Merge git://git.infradead.org/iommu-2.6

* git://git.infradead.org/iommu-2.6:
  implement early_io{re,un}map for ia64
  Revert "Intel IOMMU: Avoid memory allocation failures in dma map api calls"
  intel-iommu: ignore page table validation in pass through mode
  intel-iommu: Fix oops with intel_iommu=igfx_off
  intel-iommu: Check for an RMRR which ends before it starts.
  intel-iommu: Apply BIOS sanity checks for interrupt remapping too.
  intel-iommu: Detect DMAR in hyperspace at probe time.
  dmar: Fix build failure without NUMA, warn on bogus RHSA tables and don't abort
  iommu: Allocate dma-remapping structures using numa locality info
  intr_remap: Allocate intr-remapping table using numa locality info
  dmar: Allocate queued invalidation structure using numa locality info
  dmar: support for parsing Remapping Hardware Static Affinity structure

6 files changed, 154 insertions, 51 deletions

diff --git a/arch/ia64/include/asm/io.h b/arch/ia64/include/asm/io.h
index 0d9d16e2d949..cc8335eb3110 100644
--- a/arch/ia64/include/asm/io.h
+++ b/arch/ia64/include/asm/io.h
@@ -424,6 +424,8 @@ __writeq (unsigned long val, volatile void __iomem *addr)
 extern void __iomem * ioremap(unsigned long offset, unsigned long size);
 extern void __iomem * ioremap_nocache (unsigned long offset, unsigned long size);
 extern void iounmap (volatile void __iomem *addr);
+extern void __iomem * early_ioremap (unsigned long phys_addr, unsigned long size);
+extern void early_iounmap (volatile void __iomem *addr, unsigned long size);
 
 /*
  * String version of IO memory access ops:
diff --git a/arch/ia64/mm/ioremap.c b/arch/ia64/mm/ioremap.c
index 2a140627dfd6..3dccdd8eb275 100644
--- a/arch/ia64/mm/ioremap.c
+++ b/arch/ia64/mm/ioremap.c
@@ -22,6 +22,12 @@ __ioremap (unsigned long phys_addr)
 }
 
 void __iomem *
+early_ioremap (unsigned long phys_addr, unsigned long size)
+{
+	return __ioremap(phys_addr);
+}
+
+void __iomem *
 ioremap (unsigned long phys_addr, unsigned long size)
 {
 	void __iomem *addr;
@@ -102,6 +108,11 @@ ioremap_nocache (unsigned long phys_addr, unsigned long size)
 EXPORT_SYMBOL(ioremap_nocache);
 
 void
+early_iounmap (volatile void __iomem *addr, unsigned long size)
+{
+}
+
+void
 iounmap (volatile void __iomem *addr)
 {
 	if (REGION_NUMBER(addr) == RGN_GATE)
diff --git a/drivers/pci/dmar.c b/drivers/pci/dmar.c
index 6cdc931f7c17..83aae4747594 100644
--- a/drivers/pci/dmar.c
+++ b/drivers/pci/dmar.c
@@ -339,6 +339,35 @@ found:
 }
 #endif
 
+#ifdef CONFIG_ACPI_NUMA
+static int __init
+dmar_parse_one_rhsa(struct acpi_dmar_header *header)
+{
+	struct acpi_dmar_rhsa *rhsa;
+	struct dmar_drhd_unit *drhd;
+
+	rhsa = (struct acpi_dmar_rhsa *)header;
+	for_each_drhd_unit(drhd) {
+		if (drhd->reg_base_addr == rhsa->base_address) {
+			int node = acpi_map_pxm_to_node(rhsa->proximity_domain);
+
+			if (!node_online(node))
+				node = -1;
+			drhd->iommu->node = node;
+			return 0;
+		}
+	}
+	WARN(1, "Your BIOS is broken; RHSA refers to non-existent DMAR unit at %llx\n"
+	     "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
+	     drhd->reg_base_addr,
+	     dmi_get_system_info(DMI_BIOS_VENDOR),
+	     dmi_get_system_info(DMI_BIOS_VERSION),
+	     dmi_get_system_info(DMI_PRODUCT_VERSION));
+
+	return 0;
+}
+#endif
+
 static void __init
 dmar_table_print_dmar_entry(struct acpi_dmar_header *header)
 {
@@ -458,7 +487,9 @@ parse_dmar_table(void)
 #endif
 			break;
 		case ACPI_DMAR_HARDWARE_AFFINITY:
-			/* We don't do anything with RHSA (yet?) */
+#ifdef CONFIG_ACPI_NUMA
+			ret = dmar_parse_one_rhsa(entry_header);
+#endif
 			break;
 		default:
 			printk(KERN_WARNING PREFIX
@@ -582,6 +613,8 @@ int __init dmar_table_init(void)
 	return 0;
 }
 
