1 files changed, 110 insertions, 244 deletions

diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 87d4d6964ec..a25e202bb31 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -1,17 +1,23 @@
 #include <linux/dma-mapping.h>
+#include <linux/dma-debug.h>
 #include <linux/dmar.h>
+#include <linux/export.h>
 #include <linux/bootmem.h>
+#include <linux/gfp.h>
 #include <linux/pci.h>
+#include <linux/kmemleak.h>
 
 #include <asm/proto.h>
 #include <asm/dma.h>
 #include <asm/iommu.h>
+#include <asm/gart.h>
 #include <asm/calgary.h>
-#include <asm/amd_iommu.h>
+#include <asm/x86_init.h>
+#include <asm/iommu_table.h>
 
 static int forbid_dac __read_mostly;
 
-struct dma_mapping_ops *dma_ops;
+struct dma_map_ops *dma_ops = &nommu_dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
 static int iommu_sac_force __read_mostly;
@@ -30,22 +36,27 @@ int no_iommu __read_mostly;
 /* Set this to 1 if there is a HW IOMMU in the system */
 int iommu_detected __read_mostly = 0;
 
-/* This tells the BIO block layer to assume merging. Default to off
-   because we cannot guarantee merging later. */
-int iommu_bio_merge __read_mostly = 0;
-EXPORT_SYMBOL(iommu_bio_merge);
-
-dma_addr_t bad_dma_address __read_mostly = 0;
-EXPORT_SYMBOL(bad_dma_address);
-
-/* Dummy device used for NULL arguments (normally ISA). Better would
-   be probably a smaller DMA mask, but this is bug-to-bug compatible
-   to older i386. */
-struct device fallback_dev = {
-	.bus_id = "fallback device",
-	.coherent_dma_mask = DMA_32BIT_MASK,
-	.dma_mask = &fallback_dev.coherent_dma_mask,
+/*
+ * This variable becomes 1 if iommu=pt is passed on the kernel command line.
+ * If this variable is 1, IOMMU implementations do no DMA translation for
+ * devices and allow every device to access to whole physical memory. This is
+ * useful if a user wants to use an IOMMU only for KVM device assignment to
+ * guests and not for driver dma translation.
+ */
+int iommu_pass_through __read_mostly;
+
+extern struct iommu_table_entry __iommu_table[], __iommu_table_end[];
+
+/* Dummy device used for NULL arguments (normally ISA). */
+struct device x86_dma_fallback_dev = {
+	.init_name = "fallback device",
+	.coherent_dma_mask = ISA_DMA_BIT_MASK,
+	.dma_mask = &x86_dma_fallback_dev.coherent_dma_mask,
 };
+EXPORT_SYMBOL(x86_dma_fallback_dev);
+
+/* Number of entries preallocated for DMA-API debugging */
+#define PREALLOC_DMA_DEBUG_ENTRIES       65536
 
 int dma_set_mask(struct device *dev, u64 mask)
 {
@@ -58,84 +69,80 @@ int dma_set_mask(struct device *dev, u64 mask)
 }
 EXPORT_SYMBOL(dma_set_mask);
 
