Merge branch 'topic/dma' into next

Merge hch's big DMA rework series. This is in a topic branch in case he
wants to merge it to minimise conflicts.

arch/powerpc/Kconfig

@@ -119,9 +119,6 @@ config GENERIC_HWEIGHT
 	bool
 	default y
 
-config ARCH_HAS_DMA_SET_COHERENT_MASK
-        bool
-
 config PPC
 	bool
 	default y
@@ -130,7 +127,6 @@ config PPC
 	#
 	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
-	select ARCH_HAS_DMA_SET_COHERENT_MASK
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
@@ -887,6 +883,7 @@ config FSL_SOC
 
 config FSL_PCI
  	bool
+	select ARCH_HAS_DMA_SET_MASK
 	select PPC_INDIRECT_PCI
 	select PCI_QUIRKS
 

arch/powerpc/include/asm/device.h

@@ -19,6 +19,11 @@ 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
@@ -33,9 +38,6 @@ struct dev_archdata {
 #ifdef CONFIG_IOMMU_API
 	void			*iommu_domain;
 #endif
-#ifdef CONFIG_SWIOTLB
-	dma_addr_t		max_direct_dma_addr;
-#endif
 #ifdef CONFIG_PPC64
 	struct pci_dn		*pci_data;
 #endif
@@ -54,6 +56,4 @@ struct pdev_archdata {
 	u64 dma_mask;
 };
 
-#define ARCH_HAS_DMA_GET_REQUIRED_MASK
-
 #endif /* _ASM_POWERPC_DEVICE_H */

arch/powerpc/include/asm/dma-direct.h

@@ -4,26 +4,24 @@
 
 static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
 {
-#ifdef CONFIG_SWIOTLB
-	struct dev_archdata *sd = &dev->archdata;
-
-	if (sd->max_direct_dma_addr && addr + size > sd->max_direct_dma_addr)
-		return false;
-#endif
-
 	if (!dev->dma_mask)
 		return false;
 
-	return addr + size - 1 <= *dev->dma_mask;
+	return addr + size - 1 <=
+		min_not_zero(*dev->dma_mask, dev->bus_dma_mask);
 }
 
 static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
-	return paddr + get_dma_offset(dev);
+	if (!dev)
+		return paddr + PCI_DRAM_OFFSET;
+	return paddr + dev->archdata.dma_offset;
 }
 
 static inline phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
 {
-	return daddr - get_dma_offset(dev);
+	if (!dev)
+		return daddr - PCI_DRAM_OFFSET;
+	return daddr - dev->archdata.dma_offset;
 }
 #endif /* ASM_POWERPC_DMA_DIRECT_H */

arch/powerpc/include/asm/dma-mapping.h

 /* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (C) 2004 IBM
- *
- * Implements the generic device dma API for powerpc.
- * the pci and vio busses
  */
 #ifndef _ASM_DMA_MAPPING_H
 #define _ASM_DMA_MAPPING_H
-#ifdef __KERNEL__
-
-#include <linux/types.h>
-#include <linux/cache.h>
-/* need struct page definitions */
-#include <linux/mm.h>
-#include <linux/scatterlist.h>
-#include <linux/dma-debug.h>
-#include <asm/io.h>
-#include <asm/swiotlb.h>
-
-/* Some dma direct funcs must be visible for use in other dma_ops */
-extern void *__dma_nommu_alloc_coherent(struct device *dev, size_t size,
-					 dma_addr_t *dma_handle, gfp_t flag,
-					 unsigned long attrs);
-extern void __dma_nommu_free_coherent(struct device *dev, size_t size,
-				       void *vaddr, dma_addr_t dma_handle,
-				       unsigned long attrs);
-extern int dma_nommu_mmap_coherent(struct device *dev,
-				    struct vm_area_struct *vma,
-				    void *cpu_addr, dma_addr_t handle,
-				    size_t size, unsigned long attrs);
-
-#ifdef CONFIG_NOT_COHERENT_CACHE
-/*
- * DMA-consistent mapping functions for PowerPCs that don't support
- * cache snooping.  These allocate/free a region of uncached mapped
- * memory space for use with DMA devices.  Alternatively, you could
- * allocate the space "normally" and use the cache management functions
- * to ensure it is consistent.
- */
-struct device;
-extern void __dma_sync(void *vaddr, size_t size, int direction);
-extern void __dma_sync_page(struct page *page, unsigned long offset,
-				 size_t size, int direction);
-extern unsigned long __dma_get_coherent_pfn(unsigned long cpu_addr);
-
-#else /* ! CONFIG_NOT_COHERENT_CACHE */
-/*
- * Cache coherent cores.
- */
-
-#define __dma_sync(addr, size, rw)		((void)0)
-#define __dma_sync_page(pg, off, sz, rw)	((void)0)
-
-#endif /* ! CONFIG_NOT_COHERENT_CACHE */
-
-static inline unsigned long device_to_mask(struct device *dev)
-{
-	if (dev->dma_mask && *dev->dma_mask)
-		return *dev->dma_mask;
-	/* Assume devices without mask can take 32 bit addresses */
-	return 0xfffffffful;
-}
-
-/*
- * Available generic sets of operations
- */
-#ifdef CONFIG_PPC64
-extern struct dma_map_ops dma_iommu_ops;
-#endif
-extern const struct dma_map_ops dma_nommu_ops;
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
@@ -80,31 +15,4 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 	return NULL;
 }
 
-/*
- * get_dma_offset()
- *
- * Get the dma offset on configurations where the dma address can be determined
- * from the physical address by looking at a simple offset.  Direct dma and
- * swiotlb use this function, but it is typically not used by implementations
- * with an iommu.
- */
-static inline dma_addr_t get_dma_offset(struct device *dev)
-{
-	if (dev)
-		return dev->archdata.dma_offset;
-
-	return PCI_DRAM_OFFSET;
-}
-
-static inline void set_dma_offset(struct device *dev, dma_addr_t off)
-{
-	if (dev)
-		dev->archdata.dma_offset = off;
-}
-
-#define HAVE_ARCH_DMA_SET_MASK 1
-
-extern u64 __dma_get_required_mask(struct device *dev);
-
-#endif /* __KERNEL__ */
 #endif	/* _ASM_DMA_MAPPING_H */

arch/powerpc/include/asm/iommu.h

@@ -237,6 +237,7 @@ static inline void iommu_del_device(struct device *dev)
 }
 #endif /* !CONFIG_IOMMU_API */
 
+u64 dma_iommu_get_required_mask(struct device *dev);
 #else
 
 static inline void *get_iommu_table_base(struct device *dev)
@@ -318,5 +319,21 @@ extern void iommu_release_ownership(struct iommu_table *tbl);
 extern enum dma_data_direction iommu_tce_direction(unsigned long tce);
 extern unsigned long iommu_direction_to_tce_perm(enum dma_data_direction dir);
 
+#ifdef CONFIG_PPC_CELL_NATIVE
+extern bool iommu_fixed_is_weak;
+#else
+#define iommu_fixed_is_weak false
+#endif
+
+extern const struct dma_map_ops dma_iommu_ops;
+
+static inline unsigned long device_to_mask(struct device *dev)
+{
+	if (dev->dma_mask && *dev->dma_mask)
+		return *dev->dma_mask;
+	/* Assume devices without mask can take 32 bit addresses */
+	return 0xfffffffful;
+}
+
 #endif /* __KERNEL__ */
 #endif /* _ASM_IOMMU_H */

arch/powerpc/include/asm/machdep.h

@@ -47,9 +47,7 @@ struct machdep_calls {
 #endif
 #endif /* CONFIG_PPC64 */
 
-	/* Platform set_dma_mask and dma_get_required_mask overrides */
-	int		(*dma_set_mask)(struct device *dev, u64 dma_mask);
-	u64		(*dma_get_required_mask)(struct device *dev);
+	void		(*dma_set_mask)(struct device *dev, u64 dma_mask);
 
 	int		(*probe)(void);
 	void		(*setup_arch)(void); /* Optional, may be NULL */

arch/powerpc/include/asm/pci-bridge.h

@@ -19,6 +19,8 @@ struct device_node;
 struct pci_controller_ops {
 	void		(*dma_dev_setup)(struct pci_dev *pdev);
 	void		(*dma_bus_setup)(struct pci_bus *bus);
+	bool		(*iommu_bypass_supported)(struct pci_dev *pdev,
+				u64 mask);
 
 	int		(*probe_mode)(struct pci_bus *bus);
 
@@ -43,9 +45,6 @@ struct pci_controller_ops {
 	void		(*teardown_msi_irqs)(struct pci_dev *pdev);
 #endif
 
-	int             (*dma_set_mask)(struct pci_dev *pdev, u64 dma_mask);
-	u64		(*dma_get_required_mask)(struct pci_dev *pdev);
-
 	void		(*shutdown)(struct pci_controller *hose);
 };
 

arch/powerpc/include/asm/pci.h

@@ -52,10 +52,8 @@ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 
 #ifdef CONFIG_PCI
 extern void set_pci_dma_ops(const struct dma_map_ops *dma_ops);
-extern const struct dma_map_ops *get_pci_dma_ops(void);
 #else	/* CONFIG_PCI */
 #define set_pci_dma_ops(d)
-#define get_pci_dma_ops()	NULL
 #endif
 
 #ifdef CONFIG_PPC64

arch/powerpc/include/asm/pgtable.h

@@ -66,7 +66,6 @@ extern unsigned long empty_zero_page[];
 
 extern pgd_t swapper_pg_dir[];
 
-int dma_pfn_limit_to_zone(u64 pfn_limit);
 extern void paging_init(void);
 
 /*

arch/powerpc/include/asm/swiotlb.h

@@ -13,12 +13,7 @@
 
 #include <linux/swiotlb.h>
 
-extern const struct dma_map_ops powerpc_swiotlb_dma_ops;
-
 extern unsigned int ppc_swiotlb_enable;
-int __init swiotlb_setup_bus_notifier(void);
-
-extern void pci_dma_dev_setup_swiotlb(struct pci_dev *pdev);
 
 #ifdef CONFIG_SWIOTLB
 void swiotlb_detect_4g(void);

arch/powerpc/kernel/Makefile

@@ -36,7 +36,7 @@ obj-y				:= cputable.o ptrace.o syscalls.o \
 				   process.o systbl.o idle.o \
 				   signal.o sysfs.o cacheinfo.o time.o \
 				   prom.o traps.o setup-common.o \
-				   udbg.o misc.o io.o dma.o misc_$(BITS).o \
+				   udbg.o misc.o io.o misc_$(BITS).o \
 				   of_platform.o prom_parse.o
 obj-$(CONFIG_PPC64)		+= setup_64.o sys_ppc32.o \
 				   signal_64.o ptrace32.o \
@@ -105,6 +105,7 @@ obj-$(CONFIG_UPROBES)		+= uprobes.o
 obj-$(CONFIG_PPC_UDBG_16550)	+= legacy_serial.o udbg_16550.o
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 obj-$(CONFIG_SWIOTLB)		+= dma-swiotlb.o
+obj-$(CONFIG_ARCH_HAS_DMA_SET_MASK) += dma-mask.o
 
 pci64-$(CONFIG_PPC64)		+= pci_dn.o pci-hotplug.o isa-bridge.o
 obj-$(CONFIG_PCI)		+= pci_$(BITS).o $(pci64-y) \

arch/powerpc/kernel/dma-iommu.c

@@ -6,12 +6,31 @@
  * busses using the iommu infrastructure
  */
 
+#include <linux/dma-direct.h>
+#include <linux/pci.h>
 #include <asm/iommu.h>
 
 /*
  * 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.
@@ -20,6 +39,8 @@ 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));
@@ -29,7 +50,11 @@ static void dma_iommu_free_coherent(struct device *dev, size_t size,
 				    void *vaddr, dma_addr_t dma_handle,
 				    unsigned long attrs)
 {
-	iommu_free_coherent(get_iommu_table_base(dev), size, vaddr, dma_handle);
+	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);
 }
 