+static int bios_warned;
+
 int __init check_zero_address(void)
 {
 	struct acpi_table_dmar *dmar;
@@ -601,6 +634,9 @@ int __init check_zero_address(void)
 		}
 
 		if (entry_header->type == ACPI_DMAR_TYPE_HARDWARE_UNIT) {
+			void __iomem *addr;
+			u64 cap, ecap;
+
 			drhd = (void *)entry_header;
 			if (!drhd->address) {
 				/* Promote an attitude of violence to a BIOS engineer today */
@@ -609,17 +645,40 @@ int __init check_zero_address(void)
 				     dmi_get_system_info(DMI_BIOS_VENDOR),
 				     dmi_get_system_info(DMI_BIOS_VERSION),
 				     dmi_get_system_info(DMI_PRODUCT_VERSION));
-#ifdef CONFIG_DMAR
-				dmar_disabled = 1;
-#endif
-				return 0;
+				bios_warned = 1;
+				goto failed;
+			}
+
+			addr = early_ioremap(drhd->address, VTD_PAGE_SIZE);
+			if (!addr ) {
+				printk("IOMMU: can't validate: %llx\n", drhd->address);
+				goto failed;
+			}
+			cap = dmar_readq(addr + DMAR_CAP_REG);
+			ecap = dmar_readq(addr + DMAR_ECAP_REG);
+			early_iounmap(addr, VTD_PAGE_SIZE);
+			if (cap == (uint64_t)-1 && ecap == (uint64_t)-1) {
+				/* Promote an attitude of violence to a BIOS engineer today */
+				WARN(1, "Your BIOS is broken; DMAR reported at address %llx returns all ones!\n"
+				     "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
+				      drhd->address,
+				      dmi_get_system_info(DMI_BIOS_VENDOR),
+				      dmi_get_system_info(DMI_BIOS_VERSION),
+				      dmi_get_system_info(DMI_PRODUCT_VERSION));
+				bios_warned = 1;
+				goto failed;
 			}
-			break;
 		}
 
 		entry_header = ((void *)entry_header + entry_header->length);
 	}
 	return 1;
+
+failed:
+#ifdef CONFIG_DMAR
+	dmar_disabled = 1;
+#endif
+	return 0;
 }
 
 void __init detect_intel_iommu(void)
@@ -670,6 +729,18 @@ int alloc_iommu(struct dmar_drhd_unit *drhd)
 	int agaw = 0;
 	int msagaw = 0;
 
+	if (!drhd->reg_base_addr) {
+		if (!bios_warned) {
+			WARN(1, "Your BIOS is broken; DMAR reported at address zero!\n"
+			     "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
+			     dmi_get_system_info(DMI_BIOS_VENDOR),
+			     dmi_get_system_info(DMI_BIOS_VERSION),
+			     dmi_get_system_info(DMI_PRODUCT_VERSION));
+			bios_warned = 1;
+		}
+		return -EINVAL;
+	}
+
 	iommu = kzalloc(sizeof(*iommu), GFP_KERNEL);
 	if (!iommu)
 		return -ENOMEM;
@@ -686,13 +757,16 @@ int alloc_iommu(struct dmar_drhd_unit *drhd)
 	iommu->ecap = dmar_readq(iommu->reg + DMAR_ECAP_REG);
 
