Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux; tag 'dma-mapping-5.5' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - improve dma-debug scalability (Eric Dumazet)

 - tiny dma-debug cleanup (Dan Carpenter)

 - check for vmap memory in dma_map_single (Kees Cook)

 - check for dma_addr_t overflows in dma-direct when using DMA offsets
   (Nicolas Saenz Julienne)

 - switch the x86 sta2x11 SOC to use more generic DMA code (Nicolas
   Saenz Julienne)

 - fix arm-nommu dma-ranges handling (Vladimir Murzin)

 - use __initdata in CMA (Shyam Saini)

 - replace the bus dma mask with a limit (Nicolas Saenz Julienne)

 - merge the remapping helpers into the main dma-direct flow (me)

 - switch xtensa to the generic dma remap handling (me)

 - various cleanups around dma_capable (me)

 - remove unused dev arguments to various dma-noncoherent helpers (me)

* 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux:

* tag 'dma-mapping-5.5' of git://git.infradead.org/users/hch/dma-mapping: (22 commits)
  dma-mapping: treat dev->bus_dma_mask as a DMA limit
  dma-direct: exclude dma_direct_map_resource from the min_low_pfn check
  dma-direct: don't check swiotlb=force in dma_direct_map_resource
  dma-debug: clean up put_hash_bucket()
  powerpc: remove support for NULL dev in __phys_to_dma / __dma_to_phys
  dma-direct: avoid a forward declaration for phys_to_dma
  dma-direct: unify the dma_capable definitions
  dma-mapping: drop the dev argument to arch_sync_dma_for_*
  x86/PCI: sta2x11: use default DMA address translation
  dma-direct: check for overflows on 32 bit DMA addresses
  dma-debug: increase HASH_SIZE
  dma-debug: reorder struct dma_debug_entry fields
  xtensa: use the generic uncached segment support
  dma-mapping: merge the generic remapping helpers into dma-direct
  dma-direct: provide mmap and get_sgtable method overrides
  dma-direct: remove the dma_handle argument to __dma_direct_alloc_pages
  dma-direct: remove __dma_direct_free_pages
  usb: core: Remove redundant vmap checks
  kernel: dma-contiguous: mark CMA parameters __initdata/__initconst
  dma-debug: add a schedule point in debug_dma_dump_mappings()
  ...

45 files changed, 146 insertions, 427 deletions

diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 8383155c8c82..4d7b671c8ff4 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -6,7 +6,6 @@
 config ARC
 	def_bool y
 	select ARC_TIMERS
-	select ARCH_HAS_DMA_COHERENT_TO_PFN
 	select ARCH_HAS_DMA_PREP_COHERENT
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_SETUP_DMA_OPS
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 73a7e88a1e92..e947572a521e 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -48,8 +48,8 @@ void arch_dma_prep_coherent(struct page *page, size_t size)
  * upper layer functions (in include/linux/dma-mapping.h)
  */
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	switch (dir) {
 	case DMA_TO_DEVICE:
@@ -69,8 +69,8 @@ void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
 	}
 }
 
-void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	switch (dir) {
 	case DMA_TO_DEVICE:
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 0d3c5d7cceb7..6d532e7296d3 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -7,7 +7,6 @@ config ARM
 	select ARCH_HAS_BINFMT_FLAT
 	select ARCH_HAS_DEBUG_VIRTUAL if MMU
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
-	select ARCH_HAS_DMA_COHERENT_TO_PFN if SWIOTLB
 	select ARCH_HAS_DMA_WRITE_COMBINE if !ARM_DMA_MEM_BUFFERABLE
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FORTIFY_SOURCE
diff --git a/arch/arm/include/asm/dma-direct.h b/arch/arm/include/asm/dma-direct.h
index b67e5fc1fe43..7c3001a6a775 100644
--- a/arch/arm/include/asm/dma-direct.h
+++ b/arch/arm/include/asm/dma-direct.h
@@ -14,23 +14,4 @@ static inline phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dev_addr)
 	return __pfn_to_phys(dma_to_pfn(dev, dev_addr)) + offset;
 }
 
-static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
-{
-	u64 limit, mask;
-
-	if (!dev->dma_mask)
-		return 0;
-
-	mask = *dev->dma_mask;
-
-	limit = (mask + 1) & ~mask;
-	if (limit && size > limit)
-		return 0;
-
-	if ((addr | (addr + size - 1)) & ~mask)
-		return 0;
-
-	return 1;
-}
-
 #endif /* ASM_ARM_DMA_DIRECT_H */
diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c
index db9247898300..287ef898a55e 100644
--- a/arch/arm/mm/dma-mapping-nommu.c
+++ b/arch/arm/mm/dma-mapping-nommu.c
@@ -35,7 +35,7 @@ static void *arm_nommu_dma_alloc(struct device *dev, size_t size,
 				 unsigned long attrs)
 
 {
-	void *ret = dma_alloc_from_global_coherent(size, dma_handle);
+	void *ret = dma_alloc_from_global_coherent(dev, size, dma_handle);
 
 	/*
 	 * dma_alloc_from_global_coherent() may fail because:
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 7d042d5c43e3..da1a32b5e192 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -2332,26 +2332,20 @@ void arch_teardown_dma_ops(struct device *dev)
 }
 
 #ifdef CONFIG_SWIOTLB
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	__dma_page_cpu_to_dev(phys_to_page(paddr), paddr & (PAGE_SIZE - 1),
 			      size, dir);
 }
 
-void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	__dma_page_dev_to_cpu(phys_to_page(paddr), paddr & (PAGE_SIZE - 1),
 			      size, dir);
 }
 
