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
  ...

14 files changed, 68 insertions, 129 deletions

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 440614dc9de2..c695d103bf6d 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -1136,7 +1136,6 @@ config DMA_NONCOHERENT
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
 	select ARCH_HAS_DMA_SET_UNCACHED
 	select DMA_NONCOHERENT_MMAP
-	select DMA_NONCOHERENT_CACHE_SYNC
 	select NEED_DMA_MAP_STATE
 
 config SYS_HAS_EARLY_PRINTK
diff --git a/arch/mips/bmips/dma.c b/arch/mips/bmips/dma.c
index df56bf4179e3..49061b870680 100644
--- a/arch/mips/bmips/dma.c
+++ b/arch/mips/bmips/dma.c
@@ -40,7 +40,7 @@ static struct bmips_dma_range *bmips_dma_ranges;
 
 #define FLUSH_RAC		0x100
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t pa)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t pa)
 {
 	struct bmips_dma_range *r;
 
@@ -52,7 +52,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t pa)
 	return pa;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	struct bmips_dma_range *r;
 
diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c
index ad1aecc4b401..df70308db0e6 100644
--- a/arch/mips/cavium-octeon/dma-octeon.c
+++ b/arch/mips/cavium-octeon/dma-octeon.c
@@ -168,7 +168,7 @@ void __init octeon_pci_dma_init(void)
 }
 #endif /* CONFIG_PCI */
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 #ifdef CONFIG_PCI
 	if (dev && dev_is_pci(dev))
@@ -177,7 +177,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return paddr;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
 {
 #ifdef CONFIG_PCI
 	if (dev && dev_is_pci(dev))
diff --git a/arch/mips/include/asm/dma-direct.h b/arch/mips/include/asm/dma-direct.h
index 14e352651ce9..9a640118316c 100644
--- a/arch/mips/include/asm/dma-direct.h
+++ b/arch/mips/include/asm/dma-direct.h
@@ -2,7 +2,7 @@
 #ifndef _MIPS_DMA_DIRECT_H
 #define _MIPS_DMA_DIRECT_H 1
 
-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);
+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 /* _MIPS_DMA_DIRECT_H */
diff --git a/arch/mips/include/asm/jazzdma.h b/arch/mips/include/asm/jazzdma.h
index d13f940022d5..c831da7fa898 100644
--- a/arch/mips/include/asm/jazzdma.h
+++ b/arch/mips/include/asm/jazzdma.h
@@ -10,8 +10,6 @@
  */
 extern unsigned long vdma_alloc(unsigned long paddr, unsigned long size);
 extern int vdma_free(unsigned long laddr);
-extern int vdma_remap(unsigned long laddr, unsigned long paddr,
-		      unsigned long size);
 extern unsigned long vdma_phys2log(unsigned long paddr);
 extern unsigned long vdma_log2phys(unsigned long laddr);
 extern void vdma_stats(void);		/* for debugging only */
diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c
index 014773f0bfcd..461457b28982 100644
--- a/arch/mips/jazz/jazzdma.c
+++ b/arch/mips/jazz/jazzdma.c
@@ -16,8 +16,7 @@
 #include <linux/memblock.h>
 #include <linux/spinlock.h>
 #include <linux/gfp.h>
-#include <linux/dma-direct.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <asm/mipsregs.h>
 #include <asm/jazz.h>
 #include <asm/io.h>
@@ -210,76 +209,6 @@ int vdma_free(unsigned long laddr)
 EXPORT_SYMBOL(vdma_free);
 