 	if (iommu->cap == (uint64_t)-1 && iommu->ecap == (uint64_t)-1) {
-		/* Promote an attitude of violence to a BIOS engineer today */
-		WARN(1, "Your BIOS is broken; DMAR reported at address %llx returns all ones!\n"
-		     "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
-		     drhd->reg_base_addr,
-		     dmi_get_system_info(DMI_BIOS_VENDOR),
-		     dmi_get_system_info(DMI_BIOS_VERSION),
-		     dmi_get_system_info(DMI_PRODUCT_VERSION));
+		if (!bios_warned) {
+			/* Promote an attitude of violence to a BIOS engineer today */
+			WARN(1, "Your BIOS is broken; DMAR reported at address %llx returns all ones!\n"
+			     "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
+			     drhd->reg_base_addr,
+			     dmi_get_system_info(DMI_BIOS_VENDOR),
+			     dmi_get_system_info(DMI_BIOS_VERSION),
+			     dmi_get_system_info(DMI_PRODUCT_VERSION));
+			bios_warned = 1;
+		}
 		goto err_unmap;
 	}
 
@@ -715,6 +789,8 @@ int alloc_iommu(struct dmar_drhd_unit *drhd)
 	iommu->agaw = agaw;
 	iommu->msagaw = msagaw;
 
+	iommu->node = -1;
+
 	/* the registers might be more than one page */
 	map_size = max_t(int, ecap_max_iotlb_offset(iommu->ecap),
 		cap_max_fault_reg_offset(iommu->cap));
@@ -1056,6 +1132,7 @@ static void __dmar_enable_qi(struct intel_iommu *iommu)
 int dmar_enable_qi(struct intel_iommu *iommu)
 {
 	struct q_inval *qi;
+	struct page *desc_page;
 
 	if (!ecap_qis(iommu->ecap))
 		return -ENOENT;
@@ -1072,13 +1149,16 @@ int dmar_enable_qi(struct intel_iommu *iommu)
 
 	qi = iommu->qi;
 
-	qi->desc = (void *)(get_zeroed_page(GFP_ATOMIC));
-	if (!qi->desc) {
+
+	desc_page = alloc_pages_node(iommu->node, GFP_ATOMIC | __GFP_ZERO, 0);
+	if (!desc_page) {
 		kfree(qi);
 		iommu->qi = 0;
 		return -ENOMEM;
 	}
 
+	qi->desc = page_address(desc_page);
+
 	qi->desc_status = kmalloc(QI_LENGTH * sizeof(int), GFP_ATOMIC);
 	if (!qi->desc_status) {
 		free_page((unsigned long) qi->desc);
diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
index 8d6159426311..e56f9bed6f2b 100644
--- a/drivers/pci/intel-iommu.c
+++ b/drivers/pci/intel-iommu.c
@@ -277,6 +277,7 @@ static int hw_pass_through = 1;
 
 struct dmar_domain {
 	int	id;			/* domain id */
+	int	nid;			/* node id */
 	unsigned long iommu_bmp;	/* bitmap of iommus this domain uses*/
 
 	struct list_head devices; 	/* all devices' list */
@@ -386,30 +387,14 @@ static struct kmem_cache *iommu_domain_cache;
 static struct kmem_cache *iommu_devinfo_cache;
 static struct kmem_cache *iommu_iova_cache;
 
-static inline void *iommu_kmem_cache_alloc(struct kmem_cache *cachep)
+static inline void *alloc_pgtable_page(int node)
 {
-	unsigned int flags;
-	void *vaddr;
-
-	/* trying to avoid low memory issues */
-	flags = current->flags & PF_MEMALLOC;
-	current->flags |= PF_MEMALLOC;
-	vaddr = kmem_cache_alloc(cachep, GFP_ATOMIC);
-	current->flags &= (~PF_MEMALLOC | flags);
-	return vaddr;
-}
-
+	struct page *page;
+	void *vaddr = NULL;
 
-static inline void *alloc_pgtable_page(void)
-{
-	unsigned int flags;
-	void *vaddr;
-
-	/* trying to avoid low memory issues */
-	flags = current->flags & PF_MEMALLOC;
-	current->flags |= PF_MEMALLOC;
-	vaddr = (void *)get_zeroed_page(GFP_ATOMIC);
-	current->flags &= (~PF_MEMALLOC | flags);
+	page = alloc_pages_node(node, GFP_ATOMIC | __GFP_ZERO, 0);
+	if (page)
+		vaddr = page_address(page);
 	return vaddr;
 }
 