-long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr,
-		dma_addr_t dma_addr)
-{
-	return dma_to_pfn(dev, dma_addr);
-}
-
 void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs)
 {
diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index 3c7645d7b9b4..d40e9e5fc52b 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -71,20 +71,20 @@ static void dma_cache_maint(dma_addr_t handle, size_t size, u32 op)
  * pfn_valid returns true the pages is local and we can use the native
  * dma-direct functions, otherwise we call the Xen specific version.
  */
-void xen_dma_sync_for_cpu(struct device *dev, dma_addr_t handle,
-		phys_addr_t paddr, size_t size, enum dma_data_direction dir)
+void xen_dma_sync_for_cpu(dma_addr_t handle, phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	if (pfn_valid(PFN_DOWN(handle)))
-		arch_sync_dma_for_cpu(dev, paddr, size, dir);
+		arch_sync_dma_for_cpu(paddr, size, dir);
 	else if (dir != DMA_TO_DEVICE)
 		dma_cache_maint(handle, size, GNTTAB_CACHE_INVAL);
 }
 
-void xen_dma_sync_for_device(struct device *dev, dma_addr_t handle,
-		phys_addr_t paddr, size_t size, enum dma_data_direction dir)
+void xen_dma_sync_for_device(dma_addr_t handle, phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	if (pfn_valid(PFN_DOWN(handle)))
-		arch_sync_dma_for_device(dev, paddr, size, dir);
+		arch_sync_dma_for_device(paddr, size, dir);
 	else if (dir == DMA_FROM_DEVICE)
 		dma_cache_maint(handle, size, GNTTAB_CACHE_INVAL);
 	else
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index afe6412fe769..b1b4476ddb83 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -12,7 +12,6 @@ config ARM64
 	select ARCH_CLOCKSOURCE_DATA
 	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
-	select ARCH_HAS_DMA_COHERENT_TO_PFN
 	select ARCH_HAS_DMA_PREP_COHERENT
 	select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
 	select ARCH_HAS_FAST_MULTIPLIER
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 9239416e93d4..6c45350e33aa 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -13,14 +13,14 @@
 
 #include <asm/cacheflush.h>
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	__dma_map_area(phys_to_virt(paddr), size, dir);
 }
 
-void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	__dma_unmap_area(phys_to_virt(paddr), size, dir);
 }
diff --git a/arch/c6x/mm/dma-coherent.c b/arch/c6x/mm/dma-coherent.c
index b319808e8f6b..a5909091cb14 100644
--- a/arch/c6x/mm/dma-coherent.c
+++ b/arch/c6x/mm/dma-coherent.c
@@ -140,7 +140,7 @@ void __init coherent_mem_init(phys_addr_t start, u32 size)
 		      sizeof(long));
 }
 
-static void c6x_dma_sync(struct device *dev, phys_addr_t paddr, size_t size,
+static void c6x_dma_sync(phys_addr_t paddr, size_t size,
 		enum dma_data_direction dir)
 {
 	BUG_ON(!valid_dma_direction(dir));
@@ -160,14 +160,14 @@ static void c6x_dma_sync(struct device *dev, phys_addr_t paddr, size_t size,
 	}
 }
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
-	return c6x_dma_sync(dev, paddr, size, dir);
+	return c6x_dma_sync(paddr, size, dir);
 }
 
-void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
-	return c6x_dma_sync(dev, paddr, size, dir);
+	return c6x_dma_sync(paddr, size, dir);
 }
diff --git a/arch/csky/mm/dma-mapping.c b/arch/csky/mm/dma-mapping.c
index 06e85b565454..8f6571ae27c8 100644
--- a/arch/csky/mm/dma-mapping.c
+++ b/arch/csky/mm/dma-mapping.c
@@ -58,8 +58,8 @@ void arch_dma_prep_coherent(struct page *page, size_t size)
 	cache_op(page_to_phys(page), size, dma_wbinv_set_zero_range);
 }
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-			      size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	switch (dir) {
 	case DMA_TO_DEVICE:
@@ -74,8 +74,8 @@ void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
 	}
 }
 
-void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
-			   size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	switch (dir) {
 	case DMA_TO_DEVICE:
diff --git a/arch/hexagon/kernel/dma.c b/arch/hexagon/kernel/dma.c
index f561b127c4b4..25f388d9cfcc 100644
--- a/arch/hexagon/kernel/dma.c
+++ b/arch/hexagon/kernel/dma.c
@@ -55,8 +55,8 @@ void arch_dma_free(struct device *dev, size_t size, void *vaddr,
 	gen_pool_free(coherent_pool, (unsigned long) vaddr, size);
 }
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	void *addr = phys_to_virt(paddr);
 
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 16714477eef4..bab7cd878464 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -33,7 +33,7 @@ config IA64
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_VIRT_CPU_ACCOUNTING
-	select ARCH_HAS_DMA_COHERENT_TO_PFN
+	select DMA_NONCOHERENT_MMAP
 	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select VIRT_TO_BUS
 	select GENERIC_IRQ_PROBE
diff --git a/arch/ia64/kernel/dma-mapping.c b/arch/ia64/kernel/dma-mapping.c
index 4a3262795890..09ef9ce9988d 100644
--- a/arch/ia64/kernel/dma-mapping.c
+++ b/arch/ia64/kernel/dma-mapping.c
@@ -19,9 +19,3 @@ void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
 {
 	dma_direct_free_pages(dev, size, cpu_addr, dma_addr, attrs);
 }
-
-long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr,
-		dma_addr_t dma_addr)
-{
-	return page_to_pfn(virt_to_page(cpu_addr));
-}
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index bf9df2625bc8..58fd67068bac 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -73,8 +73,8 @@ __ia64_sync_icache_dcache (pte_t pte)
  * DMA can be marked as "clean" so that lazy_mmu_prot_update() doesn't have to
  * flush them when they get mapped into an executable vm-area.
  */
-void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	unsigned long pfn = PHYS_PFN(paddr);
 
diff --git a/arch/m68k/kernel/dma.c b/arch/m68k/kernel/dma.c
index 3fab684cc0db..871a0e11da34 100644
--- a/arch/m68k/kernel/dma.c
+++ b/arch/m68k/kernel/dma.c
@@ -61,8 +61,8 @@ void arch_dma_free(struct device *dev, size_t size, void *vaddr,
 