 /* Creates TCEs for a user provided buffer.  The user buffer must be
@@ -42,6 +67,9 @@ 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, device_to_mask(dev), direction, attrs);
 }
@@ -51,8 +79,9 @@ 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)
 {
-	iommu_unmap_page(get_iommu_table_base(dev), dma_handle, size, direction,
-			 attrs);
+	if (!dma_iommu_map_bypass(dev, attrs))
+		iommu_unmap_page(get_iommu_table_base(dev), dma_handle, size,
+				direction,  attrs);
 }
 
 
@@ -60,6 +89,8 @@ 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,
 				device_to_mask(dev), direction, attrs);
 }
@@ -68,10 +99,20 @@ static void dma_iommu_unmap_sg(struct device *dev, struct scatterlist *sglist,
 		int nelems, enum dma_data_direction direction,
 		unsigned long attrs)
 {
-	ppc_iommu_unmap_sg(get_iommu_table_base(dev), sglist, nelems,
+	if (!dma_iommu_map_bypass(dev, attrs))
+		ppc_iommu_unmap_sg(get_iommu_table_base(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);
+}
+
 /* We support DMA to/from any memory page via the iommu */
 int dma_iommu_dma_supported(struct device *dev, u64 mask)
 {
@@ -83,32 +124,48 @@ int dma_iommu_dma_supported(struct device *dev, u64 mask)
 		return 0;
 	}
 
+	if (dev_is_pci(dev) && dma_iommu_bypass_supported(dev, mask)) {
+		dev->archdata.iommu_bypass = true;
+		dev_dbg(dev, "iommu: 64-bit OK, using fixed ops\n");
+		return 1;
+	}
+
 	if (tbl->it_offset > (mask >> tbl->it_page_shift)) {
 		dev_info(dev, "Warning: IOMMU offset too big for device mask\n");
 		dev_info(dev, "mask: 0x%08llx, table offset: 0x%08lx\n",
 				mask, tbl->it_offset << tbl->it_page_shift);
 		return 0;
-	} else
-		return 1;
+	}
+
+	dev_dbg(dev, "iommu: not 64-bit, using default ops\n");
+	dev->archdata.iommu_bypass = false;
+	return 1;
 }
 
-static u64 dma_iommu_get_required_mask(struct device *dev)
+u64 dma_iommu_get_required_mask(struct device *dev)
 {
 	struct iommu_table *tbl = get_iommu_table_base(dev);
 	u64 mask;
+
 	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;
 }
 
-struct dma_map_ops dma_iommu_ops = {
+const struct dma_map_ops dma_iommu_ops = {
 	.alloc			= dma_iommu_alloc_coherent,
 	.free			= dma_iommu_free_coherent,
-	.mmap			= dma_nommu_mmap_coherent,
 	.map_sg			= dma_iommu_map_sg,
 	.unmap_sg		= dma_iommu_unmap_sg,
 	.dma_supported		= dma_iommu_dma_supported,

arch/powerpc/kernel/dma-mask.c

+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/dma-mapping.h>
+#include <linux/export.h>
+#include <asm/machdep.h>
+
+void arch_dma_set_mask(struct device *dev, u64 dma_mask)
+{
+	if (ppc_md.dma_set_mask)
+		ppc_md.dma_set_mask(dev, dma_mask);
+}
+EXPORT_SYMBOL(arch_dma_set_mask);

arch/powerpc/kernel/dma-swiotlb.c

@@ -10,101 +10,12 @@
  * option) any later version.
  *
  */
-
-#include <linux/dma-direct.h>
 #include <linux/memblock.h>
-#include <linux/pfn.h>
-#include <linux/of_platform.h>
-#include <linux/platform_device.h>
-#include <linux/pci.h>
-
 #include <asm/machdep.h>
 #include <asm/swiotlb.h>
-#include <asm/dma.h>
 
 unsigned int ppc_swiotlb_enable;
 
-static u64 swiotlb_powerpc_get_required(struct device *dev)
-{
-	u64 end, mask, max_direct_dma_addr = dev->archdata.max_direct_dma_addr;
-
-	end = memblock_end_of_DRAM();
-	if (max_direct_dma_addr && end > max_direct_dma_addr)
-		end = max_direct_dma_addr;
-	end += get_dma_offset(dev);
-
-	mask = 1ULL << (fls64(end) - 1);
-	mask += mask - 1;
-
-	return mask;
-}
-
-/*
- * At the moment, all platforms that use this code only require
- * swiotlb to be used if we're operating on HIGHMEM.  Since
- * we don't ever call anything other than map_sg, unmap_sg,
- * map_page, and unmap_page on highmem, use normal dma_ops
- * for everything else.
- */
-const struct dma_map_ops powerpc_swiotlb_dma_ops = {
-	.alloc = __dma_nommu_alloc_coherent,
-	.free = __dma_nommu_free_coherent,
-	.mmap = dma_nommu_mmap_coherent,
-	.map_sg = dma_direct_map_sg,
-	.unmap_sg = dma_direct_unmap_sg,
-	.dma_supported = swiotlb_dma_supported,
-	.map_page = dma_direct_map_page,
-	.unmap_page = dma_direct_unmap_page,
-	.sync_single_for_cpu = dma_direct_sync_single_for_cpu,
-	.sync_single_for_device = dma_direct_sync_single_for_device,
-	.sync_sg_for_cpu = dma_direct_sync_sg_for_cpu,
-	.sync_sg_for_device = dma_direct_sync_sg_for_device,
-	.get_required_mask = swiotlb_powerpc_get_required,
-};
-
-void pci_dma_dev_setup_swiotlb(struct pci_dev *pdev)
-{
-	struct pci_controller *hose;
-	struct dev_archdata *sd;
-
-	hose = pci_bus_to_host(pdev->bus);
-	sd = &pdev->dev.archdata;
-	sd->max_direct_dma_addr =
-		hose->dma_window_base_cur + hose->dma_window_size;
-}
-
-static int ppc_swiotlb_bus_notify(struct notifier_block *nb,
-				  unsigned long action, void *data)
-{
-	struct device *dev = data;
-	struct dev_archdata *sd;
-
-	/* We are only intereted in device addition */
-	if (action != BUS_NOTIFY_ADD_DEVICE)
-		return 0;
-
-	sd = &dev->archdata;
-	sd->max_direct_dma_addr = 0;
-
-	/* May need to bounce if the device can't address all of DRAM */
-	if ((dma_get_mask(dev) + 1) < memblock_end_of_DRAM())
-		set_dma_ops(dev, &powerpc_swiotlb_dma_ops);
-
-	return NOTIFY_DONE;
-}
-
-static struct notifier_block ppc_swiotlb_plat_bus_notifier = {
-	.notifier_call = ppc_swiotlb_bus_notify,
-	.priority = 0,
-};
-
-int __init swiotlb_setup_bus_notifier(void)
-{
-	bus_register_notifier(&platform_bus_type,
-			      &ppc_swiotlb_plat_bus_notifier);
-	return 0;
-}
-
 void __init swiotlb_detect_4g(void)
 {
 	if ((memblock_end_of_DRAM() - 1) > 0xffffffff)