@@ -420,7 +405,7 @@ static inline void free_pgtable_page(void *vaddr)
 
 static inline void *alloc_domain_mem(void)
 {
-	return iommu_kmem_cache_alloc(iommu_domain_cache);
+	return kmem_cache_alloc(iommu_domain_cache, GFP_ATOMIC);
 }
 
 static void free_domain_mem(void *vaddr)
@@ -430,7 +415,7 @@ static void free_domain_mem(void *vaddr)
 
 static inline void * alloc_devinfo_mem(void)
 {
-	return iommu_kmem_cache_alloc(iommu_devinfo_cache);
+	return kmem_cache_alloc(iommu_devinfo_cache, GFP_ATOMIC);
 }
 
 static inline void free_devinfo_mem(void *vaddr)
@@ -440,7 +425,7 @@ static inline void free_devinfo_mem(void *vaddr)
 
 struct iova *alloc_iova_mem(void)
 {
-	return iommu_kmem_cache_alloc(iommu_iova_cache);
+	return kmem_cache_alloc(iommu_iova_cache, GFP_ATOMIC);
 }
 
 void free_iova_mem(struct iova *iova)
@@ -589,7 +574,8 @@ static struct context_entry * device_to_context_entry(struct intel_iommu *iommu,
 	root = &iommu->root_entry[bus];
 	context = get_context_addr_from_root(root);
 	if (!context) {
-		context = (struct context_entry *)alloc_pgtable_page();
+		context = (struct context_entry *)
+				alloc_pgtable_page(iommu->node);
 		if (!context) {
 			spin_unlock_irqrestore(&iommu->lock, flags);
 			return NULL;
@@ -732,7 +718,7 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
 		if (!dma_pte_present(pte)) {
 			uint64_t pteval;
 
-			tmp_page = alloc_pgtable_page();
+			tmp_page = alloc_pgtable_page(domain->nid);
 
 			if (!tmp_page)
 				return NULL;
@@ -868,7 +854,7 @@ static int iommu_alloc_root_entry(struct intel_iommu *iommu)
 	struct root_entry *root;
 	unsigned long flags;
 
-	root = (struct root_entry *)alloc_pgtable_page();
+	root = (struct root_entry *)alloc_pgtable_page(iommu->node);
 	if (!root)
 		return -ENOMEM;
 
@@ -1263,6 +1249,7 @@ static struct dmar_domain *alloc_domain(void)
 	if (!domain)
 		return NULL;
 
+	domain->nid = -1;
 	memset(&domain->iommu_bmp, 0, sizeof(unsigned long));
 	domain->flags = 0;
 
@@ -1420,9 +1407,10 @@ static int domain_init(struct dmar_domain *domain, int guest_width)
 		domain->iommu_snooping = 0;
 
 	domain->iommu_count = 1;
+	domain->nid = iommu->node;
 
 	/* always allocate the top pgd */
-	domain->pgd = (struct dma_pte *)alloc_pgtable_page();
+	domain->pgd = (struct dma_pte *)alloc_pgtable_page(domain->nid);
 	if (!domain->pgd)
 		return -ENOMEM;
 	__iommu_flush_cache(iommu, domain->pgd, PAGE_SIZE);
@@ -1523,12 +1511,15 @@ static int domain_context_mapping_one(struct dmar_domain *domain, int segment,
 