 /*
- * Map certain page(s) to another physical address.
- * Caller must have allocated the page(s) before.
- */
-int vdma_remap(unsigned long laddr, unsigned long paddr, unsigned long size)
-{
-	int first, pages;
-
-	if (laddr > 0xffffff) {
-		if (vdma_debug)
-			printk
-			    ("vdma_map: Invalid logical address: %08lx\n",
-			     laddr);
-		return -EINVAL; /* invalid logical address */
-	}
-	if (paddr > 0x1fffffff) {
-		if (vdma_debug)
-			printk
-			    ("vdma_map: Invalid physical address: %08lx\n",
-			     paddr);
-		return -EINVAL; /* invalid physical address */
-	}
-
-	pages = (((paddr & (VDMA_PAGESIZE - 1)) + size) >> 12) + 1;
-	first = laddr >> 12;
-	if (vdma_debug)
-		printk("vdma_remap: first=%x, pages=%x\n", first, pages);
-	if (first + pages > VDMA_PGTBL_ENTRIES) {
-		if (vdma_debug)
-			printk("vdma_alloc: Invalid size: %08lx\n", size);
-		return -EINVAL;
-	}
-
-	paddr &= ~(VDMA_PAGESIZE - 1);
-	while (pages > 0 && first < VDMA_PGTBL_ENTRIES) {
-		if (pgtbl[first].owner != laddr) {
-			if (vdma_debug)
-				printk("Trying to remap other's pages.\n");
-			return -EPERM;	/* not owner */
-		}
-		pgtbl[first].frame = paddr;
-		paddr += VDMA_PAGESIZE;
-		first++;
-		pages--;
-	}
-
-	/*
-	 * Update translation table
-	 */
-	r4030_write_reg32(JAZZ_R4030_TRSTBL_INV, 0);
-
-	if (vdma_debug > 2) {
-		int i;
-		pages = (((paddr & (VDMA_PAGESIZE - 1)) + size) >> 12) + 1;
-		first = laddr >> 12;
-		printk("LADDR: ");
-		for (i = first; i < first + pages; i++)
-			printk("%08x ", i << 12);
-		printk("\nPADDR: ");
-		for (i = first; i < first + pages; i++)
-			printk("%08x ", pgtbl[i].frame);
-		printk("\nOWNER: ");
-		for (i = first; i < first + pages; i++)
-			printk("%08x ", pgtbl[i].owner);
-		printk("\n");
-	}
-
-	return 0;
-}
-
-/*
  * Translate a physical address to a logical address.
  * This will return the logical address of the first
  * match.
@@ -562,26 +491,34 @@ int vdma_get_enable(int channel)
 static void *jazz_dma_alloc(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
 {
+	struct page *page;
 	void *ret;
 
-	ret = dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs);
-	if (!ret)
-		return NULL;
+	if (attrs & DMA_ATTR_NO_WARN)
+		gfp |= __GFP_NOWARN;
 
-	*dma_handle = vdma_alloc(virt_to_phys(ret), size);
-	if (*dma_handle == DMA_MAPPING_ERROR) {
-		dma_direct_free_pages(dev, size, ret, *dma_handle, attrs);
+	size = PAGE_ALIGN(size);
+	page = alloc_pages(gfp, get_order(size));
+	if (!page)
 		return NULL;
-	}
-
-	return ret;
+	ret = page_address(page);
+	memset(ret, 0, size);
+	*dma_handle = vdma_alloc(virt_to_phys(ret), size);
+	if (*dma_handle == DMA_MAPPING_ERROR)
+		goto out_free_pages;
+	arch_dma_prep_coherent(page, size);
+	return (void *)(UNCAC_BASE + __pa(ret));
+
+out_free_pages:
+	__free_pages(page, get_order(size));
+	return NULL;
 }
 
 static void jazz_dma_free(struct device *dev, size_t size, void *vaddr,
 		dma_addr_t dma_handle, unsigned long attrs)
 {
 	vdma_free(dma_handle);
-	dma_direct_free_pages(dev, size, vaddr, dma_handle, attrs);
+	__free_pages(virt_to_page(vaddr), get_order(size));
 }
 