 #endif /* CONFIG_MMU && !CONFIG_COLDFIRE */
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t handle,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t handle, size_t size,
+		enum dma_data_direction dir)
 {
 	switch (dir) {
 	case DMA_BIDIRECTIONAL:
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index a75896f18e58..5f46ebe7bfe3 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -4,7 +4,6 @@ config MICROBLAZE
 	select ARCH_32BIT_OFF_T
 	select ARCH_NO_SWAP
 	select ARCH_HAS_BINFMT_FLAT if !MMU
-	select ARCH_HAS_DMA_COHERENT_TO_PFN if MMU
 	select ARCH_HAS_DMA_PREP_COHERENT
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_SYNC_DMA_FOR_CPU
diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c
index a89c2d4ed5ff..d7bebd04247b 100644
--- a/arch/microblaze/kernel/dma.c
+++ b/arch/microblaze/kernel/dma.c
@@ -15,7 +15,7 @@
 #include <linux/bug.h>
 #include <asm/cacheflush.h>
 
-static void __dma_sync(struct device *dev, phys_addr_t paddr, size_t size,
+static void __dma_sync(phys_addr_t paddr, size_t size,
 		enum dma_data_direction direction)
 {
 	switch (direction) {
@@ -31,14 +31,14 @@ static void __dma_sync(struct device *dev, phys_addr_t paddr, size_t size,
 	}
 }
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
-	__dma_sync(dev, paddr, size, dir);
+	__dma_sync(paddr, size, dir);
 }
 
-void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
-	__dma_sync(dev, paddr, size, dir);
+	__dma_sync(paddr, size, dir);
 }
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 61b9269cdd3e..add388236f4e 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -1194,9 +1194,9 @@ config DMA_NONCOHERENT
 	select ARCH_HAS_DMA_WRITE_COMBINE
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
 	select ARCH_HAS_UNCACHED_SEGMENT
-	select NEED_DMA_MAP_STATE
-	select ARCH_HAS_DMA_COHERENT_TO_PFN
+	select DMA_NONCOHERENT_MMAP
 	select DMA_NONCOHERENT_CACHE_SYNC
+	select NEED_DMA_MAP_STATE
 
 config SYS_HAS_EARLY_PRINTK
 	bool
diff --git a/arch/mips/bmips/dma.c b/arch/mips/bmips/dma.c
index 3d13c77c125f..df56bf4179e3 100644
--- a/arch/mips/bmips/dma.c
+++ b/arch/mips/bmips/dma.c
@@ -64,7 +64,7 @@ phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 	return dma_addr;
 }
 
-void arch_sync_dma_for_cpu_all(struct device *dev)
+void arch_sync_dma_for_cpu_all(void)
 {
 	void __iomem *cbr = BMIPS_GET_CBR();
 	u32 cfg;
diff --git a/arch/mips/include/asm/dma-direct.h b/arch/mips/include/asm/dma-direct.h
index b5c240806e1b..14e352651ce9 100644
--- a/arch/mips/include/asm/dma-direct.h
+++ b/arch/mips/include/asm/dma-direct.h
@@ -2,14 +2,6 @@
 #ifndef _MIPS_DMA_DIRECT_H
 #define _MIPS_DMA_DIRECT_H 1
 
-static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
-{
-	if (!dev->dma_mask)
-		return false;
-
-	return addr + size - 1 <= *dev->dma_mask;
-}
-
 dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr);
 phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr);
 
diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c
index a01e14955187..c64a297e82b3 100644
--- a/arch/mips/jazz/jazzdma.c
+++ b/arch/mips/jazz/jazzdma.c
@@ -592,7 +592,7 @@ static dma_addr_t jazz_dma_map_page(struct device *dev, struct page *page,
 	phys_addr_t phys = page_to_phys(page) + offset;
 
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		arch_sync_dma_for_device(dev, phys, size, dir);
+		arch_sync_dma_for_device(phys, size, dir);
 	return vdma_alloc(phys, size);
 }
 
@@ -600,7 +600,7 @@ static void jazz_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		arch_sync_dma_for_cpu(dev, vdma_log2phys(dma_addr), size, dir);
+		arch_sync_dma_for_cpu(vdma_log2phys(dma_addr), size, dir);
 	vdma_free(dma_addr);
 }
 
@@ -612,7 +612,7 @@ static int jazz_dma_map_sg(struct device *dev, struct scatterlist *sglist,
 
 	for_each_sg(sglist, sg, nents, i) {
 		if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-			arch_sync_dma_for_device(dev, sg_phys(sg), sg->length,
+			arch_sync_dma_for_device(sg_phys(sg), sg->length,
 				dir);
 		sg->dma_address = vdma_alloc(sg_phys(sg), sg->length);
 		if (sg->dma_address == DMA_MAPPING_ERROR)
@@ -631,8 +631,7 @@ static void jazz_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
 
 	for_each_sg(sglist, sg, nents, i) {
 		if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-			arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length,
-				dir);
+			arch_sync_dma_for_cpu(sg_phys(sg), sg->length, dir);
 		vdma_free(sg->dma_address);
 	}
 }
@@ -640,13 +639,13 @@ static void jazz_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
 static void jazz_dma_sync_single_for_device(struct device *dev,
 		dma_addr_t addr, size_t size, enum dma_data_direction dir)
 {
-	arch_sync_dma_for_device(dev, vdma_log2phys(addr), size, dir);
+	arch_sync_dma_for_device(vdma_log2phys(addr), size, dir);
 }
 
 static void jazz_dma_sync_single_for_cpu(struct device *dev,
 		dma_addr_t addr, size_t size, enum dma_data_direction dir)
 {
-	arch_sync_dma_for_cpu(dev, vdma_log2phys(addr), size, dir);
+	arch_sync_dma_for_cpu(vdma_log2phys(addr), size, dir);
 }
 