arch/powerpc/kernel/dma.c

-/*
- * Copyright (C) 2006 Benjamin Herrenschmidt, IBM Corporation
- *
- * Provide default implementations of the DMA mapping callbacks for
- * directly mapped busses.
- */
-
-#include <linux/device.h>
-#include <linux/dma-mapping.h>
-#include <linux/dma-debug.h>
-#include <linux/gfp.h>
-#include <linux/memblock.h>
-#include <linux/export.h>
-#include <linux/pci.h>
-#include <asm/vio.h>
-#include <asm/bug.h>
-#include <asm/machdep.h>
-#include <asm/swiotlb.h>
-#include <asm/iommu.h>
-
-/*
- * Generic direct DMA implementation
- *
- * This implementation supports a per-device offset that can be applied if
- * the address at which memory is visible to devices is not 0. Platform code
- * can set archdata.dma_data to an unsigned long holding the offset. By
- * default the offset is PCI_DRAM_OFFSET.
- */
-
-static u64 __maybe_unused get_pfn_limit(struct device *dev)
-{
-	u64 pfn = (dev->coherent_dma_mask >> PAGE_SHIFT) + 1;
-	struct dev_archdata __maybe_unused *sd = &dev->archdata;
-
-#ifdef CONFIG_SWIOTLB
-	if (sd->max_direct_dma_addr && dev->dma_ops == &powerpc_swiotlb_dma_ops)
-		pfn = min_t(u64, pfn, sd->max_direct_dma_addr >> PAGE_SHIFT);
-#endif
-
-	return pfn;
-}
-
-static int dma_nommu_dma_supported(struct device *dev, u64 mask)
-{
-#ifdef CONFIG_PPC64
-	u64 limit = get_dma_offset(dev) + (memblock_end_of_DRAM() - 1);
-
-	/* Limit fits in the mask, we are good */
-	if (mask >= limit)
-		return 1;
-
-#ifdef CONFIG_FSL_SOC
-	/*
-	 * Freescale gets another chance via ZONE_DMA, however
-	 * that will have to be refined if/when they support iommus
-	 */
-	return 1;
-#endif
-	/* Sorry ... */
-	return 0;
-#else
-	return 1;
-#endif
-}
-
-#ifndef CONFIG_NOT_COHERENT_CACHE
-void *__dma_nommu_alloc_coherent(struct device *dev, size_t size,
-				  dma_addr_t *dma_handle, gfp_t flag,
-				  unsigned long attrs)
-{
-	void *ret;
-	struct page *page;
-	int node = dev_to_node(dev);
-#ifdef CONFIG_FSL_SOC
-	u64 pfn = get_pfn_limit(dev);
-	int zone;
-
-	/*
-	 * This code should be OK on other platforms, but we have drivers that
-	 * don't set coherent_dma_mask. As a workaround we just ifdef it. This
-	 * whole routine needs some serious cleanup.
-	 */
-
-	zone = dma_pfn_limit_to_zone(pfn);
-	if (zone < 0) {
-		dev_err(dev, "%s: No suitable zone for pfn %#llx\n",
-			__func__, pfn);
-		return NULL;
-	}
-
-	switch (zone) {
-#ifdef CONFIG_ZONE_DMA
-	case ZONE_DMA:
-		flag |= GFP_DMA;
-		break;
-#endif
-	};
-#endif /* CONFIG_FSL_SOC */
-
-	page = alloc_pages_node(node, flag, get_order(size));
-	if (page == NULL)
-		return NULL;
-	ret = page_address(page);
-	memset(ret, 0, size);
-	*dma_handle = __pa(ret) + get_dma_offset(dev);
-
-	return ret;
-}
-
-void __dma_nommu_free_coherent(struct device *dev, size_t size,
-				void *vaddr, dma_addr_t dma_handle,
-				unsigned long attrs)
-{
-	free_pages((unsigned long)vaddr, get_order(size));
-}
-#endif /* !CONFIG_NOT_COHERENT_CACHE */
-
-static void *dma_nommu_alloc_coherent(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t flag,
-				       unsigned long attrs)
-{
-	struct iommu_table *iommu;
-
-	/* The coherent mask may be smaller than the real mask, check if
-	 * we can really use the direct ops
-	 */
-	if (dma_nommu_dma_supported(dev, dev->coherent_dma_mask))
-		return __dma_nommu_alloc_coherent(dev, size, dma_handle,
-						   flag, attrs);
-
-	/* Ok we can't ... do we have an iommu ? If not, fail */
-	iommu = get_iommu_table_base(dev);
-	if (!iommu)
-		return NULL;
-
-	/* Try to use the iommu */
-	return iommu_alloc_coherent(dev, iommu, size, dma_handle,
-				    dev->coherent_dma_mask, flag,
-				    dev_to_node(dev));
-}
-
-static void dma_nommu_free_coherent(struct device *dev, size_t size,
-				     void *vaddr, dma_addr_t dma_handle,
-				     unsigned long attrs)
-{
-	struct iommu_table *iommu;
-
-	/* See comments in dma_nommu_alloc_coherent() */
-	if (dma_nommu_dma_supported(dev, dev->coherent_dma_mask))
-		return __dma_nommu_free_coherent(dev, size, vaddr, dma_handle,
-						  attrs);
-	/* Maybe we used an iommu ... */
-	iommu = get_iommu_table_base(dev);
-
-	/* If we hit that we should have never allocated in the first
-	 * place so how come we are freeing ?
-	 */
-	if (WARN_ON(!iommu))
-		return;
-	iommu_free_coherent(iommu, size, vaddr, dma_handle);
-}
-
-int dma_nommu_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
-			     void *cpu_addr, dma_addr_t handle, size_t size,
-			     unsigned long attrs)
-{
-	unsigned long pfn;
-
-#ifdef CONFIG_NOT_COHERENT_CACHE
-	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
-	pfn = __dma_get_coherent_pfn((unsigned long)cpu_addr);
-#else
-	pfn = page_to_pfn(virt_to_page(cpu_addr));
-#endif
-	return remap_pfn_range(vma, vma->vm_start,
-			       pfn + vma->vm_pgoff,
-			       vma->vm_end - vma->vm_start,
-			       vma->vm_page_prot);
-}
-
-static int dma_nommu_map_sg(struct device *dev, struct scatterlist *sgl,
-			     int nents, enum dma_data_direction direction,
-			     unsigned long attrs)
-{
-	struct scatterlist *sg;
-	int i;
-
-	for_each_sg(sgl, sg, nents, i) {
-		sg->dma_address = sg_phys(sg) + get_dma_offset(dev);
-		sg->dma_length = sg->length;
-
-		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
-			continue;
-
-		__dma_sync_page(sg_page(sg), sg->offset, sg->length, direction);
-	}
-
-	return nents;
-}
-
-static void dma_nommu_unmap_sg(struct device *dev, struct scatterlist *sgl,
-				int nents, enum dma_data_direction direction,
-				unsigned long attrs)
-{
-	struct scatterlist *sg;
-	int i;
-
-	for_each_sg(sgl, sg, nents, i)
-		__dma_sync_page(sg_page(sg), sg->offset, sg->length, direction);
-}
-
-static u64 dma_nommu_get_required_mask(struct device *dev)
-{
-	u64 end, mask;
-
-	end = memblock_end_of_DRAM() + get_dma_offset(dev);
-
-	mask = 1ULL << (fls64(end) - 1);
-	mask += mask - 1;
-
-	return mask;
-}
-
-static inline dma_addr_t dma_nommu_map_page(struct device *dev,
-					     struct page *page,
-					     unsigned long offset,
-					     size_t size,
-					     enum dma_data_direction dir,
-					     unsigned long attrs)
-{
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		__dma_sync_page(page, offset, size, dir);
-
-	return page_to_phys(page) + offset + get_dma_offset(dev);
-}
-
-static inline void dma_nommu_unmap_page(struct device *dev,
-					 dma_addr_t dma_address,
-					 size_t size,
-					 enum dma_data_direction direction,
-					 unsigned long attrs)
-{
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		__dma_sync(bus_to_virt(dma_address), size, direction);
-}
-
-#ifdef CONFIG_NOT_COHERENT_CACHE
-static inline void dma_nommu_sync_sg(struct device *dev,
-		struct scatterlist *sgl, int nents,
-		enum dma_data_direction direction)
-{
-	struct scatterlist *sg;
-	int i;
-
-	for_each_sg(sgl, sg, nents, i)
-		__dma_sync_page(sg_page(sg), sg->offset, sg->length, direction);
-}
-
-static inline void dma_nommu_sync_single(struct device *dev,
-					  dma_addr_t dma_handle, size_t size,
-					  enum dma_data_direction direction)
-{
-	__dma_sync(bus_to_virt(dma_handle), size, direction);
-}
-#endif
-
-const struct dma_map_ops dma_nommu_ops = {
-	.alloc				= dma_nommu_alloc_coherent,
-	.free				= dma_nommu_free_coherent,
-	.mmap				= dma_nommu_mmap_coherent,
-	.map_sg				= dma_nommu_map_sg,
-	.unmap_sg			= dma_nommu_unmap_sg,
-	.dma_supported			= dma_nommu_dma_supported,
-	.map_page			= dma_nommu_map_page,
-	.unmap_page			= dma_nommu_unmap_page,
-	.get_required_mask		= dma_nommu_get_required_mask,
-#ifdef CONFIG_NOT_COHERENT_CACHE
-	.sync_single_for_cpu 		= dma_nommu_sync_single,
-	.sync_single_for_device 	= dma_nommu_sync_single,
-	.sync_sg_for_cpu 		= dma_nommu_sync_sg,
-	.sync_sg_for_device 		= dma_nommu_sync_sg,
-#endif
-};
-EXPORT_SYMBOL(dma_nommu_ops);
-
-int dma_set_coherent_mask(struct device *dev, u64 mask)
-{
-	if (!dma_supported(dev, mask)) {
-		/*
-		 * We need to special case the direct DMA ops which can
-		 * support a fallback for coherent allocations. There
-		 * is no dma_op->set_coherent_mask() so we have to do
-		 * things the hard way:
-		 */
-		if (get_dma_ops(dev) != &dma_nommu_ops ||
-		    get_iommu_table_base(dev) == NULL ||
-		    !dma_iommu_dma_supported(dev, mask))
-			return -EIO;
-	}
-	dev->coherent_dma_mask = mask;
-	return 0;
-}
-EXPORT_SYMBOL(dma_set_coherent_mask);
-
-int dma_set_mask(struct device *dev, u64 dma_mask)
-{
-	if (ppc_md.dma_set_mask)
-		return ppc_md.dma_set_mask(dev, dma_mask);
-
-	if (dev_is_pci(dev)) {
-		struct pci_dev *pdev = to_pci_dev(dev);
-		struct pci_controller *phb = pci_bus_to_host(pdev->bus);
-		if (phb->controller_ops.dma_set_mask)
-			return phb->controller_ops.dma_set_mask(pdev, dma_mask);
-	}
-
-	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
-		return -EIO;
-	*dev->dma_mask = dma_mask;
-	return 0;
-}
-EXPORT_SYMBOL(dma_set_mask);
-
-u64 __dma_get_required_mask(struct device *dev)
-{
-	const struct dma_map_ops *dma_ops = get_dma_ops(dev);
-
-	if (unlikely(dma_ops == NULL))
-		return 0;
-
-	if (dma_ops->get_required_mask)
-		return dma_ops->get_required_mask(dev);
-
-	return DMA_BIT_MASK(8 * sizeof(dma_addr_t));
-}
-
-u64 dma_get_required_mask(struct device *dev)
-{
-	if (ppc_md.dma_get_required_mask)
-		return ppc_md.dma_get_required_mask(dev);
-
-	if (dev_is_pci(dev)) {
-		struct pci_dev *pdev = to_pci_dev(dev);
-		struct pci_controller *phb = pci_bus_to_host(pdev->bus);
-		if (phb->controller_ops.dma_get_required_mask)
-			return phb->controller_ops.dma_get_required_mask(pdev);
-	}
-
-	return __dma_get_required_mask(dev);
-}
-EXPORT_SYMBOL_GPL(dma_get_required_mask);
-
-static int __init dma_init(void)
-{
-#ifdef CONFIG_IBMVIO
-	dma_debug_add_bus(&vio_bus_type);
-#endif
-
-       return 0;
-}
-fs_initcall(dma_init);
-

arch/powerpc/kernel/pci-common.c

@@ -62,19 +62,13 @@ resource_size_t isa_mem_base;
 EXPORT_SYMBOL(isa_mem_base);
 
 
-static const struct dma_map_ops *pci_dma_ops = &dma_nommu_ops;
+static const struct dma_map_ops *pci_dma_ops;
 
 void set_pci_dma_ops(const struct dma_map_ops *dma_ops)
 {
 	pci_dma_ops = dma_ops;
 }
 
-const struct dma_map_ops *get_pci_dma_ops(void)
-{
-	return pci_dma_ops;
-}
-EXPORT_SYMBOL(get_pci_dma_ops);
-
 /*
  * This function should run under locking protection, specifically
  * hose_spinlock.
@@ -972,7 +966,7 @@ static void pcibios_setup_device(struct pci_dev *dev)
 
 	/* Hook up default DMA ops */
 	set_dma_ops(&dev->dev, pci_dma_ops);
-	set_dma_offset(&dev->dev, PCI_DRAM_OFFSET);
+	dev->dev.archdata.dma_offset = PCI_DRAM_OFFSET;
 
 	/* Additional platform DMA/iommu setup */
 	phb = pci_bus_to_host(dev->bus);

arch/powerpc/kernel/setup-common.c

@@ -791,7 +791,6 @@ void arch_setup_pdev_archdata(struct platform_device *pdev)
 {
 	pdev->archdata.dma_mask = DMA_BIT_MASK(32);
 	pdev->dev.dma_mask = &pdev->archdata.dma_mask;
- 	set_dma_ops(&pdev->dev, &dma_nommu_ops);
 }
 
 static __init void print_system_info(void)

arch/powerpc/mm/dma-noncoherent.c

@@ -30,6 +30,7 @@
 #include <linux/types.h>
 #include <linux/highmem.h>
 #include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
 #include <linux/export.h>
 
