debug_dma_sync_sg_for_device(dev, sg, nelems, dir);
+}
+EXPORT_SYMBOL(dma_sync_sg_for_device);
+
 /*
  * Create scatter-list for the already allocated DMA buffer.
  */
@@ -138,7 +328,7 @@ int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt,
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
-	if (dma_is_direct(ops))
+	if (dma_alloc_direct(dev, ops))
 		return dma_direct_get_sgtable(dev, sgt, cpu_addr, dma_addr,
 				size, attrs);
 	if (!ops->get_sgtable)
@@ -208,7 +398,7 @@ bool dma_can_mmap(struct device *dev)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
-	if (dma_is_direct(ops))
+	if (dma_alloc_direct(dev, ops))
 		return dma_direct_can_mmap(dev);
 	return ops->mmap != NULL;
 }
@@ -233,7 +423,7 @@ int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
-	if (dma_is_direct(ops))
+	if (dma_alloc_direct(dev, ops))
 		return dma_direct_mmap(dev, vma, cpu_addr, dma_addr, size,
 				attrs);
 	if (!ops->mmap)
@@ -246,7 +436,7 @@ u64 dma_get_required_mask(struct device *dev)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
-	if (dma_is_direct(ops))
+	if (dma_alloc_direct(dev, ops))
 		return dma_direct_get_required_mask(dev);
 	if (ops->get_required_mask)
 		return ops->get_required_mask(dev);
@@ -277,7 +467,7 @@ void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	/* let the implementation decide on the zone to allocate from: */
 	flag &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM);
 
-	if (dma_is_direct(ops))
+	if (dma_alloc_direct(dev, ops))
 		cpu_addr = dma_direct_alloc(dev, size, dma_handle, flag, attrs);
 	else if (ops->alloc)
 		cpu_addr = ops->alloc(dev, size, dma_handle, flag, attrs);
@@ -309,7 +499,7 @@ void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 		return;
 
 	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
-	if (dma_is_direct(ops))
+	if (dma_alloc_direct(dev, ops))
 		dma_direct_free(dev, size, cpu_addr, dma_handle, attrs);
 	else if (ops->free)
 		ops->free(dev, size, cpu_addr, dma_handle, attrs);
@@ -320,7 +510,11 @@ int dma_supported(struct device *dev, u64 mask)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
-	if (dma_is_direct(ops))
+	/*
+	 * ->dma_supported sets the bypass flag, so we must always call
+	 * into the method here unless the device is truly direct mapped.
+	 */
+	if (!ops)
 		return dma_direct_supported(dev, mask);
 	if (!ops->dma_supported)
 		return 1;
@@ -376,7 +570,7 @@ void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 
 	BUG_ON(!valid_dma_direction(dir));
 
-	if (dma_is_direct(ops))
+	if (dma_alloc_direct(dev, ops))
 		arch_dma_cache_sync(dev, vaddr, size, dir);
 	else if (ops->cache_sync)
 		ops->cache_sync(dev, vaddr, size, dir);
@@ -388,7 +582,7 @@ size_t dma_max_mapping_size(struct device *dev)
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 	size_t size = SIZE_MAX;
 
-	if (dma_is_direct(ops))
+	if (dma_map_direct(dev, ops))
 		size = dma_direct_max_mapping_size(dev);
 	else if (ops && ops->max_mapping_size)
 		size = ops->max_mapping_size(dev);
@@ -401,7 +595,7 @@ bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
-	if (dma_is_direct(ops))
+	if (dma_map_direct(dev, ops))
 		return dma_direct_need_sync(dev, dma_addr);
 	return ops->sync_single_for_cpu || ops->sync_single_for_device;
 }