-#ifdef CONFIG_X86_64
-static __initdata void *dma32_bootmem_ptr;
-static unsigned long dma32_bootmem_size __initdata = (128ULL<<20);
-
-static int __init parse_dma32_size_opt(char *p)
-{
-	if (!p)
-		return -EINVAL;
-	dma32_bootmem_size = memparse(p, &p);
-	return 0;
-}
-early_param("dma32_size", parse_dma32_size_opt);
-
-void __init dma32_reserve_bootmem(void)
-{
-	unsigned long size, align;
-	if (max_pfn <= MAX_DMA32_PFN)
-		return;
-
-	/*
-	 * check aperture_64.c allocate_aperture() for reason about
-	 * using 512M as goal
-	 */
-	align = 64ULL<<20;
-	size = round_up(dma32_bootmem_size, align);
-	dma32_bootmem_ptr = __alloc_bootmem_nopanic(size, align,
-				 512ULL<<20);
-	if (dma32_bootmem_ptr)
-		dma32_bootmem_size = size;
-	else
-		dma32_bootmem_size = 0;
-}
-static void __init dma32_free_bootmem(void)
+void __init pci_iommu_alloc(void)
 {
-
-	if (max_pfn <= MAX_DMA32_PFN)
-		return;
-
-	if (!dma32_bootmem_ptr)
-		return;
-
-	free_bootmem(__pa(dma32_bootmem_ptr), dma32_bootmem_size);
-
-	dma32_bootmem_ptr = NULL;
-	dma32_bootmem_size = 0;
+	struct iommu_table_entry *p;
+
+	sort_iommu_table(__iommu_table, __iommu_table_end);
+	check_iommu_entries(__iommu_table, __iommu_table_end);
+
+	for (p = __iommu_table; p < __iommu_table_end; p++) {
+		if (p && p->detect && p->detect() > 0) {
+			p->flags |= IOMMU_DETECTED;
+			if (p->early_init)
+				p->early_init();
+			if (p->flags & IOMMU_FINISH_IF_DETECTED)
+				break;
+		}
+	}
 }
-
-void __init pci_iommu_alloc(void)
+void *dma_generic_alloc_coherent(struct device *dev, size_t size,
+				 dma_addr_t *dma_addr, gfp_t flag,
+				 struct dma_attrs *attrs)
 {
-	/* free the range so iommu could get some range less than 4G */
-	dma32_free_bootmem();
-	/*
-	 * The order of these functions is important for
-	 * fall-back/fail-over reasons
-	 */
-	gart_iommu_hole_init();
-
-	detect_calgary();
+	unsigned long dma_mask;
+	struct page *page;
+	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	dma_addr_t addr;
+
+	dma_mask = dma_alloc_coherent_mask(dev, flag);
+
+	flag &= ~__GFP_ZERO;
+again:
+	page = NULL;
+	/* CMA can be used only in the context which permits sleeping */
+	if (flag & __GFP_WAIT) {
+		page = dma_alloc_from_contiguous(dev, count, get_order(size));
+		if (page && page_to_phys(page) + size > dma_mask) {
+			dma_release_from_contiguous(dev, page, count);
+			page = NULL;
+		}
+	}
+	/* fallback */
+	if (!page)
+		page = alloc_pages_node(dev_to_node(dev), flag, get_order(size));
+	if (!page)
+		return NULL;
 
-	detect_intel_iommu();
+	addr = page_to_phys(page);
+	if (addr + size > dma_mask) {
+		__free_pages(page, get_order(size));
 
-	amd_iommu_detect();
+		if (dma_mask < DMA_BIT_MASK(32) && !(flag & GFP_DMA)) {
+			flag = (flag & ~GFP_DMA32) | GFP_DMA;
+			goto again;
+		}
 
-	pci_swiotlb_init();
+		return NULL;
+	}
+	memset(page_address(page), 0, size);
+	*dma_addr = addr;
+	return page_address(page);
 }
 
-unsigned long iommu_num_pages(unsigned long addr, unsigned long len)
+void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr,
+			       dma_addr_t dma_addr, struct dma_attrs *attrs)
 {
-	unsigned long size = roundup((addr & ~PAGE_MASK) + len, PAGE_SIZE);
+	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	struct page *page = virt_to_page(vaddr);
 
-	return size >> PAGE_SHIFT;
+	if (!dma_release_from_contiguous(dev, page, count))
+		free_pages((unsigned long)vaddr, get_order(size));
 }
-EXPORT_SYMBOL(iommu_num_pages);
-#endif
 
 /*
- * See <Documentation/x86_64/boot-options.txt> for the iommu kernel parameter
- * documentation.
+ * See <Documentation/x86/x86_64/boot-options.txt> for the iommu kernel
+ * parameter documentation.
  */
 static __init int iommu_setup(char *p)
 {
@@ -156,7 +163,6 @@ static __init int iommu_setup(char *p)
 		}
 
 		if (!strncmp(p, "biomerge", 8)) {
-			iommu_bio_merge = 4096;
 			iommu_merge = 1;
 			force_iommu = 1;
 		}
@@ -175,7 +181,7 @@ static __init int iommu_setup(char *p)
 		if (!strncmp(p, "allowdac", 8))
 			forbid_dac = 0;
 		if (!strncmp(p, "nodac", 5))
-			forbid_dac = -1;
+			forbid_dac = 1;
 		if (!strncmp(p, "usedac", 6)) {
 			forbid_dac = -1;
 			return 1;
@@ -184,6 +190,8 @@ static __init int iommu_setup(char *p)
 		if (!strncmp(p, "soft", 4))
 			swiotlb = 1;
 #endif
+		if (!strncmp(p, "pt", 2))
+			iommu_pass_through = 1;
 
 		gart_parse_options(p);
 
