Merge tag 'dma-mapping-4.21' of git://git.infradead.org/users/hch/dma-mapping

Pull DMA mapping updates from Christoph Hellwig:
 "A huge update this time, but a lot of that is just consolidating or
  removing code:

   - provide a common DMA_MAPPING_ERROR definition and avoid indirect
     calls for dma_map_* error checking

   - use direct calls for the DMA direct mapping case, avoiding huge
     retpoline overhead for high performance workloads

   - merge the swiotlb dma_map_ops into dma-direct

   - provide a generic remapping DMA consistent allocator for
     architectures that have devices that perform DMA that is not cache
     coherent. Based on the existing arm64 implementation and also used
     for csky now.

   - improve the dma-debug infrastructure, including dynamic allocation
     of entries (Robin Murphy)

   - default to providing chaining scatterlist everywhere, with opt-outs
     for the few architectures (alpha, parisc, most arm32 variants) that
     can't cope with it

   - misc sparc32 dma-related cleanups

   - remove the dma_mark_clean arch hook used by swiotlb on ia64 and
     replace it with the generic noncoherent infrastructure

   - fix the return type of dma_set_max_seg_size (Niklas Söderlund)

   - move the dummy dma ops for not DMA capable devices from arm64 to
     common code (Robin Murphy)

   - ensure dma_alloc_coherent returns zeroed memory to avoid kernel
     data leaks through userspace. We already did this for most common
     architectures, but this ensures we do it everywhere.
     dma_zalloc_coherent has been deprecated and can hopefully be
     removed after -rc1 with a coccinelle script"

* tag 'dma-mapping-4.21' of git://git.infradead.org/users/hch/dma-mapping: (73 commits)
  dma-mapping: fix inverted logic in dma_supported
  dma-mapping: deprecate dma_zalloc_coherent
  dma-mapping: zero memory returned from dma_alloc_*
  sparc/iommu: fix ->map_sg return value
  sparc/io-unit: fix ->map_sg return value
  arm64: default to the direct mapping in get_arch_dma_ops
  PCI: Remove unused attr variable in pci_dma_configure
  ia64: only select ARCH_HAS_DMA_COHERENT_TO_PFN if swiotlb is enabled
  dma-mapping: bypass indirect calls for dma-direct
  vmd: use the proper dma_* APIs instead of direct methods calls
  dma-direct: merge swiotlb_dma_ops into the dma_direct code
  dma-direct: use dma_direct_map_page to implement dma_direct_map_sg
  dma-direct: improve addressability error reporting
  swiotlb: remove dma_mark_clean
  swiotlb: remove SWIOTLB_MAP_ERROR
  ACPI / scan: Refactor _CCA enforcement
  dma-mapping: factor out dummy DMA ops
  dma-mapping: always build the direct mapping code
  dma-mapping: move dma_cache_sync out of line
  dma-mapping: move various slow path functions out of line
  ...

7 files changed, 15 insertions, 94 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index c7094f813183..57552f2b37eb 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -66,7 +66,6 @@ config X86
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if X86_64
 	select ARCH_HAS_UACCESS_MCSAFE		if X86_64 && X86_MCE
 	select ARCH_HAS_SET_MEMORY
-	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_HAS_STRICT_MODULE_RWX
 	select ARCH_HAS_SYNC_CORE_BEFORE_USERMODE
@@ -90,7 +89,6 @@ config X86
 	select CLOCKSOURCE_VALIDATE_LAST_CYCLE
 	select CLOCKSOURCE_WATCHDOG
 	select DCACHE_WORD_ACCESS
-	select DMA_DIRECT_OPS
 	select EDAC_ATOMIC_SCRUB
 	select EDAC_SUPPORT
 	select GENERIC_CLOCKEVENTS
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index 3f9d1b4019bb..e0ff3ac8c127 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -50,8 +50,6 @@ static unsigned long iommu_pages;	/* .. and in pages */
 
 static u32 *iommu_gatt_base;		/* Remapping table */
 
-static dma_addr_t bad_dma_addr;
-
 /*
  * If this is disabled the IOMMU will use an optimized flushing strategy
  * of only flushing when an mapping is reused. With it true the GART is
@@ -74,8 +72,6 @@ static u32 gart_unmapped_entry;
 	(((x) & 0xfffff000) | (((x) >> 32) << 4) | GPTE_VALID | GPTE_COHERENT)
 #define GPTE_DECODE(x) (((x) & 0xfffff000) | (((u64)(x) & 0xff0) << 28))
 