 static void jazz_dma_sync_sg_for_device(struct device *dev,
@@ -656,7 +655,7 @@ static void jazz_dma_sync_sg_for_device(struct device *dev,
 	int i;
 
 	for_each_sg(sgl, sg, nents, i)
-		arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir);
+		arch_sync_dma_for_device(sg_phys(sg), sg->length, dir);
 }
 
 static void jazz_dma_sync_sg_for_cpu(struct device *dev,
@@ -666,7 +665,7 @@ static void jazz_dma_sync_sg_for_cpu(struct device *dev,
 	int i;
 
 	for_each_sg(sgl, sg, nents, i)
-		arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
+		arch_sync_dma_for_cpu(sg_phys(sg), sg->length, dir);
 }
 
 const struct dma_map_ops jazz_dma_ops = {
diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c
index 1d4d57dd9acf..dc42ffc83825 100644
--- a/arch/mips/mm/dma-noncoherent.c
+++ b/arch/mips/mm/dma-noncoherent.c
@@ -27,7 +27,7 @@
  * R10000 and R12000 are used in such systems, the SGI IP28 Indigo² rsp.
  * SGI IP32 aka O2.
  */
-static inline bool cpu_needs_post_dma_flush(struct device *dev)
+static inline bool cpu_needs_post_dma_flush(void)
 {
 	switch (boot_cpu_type()) {
 	case CPU_R10000:
@@ -59,12 +59,6 @@ void *cached_kernel_address(void *addr)
 	return __va(addr) - UNCAC_BASE;
 }
 
-long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr,
-		dma_addr_t dma_addr)
-{
-	return page_to_pfn(virt_to_page(cached_kernel_address(cpu_addr)));
-}
-
 static inline void dma_sync_virt(void *addr, size_t size,
 		enum dma_data_direction dir)
 {
@@ -118,17 +112,17 @@ static inline void dma_sync_phys(phys_addr_t paddr, size_t size,
 	} while (left);
 }
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	dma_sync_phys(paddr, size, dir);
 }
 
 #ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
-void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
-	if (cpu_needs_post_dma_flush(dev))
+	if (cpu_needs_post_dma_flush())
 		dma_sync_phys(paddr, size, dir);
 }
 #endif
diff --git a/arch/mips/pci/fixup-sb1250.c b/arch/mips/pci/fixup-sb1250.c
index 8a41b359cf90..40efc990cdce 100644
--- a/arch/mips/pci/fixup-sb1250.c
+++ b/arch/mips/pci/fixup-sb1250.c
@@ -21,22 +21,22 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SIBYTE, PCI_DEVICE_ID_BCM1250_PCI,
 
 /*
  * The BCM1250, etc. PCI host bridge does not support DAC on its 32-bit
- * bus, so we set the bus's DMA mask accordingly.  However the HT link
+ * bus, so we set the bus's DMA limit accordingly.  However the HT link
  * down the artificial PCI-HT bridge supports 40-bit addressing and the
  * SP1011 HT-PCI bridge downstream supports both DAC and a 64-bit bus
  * width, so we record the PCI-HT bridge's secondary and subordinate bus
- * numbers and do not set the mask for devices present in the inclusive
+ * numbers and do not set the limit for devices present in the inclusive
  * range of those.
  */
-struct sb1250_bus_dma_mask_exclude {
+struct sb1250_bus_dma_limit_exclude {
 	bool set;
 	unsigned char start;
 	unsigned char end;
 };
 
-static int sb1250_bus_dma_mask(struct pci_dev *dev, void *data)
+static int sb1250_bus_dma_limit(struct pci_dev *dev, void *data)
 {
-	struct sb1250_bus_dma_mask_exclude *exclude = data;
+	struct sb1250_bus_dma_limit_exclude *exclude = data;
 	bool exclude_this;
 	bool ht_bridge;
 
@@ -55,7 +55,7 @@ static int sb1250_bus_dma_mask(struct pci_dev *dev, void *data)
 			exclude->start, exclude->end);
 	} else {
 		dev_dbg(&dev->dev, "disabling DAC for device");
-		dev->dev.bus_dma_mask = DMA_BIT_MASK(32);
+		dev->dev.bus_dma_limit = DMA_BIT_MASK(32);
 	}
 
 	return 0;
@@ -63,9 +63,9 @@ static int sb1250_bus_dma_mask(struct pci_dev *dev, void *data)
 
 static void quirk_sb1250_pci_dac(struct pci_dev *dev)
 {
-	struct sb1250_bus_dma_mask_exclude exclude = { .set = false };
+	struct sb1250_bus_dma_limit_exclude exclude = { .set = false };
 
-	pci_walk_bus(dev->bus, sb1250_bus_dma_mask, &exclude);
+	pci_walk_bus(dev->bus, sb1250_bus_dma_limit, &exclude);
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SIBYTE, PCI_DEVICE_ID_BCM1250_PCI,
 			quirk_sb1250_pci_dac);
diff --git a/arch/nds32/kernel/dma.c b/arch/nds32/kernel/dma.c
index 4206d4b6c8ce..69d762182d49 100644
--- a/arch/nds32/kernel/dma.c
+++ b/arch/nds32/kernel/dma.c
@@ -46,8 +46,8 @@ static inline void cache_op(phys_addr_t paddr, size_t size,
 	} while (left);
 }
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	switch (dir) {
 	case DMA_FROM_DEVICE:
@@ -61,8 +61,8 @@ void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
 	}
 }
 
-void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	switch (dir) {
 	case DMA_TO_DEVICE:
diff --git a/arch/nios2/mm/dma-mapping.c b/arch/nios2/mm/dma-mapping.c
index 9cb238664584..0ed711e37902 100644
--- a/arch/nios2/mm/dma-mapping.c
+++ b/arch/nios2/mm/dma-mapping.c
@@ -18,8 +18,8 @@
 #include <linux/cache.h>
 #include <asm/cacheflush.h>
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	void *vaddr = phys_to_virt(paddr);
 
