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

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

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

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

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

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

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

arch/powerpc/include/asm/device.h

@@ -18,11 +18,6 @@ struct iommu_table;
  * drivers/macintosh/macio_asic.c
  */
 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

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);
 }
@@ -79,20 +53,15 @@ 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);
 }
 
 
 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);
 }
@@ -101,20 +70,18 @@ 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)
 {
 	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,
 };

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

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

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

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.

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

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",

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

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

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