-#define EMERGENCY_PAGES 32 /* = 128KB */
-
 #ifdef CONFIG_AGP
 #define AGPEXTERN extern
 #else
@@ -155,9 +151,6 @@ static void flush_gart(void)
 
 #ifdef CONFIG_IOMMU_LEAK
 /* Debugging aid for drivers that don't free their IOMMU tables */
-static int leak_trace;
-static int iommu_leak_pages = 20;
-
 static void dump_leak(void)
 {
 	static int dump;
@@ -184,14 +177,6 @@ static void iommu_full(struct device *dev, size_t size, int dir)
 	 */
 
 	dev_err(dev, "PCI-DMA: Out of IOMMU space for %lu bytes\n", size);
-
-	if (size > PAGE_SIZE*EMERGENCY_PAGES) {
-		if (dir == PCI_DMA_FROMDEVICE || dir == PCI_DMA_BIDIRECTIONAL)
-			panic("PCI-DMA: Memory would be corrupted\n");
-		if (dir == PCI_DMA_TODEVICE || dir == PCI_DMA_BIDIRECTIONAL)
-			panic(KERN_ERR
-				"PCI-DMA: Random memory would be DMAed\n");
-	}
 #ifdef CONFIG_IOMMU_LEAK
 	dump_leak();
 #endif
@@ -220,7 +205,7 @@ static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem,
 	int i;
 
 	if (unlikely(phys_mem + size > GART_MAX_PHYS_ADDR))
-		return bad_dma_addr;
+		return DMA_MAPPING_ERROR;
 
 	iommu_page = alloc_iommu(dev, npages, align_mask);
 	if (iommu_page == -1) {
@@ -229,7 +214,7 @@ static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem,
 		if (panic_on_overflow)
 			panic("dma_map_area overflow %lu bytes\n", size);
 		iommu_full(dev, size, dir);
-		return bad_dma_addr;
+		return DMA_MAPPING_ERROR;
 	}
 
 	for (i = 0; i < npages; i++) {
@@ -271,7 +256,7 @@ static void gart_unmap_page(struct device *dev, dma_addr_t dma_addr,
 	int npages;
 	int i;
 
-	if (dma_addr < iommu_bus_base + EMERGENCY_PAGES*PAGE_SIZE ||
+	if (dma_addr == DMA_MAPPING_ERROR ||
 	    dma_addr >= iommu_bus_base + iommu_size)
 		return;
 
@@ -315,7 +300,7 @@ static int dma_map_sg_nonforce(struct device *dev, struct scatterlist *sg,
 
 		if (nonforced_iommu(dev, addr, s->length)) {
 			addr = dma_map_area(dev, addr, s->length, dir, 0);
-			if (addr == bad_dma_addr) {
+			if (addr == DMA_MAPPING_ERROR) {
 				if (i > 0)
 					gart_unmap_sg(dev, sg, i, dir, 0);
 				nents = 0;
@@ -471,7 +456,7 @@ error:
 
 	iommu_full(dev, pages << PAGE_SHIFT, dir);
 	for_each_sg(sg, s, nents, i)
-		s->dma_address = bad_dma_addr;
+		s->dma_address = DMA_MAPPING_ERROR;
 	return 0;
 }
 
@@ -490,7 +475,7 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
 	*dma_addr = dma_map_area(dev, virt_to_phys(vaddr), size,
 			DMA_BIDIRECTIONAL, (1UL << get_order(size)) - 1);
 	flush_gart();
-	if (unlikely(*dma_addr == bad_dma_addr))
+	if (unlikely(*dma_addr == DMA_MAPPING_ERROR))
 		goto out_free;
 	return vaddr;
 out_free:
@@ -507,11 +492,6 @@ gart_free_coherent(struct device *dev, size_t size, void *vaddr,
 	dma_direct_free_pages(dev, size, vaddr, dma_addr, attrs);
 }
 
-static int gart_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return (dma_addr == bad_dma_addr);
-}
-
 static int no_agp;
 
 static __init unsigned long check_iommu_size(unsigned long aper, u64 aper_size)
@@ -695,7 +675,6 @@ static const struct dma_map_ops gart_dma_ops = {
 	.unmap_page			= gart_unmap_page,
 	.alloc				= gart_alloc_coherent,
 	.free				= gart_free_coherent,
-	.mapping_error			= gart_mapping_error,
 	.dma_supported			= dma_direct_supported,
 };
 
@@ -730,7 +709,6 @@ int __init gart_iommu_init(void)
 	unsigned long aper_base, aper_size;
 	unsigned long start_pfn, end_pfn;
 	unsigned long scratch;
-	long i;
 
 	if (!amd_nb_has_feature(AMD_NB_GART))
 		return 0;
@@ -774,29 +752,12 @@ int __init gart_iommu_init(void)
 	if (!iommu_gart_bitmap)
 		panic("Cannot allocate iommu bitmap\n");
 