@@ -42,8 +42,8 @@ void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
 	}
 }
 
-void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	void *vaddr = phys_to_virt(paddr);
 
diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c
index 4d5b8bd1d795..adec711ad39d 100644
--- a/arch/openrisc/kernel/dma.c
+++ b/arch/openrisc/kernel/dma.c
@@ -125,7 +125,7 @@ arch_dma_free(struct device *dev, size_t size, void *vaddr,
 	free_pages_exact(vaddr, size);
 }
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t addr, size_t size,
+void arch_sync_dma_for_device(phys_addr_t addr, size_t size,
 		enum dma_data_direction dir)
 {
 	unsigned long cl;
diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c
index ca35d9a76e50..a60d47fd4d55 100644
--- a/arch/parisc/kernel/pci-dma.c
+++ b/arch/parisc/kernel/pci-dma.c
@@ -439,14 +439,14 @@ void arch_dma_free(struct device *dev, size_t size, void *vaddr,
 	free_pages((unsigned long)__va(dma_handle), order);
 }
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	flush_kernel_dcache_range((unsigned long)phys_to_virt(paddr), size);
 }
 
-void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	flush_kernel_dcache_range((unsigned long)phys_to_virt(paddr), size);
 }
diff --git a/arch/powerpc/include/asm/dma-direct.h b/arch/powerpc/include/asm/dma-direct.h
index a2912b47102c..abc154d784b0 100644
--- a/arch/powerpc/include/asm/dma-direct.h
+++ b/arch/powerpc/include/asm/dma-direct.h
@@ -2,26 +2,13 @@
 #ifndef ASM_POWERPC_DMA_DIRECT_H
 #define ASM_POWERPC_DMA_DIRECT_H 1
 
-static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
-{
-	if (!dev->dma_mask)
-		return false;
-
-	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)
 {
-	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)
 {
-	if (!dev)
-		return daddr - PCI_DRAM_OFFSET;
 	return daddr - dev->archdata.dma_offset;
 }
 #endif /* ASM_POWERPC_DMA_DIRECT_H */
diff --git a/arch/powerpc/mm/dma-noncoherent.c b/arch/powerpc/mm/dma-noncoherent.c
index 2a82984356f8..5ab4f868e919 100644
--- a/arch/powerpc/mm/dma-noncoherent.c
+++ b/arch/powerpc/mm/dma-noncoherent.c
@@ -104,14 +104,14 @@ static void __dma_sync_page(phys_addr_t paddr, size_t size, int dir)
 #endif
 }
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(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)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	__dma_sync_page(paddr, size, dir);
 }
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 12543e53fa96..303752f97c19 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -459,7 +459,6 @@ 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_DMA_PREP_COHERENT
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
 	select ARCH_HAS_SYNC_DMA_FOR_CPU
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index ff0e2b156cb5..617a443d673d 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -115,8 +115,8 @@ 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;
+	pdev->dev.bus_dma_limit =
+		hose->dma_window_base_cur + hose->dma_window_size - 1;
 }
 
 static void setup_swiotlb_ops(struct pci_controller *hose)
@@ -135,7 +135,7 @@ static void fsl_pci_dma_set_mask(struct device *dev, u64 dma_mask)
 	 * mapping that allows addressing any RAM address from across PCI.
 	 */
 	if (dev_is_pci(dev) && dma_mask >= pci64_dma_offset * 2 - 1) {
-		dev->bus_dma_mask = 0;
+		dev->bus_dma_limit = 0;
 		dev->archdata.dma_offset = pci64_dma_offset;
 	}
 }
diff --git a/arch/sh/kernel/dma-coherent.c b/arch/sh/kernel/dma-coherent.c
index b17514619b7e..eeb25a4fa55f 100644
--- a/arch/sh/kernel/dma-coherent.c
+++ b/arch/sh/kernel/dma-coherent.c
@@ -25,7 +25,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	 * Pages from the page allocator may have data present in
 	 * cache. So flush the cache before using uncached memory.
 	 */
-	arch_sync_dma_for_device(dev, virt_to_phys(ret), size,
+	arch_sync_dma_for_device(virt_to_phys(ret), size,
 			DMA_BIDIRECTIONAL);
 
 	ret_nocache = (void __force *)ioremap_nocache(virt_to_phys(ret), size);
@@ -59,8 +59,8 @@ void arch_dma_free(struct device *dev, size_t size, void *vaddr,
 	iounmap(vaddr);
 }
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	void *addr = sh_cacheop_vaddr(phys_to_virt(paddr));
 
diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c
index f89603855f1e..e59461d03b9a 100644
--- a/arch/sparc/kernel/ioport.c
+++ b/arch/sparc/kernel/ioport.c
@@ -366,8 +366,8 @@ void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
 
 /* IIep is write-through, not flushing on cpu to device transfer. */
 
-void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	if (dir != PCI_DMA_TODEVICE)
 		dma_make_coherent(paddr, PAGE_ALIGN(size));
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 58b31ee198d9..0cb1756223be 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -708,7 +708,6 @@ config X86_SUPPORTS_MEMORY_FAILURE
 config STA2X11
 	bool "STA2X11 Companion Chip Support"
 	depends on X86_32_NON_STANDARD && PCI
-	select ARCH_HAS_PHYS_TO_DMA
 	select SWIOTLB
 	select MFD_STA2X11
 	select GPIOLIB
diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h
index a8f6c809d9b1..5e12c63b47aa 100644
--- a/arch/x86/include/asm/device.h
+++ b/arch/x86/include/asm/device.h
@@ -6,9 +6,6 @@ struct dev_archdata {
 #if defined(CONFIG_INTEL_IOMMU) || defined(CONFIG_AMD_IOMMU)
 	void *iommu; /* hook for IOMMU specific extension */
 #endif
-#ifdef CONFIG_STA2X11
-	bool is_sta2x11;
-#endif
 };
 
