Merge tag 'dma-mapping-5.10' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - rework the non-coherent DMA allocator

 - move private definitions out of <linux/dma-mapping.h>

 - lower CMA_ALIGNMENT (Paul Cercueil)

 - remove the omap1 dma address translation in favor of the common code

 - make dma-direct aware of multiple dma offset ranges (Jim Quinlan)

 - support per-node DMA CMA areas (Barry Song)

 - increase the default seg boundary limit (Nicolin Chen)

 - misc fixes (Robin Murphy, Thomas Tai, Xu Wang)

 - various cleanups

* tag 'dma-mapping-5.10' of git://git.infradead.org/users/hch/dma-mapping: (63 commits)
  ARM/ixp4xx: add a missing include of dma-map-ops.h
  dma-direct: simplify the DMA_ATTR_NO_KERNEL_MAPPING handling
  dma-direct: factor out a dma_direct_alloc_from_pool helper
  dma-direct check for highmem pages in dma_direct_alloc_pages
  dma-mapping: merge <linux/dma-noncoherent.h> into <linux/dma-map-ops.h>
  dma-mapping: move large parts of <linux/dma-direct.h> to kernel/dma
  dma-mapping: move dma-debug.h to kernel/dma/
  dma-mapping: remove <asm/dma-contiguous.h>
  dma-mapping: merge <linux/dma-contiguous.h> into <linux/dma-map-ops.h>
  dma-contiguous: remove dma_contiguous_set_default
  dma-contiguous: remove dev_set_cma_area
  dma-contiguous: remove dma_declare_contiguous
  dma-mapping: split <linux/dma-mapping.h>
  cma: decrease CMA_ALIGNMENT lower limit to 2
  firewire-ohci: use dma_alloc_pages
  dma-iommu: implement ->alloc_noncoherent
  dma-mapping: add new {alloc,free}_noncoherent dma_map_ops methods
  dma-mapping: add a new dma_alloc_pages API
  dma-mapping: remove dma_cache_sync
  53c700: convert to dma_alloc_noncoherent
  ...

88 files changed, 256 insertions, 391 deletions

diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c
index 81037907268d..d84b19aa8e9d 100644
--- a/arch/alpha/kernel/pci_iommu.c
+++ b/arch/alpha/kernel/pci_iommu.c
@@ -11,7 +11,7 @@
 #include <linux/export.h>
 #include <linux/scatterlist.h>
 #include <linux/log2.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/iommu-helper.h>
 
 #include <asm/io.h>
@@ -141,12 +141,7 @@ iommu_arena_find_pages(struct device *dev, struct pci_iommu_arena *arena,
 	unsigned long boundary_size;
 
 	base = arena->dma_base >> PAGE_SHIFT;
-	if (dev) {
-		boundary_size = dma_get_seg_boundary(dev) + 1;
-		boundary_size >>= PAGE_SHIFT;
-	} else {
-		boundary_size = 1UL << (32 - PAGE_SHIFT);
-	}
+	boundary_size = dma_get_seg_boundary_nr_pages(dev, PAGE_SHIFT);
 
 	/* Search forward for the first mask-aligned sequence of N free ptes */
 	ptes = arena->ptes;
@@ -957,5 +952,7 @@ const struct dma_map_ops alpha_pci_ops = {
 	.dma_supported		= alpha_pci_supported,
 	.mmap			= dma_common_mmap,
 	.get_sgtable		= dma_common_get_sgtable,
+	.alloc_pages		= dma_common_alloc_pages,
+	.free_pages		= dma_common_free_pages,
 };
 EXPORT_SYMBOL(alpha_pci_ops);
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index e947572a521e..517988e60cfc 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -3,7 +3,7 @@
  * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
  */
 
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <asm/cache.h>
 #include <asm/cacheflush.h>
 
diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c
index f4b719bde763..7996c04393d5 100644
--- a/arch/arm/common/dmabounce.c
+++ b/arch/arm/common/dmabounce.c
@@ -24,7 +24,8 @@
 #include <linux/slab.h>
 #include <linux/page-flags.h>
 #include <linux/device.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dmapool.h>
 #include <linux/list.h>
 #include <linux/scatterlist.h>
diff --git a/arch/arm/include/asm/dma-contiguous.h b/arch/arm/include/asm/dma-contiguous.h
deleted file mode 100644
index d785187a6f8a..000000000000
--- a/arch/arm/include/asm/dma-contiguous.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef ASMARM_DMA_CONTIGUOUS_H
-#define ASMARM_DMA_CONTIGUOUS_H
-
-#ifdef __KERNEL__
-#ifdef CONFIG_DMA_CMA
-
-#include <linux/types.h>
-
-void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size);
-
-#endif
-#endif
-
-#endif
diff --git a/arch/arm/include/asm/dma-direct.h b/arch/arm/include/asm/dma-direct.h
index 7c3001a6a775..77fcb7ee5ec9 100644
--- a/arch/arm/include/asm/dma-direct.h
+++ b/arch/arm/include/asm/dma-direct.h
@@ -2,13 +2,44 @@
 #ifndef ASM_ARM_DMA_DIRECT_H
 #define ASM_ARM_DMA_DIRECT_H 1
 
-static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+#include <asm/memory.h>
+
+/*
+ * dma_to_pfn/pfn_to_dma/virt_to_dma are architecture private
+ * functions used internally by the DMA-mapping API to provide DMA
+ * addresses. They must not be used by drivers.
+ */
+static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn)
+{
+	if (dev && dev->dma_range_map)
+		pfn = PFN_DOWN(translate_phys_to_dma(dev, PFN_PHYS(pfn)));
+	return (dma_addr_t)__pfn_to_bus(pfn);
+}
+
+static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
+{
+	unsigned long pfn = __bus_to_pfn(addr);
+
+	if (dev && dev->dma_range_map)
+		pfn = PFN_DOWN(translate_dma_to_phys(dev, PFN_PHYS(pfn)));
+	return pfn;
+}
+
+static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)
+{
+	if (dev)
+		return pfn_to_dma(dev, virt_to_pfn(addr));
+
+	return (dma_addr_t)__virt_to_bus((unsigned long)(addr));
+}
+
+static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	unsigned int offset = paddr & ~PAGE_MASK;
 	return pfn_to_dma(dev, __phys_to_pfn(paddr)) + offset;
 }
 
-static inline phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dev_addr)
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr)
 {
 	unsigned int offset = dev_addr & ~PAGE_MASK;
 	return __pfn_to_phys(dma_to_pfn(dev, dev_addr)) + offset;
diff --git a/arch/arm/include/asm/dma-iommu.h b/arch/arm/include/asm/dma-iommu.h
index 86405cc81385..fe9ef6f79e9c 100644
--- a/arch/arm/include/asm/dma-iommu.h
+++ b/arch/arm/include/asm/dma-iommu.h
@@ -6,7 +6,6 @@
 
 #include <linux/mm_types.h>
 #include <linux/scatterlist.h>
-#include <linux/dma-debug.h>
 #include <linux/kref.h>
 
 struct dma_iommu_mapping {
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index bdd80ddbca34..77082246a5e1 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -6,9 +6,6 @@
 
 #include <linux/mm_types.h>
 #include <linux/scatterlist.h>
-#include <linux/dma-debug.h>
-
-#include <asm/memory.h>
 
 #include <xen/xen.h>
 #include <asm/xen/hypervisor.h>
@@ -23,74 +20,6 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 	return NULL;
 }
 