-#ifdef CONFIG_IOMMU_LEAK
-	if (leak_trace) {
-		int ret;
-
-		ret = dma_debug_resize_entries(iommu_pages);
-		if (ret)
-			pr_debug("PCI-DMA: Cannot trace all the entries\n");
-	}
-#endif
-
-	/*
-	 * Out of IOMMU space handling.
-	 * Reserve some invalid pages at the beginning of the GART.
-	 */
-	bitmap_set(iommu_gart_bitmap, 0, EMERGENCY_PAGES);
-
 	pr_info("PCI-DMA: Reserving %luMB of IOMMU area in the AGP aperture\n",
 	       iommu_size >> 20);
 
 	agp_memory_reserved	= iommu_size;
 	iommu_start		= aper_size - iommu_size;
 	iommu_bus_base		= info.aper_base + iommu_start;
-	bad_dma_addr		= iommu_bus_base;
 	iommu_gatt_base		= agp_gatt_table + (iommu_start>>PAGE_SHIFT);
 
 	/*
@@ -838,8 +799,6 @@ int __init gart_iommu_init(void)
 	if (!scratch)
 		panic("Cannot allocate iommu scratch page");
 	gart_unmapped_entry = GPTE_ENCODE(__pa(scratch));
-	for (i = EMERGENCY_PAGES; i < iommu_pages; i++)
-		iommu_gatt_base[i] = gart_unmapped_entry;
 
 	flush_gart();
 	dma_ops = &gart_dma_ops;
@@ -853,16 +812,6 @@ void __init gart_parse_options(char *p)
 {
 	int arg;
 
-#ifdef CONFIG_IOMMU_LEAK
-	if (!strncmp(p, "leak", 4)) {
-		leak_trace = 1;
-		p += 4;
-		if (*p == '=')
-			++p;
-		if (isdigit(*p) && get_option(&p, &arg))
-			iommu_leak_pages = arg;
-	}
-#endif
 	if (isdigit(*p) && get_option(&p, &arg))
 		iommu_size = arg;
 	if (!strncmp(p, "fullflush", 9))
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index bbfc8b1e9104..c70720f61a34 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -51,8 +51,6 @@
 #include <asm/x86_init.h>
 #include <asm/iommu_table.h>
 
-#define CALGARY_MAPPING_ERROR	0
-
 #ifdef CONFIG_CALGARY_IOMMU_ENABLED_BY_DEFAULT
 int use_calgary __read_mostly = 1;
 #else
@@ -157,8 +155,6 @@ static const unsigned long phb_debug_offsets[] = {
 
 #define PHB_DEBUG_STUFF_OFFSET	0x0020
 
-#define EMERGENCY_PAGES 32 /* = 128KB */
-
 unsigned int specified_table_size = TCE_TABLE_SIZE_UNSPECIFIED;
 static int translate_empty_slots __read_mostly = 0;
 static int calgary_detected __read_mostly = 0;
@@ -255,7 +251,7 @@ static unsigned long iommu_range_alloc(struct device *dev,
 			if (panic_on_overflow)
 				panic("Calgary: fix the allocator.\n");
 			else
-				return CALGARY_MAPPING_ERROR;
+				return DMA_MAPPING_ERROR;
 		}
 	}
 
@@ -274,11 +270,10 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
 	dma_addr_t ret;
 
 	entry = iommu_range_alloc(dev, tbl, npages);
-
-	if (unlikely(entry == CALGARY_MAPPING_ERROR)) {
+	if (unlikely(entry == DMA_MAPPING_ERROR)) {
 		pr_warn("failed to allocate %u pages in iommu %p\n",
 			npages, tbl);
-		return CALGARY_MAPPING_ERROR;
+		return DMA_MAPPING_ERROR;
 	}
 
 	/* set the return dma address */
@@ -294,12 +289,10 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
 	unsigned int npages)
 {
 	unsigned long entry;
-	unsigned long badend;
 	unsigned long flags;
 