@@ -202,7 +210,7 @@ early_param("iommu", iommu_setup);
 
 int dma_supported(struct device *dev, u64 mask)
 {
-	struct dma_mapping_ops *ops = get_dma_ops(dev);
+	struct dma_map_ops *ops = get_dma_ops(dev);
 
 #ifdef CONFIG_PCI
 	if (mask > 0xffffffff && forbid_dac > 0) {
@@ -217,7 +225,7 @@ int dma_supported(struct device *dev, u64 mask)
 	/* Copied from i386. Doesn't make much sense, because it will
 	   only work for pci_alloc_coherent.
 	   The caller just has to use GFP_DMA in this case. */
-	if (mask < DMA_24BIT_MASK)
+	if (mask < DMA_BIT_MASK(24))
 		return 0;
 
 	/* Tell the device to use SAC when IOMMU force is on.  This
@@ -232,7 +240,7 @@ int dma_supported(struct device *dev, u64 mask)
 	   SAC for these.  Assume all masks <= 40 bits are of this
 	   type. Normally this doesn't make any difference, but gives
 	   more gentle handling of IOMMU overflow. */
-	if (iommu_sac_force && (mask >= DMA_40BIT_MASK)) {
+	if (iommu_sac_force && (mask >= DMA_BIT_MASK(40))) {
 		dev_info(dev, "Force SAC with mask %Lx\n", mask);
 		return 0;
 	}
@@ -241,178 +249,36 @@ int dma_supported(struct device *dev, u64 mask)
 }
 EXPORT_SYMBOL(dma_supported);
 
-/* Allocate DMA memory on node near device */
-static noinline struct page *
-dma_alloc_pages(struct device *dev, gfp_t gfp, unsigned order)
-{
-	int node;
-
-	node = dev_to_node(dev);
-
-	return alloc_pages_node(node, gfp, order);
-}
-
-/*
- * Allocate memory for a coherent mapping.
- */
-void *
-dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
-		   gfp_t gfp)
+static int __init pci_iommu_init(void)
 {
-	struct dma_mapping_ops *ops = get_dma_ops(dev);
-	void *memory = NULL;
-	struct page *page;
-	unsigned long dma_mask = 0;
-	dma_addr_t bus;
-	int noretry = 0;
-
-	/* ignore region specifiers */
-	gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
-
-	if (dma_alloc_from_coherent(dev, size, dma_handle, &memory))
-		return memory;
-
-	if (!dev) {
-		dev = &fallback_dev;
-		gfp |= GFP_DMA;
-	}
-	dma_mask = dev->coherent_dma_mask;
-	if (dma_mask == 0)
-		dma_mask = (gfp & GFP_DMA) ? DMA_24BIT_MASK : DMA_32BIT_MASK;
-
-	/* Device not DMA able */
-	if (dev->dma_mask == NULL)
-		return NULL;
+	struct iommu_table_entry *p;
+	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
 
-	/* Don't invoke OOM killer or retry in lower 16MB DMA zone */
-	if (gfp & __GFP_DMA)
-		noretry = 1;
-
-#ifdef CONFIG_X86_64
-	/* Why <=? Even when the mask is smaller than 4GB it is often
-	   larger than 16MB and in this case we have a chance of
-	   finding fitting memory in the next higher zone first. If
-	   not retry with true GFP_DMA. -AK */
-	if (dma_mask <= DMA_32BIT_MASK && !(gfp & GFP_DMA)) {
-		gfp |= GFP_DMA32;
-		if (dma_mask < DMA_32BIT_MASK)
-			noretry = 1;
-	}
+#ifdef CONFIG_PCI
+	dma_debug_add_bus(&pci_bus_type);
 #endif
+	x86_init.iommu.iommu_init();
 