 #include <asm/tlbflush.h>
@@ -151,8 +152,8 @@ static struct ppc_vm_region *ppc_vm_region_find(struct ppc_vm_region *head, unsi
  * Allocate DMA-coherent memory space and return both the kernel remapped
  * virtual and bus address for that space.
  */
-void *__dma_nommu_alloc_coherent(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t gfp, unsigned long attrs)
 {
 	struct page *page;
 	struct ppc_vm_region *c;
@@ -253,7 +254,7 @@ void *__dma_nommu_alloc_coherent(struct device *dev, size_t size,
 /*
  * free a page as defined by the above mapping.
  */
-void __dma_nommu_free_coherent(struct device *dev, size_t size, void *vaddr,
+void arch_dma_free(struct device *dev, size_t size, void *vaddr,
 		dma_addr_t dma_handle, unsigned long attrs)
 {
 	struct ppc_vm_region *c;
@@ -313,7 +314,7 @@ void __dma_nommu_free_coherent(struct device *dev, size_t size, void *vaddr,
 /*
  * make an area consistent.
  */
-void __dma_sync(void *vaddr, size_t size, int direction)
+static void __dma_sync(void *vaddr, size_t size, int direction)
 {
 	unsigned long start = (unsigned long)vaddr;
 	unsigned long end   = start + size;
@@ -339,7 +340,6 @@ void __dma_sync(void *vaddr, size_t size, int direction)
 		break;
 	}
 }
-EXPORT_SYMBOL(__dma_sync);
 
 #ifdef CONFIG_HIGHMEM
 /*
@@ -386,28 +386,42 @@ static inline void __dma_sync_page_highmem(struct page *page,
  * __dma_sync_page makes memory consistent. identical to __dma_sync, but
  * takes a struct page instead of a virtual address
  */
-void __dma_sync_page(struct page *page, unsigned long offset,
-	size_t size, int direction)
+static void __dma_sync_page(phys_addr_t paddr, size_t size, int dir)
 {
+	struct page *page = pfn_to_page(paddr >> PAGE_SHIFT);
+	unsigned offset = paddr & ~PAGE_MASK;
+
 #ifdef CONFIG_HIGHMEM
-	__dma_sync_page_highmem(page, offset, size, direction);
+	__dma_sync_page_highmem(page, offset, size, dir);
 #else
 	unsigned long start = (unsigned long)page_address(page) + offset;
-	__dma_sync((void *)start, size, direction);
+	__dma_sync((void *)start, size, dir);
 #endif
 }
-EXPORT_SYMBOL(__dma_sync_page);
+
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
+{
+	__dma_sync_page(paddr, size, dir);
+}
+
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
+{
+	__dma_sync_page(paddr, size, dir);
+}
 
 /*
- * Return the PFN for a given cpu virtual address returned by
- * __dma_nommu_alloc_coherent. This is used by dma_mmap_coherent()
+ * Return the PFN for a given cpu virtual address returned by arch_dma_alloc.
  */
-unsigned long __dma_get_coherent_pfn(unsigned long cpu_addr)
+long arch_dma_coherent_to_pfn(struct device *dev, void *vaddr,
+		dma_addr_t dma_addr)
 {
 	/* This should always be populated, so we don't test every
 	 * level. If that fails, we'll have a nice crash which
 	 * will be as good as a BUG_ON()
 	 */
+	unsigned long cpu_addr = (unsigned long)vaddr;
 	pgd_t *pgd = pgd_offset_k(cpu_addr);
 	pud_t *pud = pud_offset(pgd, cpu_addr);
 	pmd_t *pmd = pmd_offset(pud, cpu_addr);

arch/powerpc/mm/mem.c

@@ -69,15 +69,12 @@ pte_t *kmap_pte;
 EXPORT_SYMBOL(kmap_pte);
 pgprot_t kmap_prot;
 EXPORT_SYMBOL(kmap_prot);
-#define TOP_ZONE ZONE_HIGHMEM
 
 static inline pte_t *virt_to_kpte(unsigned long vaddr)
 {
 	return pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(vaddr),
 			vaddr), vaddr), vaddr);
 }
-#else
-#define TOP_ZONE ZONE_NORMAL
 #endif
 
 pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
@@ -228,25 +225,6 @@ static int __init mark_nonram_nosave(void)
  */
 static unsigned long max_zone_pfns[MAX_NR_ZONES];
 
-/*
- * Find the least restrictive zone that is entirely below the
- * specified pfn limit.  Returns < 0 if no suitable zone is found.
- *
- * pfn_limit must be u64 because it can exceed 32 bits even on 32-bit
- * systems -- the DMA limit can be higher than any possible real pfn.
- */
-int dma_pfn_limit_to_zone(u64 pfn_limit)
-{
-	int i;
-
-	for (i = TOP_ZONE; i >= 0; i--) {
-		if (max_zone_pfns[i] <= pfn_limit)
-			return i;
-	}
-
-	return -EPERM;
-}
-
 /*
  * paging_init() sets up the page tables - in fact we've already done this.
  */

arch/powerpc/platforms/44x/ppc476.c

@@ -34,6 +34,7 @@
 #include <asm/ppc4xx.h>
 #include <asm/mpic.h>
 #include <asm/mmu.h>
+#include <asm/swiotlb.h>
 
 #include <linux/pci.h>
 #include <linux/i2c.h>

arch/powerpc/platforms/44x/warp.c

@@ -47,7 +47,7 @@ static int __init warp_probe(void)
 	if (!of_machine_is_compatible("pika,warp"))
 		return 0;
 
-	/* For __dma_nommu_alloc_coherent */
+	/* For arch_dma_alloc */
 	ISA_DMA_THRESHOLD = ~0L;
 
 	return 1;

arch/powerpc/platforms/85xx/corenet_generic.c

@@ -27,6 +27,7 @@
 #include <asm/udbg.h>
 #include <asm/mpic.h>
 #include <asm/ehv_pic.h>
+#include <asm/swiotlb.h>
 #include <soc/fsl/qe/qe_ic.h>
 
 #include <linux/of_platform.h>
@@ -223,7 +224,3 @@ define_machine(corenet_generic) {
 };
 
 machine_arch_initcall(corenet_generic, corenet_gen_publish_devices);
-
-#ifdef CONFIG_SWIOTLB
-machine_arch_initcall(corenet_generic, swiotlb_setup_bus_notifier);
-#endif

arch/powerpc/platforms/85xx/ge_imp3a.c

@@ -202,8 +202,6 @@ static int __init ge_imp3a_probe(void)
 
 machine_arch_initcall(ge_imp3a, mpc85xx_common_publish_devices);
 
-machine_arch_initcall(ge_imp3a, swiotlb_setup_bus_notifier);
-
 define_machine(ge_imp3a) {
 	.name			= "GE_IMP3A",
 	.probe			= ge_imp3a_probe,

arch/powerpc/platforms/85xx/mpc8536_ds.c

@@ -57,8 +57,6 @@ static void __init mpc8536_ds_setup_arch(void)
 
 machine_arch_initcall(mpc8536_ds, mpc85xx_common_publish_devices);
 
-machine_arch_initcall(mpc8536_ds, swiotlb_setup_bus_notifier);
-
 /*
  * Called very early, device-tree isn't unflattened
  */

arch/powerpc/platforms/85xx/mpc85xx_ds.c

@@ -174,10 +174,6 @@ machine_arch_initcall(mpc8544_ds, mpc85xx_common_publish_devices);
 machine_arch_initcall(mpc8572_ds, mpc85xx_common_publish_devices);
 machine_arch_initcall(p2020_ds, mpc85xx_common_publish_devices);
 
-machine_arch_initcall(mpc8544_ds, swiotlb_setup_bus_notifier);
-machine_arch_initcall(mpc8572_ds, swiotlb_setup_bus_notifier);
-machine_arch_initcall(p2020_ds, swiotlb_setup_bus_notifier);
-
 /*
  * Called very early, device-tree isn't unflattened
  */

arch/powerpc/platforms/85xx/mpc85xx_mds.c

@@ -367,10 +367,6 @@ machine_arch_initcall(mpc8568_mds, mpc85xx_publish_devices);
 machine_arch_initcall(mpc8569_mds, mpc85xx_publish_devices);
 machine_arch_initcall(p1021_mds, mpc85xx_common_publish_devices);
 
-machine_arch_initcall(mpc8568_mds, swiotlb_setup_bus_notifier);
-machine_arch_initcall(mpc8569_mds, swiotlb_setup_bus_notifier);
-machine_arch_initcall(p1021_mds, swiotlb_setup_bus_notifier);
-
 static void __init mpc85xx_mds_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |

arch/powerpc/platforms/85xx/p1010rdb.c

@@ -55,7 +55,6 @@ static void __init p1010_rdb_setup_arch(void)
 }
 
 machine_arch_initcall(p1010_rdb, mpc85xx_common_publish_devices);
-machine_arch_initcall(p1010_rdb, swiotlb_setup_bus_notifier);
 
 /*
  * Called very early, device-tree isn't unflattened

arch/powerpc/platforms/85xx/p1022_ds.c

@@ -548,8 +548,6 @@ static void __init p1022_ds_setup_arch(void)
 
 machine_arch_initcall(p1022_ds, mpc85xx_common_publish_devices);
 
-machine_arch_initcall(p1022_ds, swiotlb_setup_bus_notifier);
-
 /*
  * Called very early, device-tree isn't unflattened
  */

arch/powerpc/platforms/85xx/p1022_rdk.c

@@ -128,8 +128,6 @@ static void __init p1022_rdk_setup_arch(void)
 
 machine_arch_initcall(p1022_rdk, mpc85xx_common_publish_devices);
 
-machine_arch_initcall(p1022_rdk, swiotlb_setup_bus_notifier);
-
 /*
  * Called very early, device-tree isn't unflattened
  */

arch/powerpc/platforms/85xx/qemu_e500.c

@@ -22,6 +22,7 @@
 #include <asm/time.h>
 #include <asm/udbg.h>
 #include <asm/mpic.h>
+#include <asm/swiotlb.h>
 #include <sysdev/fsl_soc.h>
 #include <sysdev/fsl_pci.h>
 #include "smp.h"

arch/powerpc/platforms/86xx/mpc86xx_hpcn.c

@@ -121,7 +121,6 @@ static int __init declare_of_platform_devices(void)
 	return 0;
 }
 machine_arch_initcall(mpc86xx_hpcn, declare_of_platform_devices);
-machine_arch_initcall(mpc86xx_hpcn, swiotlb_setup_bus_notifier);
 
 define_machine(mpc86xx_hpcn) {
 	.name			= "MPC86xx HPCN",

arch/powerpc/platforms/Kconfig.cputype

@@ -408,6 +408,9 @@ config NOT_COHERENT_CACHE
 	bool
 	depends on 4xx || PPC_8xx || E200 || PPC_MPC512x || \
 		GAMECUBE_COMMON || AMIGAONE
+	select ARCH_HAS_DMA_COHERENT_TO_PFN
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	default n if PPC_47x
 	default y
 

arch/powerpc/platforms/cell/iommu.c

@@ -544,9 +544,10 @@ static struct cbe_iommu *cell_iommu_for_node(int nid)
 static unsigned long cell_dma_nommu_offset;
 
 static unsigned long dma_iommu_fixed_base;
+static bool cell_iommu_enabled;
 