 	/* were we called with bad_dma_address? */
-	badend = CALGARY_MAPPING_ERROR + (EMERGENCY_PAGES * PAGE_SIZE);
-	if (unlikely(dma_addr < badend)) {
+	if (unlikely(dma_addr == DMA_MAPPING_ERROR)) {
 		WARN(1, KERN_ERR "Calgary: driver tried unmapping bad DMA "
 		       "address 0x%Lx\n", dma_addr);
 		return;
@@ -383,7 +376,7 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg,
 		npages = iommu_num_pages(vaddr, s->length, PAGE_SIZE);
 
 		entry = iommu_range_alloc(dev, tbl, npages);
-		if (entry == CALGARY_MAPPING_ERROR) {
+		if (entry == DMA_MAPPING_ERROR) {
 			/* makes sure unmap knows to stop */
 			s->dma_length = 0;
 			goto error;
@@ -401,7 +394,7 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg,
 error:
 	calgary_unmap_sg(dev, sg, nelems, dir, 0);
 	for_each_sg(sg, s, nelems, i) {
-		sg->dma_address = CALGARY_MAPPING_ERROR;
+		sg->dma_address = DMA_MAPPING_ERROR;
 		sg->dma_length = 0;
 	}
 	return 0;
@@ -454,7 +447,7 @@ static void* calgary_alloc_coherent(struct device *dev, size_t size,
 
 	/* set up tces to cover the allocated range */
 	mapping = iommu_alloc(dev, tbl, ret, npages, DMA_BIDIRECTIONAL);
-	if (mapping == CALGARY_MAPPING_ERROR)
+	if (mapping == DMA_MAPPING_ERROR)
 		goto free;
 	*dma_handle = mapping;
 	return ret;
@@ -479,11 +472,6 @@ static void calgary_free_coherent(struct device *dev, size_t size,
 	free_pages((unsigned long)vaddr, get_order(size));
 }
 
-static int calgary_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return dma_addr == CALGARY_MAPPING_ERROR;
-}
-
 static const struct dma_map_ops calgary_dma_ops = {
 	.alloc = calgary_alloc_coherent,
 	.free = calgary_free_coherent,
@@ -491,7 +479,6 @@ static const struct dma_map_ops calgary_dma_ops = {
 	.unmap_sg = calgary_unmap_sg,
 	.map_page = calgary_map_page,
 	.unmap_page = calgary_unmap_page,
-	.mapping_error = calgary_mapping_error,
 	.dma_supported = dma_direct_supported,
 };
 
@@ -739,9 +726,6 @@ static void __init calgary_reserve_regions(struct pci_dev *dev)
 	u64 start;
 	struct iommu_table *tbl = pci_iommu(dev->bus);
 
-	/* reserve EMERGENCY_PAGES from bad_dma_address and up */
-	iommu_range_reserve(tbl, CALGARY_MAPPING_ERROR, EMERGENCY_PAGES);
-
 	/* avoid the BIOS/VGA first 640KB-1MB region */
 	/* for CalIOC2 - avoid the entire first MB */
 	if (is_calgary(dev->device)) {
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index f4562fcec681..d460998ae828 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -17,7 +17,7 @@
 
 static bool disable_dac_quirk __read_mostly;
 
-const struct dma_map_ops *dma_ops = &dma_direct_ops;
+const struct dma_map_ops *dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
 #ifdef CONFIG_IOMMU_DEBUG
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index bd08b9e1c9e2..5f5302028a9a 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -62,10 +62,8 @@ IOMMU_INIT(pci_swiotlb_detect_4gb,
 
 void __init pci_swiotlb_init(void)
 {
-	if (swiotlb) {
+	if (swiotlb)
 		swiotlb_init(0);
-		dma_ops = &swiotlb_dma_ops;
-	}
 }
 
 void __init pci_swiotlb_late_init(void)
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 006f373f54ab..385afa2b9e17 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -381,13 +381,6 @@ void __init mem_encrypt_init(void)
 	swiotlb_update_mem_attributes();
 
 	/*
-	 * With SEV, DMA operations cannot use encryption, we need to use
-	 * SWIOTLB to bounce buffer DMA operation.
-	 */
-	if (sev_active())
-		dma_ops = &swiotlb_dma_ops;
-
-	/*
 	 * With SEV, we need to unroll the rep string I/O instructions.
 	 */
 	if (sev_active())
diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
index 7a5bafb76d77..3cdafea55ab6 100644
--- a/arch/x86/pci/sta2x11-fixup.c
+++ b/arch/x86/pci/sta2x11-fixup.c
@@ -168,7 +168,6 @@ static void sta2x11_setup_pdev(struct pci_dev *pdev)
 		return;
 	pci_set_consistent_dma_mask(pdev, STA2X11_AMBA_SIZE - 1);
 	pci_set_dma_mask(pdev, STA2X11_AMBA_SIZE - 1);
-	pdev->dev.dma_ops = &swiotlb_dma_ops;
 	pdev->dev.archdata.is_sta2x11 = true;
 
 	/* We must enable all devices as master, for audio DMA to work */