 		/* Skip top levels of page tables for
 		 * iommu which has less agaw than default.
+		 * Unnecessary for PT mode.
 		 */
-		for (agaw = domain->agaw; agaw != iommu->agaw; agaw--) {
-			pgd = phys_to_virt(dma_pte_addr(pgd));
-			if (!dma_pte_present(pgd)) {
-				spin_unlock_irqrestore(&iommu->lock, flags);
-				return -ENOMEM;
+		if (translation != CONTEXT_TT_PASS_THROUGH) {
+			for (agaw = domain->agaw; agaw != iommu->agaw; agaw--) {
+				pgd = phys_to_virt(dma_pte_addr(pgd));
+				if (!dma_pte_present(pgd)) {
+					spin_unlock_irqrestore(&iommu->lock, flags);
+					return -ENOMEM;
+				}
 			}
 		}
 	}
@@ -1577,6 +1568,8 @@ static int domain_context_mapping_one(struct dmar_domain *domain, int segment,
 	spin_lock_irqsave(&domain->iommu_lock, flags);
 	if (!test_and_set_bit(iommu->seq_id, &domain->iommu_bmp)) {
 		domain->iommu_count++;
+		if (domain->iommu_count == 1)
+			domain->nid = iommu->node;
 		domain_update_iommu_cap(domain);
 	}
 	spin_unlock_irqrestore(&domain->iommu_lock, flags);
@@ -1991,6 +1984,16 @@ static int iommu_prepare_identity_map(struct pci_dev *pdev,
 	       "IOMMU: Setting identity map for device %s [0x%Lx - 0x%Lx]\n",
 	       pci_name(pdev), start, end);
 	
+	if (end < start) {
+		WARN(1, "Your BIOS is broken; RMRR ends before it starts!\n"
+			"BIOS vendor: %s; Ver: %s; Product Version: %s\n",
+			dmi_get_system_info(DMI_BIOS_VENDOR),
+			dmi_get_system_info(DMI_BIOS_VERSION),
+		     dmi_get_system_info(DMI_PRODUCT_VERSION));
+		ret = -EIO;
+		goto error;
+	}
+
 	if (end >> agaw_to_width(domain->agaw)) {
 		WARN(1, "Your BIOS is broken; RMRR exceeds permitted address width (%d bits)\n"
 		     "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
@@ -3228,6 +3231,9 @@ static int device_notifier(struct notifier_block *nb,
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct dmar_domain *domain;
 
+	if (iommu_no_mapping(dev))
+		return 0;
+
 	domain = find_domain(pdev);
 	if (!domain)
 		return 0;
@@ -3455,6 +3461,7 @@ static struct dmar_domain *iommu_alloc_vm_domain(void)
 		return NULL;
 
 	domain->id = vm_domid++;
+	domain->nid = -1;
 	memset(&domain->iommu_bmp, 0, sizeof(unsigned long));
 	domain->flags = DOMAIN_FLAG_VIRTUAL_MACHINE;
 
@@ -3481,9 +3488,10 @@ static int md_domain_init(struct dmar_domain *domain, int guest_width)
 	domain->iommu_coherency = 0;
 	domain->iommu_snooping = 0;
 	domain->max_addr = 0;
+	domain->nid = -1;
 
 	/* always allocate the top pgd */
-	domain->pgd = (struct dma_pte *)alloc_pgtable_page();
+	domain->pgd = (struct dma_pte *)alloc_pgtable_page(domain->nid);
 	if (!domain->pgd)
 		return -ENOMEM;
 	domain_flush_cache(domain, domain->pgd, PAGE_SIZE);
diff --git a/drivers/pci/intr_remapping.c b/drivers/pci/intr_remapping.c
index 1487bf2be863..8b65a489581b 100644
--- a/drivers/pci/intr_remapping.c
+++ b/drivers/pci/intr_remapping.c
@@ -590,7 +590,8 @@ static int setup_intr_remapping(struct intel_iommu *iommu, int mode)
 	if (!iommu->ir_table)
 		return -ENOMEM;
 
-	pages = alloc_pages(GFP_ATOMIC | __GFP_ZERO, INTR_REMAP_PAGE_ORDER);
+	pages = alloc_pages_node(iommu->node, GFP_ATOMIC | __GFP_ZERO,
+				 INTR_REMAP_PAGE_ORDER);
 
 	if (!pages) {
 		printk(KERN_ERR "failed to allocate pages of order %d\n",
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 4f0a72a9740c..9310c699a37d 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -332,6 +332,7 @@ struct intel_iommu {
 #ifdef CONFIG_INTR_REMAP
 	struct ir_table *ir_table;	/* Interrupt remapping info */
 #endif
+	int		node;
 };
 
 static inline void __iommu_flush_cache(