 /* iommu_fixed_is_weak is set if booted with iommu_fixed=weak */
-static int iommu_fixed_is_weak;
+bool iommu_fixed_is_weak;
 
 static struct iommu_table *cell_get_iommu_table(struct device *dev)
 {
@@ -568,102 +569,19 @@ static struct iommu_table *cell_get_iommu_table(struct device *dev)
 	return &window->table;
 }
 
-/* A coherent allocation implies strong ordering */
-
-static void *dma_fixed_alloc_coherent(struct device *dev, size_t size,
-				      dma_addr_t *dma_handle, gfp_t flag,
-				      unsigned long attrs)
-{
-	if (iommu_fixed_is_weak)
-		return iommu_alloc_coherent(dev, cell_get_iommu_table(dev),
-					    size, dma_handle,
-					    device_to_mask(dev), flag,
-					    dev_to_node(dev));
-	else
-		return dma_nommu_ops.alloc(dev, size, dma_handle, flag,
-					    attrs);
-}
-
-static void dma_fixed_free_coherent(struct device *dev, size_t size,
-				    void *vaddr, dma_addr_t dma_handle,
-				    unsigned long attrs)
-{
-	if (iommu_fixed_is_weak)
-		iommu_free_coherent(cell_get_iommu_table(dev), size, vaddr,
-				    dma_handle);
-	else
-		dma_nommu_ops.free(dev, size, vaddr, dma_handle, attrs);
-}
-
-static dma_addr_t dma_fixed_map_page(struct device *dev, struct page *page,
-				     unsigned long offset, size_t size,
-				     enum dma_data_direction direction,
-				     unsigned long attrs)
-{
-	if (iommu_fixed_is_weak == (attrs & DMA_ATTR_WEAK_ORDERING))
-		return dma_nommu_ops.map_page(dev, page, offset, size,
-					       direction, attrs);
-	else
-		return iommu_map_page(dev, cell_get_iommu_table(dev), page,
-				      offset, size, device_to_mask(dev),
-				      direction, attrs);
-}
-
-static void dma_fixed_unmap_page(struct device *dev, dma_addr_t dma_addr,
-				 size_t size, enum dma_data_direction direction,
-				 unsigned long attrs)
-{
-	if (iommu_fixed_is_weak == (attrs & DMA_ATTR_WEAK_ORDERING))
-		dma_nommu_ops.unmap_page(dev, dma_addr, size, direction,
-					  attrs);
-	else
-		iommu_unmap_page(cell_get_iommu_table(dev), dma_addr, size,
-				 direction, attrs);
-}
-
-static int dma_fixed_map_sg(struct device *dev, struct scatterlist *sg,
-			   int nents, enum dma_data_direction direction,
-			   unsigned long attrs)
-{
-	if (iommu_fixed_is_weak == (attrs & DMA_ATTR_WEAK_ORDERING))
-		return dma_nommu_ops.map_sg(dev, sg, nents, direction, attrs);
-	else
-		return ppc_iommu_map_sg(dev, cell_get_iommu_table(dev), sg,
-					nents, device_to_mask(dev),
-					direction, attrs);
-}
-
-static void dma_fixed_unmap_sg(struct device *dev, struct scatterlist *sg,
-			       int nents, enum dma_data_direction direction,
-			       unsigned long attrs)
-{
-	if (iommu_fixed_is_weak == (attrs & DMA_ATTR_WEAK_ORDERING))
-		dma_nommu_ops.unmap_sg(dev, sg, nents, direction, attrs);
-	else
-		ppc_iommu_unmap_sg(cell_get_iommu_table(dev), sg, nents,
-				   direction, attrs);
-}
-
-static int dma_suported_and_switch(struct device *dev, u64 dma_mask);
-
-static const struct dma_map_ops dma_iommu_fixed_ops = {
-	.alloc          = dma_fixed_alloc_coherent,
-	.free           = dma_fixed_free_coherent,
-	.map_sg         = dma_fixed_map_sg,
-	.unmap_sg       = dma_fixed_unmap_sg,
-	.dma_supported  = dma_suported_and_switch,
-	.map_page       = dma_fixed_map_page,
-	.unmap_page     = dma_fixed_unmap_page,
-};
+static u64 cell_iommu_get_fixed_address(struct device *dev);
 
 static void cell_dma_dev_setup(struct device *dev)
 {
-	if (get_pci_dma_ops() == &dma_iommu_ops)
+	if (cell_iommu_enabled) {
+		u64 addr = cell_iommu_get_fixed_address(dev);
+
+		if (addr != OF_BAD_ADDR)
+			dev->archdata.dma_offset = addr + dma_iommu_fixed_base;
 		set_iommu_table_base(dev, cell_get_iommu_table(dev));
-	else if (get_pci_dma_ops() == &dma_nommu_ops)
-		set_dma_offset(dev, cell_dma_nommu_offset);
-	else
-		BUG();
+	} else {
+		dev->archdata.dma_offset = cell_dma_nommu_offset;
+	}
 }
 
 static void cell_pci_dma_dev_setup(struct pci_dev *dev)
@@ -680,11 +598,9 @@ static int cell_of_bus_notify(struct notifier_block *nb, unsigned long action,
 	if (action != BUS_NOTIFY_ADD_DEVICE)
 		return 0;
 
-	/* We use the PCI DMA ops */
-	dev->dma_ops = get_pci_dma_ops();
-
+	if (cell_iommu_enabled)
+		dev->dma_ops = &dma_iommu_ops;
 	cell_dma_dev_setup(dev);
-
 	return 0;
 }
 
@@ -809,7 +725,6 @@ static int __init cell_iommu_init_disabled(void)
 	unsigned long base = 0, size;
 
 	/* When no iommu is present, we use direct DMA ops */
-	set_pci_dma_ops(&dma_nommu_ops);
 
 	/* First make sure all IOC translation is turned off */
 	cell_disable_iommus();
@@ -894,7 +809,11 @@ static u64 cell_iommu_get_fixed_address(struct device *dev)
 	const u32 *ranges = NULL;
 	int i, len, best, naddr, nsize, pna, range_size;
 
+	/* We can be called for platform devices that have no of_node */
 	np = of_node_get(dev->of_node);
+	if (!np)
+		goto out;
+
 	while (1) {
 		naddr = of_n_addr_cells(np);
 		nsize = of_n_size_cells(np);
@@ -945,27 +864,10 @@ static u64 cell_iommu_get_fixed_address(struct device *dev)
 	return dev_addr;
 }
 
-static int dma_suported_and_switch(struct device *dev, u64 dma_mask)
+static bool cell_pci_iommu_bypass_supported(struct pci_dev *pdev, u64 mask)
 {
-	if (dma_mask == DMA_BIT_MASK(64) &&
-	    cell_iommu_get_fixed_address(dev) != OF_BAD_ADDR) {
-		u64 addr = cell_iommu_get_fixed_address(dev) +
-			dma_iommu_fixed_base;
-		dev_dbg(dev, "iommu: 64-bit OK, using fixed ops\n");
-		dev_dbg(dev, "iommu: fixed addr = %llx\n", addr);
-		set_dma_ops(dev, &dma_iommu_fixed_ops);
-		set_dma_offset(dev, addr);
-		return 1;
-	}
-
-	if (dma_iommu_dma_supported(dev, dma_mask)) {
-		dev_dbg(dev, "iommu: not 64-bit, using default ops\n");
-		set_dma_ops(dev, get_pci_dma_ops());
-		cell_dma_dev_setup(dev);
-		return 1;
-	}
-
-	return 0;
+	return mask == DMA_BIT_MASK(64) &&
+		cell_iommu_get_fixed_address(&pdev->dev) != OF_BAD_ADDR;
 }
 
 static void insert_16M_pte(unsigned long addr, unsigned long *ptab,
@@ -1119,9 +1021,8 @@ static int __init cell_iommu_fixed_mapping_init(void)
 		cell_iommu_setup_window(iommu, np, dbase, dsize, 0);
 	}
 
-	dma_iommu_ops.dma_supported = dma_suported_and_switch;
-	set_pci_dma_ops(&dma_iommu_ops);
-
+	cell_pci_controller_ops.iommu_bypass_supported =
+		cell_pci_iommu_bypass_supported;
 	return 0;
 }
 
@@ -1142,7 +1043,7 @@ static int __init setup_iommu_fixed(char *str)
 	pciep = of_find_node_by_type(NULL, "pcie-endpoint");
 
 	if (strcmp(str, "weak") == 0 || (pciep && strcmp(str, "strong") != 0))
-		iommu_fixed_is_weak = DMA_ATTR_WEAK_ORDERING;
+		iommu_fixed_is_weak = true;
 
 	of_node_put(pciep);
 
@@ -1150,26 +1051,6 @@ static int __init setup_iommu_fixed(char *str)
 }
 __setup("iommu_fixed=", setup_iommu_fixed);
 
-static u64 cell_dma_get_required_mask(struct device *dev)
-{
-	const struct dma_map_ops *dma_ops;
-
-	if (!dev->dma_mask)
-		return 0;
-
-	if (!iommu_fixed_disabled &&
-			cell_iommu_get_fixed_address(dev) != OF_BAD_ADDR)
-		return DMA_BIT_MASK(64);
-
-	dma_ops = get_dma_ops(dev);
-	if (dma_ops->get_required_mask)
-		return dma_ops->get_required_mask(dev);
-
-	WARN_ONCE(1, "no get_required_mask in %p ops", dma_ops);
-
-	return DMA_BIT_MASK(64);
-}
-
 static int __init cell_iommu_init(void)
 {
 	struct device_node *np;
@@ -1186,10 +1067,9 @@ static int __init cell_iommu_init(void)
 
 	/* Setup various callbacks */
 	cell_pci_controller_ops.dma_dev_setup = cell_pci_dma_dev_setup;
-	ppc_md.dma_get_required_mask = cell_dma_get_required_mask;
 
 	if (!iommu_fixed_disabled && cell_iommu_fixed_mapping_init() == 0)
-		goto bail;
+		goto done;
 
 	/* Create an iommu for each /axon node.  */
 	for_each_node_by_name(np, "axon") {
@@ -1206,10 +1086,10 @@ static int __init cell_iommu_init(void)
 			continue;
 		cell_iommu_init_one(np, SPIDER_DMA_OFFSET);
 	}
-
+ done:
 	/* Setup default PCI iommu ops */
 	set_pci_dma_ops(&dma_iommu_ops);
-
+	cell_iommu_enabled = true;
  bail:
 	/* Register callbacks on OF platform device addition/removal
 	 * to handle linking them to the right DMA operations

arch/powerpc/platforms/pasemi/iommu.c

@@ -186,7 +186,7 @@ static void pci_dma_dev_setup_pasemi(struct pci_dev *dev)
 	 */
 	if (dev->vendor == 0x1959 && dev->device == 0xa007 &&
 	    !firmware_has_feature(FW_FEATURE_LPAR)) {
-		dev->dev.dma_ops = &dma_nommu_ops;
+		dev->dev.dma_ops = NULL;
 		/*
 		 * Set the coherent DMA mask to prevent the iommu
 		 * being used unnecessarily

arch/powerpc/platforms/pasemi/setup.c

@@ -411,55 +411,6 @@ static int pas_machine_check_handler(struct pt_regs *regs)
 	return !!(srr1 & 0x2);
 }
 