 #if defined(CONFIG_X86_DEV_DMA_OPS) && defined(CONFIG_PCI_DOMAINS)
diff --git a/arch/x86/include/asm/dma-direct.h b/arch/x86/include/asm/dma-direct.h
deleted file mode 100644
index 1a19251eaac9..000000000000
--- a/arch/x86/include/asm/dma-direct.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef ASM_X86_DMA_DIRECT_H
-#define ASM_X86_DMA_DIRECT_H 1
-
-bool dma_capable(struct device *dev, dma_addr_t addr, size_t size);
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr);
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr);
-
-#endif /* ASM_X86_DMA_DIRECT_H */
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index 4bbccb9d16dc..4e5f50236048 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -185,13 +185,13 @@ static void iommu_full(struct device *dev, size_t size, int dir)
 static inline int
 need_iommu(struct device *dev, unsigned long addr, size_t size)
 {
-	return force_iommu || !dma_capable(dev, addr, size);
+	return force_iommu || !dma_capable(dev, addr, size, true);
 }
 
 static inline int
 nonforced_iommu(struct device *dev, unsigned long addr, size_t size)
 {
-	return !dma_capable(dev, addr, size);
+	return !dma_capable(dev, addr, size, true);
 }
 
 /* Map a single continuous physical area into the IOMMU.
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 57de2ebff7e2..5dcedad21dff 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -140,7 +140,7 @@ rootfs_initcall(pci_iommu_init);
 
 static int via_no_dac_cb(struct pci_dev *pdev, void *data)
 {
-	pdev->dev.bus_dma_mask = DMA_BIT_MASK(32);
+	pdev->dev.bus_dma_limit = DMA_BIT_MASK(32);
 	return 0;
 }
 
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 9268c12458c8..a03614bd3e1a 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -367,7 +367,7 @@ bool force_dma_unencrypted(struct device *dev)
 	if (sme_active()) {
 		u64 dma_enc_mask = DMA_BIT_MASK(__ffs64(sme_me_mask));
 		u64 dma_dev_mask = min_not_zero(dev->coherent_dma_mask,
-						dev->bus_dma_mask);
+						dev->bus_dma_limit);
 
 		if (dma_dev_mask <= dma_enc_mask)
 			return true;
diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
index 6269a175385d..c313d784efab 100644
--- a/arch/x86/pci/sta2x11-fixup.c
+++ b/arch/x86/pci/sta2x11-fixup.c
@@ -30,7 +30,6 @@ struct sta2x11_ahb_regs { /* saved during suspend */
 };
 
 struct sta2x11_mapping {
-	u32 amba_base;
 	int is_suspended;
 	struct sta2x11_ahb_regs regs[STA2X11_NR_FUNCS];
 };
@@ -92,18 +91,6 @@ static int sta2x11_pdev_to_ep(struct pci_dev *pdev)
 	return pdev->bus->number - instance->bus0;
 }
 
-static struct sta2x11_mapping *sta2x11_pdev_to_mapping(struct pci_dev *pdev)
-{
-	struct sta2x11_instance *instance;
-	int ep;
-
-	instance = sta2x11_pdev_to_instance(pdev);
-	if (!instance)
-		return NULL;
-	ep = sta2x11_pdev_to_ep(pdev);
-	return instance->map + ep;
-}
-
 /* This is exported, as some devices need to access the MFD registers */
 struct sta2x11_instance *sta2x11_get_instance(struct pci_dev *pdev)
 {
@@ -111,39 +98,6 @@ struct sta2x11_instance *sta2x11_get_instance(struct pci_dev *pdev)
 }
 EXPORT_SYMBOL(sta2x11_get_instance);
 
-
-/**
- * p2a - Translate physical address to STA2x11 AMBA address,
- *       used for DMA transfers to STA2x11
- * @p: Physical address
- * @pdev: PCI device (must be hosted within the connext)
- */
-static dma_addr_t p2a(dma_addr_t p, struct pci_dev *pdev)
-{
-	struct sta2x11_mapping *map;
-	dma_addr_t a;
-
-	map = sta2x11_pdev_to_mapping(pdev);
-	a = p + map->amba_base;
-	return a;
-}
-
-/**
- * a2p - Translate STA2x11 AMBA address to physical address
- *       used for DMA transfers from STA2x11
- * @a: STA2x11 AMBA address
- * @pdev: PCI device (must be hosted within the connext)
- */
-static dma_addr_t a2p(dma_addr_t a, struct pci_dev *pdev)
-{
-	struct sta2x11_mapping *map;
-	dma_addr_t p;
-
-	map = sta2x11_pdev_to_mapping(pdev);
-	p = a - map->amba_base;
-	return p;
-}
-
 /* At setup time, we use our own ops if the device is a ConneXt one */
 static void sta2x11_setup_pdev(struct pci_dev *pdev)
 {
@@ -151,9 +105,6 @@ static void sta2x11_setup_pdev(struct pci_dev *pdev)
 
 	if (!instance) /* either a sta2x11 bridge or another ST device */
 		return;
-	pci_set_consistent_dma_mask(pdev, STA2X11_AMBA_SIZE - 1);
-	pci_set_dma_mask(pdev, STA2X11_AMBA_SIZE - 1);
-	pdev->dev.archdata.is_sta2x11 = true;
 
 	/* We must enable all devices as master, for audio DMA to work */
 	pci_set_master(pdev);
@@ -161,61 +112,6 @@ static void sta2x11_setup_pdev(struct pci_dev *pdev)
 DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_STMICRO, PCI_ANY_ID, sta2x11_setup_pdev);
 