 static dma_addr_t jazz_dma_map_page(struct device *dev, struct page *page,
@@ -678,9 +615,9 @@ const struct dma_map_ops jazz_dma_ops = {
 	.sync_single_for_device	= jazz_dma_sync_single_for_device,
 	.sync_sg_for_cpu	= jazz_dma_sync_sg_for_cpu,
 	.sync_sg_for_device	= jazz_dma_sync_sg_for_device,
-	.dma_supported		= dma_direct_supported,
-	.cache_sync		= arch_dma_cache_sync,
 	.mmap			= dma_common_mmap,
 	.get_sgtable		= dma_common_get_sgtable,
+	.alloc_pages		= dma_common_alloc_pages,
+	.free_pages		= dma_common_free_pages,
 };
 EXPORT_SYMBOL(jazz_dma_ops);
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 335bd188b8b4..ee8636ccded2 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -24,7 +24,7 @@
 #include <linux/kexec.h>
 #include <linux/sizes.h>
 #include <linux/device.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/decompress/generic.h>
 #include <linux/of_fdt.h>
 #include <linux/of_reserved_mem.h>
diff --git a/arch/mips/loongson2ef/fuloong-2e/dma.c b/arch/mips/loongson2ef/fuloong-2e/dma.c
index e122292bf666..cea167d8aba8 100644
--- a/arch/mips/loongson2ef/fuloong-2e/dma.c
+++ b/arch/mips/loongson2ef/fuloong-2e/dma.c
@@ -1,12 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/dma-direct.h>
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	return paddr | 0x80000000;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	return dma_addr & 0x7fffffff;
 }
diff --git a/arch/mips/loongson2ef/lemote-2f/dma.c b/arch/mips/loongson2ef/lemote-2f/dma.c
index abf0e39d7e46..3c9e99456357 100644
--- a/arch/mips/loongson2ef/lemote-2f/dma.c
+++ b/arch/mips/loongson2ef/lemote-2f/dma.c
@@ -1,12 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/dma-direct.h>
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	return paddr | 0x80000000;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	if (dma_addr > 0x8fffffff)
 		return dma_addr;
diff --git a/arch/mips/loongson64/dma.c b/arch/mips/loongson64/dma.c
index dbfe6e82fddd..364f2f27c872 100644
--- a/arch/mips/loongson64/dma.c
+++ b/arch/mips/loongson64/dma.c
@@ -4,7 +4,7 @@
 #include <linux/swiotlb.h>
 #include <boot_param.h>
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	/* We extract 2bit node id (bit 44~47, only bit 44~45 used now) from
 	 * Loongson-3's 48bit address space and embed it into 40bit */
@@ -13,7 +13,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return ((nid << 44) ^ paddr) | (nid << node_id_offset);
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
 {
 	/* We extract 2bit node id (bit 44~47, only bit 44~45 used now) from
 	 * Loongson-3's 48bit address space and embed it into 40bit */
diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c
index 563c2c0d0c81..38d3d9143b47 100644
--- a/arch/mips/mm/dma-noncoherent.c
+++ b/arch/mips/mm/dma-noncoherent.c
@@ -5,8 +5,7 @@
  * swiped from i386, and cloned for MIPS by Geert, polished by Ralf.
  */
 #include <linux/dma-direct.h>
-#include <linux/dma-noncoherent.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/highmem.h>
 
 #include <asm/cache.h>
@@ -55,22 +54,34 @@ void *arch_dma_set_uncached(void *addr, size_t size)
 	return (void *)(__pa(addr) + UNCAC_BASE);
 }
 
-static inline void dma_sync_virt(void *addr, size_t size,
+static inline void dma_sync_virt_for_device(void *addr, size_t size,
 		enum dma_data_direction dir)
 {
 	switch (dir) {
 	case DMA_TO_DEVICE:
 		dma_cache_wback((unsigned long)addr, size);
 		break;
-
 	case DMA_FROM_DEVICE:
 		dma_cache_inv((unsigned long)addr, size);
 		break;
-
 	case DMA_BIDIRECTIONAL:
 		dma_cache_wback_inv((unsigned long)addr, size);
 		break;
+	default:
+		BUG();
+	}
+}
 