-#ifdef CONFIG_PCMCIA
-static int pcmcia_notify(struct notifier_block *nb, unsigned long action,
-			 void *data)
-{
-	struct device *dev = data;
-	struct device *parent;
-	struct pcmcia_device *pdev = to_pcmcia_dev(dev);
-
-	/* We are only intereted in device addition */
-	if (action != BUS_NOTIFY_ADD_DEVICE)
-		return 0;
-
-	parent = pdev->socket->dev.parent;
-
-	/* We know electra_cf devices will always have of_node set, since
-	 * electra_cf is an of_platform driver.
-	 */
-	if (!parent->of_node)
-		return 0;
-
-	if (!of_device_is_compatible(parent->of_node, "electra-cf"))
-		return 0;
-
-	/* We use the direct ops for localbus */
-	dev->dma_ops = &dma_nommu_ops;
-
-	return 0;
-}
-
-static struct notifier_block pcmcia_notifier = {
-	.notifier_call = pcmcia_notify,
-};
-
-static inline void pasemi_pcmcia_init(void)
-{
-	extern struct bus_type pcmcia_bus_type;
-
-	bus_register_notifier(&pcmcia_bus_type, &pcmcia_notifier);
-}
-
-#else
-
-static inline void pasemi_pcmcia_init(void)
-{
-}
-
-#endif
-
-
 static const struct of_device_id pasemi_bus_ids[] = {
 	/* Unfortunately needed for legacy firmwares */
 	{ .type = "localbus", },
@@ -472,8 +423,6 @@ static const struct of_device_id pasemi_bus_ids[] = {
 
 static int __init pasemi_publish_devices(void)
 {
-	pasemi_pcmcia_init();
-
 	/* Publish OF platform devices for SDC and other non-PCI devices */
 	of_platform_bus_probe(NULL, pasemi_bus_ids, NULL);
 

arch/powerpc/platforms/powernv/npu-dma.c

@@ -216,7 +216,7 @@ static void pnv_npu_dma_set_32(struct pnv_ioda_pe *npe)
 	 * their parent device so drivers shouldn't be doing DMA
 	 * operations directly on these devices.
 	 */
-	set_dma_ops(&npe->pdev->dev, NULL);
+	set_dma_ops(&npe->pdev->dev, &dma_dummy_ops);
 }
 
 /*

arch/powerpc/platforms/powernv/pci-ioda.c

@@ -1746,7 +1746,7 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev
 
 	pe = &phb->ioda.pe_array[pdn->pe_number];
 	WARN_ON(get_dma_ops(&pdev->dev) != &dma_iommu_ops);
-	set_dma_offset(&pdev->dev, pe->tce_bypass_base);
+	pdev->dev.archdata.dma_offset = pe->tce_bypass_base;
 	set_iommu_table_base(&pdev->dev, pe->table_group.tables[0]);
 	/*
 	 * Note: iommu_add_device() will fail here as
@@ -1756,31 +1756,6 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev
 	 */
 }
 
-static bool pnv_pci_ioda_pe_single_vendor(struct pnv_ioda_pe *pe)
-{
-	unsigned short vendor = 0;
-	struct pci_dev *pdev;
-
-	if (pe->device_count == 1)
-		return true;
-
-	/* pe->pdev should be set if it's a single device, pe->pbus if not */
-	if (!pe->pbus)
-		return true;
-
-	list_for_each_entry(pdev, &pe->pbus->devices, bus_list) {
-		if (!vendor) {
-			vendor = pdev->vendor;
-			continue;
-		}
-
-		if (pdev->vendor != vendor)
-			return false;
-	}
-
-	return true;
-}
-
 /*
  * Reconfigure TVE#0 to be usable as 64-bit DMA space.
  *
@@ -1850,88 +1825,45 @@ static int pnv_pci_ioda_dma_64bit_bypass(struct pnv_ioda_pe *pe)
 	return -EIO;
 }
 
-static int pnv_pci_ioda_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
+static bool pnv_pci_ioda_iommu_bypass_supported(struct pci_dev *pdev,
+		u64 dma_mask)
 {
 	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
 	struct pnv_phb *phb = hose->private_data;
 	struct pci_dn *pdn = pci_get_pdn(pdev);
 	struct pnv_ioda_pe *pe;
-	uint64_t top;
-	bool bypass = false;
-	s64 rc;
 
 	if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE))
 		return -ENODEV;
 
 	pe = &phb->ioda.pe_array[pdn->pe_number];
 	if (pe->tce_bypass_enabled) {
-		top = pe->tce_bypass_base + memblock_end_of_DRAM() - 1;
-		bypass = (dma_mask >= top);
+		u64 top = pe->tce_bypass_base + memblock_end_of_DRAM() - 1;
+		if (dma_mask >= top)
+			return true;
 	}
 
-	if (bypass) {
-		dev_info(&pdev->dev, "Using 64-bit DMA iommu bypass\n");
-		set_dma_ops(&pdev->dev, &dma_nommu_ops);
-	} else {
-		/*
-		 * If the device can't set the TCE bypass bit but still wants
-		 * to access 4GB or more, on PHB3 we can reconfigure TVE#0 to
-		 * bypass the 32-bit region and be usable for 64-bit DMAs.
-		 * The device needs to be able to address all of this space.
-		 */
-		if (dma_mask >> 32 &&
-		    dma_mask > (memory_hotplug_max() + (1ULL << 32)) &&
-		    pnv_pci_ioda_pe_single_vendor(pe) &&
-		    phb->model == PNV_PHB_MODEL_PHB3) {
-			/* Configure the bypass mode */
-			rc = pnv_pci_ioda_dma_64bit_bypass(pe);
-			if (rc)
-				return rc;
-			/* 4GB offset bypasses 32-bit space */
-			set_dma_offset(&pdev->dev, (1ULL << 32));
-			set_dma_ops(&pdev->dev, &dma_nommu_ops);
-		} else if (dma_mask >> 32 && dma_mask != DMA_BIT_MASK(64)) {
-			/*
-			 * Fail the request if a DMA mask between 32 and 64 bits
-			 * was requested but couldn't be fulfilled. Ideally we
-			 * would do this for 64-bits but historically we have
-			 * always fallen back to 32-bits.
-			 */
-			return -ENOMEM;
-		} else {
-			dev_info(&pdev->dev, "Using 32-bit DMA via iommu\n");
-			set_dma_ops(&pdev->dev, &dma_iommu_ops);
-		}
+	/*
+	 * If the device can't set the TCE bypass bit but still wants
+	 * to access 4GB or more, on PHB3 we can reconfigure TVE#0 to
+	 * bypass the 32-bit region and be usable for 64-bit DMAs.
+	 * The device needs to be able to address all of this space.
+	 */
+	if (dma_mask >> 32 &&
+	    dma_mask > (memory_hotplug_max() + (1ULL << 32)) &&
+	    /* pe->pdev should be set if it's a single device, pe->pbus if not */
+	    (pe->device_count == 1 || !pe->pbus) &&
+	    phb->model == PNV_PHB_MODEL_PHB3) {
+		/* Configure the bypass mode */
+		s64 rc = pnv_pci_ioda_dma_64bit_bypass(pe);
+		if (rc)
+			return rc;
+		/* 4GB offset bypasses 32-bit space */
+		pdev->dev.archdata.dma_offset = (1ULL << 32);
+		return true;
 	}
-	*pdev->dev.dma_mask = dma_mask;
-
-	/* Update peer npu devices */
-	pnv_npu_try_dma_set_bypass(pdev, bypass);
-
-	return 0;
-}
-
-static u64 pnv_pci_ioda_dma_get_required_mask(struct pci_dev *pdev)
-{
-	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
-	struct pnv_phb *phb = hose->private_data;
-	struct pci_dn *pdn = pci_get_pdn(pdev);
-	struct pnv_ioda_pe *pe;
-	u64 end, mask;
-
-	if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE))
-		return 0;
-
-	pe = &phb->ioda.pe_array[pdn->pe_number];
-	if (!pe->tce_bypass_enabled)
-		return __dma_get_required_mask(&pdev->dev);
-
 
-	end = pe->tce_bypass_base + memblock_end_of_DRAM();
-	mask = 1ULL << (fls64(end) - 1);
-	mask += mask - 1;
-
-	return mask;
+	return false;
 }
 
 static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
@@ -1940,7 +1872,7 @@ static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		set_iommu_table_base(&dev->dev, pe->table_group.tables[0]);
-		set_dma_offset(&dev->dev, pe->tce_bypass_base);
+		dev->dev.archdata.dma_offset = pe->tce_bypass_base;
 
 		if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
 			pnv_ioda_setup_bus_dma(pe, dev->subordinate);
@@ -3659,6 +3591,7 @@ static void pnv_pci_ioda_shutdown(struct pci_controller *hose)
 static const struct pci_controller_ops pnv_pci_ioda_controller_ops = {
 	.dma_dev_setup		= pnv_pci_dma_dev_setup,
 	.dma_bus_setup		= pnv_pci_dma_bus_setup,
+	.iommu_bypass_supported	= pnv_pci_ioda_iommu_bypass_supported,
 	.setup_msi_irqs		= pnv_setup_msi_irqs,
 	.teardown_msi_irqs	= pnv_teardown_msi_irqs,
 	.enable_device_hook	= pnv_pci_enable_device_hook,
@@ -3666,19 +3599,9 @@ static const struct pci_controller_ops pnv_pci_ioda_controller_ops = {
 	.window_alignment	= pnv_pci_window_alignment,
 	.setup_bridge		= pnv_pci_setup_bridge,
 	.reset_secondary_bus	= pnv_pci_reset_secondary_bus,
-	.dma_set_mask		= pnv_pci_ioda_dma_set_mask,
-	.dma_get_required_mask	= pnv_pci_ioda_dma_get_required_mask,
 	.shutdown		= pnv_pci_ioda_shutdown,
 };
 
-static int pnv_npu_dma_set_mask(struct pci_dev *npdev, u64 dma_mask)
-{
-	dev_err_once(&npdev->dev,
-			"%s operation unsupported for NVLink devices\n",
-			__func__);
-	return -EPERM;
-}
-
 static const struct pci_controller_ops pnv_npu_ioda_controller_ops = {
 	.dma_dev_setup		= pnv_pci_dma_dev_setup,
 	.setup_msi_irqs		= pnv_setup_msi_irqs,
@@ -3686,7 +3609,6 @@ static const struct pci_controller_ops pnv_npu_ioda_controller_ops = {
 	.enable_device_hook	= pnv_pci_enable_device_hook,
 	.window_alignment	= pnv_pci_window_alignment,
 	.reset_secondary_bus	= pnv_pci_reset_secondary_bus,
-	.dma_set_mask		= pnv_npu_dma_set_mask,
 	.shutdown		= pnv_pci_ioda_shutdown,
 	.disable_device		= pnv_npu_disable_device,
 };

arch/powerpc/platforms/pseries/iommu.c

@@ -978,7 +978,7 @@ static phys_addr_t ddw_memory_hotplug_max(void)
  * pdn: the parent pe node with the ibm,dma_window property
  * Future: also check if we can remap the base window for our base page size
  *
- * returns the dma offset for use by dma_set_mask
+ * returns the dma offset for use by the direct mapped DMA code.
  */
 static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 {
@@ -1198,87 +1198,37 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 	iommu_add_device(pci->table_group, &dev->dev);
 }
 