- again:
-	page = dma_alloc_pages(dev,
-		noretry ? gfp | __GFP_NORETRY : gfp, get_order(size));
-	if (page == NULL)
-		return NULL;
-
-	{
-		int high, mmu;
-		bus = page_to_phys(page);
-		memory = page_address(page);
-		high = (bus + size) >= dma_mask;
-		mmu = high;
-		if (force_iommu && !(gfp & GFP_DMA))
-			mmu = 1;
-		else if (high) {
-			free_pages((unsigned long)memory,
-				   get_order(size));
-
-			/* Don't use the 16MB ZONE_DMA unless absolutely
-			   needed. It's better to use remapping first. */
-			if (dma_mask < DMA_32BIT_MASK && !(gfp & GFP_DMA)) {
-				gfp = (gfp & ~GFP_DMA32) | GFP_DMA;
-				goto again;
-			}
-
-			/* Let low level make its own zone decisions */
-			gfp &= ~(GFP_DMA32|GFP_DMA);
-
-			if (ops->alloc_coherent)
-				return ops->alloc_coherent(dev, size,
-							   dma_handle, gfp);
-			return NULL;
-		}
-
-		memset(memory, 0, size);
-		if (!mmu) {
-			*dma_handle = bus;
-			return memory;
-		}
-	}
-
-	if (ops->alloc_coherent) {
-		free_pages((unsigned long)memory, get_order(size));
-		gfp &= ~(GFP_DMA|GFP_DMA32);
-		return ops->alloc_coherent(dev, size, dma_handle, gfp);
+	for (p = __iommu_table; p < __iommu_table_end; p++) {
+		if (p && (p->flags & IOMMU_DETECTED) && p->late_init)
+			p->late_init();
 	}
 
-	if (ops->map_simple) {
-		*dma_handle = ops->map_simple(dev, virt_to_phys(memory),
-					      size,
-					      PCI_DMA_BIDIRECTIONAL);
-		if (*dma_handle != bad_dma_address)
-			return memory;
-	}
-
-	if (panic_on_overflow)
-		panic("dma_alloc_coherent: IOMMU overflow by %lu bytes\n",
-		      (unsigned long)size);
-	free_pages((unsigned long)memory, get_order(size));
-	return NULL;
-}
-EXPORT_SYMBOL(dma_alloc_coherent);
-
-/*
- * Unmap coherent memory.
- * The caller must ensure that the device has finished accessing the mapping.
- */
-void dma_free_coherent(struct device *dev, size_t size,
-			 void *vaddr, dma_addr_t bus)
-{
-	struct dma_mapping_ops *ops = get_dma_ops(dev);
-
-	int order = get_order(size);
-	WARN_ON(irqs_disabled());	/* for portability */
-	if (dma_release_from_coherent(dev, order, vaddr))
-		return;
-	if (ops->unmap_single)
-		ops->unmap_single(dev, bus, size, 0);
-	free_pages((unsigned long)vaddr, order);
-}
-EXPORT_SYMBOL(dma_free_coherent);
-
-static int __init pci_iommu_init(void)
-{
-	calgary_iommu_init();
-
-	intel_iommu_init();
-
-	amd_iommu_init();
-
-	gart_iommu_init();
-
-	no_iommu_init();
 	return 0;
 }
-
-void pci_iommu_shutdown(void)
-{
-	gart_iommu_shutdown();
-}
 /* Must execute after PCI subsystem */
-fs_initcall(pci_iommu_init);
+rootfs_initcall(pci_iommu_init);
 
 #ifdef CONFIG_PCI
 /* Many VIA bridges seem to corrupt data for DAC. Disable it here */
 
-static __devinit void via_no_dac(struct pci_dev *dev)
+static void via_no_dac(struct pci_dev *dev)
 {
-	if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI && forbid_dac == 0) {
-		printk(KERN_INFO "PCI: VIA PCI bridge detected."
-				 "Disabling DAC.\n");
+	if (forbid_dac == 0) {
+		dev_info(&dev->dev, "disabling DAC on VIA PCI bridge\n");
 		forbid_dac = 1;
 	}
 }
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_ANY_ID, via_no_dac);
+DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_VIA, PCI_ANY_ID,
+				PCI_CLASS_BRIDGE_PCI, 8, via_no_dac);
 #endif