 /*
- * The following three functions are exported (used in swiotlb: FIXME)
- */
-/**
- * dma_capable - Check if device can manage DMA transfers (FIXME: kill it)
- * @dev: device for a PCI device
- * @addr: DMA address
- * @size: DMA size
- */
-bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
-{
-	struct sta2x11_mapping *map;
-
-	if (!dev->archdata.is_sta2x11) {
-		if (!dev->dma_mask)
-			return false;
-		return addr + size - 1 <= *dev->dma_mask;
-	}
-
-	map = sta2x11_pdev_to_mapping(to_pci_dev(dev));
-
-	if (!map || (addr < map->amba_base))
-		return false;
-	if (addr + size >= map->amba_base + STA2X11_AMBA_SIZE) {
-		return false;
-	}
-
-	return true;
-}
-
-/**
- * __phys_to_dma - Return the DMA AMBA address used for this STA2x11 device
- * @dev: device for a PCI device
- * @paddr: Physical address
- */
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
-{
-	if (!dev->archdata.is_sta2x11)
-		return paddr;
-	return p2a(paddr, to_pci_dev(dev));
-}
-
-/**
- * dma_to_phys - Return the physical address used for this STA2x11 DMA address
- * @dev: device for a PCI device
- * @daddr: STA2x11 AMBA DMA address
- */
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
-{
-	if (!dev->archdata.is_sta2x11)
-		return daddr;
-	return a2p(daddr, to_pci_dev(dev));
-}
-
-
-/*
  * At boot we must set up the mappings for the pcie-to-amba bridge.
  * It involves device access, and the same happens at suspend/resume time
  */
@@ -234,12 +130,22 @@ phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
 /* At probe time, enable mapping for each endpoint, using the pdev */
 static void sta2x11_map_ep(struct pci_dev *pdev)
 {
-	struct sta2x11_mapping *map = sta2x11_pdev_to_mapping(pdev);
+	struct sta2x11_instance *instance = sta2x11_pdev_to_instance(pdev);
+	struct device *dev = &pdev->dev;
+	u32 amba_base, max_amba_addr;
 	int i;
 
-	if (!map)
+	if (!instance)
 		return;
-	pci_read_config_dword(pdev, AHB_BASE(0), &map->amba_base);
+
+	pci_read_config_dword(pdev, AHB_BASE(0), &amba_base);
+	max_amba_addr = amba_base + STA2X11_AMBA_SIZE - 1;
+
+	dev->dma_pfn_offset = PFN_DOWN(-amba_base);
+
+	dev->bus_dma_limit = max_amba_addr;
+	pci_set_consistent_dma_mask(pdev, max_amba_addr);
+	pci_set_dma_mask(pdev, max_amba_addr);
 
 	/* Configure AHB mapping */
 	pci_write_config_dword(pdev, AHB_PEXLBASE(0), 0);
@@ -253,13 +159,24 @@ static void sta2x11_map_ep(struct pci_dev *pdev)
 
 	dev_info(&pdev->dev,
 		 "sta2x11: Map EP %i: AMBA address %#8x-%#8x\n",
-		 sta2x11_pdev_to_ep(pdev),  map->amba_base,
-		 map->amba_base + STA2X11_AMBA_SIZE - 1);
+		 sta2x11_pdev_to_ep(pdev), amba_base, max_amba_addr);
 }
 DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_STMICRO, PCI_ANY_ID, sta2x11_map_ep);
 
 #ifdef CONFIG_PM /* Some register values must be saved and restored */
 
+static struct sta2x11_mapping *sta2x11_pdev_to_mapping(struct pci_dev *pdev)
+{
+	struct sta2x11_instance *instance;
+	int ep;
+
+	instance = sta2x11_pdev_to_instance(pdev);
+	if (!instance)
+		return NULL;
+	ep = sta2x11_pdev_to_ep(pdev);
+	return instance->map + ep;
+}
+
 static void suspend_mapping(struct pci_dev *pdev)
 {
 	struct sta2x11_mapping *map = sta2x11_pdev_to_mapping(pdev);
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index a8e7beb6b7b5..c95a34702242 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -3,8 +3,10 @@ config XTENSA
 	def_bool y
 	select ARCH_32BIT_OFF_T
 	select ARCH_HAS_BINFMT_FLAT if !MMU
-	select ARCH_HAS_SYNC_DMA_FOR_CPU
-	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+	select ARCH_HAS_DMA_PREP_COHERENT if MMU
+	select ARCH_HAS_SYNC_DMA_FOR_CPU if MMU
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE if MMU
+	select ARCH_HAS_UNCACHED_SEGMENT if MMU
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS
 	select ARCH_WANT_FRAME_POINTERS
diff --git a/arch/xtensa/include/asm/platform.h b/arch/xtensa/include/asm/platform.h
index 913826dfa838..f2c48522c5a1 100644
--- a/arch/xtensa/include/asm/platform.h
+++ b/arch/xtensa/include/asm/platform.h
@@ -65,31 +65,4 @@ extern void platform_calibrate_ccount (void);
  */
 void cpu_reset(void) __attribute__((noreturn));
 
-/*
- * Memory caching is platform-dependent in noMMU xtensa configurations.
- * The following set of functions should be implemented in platform code
- * in order to enable coherent DMA memory operations when CONFIG_MMU is not
- * enabled. Default implementations do nothing and issue a warning.
- */
-
-/*
- * Check whether p points to a cached memory.
- */
-bool platform_vaddr_cached(const void *p);
-
-/*
- * Check whether p points to an uncached memory.
- */
-bool platform_vaddr_uncached(const void *p);
-
-/*
- * Return pointer to an uncached view of the cached sddress p.
- */
-void *platform_vaddr_to_uncached(void *p);
-
-/*
- * Return pointer to a cached view of the uncached sddress p.
- */
-void *platform_vaddr_to_cached(void *p);
-
 #endif	/* _XTENSA_PLATFORM_H */
diff --git a/arch/xtensa/kernel/Makefile b/arch/xtensa/kernel/Makefile
index 6f629027ac7d..d4082c6a121b 100644
--- a/arch/xtensa/kernel/Makefile
+++ b/arch/xtensa/kernel/Makefile
@@ -5,10 +5,11 @@
 
 extra-y := head.o vmlinux.lds
 
-obj-y := align.o coprocessor.o entry.o irq.o pci-dma.o platform.o process.o \
+obj-y := align.o coprocessor.o entry.o irq.o platform.o process.o \
 	 ptrace.o setup.o signal.o stacktrace.o syscall.o time.o traps.o \
 	 vectors.o
 