-static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask)
+static bool iommu_bypass_supported_pSeriesLP(struct pci_dev *pdev, u64 dma_mask)
 {
-	bool ddw_enabled = false;
-	struct device_node *pdn, *dn;
-	struct pci_dev *pdev;
+	struct device_node *dn = pci_device_to_OF_node(pdev), *pdn;
 	const __be32 *dma_window = NULL;
-	u64 dma_offset;
-
-	if (!dev->dma_mask)
-		return -EIO;
-
-	if (!dev_is_pci(dev))
-		goto check_mask;
-
-	pdev = to_pci_dev(dev);
 
 	/* only attempt to use a new window if 64-bit DMA is requested */
-	if (!disable_ddw && dma_mask == DMA_BIT_MASK(64)) {
-		dn = pci_device_to_OF_node(pdev);
-		dev_dbg(dev, "node is %pOF\n", dn);
+	if (dma_mask < DMA_BIT_MASK(64))
+		return false;
 
-		/*
-		 * the device tree might contain the dma-window properties
-		 * per-device and not necessarily for the bus. So we need to
-		 * search upwards in the tree until we either hit a dma-window
-		 * property, OR find a parent with a table already allocated.
-		 */
-		for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->table_group;
-				pdn = pdn->parent) {
-			dma_window = of_get_property(pdn, "ibm,dma-window", NULL);
-			if (dma_window)
-				break;
-		}
-		if (pdn && PCI_DN(pdn)) {
-			dma_offset = enable_ddw(pdev, pdn);
-			if (dma_offset != 0) {
-				dev_info(dev, "Using 64-bit direct DMA at offset %llx\n", dma_offset);
-				set_dma_offset(dev, dma_offset);
-				set_dma_ops(dev, &dma_nommu_ops);
-				ddw_enabled = true;
-			}
-		}
-	}
+	dev_dbg(&pdev->dev, "node is %pOF\n", dn);
 
-	/* fall back on iommu ops */
-	if (!ddw_enabled && get_dma_ops(dev) != &dma_iommu_ops) {
-		dev_info(dev, "Restoring 32-bit DMA via iommu\n");
-		set_dma_ops(dev, &dma_iommu_ops);
+	/*
+	 * the device tree might contain the dma-window properties
+	 * per-device and not necessarily for the bus. So we need to
+	 * search upwards in the tree until we either hit a dma-window
+	 * property, OR find a parent with a table already allocated.
+	 */
+	for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->table_group;
+			pdn = pdn->parent) {
+		dma_window = of_get_property(pdn, "ibm,dma-window", NULL);
+		if (dma_window)
+			break;
 	}
 
-check_mask:
-	if (!dma_supported(dev, dma_mask))
-		return -EIO;
-
-	*dev->dma_mask = dma_mask;
-	return 0;
-}
-
-static u64 dma_get_required_mask_pSeriesLP(struct device *dev)
-{
-	if (!dev->dma_mask)
-		return 0;
-
-	if (!disable_ddw && dev_is_pci(dev)) {
-		struct pci_dev *pdev = to_pci_dev(dev);
-		struct device_node *dn;
-
-		dn = pci_device_to_OF_node(pdev);
-
-		/* search upwards for ibm,dma-window */
-		for (; dn && PCI_DN(dn) && !PCI_DN(dn)->table_group;
-				dn = dn->parent)
-			if (of_get_property(dn, "ibm,dma-window", NULL))
-				break;
-		/* if there is a ibm,ddw-applicable property require 64 bits */
-		if (dn && PCI_DN(dn) &&
-				of_get_property(dn, "ibm,ddw-applicable", NULL))
-			return DMA_BIT_MASK(64);
+	if (pdn && PCI_DN(pdn)) {
+		pdev->dev.archdata.dma_offset = enable_ddw(pdev, pdn);
+		if (pdev->dev.archdata.dma_offset)
+			return true;
 	}
 
-	return dma_iommu_ops.get_required_mask(dev);
+	return false;
 }
 
 static int iommu_mem_notifier(struct notifier_block *nb, unsigned long action,
@@ -1373,8 +1323,9 @@ void iommu_init_early_pSeries(void)
 	if (firmware_has_feature(FW_FEATURE_LPAR)) {
 		pseries_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pSeriesLP;
 		pseries_pci_controller_ops.dma_dev_setup = pci_dma_dev_setup_pSeriesLP;
-		ppc_md.dma_set_mask = dma_set_mask_pSeriesLP;
-		ppc_md.dma_get_required_mask = dma_get_required_mask_pSeriesLP;
+		if (!disable_ddw)
+			pseries_pci_controller_ops.iommu_bypass_supported =
+				iommu_bypass_supported_pSeriesLP;
 	} else {
 		pseries_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pSeries;
 		pseries_pci_controller_ops.dma_dev_setup = pci_dma_dev_setup_pSeries;

arch/powerpc/platforms/pseries/vio.c

@@ -492,7 +492,9 @@ static void *vio_dma_iommu_alloc_coherent(struct device *dev, size_t size,
 		return NULL;
 	}
 
-	ret = dma_iommu_ops.alloc(dev, size, dma_handle, flag, attrs);
+	ret = iommu_alloc_coherent(dev, get_iommu_table_base(dev), size,
+				    dma_handle, dev->coherent_dma_mask, flag,
+				    dev_to_node(dev));
 	if (unlikely(ret == NULL)) {
 		vio_cmo_dealloc(viodev, roundup(size, PAGE_SIZE));
 		atomic_inc(&viodev->cmo.allocs_failed);
@@ -507,8 +509,7 @@ static void vio_dma_iommu_free_coherent(struct device *dev, size_t size,
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
 
-	dma_iommu_ops.free(dev, size, vaddr, dma_handle, attrs);
-
+	iommu_free_coherent(get_iommu_table_base(dev), size, vaddr, dma_handle);
 	vio_cmo_dealloc(viodev, roundup(size, PAGE_SIZE));
 }
 
@@ -518,22 +519,22 @@ static dma_addr_t vio_dma_iommu_map_page(struct device *dev, struct page *page,
                                          unsigned long attrs)
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
-	struct iommu_table *tbl;
+	struct iommu_table *tbl = get_iommu_table_base(dev);
 	dma_addr_t ret = DMA_MAPPING_ERROR;
 
-	tbl = get_iommu_table_base(dev);
-	if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)))) {
-		atomic_inc(&viodev->cmo.allocs_failed);
-		return ret;
-	}
-
-	ret = dma_iommu_ops.map_page(dev, page, offset, size, direction, attrs);
-	if (unlikely(dma_mapping_error(dev, ret))) {
-		vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)));
-		atomic_inc(&viodev->cmo.allocs_failed);
-	}
-
+	if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl))))
+		goto out_fail;
+	ret = iommu_map_page(dev, tbl, page, offset, size, device_to_mask(dev),
+			direction, attrs);
+	if (unlikely(ret == DMA_MAPPING_ERROR))
+		goto out_deallocate;
 	return ret;
+
+out_deallocate:
+	vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)));
+out_fail:
+	atomic_inc(&viodev->cmo.allocs_failed);
+	return DMA_MAPPING_ERROR;
 }
 
 static void vio_dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle,
@@ -542,11 +543,9 @@ static void vio_dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle,
 				     unsigned long attrs)
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
-	struct iommu_table *tbl;
-
-	tbl = get_iommu_table_base(dev);
-	dma_iommu_ops.unmap_page(dev, dma_handle, size, direction, attrs);
+	struct iommu_table *tbl = get_iommu_table_base(dev);
 
+	iommu_unmap_page(tbl, dma_handle, size, direction, attrs);
 	vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)));
 }
 
@@ -555,34 +554,32 @@ static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
                                 unsigned long attrs)
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
-	struct iommu_table *tbl;
+	struct iommu_table *tbl = get_iommu_table_base(dev);
 	struct scatterlist *sgl;
 	int ret, count;
 	size_t alloc_size = 0;
 
-	tbl = get_iommu_table_base(dev);
 	for_each_sg(sglist, sgl, nelems, count)
 		alloc_size += roundup(sgl->length, IOMMU_PAGE_SIZE(tbl));
 
-	if (vio_cmo_alloc(viodev, alloc_size)) {
-		atomic_inc(&viodev->cmo.allocs_failed);
-		return 0;
-	}
-
-	ret = dma_iommu_ops.map_sg(dev, sglist, nelems, direction, attrs);
-
-	if (unlikely(!ret)) {
-		vio_cmo_dealloc(viodev, alloc_size);
-		atomic_inc(&viodev->cmo.allocs_failed);
-		return ret;
-	}
+	if (vio_cmo_alloc(viodev, alloc_size))
+		goto out_fail;
+	ret = ppc_iommu_map_sg(dev, tbl, sglist, nelems, device_to_mask(dev),
+			direction, attrs);
+	if (unlikely(!ret))
+		goto out_deallocate;
 
 	for_each_sg(sglist, sgl, ret, count)
 		alloc_size -= roundup(sgl->dma_length, IOMMU_PAGE_SIZE(tbl));
 	if (alloc_size)
 		vio_cmo_dealloc(viodev, alloc_size);
-
 	return ret;
+
+out_deallocate:
+	vio_cmo_dealloc(viodev, alloc_size);
+out_fail:
+	atomic_inc(&viodev->cmo.allocs_failed);
+	return 0;
 }
 
 static void vio_dma_iommu_unmap_sg(struct device *dev,
@@ -591,40 +588,27 @@ static void vio_dma_iommu_unmap_sg(struct device *dev,
 		unsigned long attrs)
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
-	struct iommu_table *tbl;
+	struct iommu_table *tbl = get_iommu_table_base(dev);
 	struct scatterlist *sgl;
 	size_t alloc_size = 0;
 	int count;
 
-	tbl = get_iommu_table_base(dev);
 	for_each_sg(sglist, sgl, nelems, count)
 		alloc_size += roundup(sgl->dma_length, IOMMU_PAGE_SIZE(tbl));
 
-	dma_iommu_ops.unmap_sg(dev, sglist, nelems, direction, attrs);
-
+	ppc_iommu_unmap_sg(tbl, sglist, nelems, direction, attrs);
 	vio_cmo_dealloc(viodev, alloc_size);
 }
 
-static int vio_dma_iommu_dma_supported(struct device *dev, u64 mask)
-{
-        return dma_iommu_ops.dma_supported(dev, mask);
-}
-
-static u64 vio_dma_get_required_mask(struct device *dev)
-{
-        return dma_iommu_ops.get_required_mask(dev);
-}
-
 static const struct dma_map_ops vio_dma_mapping_ops = {
 	.alloc             = vio_dma_iommu_alloc_coherent,
 	.free              = vio_dma_iommu_free_coherent,
-	.mmap		   = dma_nommu_mmap_coherent,
 	.map_sg            = vio_dma_iommu_map_sg,
 	.unmap_sg          = vio_dma_iommu_unmap_sg,
 	.map_page          = vio_dma_iommu_map_page,
 	.unmap_page        = vio_dma_iommu_unmap_page,
-	.dma_supported     = vio_dma_iommu_dma_supported,
-	.get_required_mask = vio_dma_get_required_mask,
+	.dma_supported     = dma_iommu_dma_supported,
+	.get_required_mask = dma_iommu_get_required_mask,
 };
 