-#ifdef __arch_page_to_dma
-#error Please update to __arch_pfn_to_dma
-#endif
-
-/*
- * dma_to_pfn/pfn_to_dma/dma_to_virt/virt_to_dma are architecture private
- * functions used internally by the DMA-mapping API to provide DMA
- * addresses. They must not be used by drivers.
- */
-#ifndef __arch_pfn_to_dma
-static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn)
-{
-	if (dev)
-		pfn -= dev->dma_pfn_offset;
-	return (dma_addr_t)__pfn_to_bus(pfn);
-}
-
-static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
-{
-	unsigned long pfn = __bus_to_pfn(addr);
-
-	if (dev)
-		pfn += dev->dma_pfn_offset;
-
-	return pfn;
-}
-
-static inline void *dma_to_virt(struct device *dev, dma_addr_t addr)
-{
-	if (dev) {
-		unsigned long pfn = dma_to_pfn(dev, addr);
-
-		return phys_to_virt(__pfn_to_phys(pfn));
-	}
-
-	return (void *)__bus_to_virt((unsigned long)addr);
-}
-
-static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)
-{
-	if (dev)
-		return pfn_to_dma(dev, virt_to_pfn(addr));
-
-	return (dma_addr_t)__virt_to_bus((unsigned long)(addr));
-}
-
-#else
-static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn)
-{
-	return __arch_pfn_to_dma(dev, pfn);
-}
-
-static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
-{
-	return __arch_dma_to_pfn(dev, addr);
-}
-
-static inline void *dma_to_virt(struct device *dev, dma_addr_t addr)
-{
-	return __arch_dma_to_virt(dev, addr);
-}
-
-static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)
-{
-	return __arch_virt_to_dma(dev, addr);
-}
-#endif
-
 /**
  * arm_dma_alloc - allocate consistent memory for DMA
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
diff --git a/arch/arm/mach-davinci/devices-da8xx.c b/arch/arm/mach-davinci/devices-da8xx.c
index feb206bdf6e1..bb368938fc49 100644
--- a/arch/arm/mach-davinci/devices-da8xx.c
+++ b/arch/arm/mach-davinci/devices-da8xx.c
@@ -10,7 +10,7 @@
 #include <linux/clk-provider.h>
 #include <linux/clk.h>
 #include <linux/clkdev.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dmaengine.h>
 #include <linux/init.h>
 #include <linux/io.h>
@@ -884,6 +884,7 @@ early_param("rproc_mem", early_rproc_mem);
 
 void __init da8xx_rproc_reserve_cma(void)
 {
+	struct cma *cma;
 	int ret;
 
 	if (!rproc_base || !rproc_size) {
@@ -897,13 +898,16 @@ void __init da8xx_rproc_reserve_cma(void)
 	pr_info("%s: reserving 0x%lx @ 0x%lx...\n",
 		__func__, rproc_size, (unsigned long)rproc_base);
 
-	ret = dma_declare_contiguous(&da8xx_dsp.dev, rproc_size, rproc_base, 0);
-	if (ret)
-		pr_err("%s: dma_declare_contiguous failed %d\n", __func__, ret);
-	else
-		rproc_mem_inited = true;
+	ret = dma_contiguous_reserve_area(rproc_size, rproc_base, 0, &cma,
+			true);
+	if (ret) {
+		pr_err("%s: dma_contiguous_reserve_area failed %d\n",
+			__func__, ret);
+		return;
+	}
+	da8xx_dsp.dev.cma_area = cma;
+	rproc_mem_inited = true;
 }
-
 #else
 
 void __init da8xx_rproc_reserve_cma(void)
diff --git a/arch/arm/mach-highbank/highbank.c b/arch/arm/mach-highbank/highbank.c
index 56bf29523c65..db607955a7e4 100644
--- a/arch/arm/mach-highbank/highbank.c
+++ b/arch/arm/mach-highbank/highbank.c
@@ -5,7 +5,7 @@
 #include <linux/clk.h>
 #include <linux/clkdev.h>
 #include <linux/clocksource.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/input.h>
 #include <linux/io.h>
 #include <linux/irqchip.h>
diff --git a/arch/arm/mach-imx/mach-imx27_visstrim_m10.c b/arch/arm/mach-imx/mach-imx27_visstrim_m10.c
index 3da4c0920198..a329e50928b6 100644
--- a/arch/arm/mach-imx/mach-imx27_visstrim_m10.c
+++ b/arch/arm/mach-imx/mach-imx27_visstrim_m10.c
@@ -16,7 +16,7 @@
 #include <linux/input.h>
 #include <linux/gpio.h>
 #include <linux/delay.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/leds.h>
 #include <linux/platform_data/asoc-mx27vis.h>
 #include <sound/tlv320aic32x4.h>
diff --git a/arch/arm/mach-imx/mach-mx31moboard.c b/arch/arm/mach-imx/mach-mx31moboard.c
index 96845a4eaf57..7f780ad2d459 100644
--- a/arch/arm/mach-imx/mach-mx31moboard.c
+++ b/arch/arm/mach-imx/mach-mx31moboard.c
@@ -4,7 +4,7 @@
  */
 
 #include <linux/delay.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/gfp.h>
 #include <linux/gpio.h>
 #include <linux/init.h>
diff --git a/arch/arm/mach-ixp4xx/common.c b/arch/arm/mach-ixp4xx/common.c
index 184262d660ba..000f672a94c9 100644
--- a/arch/arm/mach-ixp4xx/common.c
+++ b/arch/arm/mach-ixp4xx/common.c
@@ -29,6 +29,7 @@
 #