1 files changed, 75 insertions, 107 deletions

diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 1a041bcf506..a25e202bb31 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -1,19 +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_map_ops *dma_ops;
+struct dma_map_ops *dma_ops = &nommu_dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
 static int iommu_sac_force __read_mostly;
@@ -32,23 +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;
 
-int iommu_pass_through;
+/*
+ * 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;
 
-dma_addr_t bad_dma_address __read_mostly = 0;
-EXPORT_SYMBOL(bad_dma_address);
+extern struct iommu_table_entry __iommu_table[], __iommu_table_end[];
 
-/* 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. */
+/* Dummy device used for NULL arguments (normally ISA). */
 struct device x86_dma_fallback_dev = {
 	.init_name = "fallback device",
-	.coherent_dma_mask = DMA_BIT_MASK(32),
+	.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       32768
+#define PREALLOC_DMA_DEBUG_ENTRIES       65536
 
 int dma_set_mask(struct device *dev, u64 mask)
 {
@@ -61,93 +69,53 @@ 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 = roundup(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)
-{
-
-	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;
-}
-#endif
-
 void __init pci_iommu_alloc(void)
 {
-#ifdef CONFIG_X86_64
-	/* free the range so iommu could get some range less than 4G */
-	dma32_free_bootmem();
-#endif
-
-	/*
-	 * The order of these functions is important for
-	 * fall-back/fail-over reasons
-	 */
-	gart_iommu_hole_init();
-
-	detect_calgary();
-
-	detect_intel_iommu();
-
-	amd_iommu_detect();
-
-	pci_swiotlb_init();
+	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 *dma_generic_alloc_coherent(struct device *dev, size_t size,
-				 dma_addr_t *dma_addr, gfp_t flag)
+				 dma_addr_t *dma_addr, gfp_t flag,
+				 struct dma_attrs *attrs)
 {
 	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;
+	flag &= ~__GFP_ZERO;
 again:
-	page = alloc_pages_node(dev_to_node(dev), flag, get_order(size));
+	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;
 
 	addr = page_to_phys(page);
-	if (!is_buffer_dma_capable(dma_mask, addr, size)) {
+	if (addr + size > dma_mask) {
 		__free_pages(page, get_order(size));
 
 		if (dma_mask < DMA_BIT_MASK(32) && !(flag & GFP_DMA)) {
@@ -157,14 +125,24 @@ again:
 
 		return NULL;
 	}
-
+	memset(page_address(page), 0, size);
 	*dma_addr = addr;
 	return page_address(page);
 }
 
+void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr,
+			       dma_addr_t dma_addr, struct dma_attrs *attrs)
+{
+	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	struct page *page = virt_to_page(vaddr);
+
+	if (!dma_release_from_contiguous(dev, page, count))
+		free_pages((unsigned long)vaddr, get_order(size));
+}
+
 /*
- * 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)
 {
@@ -203,7 +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;
@@ -212,10 +190,8 @@ static __init int iommu_setup(char *p)
 		if (!strncmp(p, "soft", 4))
 			swiotlb = 1;
 #endif
-		if (!strncmp(p, "pt", 2)) {
+		if (!strncmp(p, "pt", 2))
 			iommu_pass_through = 1;
-			return 1;
-		}
 
 		gart_parse_options(p);
 
@@ -275,42 +251,34 @@ EXPORT_SYMBOL(dma_supported);
 
 static int __init pci_iommu_init(void)
 {
+	struct iommu_table_entry *p;
 	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
 
 #ifdef CONFIG_PCI
 	dma_debug_add_bus(&pci_bus_type);
 #endif
+	x86_init.iommu.iommu_init();
 
-	calgary_iommu_init();
-
-	intel_iommu_init();
-
-	amd_iommu_init();
-
-	gart_iommu_init();
+	for (p = __iommu_table; p < __iommu_table_end; p++) {
+		if (p && (p->flags & IOMMU_DETECTED) && p->late_init)
+			p->late_init();
+	}
 
-	no_iommu_init();
 	return 0;
 }
-
-void pci_iommu_shutdown(void)
-{
-	gart_iommu_shutdown();
-
-	amd_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) {
+	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