 /**
@@ -1715,3 +1699,10 @@ int vio_disable_interrupts(struct vio_dev *dev)
 }
 EXPORT_SYMBOL(vio_disable_interrupts);
 #endif /* CONFIG_PPC_PSERIES */
+
+static int __init vio_init(void)
+{
+	dma_debug_add_bus(&vio_bus_type);
+	return 0;
+}
+fs_initcall(vio_init);

arch/powerpc/sysdev/dart_iommu.c

@@ -360,13 +360,6 @@ static void iommu_table_dart_setup(void)
 	set_bit(iommu_table_dart.it_size - 1, iommu_table_dart.it_map);
 }
 
-static void pci_dma_dev_setup_dart(struct pci_dev *dev)
-{
-	if (dart_is_u4)
-		set_dma_offset(&dev->dev, DART_U4_BYPASS_BASE);
-	set_iommu_table_base(&dev->dev, &iommu_table_dart);
-}
-
 static void pci_dma_bus_setup_dart(struct pci_bus *bus)
 {
 	if (!iommu_table_dart_inited) {
@@ -390,27 +383,18 @@ static bool dart_device_on_pcie(struct device *dev)
 	return false;
 }
 
-static int dart_dma_set_mask(struct device *dev, u64 dma_mask)
+static void pci_dma_dev_setup_dart(struct pci_dev *dev)
 {
-	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
-		return -EIO;
-
-	/* U4 supports a DART bypass, we use it for 64-bit capable
-	 * devices to improve performances. However, that only works
-	 * for devices connected to U4 own PCIe interface, not bridged
-	 * through hypertransport. We need the device to support at
-	 * least 40 bits of addresses.
-	 */
-	if (dart_device_on_pcie(dev) && dma_mask >= DMA_BIT_MASK(40)) {
-		dev_info(dev, "Using 64-bit DMA iommu bypass\n");
-		set_dma_ops(dev, &dma_nommu_ops);
-	} else {
-		dev_info(dev, "Using 32-bit DMA via iommu\n");
-		set_dma_ops(dev, &dma_iommu_ops);
-	}
+	if (dart_is_u4 && dart_device_on_pcie(&dev->dev))
+		dev->dev.archdata.dma_offset = DART_U4_BYPASS_BASE;
+	set_iommu_table_base(&dev->dev, &iommu_table_dart);
+}
 
-	*dev->dma_mask = dma_mask;
-	return 0;
+static bool iommu_bypass_supported_dart(struct pci_dev *dev, u64 mask)
+{
+	return dart_is_u4 &&
+		dart_device_on_pcie(&dev->dev) &&
+		mask >= DMA_BIT_MASK(40);
 }
 
 void __init iommu_init_early_dart(struct pci_controller_ops *controller_ops)
@@ -428,26 +412,20 @@ void __init iommu_init_early_dart(struct pci_controller_ops *controller_ops)
 
 	/* Initialize the DART HW */
 	if (dart_init(dn) != 0)
-		goto bail;
-
-	/* Setup bypass if supported */
-	if (dart_is_u4)
-		ppc_md.dma_set_mask = dart_dma_set_mask;
+		return;
 
+	/*
+	 * U4 supports a DART bypass, we use it for 64-bit capable devices to
+	 * improve performance.  However, that only works for devices connected
+	 * to the U4 own PCIe interface, not bridged through hypertransport.
+	 * We need the device to support at least 40 bits of addresses.
+	 */
 	controller_ops->dma_dev_setup = pci_dma_dev_setup_dart;
 	controller_ops->dma_bus_setup = pci_dma_bus_setup_dart;
+	controller_ops->iommu_bypass_supported = iommu_bypass_supported_dart;
 
 	/* Setup pci_dma ops */
 	set_pci_dma_ops(&dma_iommu_ops);
-	return;
-
- bail:
-	/* If init failed, use direct iommu and null setup functions */
-	controller_ops->dma_dev_setup = NULL;
-	controller_ops->dma_bus_setup = NULL;
-
-	/* Setup pci_dma ops */
-	set_pci_dma_ops(&dma_nommu_ops);
 }
 
 #ifdef CONFIG_PM

arch/powerpc/sysdev/fsl_pci.c

@@ -40,6 +40,7 @@
 #include <asm/mpc85xx.h>
 #include <asm/disassemble.h>
 #include <asm/ppc-opcode.h>
+#include <asm/swiotlb.h>
 #include <sysdev/fsl_soc.h>
 #include <sysdev/fsl_pci.h>
 
@@ -114,33 +115,33 @@ static struct pci_ops fsl_indirect_pcie_ops =
 static u64 pci64_dma_offset;
 
 #ifdef CONFIG_SWIOTLB
+static void pci_dma_dev_setup_swiotlb(struct pci_dev *pdev)
+{
+	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+
+	pdev->dev.bus_dma_mask =
+		hose->dma_window_base_cur + hose->dma_window_size;
+}
+
 static void setup_swiotlb_ops(struct pci_controller *hose)
 {
-	if (ppc_swiotlb_enable) {
+	if (ppc_swiotlb_enable)
 		hose->controller_ops.dma_dev_setup = pci_dma_dev_setup_swiotlb;
-		set_pci_dma_ops(&powerpc_swiotlb_dma_ops);
-	}
 }
 #else
 static inline void setup_swiotlb_ops(struct pci_controller *hose) {}
 #endif
 
-static int fsl_pci_dma_set_mask(struct device *dev, u64 dma_mask)
+static void fsl_pci_dma_set_mask(struct device *dev, u64 dma_mask)
 {
-	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
-		return -EIO;
-
 	/*
 	 * Fix up PCI devices that are able to DMA to the large inbound
 	 * mapping that allows addressing any RAM address from across PCI.
 	 */
 	if (dev_is_pci(dev) && dma_mask >= pci64_dma_offset * 2 - 1) {
-		set_dma_ops(dev, &dma_nommu_ops);
-		set_dma_offset(dev, pci64_dma_offset);
+		dev->bus_dma_mask = 0;
+		dev->archdata.dma_offset = pci64_dma_offset;
 	}
-
-	*dev->dma_mask = dma_mask;
-	return 0;
 }
 
 static int setup_one_atmu(struct ccsr_pci __iomem *pci,

drivers/misc/cxl/vphb.c

@@ -43,8 +43,7 @@ static bool cxl_pci_enable_device_hook(struct pci_dev *dev)
 		return false;
 	}
 
-	set_dma_ops(&dev->dev, &dma_nommu_ops);
-	set_dma_offset(&dev->dev, PAGE_OFFSET);
+	dev->dev.archdata.dma_offset = PAGE_OFFSET;
 
 	/*
 	 * Allocate a context to do cxl things too.  If we eventually do real

drivers/net/ethernet/pasemi/pasemi_mac.c

@@ -1716,6 +1716,7 @@ pasemi_mac_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		err = -ENODEV;
 		goto out;
 	}
+	dma_set_mask(&mac->dma_pdev->dev, DMA_BIT_MASK(64));
 
 	mac->iob_pdev = pci_get_device(PCI_VENDOR_ID_PASEMI, 0xa001, NULL);
 	if (!mac->iob_pdev) {

include/linux/swiotlb.h

@@ -60,9 +60,6 @@ extern void swiotlb_tbl_sync_single(struct device *hwdev,
 				    size_t size, enum dma_data_direction dir,
 				    enum dma_sync_target target);
 
-extern int
-swiotlb_dma_supported(struct device *hwdev, u64 mask);
-
 #ifdef CONFIG_SWIOTLB
 extern enum swiotlb_force swiotlb_force;
 extern phys_addr_t io_tlb_start, io_tlb_end;

kernel/dma/Kconfig

@@ -16,6 +16,9 @@ config ARCH_DMA_ADDR_T_64BIT
 config ARCH_HAS_DMA_COHERENCE_H
 	bool
 
+config ARCH_HAS_DMA_SET_MASK
+	bool
+
 config HAVE_GENERIC_DMA_COHERENT
 	bool
 

kernel/dma/direct.c

@@ -132,8 +132,7 @@ struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 			goto again;
 		}
 
-		if (IS_ENABLED(CONFIG_ZONE_DMA) &&
-		    phys_mask < DMA_BIT_MASK(32) && !(gfp & GFP_DMA)) {
+		if (IS_ENABLED(CONFIG_ZONE_DMA) && !(gfp & GFP_DMA)) {
 			gfp = (gfp & ~GFP_DMA32) | GFP_DMA;
 			goto again;
 		}

kernel/dma/mapping.c

@@ -207,7 +207,6 @@ int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
 }
 EXPORT_SYMBOL(dma_mmap_attrs);
 
-#ifndef ARCH_HAS_DMA_GET_REQUIRED_MASK
 static u64 dma_default_get_required_mask(struct device *dev)
 {
 	u32 low_totalram = ((max_pfn - 1) << PAGE_SHIFT);
@@ -238,7 +237,6 @@ u64 dma_get_required_mask(struct device *dev)
 	return dma_default_get_required_mask(dev);
 }
 EXPORT_SYMBOL_GPL(dma_get_required_mask);
-#endif
 
 #ifndef arch_dma_alloc_attrs
 #define arch_dma_alloc_attrs(dev)	(true)
@@ -318,18 +316,23 @@ int dma_supported(struct device *dev, u64 mask)
 }
 EXPORT_SYMBOL(dma_supported);
 
-#ifndef HAVE_ARCH_DMA_SET_MASK
+#ifdef CONFIG_ARCH_HAS_DMA_SET_MASK
+void arch_dma_set_mask(struct device *dev, u64 mask);
+#else
+#define arch_dma_set_mask(dev, mask)	do { } while (0)
+#endif
+
 int dma_set_mask(struct device *dev, u64 mask)
 {
 	if (!dev->dma_mask || !dma_supported(dev, mask))
 		return -EIO;
 
+	arch_dma_set_mask(dev, mask);
 	dma_check_mask(dev, mask);
 	*dev->dma_mask = mask;
 	return 0;
 }
 EXPORT_SYMBOL(dma_set_mask);
-#endif
 
 #ifndef CONFIG_ARCH_HAS_DMA_SET_COHERENT_MASK
 int dma_set_coherent_mask(struct device *dev, u64 mask)

kernel/dma/swiotlb.c

@@ -648,15 +648,3 @@ bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr,
 
 	return true;
 }
-
-/*
- * Return whether the given device DMA address mask can be supported
- * properly.  For example, if your device can only drive the low 24-bits
- * during bus mastering, then you would pass 0x00ffffff as the mask to
- * this function.
- */
-int
-swiotlb_dma_supported(struct device *hwdev, u64 mask)
-{
-	return __phys_to_dma(hwdev, io_tlb_end - 1) <= mask;
-}