+obj-$(CONFIG_MMU) += pci-dma.o
 obj-$(CONFIG_PCI) += pci.o
 obj-$(CONFIG_MODULES) += xtensa_ksyms.o module.o
 obj-$(CONFIG_FUNCTION_TRACER) += mcount.o
diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c
index 154979d62b73..72b6222daa0b 100644
--- a/arch/xtensa/kernel/pci-dma.c
+++ b/arch/xtensa/kernel/pci-dma.c
@@ -44,8 +44,8 @@ static void do_cache_op(phys_addr_t paddr, size_t size,
 		}
 }
 
-void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	switch (dir) {
 	case DMA_BIDIRECTIONAL:
@@ -62,8 +62,8 @@ void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
 	}
 }
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	switch (dir) {
 	case DMA_BIDIRECTIONAL:
@@ -81,122 +81,25 @@ void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
 	}
 }
 
-#ifdef CONFIG_MMU
-bool platform_vaddr_cached(const void *p)
-{
-	unsigned long addr = (unsigned long)p;
-
-	return addr >= XCHAL_KSEG_CACHED_VADDR &&
-	       addr - XCHAL_KSEG_CACHED_VADDR < XCHAL_KSEG_SIZE;
-}
-
-bool platform_vaddr_uncached(const void *p)
-{
-	unsigned long addr = (unsigned long)p;
-
-	return addr >= XCHAL_KSEG_BYPASS_VADDR &&
-	       addr - XCHAL_KSEG_BYPASS_VADDR < XCHAL_KSEG_SIZE;
-}
-
-void *platform_vaddr_to_uncached(void *p)
-{
-	return p + XCHAL_KSEG_BYPASS_VADDR - XCHAL_KSEG_CACHED_VADDR;
-}
-
-void *platform_vaddr_to_cached(void *p)
-{
-	return p + XCHAL_KSEG_CACHED_VADDR - XCHAL_KSEG_BYPASS_VADDR;
-}
-#else
-bool __attribute__((weak)) platform_vaddr_cached(const void *p)
-{
-	WARN_ONCE(1, "Default %s implementation is used\n", __func__);
-	return true;
-}
-
-bool __attribute__((weak)) platform_vaddr_uncached(const void *p)
-{
-	WARN_ONCE(1, "Default %s implementation is used\n", __func__);
-	return false;
-}
-
-void __attribute__((weak)) *platform_vaddr_to_uncached(void *p)
+void arch_dma_prep_coherent(struct page *page, size_t size)
 {
-	WARN_ONCE(1, "Default %s implementation is used\n", __func__);
-	return p;
-}
-
-void __attribute__((weak)) *platform_vaddr_to_cached(void *p)
-{
-	WARN_ONCE(1, "Default %s implementation is used\n", __func__);
-	return p;
+	__invalidate_dcache_range((unsigned long)page_address(page), size);
 }
-#endif
 
 /*
- * Note: We assume that the full memory space is always mapped to 'kseg'
- *	 Otherwise we have to use page attributes (not implemented).
+ * Memory caching is platform-dependent in noMMU xtensa configurations.
+ * The following two functions should be implemented in platform code
+ * in order to enable coherent DMA memory operations when CONFIG_MMU is not
+ * enabled.
  */
-
-void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
-		gfp_t flag, unsigned long attrs)
-{
-	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	struct page *page = NULL;
-
-	/* ignore region speicifiers */
-
-	flag &= ~(__GFP_DMA | __GFP_HIGHMEM);
-
-	if (dev == NULL || (dev->coherent_dma_mask < 0xffffffff))
-		flag |= GFP_DMA;
-
-	if (gfpflags_allow_blocking(flag))
-		page = dma_alloc_from_contiguous(dev, count, get_order(size),
-						 flag & __GFP_NOWARN);
-
-	if (!page)
-		page = alloc_pages(flag | __GFP_ZERO, get_order(size));
-
-	if (!page)
-		return NULL;
-
-	*handle = phys_to_dma(dev, page_to_phys(page));
-
 #ifdef CONFIG_MMU
-	if (PageHighMem(page)) {
-		void *p;
-
-		p = dma_common_contiguous_remap(page, size,
-						pgprot_noncached(PAGE_KERNEL),
-						__builtin_return_address(0));
-		if (!p) {
-			if (!dma_release_from_contiguous(dev, page, count))
-				__free_pages(page, get_order(size));
-		}
-		return p;
-	}
-#endif
-	BUG_ON(!platform_vaddr_cached(page_address(page)));
-	__invalidate_dcache_range((unsigned long)page_address(page), size);
-	return platform_vaddr_to_uncached(page_address(page));
+void *uncached_kernel_address(void *p)
+{
+	return p + XCHAL_KSEG_BYPASS_VADDR - XCHAL_KSEG_CACHED_VADDR;
 }
 
-void arch_dma_free(struct device *dev, size_t size, void *vaddr,
-		dma_addr_t dma_handle, unsigned long attrs)
+void *cached_kernel_address(void *p)
 {
-	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	struct page *page;
-
-	if (platform_vaddr_uncached(vaddr)) {
-		page = virt_to_page(platform_vaddr_to_cached(vaddr));
-	} else {
-#ifdef CONFIG_MMU
-		dma_common_free_remap(vaddr, size);
-#endif
-		page = pfn_to_page(PHYS_PFN(dma_to_phys(dev, dma_handle)));
-	}
-
-	if (!dma_release_from_contiguous(dev, page, count))
-		__free_pages(page, get_order(size));
+	return p + XCHAL_KSEG_CACHED_VADDR - XCHAL_KSEG_BYPASS_VADDR;
 }
+#endif /* CONFIG_MMU */