+static inline void dma_sync_virt_for_cpu(void *addr, size_t size,
+		enum dma_data_direction dir)
+{
+	switch (dir) {
+	case DMA_TO_DEVICE:
+		break;
+	case DMA_FROM_DEVICE:
+	case DMA_BIDIRECTIONAL:
+		dma_cache_inv((unsigned long)addr, size);
+		break;
 	default:
 		BUG();
 	}
@@ -82,7 +93,7 @@ static inline void dma_sync_virt(void *addr, size_t size,
  * configured then the bulk of this loop gets optimized out.
  */
 static inline void dma_sync_phys(phys_addr_t paddr, size_t size,
-		enum dma_data_direction dir)
+		enum dma_data_direction dir, bool for_device)
 {
 	struct page *page = pfn_to_page(paddr >> PAGE_SHIFT);
 	unsigned long offset = paddr & ~PAGE_MASK;
@@ -90,18 +101,20 @@ static inline void dma_sync_phys(phys_addr_t paddr, size_t size,
 
 	do {
 		size_t len = left;
+		void *addr;
 
 		if (PageHighMem(page)) {
-			void *addr;
-
 			if (offset + len > PAGE_SIZE)
 				len = PAGE_SIZE - offset;
+		}
+
+		addr = kmap_atomic(page);
+		if (for_device)
+			dma_sync_virt_for_device(addr + offset, len, dir);
+		else
+			dma_sync_virt_for_cpu(addr + offset, len, dir);
+		kunmap_atomic(addr);
 
-			addr = kmap_atomic(page);
-			dma_sync_virt(addr + offset, len, dir);
-			kunmap_atomic(addr);
-		} else
-			dma_sync_virt(page_address(page) + offset, size, dir);
 		offset = 0;
 		page++;
 		left -= len;
@@ -111,7 +124,7 @@ static inline void dma_sync_phys(phys_addr_t paddr, size_t size,
 void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
 		enum dma_data_direction dir)
 {
-	dma_sync_phys(paddr, size, dir);
+	dma_sync_phys(paddr, size, dir, true);
 }
 
 #ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
@@ -119,18 +132,10 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
 		enum dma_data_direction dir)
 {
 	if (cpu_needs_post_dma_flush())
-		dma_sync_phys(paddr, size, dir);
+		dma_sync_phys(paddr, size, dir, false);
 }
 #endif
 
-void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-		enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-
-	dma_sync_virt(vaddr, size, direction);
-}
-
 #ifdef CONFIG_DMA_PERDEV_COHERENT
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 		const struct iommu_ops *iommu, bool coherent)
diff --git a/arch/mips/pci/pci-ar2315.c b/arch/mips/pci/pci-ar2315.c
index 490953f51528..cef4a47ab063 100644
--- a/arch/mips/pci/pci-ar2315.c
+++ b/arch/mips/pci/pci-ar2315.c
@@ -170,12 +170,12 @@ static inline dma_addr_t ar2315_dev_offset(struct device *dev)
 	return 0;
 }
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	return paddr + ar2315_dev_offset(dev);
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	return dma_addr - ar2315_dev_offset(dev);
 }
diff --git a/arch/mips/pci/pci-xtalk-bridge.c b/arch/mips/pci/pci-xtalk-bridge.c
index 9b3cc775c55e..50f7d42cca5a 100644
--- a/arch/mips/pci/pci-xtalk-bridge.c
+++ b/arch/mips/pci/pci-xtalk-bridge.c
@@ -25,7 +25,7 @@
 /*
  * Common phys<->dma mapping for platforms using pci xtalk bridge
  */
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct bridge_controller *bc = BRIDGE_CONTROLLER(pdev->bus);
@@ -33,7 +33,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return bc->baddr + paddr;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	return dma_addr & ~(0xffUL << 56);
 }
diff --git a/arch/mips/sgi-ip32/ip32-dma.c b/arch/mips/sgi-ip32/ip32-dma.c
index fa7b17cb5385..20c6da9d76bc 100644
--- a/arch/mips/sgi-ip32/ip32-dma.c
+++ b/arch/mips/sgi-ip32/ip32-dma.c
@@ -18,7 +18,7 @@
 
 #define RAM_OFFSET_MASK 0x3fffffffUL
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	dma_addr_t dma_addr = paddr & RAM_OFFSET_MASK;
 
@@ -27,7 +27,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return dma_addr;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	phys_addr_t paddr = dma_addr & RAM_OFFSET_MASK;